Compare commits

...

167 Commits

Author SHA1 Message Date
diegosouzapw 49e1d51be9 chore(release): v3.3.8
Build Electron Desktop App / Validate version (push) Failing after 28s
Build Electron Desktop App / Build Electron (macos-arm64) (push) Has been skipped
Build Electron Desktop App / Build Electron (linux) (push) Has been skipped
Build Electron Desktop App / Build Electron (macos-intel) (push) Has been skipped
Build Electron Desktop App / Build Electron (windows) (push) Has been skipped
Build Electron Desktop App / Create Release (push) Has been skipped
Build Electron Desktop App / Publish to npm (push) Has been skipped
2026-03-30 20:54:02 -03:00
diegosouzapw 23e47a74ee Merge remote main 2026-03-30 20:48:25 -03:00
Diego Rodrigues de Sa e Souza fce7f6ce47 Merge pull request #830 from rdself/coder/fix-openrouter-available-models
fix: align OpenRouter auto-sync with available models
2026-03-30 20:47:59 -03:00
Diego Rodrigues de Sa e Souza f3b47a16dd Merge pull request #831 from christopher-s/gemini-cli-adjustments
fix: use gemini-cli/ as model prefix instead of gc/
2026-03-30 20:47:56 -03:00
Diego Rodrigues de Sa e Souza aa7b754693 Merge pull request #834 from oyi77/feat/cache-page-prompt-cache-tracking
fix(debug/sidebar): debug toggle and sidebar visibility
2026-03-30 20:47:54 -03:00
Diego Rodrigues de Sa e Souza 397b13e2d8 Merge pull request #835 from tombii/fix/cache-page-ui-polish
fix(ui): improve cache page header sizing and context
2026-03-30 20:47:40 -03:00
diegosouzapw b2c203e8c1 Merge branch 'fix/streaming-reasoning-field-alias' into main
# Conflicts:
#	open-sse/services/combo.ts
#	open-sse/utils/stream.ts
#	tests/unit/chat-combo-live-test.test.mjs
2026-03-30 20:45:44 -03:00
diegosouzapw 6afb314d26 Merge branch 'feat/cache-page-prompt-cache-tracking' into main
# Conflicts:
#	src/app/(dashboard)/dashboard/settings/page.tsx
#	src/app/api/settings/cache-config/route.ts
#	src/i18n/messages/ar.json
#	src/i18n/messages/bg.json
#	src/i18n/messages/cs.json
#	src/i18n/messages/da.json
#	src/i18n/messages/de.json
#	src/i18n/messages/es.json
#	src/i18n/messages/fi.json
#	src/i18n/messages/fr.json
#	src/i18n/messages/he.json
#	src/i18n/messages/hi.json
#	src/i18n/messages/hu.json
#	src/i18n/messages/id.json
#	src/i18n/messages/in.json
#	src/i18n/messages/it.json
#	src/i18n/messages/ja.json
#	src/i18n/messages/ko.json
#	src/i18n/messages/ms.json
#	src/i18n/messages/nl.json
#	src/i18n/messages/no.json
#	src/i18n/messages/phi.json
#	src/i18n/messages/pl.json
#	src/i18n/messages/pt-BR.json
#	src/i18n/messages/pt.json
#	src/i18n/messages/ro.json
#	src/i18n/messages/ru.json
#	src/i18n/messages/sk.json
#	src/i18n/messages/sv.json
#	src/i18n/messages/th.json
#	src/i18n/messages/tr.json
#	src/i18n/messages/uk-UA.json
#	src/i18n/messages/vi.json
2026-03-30 20:43:25 -03:00
diegosouzapw 28123355b4 Merge branch 'feat/issue-660-qoder' into main
# Conflicts:
#	docs/i18n/ar/README.md
#	docs/i18n/bg/README.md
#	docs/i18n/da/README.md
#	docs/i18n/de/README.md
#	docs/i18n/es/README.md
#	docs/i18n/fi/README.md
#	docs/i18n/fr/README.md
#	docs/i18n/he/README.md
#	docs/i18n/hu/README.md
#	docs/i18n/id/README.md
#	docs/i18n/in/README.md
#	docs/i18n/it/README.md
#	docs/i18n/ja/README.md
#	docs/i18n/ko/README.md
#	docs/i18n/ms/README.md
#	docs/i18n/nl/README.md
#	docs/i18n/no/README.md
#	docs/i18n/phi/README.md
#	docs/i18n/pl/README.md
#	docs/i18n/pt-BR/README.md
#	docs/i18n/pt/README.md
#	docs/i18n/ro/README.md
#	docs/i18n/ru/README.md
#	docs/i18n/sk/README.md
#	docs/i18n/sv/README.md
#	docs/i18n/th/README.md
#	docs/i18n/uk-UA/README.md
#	docs/i18n/vi/README.md
#	docs/i18n/zh-CN/README.md
2026-03-30 20:39:31 -03:00
diegosouzapw bcb87f5d55 feat: Return only accessible models from /models for restricted API keys (#781) 2026-03-30 20:31:32 -03:00
tombii 67b9a3bc0e fix(ui): internationalize CacheStatsCard and add auto-refresh
- Add 10s auto-refresh interval matching cache page pattern
- Replace all hardcoded English strings with translation keys
- Add 13 new i18n keys to cache namespace for metrics display
- Reorganize header layout with auto-refresh indicator and reset button

Addresses Gemini Code Assist feedback on PR #835:
- Fixed internationalization (all text now uses t())
- Maintains distinct metrics (cumulative/resettable vs real-time rolling)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-31 00:32:37 +02:00
diegosouzapw ab4914ee6a chore(release): v3.3.7 — OpenCode config fix, i18n keys fix
Build Electron Desktop App / Validate version (push) Failing after 31s
Build Electron Desktop App / Build Electron (macos-arm64) (push) Has been skipped
Build Electron Desktop App / Build Electron (linux) (push) Has been skipped
Build Electron Desktop App / Build Electron (macos-intel) (push) Has been skipped
Build Electron Desktop App / Build Electron (windows) (push) Has been skipped
Build Electron Desktop App / Create Release (push) Has been skipped
Build Electron Desktop App / Publish to npm (push) Has been skipped
2026-03-30 19:30:18 -03:00
diegosouzapw e7c73c76dd chore(release): bump version to v3.3.7 2026-03-30 19:28:20 -03:00
diegosouzapw 3591a3fe5c fix: resolve opencode json structure to use record mapping instead of array (#816) 2026-03-30 19:23:25 -03:00
diegosouzapw fbdce049b2 fix: add missing cloudflaredUrlNotice i18n keys (#823) 2026-03-30 19:23:14 -03:00
diegosouzapw 9a8520a2de fix: add missing cloudflaredUrlNotice i18n keys to prevent MISSING_MESSAGE console errors (#823) 2026-03-30 19:16:50 -03:00
oyi77 a315ab29bc fix(debug/sidebar): make debug toggle control debug section visibility and fix sidebar hidden items tracking
- Sync debugMode with showDebug in Sidebar (was using enableRequestLogs env var)
- Only render debug-section sidebar toggles in AppearanceTab when debugMode=true
- Sidebar filters debug-section items based on debugMode (was already correct)
- Debug toggle now triggers omniroute:settings-updated event for instant sidebar update
EOF
2026-03-31 04:50:50 +07:00
oyi77 5437d691b5 fix(cache): address code review issues
- Add authentication to /api/cache/entries (GET and DELETE)
- Add authentication to /api/cache (GET and DELETE)
- Validate trendHours: clamp to 1-720 range
- Fix estimatedCostSaved bug: use calculated value instead of hardcoded 0
2026-03-31 04:50:50 +07:00
oyi77 f99c90dc85 feat(cache): add OpenAI prompt_cache_key and Gemini cachedContent support
Provider-specific caching enhancements:

OpenAI:
- Auto-generate prompt_cache_key from message prefix hash
- Key format: omni-{prefix_hash_32chars}
- Preserves client-provided keys (doesn't override)

Gemini:
- Preserve cachedContent ID if provided by client
- Enables explicit Gemini caching for long prompts
- cachedContentTokenCount already tracked in responses
2026-03-31 04:50:50 +07:00
tombii d838388443 fix(ui): improve cache page header sizing and context
- Match CacheStatsCard header size with other card headers (text-sm)
- Show request counts in cache hit rate label (116/359) for clarity
- Add CacheStatsCard component to cache page for cumulative metrics

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-30 23:33:48 +02:00
diegosouzapw 0b2c488a61 chore(release): bump version to v3.3.6
Build Electron Desktop App / Validate version (push) Failing after 30s
Build Electron Desktop App / Build Electron (macos-arm64) (push) Has been skipped
Build Electron Desktop App / Build Electron (linux) (push) Has been skipped
Build Electron Desktop App / Build Electron (macos-intel) (push) Has been skipped
Build Electron Desktop App / Build Electron (windows) (push) Has been skipped
Build Electron Desktop App / Create Release (push) Has been skipped
Build Electron Desktop App / Publish to npm (push) Has been skipped
2026-03-30 18:24:15 -03:00
Chris Staley e2eb4ef29d fix: address PR #831 review feedback
- Update DEFAULT_PRICING key from 'gc' to 'gemini-cli' so pricing
  lookups work with the new alias
- Restore gc -> gemini-cli in FALLBACK_ALIAS_TO_PROVIDER for backward
  compatibility (existing saved configs with gc/ prefix still resolve)
2026-03-30 15:23:34 -06:00
diegosouzapw 76e135077b Resolve merge conflicts with main natively built Prompt Cache UI 2026-03-30 18:20:19 -03:00
Diego Rodrigues de Sa e Souza 6078cd2eab Merge pull request #829 from rdself/coder/fix-cloudflared-startup
Fix cloudflared quick tunnel startup in Docker
2026-03-30 18:18:03 -03:00
Diego Rodrigues de Sa e Souza 3482dade71 Merge pull request #828 from rdself/coder/fix-combo-test-false-negative
Fix combo test false negatives and parallelize model probes
2026-03-30 18:18:00 -03:00
R.D. ff73de5716 fix openrouter available models sync 2026-03-30 17:07:46 -04:00
diegosouzapw 04d0c350db build: sync monorepo package versions across electron and open-sse 2026-03-30 18:02:33 -03:00
R.D. b6a5c91045 Install CA certificates in runtime image 2026-03-30 17:01:50 -04:00
diegosouzapw 7a37c79ebc ci: fix pipeline errors and enforce route lint validatation 2026-03-30 17:54:44 -03:00
R.D. ba227c5ec3 Run combo health probes concurrently 2026-03-30 16:49:01 -04:00
Chris Staley 7ab75dd15a fix: use gemini-cli/ as model prefix instead of gc/
Gemini CLI clients use bare model names, not provider-prefixed IDs.
The gc/ alias was opaque — gemini-cli/ is self-documenting. Since
alias now equals provider ID, the dual-prefix duplication logic
naturally skips Gemini CLI (no duplicate gemini-cli/ entries).
2026-03-30 14:42:00 -06:00
diegosouzapw df23162e9d chore(release): v3.3.5 - all changes in ONE commit
Build Electron Desktop App / Validate version (push) Failing after 31s
Build Electron Desktop App / Build Electron (macos-arm64) (push) Has been skipped
Build Electron Desktop App / Build Electron (linux) (push) Has been skipped
Build Electron Desktop App / Build Electron (macos-intel) (push) Has been skipped
Build Electron Desktop App / Build Electron (windows) (push) Has been skipped
Build Electron Desktop App / Create Release (push) Has been skipped
Build Electron Desktop App / Publish to npm (push) Has been skipped
2026-03-30 17:35:51 -03:00
dependabot[bot] 2c12f18b44 deps: bump the production group with 8 updates
Bumps the production group with 8 updates:

| Package | From | To |
| --- | --- | --- |
| [@lobehub/icons](https://github.com/lobehub/lobe-icons) | `5.0.1` | `5.2.0` |
| [@modelcontextprotocol/sdk](https://github.com/modelcontextprotocol/typescript-sdk) | `1.27.1` | `1.29.0` |
| [@swc/helpers](https://github.com/swc-project/swc/tree/HEAD/packages/helpers) | `0.5.19` | `0.5.20` |
| [jose](https://github.com/panva/jose) | `6.2.1` | `6.2.2` |
| [next](https://github.com/vercel/next.js) | `16.1.7` | `16.2.1` |
| [recharts](https://github.com/recharts/recharts) | `3.8.0` | `3.8.1` |
| [undici](https://github.com/nodejs/undici) | `7.24.4` | `7.24.6` |
| [wreq-js](https://github.com/sqdshguy/wreq-js) | `2.2.0` | `2.2.2` |


Updates `@lobehub/icons` from 5.0.1 to 5.2.0
- [Release notes](https://github.com/lobehub/lobe-icons/releases)
- [Changelog](https://github.com/lobehub/lobe-icons/blob/master/CHANGELOG.md)
- [Commits](https://github.com/lobehub/lobe-icons/compare/v5.0.1...v5.2.0)

Updates `@modelcontextprotocol/sdk` from 1.27.1 to 1.29.0
- [Release notes](https://github.com/modelcontextprotocol/typescript-sdk/releases)
- [Commits](https://github.com/modelcontextprotocol/typescript-sdk/compare/v1.27.1...v1.29.0)

Updates `@swc/helpers` from 0.5.19 to 0.5.20
- [Release notes](https://github.com/swc-project/swc/releases)
- [Changelog](https://github.com/swc-project/swc/blob/main/CHANGELOG-CORE.md)
- [Commits](https://github.com/swc-project/swc/commits/HEAD/packages/helpers)

Updates `jose` from 6.2.1 to 6.2.2
- [Release notes](https://github.com/panva/jose/releases)
- [Changelog](https://github.com/panva/jose/blob/main/CHANGELOG.md)
- [Commits](https://github.com/panva/jose/compare/v6.2.1...v6.2.2)

Updates `next` from 16.1.7 to 16.2.1
- [Release notes](https://github.com/vercel/next.js/releases)
- [Changelog](https://github.com/vercel/next.js/blob/canary/release.js)
- [Commits](https://github.com/vercel/next.js/compare/v16.1.7...v16.2.1)

Updates `recharts` from 3.8.0 to 3.8.1
- [Release notes](https://github.com/recharts/recharts/releases)
- [Changelog](https://github.com/recharts/recharts/blob/main/CHANGELOG.md)
- [Commits](https://github.com/recharts/recharts/compare/v3.8.0...v3.8.1)

Updates `undici` from 7.24.4 to 7.24.6
- [Release notes](https://github.com/nodejs/undici/releases)
- [Commits](https://github.com/nodejs/undici/compare/v7.24.4...v7.24.6)

Updates `wreq-js` from 2.2.0 to 2.2.2
- [Release notes](https://github.com/sqdshguy/wreq-js/releases)
- [Commits](https://github.com/sqdshguy/wreq-js/compare/v2.2.0...v2.2.2)

---
updated-dependencies:
- dependency-name: "@lobehub/icons"
  dependency-version: 5.2.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
  dependency-group: production
- dependency-name: "@modelcontextprotocol/sdk"
  dependency-version: 1.29.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
  dependency-group: production
- dependency-name: "@swc/helpers"
  dependency-version: 0.5.20
  dependency-type: direct:production
  update-type: version-update:semver-patch
  dependency-group: production
- dependency-name: jose
  dependency-version: 6.2.2
  dependency-type: direct:production
  update-type: version-update:semver-patch
  dependency-group: production
- dependency-name: next
  dependency-version: 16.2.1
  dependency-type: direct:production
  update-type: version-update:semver-minor
  dependency-group: production
- dependency-name: recharts
  dependency-version: 3.8.1
  dependency-type: direct:production
  update-type: version-update:semver-patch
  dependency-group: production
- dependency-name: undici
  dependency-version: 7.24.6
  dependency-type: direct:production
  update-type: version-update:semver-patch
  dependency-group: production
- dependency-name: wreq-js
  dependency-version: 2.2.2
  dependency-type: direct:production
  update-type: version-update:semver-patch
  dependency-group: production
...

Signed-off-by: dependabot[bot] <support@github.com>
2026-03-30 17:32:55 -03:00
dependabot[bot] eaeb28b4e1 deps: bump the development group with 7 updates
Bumps the development group with 7 updates:

| Package | From | To |
| --- | --- | --- |
| [@tailwindcss/postcss](https://github.com/tailwindlabs/tailwindcss/tree/HEAD/packages/@tailwindcss-postcss) | `4.2.1` | `4.2.2` |
| [@types/keytar](https://github.com/DefinitelyTyped/DefinitelyTyped/tree/HEAD/types/keytar) | `4.4.0` | `4.4.2` |
| [eslint-config-next](https://github.com/vercel/next.js/tree/HEAD/packages/eslint-config-next) | `16.1.6` | `16.2.1` |
| [tailwindcss](https://github.com/tailwindlabs/tailwindcss/tree/HEAD/packages/tailwindcss) | `4.2.1` | `4.2.2` |
| [typescript](https://github.com/microsoft/TypeScript) | `5.9.3` | `6.0.2` |
| [typescript-eslint](https://github.com/typescript-eslint/typescript-eslint/tree/HEAD/packages/typescript-eslint) | `8.57.1` | `8.58.0` |
| [vitest](https://github.com/vitest-dev/vitest/tree/HEAD/packages/vitest) | `4.1.0` | `4.1.2` |


Updates `@tailwindcss/postcss` from 4.2.1 to 4.2.2
- [Release notes](https://github.com/tailwindlabs/tailwindcss/releases)
- [Changelog](https://github.com/tailwindlabs/tailwindcss/blob/main/CHANGELOG.md)
- [Commits](https://github.com/tailwindlabs/tailwindcss/commits/v4.2.2/packages/@tailwindcss-postcss)

Updates `@types/keytar` from 4.4.0 to 4.4.2
- [Release notes](https://github.com/DefinitelyTyped/DefinitelyTyped/releases)
- [Commits](https://github.com/DefinitelyTyped/DefinitelyTyped/commits/HEAD/types/keytar)

Updates `eslint-config-next` from 16.1.6 to 16.2.1
- [Release notes](https://github.com/vercel/next.js/releases)
- [Changelog](https://github.com/vercel/next.js/blob/canary/release.js)
- [Commits](https://github.com/vercel/next.js/commits/v16.2.1/packages/eslint-config-next)

Updates `tailwindcss` from 4.2.1 to 4.2.2
- [Release notes](https://github.com/tailwindlabs/tailwindcss/releases)
- [Changelog](https://github.com/tailwindlabs/tailwindcss/blob/main/CHANGELOG.md)
- [Commits](https://github.com/tailwindlabs/tailwindcss/commits/v4.2.2/packages/tailwindcss)

Updates `typescript` from 5.9.3 to 6.0.2
- [Release notes](https://github.com/microsoft/TypeScript/releases)
- [Commits](https://github.com/microsoft/TypeScript/compare/v5.9.3...v6.0.2)

Updates `typescript-eslint` from 8.57.1 to 8.58.0
- [Release notes](https://github.com/typescript-eslint/typescript-eslint/releases)
- [Changelog](https://github.com/typescript-eslint/typescript-eslint/blob/main/packages/typescript-eslint/CHANGELOG.md)
- [Commits](https://github.com/typescript-eslint/typescript-eslint/commits/v8.58.0/packages/typescript-eslint)

Updates `vitest` from 4.1.0 to 4.1.2
- [Release notes](https://github.com/vitest-dev/vitest/releases)
- [Commits](https://github.com/vitest-dev/vitest/commits/v4.1.2/packages/vitest)

---
updated-dependencies:
- dependency-name: "@tailwindcss/postcss"
  dependency-version: 4.2.2
  dependency-type: direct:development
  update-type: version-update:semver-patch
  dependency-group: development
- dependency-name: "@types/keytar"
  dependency-version: 4.4.2
  dependency-type: direct:development
  update-type: version-update:semver-patch
  dependency-group: development
- dependency-name: eslint-config-next
  dependency-version: 16.2.1
  dependency-type: direct:development
  update-type: version-update:semver-minor
  dependency-group: development
- dependency-name: tailwindcss
  dependency-version: 4.2.2
  dependency-type: direct:development
  update-type: version-update:semver-patch
  dependency-group: development
- dependency-name: typescript
  dependency-version: 6.0.2
  dependency-type: direct:development
  update-type: version-update:semver-major
  dependency-group: development
- dependency-name: typescript-eslint
  dependency-version: 8.58.0
  dependency-type: direct:development
  update-type: version-update:semver-minor
  dependency-group: development
- dependency-name: vitest
  dependency-version: 4.1.2
  dependency-type: direct:development
  update-type: version-update:semver-patch
  dependency-group: development
...

Signed-off-by: dependabot[bot] <support@github.com>
2026-03-30 17:32:51 -03:00
Chris Staley d5647eab33 fix: remove dead userDismissed ref after auto-open removal
The userDismissed ref was only read by the removed auto-open useEffect.
Remove the ref declaration and the three onClose assignments that set it.
2026-03-30 17:32:49 -03:00
Chris Staley 89eb8885b1 fix: remove unnecessary comment from previous commit 2026-03-30 17:32:49 -03:00
Chris Staley a5dc5687f8 fix: remove auto-opening OAuth/API key modal on provider detail page
Auto-opening the "Add Connection" dialog when navigating to a provider
with zero connections was a poor UX pattern. It surprised users who were
simply browsing provider details (e.g. after deleting a connection or
checking settings). The page already displays a clear empty state with
an "Add Connection" button — users should click it when ready.
2026-03-30 17:32:49 -03:00
oyi77 6780485051 feat(cache): persistent metrics, cache entry browser, settings UI, MCP tools, prefix analyzer
Implements remaining features from #813:

Phase 1 - Persistent Metrics:
- Add cache_metrics table for persistent hit/miss tracking
- Semantic cache stats now survive server restarts

Phase 2 - Cache Entry Browser:
- /api/cache/entries endpoint with search, pagination, delete
- CacheEntriesTab component for browsing cached entries

Phase 3 - Settings UI:
- CacheSettingsTab for semantic/prompt cache configuration
- /api/settings/cache-config endpoint

Phase 4 - Prefix Analyzer:
- src/lib/promptCache/prefixAnalyzer.ts for intelligent caching
- Analyzes message arrays to find stable prefixes

Phase 5 - Provider Support:
- Added deepseek to CACHING_PROVIDERS

Phase 6 - MCP Tools:
- omniroute_cache_stats tool
- omniroute_cache_flush tool

Phase 7 - Retention:
- cleanOldMetrics() for auto-purge of old entries

Closes #813
2026-03-30 17:32:45 -03:00
oyi77 d043e7a242 feat(cache): fix cache page to display prompt cache metrics and trend data
Closes #813
2026-03-30 17:32:45 -03:00
Chris Staley c5d9b5f51d fix: apply PR review feedback for Gemini CLI quota
- Add early return guard for missing accessToken in getGeminiUsage
- Add 10s fetch timeout (AbortSignal.timeout) on retrieveUserQuota calls
- Clamp used value with Math.max(0, ...) for non-negative display
- Use full accessToken as cache key instead of truncated prefix
- Replace catch(err: any) with instanceof Error check in models route
2026-03-30 17:32:42 -03:00
Chris Staley 35e2892b98 feat: add real Gemini CLI quota tracking via retrieveUserQuota API
Replace stub getGeminiUsage() with per-model quota fetching from Google
Cloud Code Assist's retrieveUserQuota endpoint (same API the official
Gemini CLI /stats command uses). Fixes OAuth env var name, aligns model
list with official Gemini CLI VALID_GEMINI_MODELS, and makes "Import
from /models" discover new models via the quota endpoint.
2026-03-30 17:32:42 -03:00
R.D. b492c5ac1a Fix cloudflared startup TLS handling 2026-03-30 16:31:07 -04:00
diegosouzapw df38b3c62a docs(i18n): sync cache metrics translation keys across 30 languages 2026-03-30 17:29:44 -03:00
R.D. 03a860dd6f Fix combo smoke tests for reasoning responses 2026-03-30 16:23:53 -04:00
oyi77 fec585e44b feat(cache): persistent metrics, cache entry browser, settings UI, MCP tools, prefix analyzer
Implements remaining features from #813:

Phase 1 - Persistent Metrics:
- Add cache_metrics table for persistent hit/miss tracking
- Semantic cache stats now survive server restarts

Phase 2 - Cache Entry Browser:
- /api/cache/entries endpoint with search, pagination, delete
- CacheEntriesTab component for browsing cached entries

Phase 3 - Settings UI:
- CacheSettingsTab for semantic/prompt cache configuration
- /api/settings/cache-config endpoint

Phase 4 - Prefix Analyzer:
- src/lib/promptCache/prefixAnalyzer.ts for intelligent caching
- Analyzes message arrays to find stable prefixes

Phase 5 - Provider Support:
- Added deepseek to CACHING_PROVIDERS

Phase 6 - MCP Tools:
- omniroute_cache_stats tool
- omniroute_cache_flush tool

Phase 7 - Retention:
- cleanOldMetrics() for auto-purge of old entries

Closes #813
2026-03-31 02:41:30 +07:00
diegosouzapw 11dfdbb7a3 feat(analytics): add diversity score card UI and diversity API route
Implement DiversityScoreCard component to fetch and display provider diversity score with loading state and conditional styling, integrate it into AnalyticsPage overview, and add a new API route at src/app/api/analytics/diversity/route.ts to return the diversity report using getDiversityReport
2026-03-30 16:37:49 -03:00
oyi77 ae1a0f411b feat(cache): fix cache page to display prompt cache metrics and trend data
Closes #813
2026-03-31 00:53:18 +07:00
tombii 007b5d7f50 fix(test): split CacheStatsCard check into cache page test
Integration test was failing because CacheStatsCard was moved from
settings page to cache page in previous commit. Split the test into
two separate describe blocks for accurate page-specific verification.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-30 19:49:57 +02:00
tombii c6eadc504b fix(usage): include cache tokens in input token counts
- Fix getLoggedInputTokens to return full prompt_tokens (input + cache_read + cache_creation)
- Fix usageExtractor for non-streaming Claude responses to calculate total correctly
- Add formatUsageLog helper to show CR=<cache_read> in logs
- Add migration 012 to fix historical token counts in usage_history
- Move prompt cache metrics from Settings to /dashboard/cache page

Per Claude API docs:
Total input tokens = input_tokens + cache_creation_input_tokens + cache_read_input_tokens

Fixes issue where totalInputTokens (71k) was less than totalCacheCreationTokens (1.35M).

Tested:
- All 1134 unit tests pass
- Cache metrics API returns correct totals
- Migration is idempotent and tracked in _omniroute_migrations
- Logs show cache read tokens: 'in=6055 | out=211 | CR=22399'

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-30 19:24:26 +02:00
diegosouzapw a864258cb8 feat(ui): integrate FSM, adaptive routing, and provider diversity
Build Electron Desktop App / Validate version (push) Failing after 35s
Build Electron Desktop App / Build Electron (macos-arm64) (push) Has been skipped
Build Electron Desktop App / Build Electron (linux) (push) Has been skipped
Build Electron Desktop App / Build Electron (macos-intel) (push) Has been skipped
Build Electron Desktop App / Build Electron (windows) (push) Has been skipped
Build Electron Desktop App / Create Release (push) Has been skipped
Build Electron Desktop App / Publish to npm (push) Has been skipped
2026-03-30 12:58:45 -03:00
Diego Rodrigues de Sa e Souza 8a9c15c874 Merge pull request #819 from diegosouzapw/release/v3.3.4
Release v3.3.4
2026-03-30 11:26:17 -03:00
diegosouzapw 7a666526b7 chore(release): bump version to 3.3.4 2026-03-30 11:23:59 -03:00
diegosouzapw 3fc1cac015 docs(i18n): update CHANGELOG, README and sync multi-language FEATURES docs 2026-03-30 11:21:47 -03:00
Diego Rodrigues de Sa e Souza 04a0b07bf6 Merge pull request #793 from igormorais123/feat/provider-diversity-scoring
feat(sse): add provider diversity scoring via Shannon entropy
2026-03-30 11:07:03 -03:00
Diego Rodrigues de Sa e Souza 59e48ca91a Merge pull request #794 from igormorais123/feat/adaptive-volume-routing
feat(sse): add adaptive volume/complexity detector for routing strategy override
2026-03-30 11:07:00 -03:00
Diego Rodrigues de Sa e Souza 8ff562c5af Merge pull request #795 from igormorais123/feat/provider-expiration-tracking
feat(domain): add provider expiration tracking with proactive alerts
2026-03-30 11:06:56 -03:00
Diego Rodrigues de Sa e Souza b502a93728 Merge pull request #796 from igormorais123/feat/config-audit-trail
feat(domain): add configuration audit trail with diff detection and rollback
2026-03-30 11:06:53 -03:00
Diego Rodrigues de Sa e Souza b6afa6c2c7 Merge pull request #803 from igormorais123/feat/graceful-degradation-wrapper
feat(domain): add graceful degradation framework with multi-layer fallback
2026-03-30 11:06:50 -03:00
Diego Rodrigues de Sa e Souza 5887da0229 Merge pull request #805 from igormorais123/feat/fsm-workflow-orchestrator
feat(sse): add deterministic FSM orchestrator for multi-step workflows
2026-03-30 11:06:46 -03:00
Diego Rodrigues de Sa e Souza a7d833d96a Merge pull request #817 from diegosouzapw/feat/auto-disable-banned-accounts-setting
Feat/auto disable banned accounts setting
2026-03-30 11:06:42 -03:00
Diego Rodrigues de Sa e Souza db3753d611 Merge PR 811: fix UI fallbacks and Electron release workflow
fix: UI fallbacks and Electron release workflow
2026-03-30 11:04:02 -03:00
diegosouzapw f810b13bca fix: complete bugfixes for UI, OAuth fallbacks, cliRuntime Windows constraints and Codex non-streaming integration 2026-03-30 11:01:55 -03:00
diegosouzapw 5ad687c6d8 fix(ui/ci): use ProviderIcon for Provider header breadcrumbs and add permissions to electron-release.yml (#745, #761)
- Use ProviderIcon for internal .png paths solving SVG provider 404 images (#745).
- Add id-token: write and packages: write permissions to .github/workflows/electron-release.yml to fix permissions denied failure when calling the reusable workflow npm-publish.yml (#761).
- Fix tests and ESM resolution for autoUpdate.ts override logic.
2026-03-30 07:38:30 -03:00
Diego Rodrigues de Sa e Souza 6ad0910790 Merge pull request #810 from oyi77/main
feat(settings): add debug toggle and sidebar visibility toggle
2026-03-30 07:07:54 -03:00
Diego Rodrigues de Sa e Souza 4d8c0546cf Merge pull request #783 from rdself/coder/cloudflared-exit1-fix
Fix cloudflared quick tunnel startup in Docker
2026-03-30 07:07:39 -03:00
oyi77 35f96d4a40 feat(settings): add debug toggle and sidebar visibility toggle
feat(ui): replace hide-sidebar toggle with dynamic visibility toggle
2026-03-30 15:15:02 +07:00
igormorais123 ae96fb6f63 feat(sse): add deterministic FSM orchestrator for multi-step workflows
Risk-based phase skipping: high=all 9 phases, medium=skip planner, low=execute+test.
Veto authority, pause/resume, retry limits, full audit trail.

Closes #800, closes #802
2026-03-30 01:28:45 -03:00
igormorais123 67592d80aa feat(domain): add graceful degradation framework with multi-layer fallback
Add a standardized degradation pattern for services depending on external
systems. withDegradation() tries primary → fallback → safe default,
tracking status in a global registry for dashboard visibility.

Features:
- Async and sync variants
- Global registry with per-feature status tracking
- Degradation levels: full → reduced → minimal → default
- Summary and report APIs for dashboard integration
- Reason tracking for debugging

Example: Rate limiting degrades from Redis → in-memory → permissive
instead of crashing when Redis is unavailable.

Closes #799
2026-03-30 01:23:10 -03:00
igormorais123 94a5e43e5d feat(domain): add configuration audit trail with diff detection and rollback
Add configAudit module that records every change to provider connections,
combos, and routing policies with:

- Before/after state snapshots
- Structured diff (added, removed, changed keys)
- Source tracking (dashboard, API, sync, auto-healing)
- Filtered retrieval with pagination
- Rollback state extraction
- Configuration snapshot export for backup

Enables traceability and quick rollback when config changes cause issues.

Closes #791
2026-03-30 00:49:22 -03:00
igormorais123 26958f8f70 feat(domain): add provider expiration tracking with proactive alerts
Add providerExpiration module to track OAuth token, subscription, and
API credit expiration dates per provider connection. Provides:

- setExpiration() / getExpiration() for CRUD operations
- getExpiringSoon() for proactive alerts
- getExpirationSummary() for dashboard health display
- detectExpirationFromResponse() for auto-detection from HTTP headers
- Status classification: active → expiring_soon → expired

Prevents silent failures from expired credentials by alerting operators
before tokens/subscriptions expire.

Closes #790
2026-03-30 00:48:06 -03:00
igormorais123 a427d215e3 feat(sse): add adaptive volume/complexity detector for routing strategy override
Add volumeDetector module that analyzes request characteristics (batch
size, token count, tool usage, browser signals, complexity keywords)
and recommends routing strategy overrides.

Rules:
- Batch >= 50 items → round-robin with economy models
- Critical complexity (many tools, browser, deploy) → priority premium-first
- Browser/UI interaction → force premium priority
- Short requests (<200 tokens) → flag for economy tier

Closes #789
2026-03-30 00:46:55 -03:00
igormorais123 271cf37b8a feat(sse): add provider diversity scoring via Shannon entropy
Add a providerDiversity module that tracks provider usage distribution
using a rolling time window and calculates Shannon entropy normalized
to [0..1]. This enables the auto-combo scoring engine to factor in
provider diversity — boosting underrepresented providers to reduce
single-point-of-failure risk.

Key features:
- Rolling window with configurable size and TTL
- Shannon entropy calculation normalized to [0..1]
- Per-provider diversity boost for auto-combo integration
- Diversity report for dashboard display
- Full test coverage

Closes #788
2026-03-30 00:45:17 -03:00
R.D. 179c03e79d Isolate cloudflared runtime environment 2026-03-29 22:30:07 -04:00
Diego Rodrigues de Sa e Souza 0a1b68639b Merge pull request #782 from diegosouzapw/release/v3.3.3
chore(release): v3.3.3 — UI bugfixes and AutoUpdate repairs
2026-03-29 22:51:52 -03:00
diegosouzapw d69e7ec850 chore(release): v3.3.3 — Core UI bugfixes and AutoUpdate repairs 2026-03-29 21:18:07 -03:00
Diego Rodrigues de Sa e Souza 76a6d8292c Merge pull request #780 from diegosouzapw/release/v3.3.2
Build Electron Desktop App / Validate version (push) Failing after 30s
Build Electron Desktop App / Build Electron (macos-arm64) (push) Has been skipped
Build Electron Desktop App / Build Electron (linux) (push) Has been skipped
Build Electron Desktop App / Build Electron (macos-intel) (push) Has been skipped
Build Electron Desktop App / Build Electron (windows) (push) Has been skipped
Build Electron Desktop App / Create Release (push) Has been skipped
Build Electron Desktop App / Publish to npm (push) Has been skipped
chore(release): v3.3.2 — bug fixes and feature enhancements
2026-03-29 20:04:58 -03:00
diegosouzapw 8f09c444b6 chore(release): v3.3.2 — bug fixes and feature enhancements 2026-03-29 20:01:06 -03:00
Diego Rodrigues de Sa e Souza 9032e6abb8 Merge pull request #779 from diegosouzapw/fix/batch-bugs-748-769
fix: missing i18n keys and streaming fetch timeout (#748, #769)
2026-03-29 19:45:45 -03:00
diegosouzapw 1c070d16a6 fix: add missing i18n keys for windsurf/copilot and apply fetch timeout to streaming requests (#748, #769)
- Add windsurf and copilot entries to toolDescriptions in all 33 locale files
  to fix MISSING_MESSAGE errors on the CLI Tools page (#748)
- Apply FETCH_TIMEOUT_MS to streaming requests' initial fetch() call to prevent
  300s TCP default timeout causing silent failures on long-running requests (#769)
- Previously only non-streaming requests had timeout protection; streaming requests
  relied solely on stream idle detection which doesn't cover initial connection hangs
2026-03-29 19:43:21 -03:00
Diego Rodrigues de Sa e Souza 7837fcc657 Merge pull request #772 from rdself/coder/cloudflared-tunnel-endpoint
Add Cloudflare Quick Tunnel controls to endpoint page
2026-03-29 19:37:03 -03:00
Diego Rodrigues de Sa e Souza f9690d40d3 Merge pull request #778 from christopher-s/glm-coding-audit
feat: GLM Coding provider enhancements and fixes
2026-03-29 19:36:52 -03:00
Diego Rodrigues de Sa e Souza 5de6cd77dc Merge pull request #773 from rdself/codex/fix-combo-live-test-no-cache
Bypass semantic cache in combo live tests
2026-03-29 19:36:40 -03:00
Diego Rodrigues de Sa e Souza aa5ab55b14 Merge pull request #777 from diegosouzapw/release/v3.3.1
chore(release): v3.3.1 — bug fixes and schema adjustments
2026-03-29 19:36:11 -03:00
Chris Staley 9195b18981 fix: resolve t11 any-budget lint failures and remove audit doc from tracking
Pre-existing any-budget violations in chatCore.ts (6), combo.ts (2), and
embeddings.ts (1 false positive in comment) — none introduced by GLM work.
Replace `as any` with `Record<string, unknown>` casts and reword comment.

Also removes docs/superpowers audit worksheet from git tracking (not part
of GLM Coding provider changes).
2026-03-29 15:35:55 -06:00
Chris Staley b812d6efb8 fix: use relative paths in audit doc and correct Indonesian translations in in.json 2026-03-29 15:17:39 -06:00
Chris Staley 231a02eb10 fix: correct GLM context windows for glm-4.6v (128K) and glm-4.5v (16K) per Z.AI docs 2026-03-29 15:13:07 -06:00
Chris Staley 6736806361 i18n: add proper translations for model import dialog keys in all locales
Add allModelsAlreadyImported, noNewModelsToImport, and
skippingExistingModels translations for all 32 non-English locales.
2026-03-29 15:13:07 -06:00
Chris Staley 8e17756bf8 fix: filter registry models from auto-sync to prevent duplicates
The model sync scheduler and sync-models endpoint were blindly
replacing custom models with all fetched models, including ones
already in the built-in registry. Now filters out registry models
before saving to custom models.
2026-03-29 15:13:07 -06:00
Chris Staley 0b133fe55e fix: skip duplicate models during Import from /models
Compare fetched models against existing custom models AND built-in
registry models before posting. Only new models trigger
POST /api/provider-models calls. Shows skip count in import progress
when some models already exist. Adds i18n keys for all locales.
2026-03-29 15:13:07 -06:00
Chris Staley d01266c642 fix: remove glm-4.7-flashx from GLM Coding provider (429 insufficient balance)
Live-tested all GLM Coding models against the /api/coding/paas/v4
endpoint. glm-4.7-flashx returns 429 "Insufficient balance or no
resource package" and is not listed on the /models endpoint.

All other models (glm-5.1, glm-5, glm-5-turbo, glm-4.7, glm-4.7-flash,
glm-4.6v, glm-4.6, glm-4.5v, glm-4.5, glm-4.5-air) return 200.
2026-03-29 15:13:07 -06:00
Chris Staley fe3f9c86d5 fix: use GLM Coding API endpoints for model import with region-aware URLs
The "Import from /models" button was using the wrong Z.AI API surface
(Anthropic-compatible /api/anthropic/v1/models with x-api-key auth).
Switched to the correct Coding API endpoints with Authorization: Bearer
auth, matching the pattern used by the quota/usage tracking code.

- International: https://api.z.ai/api/coding/paas/v4/models
- China: https://open.bigmodel.cn/api/coding/paas/v4/models
- Auth: Authorization: Bearer <token> (not x-api-key)
- Region sourced from providerSpecificData.apiRegion

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-29 15:13:07 -06:00
Chris Staley 14bf3645d6 fix: validate GLM coding provider settings
Record the family-by-family GLM Coding audit, add regression coverage, and fix the documented GLM-5.1 context window override.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-29 15:13:07 -06:00
Chris Staley 0f4a7b2405 fix: add GLM-4.7-FlashX model and correct GLM-4.7 tool calling support
- Add missing glm-4.7-flashx variant to provider registry (confirmed in
  Z.AI official GLM-4.7 overview docs as one of three variants)
- Remove glm-4.7/glm4.7 from tool calling denylist — official docs
  explicitly show GLM-4.7 supporting function calling with tools param
- Add estimated pricing for glm-4.7-flashx ($0.3/$1.1) between free
  Flash and standard 4.7 tiers

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-29 15:13:07 -06:00
Chris Staley 681e49a4cc fix: set correct 128k context length for GLM 4.5 and GLM 4.5 Air
Official docs at https://docs.z.ai/guides/llm/glm-4.5 confirm both models
have 128k token context, not the 200k provider default.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-29 15:13:07 -06:00
diegosouzapw 6e9c97fbff chore(release): v3.3.1 — bug fixes and schema adjustments 2026-03-29 16:39:10 -03:00
mikhailsal 370070f489 fix(stream): normalize delta.reasoning alias and separate reasoning in client response (#771)
Build Electron Desktop App / Validate version (push) Failing after 44s
Build Electron Desktop App / Build Electron (macos-arm64) (push) Has been skipped
Build Electron Desktop App / Build Electron (linux) (push) Has been skipped
Build Electron Desktop App / Build Electron (macos-intel) (push) Has been skipped
Build Electron Desktop App / Build Electron (windows) (push) Has been skipped
Build Electron Desktop App / Create Release (push) Has been skipped
Build Electron Desktop App / Publish to npm (push) Has been skipped
* fix(stream): normalize delta.reasoning to reasoning_content in SSE streaming

NVIDIA kimi-k2.5 (and potentially other providers) send reasoning
tokens as `delta.reasoning` in SSE streaming chunks instead of the
standard OpenAI `delta.reasoning_content` field. This caused reasoning
content to be silently dropped during stream passthrough — clients
received only the final answer with no reasoning separation.

The non-streaming sanitizer (responseSanitizer.ts) already handled this
alias, but the streaming pipeline did not.

Fix applied in 4 locations:
- stream.ts passthrough: normalize + force re-serialize sanitized chunk
- stream.ts translate: accumulate reasoning from delta.reasoning
- sseParser.ts: collect delta.reasoning in parseSSEToOpenAIResponse
- streamPayloadCollector.ts: collect delta.reasoning in buildOpenAISummary

* fix: eliminate injectedUsage reuse bug and add reasoning alias tests

- Detect delta.reasoning alias before sanitizeStreamingChunk() which
  already normalizes it, removing dead post-sanitization normalization
- Replace injectedUsage reuse with separate needsReserialization flag
  so reasoning re-serialization cannot block finish_reason/usage
  mutations on the same SSE chunk (fixes CRITICAL review finding)
- Add unit test for parseSSEToOpenAIResponse reasoning alias
- Add unit test for buildStreamSummaryFromEvents reasoning alias

* fix(stream): separate reasoning from content in passthrough response body

The passthroughAccumulatedContent variable was mixing delta.content and
delta.reasoning_content into one string, causing the client_response
log and responseBody to lose reasoning separation.

- Add passthroughAccumulatedReasoning accumulator for reasoning deltas
- Set message.reasoning_content in responseBody when reasoning exists
- Only accumulate delta.content into passthroughAccumulatedContent

* fix: trim leading whitespace from assembled content in log summaries

NVIDIA and other providers emit token deltas with leading spaces
(e.g. ' The', ' user'). When joined, these produce a leading space in
the provider_response and parsed non-streaming response logs. Trim
the joined content and reasoning_content in both buildOpenAISummary
and parseSSEToOpenAIResponse for consistent log output.

* fix(stream): split combined reasoning+content deltas into separate SSE events

Some providers (e.g. NVIDIA NIM) send transition chunks with both
`delta.reasoning` and `delta.content` in the same SSE event.
After sanitization this becomes `reasoning_content` + `content`,
which violates the standard OpenAI streaming contract where these
fields are never mixed. Clients using if/else logic (LobeChat, etc.)
skip content when reasoning_content is present, losing the first
content token.

Split such combined chunks into two separate SSE events:
1. Reasoning-only event (finish_reason=null, no usage)
2. Content-only event (carries finish_reason and usage)
2026-03-29 16:12:22 -03:00
Paijo 7168f4014d fix: strip reasoning/thinking params for models that don't support them (#766)
Models like antigravity/claude-sonnet-4-6 route through Google's internal
Cloud Code API which returns HTTP 400 when thinking/reasoning parameters
are included in the request body.

Changes:
- open-sse/services/modelCapabilities.ts: add supportsReasoning() function
  with a denylist of known-unsupported patterns (antigravity/claude-sonnet-*)
  and a registry-based lookup hook (supportsReasoning flag per model)
- open-sse/services/thinkingBudget.ts: in applyThinkingBudget(), add early
  exit before the mode switch — if model string is present and
  supportsReasoning() returns false, call stripThinkingConfig() immediately
  regardless of the configured ThinkingMode

This is fully backward-compatible: models not in the denylist are unaffected,
and the supportsReasoning registry flag defaults to null (pass-through).

Fixes: HTTP 400 errors on antigravity provider when client sends requests
with thinking/reasoning budget parameters (e.g. claude-sonnet-4-6 via AG).

Co-authored-by: oyi77 <oyi77@github.com>
Co-authored-by: oyi77 <oyi77@users.noreply.github.com>
2026-03-29 16:12:19 -03:00
Paijo f0912feefb feat: auto-disable permanently banned provider accounts (with Settings toggle) (#765)
* feat: auto-disable banned accounts setting with UI toggle

Add a configurable setting to automatically disable provider accounts
that return permanent/terminal errors (403 banned, ToS violation, etc.)

Changes:
- open-sse/services/accountFallback.ts: extend ACCOUNT_DEACTIVATED_SIGNALS
  with AG-specific ban messages ('verify your account', 'service disabled
  for violation')
- src/app/api/settings/auto-disable-accounts/route.ts: new GET/PUT endpoint
  for the setting (enabled bool + threshold int)
- src/shared/validation/schemas.ts: updateAutoDisableAccountsSchema
- src/sse/services/auth.ts: in markAccountUnavailable(), capture result.permanent
  from checkFallbackError() and — when autoDisableBannedAccounts is enabled and
  backoffLevel >= threshold — set isActive=false on the connection

Default: disabled (backward-compatible). Enable via Settings UI or PUT
/api/settings/auto-disable-accounts { "enabled": true, "threshold": 3 }

Fixes: antigravity accounts with 403/Verify-your-account errors being
retried indefinitely in the rotation pool.

Co-authored-by: oyi77 <oyi77@users.noreply.github.com>

* fix: address reviewer comments for auto-disable (use getCachedSettings, immediate disable on permanent bans)

---------

Co-authored-by: oyi77 <oyi77@github.com>
Co-authored-by: oyi77 <oyi77@users.noreply.github.com>
2026-03-29 16:12:17 -03:00
diegosouzapw e90c9c171a Merge branch 'main' into fix/streaming-reasoning-field-alias 2026-03-29 16:03:13 -03:00
diegosouzapw d0c172830c feat(ui): add AutoDisableCard to Resilience settings (#765) 2026-03-29 15:57:19 -03:00
oyi77 d5bf0d1199 fix: address reviewer comments for auto-disable (use getCachedSettings, immediate disable on permanent bans) 2026-03-30 01:47:28 +07:00
Mikhail Salnikov d3a24446b8 fix: trim leading whitespace from assembled content in log summaries
NVIDIA and other providers emit token deltas with leading spaces
(e.g. ' The', ' user'). When joined, these produce a leading space in
the provider_response and parsed non-streaming response logs. Trim
the joined content and reasoning_content in both buildOpenAISummary
and parseSSEToOpenAIResponse for consistent log output.
2026-03-29 21:44:13 +03:00
Mikhail Salnikov aa93276e6e fix(stream): separate reasoning from content in passthrough response body
The passthroughAccumulatedContent variable was mixing delta.content and
delta.reasoning_content into one string, causing the client_response
log and responseBody to lose reasoning separation.

- Add passthroughAccumulatedReasoning accumulator for reasoning deltas
- Set message.reasoning_content in responseBody when reasoning exists
- Only accumulate delta.content into passthroughAccumulatedContent
2026-03-29 21:41:32 +03:00
R.D. cf36972969 Harden cloudflared child process environment 2026-03-29 14:25:07 -04:00
R.D. 40862f26e6 Bypass semantic cache in combo live tests 2026-03-29 14:21:39 -04:00
Mikhail Salnikov 4083447c3f fix: eliminate injectedUsage reuse bug and add reasoning alias tests
- Detect delta.reasoning alias before sanitizeStreamingChunk() which
  already normalizes it, removing dead post-sanitization normalization
- Replace injectedUsage reuse with separate needsReserialization flag
  so reasoning re-serialization cannot block finish_reason/usage
  mutations on the same SSE chunk (fixes CRITICAL review finding)
- Add unit test for parseSSEToOpenAIResponse reasoning alias
- Add unit test for buildStreamSummaryFromEvents reasoning alias
2026-03-29 21:18:46 +03:00
R.D. 3cb34ad827 Add Cloudflare Quick Tunnel controls to endpoint page 2026-03-29 14:04:50 -04:00
Mikhail Salnikov 61d7566ca1 fix(stream): normalize delta.reasoning to reasoning_content in SSE streaming
NVIDIA kimi-k2.5 (and potentially other providers) send reasoning
tokens as `delta.reasoning` in SSE streaming chunks instead of the
standard OpenAI `delta.reasoning_content` field. This caused reasoning
content to be silently dropped during stream passthrough — clients
received only the final answer with no reasoning separation.

The non-streaming sanitizer (responseSanitizer.ts) already handled this
alias, but the streaming pipeline did not.

Fix applied in 4 locations:
- stream.ts passthrough: normalize + force re-serialize sanitized chunk
- stream.ts translate: accumulate reasoning from delta.reasoning
- sseParser.ts: collect delta.reasoning in parseSSEToOpenAIResponse
- streamPayloadCollector.ts: collect delta.reasoning in buildOpenAISummary
2026-03-29 20:51:26 +03:00
Diego Rodrigues de Sa e Souza af338d447b Merge pull request #768 from diegosouzapw/release/v3.3.0
Build Electron Desktop App / Validate version (push) Failing after 32s
Build Electron Desktop App / Build Electron (macos-arm64) (push) Has been skipped
Build Electron Desktop App / Build Electron (linux) (push) Has been skipped
Build Electron Desktop App / Build Electron (macos-intel) (push) Has been skipped
Build Electron Desktop App / Build Electron (windows) (push) Has been skipped
Build Electron Desktop App / Create Release (push) Has been skipped
Build Electron Desktop App / Publish to npm (push) Has been skipped
chore(release): v3.3.0 — test stability, release consolidation
2026-03-29 14:30:59 -03:00
diegosouzapw 6fad06f659 chore(release): v3.3.0 — test stability, release consolidation 2026-03-29 14:22:25 -03:00
diegosouzapw 1d51d8ff27 chore(release): v3.2.9 — combo diagnostics, quality gates, Gemini tool fix
Build Electron Desktop App / Validate version (push) Failing after 32s
Build Electron Desktop App / Build Electron (macos-arm64) (push) Has been skipped
Build Electron Desktop App / Build Electron (linux) (push) Has been skipped
Build Electron Desktop App / Build Electron (macos-intel) (push) Has been skipped
Build Electron Desktop App / Build Electron (windows) (push) Has been skipped
Build Electron Desktop App / Create Release (push) Has been skipped
Build Electron Desktop App / Publish to npm (push) Has been skipped
2026-03-29 14:16:37 -03:00
oyi77 82dd4aa403 feat: auto-disable banned accounts setting with UI toggle
Add a configurable setting to automatically disable provider accounts
that return permanent/terminal errors (403 banned, ToS violation, etc.)

Changes:
- open-sse/services/accountFallback.ts: extend ACCOUNT_DEACTIVATED_SIGNALS
  with AG-specific ban messages ('verify your account', 'service disabled
  for violation')
- src/app/api/settings/auto-disable-accounts/route.ts: new GET/PUT endpoint
  for the setting (enabled bool + threshold int)
- src/shared/validation/schemas.ts: updateAutoDisableAccountsSchema
- src/sse/services/auth.ts: in markAccountUnavailable(), capture result.permanent
  from checkFallbackError() and — when autoDisableBannedAccounts is enabled and
  backoffLevel >= threshold — set isActive=false on the connection

Default: disabled (backward-compatible). Enable via Settings UI or PUT
/api/settings/auto-disable-accounts { "enabled": true, "threshold": 3 }

Fixes: antigravity accounts with 403/Verify-your-account errors being
retried indefinitely in the rotation pool.

Co-authored-by: oyi77 <oyi77@users.noreply.github.com>
2026-03-29 23:24:27 +07:00
Randi 8af9bd1ac3 Force real upstream combo live tests (#759) 2026-03-29 13:21:53 -03:00
LASTHXH 9fc3845d92 Fix Gemini API error with integer enum in tool parameters (#760)
Gemini API returns 400 error when tools have enum constraints on integer/number types:
"enum: only allowed for STRING type"

This fix removes enum constraints for integer and number types in JSON schemas
before sending to Gemini API, while keeping enum for string types.

Fixes tools like mcp__pointer__get-pointed-element that use integer enums
for cssLevel and textDetail parameters.

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-29 13:21:51 -03:00
Gorchakov-Pressure 93bbe8e7a8 feat(combo): response quality validation, circuit breaker fix, Cursor 4.6 models (#762)
- Add `validateResponseQuality()` to detect empty/invalid 200 responses from
  upstream providers in combo routing. Non-streaming responses with empty body,
  invalid JSON, or missing content/tool_calls now trigger circuit breaker
  failure and fallback to the next model instead of being returned to the client.

- Add missing `breaker._onSuccess()` calls in both priority and round-robin
  combo paths. Previously failures accumulated without reset, causing premature
  circuit breaker trips on healthy models.

- Update Cursor provider registry with Claude 4.6 model IDs (opus-high,
  sonnet-high, haiku, opus + thinking variants). Keep 4.5 IDs for backward
  compatibility.

- Update free-stack preset: replace duplicate qw/qwen3-coder-plus with
  if/deepseek-v3.2 for better model diversity.

- Add paid-premium combo template for round-robin load distribution across
  paid subscription providers (Cursor, Antigravity).

Made-with: Cursor
2026-03-29 13:21:48 -03:00
Diego Rodrigues de Sa e Souza 46acd16999 chore(release): v3.2.8 — Docker Auto-Update & Analytics Fixes (#755)
* chore(release): v3.2.8 — Docker auto-update UI and cache analytics fixes

* fix(sse): remove race condition in cache metrics tracking (#758)

- Remove in-memory metrics tracking (currentMetrics, trackCacheMetrics, updateCacheMetrics)
- Cache metrics now computed on-the-fly from usage_history table (single source of truth)
- Fixes CRITICAL issue from code review: concurrent requests overwriting metrics
- Fixes WARNING: duplicate metric tracking logic in streaming/non-streaming paths

Ref: PR #752 (merged before this fix was included)

* fix: handle allRateLimited credentials & forward extra body keys in embeddings/images routes (#757)

* fix: handle allRateLimited credentials in embeddings and images routes

When getProviderCredentials() returns an allRateLimited object (truthy,
but without apiKey/accessToken), the embeddings and images routes
incorrectly passed it to handlers as valid credentials. The handlers
then sent upstream requests without Authorization headers, causing
401 errors from providers (e.g. NVIDIA NIM).

This only manifested under concurrent requests: a chat/completions
call could trigger rate limiting on a provider account, and a
simultaneous embeddings request would receive the allRateLimited
sentinel — but treat it as valid credentials.

The chat pipeline already handled this case correctly. This commit
adds the same allRateLimited guard to all affected routes:
- POST /v1/embeddings
- POST /v1/providers/{provider}/embeddings
- POST /v1/images/generations
- POST /v1/providers/{provider}/images/generations

Also adds a defense-in-depth guard in the embeddings handler itself:
if no auth token is available for a non-local provider, return 401
immediately instead of sending an unauthenticated request upstream.

Made-with: Cursor

* fix(embeddings): forward extra body keys to upstream providers

The embeddings handler only forwarded model, input, dimensions, and
encoding_format to upstream providers, silently dropping any additional
fields. This broke asymmetric embedding APIs (e.g. NVIDIA NIM
nv-embedqa-e5-v5) that require input_type, and other providers
expecting user or truncate parameters.

Add a KNOWN_FIELDS exclusion set and forward all unrecognized body
keys to the upstream request, matching the passthrough pattern used
by the chat pipeline's DefaultExecutor.transformRequest().

Made-with: Cursor

* fix(auth): redirect and unconditional 401 on disabled requireLogin + fix test cases

* fix(build): remove legacy proxy.ts causing Next.js build collision

* fix(build): revert middleware.ts rename to proxy.ts because of Next.js Edge constraints

---------

Co-authored-by: diegosouzapw <diegosouzapw@users.noreply.github.com>
Co-authored-by: tombii <tombii@users.noreply.github.com>
Co-authored-by: Gorchakov-Pressure <117600961+Gorchakov-Pressure@users.noreply.github.com>
2026-03-29 13:09:38 -03:00
diegosouzapw 5ad2c6abf6 Fix merge conflicts 2026-03-29 11:26:17 -03:00
Diego Rodrigues de Sa e Souza d5781d60bd Merge pull request #752 from tombii/feat/preserve-client-cache-control
feat: preserve client cache_control with deterministic routing + metrics dashboard
2026-03-29 11:23:22 -03:00
Diego Rodrigues de Sa e Souza e464a95c5a Merge pull request #747 from AveryanAlex/fix/responses-chat-translation-bugs
Improve responses<->chat translation
2026-03-29 11:23:19 -03:00
Diego Rodrigues de Sa e Souza a50ea4bb9e Merge pull request #746 from AveryanAlex/fix/codex-passthrough-store-instructions
fix: ensure Codex passthrough path sets instructions and store=false
2026-03-29 11:23:05 -03:00
Diego Rodrigues de Sa e Souza aa11bb6d93 Merge pull request #753 from LASTHXH/fix/cli-tools-status-undefined
Fix CLI tools status endpoint crash and add droid detection support
2026-03-29 11:22:45 -03:00
tombii 319018f055 test: fix cache metrics tests with usage_history table
- Add usage_history table creation in test setup
- Simplify byStrategy query to avoid non-existent combo_strategy column
- Update test assertions to work with existing test data
2026-03-29 16:05:32 +02:00
LASTHXH 394b986ccb Fix CLI tools status endpoint crash and add droid detection support
1. Fixed crash in /api/cli-tools/status when statuses[toolId] is undefined
   - Added null check before accessing statuses[toolId] properties
   - Prevents "Cannot set property of undefined" error

2. Added support for droid.exe detection in ~/bin directory
   - Added ~/bin and ~/.local/bin to EXPECTED_PARENT_PATHS
   - Added droid.exe variant to toolBins for Windows
   - Added specific path check for droid in ~/bin/droid.exe

These fixes resolve issues where CLI tools (Claude Code, Codex, Droid)
were showing as "not installed" even when properly installed.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-29 17:44:37 +05:00
tombii 26f7b36ce4 feat: add cache control settings and token-based metrics
Settings:
- Add `alwaysPreserveClientCache` setting with modes: auto/always/never
- UI toggle in Dashboard > Settings > Routing tab
- Auto mode preserves cache_control for Claude Code clients with deterministic routing

Metrics:
- Track prompt cache token usage (input, cached, creation)
- Display cache reuse ratio (cached/input tokens)
- Breakdown by provider and routing strategy
- Shows tokens saved and estimated cost savings

API Endpoints:
- GET /api/settings/cache-metrics - retrieve metrics
- DELETE /api/settings/cache-metrics - reset metrics

Files:
- open-sse/utils/cacheControlPolicy.ts: CacheControlMetrics interface, trackCacheMetrics, updateCacheTokenMetrics
- open-sse/handlers/chatCore.ts: Track cache tokens from provider responses
- src/lib/db/settings.ts: Database functions for metrics persistence
- src/lib/cacheControlSettings.ts: Cached settings accessor
- src/app/(dashboard)/dashboard/settings/components/CacheStatsCard.tsx: Metrics dashboard UI
- tests/unit/*.test.mjs: Unit tests (41 tests pass)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-29 14:37:55 +02:00
cai kerui f0daad10ce Add Docker-aware dashboard auto-update flow 2026-03-29 20:25:14 +09:00
tombii 0bc557fb8b feat(sse): preserve client cache_control for Claude Code with deterministic routing
Adds intelligent cache control preservation for Claude Code clients:

- New cacheControlPolicy.ts module with detection logic:
  - isClaudeCodeClient(): Detects Claude Code via User-Agent
  - providerSupportsCaching(): Checks provider (claude, anthropic, zai, qwen)
  - isDeterministicStrategy(): Identifies priority/cost-optimized strategies
  - shouldPreserveCacheControl(): Main policy decision

- Cache control is preserved when:
  1. Client is Claude Code (detected via User-Agent)
  2. Provider supports prompt caching
  3. Request routing is deterministic:
     - Single model requests (always)
     - Combo with priority or cost-optimized strategy only

- Updated translator to accept preserveCacheControl option
- Updated chatCore and chat handler to propagate combo strategy
- Added comprehensive unit tests (24 tests)

Non-deterministic combo strategies (weighted, round-robin, random, etc.)
continue to use OmniRoute's managed caching strategy.

Refs: #cache-control-preservation
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-29 12:24:44 +02:00
tombii 3571421a0e fix(ci): push sync to correct fork repo 2026-03-29 10:45:21 +02:00
tombii aed80f3e4f ci: add upstream sync workflow 2026-03-29 10:44:45 +02:00
diegosouzapw b84e79362e docs: sync v3.2.6 features across 30 languages (README + FEATURES)
Build Electron Desktop App / Validate version (push) Failing after 36s
Build Electron Desktop App / Build Electron (macos-arm64) (push) Has been skipped
Build Electron Desktop App / Build Electron (linux) (push) Has been skipped
Build Electron Desktop App / Build Electron (macos-intel) (push) Has been skipped
Build Electron Desktop App / Build Electron (windows) (push) Has been skipped
Build Electron Desktop App / Create Release (push) Has been skipped
Build Electron Desktop App / Publish to npm (push) Has been skipped
2026-03-29 05:32:01 -03:00
Diego Rodrigues de Sa e Souza dc077bc309 Merge pull request #741 from diegosouzapw/release/v3.2.6
Build Electron Desktop App / Validate version (push) Failing after 43s
Build Electron Desktop App / Build Electron (macos-arm64) (push) Has been skipped
Build Electron Desktop App / Build Electron (linux) (push) Has been skipped
Build Electron Desktop App / Build Electron (macos-intel) (push) Has been skipped
Build Electron Desktop App / Build Electron (windows) (push) Has been skipped
Build Electron Desktop App / Create Release (push) Has been skipped
Build Electron Desktop App / Publish to npm (push) Has been skipped
chore(release): v3.2.6 — summary
2026-03-29 04:36:55 -03:00
diegosouzapw 0fd634ef43 chore(release): v3.2.6 — API Key Reveal, Sidebar Controls, Combo Health, Stream Logs 2026-03-29 04:34:55 -03:00
Randi d352b6b509 Scope API key reveal to Api Manager (#740) 2026-03-29 04:30:11 -03:00
Randi fcc48cc738 Add full sidebar visibility controls (#739) 2026-03-29 04:30:08 -03:00
Randi ec06a345cc Require live responses for combo tests (#735) 2026-03-29 04:30:06 -03:00
Randi 7690b364e7 fix detailed log summaries for streamed responses (#734) 2026-03-29 04:30:03 -03:00
Otto G b94c0c7d04 fix(sse): use x-api-key for opencode-go minimax messages requests (#733)
OpenCode Go mixes request protocols by model family:

   - `glm-5` and `kimi-k2.5` use OpenAI-style `/chat/completions`
   - `minimax-m2.5` and `minimax-m2.7` use Anthropic-style `/messages`

   OmniRoute already routed MiniMax Go models to `/messages`, but the
   executor still sent `Authorization: Bearer ...`, which caused upstream
   `401 Missing API key` errors.

   This changes `OpencodeExecutor` to send:
   - `x-api-key` + `anthropic-version` for Claude-targeted OpenCode Go requests
   - `Authorization: Bearer ...` for the remaining OpenCode Go request formats

   Also updates unit coverage to assert the correct header behavior for
   MiniMax Go models.

   Validated with:
   - direct curl repro against OpenCode Go endpoints
   - `node --import tsx/esm --test tests/unit/opencode-executor.test.mjs`
   - `npm run typecheck:core`
   - `npm run build`
2026-03-29 04:29:59 -03:00
Diego Souza 500bfdf588 ci: authorize packages write scopes for github packages 2026-03-29 02:06:28 -03:00
diegosouzapw d23b19c466 fix(core): prevent emergency fallback from masking original errors 2026-03-29 01:46:05 -03:00
Diego Rodrigues de Sa e Souza 3a5450039d Merge pull request #736 from diegosouzapw/release/v3.2.5
Build Electron Desktop App / Validate version (push) Failing after 40s
Build Electron Desktop App / Build Electron (macos-arm64) (push) Has been skipped
Build Electron Desktop App / Build Electron (linux) (push) Has been skipped
Build Electron Desktop App / Build Electron (macos-intel) (push) Has been skipped
Build Electron Desktop App / Build Electron (windows) (push) Has been skipped
Build Electron Desktop App / Create Release (push) Has been skipped
Build Electron Desktop App / Publish to npm (push) Has been skipped
chore(release): v3.2.5 — Void Linux support
2026-03-29 01:39:08 -03:00
diegosouzapw b582ddf090 chore(release): v3.2.5 — Void Linux support 2026-03-29 01:33:21 -03:00
diegosouzapw ef8b470e8b docs: merge issue #732 void linux template 2026-03-29 01:28:56 -03:00
diegosouzapw 5a0841a994 docs(i18n): sync USER_GUIDE.md to 30 languages with Void Linux template 2026-03-29 01:26:09 -03:00
diegosouzapw bd462c4e0b chore(release): bump version to v3.2.4
Build Electron Desktop App / Validate version (push) Failing after 42s
Build Electron Desktop App / Build Electron (macos-arm64) (push) Has been skipped
Build Electron Desktop App / Build Electron (linux) (push) Has been skipped
Build Electron Desktop App / Build Electron (macos-intel) (push) Has been skipped
Build Electron Desktop App / Build Electron (windows) (push) Has been skipped
Build Electron Desktop App / Create Release (push) Has been skipped
Build Electron Desktop App / Publish to npm (push) Has been skipped
2026-03-28 23:45:41 -03:00
Diego Rodrigues de Sa e Souza f11ec4e142 Merge pull request #731 from oyi77/fix/tool-call-invalid-argument-400
fix(translator): remove thoughtSignature from functionCall parts in all Gemini translators
2026-03-28 23:43:34 -03:00
diegosouzapw a5393a3ec4 feat: migrate iFlow provider to Qoder AI (#660) 2026-03-28 23:35:59 -03:00
Diego Souza bf76da3222 ci: enable ghcr build on main 2026-03-28 23:25:04 -03:00
Diego Rodrigues de Sa e Souza f171b7de96 Merge pull request #730 from diegosouzapw/release/v3.2.3
Build Electron Desktop App / Validate version (push) Failing after 40s
Build Electron Desktop App / Build Electron (macos-arm64) (push) Has been skipped
Build Electron Desktop App / Build Electron (linux) (push) Has been skipped
Build Electron Desktop App / Build Electron (macos-intel) (push) Has been skipped
Build Electron Desktop App / Build Electron (windows) (push) Has been skipped
Build Electron Desktop App / Create Release (push) Has been skipped
Build Electron Desktop App / Publish to npm (push) Has been skipped
chore(release): v3.2.3 — Enhancements and Bugfixes
2026-03-28 23:21:55 -03:00
diegosouzapw c0cbf00199 chore(release): v3.2.3 — Enhancements and Bugfixes 2026-03-28 23:19:01 -03:00
diegosouzapw 0cd6e59fb9 Merge cache-control fix and resolve changelog conflict 2026-03-28 23:13:03 -03:00
diegosouzapw 11a8adc71c Merge branch 'feat/issue-659-mobile-ui' 2026-03-28 23:12:26 -03:00
diegosouzapw b9c7fd879f fix(core): resolve routing schemas, CLI streaming leaks, and thinking tag extraction 2026-03-28 23:11:22 -03:00
Diego Rodrigues de Sa e Souza 2fc4c7ea33 Merge pull request #728 from rdself/codex/normalize-provider-limits-labels
normalize provider limits labels
2026-03-28 23:06:16 -03:00
oyi77 c5003665c3 fix(translator): remove thoughtSignature from functionCall parts in all Gemini translators
HTTP 400 "invalid argument" was triggered when OmniRoute translated tool calls
to Gemini format, because thoughtSignature was injected onto every functionCall
part unconditionally. Affects two code paths:

1. openai-to-gemini.ts — OpenAI tool_calls → Gemini functionCall
2. claude-to-gemini.ts — Claude tool_use blocks → Gemini functionCall

thoughtSignature is only valid on thinking/reasoning parts (those with
thought: true or thoughtSignature as their primary field). When present on a
functionCall part, the Gemini API returns HTTP 400 'invalid argument'.

The thinking parts that legitimately carry thoughtSignature (emitted when a
message has reasoning_content / thinking blocks) are untouched.

Regression tests (T43) cover:
- single tool call: no thoughtSignature on functionCall part (openai path)
- multiple tool calls: none carry thoughtSignature (openai path)
- thinking regression guard: thoughtSignature still on thought parts
- claude-to-gemini path: tool_use blocks produce clean functionCall parts

Fixes #724
2026-03-29 08:48:58 +07:00
R.D. 538028c150 normalize provider limits quota labels 2026-03-28 21:17:07 -04:00
diegosouzapw 94a00cb6d6 feat: improve dashboard layout for smaller screens (#659) 2026-03-28 21:53:07 -03:00
AveryanAlex fdaeccf1e5 fix: use replaceAll for think tags to handle multiple occurrences 2026-03-29 00:26:24 +03:00
AveryanAlex 7723e46c26 fix: emit reasoning_content in Responses→Chat streaming translation 2026-03-29 00:23:54 +03:00
AveryanAlex dce355cce6 fix: capture usage and accumulate output in response.completed event 2026-03-29 00:23:06 +03:00
AveryanAlex 213e7b7093 fix: handle deprecated function_call field and function role in Chat→Responses 2026-03-29 00:18:50 +03:00
AveryanAlex fe7d8f93a1 fix: stringify arguments and convert tool output content types 2026-03-29 00:17:49 +03:00
AveryanAlex 9e2f4216f9 fix: reject all non-function tool types in Responses→Chat translation 2026-03-29 00:16:59 +03:00
AveryanAlex a48f7b2222 fix: translate tool_choice object format between Responses and Chat APIs 2026-03-29 00:14:26 +03:00
AveryanAlex 0b85d8a9bc fix: translate input_file↔file content parts 2026-03-29 00:12:18 +03:00
AveryanAlex 58d6938065 fix: translate input_image↔image_url with detail preservation 2026-03-29 00:11:25 +03:00
AveryanAlex a536a2b822 refactor: consolidate responsesApiHelper to delegate to main translator 2026-03-29 00:09:54 +03:00
tombii b84c915b23 fix(sse): preserve cache_control in Claude passthrough mode
When Claude Code routes through OmniRoute (Claude → OmniRoute → Claude),
OmniRoute was stripping all cache_control markers and replacing them with
its own generic caching strategy. This broke Claude Code's carefully
placed cache breakpoints for plans and other features.

Changes:
- Add preserveCacheControl parameter to prepareClaudeRequest()
- Detect Claude passthrough mode (sourceFormat === targetFormat === CLAUDE)
- Skip cache_control normalization when preserveCacheControl=true
- Preserve client's cache_control markers in system, messages, and tools

This ensures Claude Code's prompt caching optimization works correctly
while maintaining OmniRoute's caching strategy for translation scenarios.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-28 16:30:41 +01:00
AveryanAlex 769be46bf9 fix: ensure Codex passthrough path sets instructions and store=false
The native Codex passthrough path returned early before injecting
default instructions and enforcing store=false. Clients sending
Responses API requests without instructions (e.g. opencode) got
400 "Instructions are required", and requests missing store=false
got 400 "Store must be set to false" from the Codex upstream.

Move both assignments before the passthrough return so they apply
to all code paths.
2026-03-27 19:40:55 +03:00
465 changed files with 61294 additions and 24636 deletions
+12 -1
View File
@@ -96,7 +96,18 @@ Keep an empty `## [Unreleased]` section above it.
// turbo
```bash
VERSION=$(node -p "require('./package.json').version") && sed -i "s/ version: .*/ version: $VERSION/" docs/openapi.yaml && echo "✓ openapi.yaml → $VERSION"
VERSION=$(node -p "require('./package.json').version")
sed -i "s/ version: .*/ version: $VERSION/" docs/openapi.yaml
echo "✓ openapi.yaml → $VERSION"
for dir in electron open-sse; do
if [ -d "$dir" ] && [ -f "$dir/package.json" ]; then
(cd "$dir" && npm version "$VERSION" --no-git-tag-version --allow-same-version > /dev/null)
echo "$dir/package.json → $VERSION"
fi
done
# Re-run install to assert the workspace lockfile is updated
npm install
```
### 6. Update README.md and i18n docs
+14 -4
View File
@@ -19,11 +19,21 @@ This workflow fetches all open issues from the project's GitHub repository, clas
### 2. Fetch All Open Issues
// turbo
// turbo-all
- Run: `gh issue list --repo <owner>/<repo> --state open --limit 500 --json number,title,labels,body,comments,createdAt,author`
- Parse the JSON output to get a list of **all** open issues
- Sort by oldest first (FIFO)
**⚠️ CRITICAL**: The JSON output of `gh issue list` can be truncated by the tool, silently hiding issues. You MUST use the two-step approach below to guarantee **all** issues are fetched.
**Step 2a — Get Issue numbers only** (small output, never truncated):
- Run: `gh issue list --repo <owner>/<repo> --state open --limit 500 --json number --jq '.[].number'`
- This outputs one issue number per line. Count them and confirm total.
**Step 2b — Fetch full metadata for each Issue** (one call per issue):
- For each issue number from step 2a, run:
`gh issue view <NUMBER> --repo <owner>/<repo> --json number,title,labels,body,comments,createdAt,author`
- You may batch these into parallel calls (up to 4 at a time).
- Sort by oldest first (FIFO).
### 3. Classify Each Issue
+22 -4
View File
@@ -18,17 +18,35 @@ This workflow fetches all open PRs from the project's GitHub repository, perform
### 2. Fetch Open Pull Requests
// turbo
// turbo-all
**⚠️ CRITICAL**: The JSON output of `gh pr list` can be truncated by the tool, silently hiding PRs. You MUST use the two-step approach below to guarantee **all** PRs are fetched.
**Step 2a — Get PR numbers only** (small output, never truncated):
- Run: `gh pr list --repo <owner>/<repo> --state open --limit 500 --json number --jq '.[].number'`
- This outputs one PR number per line. Count them and confirm total.
**Step 2b — Fetch full metadata for each PR** (one call per PR):
- For each PR number from step 2a, run:
`gh pr view <NUMBER> --repo <owner>/<repo> --json number,title,author,headRefName,body,createdAt,additions,deletions,files`
- You may batch these into parallel calls (up to 4 at a time).
**Step 2c — Fetch diffs for each PR** (one call per PR, saved to /tmp):
- For each PR number, run:
`gh pr diff <NUMBER> --repo <owner>/<repo> > /tmp/pr<NUMBER>.diff`
- Then read each diff file with `view_file`.
- Run: `gh pr list --repo <owner>/<repo> --state open --limit 500 --json number,title,author,headRefName,body,createdAt,additions,deletions,files`
- This fetches **all** open PRs without restriction. Get the diff for each with:
`gh pr diff <NUMBER> --repo <owner>/<repo>`
- For each open PR, collect:
- PR number, title, author, branch, number of commits, date
- PR description/body
- Files changed (diff)
- Existing review comments (from bots or humans)
**Verification**: Confirm the count of PRs analyzed matches the count from step 2a before proceeding.
### 3. Analyze Each PR — For each open PR, perform the following analysis:
#### 3a. Feature Assessment
+4 -3
View File
@@ -40,6 +40,7 @@ MACHINE_ID_SALT=endpoint-proxy-salt
ENABLE_REQUEST_LOGS=false
AUTH_COOKIE_SECURE=false
REQUIRE_API_KEY=false
ALLOW_API_KEY_REVEAL=false
# Input Sanitizer (FASE-01 — prompt injection & PII protection)
# INPUT_SANITIZER_ENABLED=true
@@ -127,8 +128,8 @@ GEMINI_CLI_OAUTH_CLIENT_SECRET=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
# CODEX_OAUTH_CLIENT_ID=
# CODEX_OAUTH_CLIENT_SECRET=
# QWEN_OAUTH_CLIENT_ID=
# IFLOW_OAUTH_CLIENT_ID=
IFLOW_OAUTH_CLIENT_SECRET=4Z3YjXycVsQvyGF1etiNlIBB4RsqSDtW
# QODER_OAUTH_CLIENT_ID=
QODER_OAUTH_CLIENT_SECRET=4Z3YjXycVsQvyGF1etiNlIBB4RsqSDtW
# ─────────────────────────────────────────────────────────────────────────────
# Provider User-Agent Overrides (optional — customize per-provider UA headers)
@@ -141,7 +142,7 @@ CODEX_USER_AGENT=codex-cli/0.92.0 (Windows 10.0.26100; x64)
GITHUB_USER_AGENT=GitHubCopilotChat/0.26.7
ANTIGRAVITY_USER_AGENT=antigravity/1.104.0 darwin/arm64
KIRO_USER_AGENT=AWS-SDK-JS/3.0.0 kiro-ide/1.0.0
IFLOW_USER_AGENT=iFlow-Cli
QODER_USER_AGENT=Qoder-Cli
QWEN_USER_AGENT=QwenCode/0.12.3 (linux; x64)
CURSOR_USER_AGENT=connect-es/1.6.1
GEMINI_CLI_USER_AGENT=google-api-nodejs-client/9.15.1
+16 -16
View File
@@ -18,8 +18,8 @@ jobs:
name: Lint
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v6
- uses: actions/setup-node@v6
- uses: actions/checkout@v4
- uses: actions/setup-node@v4
with:
node-version: 22
cache: npm
@@ -36,8 +36,8 @@ jobs:
name: Security Audit
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v6
- uses: actions/setup-node@v6
- uses: actions/checkout@v4
- uses: actions/setup-node@v4
with:
node-version: 22
cache: npm
@@ -55,8 +55,8 @@ jobs:
matrix:
node-version: [20, 22]
steps:
- uses: actions/checkout@v6
- uses: actions/setup-node@v6
- uses: actions/checkout@v4
- uses: actions/setup-node@v4
with:
node-version: ${{ matrix.node-version }}
cache: npm
@@ -74,8 +74,8 @@ jobs:
JWT_SECRET: ci-test-secret-with-sufficient-length-for-validation
API_KEY_SECRET: ci-test-api-key-secret-long
steps:
- uses: actions/checkout@v6
- uses: actions/setup-node@v6
- uses: actions/checkout@v4
- uses: actions/setup-node@v4
with:
node-version: ${{ matrix.node-version }}
cache: npm
@@ -90,8 +90,8 @@ jobs:
JWT_SECRET: ci-test-secret-with-sufficient-length-for-validation
API_KEY_SECRET: ci-test-api-key-secret-long
steps:
- uses: actions/checkout@v6
- uses: actions/setup-node@v6
- uses: actions/checkout@v4
- uses: actions/setup-node@v4
with:
node-version: 22
cache: npm
@@ -109,8 +109,8 @@ jobs:
JWT_SECRET: ci-test-secret-with-sufficient-length-for-validation
API_KEY_SECRET: ci-test-api-key-secret-long
steps:
- uses: actions/checkout@v6
- uses: actions/setup-node@v6
- uses: actions/checkout@v4
- uses: actions/setup-node@v4
with:
node-version: 22
cache: npm
@@ -129,8 +129,8 @@ jobs:
INITIAL_PASSWORD: ci-test-password-for-integration
DATA_DIR: /tmp/omniroute-ci
steps:
- uses: actions/checkout@v6
- uses: actions/setup-node@v6
- uses: actions/checkout@v4
- uses: actions/setup-node@v4
with:
node-version: 22
cache: npm
@@ -145,8 +145,8 @@ jobs:
JWT_SECRET: ci-test-secret-with-sufficient-length-for-validation
API_KEY_SECRET: ci-test-api-key-secret-long
steps:
- uses: actions/checkout@v6
- uses: actions/setup-node@v6
- uses: actions/checkout@v4
- uses: actions/setup-node@v4
with:
node-version: 22
cache: npm
+11 -7
View File
@@ -1,6 +1,9 @@
name: Publish to Docker Hub
on:
push:
branches:
- main
release:
types: [published]
workflow_dispatch:
@@ -12,6 +15,7 @@ on:
permissions:
contents: read
packages: write
jobs:
docker:
@@ -21,24 +25,24 @@ jobs:
IMAGE_NAME: diegosouzapw/omniroute
steps:
- name: Checkout
uses: actions/checkout@v6
uses: actions/checkout@v4
with:
ref: ${{ github.event_name == 'workflow_dispatch' && format('refs/tags/v{0}', inputs.version) || '' }}
- name: Set up QEMU (for multi-arch builds)
uses: docker/setup-qemu-action@v4
uses: docker/setup-qemu-action@v3
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v4
uses: docker/setup-buildx-action@v3
- name: Login to Docker Hub
uses: docker/login-action@v4
uses: docker/login-action@v3
with:
username: ${{ secrets.DOCKERHUB_USERNAME }}
password: ${{ secrets.DOCKERHUB_TOKEN }}
- name: Login to GitHub Container Registry
uses: docker/login-action@v4
uses: docker/login-action@v3
with:
registry: ghcr.io
username: ${{ github.actor }}
@@ -57,7 +61,7 @@ jobs:
echo "Publishing Docker image: $IMAGE_NAME:$VERSION"
- name: Build and push multi-arch image
uses: docker/build-push-action@v7
uses: docker/build-push-action@v6
with:
context: .
target: runner-base
@@ -79,7 +83,7 @@ jobs:
docker buildx imagetools inspect "${{ env.IMAGE_NAME }}:${{ steps.version.outputs.version }}"
- name: Update Docker Hub description
uses: peter-evans/dockerhub-description@v5
uses: peter-evans/dockerhub-description@v4
with:
username: ${{ secrets.DOCKERHUB_USERNAME }}
password: ${{ secrets.DOCKERHUB_TOKEN }}
+9 -7
View File
@@ -13,6 +13,8 @@ on:
permissions:
contents: write
id-token: write
packages: write
jobs:
validate:
@@ -22,7 +24,7 @@ jobs:
version: ${{ steps.validate.outputs.version }}
steps:
- name: Checkout code
uses: actions/checkout@v6
uses: actions/checkout@v4
with:
fetch-depth: 0
@@ -70,16 +72,16 @@ jobs:
steps:
- name: Checkout
uses: actions/checkout@v6
uses: actions/checkout@v4
- name: Setup Node.js
uses: actions/setup-node@v6
uses: actions/setup-node@v4
with:
node-version: 22
cache: npm
- name: Cache node_modules
uses: actions/cache@v5
uses: actions/cache@v4
with:
path: node_modules
key: ${{ runner.os }}-node-${{ hashFiles('package-lock.json') }}
@@ -146,7 +148,7 @@ jobs:
fi
- name: Upload artifacts
uses: actions/upload-artifact@v7
uses: actions/upload-artifact@v4
with:
name: electron-${{ matrix.platform }}
path: release-assets/
@@ -157,12 +159,12 @@ jobs:
runs-on: ubuntu-latest
steps:
- name: Checkout
uses: actions/checkout@v6
uses: actions/checkout@v4
with:
fetch-depth: 0
- name: Download all artifacts
uses: actions/download-artifact@v8
uses: actions/download-artifact@v4
with:
path: release-assets
merge-multiple: true
+14 -12
View File
@@ -35,6 +35,7 @@ on:
permissions:
contents: read
id-token: write
packages: write
jobs:
publish:
@@ -42,10 +43,10 @@ jobs:
environment: NPM_TOKEN
steps:
- name: Checkout
uses: actions/checkout@v6
uses: actions/checkout@v4
- name: Setup Node.js
uses: actions/setup-node@v6
uses: actions/setup-node@v4
with:
node-version: 22
registry-url: https://registry.npmjs.org
@@ -56,17 +57,18 @@ jobs:
- name: Resolve version and dist-tag
id: resolve
run: |
case "${{ github.event_name }}" in
workflow_dispatch|workflow_call)
VERSION="${{ inputs.version }}"
TAG="${{ inputs.tag }}"
;;
release)
VERSION="${{ inputs.version }}"
TAG="${{ inputs.tag }}"
if [ -z "$VERSION" ]; then
if [ "${{ github.event_name }}" = "release" ]; then
VERSION="${GITHUB_REF_NAME}"
;;
esac
fi
fi
# Strip v prefix if present
VERSION="${VERSION#v}"
# Default dist-tag logic
if [ -z "$TAG" ]; then
if [[ "$VERSION" == *-* ]]; then
@@ -110,11 +112,11 @@ jobs:
run: |
VERSION="${{ steps.resolve.outputs.version }}"
TAG="${{ steps.resolve.outputs.tag }}"
echo "Configuring for GitHub Packages..."
echo "//npm.pkg.github.com/:_authToken=${{ secrets.GITHUB_TOKEN }}" > .npmrc
npm pkg set name="@diegosouzapw/omniroute"
if [ "$TAG" = "latest" ]; then
npm publish --registry=https://npm.pkg.github.com || echo "⚠️ Version ${VERSION} might already be published on GitHub."
else
+43
View File
@@ -0,0 +1,43 @@
name: Sync Upstream
on:
schedule:
# Run every 6 hours
- cron: '0 */6 * * *'
workflow_dispatch:
permissions:
contents: write
jobs:
sync:
name: Sync with upstream
runs-on: ubuntu-latest
steps:
- name: Checkout
uses: actions/checkout@v4
with:
fetch-depth: 0
token: ${{ secrets.GITHUB_TOKEN }}
- name: Configure Git
run: |
git config user.name "github-actions[bot]"
git config user.email "github-actions[bot]@users.noreply.github.com"
- name: Fetch upstream
run: |
git remote add upstream https://github.com/diegosouzapw/OmniRoute.git || true
git fetch upstream
git fetch origin
- name: Sync main branch
run: |
git checkout main
git merge upstream/main --no-edit || {
echo "Merge conflict detected. Manual intervention required."
exit 1
}
- name: Push changes
run: git push https://x-access-token:${{ secrets.GITHUB_TOKEN }}@github.com/tombii/OmniRoute.git main
+9
View File
@@ -47,3 +47,12 @@ AGENTS.md
# Build artifacts (pre-built goes inside app/)
.next/
node_modules/
# Ignore large binary files and other build directories
*.tgz
*.AppImage
*.deb
*.rpm
electron/
app/electron/
app/vscode-extension/
+217 -7
View File
@@ -4,6 +4,216 @@
---
## [3.3.8] - 2026-03-30
### 🚀 Features
- **Models API Filtering:** Endpoint `/v1/models` now dynamically filters its list based on the permissions tied to the `Authorization: Bearer <token>` when restricted access is on (#781)
- **Qoder Integration:** Native integration for Qoder AI natively replacing the legacy iFlow platform mappings (#660)
- **Prompt Cache Tracking:** Added tracking capabilities and frontend visualization (Stats card) for semantic and prompt caching in the Dashboard UI
### 🐛 Bug Fixes
- **Cache Dashboard Sizing:** Improved the UI layout sizes and context headers for the advanced cache pages (#835)
- **Debug Sidebar Visibility:** Fixed an issue where the debug toggle wouldn't correctly show/hide sidebar debug details (#834)
- **Gemini Model Prefixing:** Modified the namespace fallback to properly route via `gemini-cli/` instead of `gc/` to respect upstream specs (#831)
- **OpenRouter Sync:** Improved compatibility synchronization to automatically ingest the available models catalog correctly from OpenRouter (#830)
- **Streaming Payloads Mapping:** Reserialization of reasoning fields natively resolves conflict alias paths when output is streaming to edge devices
---
## [3.3.7] - 2026-03-30
### 🐛 Bug Fixes
- **OpenCode Config:** Restructured generated `opencode.json` to use the `@ai-sdk/openai-compatible` record-based schema with `options` and `models` as object maps instead of flat arrays, fixing config validation failures (#816)
- **i18n Missing Keys:** Added missing `cloudflaredUrlNotice` translation key across all 30 language files to prevent `MISSING_MESSAGE` console errors in the Endpoint page (#823)
---
## [3.3.6] - 2026-03-30
### 🐛 Bug Fixes
- **Token Accounting:** Included prompt cache tokens safely in historical usage inputs calculations for correct quota deductions (PR #822)
- **Combo Test Probes:** Fixed combo testing logic false negatives by resolving parsing for reasoning-only responses and enabled massive parallelization via Promise.all (PR #828)
- **Docker Quick Tunnels:** Embedded required ca-certificates inside the base runtime container to resolve Cloudflared TLS startup failures, and surfaced stdout network errors replacing generic exit codes (PR #829)
---
## [3.3.5] - 2026-03-30
### ✨ New Features
- **Gemini Quota Tracking:** Added real-time Gemini CLI quota tracking via the `retrieveUserQuota` API (PR #825)
- **Cache Dashboard:** Enhanced the Cache Dashboard to display prompt cache metrics, 24h trends, and estimated cost savings (PR #824)
### 🐛 Bug Fixes
- **User Experience:** Removed invasive auto-opening OAuth modal loops on barren provider detailed pages (PR #820)
- **Dependency Updates:** Bumped and locked down dependencies for development and production trees including Next.js 16.2.1, Recharts, and TailwindCSS 4.2.2 (PR #826, #827)
---
## [3.3.4] - 2026-03-30
### ✨ New Features
- **A2A Workflows:** Added deterministic FSM orchestrator for multi-step agent workflows.
- **Graceful Degradation:** Added a new multi-layer fallback framework to preserve core functionality during partial system outages.
- **Config Audit:** Added an audit trail with diff detection to track changes and enable configuration rollbacks.
- **Provider Health:** Added provider expiration tracking with proactive UI alerts for expiring API keys.
- **Adaptive Routing:** Added an adaptive volume and complexity detector to override routing strategies dynamically based on load.
- **Provider Diversity:** Implemented provider diversity scoring via Shannon entropy to improve load distribution.
- **Auto-Disable Bounds:** Added an Auto-Disable Banned Accounts setting toggle to the Resilience dashboard.
### 🐛 Bug Fixes
- **Codex & Claude Compatibility:** Fixed UI fallbacks, patched Codex non-streaming integration issues, and resolved CLI runtime detection on Windows.
- **Release Automation:** Expanded permissions required for the Electron App build in GitHub Actions.
- **Cloudflare Runtime:** Addressed correct runtime isolation exit codes for Cloudflared tunnel components.
### 🧪 Tests
- **Test Suite Updates:** Expanded test coverage for volume detectors, provider diversity, configuration audit, and FSM.
---
## [3.3.3] - 2026-03-29
### 🐛 Bug Fixes
- **CI/CD Reliability:** Patched GitHub Actions to stable dependency versions (`actions/checkout@v4`, `actions/upload-artifact@v4`) to mitigate unannounced builder environment deprecations.
- **Image Fallbacks:** Replaced arbitrary fallback chains in `ProviderIcon.tsx` with explicit asset validation to prevent UI loading `<Image>` components for files that don't exist, eliminating `404` errors in dashboard console logs (#745).
- **Admin Updater:** Dynamic source-installation detection for the dashboard Updater. Safely disables the `Update Now` button when OmniRoute is built locally rather than through npm, prompting for `git pull` (#743).
- **Update ERESOLVE Error:** Injected `package.json` overrides for `react`/`react-dom` and enabled `--legacy-peer-deps` within the internal automatic updater scripts to resolve breaking dependency tree conflicts with `@lobehub/ui`.
---
## [3.3.2] - 2026-03-29
### ✨ New Features
- **Cloudflare Tunnels:** Cloudflare Quick Tunnel integration with dashboard controls (PR #772).
- **Diagnostics:** Semantic cache bypass for combo live tests (PR #773).
### 🐛 Bug Fixes
- **Streaming Stability:** Apply `FETCH_TIMEOUT_MS` to streaming requests' initial `fetch()` call to prevent 300s Node.js TCP timeout causing silent task failures (#769).
- **i18n:** Add missing `windsurf` and `copilot` entries to `toolDescriptions` across all 33 locale files (#748).
- **GLM Coding Audit:** Complete provider audit fixing ReDoS vulnerabilities, context window sizing (128k/16k), and model registry syncing (PR #778).
---
## [3.3.1] - 2026-03-29
### 🐛 Bug Fixes
- **OpenAI Codex:** Fallback processing fix for `type: "text"` elements carrying null or empty datasets that caused 400 rejection (#742).
- **Opencode:** Update schema alignment to singular `provider` to match official spec (#774).
- **Gemini CLI:** Inject missing end-user quota headers preventing 403 authorization lockouts (#775).
- **DB Recovery:** Refactor multipart payload imports into raw binary buffered arrays to bypass reverse proxy max body limits (#770).
---
## [3.3.0] - 2026-03-29
### ✨ Enhancements & Refactoring
- **Release Stabilization** — Finalized v3.2.9 release (combo diagnostics, quality gates, Gemini tool fix) and created missing git tag. Consolidated all staged changes into a single atomic release commit.
### 🐛 Bug Fixes
- **Auto-Update Test** — Fixed `buildDockerComposeUpdateScript` test assertion to match unexpanded shell variable references (`$TARGET_TAG`, `${TARGET_TAG#v}`) in the generated deploy script, aligning with the refactored template from v3.2.8.
- **Circuit Breaker Test** — Hardened `combo-circuit-breaker.test.mjs` by injecting `maxRetries: 0` to prevent retry inflation from skewing failure count assertions during breaker state transitions.
---
## [3.2.9] - 2026-03-29
### ✨ Enhancements & Refactoring
- **Combo Diagnostics** — Introduced a live test bypass flag (`forceLiveComboTest`) allowing administrators to execute real upstream health checks that bypass all local circuit-breaker and cooldown state mechanisms, enabling precise diagnostics during rolling outages (PR #759)
- **Quality Gates** — Added automated response quality validation for combos and officially integrated `claude-4.6` model support into the core routing schemas (PR #762)
### 🐛 Bug Fixes
- **Tool Definition Validation** — Repaired Gemini API integration by normalizing enum types inside tool definitions, preventing upstream HTTP 400 parameter errors (PR #760)
---
## [3.2.8] - 2026-03-29
### ✨ Enhancements & Refactoring
- **Docker Auto-Update UI** — Integrated a detached background update process for Docker Compose deployments. The Dashboard UI now seamlessly tracks update lifecycle events combining JSON REST responses with SSE streaming progress overlays for robust cross-environment reliability.
- **Cache Analytics** — Repaired zero-metrics visualization mapping by migrating Semantic Cache telemetry logs directly into the centralized tracking SQLite module.
### 🐛 Bug Fixes
- **Authentication Logic** — Fixed a bug where saving dashboard settings or adding models failed with a 401 Unauthorized error when `requireLogin` was disabled. API endpoints now correctly evaluate the global authentication toggle. Resolved global redirection by reactivating `src/middleware.ts`.
- **CLI Tool Detection (Windows)** — Prevented fatal initialization exceptions during CLI environment detection by catching `cross-spawn` ENOENT errors correctly. Adds explicit detection paths for `\AppData\Local\droid\droid.exe`.
- **Codex Native Passthrough** — Normalized model translation parameters preventing context poisoning in proxy pass-through mode, enforcing generic `store: false` constraints explicitly for all Codex-originated requests.
- **SSE Token Reporting** — Normalized provider tool-call chunk `finish_reason` detection, fixing 0% Usage analytics for stream-only responses missing strict `<DONE>` indicators.
- **DeepSeek <think> Tags** — Implemented an explicit `<think>` extraction mapping inside `responsesHandler.ts`, ensuring DeepSeek reasoning streams map equivalently to native Anthropic `<thinking>` structures.
---
## [3.2.7] - 2026-03-29
### Fixed
- **Seamless UI Updates**: The "Update Now" feature on the Dashboard now provides live, transparent feedback using Server-Sent Events (SSE). It performs package installation, native module rebuilds (better-sqlite3), and PM2 restarts reliably while showing real-time loaders instead of silently hanging.
---
## [3.2.6] — 2026-03-29
### ✨ Enhancements & Refactoring
- **API Key Reveal (#740)** — Added a scoped API key copy flow in the Api Manager, protected by the `ALLOW_API_KEY_REVEAL` environment variable.
- **Sidebar Visibility Controls (#739)** — Admins can now hide any sidebar navigation link via the Appearance settings to reduce visual clutter.
- **Strict Combo Testing (#735)** — Hardened the combo health check endpoint to require live text responses from models instead of just soft reachability signals.
- **Streamed Detailed Logs (#734)** — Switched detailed request logging for SSE streams to reconstruct the final payload, saving immense amounts of SQLite database size and significantly cleaning up the UI.
### 🐛 Bug Fixes
- **OpenCode Go MiniMax Auth (#733)** — Corrected the authentication header logic for `minimax` models on OpenCode Go to use `x-api-key` instead of standard bearer tokens across the `/messages` protocol.
---
## [3.2.5] — 2026-03-29
### ✨ Enhancements & Refactoring
- **Void Linux Deployment Support (#732)** — Integrated `xbps-src` packaging template and instructions to natively compile and install OmniRoute with `better-sqlite3` bindings via cross-compilation target.
## [3.2.4] — 2026-03-29
### ✨ Enhancements & Refactoring
- **Qoder AI Migration (#660)** — Completely migrated the legacy `iFlow` core provider onto `Qoder AI` maintaining stable API routing capabilities.
### 🐛 Bug Fixes
- **Gemini Tools HTTP 400 Payload Invalid Argument (#731)** — Prevented `thoughtSignature` array injections inside standard Gemini `functionCall` sequences blocking agentic routing flows.
---
## [3.2.3] — 2026-03-29
### ✨ Enhancements & Refactoring
- **Provider Limits Quota UI (#728)** — Normalized quota limit logic and data labeling inside the Limits interface.
### 🐛 Bug Fixes
- **Core Routing Schemas & Leaks** — Expanded `comboStrategySchema` to natively support `fill-first` and `p2c` strategies to unblock complex combo editing natively.
- **Thinking Tags Extraction (CLI)** — Restructured CLI token responses sanitizer RegEx capturing model reasoning structures inside streams avoiding broken `<thinking>` extractions breaking response text output format.
- **Strict Format Enforcements** — Hardened pipeline sanitization execution making it universally apply to translation mode targets.
---
## [3.2.2] — 2026-03-29
### ✨ New Features
@@ -1789,7 +1999,7 @@ OmniRoute now automatically refreshes model lists for connected providers every
- **fix(media)**: ComfyUI and SD WebUI no longer appear in the Media page provider list when unconfigured — fetches `/api/providers` on mount and hides local providers with no connections (#390)
- **fix(auth)**: Round-robin no longer re-selects rate-limited accounts immediately after cooldown — `backoffLevel` is now used as primary sort key in the LRU rotation (#340)
- **fix(oauth)**: iFlow (and other providers that redirect to their own UI) no longer leave the OAuth modal stuck at "Waiting for Authorization" — popup-closed detector auto-transitions to manual URL input mode (#344)
- **fix(oauth)**: Qoder (and other providers that redirect to their own UI) no longer leave the OAuth modal stuck at "Waiting for Authorization" — popup-closed detector auto-transitions to manual URL input mode (#344)
- **fix(logs)**: Request log table is now readable in light mode — status badges, token counts, and combo tags use adaptive `dark:` color classes (#378)
### ✨ Features
@@ -1941,7 +2151,7 @@ OmniRoute now automatically refreshes model lists for connected providers every
### ✨ New Features
- **Fill-First & P2C Routing Strategies**: Added `fill-first` (drain quota before moving on) and `p2c` (Power-of-Two-Choices low-latency selection) to combo strategy picker, with full guidance panels and color-coded badges.
- **Free Stack Preset Models**: Creating a combo with the Free Stack template now auto-fills 7 best-in-class free provider models (Gemini CLI, Kiro, iFlow×2, Qwen, NVIDIA NIM, Groq). Users just activate the providers and get a $0/month combo out-of-the-box.
- **Free Stack Preset Models**: Creating a combo with the Free Stack template now auto-fills 7 best-in-class free provider models (Gemini CLI, Kiro, Qoder×2, Qwen, NVIDIA NIM, Groq). Users just activate the providers and get a $0/month combo out-of-the-box.
- **Wider Combo Modal**: Create/Edit combo modal now uses `max-w-4xl` for comfortable editing of large combos.
### 🐛 Bug Fixes
@@ -2007,7 +2217,7 @@ OmniRoute now automatically refreshes model lists for connected providers every
### ✨ Features
- **Combos: Free Stack template** — New 4th template "Free Stack ($0)" using round-robin across Kiro + iFlow + Qwen + Gemini CLI. Suggests the pre-built zero-cost combo on first use.
- **Combos: Free Stack template** — New 4th template "Free Stack ($0)" using round-robin across Kiro + Qoder + Qwen + Gemini CLI. Suggests the pre-built zero-cost combo on first use.
- **Media/Transcription: Deepgram as default** — Deepgram (Nova 3, $200 free) is now the default transcription provider. AssemblyAI ($50 free) and Groq Whisper (free forever) shown with free credit badges.
- **README: "Start Free" section** — New early-README 5-step table showing how to set up zero-cost AI in minutes.
- **README: Free Transcription Combo** — New section with Deepgram/AssemblyAI/Groq combo suggestion and per-provider free credit details.
@@ -2019,9 +2229,9 @@ OmniRoute now automatically refreshes model lists for connected providers every
### 📖 Documentation
- **README: 44+ Providers** — Updated all 3 occurrences of "36+ providers" to "44+" reflecting the actual codebase count (44 providers in providers.ts)
- **README: New Section "🆓 Free Models — What You Actually Get"** — Added 7-provider table with per-model rate limits for: Kiro (Claude unlimited via AWS Builder ID), iFlow (5 models unlimited), Qwen (4 models unlimited), Gemini CLI (180K/mo), NVIDIA NIM (~40 RPM dev-forever), Cerebras (1M tok/day / 60K TPM), Groq (30 RPM / 14.4K RPD). Includes the \/usr/bin/bash Ultimate Free Stack combo recommendation.
- **README: Pricing Table Updated** — Added Cerebras to API KEY tier, fixed NVIDIA from "1000 credits" to "dev-forever free", updated iFlow/Qwen model counts and names
- **README: iFlow 8→5 models** (named: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2)
- **README: New Section "🆓 Free Models — What You Actually Get"** — Added 7-provider table with per-model rate limits for: Kiro (Claude unlimited via AWS Builder ID), Qoder (5 models unlimited), Qwen (4 models unlimited), Gemini CLI (180K/mo), NVIDIA NIM (~40 RPM dev-forever), Cerebras (1M tok/day / 60K TPM), Groq (30 RPM / 14.4K RPD). Includes the \/usr/bin/bash Ultimate Free Stack combo recommendation.
- **README: Pricing Table Updated** — Added Cerebras to API KEY tier, fixed NVIDIA from "1000 credits" to "dev-forever free", updated Qoder/Qwen model counts and names
- **README: Qoder 8→5 models** (named: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2)
- **README: Qwen 3→4 models** (named: qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next, vision-model)
## [2.3.15] - 2026-03-13
@@ -2035,7 +2245,7 @@ OmniRoute now automatically refreshes model lists for connected providers every
### 🐛 Bug Fixes
- **iFlow OAuth (#339)**: Restored the valid default `clientSecret` — was previously an empty string, causing "Bad client credentials" on every connect attempt. The public credential is now the default fallback (overridable via `IFLOW_OAUTH_CLIENT_SECRET` env var).
- **Qoder OAuth (#339)**: Restored the valid default `clientSecret` — was previously an empty string, causing "Bad client credentials" on every connect attempt. The public credential is now the default fallback (overridable via `QODER_OAUTH_CLIENT_SECRET` env var).
- **MITM server not found (#335)**: `prepublish.mjs` now compiles `src/mitm/*.ts` to JavaScript using `tsc` before copying to the npm bundle. Previously only raw `.ts` files were copied — meaning `server.js` never existed in npm/Volta global installs.
- **GeminiCLI missing projectId (#338)**: Instead of throwing a hard 500 error when `projectId` is missing from stored credentials (e.g. after Docker restart), OmniRoute now logs a warning and attempts the request — returning a meaningful provider-side error instead of an OmniRoute crash.
- **Electron version mismatch (#323)**: Synced `electron/package.json` version to `2.3.13` (was `2.0.13`) so the desktop binary version matches the npm package.
+3 -3
View File
@@ -2,7 +2,7 @@ FROM node:22-bookworm-slim AS builder
WORKDIR /app
RUN apt-get update \
&& apt-get install -y --no-install-recommends libsecret-1-0 \
&& apt-get install -y --no-install-recommends libsecret-1-0 ca-certificates \
&& rm -rf /var/lib/apt/lists/*
COPY package*.json ./
@@ -30,7 +30,7 @@ ENV NODE_OPTIONS="--max-old-space-size=256"
# Data directory inside Docker — must match the volume mount in docker-compose.yml
ENV DATA_DIR=/app/data
RUN apt-get update \
&& apt-get install -y --no-install-recommends libsecret-1-0 \
&& apt-get install -y --no-install-recommends libsecret-1-0 ca-certificates \
&& rm -rf /var/lib/apt/lists/*
RUN mkdir -p /app/data
@@ -60,7 +60,7 @@ FROM runner-base AS runner-cli
# Install system dependencies required by openclaw (git+ssh references).
RUN apt-get update \
&& apt-get install -y --no-install-recommends git ca-certificates \
&& apt-get install -y --no-install-recommends git ca-certificates docker.io docker-compose \
&& rm -rf /var/lib/apt/lists/* \
&& git config --system url."https://github.com/".insteadOf "ssh://git@github.com/"
+27 -25
View File
@@ -199,7 +199,7 @@ _قم بتوصيل أي أداة IDE أو CLI مدعومة بالذكاء الا
npm run system-info
```
يؤدي هذا إلى إنشاء `system-info.txt` مع إصدار Node.js، وإصدار OmniRoute، وتفاصيل نظام التشغيل، وأدوات CLI المثبتة (iflow، وgemini، و claude، وcodex، وantigravity، وdroid، وما إلى ذلك)، وحالة Docker/PM2، وحزم النظام - كل ما نحتاجه لإعادة إنتاج مشكلتك بسرعة. قم بإرفاق الملف مباشرة بمشكلة GitHub الخاصة بك.
يؤدي هذا إلى إنشاء `system-info.txt` مع إصدار Node.js، وإصدار OmniRoute، وتفاصيل نظام التشغيل، وأدوات CLI المثبتة (qoder، وgemini، و claude، وcodex، وantigravity، وdroid، وما إلى ذلك)، وحالة Docker/PM2، وحزم النظام - كل ما نحتاجه لإعادة إنتاج مشكلتك بسرعة. قم بإرفاق الملف مباشرة بمشكلة GitHub الخاصة بك.
---
@@ -225,7 +225,7 @@ npm run system-info
│ ↓ budget limit
├─→ [Tier 3: CHEAP] GLM ($0.6/1M), MiniMax ($0.2/1M)
│ ↓ budget limit
└─→ [Tier 4: FREE] iFlow, Qwen, Kiro (unlimited)
└─→ [Tier 4: FREE] Qoder, Qwen, Kiro (unlimited)
Result: Never stop coding, minimal cost
```
@@ -292,7 +292,7 @@ Result: Never stop coding, minimal cost
**كيف يحل OmniRoute المشكلة:**
- **موفرو الطبقة المجانية المضمنون** — دعم أصلي لمقدمي الخدمة المجانية بنسبة 100%: iFlow (5 نماذج غير محدودة عبر OAuth: kimi-k2-thinking، qwen3-coder-plus، Deepseek-r1، minimax-m2، kimi-k2)، Qwen (4 نماذج غير محدودة: qwen3-coder-plus، qwen3-coder-flash، qwen3-coder-next، Vision-model)، Kiro (Claude + AWS Builder ID مجانًا)، Gemini CLI (180 ألف رمز مميز شهريًا مجانًا)
- **موفرو الطبقة المجانية المضمنون** — دعم أصلي لمقدمي الخدمة المجانية بنسبة 100%: Qoder (5 نماذج غير محدودة عبر OAuth: kimi-k2-thinking، qwen3-coder-plus، Deepseek-r1، minimax-m2، kimi-k2)، Qwen (4 نماذج غير محدودة: qwen3-coder-plus، qwen3-coder-flash، qwen3-coder-next، Vision-model)، Kiro (Claude + AWS Builder ID مجانًا)، Gemini CLI (180 ألف رمز مميز شهريًا مجانًا)
- **Ollama Cloud** — نماذج Ollama المستضافة على السحابة في `api.ollama.com` مع فئة "الاستخدام الخفيف" مجانًا؛ استخدم البادئة `ollamacloud/<model>`
- **المجموعات المجانية فقط** — السلسلة `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = 0 USD/الشهر بدون أي توقف عن العمل
- **NVIDIA NIM Free Access** — ~40 دورة في الدقيقة وصول مجاني للأبد إلى أكثر من 70 نموذجًا على build.nvidia.com (الانتقال من الاعتمادات إلى حدود المعدل النقي)
@@ -356,7 +356,7 @@ Claude Code، وCodex، وGemini CLI، وCopilot — جميعهم يستخدمو
**كيف يحل OmniRoute المشكلة:**
- **التحديث التلقائي للرمز المميز** — يتم تحديث رموز OAuth المميزة في الخلفية قبل انتهاء الصلاحية
- **OAuth 2.0 (PKCE) مدمج** — التدفق التلقائي لـ Claude Code وCodex وGemini CLI وCopilot وKiro وQwen وiFlow
- **OAuth 2.0 (PKCE) مدمج** — التدفق التلقائي لـ Claude Code وCodex وGemini CLI وCopilot وKiro وQwen وQoder
- **OAuth متعدد الحسابات** — حسابات متعددة لكل مزود عبر استخراج الرمز المميز JWT/ID
- **OAuth LAN/Remote Fix** — اكتشاف IP الخاص لـ `redirect_uri` + وضع URL اليدوي للخوادم البعيدة
- **OAuth Behind Nginx** — يستخدم `window.location.origin` للتوافق العكسي مع الوكيل
@@ -733,7 +733,7 @@ Outcome: deep fallback depth for deadline-critical workloads
| خطوة | العمل | مقدمي الخدمات مقفلة |
| ---- | -------------------------------------------------- | ------------------------------------------------------------------ |
| 1 | الاتصال **Kiro** (معرف AWS Builder OAuth) | كلود سونيت 4.5، هايكو 4.5 — **غير محدود** |
| 2 | ربط **iFlow** (Google OAuth) | kimi-k2-thinking, qwen3-coder-plus, Deepseek-r1... — **غير محدود** |
| 2 | ربط **Qoder** (Google OAuth) | kimi-k2-thinking, qwen3-coder-plus, Deepseek-r1... — **غير محدود** |
| 3 | ربط **كوين** (رمز الجهاز) | qwen3-coder-plus، qwen3-coder-flash... — **غير محدود** |
| 4 | الاتصال **Gemini CLI** (Google OAuth) | gemini-3-flash,gemini-2.5-pro — **180 ألف/الشهر مجانًا** |
| 5 | `/dashboard/combos`**قالب المكدس المجاني ($0)** | جولة روبن لجميع مقدمي الخدمات المجانية تلقائيًا |
@@ -957,7 +957,7 @@ npm run electron:build:linux # Linux (.AppImage)
```
# 🆓 Ultimate Free Stack 2026 — 11 Providers, $0 Forever
Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
Qwen (qw/) → qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next UNLIMITED
@@ -987,7 +987,7 @@ Cerebras (cerebras/) → Llama/Qwen world-fastest — 1M tok/day
| `claude-haiku-4.5` | `kr/` | **غير محدود** | لم يتم الإبلاغ عن الحد الأقصى اليومي |
| `claude-opus-4.6` | `kr/` | **غير محدود** | أحدث أعمال أوبوس عبر كيرو |
### 🟢 نماذج IFLOW (بروتوكول OAuth مجاني — بدون بطاقة ائتمان)
### 🟢 نماذج QODER (بروتوكول OAuth مجاني — بدون بطاقة ائتمان)
| نموذج | البادئة | الحد | حد السعر |
| ------------------ | ------- | ------------- | ----------------------------- |
@@ -1086,7 +1086,7 @@ Cerebras (cerebras/) → Llama/Qwen world-fastest — 1M tok/day
>
> ```
> Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
> iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
> Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
> Qwen (qw/) → qwen3-coder models UNLIMITED
@@ -1219,6 +1219,7 @@ Nodes:
| ميزة | ماذا يفعل |
| -------------------------------- | ------------------------------------------------------------------------- |
| 📝 **الطلب + تسجيل الوكيل** | الطلب/الاستجابة الكاملة وتسجيل الوكيل |
| 📉 **Streamed Detailed Logs** 🆕 | Reconstructs SSE payload streams cleanly into the UI |
| 📋 **لوحة تحكم السجلات الموحدة** | طلب العروض والوكيل والتدقيق ووحدة التحكم في صفحة واحدة |
| 🔍 **طلب القياس عن بعد** | زمن الاستجابة p50/p95/p99 وطلب التتبع |
| 🏥 **لوحة المعلومات الصحية** | وقت التشغيل، حالات الكسارة، عمليات الإغلاق، إحصائيات ذاكرة التخزين المؤقت |
@@ -1228,19 +1229,20 @@ Nodes:
### ☁️ النشر والمنصة
| ميزة | ماذا يفعل |
| -------------------------------- | --------------------------------------------------- |
| 🌐 **النشر في أي مكان** | المضيف المحلي، VPS، Docker، البيئات السحابية |
| 💾 **المزامنة السحابية** | مزامنة التكوين عبر عامل السحابة |
| 🔄 **النسخ الاحتياطي/الاستعادة** | تدفقات التصدير/الاستيراد والتعافي من الكوارث |
| 🧙 **معالج الإعداد** | الإعداد الموجه لأول مرة |
| 🔧 **لوحة تحكم أدوات CLI** | إعداد بنقرة واحدة لأدوات الترميز الشائعة |
| 🎮 **ساحة اللعب النموذجية** | اختبر أي موفر/نموذج/نقطة نهاية من لوحة المعلومات |
| 🔏 **تبديل بصمة الإصبع CLI** | مطابقة بصمات الأصابع لكل موفر في الإعدادات > الأمان |
| 🌐 **i18n (30 لغة)** | لوحة تحكم كاملة + دعم لغة المستندات مع تغطية RTL |
| 🧹 **مسح كافة النماذج** | مسح قائمة النماذج بنقرة واحدة في تفاصيل المزود |
| 📋 **نماذج الإصدارات** | قوالب GitHub الموحدة للأخطاء والميزات |
| 📂 **دليل البيانات المخصصة** | `DATA_DIR` تجاوز لموقع التخزين |
| ميزة | ماذا يفعل |
| -------------------------------- | --------------------------------------------------------- |
| 🌐 **النشر في أي مكان** | المضيف المحلي، VPS، Docker، البيئات السحابية |
| 💾 **المزامنة السحابية** | مزامنة التكوين عبر عامل السحابة |
| 🔄 **النسخ الاحتياطي/الاستعادة** | تدفقات التصدير/الاستيراد والتعافي من الكوارث |
| 🧙 **معالج الإعداد** | الإعداد الموجه لأول مرة |
| 🔧 **لوحة تحكم أدوات CLI** | إعداد بنقرة واحدة لأدوات الترميز الشائعة |
| 🎮 **ساحة اللعب النموذجية** | اختبر أي موفر/نموذج/نقطة نهاية من لوحة المعلومات |
| 🔏 **تبديل بصمة الإصبع CLI** | مطابقة بصمات الأصابع لكل موفر في الإعدادات > الأمان |
| 🌐 **i18n (30 لغة)** | لوحة تحكم كاملة + دعم لغة المستندات مع تغطية RTL |
| 🧹 **مسح كافة النماذج** | مسح قائمة النماذج بنقرة واحدة في تفاصيل المزود |
| 👁️ **Sidebar Controls** 🆕 | Hide components and integrations from Appearance Settings |
| 📋 **نماذج الإصدارات** | قوالب GitHub الموحدة للأخطاء والميزات |
| 📂 **دليل البيانات المخصصة** | `DATA_DIR` تجاوز لموقع التخزين |
### ميزة الغوص العميق
@@ -1534,11 +1536,11 @@ Models:
<details>
<summary><b>🆓 موفرو الخدمة المجانية (النسخ الاحتياطي في حالات الطوارئ)</b></summary>
### iFlow (5 نماذج مجانية عبر OAuth)
### Qoder (5 نماذج مجانية عبر OAuth)
```bash
Dashboard → Connect iFlow
iFlow OAuth login
Dashboard → Connect Qoder
Qoder OAuth login
→ Unlimited usage
Models:
@@ -1736,7 +1738,7 @@ opencode
- التحقق من إحصائيات الاستخدام في لوحة المعلومات → التكاليف
- تبديل النموذج الأساسي إلى GLM/MiniMax
- استخدم الطبقة المجانية (Gemini CLI، iFlow) للمهام غير الحرجة
- استخدم الطبقة المجانية (Gemini CLI، Qoder) للمهام غير الحرجة
**منافذ لوحة المعلومات/واجهة برمجة التطبيقات غير صحيحة**
+16 -13
View File
@@ -199,7 +199,7 @@ _Свържете всеки базиран на AI IDE или CLI инстру
npm run system-info
```
Това генерира `system-info.txt` с вашата версия на Node.js, версия на OmniRoute, подробности за операционната система, инсталирани CLI инструменти (iflow, gemini, claude, codex, antigravity, droid и т.н.), състояние на Docker/PM2 и системни пакети — всичко, от което се нуждаем, за да възпроизведем бързо проблема ви. Прикачете файла директно към вашия проблем с GitHub.
Това генерира `system-info.txt` с вашата версия на Node.js, версия на OmniRoute, подробности за операционната система, инсталирани CLI инструменти (qoder, gemini, claude, codex, antigravity, droid и т.н.), състояние на Docker/PM2 и системни пакети — всичко, от което се нуждаем, за да възпроизведем бързо проблема ви. Прикачете файла директно към вашия проблем с GitHub.
---
@@ -225,7 +225,7 @@ npm run system-info
│ ↓ budget limit
├─→ [Tier 3: CHEAP] GLM ($0.6/1M), MiniMax ($0.2/1M)
│ ↓ budget limit
└─→ [Tier 4: FREE] iFlow, Qwen, Kiro (unlimited)
└─→ [Tier 4: FREE] Qoder, Qwen, Kiro (unlimited)
Result: Never stop coding, minimal cost
```
@@ -292,7 +292,7 @@ OpenAI използва един формат, Claude (Anthropic) използв
**Как OmniRoute го решава:**
- **Вградени доставчици на безплатни нива** — Вградена поддръжка за 100% безплатни доставчици: iFlow (5 неограничени модела чрез OAuth: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2), Qwen (4 неограничени модела: qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next, vision-model), Kiro (Claude + AWS Builder ID безплатно), Gemini CLI (180K токена/месец безплатно)
- **Вградени доставчици на безплатни нива** — Вградена поддръжка за 100% безплатни доставчици: Qoder (5 неограничени модела чрез OAuth: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2), Qwen (4 неограничени модела: qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next, vision-model), Kiro (Claude + AWS Builder ID безплатно), Gemini CLI (180K токена/месец безплатно)
- **Ollama Cloud** — Хоствани в облака Ollama модели на `api.ollama.com` с безплатно ниво „Light usage“; използвайте префикс `ollamacloud/<model>`
- **Безплатни само комбинации** — Верига `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = $0/месец с нулев престой
- **NVIDIA NIM безплатен достъп** — ~40 RPM dev-вечно безплатен достъп до 70+ модела на build.nvidia.com (преход от кредити към чисти лимити на скоростта)
@@ -356,7 +356,7 @@ Claude Code, Codex, Gemini CLI, Copilot — всички използват OAut
**Как OmniRoute го решава:**
- **Auto Token Refresh** — OAuth токените се опресняват във фонов режим преди изтичане
- **OAuth 2.0 (PKCE) Вграден** — Автоматичен поток за Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
- **OAuth 2.0 (PKCE) Вграден** — Автоматичен поток за Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, Qoder
- **Multi-Account OAuth** — Множество акаунти на доставчик чрез JWT/ID извличане на токени
- **OAuth LAN/Remote Fix** — Частно IP откриване за `redirect_uri` + ръчен URL режим за отдалечени сървъри
- **OAuth зад Nginx** — Използва `window.location.origin` за обратна прокси съвместимост
@@ -733,7 +733,7 @@ Outcome: deep fallback depth for deadline-critical workloads
| Стъпка | Действие | Отключени доставчици |
| ------ | ---------------------------------------------------- | ------------------------------------------------------------------- |
| 1 | Свържете **Kiro** (AWS Builder ID OAuth) | Клод Сонет 4.5, Хайку 4.5 — **неограничен** |
| 2 | Свържете **iFlow** (Google OAuth) | kimi-k2-мислене, qwen3-coder-plus, deepseek-r1... — **неограничен** |
| 2 | Свържете **Qoder** (Google OAuth) | kimi-k2-мислене, qwen3-coder-plus, deepseek-r1... — **неограничен** |
| 3 | Свържете **Qwen** (Код на устройството) | qwen3-coder-plus, qwen3-coder-flash... — **неограничен** |
| 4 | Свържете **Gemini CLI** (Google OAuth) | gemini-3-flash, gemini-2.5-pro — **180K/мес безплатно** |
| 5 | `/dashboard/combos`**Безплатен стек ($0)** шаблон | Кръгово обвързване на всички безплатни доставчици автоматично |
@@ -942,7 +942,7 @@ npm run electron:build:linux # Linux (.AppImage)
| | MiniMax M2.1 | $0,2/1 милион | 5-часово търкаляне | Най-евтиният вариант |
| | Kimi K2.5 (Moonshot API) 🆕 | Плащане при използване | Няма | Директен достъп до API на Moonshot |
| | Кими К2 | $9/месец апартамент | 10 милиона токена/месец | Предвидими разходи |
| **🆓 БЕЗПЛАТНО** | iFlow | **$0** | Неограничен | 5 модела неограничено |
| **🆓 БЕЗПЛАТНО** | Qoder | **$0** | Неограничен | 5 модела неограничено |
| | Куен | **$0** | Неограничен | 4 модела неограничено |
| | Киро | **$0** | Неограничен | Клод Сонет/Хайку (AWS Builder) |
| | LongCat Flash-Lite 🆕 | **$0** (50M ток/ден 🔥) | 1 RPS | Най-голямата безплатна квота на Земята |
@@ -957,7 +957,7 @@ npm run electron:build:linux # Linux (.AppImage)
```
# 🆓 Ultimate Free Stack 2026 — 11 Providers, $0 Forever
Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
Qwen (qw/) → qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next UNLIMITED
@@ -987,7 +987,7 @@ Cerebras (cerebras/) → Llama/Qwen world-fastest — 1M tok/day
| `claude-haiku-4.5` | `kr/` | **Неограничен** | Няма отчетено дневно ограничение |
| `claude-opus-4.6` | `kr/` | **Неограничен** | Най-новият Opus чрез Kiro |
### 🟢 IFLOW МОДЕЛИ (Безплатен OAuth — Без кредитна карта)
### 🟢 QODER МОДЕЛИ (Безплатен OAuth — Без кредитна карта)
| Модел | Префикс | Лимит | Ограничение на скоростта |
| ------------------ | ------- | --------------- | ------------------------- |
@@ -1086,7 +1086,7 @@ Cerebras (cerebras/) → Llama/Qwen world-fastest — 1M tok/day
>
> ```
> Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
> iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
> Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
> Qwen (qw/) → qwen3-coder models UNLIMITED
@@ -1212,6 +1212,7 @@ OmniRoute v2.0 е създаден като операционна платфо
| 🌐 **IP филтриране** | Списък с разрешени/списъци с блокирани контроли за открити внедрявания |
| 📊 **Редактируеми ограничения на скоростта** | Конфигурируеми глобални/на ниво доставчик ограничения с постоянство |
| 🔑 **API Key Management + Scoping** | Сигурно издаване/ротация на ключове и контроли на модел/доставчик |
| 👁️ **Scoped API Key Reveal** 🆕 | Opt-in recovery of API keys via `ALLOW_API_KEY_REVEAL` |
| 🛡️ **Защитен `/models`** | Опционално удостоверяване и скриване на доставчик за каталог на модели |
### 📊 Наблюдаемост и анализ
@@ -1219,6 +1220,7 @@ OmniRoute v2.0 е създаден като операционна платфо
| Характеристика | Какво прави |
| --------------------------------------------- | ------------------------------------------------------------------------ |
| 📝 **Заявка + Регистриране на прокси сървър** | Пълно регистриране на заявка/отговор и прокси |
| 📉 **Streamed Detailed Logs** 🆕 | Reconstructs SSE payload streams cleanly into the UI |
| 📋 **Табло за управление на Unified Logs** | Изгледи на заявка, прокси, одит и конзола на една страница |
| 🔍 **Заявка за телеметрия** | p50/p95/p99 латентност и проследяване на заявки |
| 🏥 **Здравно табло** | Време на работа, състояния на прекъсване, блокировки, статистика на кеша |
@@ -1239,6 +1241,7 @@ OmniRoute v2.0 е създаден като операционна платфо
| 🔏 **CLI Fingerprint Toggle** | Съвпадение на пръстови отпечатъци за всеки доставчик в Настройки > Сигурност |
| 🌐 **i18n (30 езика)** | Пълно табло за управление + езикова поддръжка на документи с RTL покритие |
| 🧹 **Изчистване на всички модели** | Изчистване на списък с модели с едно щракване в подробности за доставчика |
| 👁️ **Sidebar Controls** 🆕 | Hide components and integrations from Appearance Settings |
| 📋 **Шаблони за проблеми** | Стандартизирани GitHub шаблони за грешки и функции |
| 📂 **Директория с персонализирани данни** | `DATA_DIR` отмяна за място за съхранение |
@@ -1534,11 +1537,11 @@ Models:
<details>
<summary><b>🆓 БЕЗПЛАТНИ доставчици (Спешно архивиране)</b></summary>
### iFlow (5 БЕЗПЛАТНИ модела чрез OAuth)
### Qoder (5 БЕЗПЛАТНИ модела чрез OAuth)
```bash
Dashboard → Connect iFlow
iFlow OAuth login
Dashboard → Connect Qoder
Qoder OAuth login
→ Unlimited usage
Models:
@@ -1736,7 +1739,7 @@ opencode
- Проверете статистическите данни за използването в Табло → Разходи
- Превключете основния модел към GLM/MiniMax
- Използвайте безплатно ниво (Gemini CLI, iFlow) за некритични задачи
- Използвайте безплатно ниво (Gemini CLI, Qoder) за некритични задачи
**Портовете на таблото/API са грешни**
+16 -13
View File
@@ -36,6 +36,7 @@ _Váš univerzální API proxy jeden koncový bod, 67+ poskytovatelů, nulov
| ✅ **Ověření trasy** | Všech 176 tras API je nyní ověřeno pomocí schémat Zod + `validateBody()` průkazy CI `check:route-validation:t06` |
| 🐛 **omniModel Tag Leak** | Interní značky `<omniModel>` již neunikají klientům v odpovědích streamování SSE (#585) |
| 🔑 **Registered Keys API** | Klíče API pro automatické poskytování prostřednictvím `POST /api/v1/registered-keys` s vynucováním kvót pro jednotlivé poskytovatele/účty, idempotence, úložiště SHA-256 a volitelné hlášení problémů GitHub |
| 👁️ **Scoped API Key Reveal** 🆕 | Opt-in recovery of API keys via `ALLOW_API_KEY_REVEAL` |
| 🎨 **Ikony poskytovatelů** | Více než 130 log poskytovatelů prostřednictvím `@lobehub/icons` (SVG) s PNG → obecný záložní řetězec |
| 🔄 **Automatická synchronizace modelu** | 24h plánovač a ruční přepínání uživatelského rozhraní pro synchronizaci seznamů modelů pro vestavěné a vlastní poskytovatele kompatibilní s OpenAI |
| 🌐 **OpenCode Zen/Go** | Dva noví poskytovatelé od @kang-heewon prostřednictvím PR #530: úroveň zdarma + úroveň předplatného přes `OpencodeExecutor` |
@@ -199,7 +200,7 @@ Při otevírání problému spusťte příkaz system-info a připojte vygenerova
npm run system-info
```
Tím se vygeneruje `system-info.txt` s vaší verzí Node.js, verzí OmniRoute, podrobnostmi OS, nainstalovanými nástroji CLI (iflow, gemini, claude, codex, antigravity, droid atd.), stavem Docker/PM2 a systémovými balíčky vše, co potřebujeme k rychlé reprodukci vašeho problému. Připojte soubor přímo k vašemu problému na GitHubu.
Tím se vygeneruje `system-info.txt` s vaší verzí Node.js, verzí OmniRoute, podrobnostmi OS, nainstalovanými nástroji CLI (qoder, gemini, claude, codex, antigravity, droid atd.), stavem Docker/PM2 a systémovými balíčky vše, co potřebujeme k rychlé reprodukci vašeho problému. Připojte soubor přímo k vašemu problému na GitHubu.
---
@@ -225,7 +226,7 @@ Tím se vygeneruje `system-info.txt` s vaší verzí Node.js, verzí OmniRoute,
│ ↓ budget limit
├─→ [Tier 3: CHEAP] GLM ($0.6/1M), MiniMax ($0.2/1M)
│ ↓ budget limit
└─→ [Tier 4: FREE] iFlow, Qwen, Kiro (unlimited)
└─→ [Tier 4: FREE] Qoder, Qwen, Kiro (unlimited)
Result: Never stop coding, minimal cost
```
@@ -293,7 +294,7 @@ Ne každý může platit 20200 $ měsíčně za předplatné AI. Studenti, v
**Jak to řeší OmniRoute:**
- **Vestavění poskytovatelé bezplatných úrovní** — Nativní podpora pro 100% bezplatné poskytovatele: iFlow (5 neomezených modelů přes OAuth: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2), Qwen (4 neomezené modely: qwen3-qwender-lash, qwen3-qwender-lash qwen3-coder-next, vision-model), Kiro (Claude + AWS Builder ID zdarma), Gemini CLI (180 000 tokenů/měsíc zdarma)
- **Vestavění poskytovatelé bezplatných úrovní** — Nativní podpora pro 100% bezplatné poskytovatele: Qoder (5 neomezených modelů přes OAuth: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2), Qwen (4 neomezené modely: qwen3-qwender-lash, qwen3-qwender-lash qwen3-coder-next, vision-model), Kiro (Claude + AWS Builder ID zdarma), Gemini CLI (180 000 tokenů/měsíc zdarma)
- **Ollama Cloud** modely Ollama hostované v cloudu na `api.ollama.com` s bezplatnou úrovní „Light use“; použijte předponu `ollamacloud/<model>`
- **Pouze bezplatná komba** — Řetězec `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = 0 $/měsíc s nulovými prostoji
- **Volný přístup NVIDIA NIM** — ~40 RPM pro vývojáře - navždy bezplatný přístup k více než 70 modelům na build.nvidia.com (přechod z kreditů na limity čisté sazby)
@@ -358,7 +359,7 @@ Claude Code, Codex, Gemini CLI, Copilot všechny používají OAuth 2.0 s ko
**Jak to řeší OmniRoute:**
- **Automatické obnovení tokenu** Tokeny OAuth se před vypršením platnosti obnovují na pozadí
- **Vestavěný OAuth 2.0 (PKCE)** — Automatický tok pro Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
- **Vestavěný OAuth 2.0 (PKCE)** — Automatický tok pro Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, Qoder
**Multi-Account OAuth** Více účtů na poskytovatele prostřednictvím extrakce tokenů JWT/ID
- **OAuth LAN/Remote Fix** — Detekce privátní IP adresy pro `redirect_uri` + ruční režim URL pro vzdálené servery
- **OAuth Behind Nginx** - Používá `window.location.origin` pro reverzní kompatibilitu proxy
@@ -738,7 +739,7 @@ Outcome: deep fallback depth for deadline-critical workloads
| Krok | Akce | Poskytovatelé odemčeni |
| ---- | ---------------------------------------------------- | -------------------------------------------------------------------- |
| 1 | Connect **Kiro** (AWS Builder ID OAuth) | Claude Sonnet 4.5, Haiku 4.5 — **neomezeno** |
| 2 | Připojte **iFlow** (Google OAuth) | kimi-k2-thinking, qwen3-coder-plus, deepseek-r1... — **bez omezení** |
| 2 | Připojte **Qoder** (Google OAuth) | kimi-k2-thinking, qwen3-coder-plus, deepseek-r1... — **bez omezení** |
| 3 | Připojte **Qwen** (kód zařízení) | qwen3-coder-plus, qwen3-coder-flash... — **bez omezení** |
| 4 | Připojte **Gemini CLI** (Google OAuth) | gemini-3-flash, gemini-2.5-pro — **180 000/měsíc zdarma** |
| 5 | `/dashboard/combos` → Šablona **Stack zdarma (0 $)** | Round-robin všechny bezplatné poskytovatele automaticky |
@@ -947,7 +948,7 @@ Když je minimalizován, OmniRoute žije v systémové liště s rychlými akcem
| | MiniMax M2.1 | 0,2 $/1 mil. | 5hodinové válcování | Nejlevnější varianta |
| | Kimi K2.5 (Moonshot API) 🆕 | Platba za použití | Žádné | Přímý přístup Moonshot API |
| | Kimi K2 | 9 $/měsíc byt | 10 milionů tokenů/měsíc | Předvídatelné náklady |
| **🆓 ZDARMA** | iFlow | **$0** | Neomezené | 5 modelů neomezeně |
| **🆓 ZDARMA** | Qoder | **$0** | Neomezené | 5 modelů neomezeně |
| | Qwen | **$0** | Neomezené | 4 modely neomezeně |
| | Kiro | **$0** | Neomezené | Claude Sonnet/Haiku (stavitel AWS) |
| | LongCat Flash-Lite 🆕 | **$0** (50 milionů toku/den 🔥) | 1 RPS | Největší bezplatná kvóta na Zemi |
@@ -962,7 +963,7 @@ Když je minimalizován, OmniRoute žije v systémové liště s rychlými akcem
```
# 🆓 Ultimate Free Stack 2026 — 11 Providers, $0 Forever
Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
Qwen (qw/) → qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next UNLIMITED
@@ -992,7 +993,7 @@ Cerebras (cerebras/) → Llama/Qwen world-fastest — 1M tok/day
| `claude-haiku-4.5` | `kr/` | **Neomezeno** | Žádný hlášený denní limit |
| `claude-opus-4.6` | `kr/` | **Neomezeno** | Nejnovější Opus přes Kiro |
### 🢢 MODELY IFLOW (bezplatný protokol OAuth žádná kreditní karta)
### 🢢 MODELY QODER (bezplatný protokol OAuth žádná kreditní karta)
| Model | Předpona | Limit | Limit sazby |
| ------------------ | -------- | ------------- | --------------------- |
@@ -1091,7 +1092,7 @@ Dostupné zdarma: `qwen3-235b-a22b-instruct-2507` (Qwen3 235B!), `llama-3.1-70b-
>
> ```
> Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
> iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
> Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
> Qwen (qw/) → qwen3-coder models UNLIMITED
@@ -1224,6 +1225,7 @@ OmniRoute v2.0 je postaven jako operační platforma, nikoli pouze jako přenoso
| Funkce | Co to dělá |
| -------------------------------------- | ---------------------------------------------------------------------- |
| 📝 **Požadavek + protokolování proxy** | Úplný požadavek/odpověď a protokolování proxy |
| 📉 **Streamed Detailed Logs** 🆕 | Reconstructs SSE payload streams cleanly into the UI |
| 📋 **Sjednocený panel protokolů** | Požadavek, proxy, audit a zobrazení konzoly na jedné stránce |
| 🔍 **Požádejte o telemetrii** | p50/p95/p99 latence a trasování požadavků |
| 🏥 **Health Dashboard** | Doba provozuschopnosti, stavy jističe, uzamčení, statistiky mezipaměti |
@@ -1244,6 +1246,7 @@ OmniRoute v2.0 je postaven jako operační platforma, nikoli pouze jako přenoso
| 🔏 **CLI Fingerprint Toggle** | Shoda otisků prstů jednotlivých poskytovatelů v Nastavení > Zabezpečení |
| 🌐 **i18n (30 jazyků)** | Plná podpora řídicího panelu + docs s pokrytím RTL |
| 🧹 **Vymazat všechny modely** | Vymazání seznamu modelů jedním kliknutím v detailech poskytovatele |
| 👁️ **Sidebar Controls** 🆕 | Hide components and integrations from Appearance Settings |
| 📋 **Šablony vydání** | Standardizované šablony GitHub pro chyby a funkce |
| 📂 **Custom Data Directory** | `DATA_DIR` přepsání umístění úložiště |
@@ -1539,11 +1542,11 @@ Models:
<details>
<summary><b>🆓 ZDARMA poskytovatelé (nouzová záloha)</b></summary>
### iFlow (5 ZDARMA modelů přes OAuth)
### Qoder (5 ZDARMA modelů přes OAuth)
```bash
Dashboard → Connect iFlow
iFlow OAuth login
Dashboard → Connect Qoder
Qoder OAuth login
→ Unlimited usage
Models:
@@ -1741,7 +1744,7 @@ opencode
- Zkontrolujte statistiky využití v Dashboard → Náklady
- Přepněte primární model na GLM/MiniMax
- Používejte bezplatnou vrstvu (Gemini CLI, iFlow) pro nekritické úkoly
- Používejte bezplatnou vrstvu (Gemini CLI, Qoder) pro nekritické úkoly
**Porty řídicího panelu/API jsou chybné**
+16 -13
View File
@@ -199,7 +199,7 @@ When opening an issue, please run the system-info command and attach the generat
npm run system-info
```
Dette genererer en `system-info.txt` med din Node.js-version, OmniRoute-version, OS-detaljer, installerede CLI-værktøjer (iflow, gemini, claude, codex, antigravity, droid osv.), Docker/PM2-status og systempakker - alt hvad vi behøver for hurtigt at genskabe dit problem. Vedhæft filen direkte til dit GitHub-problem.
Dette genererer en `system-info.txt` med din Node.js-version, OmniRoute-version, OS-detaljer, installerede CLI-værktøjer (qoder, gemini, claude, codex, antigravity, droid osv.), Docker/PM2-status og systempakker - alt hvad vi behøver for hurtigt at genskabe dit problem. Vedhæft filen direkte til dit GitHub-problem.
---
@@ -225,7 +225,7 @@ Dette genererer en `system-info.txt` med din Node.js-version, OmniRoute-version,
│ ↓ budget limit
├─→ [Tier 3: CHEAP] GLM ($0.6/1M), MiniMax ($0.2/1M)
│ ↓ budget limit
└─→ [Tier 4: FREE] iFlow, Qwen, Kiro (unlimited)
└─→ [Tier 4: FREE] Qoder, Qwen, Kiro (unlimited)
Result: Never stop coding, minimal cost
```
@@ -292,7 +292,7 @@ Ikke alle kan betale $20-200/måned for AI-abonnementer. Studerende, udviklere f
**Sådan løser OmniRoute det:**
- **Free Tier Providers Indbygget** — Indbygget understøttelse af 100 % gratis udbydere: iFlow (5 ubegrænsede modeller via OAuth: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2), Qwen (4 unlimited-modeller,-r-modeller) qwen3-coder-flash, qwen3-coder-next, vision-model), Kiro (Claude + AWS Builder ID gratis), Gemini CLI (180K tokens/måned gratis)
- **Free Tier Providers Indbygget** — Indbygget understøttelse af 100 % gratis udbydere: Qoder (5 ubegrænsede modeller via OAuth: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2), Qwen (4 unlimited-modeller,-r-modeller) qwen3-coder-flash, qwen3-coder-next, vision-model), Kiro (Claude + AWS Builder ID gratis), Gemini CLI (180K tokens/måned gratis)
- **Ollama Cloud** — Cloud-hostede Ollama-modeller på `api.ollama.com` med gratis "Light usage"-niveau; brug præfikset `ollamacloud/<model>`
- **Kun gratis kombinationer** — Kæde `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = $0/måned uden nedetid
- **NVIDIA NIM Free Access** — ~40 RPM dev-forever gratis adgang til 70+ modeller på build.nvidia.com (overgang fra kreditter til rene hastighedsgrænser)
@@ -356,7 +356,7 @@ Claude Code, Codex, Gemini CLI, Copilot - alle bruger OAuth 2.0 med udløbende t
**Sådan løser OmniRoute det:**
- **Automatisk tokenopdatering** — OAuth-tokens opdateres i baggrunden før udløb
- **OAuth 2.0 (PKCE) Indbygget** — Automatisk flow for Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
- **OAuth 2.0 (PKCE) Indbygget** — Automatisk flow for Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, Qoder
- **Multi-Account OAuth** — Flere konti pr. udbyder via JWT/ID-tokenudtrækning
- **OAuth LAN/Remote Fix** — Privat IP-detektering for `redirect_uri` + manuel URL-tilstand til fjernservere
- **OAuth Behind Nginx** — Bruger `window.location.origin` til omvendt proxykompatibilitet
@@ -733,7 +733,7 @@ Outcome: deep fallback depth for deadline-critical workloads
| Trin | Handling | Udbydere ulåst |
| ---- | --------------------------------------------------- | ------------------------------------------------------------------- |
| 1 | Tilslut **Kiro** (AWS Builder ID OAuth) | Claude Sonnet 4.5, Haiku 4.5 — **ubegrænset** |
| 2 | Tilslut **iFlow** (Google OAuth) | kimi-k2-tænkning, qwen3-coder-plus, deepseek-r1... — **ubegrænset** |
| 2 | Tilslut **Qoder** (Google OAuth) | kimi-k2-tænkning, qwen3-coder-plus, deepseek-r1... — **ubegrænset** |
| 3 | Tilslut **Qwen** (enhedskode) | qwen3-coder-plus, qwen3-coder-flash... — **ubegrænset** |
| 4 | Tilslut **Gemini CLI** (Google OAuth) | gemini-3-flash, gemini-2.5-pro — **180K/md gratis** |
| 5 | `/dashboard/combos`**Gratis stak ($0)** skabelon | Round-robin alle gratis udbydere automatisk |
@@ -942,7 +942,7 @@ Når den er minimeret, lever OmniRoute i din procesbakke med hurtige handlinger:
| | MiniMax M2.1 | $0,2/1 mio. | 5-timers rullende | Billigste mulighed |
| | Kimi K2.5 (Moonshot API) 🆕 | Betal pr. brug | Ingen | Direkte Moonshot API-adgang |
| | Kimi K2 | 9 USD/md. lejlighed | 10M tokens/md. | Forudsigelige omkostninger |
| **🆓 GRATIS** | iFlow | **$0** | Ubegrænset | 5 modeller ubegrænset |
| **🆓 GRATIS** | Qoder | **$0** | Ubegrænset | 5 modeller ubegrænset |
| | Qwen | **$0** | Ubegrænset | 4 modeller ubegrænset |
| | Kiro | **$0** | Ubegrænset | Claude Sonnet/Haiku (AWS Builder) |
| | LongCat Flash-Lite 🆕 | **$0** (50 mio. tok/dag 🔥) | 1 RPS | Største gratis kvote på jorden |
@@ -957,7 +957,7 @@ Når den er minimeret, lever OmniRoute i din procesbakke med hurtige handlinger:
```
# 🆓 Ultimate Free Stack 2026 — 11 Providers, $0 Forever
Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
Qwen (qw/) → qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next UNLIMITED
@@ -987,7 +987,7 @@ Cerebras (cerebras/) → Llama/Qwen world-fastest — 1M tok/day
| `claude-haiku-4.5` | `kr/` | **Ubegrænset** | Ingen rapporteret dagligt loft |
| `claude-opus-4.6` | `kr/` | **Ubegrænset** | Seneste Opus via Kiro |
### IFLOW MODELLER (gratis OAuth — intet kreditkort)
### QODER MODELLER (gratis OAuth — intet kreditkort)
| Model | Præfiks | Grænse | Satsgrænse |
| ------------------ | ------- | -------------- | ---------------------- |
@@ -1086,7 +1086,7 @@ Tilgængelig gratis: `qwen3-235b-a22b-instruct-2507` (Qwen3 235B!), `llama-3.1-7
>
> ```
> Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
> iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
> Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
> Qwen (qw/) → qwen3-coder models UNLIMITED
@@ -1212,6 +1212,7 @@ OmniRoute v2.0 er bygget som en operationel platform, ikke kun en relæ-proxy.
| 🌐 **IP-filtrering** | Tilladelsesliste/blokeringslistekontrol for udsatte implementeringer |
| 📊 **Redigerbare satsgrænser** | Konfigurerbare grænser på globalt niveau/udbyderniveau med persistens |
| 🔑 **API Key Management + Scoping** | Sikker nøgleudstedelse/rotation og model-/leverandørkontrol |
| 👁️ **Scoped API Key Reveal** 🆕 | Opt-in recovery of API keys via `ALLOW_API_KEY_REVEAL` |
| 🛡️ **Beskyttet `/models`** | Valgfri godkendelse og udbyderskjul til modelkatalog |
### 📊 Observerbarhed og analyse
@@ -1219,6 +1220,7 @@ OmniRoute v2.0 er bygget som en operationel platform, ikke kun en relæ-proxy.
| Funktion | Hvad det gør |
| ---------------------------------- | ------------------------------------------------------ |
| 📝 **Forespørgsel + Proxylogning** | Fuld anmodning/svar og proxy-logning |
| 📉 **Streamed Detailed Logs** 🆕 | Reconstructs SSE payload streams cleanly into the UI |
| 📋 **Unified Logs Dashboard** | Anmodning, proxy, revision og konsolvisning på én side |
| 🔍 **Anmod om telemetri** | p50/p95/p99 latens og anmodningssporing |
| 🏥 **Sundhedskontrolpanel** | Oppetid, breaker-tilstande, lockouts, cache-statistik |
@@ -1239,6 +1241,7 @@ OmniRoute v2.0 er bygget som en operationel platform, ikke kun en relæ-proxy.
| 🔏 **CLI Fingerprint Toggle** | Fingeraftryksmatchning pr. udbyder i Indstillinger > Sikkerhed |
| 🌐 **i18n (30 sprog)** | Fuldt dashboard + understøttelse af docs-sprog med RTL-dækning |
| 🧹 **Ryd alle modeller** | Rydning af modelliste med ét klik i udbyderoplysninger |
| 👁️ **Sidebar Controls** 🆕 | Hide components and integrations from Appearance Settings |
| 📋 **Udgaveskabeloner** | Standardiserede GitHub-skabeloner til fejl og funktioner |
| 📂 **Tilpasset datakatalog** | `DATA_DIR` tilsidesættelse for lagerplacering |
@@ -1534,11 +1537,11 @@ Models:
<details>
<summary><b>🆓 GRATIS udbydere (nødbackup)</b></summary>
### iFlow (5 GRATIS modeller via OAuth)
### Qoder (5 GRATIS modeller via OAuth)
```bash
Dashboard → Connect iFlow
iFlow OAuth login
Dashboard → Connect Qoder
Qoder OAuth login
→ Unlimited usage
Models:
@@ -1736,7 +1739,7 @@ opencode
- Tjek brugsstatistik i Dashboard → Omkostninger
- Skift primær model til GLM/MiniMax
- Brug gratis niveau (Gemini CLI, iFlow) til ikke-kritiske opgaver
- Brug gratis niveau (Gemini CLI, Qoder) til ikke-kritiske opgaver
**Dashboard/API-porte er forkerte**
+16 -13
View File
@@ -36,6 +36,7 @@ _Universaali API-välityspalvelin yksi päätepiste, yli 67 palveluntarjoaja
| ✅ **Reitin vahvistaminen** | Kaikki 176 API-reittiä nyt validoitu Zod-skeemoilla + `validateBody()` — CI `check:route-validation:t06` -passit |
| 🐛 **omniModel Tag Leak** | Sisäiset `<omniModel>` -tunnisteet eivät enää vuoda asiakkaille SSE-suoratoistovastauksissa (#585) |
| 🔑 **Registered Keys API** | Määritä API-avaimet automaattisesti `POST /api/v1/registered-keys`:n kautta palveluntarjoaja-/tilikiintiön pakottamisen, idempotenssin, SHA-256-tallennustilan ja valinnaisen GitHub-ongelmaraportoinnin avulla |
| 👁️ **Scoped API Key Reveal** 🆕 | Opt-in recovery of API keys via `ALLOW_API_KEY_REVEAL` |
| 🎨 ** Palveluntarjoajan kuvakkeet** | Yli 130 palveluntarjoajan logoa `@lobehub/icons` (SVG) ja PNG:n kautta → yleinen varaketju |
| 🔄 **Mallin automaattinen synkronointi** | 24 tunnin ajastin ja manuaalinen käyttöliittymä synkronoidaksesi malliluettelot sisäänrakennetuille ja mukautetuille OpenAI-yhteensopiville palveluntarjoajille |
| 🌐 **OpenCode Zen/Go** | Kaksi uutta palveluntarjoajaa @kang-heewonilta PR #530:n kautta: ilmainen taso + tilaustaso `OpencodeExecutor` -palvelun kautta |
@@ -199,7 +200,7 @@ Kun avaat ongelman, suorita system-info-komento ja liitä luotu tiedosto:
npm run system-info
```
Tämä luo `system-info.txt`, jossa on Node.js-versiosi, OmniRoute-versiosi, käyttöjärjestelmätiedot, asennetut CLI-työkalut (iflow, gemini, claude, codex, antigravity, droidi jne.), Docker/PM2-tila ja järjestelmäpaketit kaikki, mitä tarvitsemme ongelmasi nopeaan toistamiseen. Liitä tiedosto suoraan GitHub-ongelmaasi.
Tämä luo `system-info.txt`, jossa on Node.js-versiosi, OmniRoute-versiosi, käyttöjärjestelmätiedot, asennetut CLI-työkalut (qoder, gemini, claude, codex, antigravity, droidi jne.), Docker/PM2-tila ja järjestelmäpaketit kaikki, mitä tarvitsemme ongelmasi nopeaan toistamiseen. Liitä tiedosto suoraan GitHub-ongelmaasi.
---
@@ -225,7 +226,7 @@ Tämä luo `system-info.txt`, jossa on Node.js-versiosi, OmniRoute-versiosi, kä
│ ↓ budget limit
├─→ [Tier 3: CHEAP] GLM ($0.6/1M), MiniMax ($0.2/1M)
│ ↓ budget limit
└─→ [Tier 4: FREE] iFlow, Qwen, Kiro (unlimited)
└─→ [Tier 4: FREE] Qoder, Qwen, Kiro (unlimited)
Result: Never stop coding, minimal cost
```
@@ -292,7 +293,7 @@ Kaikki eivät voi maksaa 20200 dollaria kuukaudessa tekoälytilauksista. Opis
**Kuinka OmniRoute ratkaisee sen:**
- **Free Tier Providers Built-in** — Natiivituki 100 % ilmaisille palveluntarjoajille: iFlow (5 rajoittamaton mallia OAuthin kautta: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2), Qwen-mallit: 4 unqlim-plus3 qwen3-coder-flash, qwen3-coder-next, vision-model), Kiro (Claude + AWS Builder ID ilmaiseksi), Gemini CLI (180 000 tokenia / kuukausi ilmaiseksi)
- **Free Tier Providers Built-in** — Natiivituki 100 % ilmaisille palveluntarjoajille: Qoder (5 rajoittamaton mallia OAuthin kautta: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2), Qwen-mallit: 4 unqlim-plus3 qwen3-coder-flash, qwen3-coder-next, vision-model), Kiro (Claude + AWS Builder ID ilmaiseksi), Gemini CLI (180 000 tokenia / kuukausi ilmaiseksi)
- **Ollama Cloud** — pilvipalvelussa isännöityjä Ollama-malleja osoitteessa `api.ollama.com` ilmaisella "kevytkäyttö"-tasolla; käytä `ollamacloud/<model>`-etuliitettä
- **Vain ilmaiset yhdistelmät** — ketju `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = 0 $/kk ilman seisokkeja
- **NVIDIA NIM Free Access** - ~40 RPM:n kehittäjä - ikuisesti ilmainen pääsy yli 70 malliin osoitteessa build.nvidia.com (siirrytään hyvityksistä puhtaisiin hintarajoihin)
@@ -356,7 +357,7 @@ Claude Code, Codex, Gemini CLI, Copilot kaikki käyttävät OAuth 2.0:aa van
**Kuinka OmniRoute ratkaisee sen:**
- **Automaattinen tunnuksen päivitys** - OAuth-tunnukset päivittyvät taustalla ennen vanhenemista
- **Sisäänrakennettu OAuth 2.0 (PKCE)** - Automaattinen kulku Claude Codelle, Codexille, Gemini CLI:lle, Copilotille, Kirolle, Qwenille, iFlowille
- **Sisäänrakennettu OAuth 2.0 (PKCE)** - Automaattinen kulku Claude Codelle, Codexille, Gemini CLI:lle, Copilotille, Kirolle, Qwenille, Qoderille
- **Multi-Account OAuth** - Useita tilejä palveluntarjoajaa kohden JWT/ID-tunnuksen purkamisen kautta
- **OAuth LAN/Remote Fix** - Yksityinen IP-tunnistus kohteelle `redirect_uri` + manuaalinen URL-tila etäpalvelimille
- **OAuth Nginxin takana** - Käyttää `window.location.origin` käänteisen välityspalvelimen yhteensopivuutta varten
@@ -733,7 +734,7 @@ Outcome: deep fallback depth for deadline-critical workloads
| Vaihe | Toiminta | Palveluntarjoajat avattu |
| ----- | -------------------------------------------------- | ---------------------------------------------------------------------- |
| 1 | Yhdistä **Kiro** (AWS Builder ID OAuth) | Claude Sonnet 4.5, Haiku 4.5 — **rajaton** |
| 2 | Yhdistä **iFlow** (Google OAuth) | kimi-k2-ajattelu, qwen3-coder-plus, deepseek-r1... — **rajoittamaton** |
| 2 | Yhdistä **Qoder** (Google OAuth) | kimi-k2-ajattelu, qwen3-coder-plus, deepseek-r1... — **rajoittamaton** |
| 3 | Yhdistä **Qwen** (laitekoodi) | qwen3-coder-plus, qwen3-coder-flash... — **rajoittamaton** |
| 4 | Yhdistä **Gemini CLI** (Google OAuth) | gemini-3-flash, gemini-2.5-pro — **180K/kk ilmaiseksi** |
| 5 | `/dashboard/combos`**Ilmainen pino ($0)** malli | Round-robin kaikki ilmaiset palveluntarjoajat automaattisesti |
@@ -942,7 +943,7 @@ Kun OmniRoute on minimoitu, se elää ilmaisinalueellasi nopeilla toimilla:
| | MiniMax M2.1 | 0,2 $/1 milj. | 5 tunnin rullaus | Halvin vaihtoehto |
| | Kimi K2.5 (Moonshot API) 🆕 | Maksu per käyttö | Ei yhtään | Suora Moonshot API -käyttö |
| | Kimi K2 | 9 dollaria/kk asunto | 10 milj. rahakkeita/kk | Ennustettavat kustannukset |
| **🆓 ILMAINEN** | iFlow | **0 $** | Rajoittamaton | 5 mallia rajoittamaton |
| **🆓 ILMAINEN** | Qoder | **0 $** | Rajoittamaton | 5 mallia rajoittamaton |
| | Qwen | **0 $** | Rajoittamaton | 4 mallia rajoittamaton |
| | Kiro | **0 $** | Rajoittamaton | Claude Sonnet/Haiku (AWS Builder) |
| | LongCat Flash-Lite 🆕 | **0 $** (50 milj. tok/päivä 🔥) | 1 RPS | Suurin ilmainen kiintiö maailmassa |
@@ -957,7 +958,7 @@ Kun OmniRoute on minimoitu, se elää ilmaisinalueellasi nopeilla toimilla:
```
# 🆓 Ultimate Free Stack 2026 — 11 Providers, $0 Forever
Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
Qwen (qw/) → qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next UNLIMITED
@@ -987,7 +988,7 @@ Cerebras (cerebras/) → Llama/Qwen world-fastest — 1M tok/day
| `claude-haiku-4.5` | `kr/` | **Rajoittamaton** | Ei raportoitu päivittäistä ylärajaa |
| `claude-opus-4.6` | `kr/` | **Rajoittamaton** | Uusin Opus kautta Kiro |
### 🟢 IFLOW-MALLIT (ilmainen OAuth ei luottokorttia)
### 🟢 QODER-MALLIT (ilmainen OAuth ei luottokorttia)
| Malli | Etuliite | Raja | Hintarajoitus |
| ------------------ | -------- | ----------------- | --------------------- |
@@ -1086,7 +1087,7 @@ Saatavilla ilmaiseksi: `qwen3-235b-a22b-instruct-2507` (Qwen3 235B!), `llama-3.1
>
> ```
> Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
> iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
> Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
> Qwen (qw/) → qwen3-coder models UNLIMITED
@@ -1219,6 +1220,7 @@ OmniRoute v2.0 on rakennettu toiminnalliseksi alustaksi, ei vain välityspalveli
| Ominaisuus | Mitä se tekee |
| ----------------------------------------- | ----------------------------------------------------------------------- |
| 📝 **Pyyntö + välityspalvelimen kirjaus** | Täysi pyyntö/vastaus ja välityspalvelimen kirjaus |
| 📉 **Streamed Detailed Logs** 🆕 | Reconstructs SSE payload streams cleanly into the UI |
| 📋 **Unified Logs Dashboard** | Pyyntö-, välityspalvelin-, tarkastus- ja konsolinäkymät yhdellä sivulla |
| 🔍 **Pyydä telemetriaa** | p50/p95/p99 latenssi ja pyynnön jäljitys |
| 🏥 **Terveyden hallintapaneeli** | Käyttöaika, katkaisutilat, lukitukset, välimuistitilastot |
@@ -1239,6 +1241,7 @@ OmniRoute v2.0 on rakennettu toiminnalliseksi alustaksi, ei vain välityspalveli
| 🔏 **CLI-sormenjälkivalitsin** | Palveluntarjoajakohtainen sormenjälkien vastaavuus kohdassa Asetukset > Suojaus |
| 🌐 **i18n (30 kieltä)** | Täysi kojelauta + asiakirjojen kielen tuki RTL-kattauksella |
| 🧹 **Tyhjennä kaikki mallit** | Yhden napsautuksen malliluettelon tyhjennys toimittajan tiedoissa |
| 👁️ **Sidebar Controls** 🆕 | Hide components and integrations from Appearance Settings |
| 📋 **Ongelman mallit** | Standardoidut GitHub-mallit bugeille ja ominaisuuksille |
| 📂 **Muokattu tietohakemisto** | `DATA_DIR` ohitus tallennuspaikalle |
@@ -1534,11 +1537,11 @@ Models:
<details>
<summary><b>🆓 ILMAISIA palveluntarjoajia (hätävarmuuskopio)</b></summary>
### iFlow (5 ILMAISTA mallia OAuthin kautta)
### Qoder (5 ILMAISTA mallia OAuthin kautta)
```bash
Dashboard → Connect iFlow
iFlow OAuth login
Dashboard → Connect Qoder
Qoder OAuth login
→ Unlimited usage
Models:
@@ -1736,7 +1739,7 @@ opencode
- Tarkista käyttötilastot kohdassa Dashboard → Costs
- Vaihda ensisijaiseksi malliksi GLM/MiniMax
- Use free tier (Gemini CLI, iFlow) for non-critical tasks
- Use free tier (Gemini CLI, Qoder) for non-critical tasks
**Kojelauta/API-portit ovat väärin**
+53 -50
View File
@@ -30,21 +30,22 @@ _שרת ה-API האוניברסלי שלך - נקודת קצה אחת, 67+ ספ
> **משדרגים מגרסה 2.9.5?** — עיין ב-[full CHANGELOG](CHANGELOG.md#300--2026-03-22-release-candidate--not-yet-merged-to-main) לכל השינויים.
| אזור | שנה |
| -------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| 🔒 **CodeQL Security** | תוקן יותר מ-10 התראות CodeQL: פולינום-redos, unsecure-randomness, תיקון הזרקת מעטפת |
| ✅ **אימות מסלול** | כל 176 מסלולי ה-API מאומתים כעת עם סכימות Zod + `validateBody()` — מעברי CI `check:route-validation:t06` |
| 🐛 **הדלפת תג omniModel** | תגי `<omniModel>` פנימיים אינם דולפים יותר ללקוחות בתגובות הזרמת SSE (#585) |
| 🔑 **Registered Keys API** | הקצאה אוטומטית של מפתחות API באמצעות `POST /api/v1/registered-keys` עם אכיפת מכסות לכל ספק/חשבון, אימפוטנציה, אחסון SHA-256 ודיווח אופציונלי על בעיות GitHub |
| 🎨 **אייקוני ספק** | יותר מ-130 סמלי לוגו של ספקים באמצעות `@lobehub/icons` (SVG) עם PNG → שרשרת חילופין גנרית |
| 🔄 **סנכרון אוטומטי דגם** | מתזמן 24 שעות וממשק משתמש ידני כדי לסנכרן רשימות דגמים עבור ספקים מובנים ומותאמים אישית תואמי OpenAI |
| 🌐 **OpenCode Zen/Go** | שני ספקים חדשים מ-@kang-heewon דרך PR #530: שכבת חינם + שכבת מנוי דרך `OpencodeExecutor` |
| 🐛 **Gemini CLI OAuth** | שגיאה ניתנת לפעולה כאשר `GEMINI_OAUTH_CLIENT_SECRET` חסר ב-Docker (הייתה שגיאה סתמית של Google) |
| 🐛 **תצורת OpenCode** | `saveOpenCodeConfig()` כותב כעת כראוי TOML ל-`XDG_CONFIG_HOME` |
| 🐛 **עקיפת דגם מוצמד** | `body.model` מוגדר כראוי ל-`pinnedModel` על הגנת הקשר מטמון |
| 🐛 **קודקס/לולאת קלוד** | `tool_result` בלוקים מומרים כעת לטקסט כדי לעצור לולאות אינסופיות |
| 🐛 **הפניה מחדש לכניסה** | הכניסה לא קופאת עוד לאחר דילוג על הגדרת הסיסמה |
| 🐛 **נתיבי חלונות** | נתיבי MSYS2/Git-Bash (`/c/...`) מנורמלים ל-`C:\...` באופן אוטומטי |
| אזור | שנה |
| ------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| 🔒 **CodeQL Security** | תוקן יותר מ-10 התראות CodeQL: פולינום-redos, unsecure-randomness, תיקון הזרקת מעטפת |
| ✅ **אימות מסלול** | כל 176 מסלולי ה-API מאומתים כעת עם סכימות Zod + `validateBody()` — מעברי CI `check:route-validation:t06` |
| 🐛 **הדלפת תג omniModel** | תגי `<omniModel>` פנימיים אינם דולפים יותר ללקוחות בתגובות הזרמת SSE (#585) |
| 🔑 **Registered Keys API** | הקצאה אוטומטית של מפתחות API באמצעות `POST /api/v1/registered-keys` עם אכיפת מכסות לכל ספק/חשבון, אימפוטנציה, אחסון SHA-256 ודיווח אופציונלי על בעיות GitHub |
| 👁️ **Scoped API Key Reveal** 🆕 | Opt-in recovery of API keys via `ALLOW_API_KEY_REVEAL` |
| 🎨 **אייקוני ספק** | יותר מ-130 סמלי לוגו של ספקים באמצעות `@lobehub/icons` (SVG) עם PNG → שרשרת חילופין גנרית |
| 🔄 **סנכרון אוטומטי דגם** | מתזמן 24 שעות וממשק משתמש ידני כדי לסנכרן רשימות דגמים עבור ספקים מובנים ומותאמים אישית תואמי OpenAI |
| 🌐 **OpenCode Zen/Go** | שני ספקים חדשים מ-@kang-heewon דרך PR #530: שכבת חינם + שכבת מנוי דרך `OpencodeExecutor` |
| 🐛 **Gemini CLI OAuth** | שגיאה ניתנת לפעולה כאשר `GEMINI_OAUTH_CLIENT_SECRET` חסר ב-Docker (הייתה שגיאה סתמית של Google) |
| 🐛 **תצורת OpenCode** | `saveOpenCodeConfig()` כותב כעת כראוי TOML ל-`XDG_CONFIG_HOME` |
| 🐛 **עקיפת דגם מוצמד** | `body.model` מוגדר כראוי ל-`pinnedModel` על הגנת הקשר מטמון |
| 🐛 **קודקס/לולאת קלוד** | `tool_result` בלוקים מומרים כעת לטקסט כדי לעצור לולאות אינסופיות |
| 🐛 **הפניה מחדש לכניסה** | הכניסה לא קופאת עוד לאחר דילוג על הגדרת הסיסמה |
| 🐛 **נתיבי חלונות** | נתיבי MSYS2/Git-Bash (`/c/...`) מנורמלים ל-`C:\...` באופן אוטומטי |
---
@@ -199,7 +200,7 @@ _חבר כל כלי IDE או CLI המופעל על ידי AI דרך OmniRoute -
npm run system-info
```
זה יוצר `system-info.txt` עם גרסת Node.js, גרסת OmniRoute, פרטי מערכת ההפעלה, כלי CLI מותקנים (iflow, gemini, claude, codex, antigravity, droid וכו'), סטטוס Docker/PM2 וחבילות מערכת - כל מה שאנחנו צריכים כדי לשחזר את הבעיה במהירות. צרף את הקובץ ישירות לבעיית GitHub שלך.
זה יוצר `system-info.txt` עם גרסת Node.js, גרסת OmniRoute, פרטי מערכת ההפעלה, כלי CLI מותקנים (qoder, gemini, claude, codex, antigravity, droid וכו'), סטטוס Docker/PM2 וחבילות מערכת - כל מה שאנחנו צריכים כדי לשחזר את הבעיה במהירות. צרף את הקובץ ישירות לבעיית GitHub שלך.
---
@@ -225,7 +226,7 @@ npm run system-info
│ ↓ budget limit
├─→ [Tier 3: CHEAP] GLM ($0.6/1M), MiniMax ($0.2/1M)
│ ↓ budget limit
└─→ [Tier 4: FREE] iFlow, Qwen, Kiro (unlimited)
└─→ [Tier 4: FREE] Qoder, Qwen, Kiro (unlimited)
Result: Never stop coding, minimal cost
```
@@ -292,7 +293,7 @@ OpenAI משתמש בפורמט אחד, קלוד (אנתרופיק) משתמש ב
**איך OmniRoute פותר את זה:**
- **ספקי שכבת חינם מובנית** - תמיכה מקורית עבור 100% ספקים חינמיים: iFlow (5 דגמים ללא הגבלה דרך OAuth: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2), Qwen (4 unlimited-qwens,-rs) qwen3-coder-flash, qwen3-coder-next, vision-model), Kiro (קלוד + AWS Builder ID בחינם), Gemini CLI (180K אסימונים/חודש חינם)
- **ספקי שכבת חינם מובנית** - תמיכה מקורית עבור 100% ספקים חינמיים: Qoder (5 דגמים ללא הגבלה דרך OAuth: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2), Qwen (4 unlimited-qwens,-rs) qwen3-coder-flash, qwen3-coder-next, vision-model), Kiro (קלוד + AWS Builder ID בחינם), Gemini CLI (180K אסימונים/חודש חינם)
- **Ollama Cloud** - דגמי Ollama המתארחים בענן ב-`api.ollama.com` עם שכבת "שימוש קל" בחינם; השתמש בקידומת `ollamacloud/<model>`
- **שילובים בחינם בלבד** — שרשרת `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = $0 לחודש עם אפס זמן השבתה
- **גישה חופשית ל-NVIDIA NIM** - גישה חופשית של ~40 RPM ל-dev-forever ל-70+ דגמים בכתובת build.nvidia.com (מעבר מנקודות זכות למגבלות תעריף טהורות)
@@ -356,7 +357,7 @@ Claude Code, Codex, Gemini CLI, Copilot - כולם משתמשים ב-OAuth 2.0
**איך OmniRoute פותר את זה:**
- **רענון אסימון אוטומטי** - אסימוני OAuth מתרעננים ברקע לפני פקיעת תוקף
- **OAuth 2.0 (PKCE) מובנה** - זרימה אוטומטית עבור Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
- **OAuth 2.0 (PKCE) מובנה** - זרימה אוטומטית עבור Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, Qoder
- ** OAuth מרובה חשבונות** - מספר חשבונות לכל ספק באמצעות חילוץ אסימון JWT/ID
- **OAuth LAN/תיקון מרחוק** - זיהוי IP פרטי עבור `redirect_uri` + מצב כתובת URL ידני עבור שרתים מרוחקים
- **OAuth Behind Nginx** - משתמש ב-`window.location.origin` לתאימות פרוקסי הפוכה
@@ -733,7 +734,7 @@ Outcome: deep fallback depth for deadline-critical workloads
| שלב | פעולה | ספקים לא נעולים |
| --- | ----------------------------------------------- | ------------------------------------------------------------------ |
| 1 | התחבר **Kiro** (AWS Builder ID OAuth) | קלוד סונטה 4.5, הייקו 4.5 — **ללא הגבלה** |
| 2 | חבר את **iFlow** (Google OAuth) | kimi-k2-thinking, qwen3-coder-plus, deepseek-r1... — **ללא הגבלה** |
| 2 | חבר את **Qoder** (Google OAuth) | kimi-k2-thinking, qwen3-coder-plus, deepseek-r1... — **ללא הגבלה** |
| 3 | חבר **Qwen** (קוד מכשיר) | qwen3-coder-plus, qwen3-coder-flash... — **ללא הגבלה** |
| 4 | חבר את **Gemini CLI** (Google OAuth) | gemini-3-flash, gemini-2.5-pro — **180K/mo חינם** |
| 5 | `/dashboard/combos` → תבנית ערימה חינם ($0)\*\* | Round-robin כל הספקים בחינם אוטומטית |
@@ -942,7 +943,7 @@ npm run electron:build:linux # Linux (.AppImage)
| | MiniMax M2.1 | $0.2/1 מיליון | גלגול של 5 שעות | האפשרות הזולה ביותר |
| | Kimi K2.5 (Moonshot API) 🆕 | תשלום לפי שימוש | אין | גישה ישירה ל-Monshot API |
| | קימי K2 | 9 $ לחודש דירה | 10 מיליון אסימונים לחודש | עלות צפויה |
| **🆓 חינם** | iFlow | **$0** | ללא הגבלה | 5 דגמים ללא הגבלה |
| **🆓 חינם** | Qoder | **$0** | ללא הגבלה | 5 דגמים ללא הגבלה |
| | קוון | **$0** | ללא הגבלה | 4 דגמים ללא הגבלה |
| | קירו | **$0** | ללא הגבלה | קלוד סונטה/הייקו (AWS Builder) |
| | LongCat Flash-Lite 🆕 | **$0** (50 מיליון טוקי ליום 🔥) | 1 RPS | המכסה החינמית הגדולה ביותר על פני כדור הארץ |
@@ -957,7 +958,7 @@ npm run electron:build:linux # Linux (.AppImage)
```
# 🆓 Ultimate Free Stack 2026 — 11 Providers, $0 Forever
Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
Qwen (qw/) → qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next UNLIMITED
@@ -987,7 +988,7 @@ Cerebras (cerebras/) → Llama/Qwen world-fastest — 1M tok/day
| `claude-haiku-4.5` | `kr/` | **ללא הגבלה** | אין מכסה יומית מדווחת |
| `claude-opus-4.6` | `kr/` | **ללא הגבלה** | אופוס אחרון דרך קירו |
### דגמי IFLOW (OAuth בחינם - ללא כרטיס אשראי)
### דגמי QODER (OAuth בחינם - ללא כרטיס אשראי)
| דגם | קידומת | הגבלה | מגבלת שיעור |
| ------------------ | ------ | ------------- | -------------- |
@@ -1086,7 +1087,7 @@ Cerebras (cerebras/) → Llama/Qwen world-fastest — 1M tok/day
>
> ```
> Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
> iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
> Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
> Qwen (qw/) → qwen3-coder models UNLIMITED
@@ -1216,31 +1217,33 @@ OmniRoute v2.0 בנויה כפלטפורמה תפעולית, לא רק כפרו
### 📊 יכולת תצפית וניתוח
| תכונה | מה זה עושה |
| ------------------------------------ | ---------------------------------------------- |
| 📝 **בקשה + רישום פרוקסי** | בקשה/תשובה מלאה ורישום פרוקסי |
| 📋 **לוח מחוונים של יומנים מאוחדים** | תצוגות בקשה, פרוקסי, ביקורת ומסוף בעמוד אחד |
| 🔍 **בקש טלמטריה** | חביון p50/p95/p99 ומעקב אחר בקשות |
| 🏥 **לוח מחוונים לבריאות** | זמן פעולה, מצבי מפסק, נעילות, סטטיסטיקות מטמון |
| 💰 **מעקב עלויות** | בקרות תקציב ונראות תמחור לפי דגם |
| 📈 **הדמיות של אנליטיקס** | תובנות שימוש במודל/ספק ותצוגות מגמה |
| 🧪 **מסגרת הערכה** | בדיקת סט זהב עם אסטרטגיות התאמה הניתנות להגדרה |
| תכונה | מה זה עושה |
| ------------------------------------ | ---------------------------------------------------- |
| 📝 **בקשה + רישום פרוקסי** | בקשה/תשובה מלאה ורישום פרוקסי |
| 📉 **Streamed Detailed Logs** 🆕 | Reconstructs SSE payload streams cleanly into the UI |
| 📋 **לוח מחוונים של יומנים מאוחדים** | תצוגות בקשה, פרוקסי, ביקורת ומסוף בעמוד אחד |
| 🔍 **בקש טלמטריה** | חביון p50/p95/p99 ומעקב אחר בקשות |
| 🏥 **לוח מחוונים לבריאות** | זמן פעולה, מצבי מפסק, נעילות, סטטיסטיקות מטמון |
| 💰 **מעקב עלויות** | בקרות תקציב ונראות תמחור לפי דגם |
| 📈 **הדמיות של אנליטיקס** | תובנות שימוש במודל/ספק ותצוגות מגמה |
| 🧪 **מסגרת הערכה** | בדיקת סט זהב עם אסטרטגיות התאמה הניתנות להגדרה |
### ☁️ פריסה ופלטפורמה
| תכונה | מה זה עושה |
| ---------------------------------- | ------------------------------------------------ |
| 🌐 **פרוס בכל מקום** | סביבות Localhost, VPS, Docker, ענן |
| 💾 **סנכרון ענן** | סנכרון תצורה באמצעות Cloud Worker |
| 🔄 **גיבוי/שחזור** | זרימות יצוא/יבוא והתאוששות מאסון |
| 🧙 **אשף העלייה למטוס** | התקנה מודרכת הפעלה ראשונה |
| 🔧 **לוח המחוונים של כלי CLI** | הגדרה בלחיצה אחת לכלי קידוד פופולריים |
| 🎮 **מגרש משחקים דגם** | בדוק כל ספק/דגם/נקודת קצה מלוח המחוונים |
| 🔏 **CLI Fingerprint Toggle** | התאמת טביעת אצבע לכל ספק בהגדרות > אבטחה |
| 🌐 **i18n (30 שפות)** | לוח מחוונים מלא + תמיכה בשפת מסמכים עם כיסוי RTL |
| 🧹 **נקה את כל הדגמים** | ניקוי רשימת דגמים בלחיצה אחת בפרטי הספק |
| 📋 **תבניות גיליון** | תבניות GitHub סטנדרטיות עבור באגים ותכונות |
| 📂 **ספריית נתונים מותאמים אישית** | `DATA_DIR` ביטול עבור מיקום אחסון |
| תכונה | מה זה עושה |
| ---------------------------------- | --------------------------------------------------------- |
| 🌐 **פרוס בכל מקום** | סביבות Localhost, VPS, Docker, ענן |
| 💾 **סנכרון ענן** | סנכרון תצורה באמצעות Cloud Worker |
| 🔄 **גיבוי/שחזור** | זרימות יצוא/יבוא והתאוששות מאסון |
| 🧙 **אשף העלייה למטוס** | התקנה מודרכת הפעלה ראשונה |
| 🔧 **לוח המחוונים של כלי CLI** | הגדרה בלחיצה אחת לכלי קידוד פופולריים |
| 🎮 **מגרש משחקים דגם** | בדוק כל ספק/דגם/נקודת קצה מלוח המחוונים |
| 🔏 **CLI Fingerprint Toggle** | התאמת טביעת אצבע לכל ספק בהגדרות > אבטחה |
| 🌐 **i18n (30 שפות)** | לוח מחוונים מלא + תמיכה בשפת מסמכים עם כיסוי RTL |
| 🧹 **נקה את כל הדגמים** | ניקוי רשימת דגמים בלחיצה אחת בפרטי הספק |
| 👁️ **Sidebar Controls** 🆕 | Hide components and integrations from Appearance Settings |
| 📋 **תבניות גיליון** | תבניות GitHub סטנדרטיות עבור באגים ותכונות |
| 📂 **ספריית נתונים מותאמים אישית** | `DATA_DIR` ביטול עבור מיקום אחסון |
### תכונה Deep Deep
@@ -1534,11 +1537,11 @@ Models:
<details>
<summary><b>🆓 FREE Providers (Emergency Backup)</b></summary>
### iFlow (5 דגמים בחינם באמצעות OAuth)
### Qoder (5 דגמים בחינם באמצעות OAuth)
```bash
Dashboard → Connect iFlow
iFlow OAuth login
Dashboard → Connect Qoder
Qoder OAuth login
→ Unlimited usage
Models:
@@ -1736,7 +1739,7 @@ opencode
- בדוק סטטיסטיקת שימוש בלוח המחוונים ← עלויות
- החלף את הדגם הראשי ל-GLM/MiniMax
- השתמש בשכבה חינמית (Gemini CLI, iFlow) עבור משימות לא קריטיות
- השתמש בשכבה חינמית (Gemini CLI, Qoder) עבור משימות לא קריטיות
**יציאות לוח המחוונים/API שגויות**
+25 -22
View File
@@ -36,6 +36,7 @@ _Az univerzális API-proxy egy végpont, 67+ szolgáltató, nulla állásid
| ✅ **Útvonal ellenőrzése** | Mind a 176 API-útvonal érvényes Zod-sémákkal + `validateBody()` — CI `check:route-validation:t06` |
| 🐛 **omniModel címkeszivárgás** | A belső `<omniModel>` címkék többé nem szivárognak ki az ügyfelekhez az SSE streaming válaszaiban (#585) |
| 🔑 **Regisztrált kulcsok API** | API-kulcsok automatikus rendelkezésre bocsátása a `POST /api/v1/registered-keys`-on keresztül szolgáltatónkénti/fiókonkénti kvóta-érvényesítéssel, idempotenciával, SHA-256 tárhellyel és opcionális GitHub-hibajelentéssel |
| 👁️ **Scoped API Key Reveal** 🆕 | Opt-in recovery of API keys via `ALLOW_API_KEY_REVEAL` |
| 🎨 ** Szolgáltatói ikonok** | 130+ szolgáltatói logó a `@lobehub/icons` (SVG)-n keresztül PNG-vel → általános tartaléklánc |
| 🔄 **Modell automatikus szinkronizálása** | 24 órás ütemező és kézi felhasználói felület kapcsoló a beépített és egyéni OpenAI-kompatibilis szolgáltatók modelllistáinak szinkronizálásához |
| 🌐 **OpenCode Zen/Go** | Két új szolgáltató a @kang-heewontól a PR #530-on keresztül: ingyenes szint + előfizetési szint a következőn keresztül: `OpencodeExecutor` |
@@ -199,7 +200,7 @@ Egy probléma megnyitásakor futtassa a system-info parancsot, és csatolja a ge
npm run system-info
```
Ez létrehoz egy `system-info.txt`-t a Node.js verziójával, az OmniRoute verziójával, az operációs rendszer részleteivel, a telepített CLI-eszközökkel (iflow, gemini, claude, codex, antigravitáció, droid stb.), Docker/PM2 állapottal és rendszercsomagokkal mindennel, amire szükségünk van a probléma gyors reprodukálásához. Csatolja a fájlt közvetlenül a GitHub-problémához.
Ez létrehoz egy `system-info.txt`-t a Node.js verziójával, az OmniRoute verziójával, az operációs rendszer részleteivel, a telepített CLI-eszközökkel (qoder, gemini, claude, codex, antigravitáció, droid stb.), Docker/PM2 állapottal és rendszercsomagokkal mindennel, amire szükségünk van a probléma gyors reprodukálásához. Csatolja a fájlt közvetlenül a GitHub-problémához.
---
@@ -225,7 +226,7 @@ Ez létrehoz egy `system-info.txt`-t a Node.js verziójával, az OmniRoute verzi
│ ↓ budget limit
├─→ [Tier 3: CHEAP] GLM ($0.6/1M), MiniMax ($0.2/1M)
│ ↓ budget limit
└─→ [Tier 4: FREE] iFlow, Qwen, Kiro (unlimited)
└─→ [Tier 4: FREE] Qoder, Qwen, Kiro (unlimited)
Result: Never stop coding, minimal cost
```
@@ -292,7 +293,7 @@ Nem mindenki fizethet havi 20200 dollárt az AI-előfizetésekért. A feltör
**Hogyan oldja meg az OmniRoute:**
- **Beépített ingyenes szolgáltatók** - Natív támogatás a 100%-ban ingyenes szolgáltatókhoz: iFlow (5 korlátlan modell az OAuth-on keresztül: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2), Qwen-modellek: 4 unqlim-plus3 qwen3-coder-flash, qwen3-coder-next, vision-model), Kiro (Claude + AWS Builder ID ingyen), Gemini CLI (180 000 token/hónap ingyenes)
- **Beépített ingyenes szolgáltatók** - Natív támogatás a 100%-ban ingyenes szolgáltatókhoz: Qoder (5 korlátlan modell az OAuth-on keresztül: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2), Qwen-modellek: 4 unqlim-plus3 qwen3-coder-flash, qwen3-coder-next, vision-model), Kiro (Claude + AWS Builder ID ingyen), Gemini CLI (180 000 token/hónap ingyenes)
- **Ollama Cloud** Felhőben tárolt Ollama modellek a `api.ollama.com` címen ingyenes „Light usage” szinttel; használja az `ollamacloud/<model>` előtagot
- **Csak ingyenes kombók** - Lánc `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = 0 USD/hó nulla állásidővel
- **NVIDIA NIM ingyenes hozzáférés** ~40 RPM fejlesztői örökké ingyenes hozzáférés több mint 70 modellhez a build.nvidia.com oldalon (áttérés a kreditekről a tiszta sebességkorlátokra)
@@ -356,7 +357,7 @@ Claude Code, Codex, Gemini CLI, Copilot mindegyik az OAuth 2.0-t használja
**Hogyan oldja meg az OmniRoute:**
- **Automatikus tokenfrissítés** - Az OAuth-tokenek a háttérben frissülnek a lejárat előtt
- **OAuth 2.0 (PKCE) beépített** - Automatikus áramlás Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow számára
- **OAuth 2.0 (PKCE) beépített** - Automatikus áramlás Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, Qoder számára
- **Multi-Account OAuth** - Több fiók szolgáltatónként a JWT/ID token kivonattal
- **OAuth LAN/Távoli javítás** - Privát IP-észlelés a `redirect_uri` számára + kézi URL mód távoli szerverekhez
- **OAuth az Nginx mögött** - A `window.location.origin` kódot használja a fordított proxy kompatibilitáshoz
@@ -733,7 +734,7 @@ Outcome: deep fallback depth for deadline-critical workloads
| lépés | Akció | Szolgáltatók feloldva |
| ----- | ---------------------------------------------------- | --------------------------------------------------------------------- |
| 1 | Csatlakozás **Kiro** (AWS Builder ID OAuth) | Claude Sonnet 4.5, Haiku 4.5 — **korlátlan** |
| 2 | Csatlakoztassa az **iFlow-t** (Google OAuth) | kimi-k2-gondolkodás, qwen3-coder-plus, deepseek-r1... — **korlátlan** |
| 2 | Csatlakoztassa az **Qoder-t** (Google OAuth) | kimi-k2-gondolkodás, qwen3-coder-plus, deepseek-r1... — **korlátlan** |
| 3 | Csatlakoztassa a **Qwen** (eszközkód) | qwen3-coder-plus, qwen3-coder-flash... — **korlátlan** |
| 4 | Csatlakozás **Gemini CLI** (Google OAuth) | gemini-3-flash, gemini-2.5-pro **180K/hó ingyenes** |
| 5 | `/dashboard/combos`**Ingyenes köteg ($0)** sablon | Körbe-körbe minden ingyenes szolgáltató automatikusan |
@@ -942,7 +943,7 @@ Ha minimalizálja, az OmniRoute a tálcán él, gyors műveletekkel:
| | MiniMax M2.1 | 0,2 USD/1M | 5 órás gurulás | Legolcsóbb lehetőség |
| | Kimi K2.5 (Moonshot API) 🆕 | Felhasználásonkénti fizetés | Nincs | Közvetlen Moonshot API hozzáférés |
| | Kimi K2 | 9 USD/hó lakás | 10 millió token/hó | Előrelátható költség |
| **🆓 INGYENES** | iFlow | **0 USD** | Korlátlan | 5 modell korlátlan |
| **🆓 INGYENES** | Qoder | **0 USD** | Korlátlan | 5 modell korlátlan |
| | Qwen | **0 USD** | Korlátlan | 4 modell korlátlan |
| | Kiro | **0 USD** | Korlátlan | Claude Sonnet/Haiku (AWS Builder) |
| | LongCat Flash-Lite 🆕 | **0 USD** (50 millió tok/nap 🔥) | 1 RPS | A legnagyobb ingyenes kvóta a Földön |
@@ -957,7 +958,7 @@ Ha minimalizálja, az OmniRoute a tálcán él, gyors műveletekkel:
```
# 🆓 Ultimate Free Stack 2026 — 11 Providers, $0 Forever
Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
Qwen (qw/) → qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next UNLIMITED
@@ -987,7 +988,7 @@ Cerebras (cerebras/) → Llama/Qwen world-fastest — 1M tok/day
| `claude-haiku-4.5` | `kr/` | **Korlátlan** | Nincs bejelentett napi felső határ |
| `claude-opus-4.6` | `kr/` | **Korlátlan** | Legújabb Opus via Kiro |
### IFLOW MODELLEK (ingyenes OAuth hitelkártya nélkül)
### QODER MODELLEK (ingyenes OAuth hitelkártya nélkül)
| Modell | Előtag | Limit | Rate Limit |
| ------------------ | ------ | ------------- | ----------------------------- |
@@ -1086,7 +1087,7 @@ Ingyenesen elérhető: `qwen3-235b-a22b-instruct-2507` (Qwen3 235B!), `llama-3.1
>
> ```
> Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
> iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
> Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
> Qwen (qw/) → qwen3-coder models UNLIMITED
@@ -1216,15 +1217,16 @@ Az OmniRoute v2.0 működési platformként készült, nem csak közvetítő pro
### 📊 Observability & Analytics
| Feature | What It Does |
| ------------------------------- | ----------------------------------------------------- |
| 📝 **Request + Proxy Logging** | Full request/response and proxy logging |
| 📋 **Unified Logs Dashboard** | Request, proxy, audit, and console views in one page |
| 🔍 **Request Telemetry** | p50/p95/p99 latency and request tracing |
| 🏥 **Health Dashboard** | Uptime, breaker states, lockouts, cache stats |
| 💰 **Cost Tracking** | Budget controls and per-model pricing visibility |
| 📈 **Analytics Visualizations** | Model/provider usage insights and trend views |
| 🧪 **Evaluation Framework** | Golden set testing with configurable match strategies |
| Feature | What It Does |
| -------------------------------- | ----------------------------------------------------- |
| 📝 **Request + Proxy Logging** | Full request/response and proxy logging |
| 📉 **Streamed Detailed Logs** 🆕 | Reconstructs SSE payload streams cleanly into the UI |
| 📋 **Unified Logs Dashboard** | Request, proxy, audit, and console views in one page |
| 🔍 **Request Telemetry** | p50/p95/p99 latency and request tracing |
| 🏥 **Health Dashboard** | Uptime, breaker states, lockouts, cache stats |
| 💰 **Cost Tracking** | Budget controls and per-model pricing visibility |
| 📈 **Analytics Visualizations** | Model/provider usage insights and trend views |
| 🧪 **Evaluation Framework** | Golden set testing with configurable match strategies |
### ☁️ Deployment & Platform
@@ -1239,6 +1241,7 @@ Az OmniRoute v2.0 működési platformként készült, nem csak közvetítő pro
| 🔏 **CLI ujjlenyomat kapcsoló** | Szolgáltatónkénti ujjlenyomat-egyeztetés a Beállítások > Biztonság |
| 🌐 **i18n (30 nyelv)** | Teljes irányítópult + dokumentumok nyelvi támogatása RTL lefedettséggel |
| 🧹 **Minden modell törlése** | Egykattintásos modelllista törlése a szolgáltató adatai között |
| 👁️ **Sidebar Controls** 🆕 | Hide components and integrations from Appearance Settings |
| 📋 **Kiadássablonok** | Szabványos GitHub-sablonok hibákhoz és szolgáltatásokhoz |
| 📂 **Egyéni adattár** | `DATA_DIR` felülírása a tárolási helyhez |
@@ -1534,11 +1537,11 @@ Models:
<details>
<summary><b>🆓 INGYENES szolgáltatók (vészhelyzeti biztonsági mentés)</b></summary>
### iFlow (5 INGYENES modell OAuth-on keresztül)
### Qoder (5 INGYENES modell OAuth-on keresztül)
```bash
Dashboard → Connect iFlow
iFlow OAuth login
Dashboard → Connect Qoder
Qoder OAuth login
→ Unlimited usage
Models:
@@ -1736,7 +1739,7 @@ opencode
- Ellenőrizze a használati statisztikákat az Irányítópult → Költségek menüpontban
- Állítsa át az elsődleges modellt GLM/MiniMax-ra
- Használjon ingyenes réteget (Gemini CLI, iFlow) a nem kritikus feladatokhoz
- Használjon ingyenes réteget (Gemini CLI, Qoder) a nem kritikus feladatokhoz
**Az irányítópult/API portok hibásak**
+16 -13
View File
@@ -36,6 +36,7 @@ _Proksi API universal Anda — satu titik akhir, 67+ penyedia, tanpa waktu henti
| ✅ **Validasi Rute** | Semua 176 rute API sekarang divalidasi dengan skema Zod + `validateBody()` — tiket CI `check:route-validation:t06` |
| 🐛 **Kebocoran Tag omniModel** | Tag `<omniModel>` internal tidak lagi bocor ke klien dalam respons streaming SSE (#585) |
| 🔑 **API Kunci Terdaftar** | Kunci API penyediaan otomatis melalui `POST /api/v1/registered-keys` dengan penerapan kuota per penyedia/akun, idempotensi, penyimpanan SHA-256, dan pelaporan masalah GitHub opsional |
| 👁️ **Scoped API Key Reveal** 🆕 | Opt-in recovery of API keys via `ALLOW_API_KEY_REVEAL` |
| 🎨 **Ikon Penyedia** | 130+ logo penyedia melalui `@lobehub/icons` (SVG) dengan PNG → rantai fallback umum |
| 🔄 **Sinkronisasi Otomatis Model** | Penjadwal 24 jam dan UI manual beralih untuk menyinkronkan daftar model untuk penyedia bawaan dan kustom yang kompatibel dengan OpenAI |
| 🌐 **OpenCode Zen/Go** | Dua penyedia baru dari @kang-heewon melalui PR #530: tingkat gratis + tingkat berlangganan melalui `OpencodeExecutor` |
@@ -199,7 +200,7 @@ Saat membuka masalah, jalankan perintah info sistem dan lampirkan file yang diha
npm run system-info
```
Ini menghasilkan `system-info.txt` dengan versi Node.js, versi OmniRoute, detail OS, alat CLI yang diinstal (iflow, gemini, claude, codex, antigravity, droid, dll.), status Docker/PM2, dan paket sistem — semua yang kami perlukan untuk mereproduksi masalah Anda dengan cepat. Lampirkan file langsung ke masalah GitHub Anda.
Ini menghasilkan `system-info.txt` dengan versi Node.js, versi OmniRoute, detail OS, alat CLI yang diinstal (qoder, gemini, claude, codex, antigravity, droid, dll.), status Docker/PM2, dan paket sistem — semua yang kami perlukan untuk mereproduksi masalah Anda dengan cepat. Lampirkan file langsung ke masalah GitHub Anda.
---
@@ -225,7 +226,7 @@ Ini menghasilkan `system-info.txt` dengan versi Node.js, versi OmniRoute, detail
│ ↓ budget limit
├─→ [Tier 3: CHEAP] GLM ($0.6/1M), MiniMax ($0.2/1M)
│ ↓ budget limit
└─→ [Tier 4: FREE] iFlow, Qwen, Kiro (unlimited)
└─→ [Tier 4: FREE] Qoder, Qwen, Kiro (unlimited)
Result: Never stop coding, minimal cost
```
@@ -292,7 +293,7 @@ Tidak semua orang mampu membayar $20200/bulan untuk berlangganan AI. Pelajar,
**Bagaimana OmniRoute menyelesaikannya:**
- **Penyedia Tingkat Gratis Bawaan** — Dukungan asli untuk 100% penyedia gratis: iFlow (5 model tak terbatas melalui OAuth: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2), Qwen (4 model tak terbatas: qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next, vision-model), Kiro (Claude + AWS Builder ID gratis), Gemini CLI (gratis 180 ribu token/bulan)
- **Penyedia Tingkat Gratis Bawaan** — Dukungan asli untuk 100% penyedia gratis: Qoder (5 model tak terbatas melalui OAuth: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2), Qwen (4 model tak terbatas: qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next, vision-model), Kiro (Claude + AWS Builder ID gratis), Gemini CLI (gratis 180 ribu token/bulan)
- **Ollama Cloud** — Model Ollama yang dihosting cloud di `api.ollama.com` dengan tingkat "Penggunaan ringan" gratis; gunakan awalan `ollamacloud/<model>`
- **Kombo Khusus Gratis** — Rantai `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = $0/bulan tanpa downtime
- **Akses Gratis NVIDIA NIM** — akses gratis dev-selamanya ~40 RPM ke 70+ model di build.nvidia.com (beralih dari kredit ke batas tarif murni)
@@ -356,7 +357,7 @@ Claude Code, Codex, Gemini CLI, Copilot — semuanya menggunakan OAuth 2.0 denga
**Bagaimana OmniRoute menyelesaikannya:**
- **Penyegaran Token Otomatis** — Penyegaran token OAuth di latar belakang sebelum masa berlakunya habis
- **OAuth 2.0 (PKCE) Bawaan** — Aliran otomatis untuk Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
- **OAuth 2.0 (PKCE) Bawaan** — Aliran otomatis untuk Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, Qoder
- **OAuth Multi-Akun** — Beberapa akun per penyedia melalui ekstraksi token JWT/ID
- **OAuth LAN/Remote Fix** — Deteksi IP pribadi untuk `redirect_uri` + mode URL manual untuk server jarak jauh
- **OAuth Dibalik Nginx** — Menggunakan `window.location.origin` untuk kompatibilitas proxy terbalik
@@ -733,7 +734,7 @@ Outcome: deep fallback depth for deadline-critical workloads
| Langkah | Aksi | Penyedia Tidak Terkunci |
| ------- | ------------------------------------------------------ | ------------------------------------------------------------------------ |
| 1 | Hubungkan **Kiro** (AWS Builder ID OAuth) | Claude Sonnet 4.5, Haiku 4.5 — **tidak terbatas** |
| 2 | Hubungkan **iFlow** (Google OAuth) | pemikiran kimi-k2, qwen3-coder-plus, deepseek-r1... — **tidak terbatas** |
| 2 | Hubungkan **Qoder** (Google OAuth) | pemikiran kimi-k2, qwen3-coder-plus, deepseek-r1... — **tidak terbatas** |
| 3 | Hubungkan **Qwen** (Kode Perangkat) | qwen3-coder-plus, qwen3-coder-flash... — **tidak terbatas** |
| 4 | Hubungkan **Gemini CLI** (Google OAuth) | gemini-3-flash, gemini-2.5-pro — **180K/bln gratis** |
| 5 | `/dashboard/combos`**Templat Tumpukan Gratis ($0)** | Round-robin semua penyedia gratis secara otomatis |
@@ -942,7 +943,7 @@ Saat diminimalkan, OmniRoute ada di baki sistem Anda dengan tindakan cepat:
| | MiniMax M2.1 | $0,2/1 juta | 5 jam bergulir | Pilihan termurah |
| | Kimi K2.5 (API Moonshot) 🆕 | Bayar per penggunaan | Tidak ada | Akses langsung Moonshot API |
| | Kimi K2 | $9/bln tetap | 10 juta token/bln | Biaya yang dapat diprediksi |
| **🆓 GRATIS** | iFlow | **$0** | Tidak terbatas | 5 model tidak terbatas |
| **🆓 GRATIS** | Qoder | **$0** | Tidak terbatas | 5 model tidak terbatas |
| | Qwen | **$0** | Tidak terbatas | 4 model tidak terbatas |
| | Kiro | **$0** | Tidak terbatas | Claude Soneta/Haiku (Pembuat AWS) |
| | LongCat Flash-Lite 🆕 | **$0** (50 juta tok/hari 🔥) | 1RPS | Kuota gratis terbesar di dunia |
@@ -957,7 +958,7 @@ Saat diminimalkan, OmniRoute ada di baki sistem Anda dengan tindakan cepat:
```
# 🆓 Ultimate Free Stack 2026 — 11 Providers, $0 Forever
Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
Qwen (qw/) → qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next UNLIMITED
@@ -987,7 +988,7 @@ Cerebras (cerebras/) → Llama/Qwen world-fastest — 1M tok/day
| `claude-haiku-4.5` | `kr/` | **Tidak terbatas** | Tidak ada batas harian yang dilaporkan |
| `claude-opus-4.6` | `kr/` | **Tidak terbatas** | Opus Terbaru melalui Kiro |
### 🟢 MODEL IFLOW (OAuth Gratis — Tanpa Kartu Kredit)
### 🟢 MODEL QODER (OAuth Gratis — Tanpa Kartu Kredit)
| Model | Awalan | Batasi | Batas Tarif |
| ------------------ | ------ | ------------------ | ------------------------------- |
@@ -1086,7 +1087,7 @@ Tersedia gratis: `qwen3-235b-a22b-instruct-2507` (Qwen3 235B!), `llama-3.1-70b-i
>
> ```
> Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
> iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
> Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
> Qwen (qw/) → qwen3-coder models UNLIMITED
@@ -1219,6 +1220,7 @@ OmniRoute v2.0 dibangun sebagai platform operasional, bukan hanya proxy relai.
| Fitur | Apa Fungsinya |
| ------------------------------------- | ---------------------------------------------------------------------- |
| 📝 **Permintaan + Pencatatan Proksi** | Permintaan/tanggapan lengkap dan pencatatan proksi |
| 📉 **Streamed Detailed Logs** 🆕 | Reconstructs SSE payload streams cleanly into the UI |
| 📋 **Dasbor Log Terpadu** | Tampilan permintaan, proksi, audit, dan konsol dalam satu halaman |
| 🔍 **Permintaan Telemetri** | latensi p50/p95/p99 dan penelusuran permintaan |
| 🏥 **Dasbor Kesehatan** | Waktu aktif, status pemutus, penguncian, statistik cache |
@@ -1239,6 +1241,7 @@ OmniRoute v2.0 dibangun sebagai platform operasional, bukan hanya proxy relai.
| 🔏 **Tolak Sidik Jari CLI** | Pencocokan sidik jari per penyedia di Pengaturan > Keamanan |
| 🌐 **i18n (30 bahasa)** | Dasbor lengkap + dukungan bahasa dokumen dengan cakupan RTL |
| 🧹 **Hapus Semua Model** | Pembersihan daftar model sekali klik di detail penyedia |
| 👁️ **Sidebar Controls** 🆕 | Hide components and integrations from Appearance Settings |
| 📋 **Template Masalah** | Templat GitHub standar untuk bug dan fitur |
| 📂 **Direktori Data Khusus** | `DATA_DIR` penggantian untuk lokasi penyimpanan |
@@ -1534,11 +1537,11 @@ Models:
<details>
<summary><b>🆓 Penyedia GRATIS (Cadangan Darurat)</b></summary>
### iFlow (5 model GRATIS melalui OAuth)
### Qoder (5 model GRATIS melalui OAuth)
```bash
Dashboard → Connect iFlow
iFlow OAuth login
Dashboard → Connect Qoder
Qoder OAuth login
→ Unlimited usage
Models:
@@ -1736,7 +1739,7 @@ opencode
- Periksa statistik penggunaan di Dashboard → Biaya
- Ganti model utama ke GLM/MiniMax
- Gunakan tingkat gratis (Gemini CLI, iFlow) untuk tugas-tugas yang tidak penting
- Gunakan tingkat gratis (Gemini CLI, Qoder) untuk tugas-tugas yang tidak penting
**Port dasbor/API salah**
+11 -8
View File
@@ -36,6 +36,7 @@ _आपका सार्वभौमिक एपीआई प्रॉक्
| ✅ **रूट सत्यापन** | सभी 176 एपीआई रूट अब ज़ॉड स्कीमा + `validateBody()` — CI `check:route-validation:t06` पास के साथ मान्य हैं |
| 🐛 **ओम्नीमॉडल टैग लीक** | आंतरिक `<omniModel>` टैग अब SSE स्ट्रीमिंग प्रतिक्रियाओं में ग्राहकों के लिए लीक नहीं होंगे (#585) |
| 🔑 **पंजीकृत कुंजी एपीआई** | प्रति-प्रदाता/खाता कोटा प्रवर्तन, निष्क्रियता, SHA-256 भंडारण और वैकल्पिक GitHub समस्या रिपोर्टिंग के साथ `POST /api/v1/registered-keys` के माध्यम से स्वचालित-प्रावधान API कुंजियाँ |
| 👁️ **Scoped API Key Reveal** 🆕 | Opt-in recovery of API keys via `ALLOW_API_KEY_REVEAL` |
| 🎨 **प्रदाता चिह्न** | पीएनजी के साथ `@lobehub/icons` (एसवीजी) के माध्यम से 130+ प्रदाता लोगो → सामान्य फ़ॉलबैक श्रृंखला |
| 🔄 **मॉडल ऑटो-सिंक** | बिल्ट-इन और कस्टम ओपनएआई-संगत प्रदाताओं के लिए मॉडल सूचियों को सिंक करने के लिए 24 घंटे शेड्यूलर और मैनुअल यूआई टॉगल |
| 🌐 **ओपनकोड ज़ेन/गो** | @kang-heewon से PR #530 के माध्यम से दो नए प्रदाता: निःशुल्क स्तर + `OpencodeExecutor` के माध्यम से सदस्यता स्तर |
@@ -200,7 +201,7 @@ _OmniRoute के माध्यम से किसी भी AI-संचा
npm run system-info
```
यह आपके Node.js संस्करण, ओमनीरूट संस्करण, OS विवरण, स्थापित CLI उपकरण (iflow, जेमिनी, क्लाउड, कोडेक्स, एंटीग्रेविटी, ड्रॉइड, आदि), Docker/PM2 स्थिति और सिस्टम पैकेज के साथ एक `system-info.txt` उत्पन्न करता है - वह सब कुछ जो हमें आपकी समस्या को शीघ्रता से पुन: उत्पन्न करने के लिए चाहिए। फ़ाइल को सीधे अपने GitHub मुद्दे से संलग्न करें।
यह आपके Node.js संस्करण, ओमनीरूट संस्करण, OS विवरण, स्थापित CLI उपकरण (qoder, जेमिनी, क्लाउड, कोडेक्स, एंटीग्रेविटी, ड्रॉइड, आदि), Docker/PM2 स्थिति और सिस्टम पैकेज के साथ एक `system-info.txt` उत्पन्न करता है - वह सब कुछ जो हमें आपकी समस्या को शीघ्रता से पुन: उत्पन्न करने के लिए चाहिए। फ़ाइल को सीधे अपने GitHub मुद्दे से संलग्न करें।
---
@@ -274,7 +275,7 @@ OpenAI/Codex जैसे प्रदाता कुछ भौगोलिक
**ओम्नीरूट इसे कैसे हल करता है:**
- **फ्री टियर प्रोवाइडर बिल्ट-इन** - 100% फ्री प्रदाताओं के लिए मूल समर्थन: iFlow (OAuth के माध्यम से 5 असीमित मॉडल: किमी-के2-थिंकिंग, क्वेन3-कोडर-प्लस, डीपसीक-आर1, मिनिमैक्स-एम2, किमी-के2), क्वेन (4 असीमित मॉडल: क्वेन3-कोडर-प्लस, क्वेन3-कोडर-फ्लैश, क्वेन3-कोडर-नेक्स्ट, विज़न-मॉडल), किरो (क्लाउड + एडब्ल्यूएस बिल्डर आईडी मुफ़्त), जेमिनी सीएलआई (180K टोकन/माह मुफ़्त)
- **फ्री टियर प्रोवाइडर बिल्ट-इन** - 100% फ्री प्रदाताओं के लिए मूल समर्थन: Qoder (OAuth के माध्यम से 5 असीमित मॉडल: किमी-के2-थिंकिंग, क्वेन3-कोडर-प्लस, डीपसीक-आर1, मिनिमैक्स-एम2, किमी-के2), क्वेन (4 असीमित मॉडल: क्वेन3-कोडर-प्लस, क्वेन3-कोडर-फ्लैश, क्वेन3-कोडर-नेक्स्ट, विज़न-मॉडल), किरो (क्लाउड + एडब्ल्यूएस बिल्डर आईडी मुफ़्त), जेमिनी सीएलआई (180K टोकन/माह मुफ़्त)
- **ओलामा क्लाउड** - निःशुल्क "लाइट उपयोग" स्तर के साथ `api.ollama.com` पर क्लाउड-होस्टेड ओलामा मॉडल; `ollamacloud/<model>` उपसर्ग का उपयोग करें
- **केवल-निःशुल्क कॉम्बो** — चेन `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = $0/माह, शून्य डाउनटाइम के साथ
- **एनवीडिया एनआईएम फ्री एक्सेस** - ~40 आरपीएम डेव-बिल्ड.एनवीडिया.कॉम पर 70+ मॉडलों तक हमेशा के लिए मुफ्त एक्सेस (क्रेडिट से शुद्ध दर सीमा तक संक्रमण)
@@ -727,7 +728,7 @@ Outcome: deep fallback depth for deadline-critical workloads
| कदम | कार्रवाई | प्रदाता अनलॉक |
| --- | ------------------------------------------------------ | ---------------------------------------------------------- |
| 1 | कनेक्ट **किरो** (AWS बिल्डर आईडी OAuth) | क्लाउड सॉनेट 4.5, हाइकु 4.5 - **असीमित** |
| 2 | कनेक्ट करें **iFlow** (Google OAuth) | किमी-के2-सोच, क्वेन3-कोडर-प्लस, डीपसीक-आर1... — **असीमित** |
| 2 | कनेक्ट करें **Qoder** (Google OAuth) | किमी-के2-सोच, क्वेन3-कोडर-प्लस, डीपसीक-आर1... — **असीमित** |
| 3 | कनेक्ट **क्वेन** (डिवाइस कोड) | qwen3-कोडर-प्लस, qwen3-कोडर-फ़्लैश... — **असीमित** |
| 4 | कनेक्ट **मिथुन सीएलआई** (Google OAuth) | जेमिनी-3-फ़्लैश, जेमिनी-2.5-प्रो — **180K/महीना मुफ़्त** |
| 5 | `/dashboard/combos`**निःशुल्क स्टैक ($0)** टेम्पलेट | सभी मुफ़्त प्रदाताओं को स्वचालित रूप से राउंड-रॉबिन करें |
@@ -916,7 +917,7 @@ omniroute --mcp
| `claude-haiku-4.5` | `kr/` | **असीमित** | कोई रिपोर्ट नहीं की गई दैनिक सीमा |
| `claude-opus-4.6` | `kr/` | **असीमित** | किरो के माध्यम से नवीनतम रचना |
### 🟢 IFLOW मॉडल (निःशुल्क OAuth - कोई क्रेडिट कार्ड नहीं)
### 🟢 QODER मॉडल (निःशुल्क OAuth - कोई क्रेडिट कार्ड नहीं)
| मॉडल | उपसर्ग | सीमा | दर सीमा |
| ------------------ | ------ | ---------- | --------------------------- |
@@ -1015,7 +1016,7 @@ omniroute --mcp
>
> ```
> Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
> iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
> Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
> Qwen (qw/) → qwen3-coder models UNLIMITED
@@ -1141,6 +1142,7 @@ omniroute --mcp
| फ़ीचर | यह क्या करता है |
| -------------------------------- | ------------------------------------------------------- |
| 📝 **अनुरोध + प्रॉक्सी लॉगिंग** | पूर्ण अनुरोध/प्रतिक्रिया और प्रॉक्सी लॉगिंग |
| 📉 **Streamed Detailed Logs** 🆕 | Reconstructs SSE payload streams cleanly into the UI |
| 📋 **एकीकृत लॉग डैशबोर्ड** | एक पृष्ठ में अनुरोध, प्रॉक्सी, ऑडिट और कंसोल दृश्य |
| 🔍 **टेलीमेट्री के लिए अनुरोध** | p50/p95/p99 विलंबता और अनुरोध अनुरेखण |
| 🏥 **स्वास्थ्य डैशबोर्ड** | अपटाइम, ब्रेकर स्थिति, लॉकआउट, कैश आँकड़े |
@@ -1161,6 +1163,7 @@ omniroute --mcp
| 🔏 **सीएलआई फ़िंगरप्रिंट टॉगल** | सेटिंग्स > सुरक्षा | में प्रति प्रदाता फ़िंगरप्रिंट मिलान |
| 🌐 **i18n (30 भाषाएँ)** | पूर्ण डैशबोर्ड + आरटीएल कवरेज के साथ डॉक्स भाषा समर्थन |
| 🧹 **सभी मॉडल साफ़ करें** | प्रदाता विवरण में एक-क्लिक मॉडल सूची समाशोधन |
| 👁️ **Sidebar Controls** 🆕 | Hide components and integrations from Appearance Settings |
| 📋 **मुद्दा टेम्पलेट** | बग और सुविधाओं के लिए मानकीकृत GitHub टेम्पलेट |
| 📂 **कस्टम डेटा निर्देशिका** | भंडारण स्थान के लिए `DATA_DIR` ओवरराइड |
@@ -1447,11 +1450,11 @@ Models:
<summary><b>🆓 मुफ़्त प्रदाता (आपातकालीन बैकअप)</b></summary>
### iFlow (OAuth के माध्यम से 5 निःशुल्क मॉडल)
### Qoder (OAuth के माध्यम से 5 निःशुल्क मॉडल)
```bash
Dashboard → Connect iFlow
iFlow OAuth login
Dashboard → Connect Qoder
Qoder OAuth login
→ Unlimited usage
Models:
+16 -13
View File
@@ -36,6 +36,7 @@ _ユニバーサル API プロキシ - 1 つのエンドポイント、67 以上
| ✅ **ルート検証** | 176 個の API ルートすべてが Zod スキーマ + `validateBody()` — CI `check:route-validation:t06` パスで検証されるようになりました。 |
| 🐛 **omniModel タグのリーク** | 内部 `<omniModel>` タグは、SSE ストリーミング応答でクライアントにリークしなくなりました (#585)。 |
| 🔑 **登録キー API** | `POST /api/v1/registered-keys` 経由で API キーを自動プロビジョニングし、プロバイダー/アカウントごとのクォータ適用、冪等性、SHA-256 ストレージ、およびオプションの GitHub 問題レポートを使用できます。 |
| 👁️ **Scoped API Key Reveal** 🆕 | Opt-in recovery of API keys via `ALLOW_API_KEY_REVEAL` |
| 🎨 **プロバイダーアイコン** | PNG を使用した `@lobehub/icons` (SVG) → 汎用フォールバック チェーン経由の 130 以上のプロバイダー ロゴ |
| 🔄 **モデルの自動同期** | 24 時間スケジューラーと手動 UI を切り替えて、組み込みおよびカスタムの OpenAI 互換プロバイダーのモデル リストを同期 |
| 🌐 **OpenCode Zen/Go** | PR #530 経由の @kang-heewon からの 2 つの新しいプロバイダー: 無料枠 + `OpencodeExecutor` 経由のサブスクリプション枠 |
@@ -199,7 +200,7 @@ _AI を活用した IDE または CLI ツールを、無制限のコーディン
npm run system-info
```
これにより、Node.js のバージョン、OmniRoute のバージョン、OS の詳細、インストールされている CLI ツール (iflow、gemini、claude、codex、antigravity、droid など)、Docker/PM2 のステータス、システム パッケージなど、問題を迅速に再現するために必要なものすべてを含む `system-info.txt` が生成されます。ファイルを GitHub の問題に直接添付します。
これにより、Node.js のバージョン、OmniRoute のバージョン、OS の詳細、インストールされている CLI ツール (qoder、gemini、claude、codex、antigravity、droid など)、Docker/PM2 のステータス、システム パッケージなど、問題を迅速に再現するために必要なものすべてを含む `system-info.txt` が生成されます。ファイルを GitHub の問題に直接添付します。
---
@@ -225,7 +226,7 @@ npm run system-info
│ ↓ budget limit
├─→ [Tier 3: CHEAP] GLM ($0.6/1M), MiniMax ($0.2/1M)
│ ↓ budget limit
└─→ [Tier 4: FREE] iFlow, Qwen, Kiro (unlimited)
└─→ [Tier 4: FREE] Qoder, Qwen, Kiro (unlimited)
Result: Never stop coding, minimal cost
```
@@ -292,7 +293,7 @@ OpenAI/Codex などのプロバイダーは、特定の地理的地域からの
**OmniRoute がそれを解決する方法:**
- **無料利用枠プロバイダーの組み込み** — 100% 無料プロバイダーのネイティブ サポート: iFlow (OAuth 経由の 5 つの無制限のモデル: kimi-k2- Thinking、qwen3-coder-plus、deepseek-r1、minimax-m2、kimi-k2)、Qwen (4 つの無制限のモデル: qwen3-coder-plus、qwen3-coder-flash、qwen3-coder-next、 vision-model)、Kiro (Claude + AWS Builder ID は無料)、Gemini CLI (180,000 トークン/月は無料)
- **無料利用枠プロバイダーの組み込み** — 100% 無料プロバイダーのネイティブ サポート: Qoder (OAuth 経由の 5 つの無制限のモデル: kimi-k2- Thinking、qwen3-coder-plus、deepseek-r1、minimax-m2、kimi-k2)、Qwen (4 つの無制限のモデル: qwen3-coder-plus、qwen3-coder-flash、qwen3-coder-next、 vision-model)、Kiro (Claude + AWS Builder ID は無料)、Gemini CLI (180,000 トークン/月は無料)
- **Ollama Cloud** — 無料の「ライト使用量」レベルの `api.ollama.com` のクラウド ホスト型 Ollama モデル。 `ollamacloud/<model>` プレフィックスを使用する
- **無料のみのコンボ** — チェーン `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = 月額 0 ドル、ダウンタイムなし
- **NVIDIA NIM 無料アクセス** — ~40 RPM 開発 - build.nvidia.com で 70 以上のモデルに永久に無料アクセス (クレジットから純粋なレート制限に移行)
@@ -356,7 +357,7 @@ Claude Code、Codex、Gemini CLI、Copilot — すべては有効期限切れの
**OmniRoute がそれを解決する方法:**
- **自動トークン更新** — OAuth トークンは有効期限が切れる前にバックグラウンドで更新されます。
- **OAuth 2.0 (PKCE) ビルトイン** — Claude Code、Codex、Gemini CLI、Copilot、Kiro、Qwen、iFlow の自動フロー
- **OAuth 2.0 (PKCE) ビルトイン** — Claude Code、Codex、Gemini CLI、Copilot、Kiro、Qwen、Qoder の自動フロー
- **マルチアカウント OAuth** — JWT/ID トークン抽出によるプロバイダーごとの複数のアカウント
- **OAuth LAN/リモート修正**`redirect_uri` のプライベート IP 検出 + リモート サーバーの手動 URL モード
- **Nginx の背後にある OAuth** — リバース プロキシの互換性のために `window.location.origin` を使用します
@@ -733,7 +734,7 @@ Outcome: deep fallback depth for deadline-critical workloads
| ステップ | アクション | プロバイダーのロックが解除されました |
| -------- | -------------------------------------------------------- | ---------------------------------------------------------------- |
| 1 | **Kiro** に接続 (AWS ビルダー ID OAuth) | Claude Sonnet 4.5、Haiku 4.5 — **無制限** |
| 2 | **iFlow** に接続する (Google OAuth) | kimi-k2- Thinking、qwen3-coder-plus、deepseek-r1... — **無制限** |
| 2 | **Qoder** に接続する (Google OAuth) | kimi-k2- Thinking、qwen3-coder-plus、deepseek-r1... — **無制限** |
| 3 | **Qwen** を接続 (デバイス コード) | qwen3-coder-plus、qwen3-coder-flash... — **無制限** |
| 4 | **Gemini CLI** に接続する (Google OAuth) | gemini-3-flash、gemini-2.5-pro — **180K/月無料** |
| 5 | `/dashboard/combos`**無料スタック ($0)** テンプレート | すべての無料プロバイダーを自動的にラウンドロビンします。 |
@@ -942,7 +943,7 @@ npm run electron:build:linux # Linux (.AppImage)
| | ミニマックス M2.1 | $0.2/100万 | 5時間ローリング | 最も安いオプション |
| | キミ K2.5 (ムーンショット API) 🆕 | 従量課金制 | なし | Moonshot API への直接アクセス |
| | キミ K2 | 月額 9 ドルのフラット | 1,000 万トークン/月 | 予測可能なコスト |
| **🆓 無料** | iFlow | **$0** | 無制限 | 5モデル無制限 |
| **🆓 無料** | Qoder | **$0** | 無制限 | 5モデル無制限 |
| | クウェン | **$0** | 無制限 | 4モデル無制限 |
| | キロ | **$0** | 無制限 | クロード・ソネット/俳句 (AWS ビルダー) |
| | LongCat Flash-Lite 🆕 | **$0** (5,000 万トーク/日 🔥) | 1 RPS | 地球上で最大の無料割り当て |
@@ -957,7 +958,7 @@ npm run electron:build:linux # Linux (.AppImage)
```
# 🆓 Ultimate Free Stack 2026 — 11 Providers, $0 Forever
Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
Qwen (qw/) → qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next UNLIMITED
@@ -987,7 +988,7 @@ Cerebras (cerebras/) → Llama/Qwen world-fastest — 1M tok/day
| `claude-haiku-4.5` | `kr/` | **無制限** | 1 日あたりの上限は報告されていません |
| `claude-opus-4.6` | `kr/` | **無制限** | Kiro 経由の最新作品 |
### 🟢 IFLOW モデル (無料 OAuth — クレジット カードなし)
### 🟢 QODER モデル (無料 OAuth — クレジット カードなし)
| モデル | プレフィックス | 制限 | レート制限 |
| ------------------ | -------------- | ---------- | -------------------------- |
@@ -1086,7 +1087,7 @@ Cerebras (cerebras/) → Llama/Qwen world-fastest — 1M tok/day
>
> ```
> Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
> iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
> Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
> Qwen (qw/) → qwen3-coder models UNLIMITED
@@ -1219,6 +1220,7 @@ OmniRoute v2.0 は、単なるリレー プロキシではなく、運用プラ
| 特集 | 何をするのか |
| --------------------------------- | --------------------------------------------------------------------- |
| 📝 **リクエスト + プロキシ ログ** | 完全なリクエスト/レスポンスとプロキシ ログ |
| 📉 **Streamed Detailed Logs** 🆕 | Reconstructs SSE payload streams cleanly into the UI |
| 📋 **統合ログ ダッシュボード** | リクエスト、プロキシ、監査、およびコンソールのビューを 1 ページに表示 |
| 🔍 **テレメトリのリクエスト** | p50/p95/p99 レイテンシーとリクエストのトレース |
| 🏥 **健康ダッシュボード** | 稼働時間、ブレーカー状態、ロックアウト、キャッシュ統計 |
@@ -1239,6 +1241,7 @@ OmniRoute v2.0 は、単なるリレー プロキシではなく、運用プラ
| 🔏 **CLI 指紋切り替え** | [設定] > [セキュリティ] | でのプロバイダーごとの指紋照合 |
| 🌐 **i18n (30 言語)** | RTL をカバーする完全なダッシュボード + ドキュメント言語サポート |
| 🧹 **すべてのモデルをクリア** | ワンクリックでプロバイダー詳細のモデルリストをクリア |
| 👁️ **Sidebar Controls** 🆕 | Hide components and integrations from Appearance Settings |
| 📋 **問題テンプレート** | バグと機能用の標準化された GitHub テンプレート |
| 📂 **カスタム データ ディレクトリ** | `DATA_DIR` 保管場所のオーバーライド |
@@ -1533,11 +1536,11 @@ Models:
<details>
<summary><b>🆓 無料プロバイダー (緊急バックアップ)</b></summary>
### iFlow (OAuth 経由の 5 つの無料モデル)
### Qoder (OAuth 経由の 5 つの無料モデル)
```bash
Dashboard → Connect iFlow
iFlow OAuth login
Dashboard → Connect Qoder
Qoder OAuth login
→ Unlimited usage
Models:
@@ -1735,7 +1738,7 @@ opencode
- [ダッシュボード] → [コスト] で使用状況の統計を確認します。
- プライマリ モデルを GLM/MiniMax に切り替えます
- 重要ではないタスクには無料枠 (Gemini CLI、iFlow) を使用する
- 重要ではないタスクには無料枠 (Gemini CLI、Qoder) を使用する
**ダッシュボード/API ポートが間違っています**
+52 -49
View File
@@ -30,21 +30,22 @@ _범용 API 프록시 — 하나의 엔드포인트, 67개 이상의 공급자,
> **Upgrading from v2.9.5?** — See the [full CHANGELOG](CHANGELOG.md#300--2026-03-22-release-candidate--not-yet-merged-to-main) for all changes.
| 면적 | 변경 |
| -------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------- |
| 🔒 **CodeQL 보안** | 10개 이상의 CodeQL 경고 수정: 다항식 재실행, 안전하지 않은 무작위성, 셸 주입 수정 |
| ✅ **경로 검증** | 이제 Zod 스키마 + `validateBody()` — CI `check:route-validation:t06` 통과로 검증된 모든 176개 API 경로 |
| 🐛 **omniModel 태그 유출** | 내부 `<omniModel>` 태그가 더 이상 SSE 스트리밍 응답에서 클라이언트로 누출되지 않습니다(#585) |
| 🔑 **등록된 키 API** | 공급자/계정별 할당량 적용, 멱등성, SHA-256 저장소 및 선택적 GitHub 문제 보고 기능을 갖춘 `POST /api/v1/registered-keys`을 통해 API 키 자동 프로비저닝 |
| 🎨 **공급자 아이콘** | PNG가 포함된 `@lobehub/icons`(SVG)을 통한 130개 이상의 공급자 로고 → 일반 폴백 체인 |
| 🔄 **모델 자동 동기화** | 내장 및 사용자 정의 OpenAI 호환 공급자에 대한 모델 목록을 동기화하기 위한 24시간 스케줄러 및 수동 UI 토글 |
| 🌐 **오픈코드 Zen/Go** | PR #530을 통한 @kang-heewon의 두 가지 새로운 제공자: `OpencodeExecutor`를 통한 무료 등급 + 구독 등급 |
| 🐛 **Gemini CLI OAuth** | Docker에 `GEMINI_OAUTH_CLIENT_SECRET`이 누락된 경우 실행 가능한 오류(암호적인 Google 오류임) |
| 🐛 **OpenCode 구성** | `saveOpenCodeConfig()`은 이제 TOML을 `XDG_CONFIG_HOME`에 올바르게 씁니다. |
| 🐛 **고정된 모델 재정의** | `body.model`이 컨텍스트 캐시 보호에서 `pinnedModel` 올바르게 설정됨 |
| 🐛 **코덱스/클로드 루프** | `tool_result` 블록이 이제 무한 루프를 중지하기 위해 텍스트로 변환되었습니다. |
| 🐛 **로그인 리디렉션** | 비밀번호 설정을 건너뛴 후 로그인이 더 이상 정지되지 않습니다. |
| 🐛 **Windows 경로** | MSYS2/Git-Bash 경로(`/c/...`)가 자동으로 `C:\...`로 정규화됨 |
| 면적 | 변경 |
| ------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------- |
| 🔒 **CodeQL 보안** | 10개 이상의 CodeQL 경고 수정: 다항식 재실행, 안전하지 않은 무작위성, 셸 주입 수정 |
| ✅ **경로 검증** | 이제 Zod 스키마 + `validateBody()` — CI `check:route-validation:t06` 통과로 검증된 모든 176개 API 경로 |
| 🐛 **omniModel 태그 유출** | 내부 `<omniModel>` 태그가 더 이상 SSE 스트리밍 응답에서 클라이언트로 누출되지 않습니다(#585) |
| 🔑 **등록된 키 API** | 공급자/계정별 할당량 적용, 멱등성, SHA-256 저장소 및 선택적 GitHub 문제 보고 기능을 갖춘 `POST /api/v1/registered-keys`을 통해 API 키 자동 프로비저닝 |
| 👁️ **Scoped API Key Reveal** 🆕 | Opt-in recovery of API keys via `ALLOW_API_KEY_REVEAL` |
| 🎨 **공급자 아이콘** | PNG가 포함된 `@lobehub/icons`(SVG)을 통한 130개 이상의 공급자 로고 → 일반 폴백 체인 |
| 🔄 **모델 자동 동기화** | 내장 및 사용자 정의 OpenAI 호환 공급자에 대한 모델 목록을 동기화하기 위한 24시간 스케줄러 및 수동 UI 토글 |
| 🌐 **오픈코드 Zen/Go** | PR #530을 통한 @kang-heewon의 두 가지 새로운 제공자: `OpencodeExecutor`를 통한 무료 등급 + 구독 등급 |
| 🐛 **Gemini CLI OAuth** | Docker에 `GEMINI_OAUTH_CLIENT_SECRET`이 누락된 경우 실행 가능한 오류(암호적인 Google 오류임) |
| 🐛 **OpenCode 구성** | `saveOpenCodeConfig()`은 이제 TOML을 `XDG_CONFIG_HOME` 올바르게 씁니다. |
| 🐛 **고정된 모델 재정의** | `body.model`이 컨텍스트 캐시 보호에서 `pinnedModel`로 올바르게 설정됨 |
| 🐛 **코덱스/클로드 루프** | `tool_result` 블록이 이제 무한 루프를 중지하기 위해 텍스트로 변환되었습니다. |
| 🐛 **로그인 리디렉션** | 비밀번호 설정을 건너뛴 후 로그인이 더 이상 정지되지 않습니다. |
| 🐛 **Windows 경로** | MSYS2/Git-Bash 경로(`/c/...`)가 자동으로 `C:\...`로 정규화됨 |
---
@@ -199,7 +200,7 @@ When opening an issue, please run the system-info command and attach the generat
npm run system-info
```
그러면 Node.js 버전, OmniRoute 버전, OS 세부 정보, 설치된 CLI 도구(iflow, gemini, claude, codex, antigravity, droid 등), Docker/PM2 상태, 시스템 패키지 등 문제를 신속하게 재현하는 데 필요한 모든 항목이 포함된 `system-info.txt`이 생성됩니다. GitHub 문제에 직접 파일을 첨부하세요.
그러면 Node.js 버전, OmniRoute 버전, OS 세부 정보, 설치된 CLI 도구(qoder, gemini, claude, codex, antigravity, droid 등), Docker/PM2 상태, 시스템 패키지 등 문제를 신속하게 재현하는 데 필요한 모든 항목이 포함된 `system-info.txt`이 생성됩니다. GitHub 문제에 직접 파일을 첨부하세요.
---
@@ -225,7 +226,7 @@ npm run system-info
│ ↓ budget limit
├─→ [Tier 3: CHEAP] GLM ($0.6/1M), MiniMax ($0.2/1M)
│ ↓ budget limit
└─→ [Tier 4: FREE] iFlow, Qwen, Kiro (unlimited)
└─→ [Tier 4: FREE] Qoder, Qwen, Kiro (unlimited)
Result: Never stop coding, minimal cost
```
@@ -292,7 +293,7 @@ Not everyone can pay $20200/month for AI subscriptions. Students, devs from e
**OmniRoute가 이를 해결하는 방법:**
- **무료 계층 제공자 내장** — 100% 무료 제공자에 대한 기본 지원: iFlow(OAuth를 통한 5개의 무제한 모델: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2), Qwen(4개의 무제한 모델: qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next, Vision-model), Kiro (Claude + AWS Builder ID for free), Gemini CLI (180K tokens/month free)
- **무료 계층 제공자 내장** — 100% 무료 제공자에 대한 기본 지원: Qoder(OAuth를 통한 5개의 무제한 모델: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2), Qwen(4개의 무제한 모델: qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next, Vision-model), Kiro (Claude + AWS Builder ID for free), Gemini CLI (180K tokens/month free)
- **Ollama Cloud** — Cloud-hosted Ollama models at `api.ollama.com` with free "Light usage" tier; `ollamacloud/<model>` 접두사 사용
- **Free-Only Combos** — Chain `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = $0/month with zero downtime
- **NVIDIA NIM 무료 액세스** — ~40RPM 개발 - build.nvidia.com에서 70개 이상의 모델에 영원히 무료 액세스(크레딧에서 순수 속도 제한으로 전환)
@@ -356,7 +357,7 @@ Claude Code, Codex, Gemini CLI, Copilot — all use OAuth 2.0 with expiring toke
**OmniRoute가 이를 해결하는 방법:**
- **Auto Token Refresh** — OAuth tokens refresh in background before expiration
- **OAuth 2.0 (PKCE) Built-in** — Automatic flow for Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
- **OAuth 2.0 (PKCE) Built-in** — Automatic flow for Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, Qoder
- **Multi-Account OAuth** — Multiple accounts per provider via JWT/ID token extraction
- **OAuth LAN/Remote Fix** — Private IP detection for `redirect_uri` + manual URL mode for remote servers
- **OAuth Behind Nginx** — Uses `window.location.origin` for reverse proxy compatibility
@@ -733,7 +734,7 @@ Outcome: deep fallback depth for deadline-critical workloads
| 단계 | 액션 | 제공자 잠금 해제 |
| ---- | ---------------------------------------------- | --------------------------------------------------------------- |
| 1 | **Kiro** 연결(AWS Builder ID OAuth) | 클로드 소네트 4.5, 하이쿠 4.5 — **무제한** |
| 2 | **iFlow** 연결(Google OAuth) | kimi-k2-thinking, qwen3-coder-plus, deepseek-r1... — **무제한** |
| 2 | **Qoder** 연결(Google OAuth) | kimi-k2-thinking, qwen3-coder-plus, deepseek-r1... — **무제한** |
| 3 | 연결 **Qwen**(장치 코드) | qwen3-coder-plus, qwen3-coder-flash... — **무제한** |
| 4 | **Gemini CLI**(Google OAuth) 연결 | gemini-3-flash, gemini-2.5-pro — **180K/월 무료** |
| 5 | `/dashboard/combos`**무료 스택($0)** 템플릿 | 모든 무료 공급자를 자동으로 라운드 로빈 |
@@ -957,7 +958,7 @@ npm run electron:build:linux # Linux (.AppImage)
```
# 🆓 Ultimate Free Stack 2026 — 11 Providers, $0 Forever
Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
Qwen (qw/) → qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next UNLIMITED
@@ -987,7 +988,7 @@ Cerebras (cerebras/) → Llama/Qwen world-fastest — 1M tok/day
| `claude-haiku-4.5` | `kr/` | **무제한** | 보고된 일일 한도 없음 |
| `claude-opus-4.6` | `kr/` | **무제한** | Kiro를 통한 최신 Opus |
### 🟢 IFLOW 모델(무료 OAuth — 신용카드 없음)
### 🟢 QODER 모델(무료 OAuth — 신용카드 없음)
| 모델 | 접두사 | 한도 | 비율 제한 |
| ------------------ | ------ | ---------- | ---------------- |
@@ -1086,7 +1087,7 @@ Cerebras (cerebras/) → Llama/Qwen world-fastest — 1M tok/day
>
> ```
> Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
> iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
> Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
> Qwen (qw/) → qwen3-coder models UNLIMITED
@@ -1216,31 +1217,33 @@ OmniRoute v2.0은 단순한 릴레이 프록시가 아닌 운영 플랫폼으로
### 📊 관찰 가능성 및 분석
| 기능 | 그것이 하는 일 |
| ------------------------- | ----------------------------------------------- |
| 📝 **요청 + 프록시 로깅** | 전체 요청/응답 및 프록시 로깅 |
| 📋 **통합 로그 대시보드** | 한 페이지에서 요청, 프록시, 감사 및 콘솔 보기 |
| 🔍 **원격 측정 요청** | p50/p95/p99 대기 시간 및 요청 추적 |
| 🏥 **건강 대시보드** | 가동 시간, 차단기 상태, 잠금, 캐시 통계 |
| 💰 **비용 추적** | 예산 제어 및 모델별 가격 가시성 |
| 📈 **분석 시각화** | 모델/공급자 사용량 통찰력 및 추세 보기 |
| 🧪 **평가 프레임워크** | 구성 가능한 매치 전략을 사용한 골든 세트 테스트 |
| 기능 | 그것이 하는 일 |
| -------------------------------- | ---------------------------------------------------- |
| 📝 **요청 + 프록시 로깅** | 전체 요청/응답 및 프록시 로깅 |
| 📉 **Streamed Detailed Logs** 🆕 | Reconstructs SSE payload streams cleanly into the UI |
| 📋 **통합 로그 대시보드** | 한 페이지에서 요청, 프록시, 감사 및 콘솔 보기 |
| 🔍 **원격 측정 요청** | p50/p95/p99 대기 시간 및 요청 추적 |
| 🏥 **건강 대시보드** | 가동 시간, 차단기 상태, 잠금, 캐시 통계 |
| 💰 **비용 추적** | 예산 제어 및 모델별 가격 가시성 |
| 📈 **분석 시각화** | 모델/공급자 사용량 통찰력 및 추세 보기 |
| 🧪 **평가 프레임워크** | 구성 가능한 매치 전략을 사용한 골든 세트 테스트 |
### ☁️ 배포 및 플랫폼
| 기능 | 그것이 하는 일 |
| ---------------------------------- | ----------------------------------------------------- | ------------------ |
| 🌐 **어디서나 배포** | 로컬호스트, VPS, Docker, 클라우드 환경 |
| 💾 **클라우드 동기화** | 클라우드 작업자를 통한 구성 동기화 |
| 🔄 **백업/복원** | 내보내기/가져오기 및 재해 복구 흐름 |
| 🧙 **온보딩 마법사** | 첫 실행 안내 설정 |
| 🔧 **CLI 도구 대시보드** | 널리 사용되는 코딩 도구를 위한 원클릭 설정 |
| 🎮 **모델 놀이터** | 대시보드에서 공급자/모델/엔드포인트 테스트 |
| 🔏 **CLI 지문 토글** | 설정 > 보안 | 공급자별 지문 일치 |
| 🌐 **i18n(30개 언어)** | RTL 적용 범위를 포함한 전체 대시보드 + 문서 언어 지원 |
| 🧹 **모든 모델 지우기** | 공급자 세부정보에서 원클릭 모델 목록 삭제 |
| 📋 **이슈 템플릿** | 버그 및 기능을 위한 표준화된 GitHub 템플릿 |
| 📂 **사용자 정의 데이터 디렉터리** | `DATA_DIR` 저장 위치 재정의 |
| 기능 | 그것이 하는 일 |
| ---------------------------------- | --------------------------------------------------------- | ------------------ |
| 🌐 **어디서나 배포** | 로컬호스트, VPS, Docker, 클라우드 환경 |
| 💾 **클라우드 동기화** | 클라우드 작업자를 통한 구성 동기화 |
| 🔄 **백업/복원** | 내보내기/가져오기 및 재해 복구 흐름 |
| 🧙 **온보딩 마법사** | 첫 실행 안내 설정 |
| 🔧 **CLI 도구 대시보드** | 널리 사용되는 코딩 도구를 위한 원클릭 설정 |
| 🎮 **모델 놀이터** | 대시보드에서 공급자/모델/엔드포인트 테스트 |
| 🔏 **CLI 지문 토글** | 설정 > 보안 | 공급자별 지문 일치 |
| 🌐 **i18n(30개 언어)** | RTL 적용 범위를 포함한 전체 대시보드 + 문서 언어 지원 |
| 🧹 **모든 모델 지우기** | 공급자 세부정보에서 원클릭 모델 목록 삭제 |
| 👁️ **Sidebar Controls** 🆕 | Hide components and integrations from Appearance Settings |
| 📋 **이슈 템플릿** | 버그 및 기능을 위한 표준화된 GitHub 템플릿 |
| 📂 **사용자 정의 데이터 디렉터리** | `DATA_DIR` 저장 위치 재정의 |
### 기능 심층 분석
@@ -1534,11 +1537,11 @@ Models:
<details>
<summary><b>🆓 무료 제공업체(긴급 백업)</b></summary>
### iFlow(OAuth를 통한 5개 무료 모델)
### Qoder(OAuth를 통한 5개 무료 모델)
```bash
Dashboard → Connect iFlow
iFlow OAuth login
Dashboard → Connect Qoder
Qoder OAuth login
→ Unlimited usage
Models:
@@ -1736,7 +1739,7 @@ opencode
- 대시보드 → 비용에서 사용 통계를 확인하세요.
- 기본 모델을 GLM/MiniMax로 전환
- 중요하지 않은 작업에는 무료 계층(Gemini CLI, iFlow)을 사용합니다.
- 중요하지 않은 작업에는 무료 계층(Gemini CLI, Qoder)을 사용합니다.
**대시보드/API 포트가 잘못되었습니다**
+58 -35
View File
@@ -199,7 +199,7 @@ When opening an issue, please run the system-info command and attach the generat
npm run system-info
```
This generates a `system-info.txt` with your Node.js version, OmniRoute version, OS details, installed CLI tools (iflow, gemini, claude, codex, antigravity, droid, etc.), Docker/PM2 status, and system packages — everything we need to reproduce your issue quickly. Attach the file directly to your GitHub issue.
This generates a `system-info.txt` with your Node.js version, OmniRoute version, OS details, installed CLI tools (qoder, gemini, claude, codex, antigravity, droid, etc.), Docker/PM2 status, and system packages — everything we need to reproduce your issue quickly. Attach the file directly to your GitHub issue.
---
@@ -225,7 +225,7 @@ This generates a `system-info.txt` with your Node.js version, OmniRoute version,
│ ↓ budget limit
├─→ [Tier 3: CHEAP] GLM ($0.6/1M), MiniMax ($0.2/1M)
│ ↓ budget limit
└─→ [Tier 4: FREE] iFlow, Qwen, Kiro (unlimited)
└─→ [Tier 4: FREE] Qoder, Qwen, Kiro (unlimited)
Result: Never stop coding, minimal cost
```
@@ -292,7 +292,7 @@ Not everyone can pay $20200/month for AI subscriptions. Students, devs from e
**How OmniRoute solves it:**
- **Free Tier Providers Built-in** — Native support for 100% free providers: iFlow (5 unlimited models via OAuth: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2), Qwen (4 unlimited models: qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next, vision-model), Kiro (Claude + AWS Builder ID for free), Gemini CLI (180K tokens/month free)
- **Free Tier Providers Built-in** — Native support for 100% free providers: Qoder (5 unlimited models via OAuth: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2), Qwen (4 unlimited models: qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next, vision-model), Kiro (Claude + AWS Builder ID for free), Gemini CLI (180K tokens/month free)
- **Ollama Cloud** — Cloud-hosted Ollama models at `api.ollama.com` with free "Light usage" tier; use `ollamacloud/<model>` prefix
- **Free-Only Combos** — Chain `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = $0/month with zero downtime
- **NVIDIA NIM Free Access** — ~40 RPM dev-forever free access to 70+ models at build.nvidia.com (transitioning from credits to pure rate limits)
@@ -356,7 +356,7 @@ Claude Code, Codex, Gemini CLI, Copilot — all use OAuth 2.0 with expiring toke
**How OmniRoute solves it:**
- **Auto Token Refresh** — OAuth tokens refresh in background before expiration
- **OAuth 2.0 (PKCE) Built-in** — Automatic flow for Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
- **OAuth 2.0 (PKCE) Built-in** — Automatic flow for Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, Qoder
- **Multi-Account OAuth** — Multiple accounts per provider via JWT/ID token extraction
- **OAuth LAN/Remote Fix** — Private IP detection for `redirect_uri` + manual URL mode for remote servers
- **OAuth Behind Nginx** — Uses `window.location.origin` for reverse proxy compatibility
@@ -733,7 +733,7 @@ Outcome: deep fallback depth for deadline-critical workloads
| Step | Action | Providers Unlocked |
| ---- | -------------------------------------------------- | ------------------------------------------------------------------ |
| 1 | Connect **Kiro** (AWS Builder ID OAuth) | Claude Sonnet 4.5, Haiku 4.5 — **unlimited** |
| 2 | Connect **iFlow** (Google OAuth) | kimi-k2-thinking, qwen3-coder-plus, deepseek-r1... — **unlimited** |
| 2 | Connect **Qoder** (Google OAuth) | kimi-k2-thinking, qwen3-coder-plus, deepseek-r1... — **unlimited** |
| 3 | Connect **Qwen** (Device Code) | qwen3-coder-plus, qwen3-coder-flash... — **unlimited** |
| 4 | Connect **Gemini CLI** (Google OAuth) | gemini-3-flash, gemini-2.5-pro — **180K/mo free** |
| 5 | `/dashboard/combos`**Free Stack ($0)** template | Round-robin all free providers automatically |
@@ -876,6 +876,15 @@ docker compose --profile base up -d
docker compose --profile cli up -d
```
Dashboard support for Docker deployments now includes a one-click **Cloudflare Quick Tunnel** on `Dashboard → Endpoints`. The first enable downloads `cloudflared` only when needed, starts a temporary tunnel to your current `/v1` endpoint, and shows the generated `https://*.trycloudflare.com/v1` URL directly below your normal public URL.
Notes:
- Quick Tunnel URLs are temporary and change after every restart.
- Managed install currently supports Linux, macOS, and Windows on `x64` / `arm64`.
- Docker images bundle system CA roots and pass them to managed `cloudflared`, which avoids TLS trust failures when the tunnel bootstraps inside the container.
- Set `CLOUDFLARED_BIN=/absolute/path/to/cloudflared` if you want OmniRoute to use an existing binary instead of downloading one.
**Using Docker Compose with Caddy (HTTPS Auto-TLS):**
OmniRoute can be securely exposed using Caddy's automatic SSL provisioning. Ensure your domain's DNS A record points to your server's IP.
@@ -971,7 +980,7 @@ When minimized, OmniRoute lives in your system tray with quick actions:
| | MiniMax M2.1 | $0.2/1M | 5-hour rolling | Cheapest option |
| | Kimi K2.5 (Moonshot API) 🆕 | Pay-per-use | None | Direct Moonshot API access |
| | Kimi K2 | $9/mo flat | 10M tokens/mo | Predictable cost |
| **🆓 FREE** | iFlow | **$0** | Unlimited | 5 models unlimited |
| **🆓 FREE** | Qoder | **$0** | Unlimited | 5 models unlimited |
| | Qwen | **$0** | Unlimited | 4 models unlimited |
| | Kiro | **$0** | Unlimited | Claude Sonnet/Haiku (AWS Builder) |
| | LongCat Flash-Lite 🆕 | **$0** (50M tok/day 🔥) | 1 RPS | Largest free quota on Earth |
@@ -986,7 +995,7 @@ When minimized, OmniRoute lives in your system tray with quick actions:
```
# 🆓 Ultimate Free Stack 2026 — 11 Providers, $0 Forever
Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
Qwen (qw/) → qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next UNLIMITED
@@ -1016,7 +1025,7 @@ Cerebras (cerebras/) → Llama/Qwen world-fastest — 1M tok/day
| `claude-haiku-4.5` | `kr/` | **Unlimited** | No reported daily cap |
| `claude-opus-4.6` | `kr/` | **Unlimited** | Latest Opus via Kiro |
### 🟢 IFLOW MODELS (Free OAuth — No Credit Card)
### 🟢 QODER MODELS (Free OAuth — No Credit Card)
| Model | Prefix | Limit | Rate Limit |
| ------------------ | ------ | ------------- | --------------- |
@@ -1115,7 +1124,7 @@ Available free: `qwen3-235b-a22b-instruct-2507` (Qwen3 235B!), `llama-3.1-70b-in
>
> ```
> Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
> iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
> Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
> Qwen (qw/) → qwen3-coder models UNLIMITED
@@ -1210,6 +1219,9 @@ OmniRoute v2.0 is built as an operational platform, not just a relay proxy.
| 🔀 **Model Aliases** | Built-in + custom model aliasing and migration safety |
| ⚡ **Background Degradation** | Route low-priority background tasks to cheaper models |
| 🧪 **Task-Aware Smart Routing** | Auto-select model by content type (coding/vision/analysis/summarization) |
| 🔄 **A2A Agent Workflows** | Deterministic FSM orchestrator for stateful multi-step agent executions |
| 🔀 **Adaptive Routing** | Dynamic strategy override based on token volume and prompt complexity |
| 🎲 **Provider Diversity** | Shannon entropy scoring balancing auto-combo traffic distribution |
| 💬 **System Prompt Injection** | Global behavior controls applied consistently |
| 📄 **Responses API Compatibility** | Full `/v1/responses` support for Codex and advanced agentic workflows |
@@ -1240,36 +1252,45 @@ OmniRoute v2.0 is built as an operational platform, not just a relay proxy.
| 🔏 **CLI Fingerprint Matching** | Matches native CLI request signatures — **reduces ban risk while preserving proxy IP** |
| 🌐 **IP Filtering** | Allowlist/blocklist control for exposed deployments |
| 📊 **Editable Rate Limits** | Configurable global/provider-level limits with persistence |
| 📉 **Graceful Degradation** | Multi-layer capability fallbacks protecting core gateway operations |
| 📜 **Config Audit Trail** | Diff-based change tracking preventing operational drift with simple rollbacks |
| ⏳ **Provider Health Sync** | Proactive token expiration monitoring triggering alerts before authorization failures |
| 🚪 **Auto-Disable Banned Accounts** | Operational circuit breaker sealing permanently blocked token accounts automatically |
| 🔑 **API Key Management + Scoping** | Secure key issuance/rotation and model/provider controls |
| 👁️ **Scoped API Key Reveal** 🆕 | Opt-in recovery of API keys via `ALLOW_API_KEY_REVEAL` |
| 🛡️ **Protected `/models`** | Optional auth gating and provider hiding for model catalog |
### 📊 Observability & Analytics
| Feature | What It Does |
| ------------------------------- | ----------------------------------------------------- |
| 📝 **Request + Proxy Logging** | Full request/response and proxy logging |
| 📋 **Unified Logs Dashboard** | Request, proxy, audit, and console views in one page |
| 🔍 **Request Telemetry** | p50/p95/p99 latency and request tracing |
| 🏥 **Health Dashboard** | Uptime, breaker states, lockouts, cache stats |
| 💰 **Cost Tracking** | Budget controls and per-model pricing visibility |
| 📈 **Analytics Visualizations** | Model/provider usage insights and trend views |
| 🧪 **Evaluation Framework** | Golden set testing with configurable match strategies |
| Feature | What It Does |
| -------------------------------- | ----------------------------------------------------- |
| 📝 **Request + Proxy Logging** | Full request/response and proxy logging |
| 📉 **Streamed Detailed Logs** 🆕 | Reconstructs SSE payload streams cleanly into the UI |
| 📋 **Unified Logs Dashboard** | Request, proxy, audit, and console views in one page |
| 🔍 **Request Telemetry** | p50/p95/p99 latency and request tracing |
| 🏥 **Health Dashboard** | Uptime, breaker states, lockouts, cache stats |
| 💰 **Cost Tracking** | Budget controls and per-model pricing visibility |
| 📈 **Analytics Visualizations** | Model/provider usage insights and trend views |
| 🧪 **Evaluation Framework** | Golden set testing with configurable match strategies |
| 📡 **Live Diagnostics** 🆕 | Semantic cache bypass for accurate combo live testing |
### ☁️ Deployment & Platform
| Feature | What It Does |
| ----------------------------- | -------------------------------------------------------- |
| 🌐 **Deploy Anywhere** | Localhost, VPS, Docker, Cloud environments |
| 💾 **Cloud Sync** | Configuration sync via cloud worker |
| 🔄 **Backup/Restore** | Export/import and disaster recovery flows |
| 🧙 **Onboarding Wizard** | First-run guided setup |
| 🔧 **CLI Tools Dashboard** | One-click setup for popular coding tools |
| 🎮 **Model Playground** | Test any provider/model/endpoint from the dashboard |
| 🔏 **CLI Fingerprint Toggle** | Per-provider fingerprint matching in Settings > Security |
| 🌐 **i18n (30 languages)** | Full dashboard + docs language support with RTL coverage |
| 🧹 **Clear All Models** | One-click model list clearing in provider details |
| 📋 **Issue Templates** | Standardized GitHub templates for bugs and features |
| 📂 **Custom Data Directory** | `DATA_DIR` override for storage location |
| Feature | What It Does |
| ----------------------------- | --------------------------------------------------------- |
| 🌐 **Deploy Anywhere** | Localhost, VPS, Docker, Cloud environments |
| 🚇 **Cloudflare Tunnel** 🆕 | One-click Quick Tunnel integration from the dashboard |
| 💾 **Cloud Sync** | Configuration sync via cloud worker |
| 🔄 **Backup/Restore** | Export/import and disaster recovery flows |
| 🧙 **Onboarding Wizard** | First-run guided setup |
| 🔧 **CLI Tools Dashboard** | One-click setup for popular coding tools |
| 🎮 **Model Playground** | Test any provider/model/endpoint from the dashboard |
| 🔏 **CLI Fingerprint Toggle** | Per-provider fingerprint matching in Settings > Security |
| 🌐 **i18n (30 languages)** | Full dashboard + docs language support with RTL coverage |
| 🧹 **Clear All Models** | One-click model list clearing in provider details |
| 👁️ **Sidebar Controls** 🆕 | Hide components and integrations from Appearance Settings |
| 📋 **Issue Templates** | Standardized GitHub templates for bugs and features |
| 📂 **Custom Data Directory** | `DATA_DIR` override for storage location |
### Feature Deep Dive
@@ -1521,6 +1542,8 @@ Models:
**Models:** Access 100+ models from all major providers through a single API key.
**Dashboard behavior:** OpenRouter models are managed from **Available Models**. Manual add, import, and auto-sync all update the same list.
</details>
<details>
@@ -1563,11 +1586,11 @@ Models:
<details>
<summary><b>🆓 FREE Providers (Emergency Backup)</b></summary>
### iFlow (5 FREE models via OAuth)
### Qoder (5 FREE models via OAuth)
```bash
Dashboard → Connect iFlow
iFlow OAuth login
Dashboard → Connect Qoder
Qoder OAuth login
→ Unlimited usage
Models:
@@ -1765,7 +1788,7 @@ opencode
- Check usage stats in Dashboard → Costs
- Switch primary model to GLM/MiniMax
- Use free tier (Gemini CLI, iFlow) for non-critical tasks
- Use free tier (Gemini CLI, Qoder) for non-critical tasks
**Dashboard/API ports are wrong**
+31 -28
View File
@@ -30,21 +30,22 @@ _Proksi API universal anda — satu titik akhir, 67+ pembekal, masa henti sifar.
> **Menaik taraf daripada v2.9.5?** — Lihat [full CHANGELOG](CHANGELOG.md#300--2026-03-22-release-candidate--not-yet-merged-to-main) untuk semua perubahan.
| Kawasan | Tukar |
| ----------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| 🔒 **Keselamatan CodeQL** | Memperbaiki 10+ amaran CodeQL: polinomial-redos, tidak selamat-rawak, pemulihan suntikan shell |
| ✅ **Pengesahan Laluan** | Semua 176 laluan API kini disahkan dengan skema Zod + `validateBody()` — CI `check:route-validation:t06` pas |
| 🐛 **omniModel Tag Bocor** | Teg dalaman `<omniModel>` tidak lagi bocor kepada pelanggan dalam respons penstriman SSE (#585) |
| 🔑 **API Kunci Berdaftar** | Auto-peruntukkan kunci API melalui `POST /api/v1/registered-keys` dengan penguatkuasaan kuota setiap pembekal/akaun, idempotency, storan SHA-256 dan pelaporan isu GitHub pilihan |
| 🎨 **Ikon Pembekal** | 130+ logo pembekal melalui `@lobehub/icons` (SVG) dengan PNG → rantaian sandaran generik |
| 🔄 **Model Auto-Segerak** | Penjadual 24 jam dan togol UI manual untuk menyegerakkan senarai model bagi pembekal terbina dalam dan tersuai serasi OpenAI |
| 🌐 **OpenCode Zen/Go** | Dua pembekal baharu daripada @kang-heewon melalui PR #530: peringkat percuma + peringkat langganan melalui `OpencodeExecutor` |
| 🐛 **Gemini CLI OAuth** | Ralat boleh diambil tindakan apabila `GEMINI_OAUTH_CLIENT_SECRET` tiada dalam Docker (adalah ralat Google samar) |
| 🐛 **Konfigurasi OpenCode** | `saveOpenCodeConfig()` kini menulis TOML dengan betul kepada `XDG_CONFIG_HOME` |
| 🐛 **Timpa model disematkan** | `body.model` ditetapkan dengan betul kepada `pinnedModel` pada perlindungan konteks-cache |
| 🐛 **Gelung Codex/Claude** | `tool_result` blok kini ditukar kepada teks untuk menghentikan gelung tak terhingga |
| 🐛 **Ubah hala log masuk** | Log masuk tidak lagi membeku selepas melangkau persediaan kata laluan |
| 🐛 **Laluan Windows** | Laluan MSYS2/Git-Bash (`/c/...`) dinormalkan kepada `C:\...` secara automatik |
| Kawasan | Tukar |
| ------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| 🔒 **Keselamatan CodeQL** | Memperbaiki 10+ amaran CodeQL: polinomial-redos, tidak selamat-rawak, pemulihan suntikan shell |
| ✅ **Pengesahan Laluan** | Semua 176 laluan API kini disahkan dengan skema Zod + `validateBody()` — CI `check:route-validation:t06` pas |
| 🐛 **omniModel Tag Bocor** | Teg dalaman `<omniModel>` tidak lagi bocor kepada pelanggan dalam respons penstriman SSE (#585) |
| 🔑 **API Kunci Berdaftar** | Auto-peruntukkan kunci API melalui `POST /api/v1/registered-keys` dengan penguatkuasaan kuota setiap pembekal/akaun, idempotency, storan SHA-256 dan pelaporan isu GitHub pilihan |
| 👁️ **Scoped API Key Reveal** 🆕 | Opt-in recovery of API keys via `ALLOW_API_KEY_REVEAL` |
| 🎨 **Ikon Pembekal** | 130+ logo pembekal melalui `@lobehub/icons` (SVG) dengan PNG → rantaian sandaran generik |
| 🔄 **Model Auto-Segerak** | Penjadual 24 jam dan togol UI manual untuk menyegerakkan senarai model bagi pembekal terbina dalam dan tersuai serasi OpenAI |
| 🌐 **OpenCode Zen/Go** | Dua pembekal baharu daripada @kang-heewon melalui PR #530: peringkat percuma + peringkat langganan melalui `OpencodeExecutor` |
| 🐛 **Gemini CLI OAuth** | Ralat boleh diambil tindakan apabila `GEMINI_OAUTH_CLIENT_SECRET` tiada dalam Docker (adalah ralat Google samar) |
| 🐛 **Konfigurasi OpenCode** | `saveOpenCodeConfig()` kini menulis TOML dengan betul kepada `XDG_CONFIG_HOME` |
| 🐛 **Timpa model disematkan** | `body.model` ditetapkan dengan betul kepada `pinnedModel` pada perlindungan konteks-cache |
| 🐛 **Gelung Codex/Claude** | `tool_result` blok kini ditukar kepada teks untuk menghentikan gelung tak terhingga |
| 🐛 **Ubah hala log masuk** | Log masuk tidak lagi membeku selepas melangkau persediaan kata laluan |
| 🐛 **Laluan Windows** | Laluan MSYS2/Git-Bash (`/c/...`) dinormalkan kepada `C:\...` secara automatik |
---
@@ -199,7 +200,7 @@ Apabila membuka isu, sila jalankan arahan maklumat sistem dan lampirkan fail yan
npm run system-info
```
Ini menjana `system-info.txt` dengan versi Node.js anda, versi OmniRoute, butiran OS, alat CLI yang dipasang (iflow, gemini, claude, codex, antigravity, droid, dll.), status Docker/PM2 dan pakej sistem — semua yang kami perlukan untuk mengeluarkan semula isu anda dengan cepat. Lampirkan fail terus pada isu GitHub anda.
Ini menjana `system-info.txt` dengan versi Node.js anda, versi OmniRoute, butiran OS, alat CLI yang dipasang (qoder, gemini, claude, codex, antigravity, droid, dll.), status Docker/PM2 dan pakej sistem — semua yang kami perlukan untuk mengeluarkan semula isu anda dengan cepat. Lampirkan fail terus pada isu GitHub anda.
---
@@ -225,7 +226,7 @@ Ini menjana `system-info.txt` dengan versi Node.js anda, versi OmniRoute, butira
│ ↓ budget limit
├─→ [Tier 3: CHEAP] GLM ($0.6/1M), MiniMax ($0.2/1M)
│ ↓ budget limit
└─→ [Tier 4: FREE] iFlow, Qwen, Kiro (unlimited)
└─→ [Tier 4: FREE] Qoder, Qwen, Kiro (unlimited)
Result: Never stop coding, minimal cost
```
@@ -292,7 +293,7 @@ Tidak semua orang boleh membayar $20200/bulan untuk langganan AI. Pelajar, pe
**Cara OmniRoute menyelesaikannya:**
- **Pembekal Peringkat Percuma Terbina dalam** — Sokongan asli untuk penyedia percuma 100%: iFlow (5 model tanpa had melalui OAuth: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2), Qwen (4 model tanpa had: qwender3-coder3,-coplus qwen3-coder-next, vision-model), Kiro (Claude + AWS Builder ID secara percuma), Gemini CLI (180K token/bulan percuma)
- **Pembekal Peringkat Percuma Terbina dalam** — Sokongan asli untuk penyedia percuma 100%: Qoder (5 model tanpa had melalui OAuth: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2), Qwen (4 model tanpa had: qwender3-coder3,-coplus qwen3-coder-next, vision-model), Kiro (Claude + AWS Builder ID secara percuma), Gemini CLI (180K token/bulan percuma)
- **Ollama Cloud** — Model Ollama dihoskan awan di `api.ollama.com` dengan peringkat "Penggunaan cahaya" percuma; gunakan awalan `ollamacloud/<model>`
- **Kombo Percuma-Sahaja** — Rantaian `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = $0/bulan tanpa masa berhenti sifar
- **Akses Percuma NVIDIA NIM** — ~40 RPM dev-forever akses percuma kepada 70+ model di build.nvidia.com (peralihan daripada kredit kepada had kadar tulen)
@@ -356,7 +357,7 @@ Kod Claude, Codex, Gemini CLI, Copilot — semuanya menggunakan OAuth 2.0 dengan
**Cara OmniRoute menyelesaikannya:**
- **Muat Semula Token Auto** — Token OAuth dimuat semula di latar belakang sebelum tamat tempoh
- **OAuth 2.0 (PKCE) Terbina dalam** — Aliran automatik untuk Kod Claude, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
- **OAuth 2.0 (PKCE) Terbina dalam** — Aliran automatik untuk Kod Claude, Codex, Gemini CLI, Copilot, Kiro, Qwen, Qoder
- **OAuth Berbilang Akaun** — Berbilang akaun bagi setiap pembekal melalui pengekstrakan token JWT/ID
- **OAuth LAN/Remote Fix** — Pengesanan IP peribadi untuk `redirect_uri` + mod URL manual untuk pelayan jauh
- **OAuth Behind Nginx** — Menggunakan `window.location.origin` untuk keserasian proksi terbalik
@@ -733,7 +734,7 @@ Outcome: deep fallback depth for deadline-critical workloads
| Langkah | Tindakan | Pembekal Dibuka Kunci |
| ------- | ------------------------------------------------------- | ------------------------------------------------------------------ |
| 1 | Sambung **Kiro** (AWS Builder ID OAuth) | Claude Sonnet 4.5, Haiku 4.5 — **tanpa had** |
| 2 | Sambung **iFlow** (Google OAuth) | kimi-k2-thinking, qwen3-coder-plus, deepseek-r1... — **tanpa had** |
| 2 | Sambung **Qoder** (Google OAuth) | kimi-k2-thinking, qwen3-coder-plus, deepseek-r1... — **tanpa had** |
| 3 | Sambung **Qwen** (Kod Peranti) | qwen3-coder-plus, qwen3-coder-flash... — **tanpa had** |
| 4 | Sambung **Gemini CLI** (Google OAuth) | gemini-3-flash, Gemini-2.5-pro — **180K/bln percuma** |
| 5 | `/dashboard/combos`**Templat Timbunan Percuma ($0)** | Round-robin semua pembekal percuma secara automatik |
@@ -942,7 +943,7 @@ Apabila diminimumkan, OmniRoute tinggal dalam dulang sistem anda dengan tindakan
| | MiniMax M2.1 | $0.2/1J | 5 jam bergolek | Pilihan termurah |
| | Kimi K2.5 (Moonshot API) 🆕 | Bayar setiap penggunaan | Tiada | Akses langsung Moonshot API |
| | Kimi K2 | $9/bln flat | 10 juta token/bln | Kos yang boleh diramal |
| **🆓 PERCUMA** | iFlow | **$0** | tanpa had | 5 model tanpa had |
| **🆓 PERCUMA** | Qoder | **$0** | tanpa had | 5 model tanpa had |
| | Qwen | **$0** | tanpa had | 4 model tanpa had |
| | Kiro | **$0** | tanpa had | Claude Sonnet/Haiku (Pembina AWS) |
| | LongCat Flash-Lite 🆕 | **$0** (50J tok/hari 🔥) | 1 RPS | Kuota percuma terbesar di Bumi |
@@ -957,7 +958,7 @@ Apabila diminimumkan, OmniRoute tinggal dalam dulang sistem anda dengan tindakan
```
# 🆓 Ultimate Free Stack 2026 — 11 Providers, $0 Forever
Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
Qwen (qw/) → qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next UNLIMITED
@@ -987,7 +988,7 @@ Cerebras (cerebras/) → Llama/Qwen world-fastest — 1M tok/day
| `claude-haiku-4.5` | `kr/` | **Tidak terhad** | Tiada had harian dilaporkan |
| `claude-opus-4.6` | `kr/` | **Tidak terhad** | Opus terkini melalui Kiro |
### 🟢 MODEL IFLOW (OAuth Percuma — Tiada Kad Kredit)
### 🟢 MODEL QODER (OAuth Percuma — Tiada Kad Kredit)
| Model | Awalan | Had | Had Kadar |
| ------------------ | ------ | ---------------- | ------------------------- |
@@ -1086,7 +1087,7 @@ Tersedia secara percuma: `qwen3-235b-a22b-instruct-2507` (Qwen3 235B!), `llama-3
>
> ```
> Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
> iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
> Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
> Qwen (qw/) → qwen3-coder models UNLIMITED
@@ -1219,6 +1220,7 @@ OmniRoute v2.0 dibina sebagai platform operasi, bukan hanya proksi geganti.
| Ciri | Apa yang Dilakukan |
| ------------------------------------- | ---------------------------------------------------------------- |
| 📝 **Permintaan + Pembalakan Proksi** | Permintaan/tindak balas penuh dan pengelogan proksi |
| 📉 **Streamed Detailed Logs** 🆕 | Reconstructs SSE payload streams cleanly into the UI |
| 📋 **Papan Pemuka Log Bersatu** | Permintaan, proksi, audit dan paparan konsol dalam satu halaman |
| 🔍 **Minta Telemetri** | kependaman p50/p95/p99 dan pengesanan permintaan |
| 🏥 **Papan Pemuka Kesihatan** | Masa aktif, keadaan pemutus, sekatan, statistik cache |
@@ -1239,6 +1241,7 @@ OmniRoute v2.0 dibina sebagai platform operasi, bukan hanya proksi geganti.
| 🔏 **Togol Cap Jari CLI** | Padanan cap jari setiap pembekal dalam Tetapan > Keselamatan |
| 🌐 **i18n (30 bahasa)** | Papan pemuka penuh + sokongan bahasa dokumen dengan liputan RTL |
| 🧹 **Kosongkan Semua Model** | Pembersihan senarai model satu klik dalam butiran pembekal |
| 👁️ **Sidebar Controls** 🆕 | Hide components and integrations from Appearance Settings |
| 📋 **Templat Isu** | Templat GitHub standard untuk pepijat dan ciri |
| 📂 **Direktori Data Tersuai** | `DATA_DIR` ganti untuk lokasi storan |
@@ -1534,11 +1537,11 @@ Models:
<details>
<summary><b>🆓 Pembekal PERCUMA (Sandaran Kecemasan)</b></summary>
### iFlow (5 model PERCUMA melalui OAuth)
### Qoder (5 model PERCUMA melalui OAuth)
```bash
Dashboard → Connect iFlow
iFlow OAuth login
Dashboard → Connect Qoder
Qoder OAuth login
→ Unlimited usage
Models:
@@ -1736,7 +1739,7 @@ opencode
- Semak statistik penggunaan dalam Papan Pemuka → Kos
- Tukar model utama kepada GLM/MiniMax
- Gunakan peringkat percuma (Gemini CLI, iFlow) untuk tugasan yang tidak kritikal
- Gunakan peringkat percuma (Gemini CLI, Qoder) untuk tugasan yang tidak kritikal
**Port papan pemuka/API salah**
+16 -13
View File
@@ -36,6 +36,7 @@ _Uw universele API-proxy: één eindpunt, meer dan 67 providers, geen downtime.
| ✅ **Routevalidatie** | Alle 176 API-routes nu gevalideerd met Zod-schema's + `validateBody()` — CI `check:route-validation:t06` passen |
| 🐛 **omniModel-tag lekt** | Interne `<omniModel>`-tags lekken niet langer naar clients in SSE-streamingreacties (#585) |
| 🔑 **Geregistreerde sleutels-API** | API-sleutels automatisch inrichten via `POST /api/v1/registered-keys` met handhaving van quota per provider/account, idempotentie, SHA-256-opslag en optionele GitHub-probleemrapportage |
| 👁️ **Scoped API Key Reveal** 🆕 | Opt-in recovery of API keys via `ALLOW_API_KEY_REVEAL` |
| 🎨 **Providerpictogrammen** | 130+ providerlogo's via `@lobehub/icons` (SVG) met PNG → generieke fallback-keten |
| 🔄 **Model automatische synchronisatie** | 24-uurs planner en handmatige UI-schakelaar om modellijsten te synchroniseren voor ingebouwde en aangepaste OpenAI-compatibele providers |
| 🌐 **OpenCode Zen/Go** | Twee nieuwe providers van @kang-heewon via PR #530: gratis niveau + abonnementsniveau via `OpencodeExecutor` |
@@ -199,7 +200,7 @@ Wanneer u een probleem opent, voert u de opdracht system-info uit en voegt u het
npm run system-info
```
Dit genereert een `system-info.txt` met uw Node.js-versie, OmniRoute-versie, OS-details, geïnstalleerde CLI-tools (iflow, gemini, claude, codex, antigravity, droid, enz.), Docker/PM2-status en systeempakketten - alles wat we nodig hebben om uw probleem snel te reproduceren. Voeg het bestand rechtstreeks toe aan uw GitHub-probleem.
Dit genereert een `system-info.txt` met uw Node.js-versie, OmniRoute-versie, OS-details, geïnstalleerde CLI-tools (qoder, gemini, claude, codex, antigravity, droid, enz.), Docker/PM2-status en systeempakketten - alles wat we nodig hebben om uw probleem snel te reproduceren. Voeg het bestand rechtstreeks toe aan uw GitHub-probleem.
---
@@ -225,7 +226,7 @@ Dit genereert een `system-info.txt` met uw Node.js-versie, OmniRoute-versie, OS-
│ ↓ budget limit
├─→ [Tier 3: CHEAP] GLM ($0.6/1M), MiniMax ($0.2/1M)
│ ↓ budget limit
└─→ [Tier 4: FREE] iFlow, Qwen, Kiro (unlimited)
└─→ [Tier 4: FREE] Qoder, Qwen, Kiro (unlimited)
Result: Never stop coding, minimal cost
```
@@ -292,7 +293,7 @@ Niet iedereen kan $ 20-200 per maand betalen voor AI-abonnementen. Studenten, on
**Hoe OmniRoute het oplost:**
- **Free Tier Providers ingebouwd** — Native ondersteuning voor 100% gratis providers: iFlow (5 onbeperkte modellen via OAuth: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2), Qwen (4 onbeperkte modellen: qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next, vision-model), Kiro (Claude + AWS Builder ID gratis), Gemini CLI (180K tokens/maand gratis)
- **Free Tier Providers ingebouwd** — Native ondersteuning voor 100% gratis providers: Qoder (5 onbeperkte modellen via OAuth: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2), Qwen (4 onbeperkte modellen: qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next, vision-model), Kiro (Claude + AWS Builder ID gratis), Gemini CLI (180K tokens/maand gratis)
- **Ollama Cloud** — In de cloud gehoste Ollama-modellen op `api.ollama.com` met gratis laag "Licht gebruik"; gebruik het voorvoegsel `ollamacloud/<model>`
- **Alleen gratis combo's** — Chain `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = $0/maand zonder downtime
- **NVIDIA NIM Free Access** — ~40 RPM ontwikkelaars-voor altijd gratis toegang tot meer dan 70 modellen op build.nvidia.com (overgang van credits naar pure tarieflimieten)
@@ -356,7 +357,7 @@ Claude Code, Codex, Gemini CLI, Copilot: ze gebruiken allemaal OAuth 2.0 met afl
**Hoe OmniRoute het oplost:**
- **Automatische tokenvernieuwing**: OAuth-tokens worden op de achtergrond vernieuwd voordat ze verlopen
- **OAuth 2.0 (PKCE) ingebouwd** — Automatische stroom voor Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
- **OAuth 2.0 (PKCE) ingebouwd** — Automatische stroom voor Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, Qoder
- **Multi-Account OAuth** — Meerdere accounts per provider via JWT/ID-tokenextractie
- **OAuth LAN/Remote Fix** — Privé-IP-detectie voor `redirect_uri` + handmatige URL-modus voor externe servers
- **OAuth achter Nginx** — Gebruikt `window.location.origin` voor reverse proxy-compatibiliteit
@@ -733,7 +734,7 @@ Outcome: deep fallback depth for deadline-critical workloads
| Stap | Actie | Aanbieders ontgrendeld |
| ---- | ----------------------------------------------------- | ------------------------------------------------------------------ |
| 1 | Verbind **Kiro** (AWS Builder ID OAuth) | Claude Sonnet 4.5, Haiku 4.5 — **onbeperkt** |
| 2 | **iFlow** (Google OAuth) verbinden | kimi-k2-thinking, qwen3-coder-plus, deepseek-r1... — **onbeperkt** |
| 2 | **Qoder** (Google OAuth) verbinden | kimi-k2-thinking, qwen3-coder-plus, deepseek-r1... — **onbeperkt** |
| 3 | Verbind **Qwen** (apparaatcode) | qwen3-coder-plus, qwen3-coder-flash... — **onbeperkt** |
| 4 | **Gemini CLI** verbinden (Google OAuth) | gemini-3-flash, gemini-2.5-pro — **180K/maand gratis** |
| 5 | `/dashboard/combos`**Gratis stapel ($0)**-sjabloon | Round-robin alle gratis aanbieders automatisch |
@@ -942,7 +943,7 @@ Wanneer geminimaliseerd, blijft OmniRoute in uw systeemvak staan met snelle acti
| | MiniMax M2.1 | $ 0,2/1 miljoen | 5-uurs rollen | Goedkoopste optie |
| | Kimi K2.5 (Moonshot-API) 🆕 | Betalen per gebruik | Geen | Directe Moonshot API-toegang |
| | Kimi K2 | $ 9/maand plat | 10 miljoen tokens/maand | Voorspelbare kosten |
| **🆓 GRATIS** | iFlow | **$0** | Onbeperkt | 5 modellen onbeperkt |
| **🆓 GRATIS** | Qoder | **$0** | Onbeperkt | 5 modellen onbeperkt |
| | Qwen | **$0** | Onbeperkt | 4 modellen onbeperkt |
| | Kiro | **$0** | Onbeperkt | Claude Sonnet/Haiku (AWS-bouwer) |
| | LongCat Flash-Lite 🆕 | **$0** (50 miljoen tok/dag 🔥) | 1 RPS | Grootste gratis quotum ter wereld |
@@ -957,7 +958,7 @@ Wanneer geminimaliseerd, blijft OmniRoute in uw systeemvak staan met snelle acti
```
# 🆓 Ultimate Free Stack 2026 — 11 Providers, $0 Forever
Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
Qwen (qw/) → qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next UNLIMITED
@@ -987,7 +988,7 @@ Cerebras (cerebras/) → Llama/Qwen world-fastest — 1M tok/day
| `claude-haiku-4.5` | `kr/` | **Onbeperkt** | Geen gerapporteerde dagelijkse limiet |
| `claude-opus-4.6` | `kr/` | **Onbeperkt** | Nieuwste opus via Kiro |
### 🟢 IFLOW-MODELLEN (gratis OAuth — geen creditcard)
### 🟢 QODER-MODELLEN (gratis OAuth — geen creditcard)
| Model | Voorvoegsel | Limiet | Tarieflimiet |
| ------------------ | ----------- | ------------- | -------------------------- |
@@ -1086,7 +1087,7 @@ Gratis verkrijgbaar: `qwen3-235b-a22b-instruct-2507` (Qwen3 235B!), `llama-3.1-7
>
> ```
> Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
> iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
> Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
> Qwen (qw/) → qwen3-coder models UNLIMITED
@@ -1219,6 +1220,7 @@ OmniRoute v2.0 is gebouwd als een operationeel platform, niet alleen als een rel
| Kenmerk | Wat het doet |
| --------------------------------- | ----------------------------------------------------------------------- |
| 📝 **Verzoek + proxyregistratie** | Volledige aanvraag/antwoord en proxyregistratie |
| 📉 **Streamed Detailed Logs** 🆕 | Reconstructs SSE payload streams cleanly into the UI |
| 📋 **Unified Logdashboard** | Verzoek-, proxy-, audit- en consoleweergaven op één pagina |
| 🔍 **Telemetrie aanvragen** | p50/p95/p99-latentie en tracering van aanvragen |
| 🏥 **Gezondheidsdashboard** | Uptime, status van stroomonderbrekers, uitsluitingen, cachestatistieken |
@@ -1239,6 +1241,7 @@ OmniRoute v2.0 is gebouwd als een operationeel platform, niet alleen als een rel
| 🔏 **CLI-vingerafdrukschakelaar** | Matching van vingerafdrukken per provider in Instellingen > Beveiliging |
| 🌐 **i18n (30 talen)** | Volledig dashboard + documenttaalondersteuning met RTL-dekking |
| 🧹 **Alle modellen wissen** | Modellijst wissen met één klik in providergegevens |
| 👁️ **Sidebar Controls** 🆕 | Hide components and integrations from Appearance Settings |
| 📋 **Uitgiftesjablonen** | Gestandaardiseerde GitHub-sjablonen voor bugs en functies |
| 📂 **Aangepaste gegevensmap** | `DATA_DIR` overschrijven voor opslaglocatie |
@@ -1534,11 +1537,11 @@ Models:
<details>
<summary><b>🆓 GRATIS providers (noodback-up)</b></summary>
### iFlow (5 GRATIS modellen via OAuth)
### Qoder (5 GRATIS modellen via OAuth)
```bash
Dashboard → Connect iFlow
iFlow OAuth login
Dashboard → Connect Qoder
Qoder OAuth login
→ Unlimited usage
Models:
@@ -1736,7 +1739,7 @@ opencode
- Controleer gebruiksstatistieken in Dashboard → Kosten
- Schakel het primaire model over naar GLM/MiniMax
- Gebruik de gratis laag (Gemini CLI, iFlow) voor niet-kritieke taken
- Gebruik de gratis laag (Gemini CLI, Qoder) voor niet-kritieke taken
**Dashboard-/API-poorten zijn verkeerd**
+16 -13
View File
@@ -199,7 +199,7 @@ Når du åpner et problem, kjør systeminfo-kommandoen og legg ved den genererte
npm run system-info
```
Dette genererer en `system-info.txt` med Node.js-versjonen, OmniRoute-versjonen, OS-detaljer, installerte CLI-verktøy (iflow, gemini, claude, codex, antigravity, droid, etc.), Docker/PM2-status og systempakker alt vi trenger for å gjenskape problemet raskt. Legg ved filen direkte til GitHub-problemet ditt.
Dette genererer en `system-info.txt` med Node.js-versjonen, OmniRoute-versjonen, OS-detaljer, installerte CLI-verktøy (qoder, gemini, claude, codex, antigravity, droid, etc.), Docker/PM2-status og systempakker alt vi trenger for å gjenskape problemet raskt. Legg ved filen direkte til GitHub-problemet ditt.
---
@@ -225,7 +225,7 @@ Dette genererer en `system-info.txt` med Node.js-versjonen, OmniRoute-versjonen,
│ ↓ budget limit
├─→ [Tier 3: CHEAP] GLM ($0.6/1M), MiniMax ($0.2/1M)
│ ↓ budget limit
└─→ [Tier 4: FREE] iFlow, Qwen, Kiro (unlimited)
└─→ [Tier 4: FREE] Qoder, Qwen, Kiro (unlimited)
Result: Never stop coding, minimal cost
```
@@ -292,7 +292,7 @@ Ikke alle kan betale $20200 per måned for AI-abonnementer. Studenter, utvikl
**Hvordan OmniRoute løser det:**
- **Gratis-tilbydere innebygd** — Innebygd støtte for 100 % gratis leverandører: iFlow (5 ubegrensede modeller via OAuth: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2), Qwen: 4 qwen3-modeller,-r qwen3-coder-flash, qwen3-coder-next, vision-model), Kiro (Claude + AWS Builder ID gratis), Gemini CLI (180K tokens/måned gratis)
- **Gratis-tilbydere innebygd** — Innebygd støtte for 100 % gratis leverandører: Qoder (5 ubegrensede modeller via OAuth: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2), Qwen: 4 qwen3-modeller,-r qwen3-coder-flash, qwen3-coder-next, vision-model), Kiro (Claude + AWS Builder ID gratis), Gemini CLI (180K tokens/måned gratis)
- **Ollama Cloud** — Ollama-modeller med skyvert hos `api.ollama.com` med gratis «Lett bruk»-lag; bruk `ollamacloud/<model>` prefiks
- **Kun gratis kombinasjoner** — Kjede `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = $0/måned med null nedetid
- **NVIDIA NIM Free Access** — ~40 RPM dev-forever gratis tilgang til 70+ modeller på build.nvidia.com (overgang fra kreditter til rene rategrenser)
@@ -356,7 +356,7 @@ Claude Code, Codex, Gemini CLI, Copilot alle bruker OAuth 2.0 med tokens som
**Hvordan OmniRoute løser det:**
- **Automatisk oppdatering av token** — OAuth-tokener oppdateres i bakgrunnen før utløp
- **OAuth 2.0 (PKCE) innebygd** — Automatisk flyt for Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
- **OAuth 2.0 (PKCE) innebygd** — Automatisk flyt for Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, Qoder
- **Multi-Account OAuth** - Flere kontoer per leverandør via JWT/ID-tokenutvinning
- **OAuth LAN/Remote Fix** — Privat IP-deteksjon for `redirect_uri` + manuell URL-modus for eksterne servere
- **OAuth Behind Nginx** — Bruker `window.location.origin` for omvendt proxy-kompatibilitet
@@ -733,7 +733,7 @@ Outcome: deep fallback depth for deadline-critical workloads
| Trinn | Handling | Leverandører ulåst |
| ----- | ------------------------------------------------ | ------------------------------------------------------------------- |
| 1 | Koble til **Kiro** (AWS Builder ID OAuth) | Claude Sonnet 4.5, Haiku 4.5 — **ubegrenset** |
| 2 | Koble til **iFlow** (Google OAuth) | kimi-k2-tenkning, qwen3-coder-plus, deepseek-r1... — **ubegrenset** |
| 2 | Koble til **Qoder** (Google OAuth) | kimi-k2-tenkning, qwen3-coder-plus, deepseek-r1... — **ubegrenset** |
| 3 | Koble til **Qwen** (enhetskode) | qwen3-coder-pluss, qwen3-coder-flash... — **ubegrenset** |
| 4 | Koble til **Gemini CLI** (Google OAuth) | gemini-3-flash, gemini-2.5-pro — **180K/mnd gratis** |
| 5 | `/dashboard/combos`**Gratis stabel ($0)** mal | Round-robin alle gratisleverandører automatisk |
@@ -942,7 +942,7 @@ Når den er minimert, lever OmniRoute i systemstatusfeltet med raske handlinger:
| | MiniMax M2.1 | $0,2/1M | 5-timers rullende | Billigste alternativ |
| | Kimi K2.5 (Moonshot API) 🆕 | Betal per bruk | Ingen | Direkte Moonshot API-tilgang |
| | Kimi K2 | $9/md leilighet | 10M tokens/md | Forutsigbar kostnad |
| **🆓 GRATIS** | iFlow | **$0** | Ubegrenset | 5 modeller ubegrenset |
| **🆓 GRATIS** | Qoder | **$0** | Ubegrenset | 5 modeller ubegrenset |
| | Qwen | **$0** | Ubegrenset | 4 modeller ubegrenset |
| | Kiro | **$0** | Ubegrenset | Claude Sonnet/Haiku (AWS-bygger) |
| | LongCat Flash-Lite 🆕 | **$0** (50 millioner tok/dag 🔥) | 1 RPS | Største gratis kvote på jorden |
@@ -957,7 +957,7 @@ Når den er minimert, lever OmniRoute i systemstatusfeltet med raske handlinger:
```
# 🆓 Ultimate Free Stack 2026 — 11 Providers, $0 Forever
Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
Qwen (qw/) → qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next UNLIMITED
@@ -987,7 +987,7 @@ Cerebras (cerebras/) → Llama/Qwen world-fastest — 1M tok/day
| `claude-haiku-4.5` | `kr/` | **Ubegrenset** | Ingen rapportert daglig tak |
| `claude-opus-4.6` | `kr/` | **Ubegrenset** | Siste Opus via Kiro |
### IFLOW-MODELLER (gratis OAuth uten kredittkort)
### QODER-MODELLER (gratis OAuth uten kredittkort)
| Modell | Prefiks | Grens | Satsgrense |
| ------------------ | ------- | -------------- | -------------------- |
@@ -1086,7 +1086,7 @@ Gratis tilgjengelig: `qwen3-235b-a22b-instruct-2507` (Qwen3 235B!), `llama-3.1-7
>
> ```
> Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
> iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
> Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
> Qwen (qw/) → qwen3-coder models UNLIMITED
@@ -1212,6 +1212,7 @@ OmniRoute v2.0 er bygget som en operativ plattform, ikke bare en reléproxy.
| 🌐 **IP-filtrering** | Tillatelsesliste/blokkeringslistekontroll for eksponerte distribusjoner |
| 📊 **Redigerbare satsgrenser** | Konfigurerbare grenser på globalt nivå/leverandørnivå med utholdenhet |
| 🔑 **API Key Management + Scoping** | Sikker nøkkelutstedelse/rotasjon og modell/leverandørkontroller |
| 👁️ **Scoped API Key Reveal** 🆕 | Opt-in recovery of API keys via `ALLOW_API_KEY_REVEAL` |
| 🛡️ **Beskyttet `/models`** | Valgfri godkjenning og leverandørskjul for modellkatalog |
### 📊 Observerbarhet og analyse
@@ -1219,6 +1220,7 @@ OmniRoute v2.0 er bygget som en operativ plattform, ikke bare en reléproxy.
| Funksjon | Hva det gjør |
| ---------------------------------- | ---------------------------------------------------------------- |
| 📝 **Forespørsel + proxy-logging** | Full forespørsel/svar og proxy-logging |
| 📉 **Streamed Detailed Logs** 🆕 | Reconstructs SSE payload streams cleanly into the UI |
| 📋 **Unified Logs Dashboard** | Forespørsels-, proxy-, revisjons- og konsollvisninger på én side |
| 🔍 **Be om telemetri** | p50/p95/p99 ventetid og forespørselssporing |
| 🏥 **Helse Dashboard** | Oppetid, breaker-tilstander, lockouts, cachestatistikk |
@@ -1239,6 +1241,7 @@ OmniRoute v2.0 er bygget som en operativ plattform, ikke bare en reléproxy.
| 🔏 **CLI Fingerprint Toggle** | Fingeravtrykksmatching per leverandør i Innstillinger > Sikkerhet |
| 🌐 **i18n (30 språk)** | Fullt dashbord + støtte for dokumentspråk med RTL-dekning |
| 🧹 **Slett alle modeller** | Sletting av modellliste med ett klikk i leverandørdetaljer |
| 👁️ **Sidebar Controls** 🆕 | Hide components and integrations from Appearance Settings |
| 📋 **Utgavemaler** | Standardiserte GitHub-maler for feil og funksjoner |
| 📂 **Tilpasset datakatalog** | `DATA_DIR` overstyring for lagringssted |
@@ -1534,11 +1537,11 @@ Models:
<details>
<summary><b>🆓 GRATIS Leverandører (Emergency Backup)</b></summary>
### iFlow (5 GRATIS modeller via OAuth)
### Qoder (5 GRATIS modeller via OAuth)
```bash
Dashboard → Connect iFlow
iFlow OAuth login
Dashboard → Connect Qoder
Qoder OAuth login
→ Unlimited usage
Models:
@@ -1736,7 +1739,7 @@ opencode
- Sjekk bruksstatistikk i Dashboard → Kostnader
- Bytt primærmodell til GLM/MiniMax
- Bruk gratis nivå (Gemini CLI, iFlow) for ikke-kritiske oppgaver
- Bruk gratis nivå (Gemini CLI, Qoder) for ikke-kritiske oppgaver
**Dashboard/API-porter er feil**
+16 -13
View File
@@ -199,7 +199,7 @@ Kapag nagbubukas ng isyu, mangyaring patakbuhin ang system-info command at ilaki
npm run system-info
```
Bumubuo ito ng `system-info.txt` gamit ang iyong bersyon ng Node.js, bersyon ng OmniRoute, mga detalye ng OS, mga naka-install na tool sa CLI (iflow, gemini, claude, codex, antigravity, droid, atbp.), status ng Docker/PM2, at mga system package — lahat ng kailangan namin para mabilis na ma-reproduce ang iyong isyu. Direktang ilakip ang file sa iyong isyu sa GitHub.
Bumubuo ito ng `system-info.txt` gamit ang iyong bersyon ng Node.js, bersyon ng OmniRoute, mga detalye ng OS, mga naka-install na tool sa CLI (qoder, gemini, claude, codex, antigravity, droid, atbp.), status ng Docker/PM2, at mga system package — lahat ng kailangan namin para mabilis na ma-reproduce ang iyong isyu. Direktang ilakip ang file sa iyong isyu sa GitHub.
---
@@ -225,7 +225,7 @@ Bumubuo ito ng `system-info.txt` gamit ang iyong bersyon ng Node.js, bersyon ng
│ ↓ budget limit
├─→ [Tier 3: CHEAP] GLM ($0.6/1M), MiniMax ($0.2/1M)
│ ↓ budget limit
└─→ [Tier 4: FREE] iFlow, Qwen, Kiro (unlimited)
└─→ [Tier 4: FREE] Qoder, Qwen, Kiro (unlimited)
Result: Never stop coding, minimal cost
```
@@ -292,7 +292,7 @@ Hindi lahat ay maaaring magbayad ng $20200/buwan para sa mga subscription sa
**Paano ito niresolba ng OmniRoute:**
- **Libreng Tier Provider Built-in** — Native na suporta para sa 100% libreng provider: iFlow (5 unlimited na mga modelo sa pamamagitan ng OAuth: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2), Qwen (4 unlimited models: qwender3-wenlash3-coplus qwen3-coder-next, vision-model), Kiro (Claude + AWS Builder ID nang libre), Gemini CLI (180K token/buwan libre)
- **Libreng Tier Provider Built-in** — Native na suporta para sa 100% libreng provider: Qoder (5 unlimited na mga modelo sa pamamagitan ng OAuth: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2), Qwen (4 unlimited models: qwender3-wenlash3-coplus qwen3-coder-next, vision-model), Kiro (Claude + AWS Builder ID nang libre), Gemini CLI (180K token/buwan libre)
- **Ollama Cloud** — Cloud-hosted Ollama models sa `api.ollama.com` na may libreng "Light usage" tier; gumamit ng `ollamacloud/<model>` prefix
- **Free-Only Combos** — Chain `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = $0/buwan na walang downtime
- **NVIDIA NIM Free Access** — ~40 RPM dev-forever na libreng access sa 70+ na modelo sa build.nvidia.com (paglilipat mula sa mga credit patungo sa mga purong limitasyon sa rate)
@@ -356,7 +356,7 @@ Claude Code, Codex, Gemini CLI, Copilot — lahat ay gumagamit ng OAuth 2.0 na m
**Paano ito niresolba ng OmniRoute:**
- **Auto Token Refresh** — Ang mga token ng OAuth ay nagre-refresh sa background bago mag-expire
- **OAuth 2.0 (PKCE) Built-in** — Awtomatikong daloy para sa Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
- **OAuth 2.0 (PKCE) Built-in** — Awtomatikong daloy para sa Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, Qoder
- **Multi-Account OAuth** — Maramihang account bawat provider sa pamamagitan ng pagkuha ng token ng JWT/ID
- **OAuth LAN/Remote Fix** — Pribadong IP detection para sa `redirect_uri` + manu-manong URL mode para sa mga malalayong server
- **OAuth Behind Nginx** — Gumagamit ng `window.location.origin` para sa reverse proxy compatibility
@@ -733,7 +733,7 @@ Outcome: deep fallback depth for deadline-critical workloads
| Hakbang | Aksyon | Na-unlock ang Mga Provider |
| ------- | ----------------------------------------------------- | ------------------------------------------------------------------ |
| 1 | Ikonekta ang **Kiro** (AWS Builder ID OAuth) | Claude Sonnet 4.5, Haiku 4.5 — **walang limitasyon** |
| 2 | Ikonekta ang **iFlow** (Google OAuth) | kimi-k2-thinking, qwen3-coder-plus, deepseek-r1... — **unlimited** |
| 2 | Ikonekta ang **Qoder** (Google OAuth) | kimi-k2-thinking, qwen3-coder-plus, deepseek-r1... — **unlimited** |
| 3 | Ikonekta ang **Qwen** (Device Code) | qwen3-coder-plus, qwen3-coder-flash... — **walang limitasyon** |
| 4 | Ikonekta ang **Gemini CLI** (Google OAuth) | gemini-3-flash, gemini-2.5-pro — **180K/mo libre** |
| 5 | `/dashboard/combos`**Libreng Stack ($0)** template | Awtomatikong round-robin lahat ng libreng provider |
@@ -942,7 +942,7 @@ Kapag pinaliit, nakatira ang OmniRoute sa iyong system tray na may mabilis na pa
| | MiniMax M2.1 | $0.2/1M | 5 oras na rolling | Pinaka murang opsyon |
| | Kimi K2.5 (Moonshot API) 🆕 | Pay-per-use | Wala | Direktang Moonshot API access |
| | Kimi K2 | $9/buwan flat | 10M token/buwan | Nahuhulaang gastos |
| **🆓 LIBRE** | iFlow | **$0** | Walang limitasyong | 5 mga modelong walang limitasyon |
| **🆓 LIBRE** | Qoder | **$0** | Walang limitasyong | 5 mga modelong walang limitasyon |
| | Qwen | **$0** | Walang limitasyong | 4 na modelong walang limitasyon |
| | Kiro | **$0** | Walang limitasyong | Claude Sonnet/Haiku (AWS Builder) |
| | LongCat Flash-Lite 🆕 | **$0** (50M tok/araw 🔥) | 1 RPS | Pinakamalaking libreng quota sa Earth |
@@ -957,7 +957,7 @@ Kapag pinaliit, nakatira ang OmniRoute sa iyong system tray na may mabilis na pa
```
# 🆓 Ultimate Free Stack 2026 — 11 Providers, $0 Forever
Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
Qwen (qw/) → qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next UNLIMITED
@@ -987,7 +987,7 @@ Cerebras (cerebras/) → Llama/Qwen world-fastest — 1M tok/day
| `claude-haiku-4.5` | `kr/` | **Walang limitasyon** | Walang iniulat na pang-araw-araw na cap |
| `claude-opus-4.6` | `kr/` | **Walang limitasyon** | Pinakabagong Opus sa pamamagitan ng Kiro |
### 🟢 MGA MODELONG IFLOW (Libreng OAuth — Walang Credit Card)
### 🟢 MGA MODELONG QODER (Libreng OAuth — Walang Credit Card)
| Modelo | Prefix | Limitahan | Hangganan ng Rate |
| ------------------ | ------ | --------------------- | --------------------- |
@@ -1086,7 +1086,7 @@ Available nang libre: `qwen3-235b-a22b-instruct-2507` (Qwen3 235B!), `llama-3.1-
>
> ```
> Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
> iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
> Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
> Qwen (qw/) → qwen3-coder models UNLIMITED
@@ -1212,6 +1212,7 @@ Ang OmniRoute v2.0 ay binuo bilang isang operating platform, hindi lamang isang
| 🌐 **Pag-filter ng IP** | Allowlist/blocklist control para sa mga nakalantad na deployment |
| 📊 **Mga Nae-edit na Limitasyon sa Rate** | Nako-configure ang mga limitasyon sa antas ng global/provider na may pagtitiyaga |
| 🔑 **API Key Management + Scoping** | Secure na pagpapalabas/pag-ikot ng susi at mga kontrol ng modelo/tagapagbigay |
| 👁️ **Scoped API Key Reveal** 🆕 | Opt-in recovery of API keys via `ALLOW_API_KEY_REVEAL` |
| 🛡️ **Protektado `/models`** | Opsyonal na auth gating at pagtatago ng provider para sa catalog ng modelo |
### 📊 Pagmamasid at Analytics
@@ -1219,6 +1220,7 @@ Ang OmniRoute v2.0 ay binuo bilang isang operating platform, hindi lamang isang
| Tampok | Ano ang Ginagawa Nito |
| ------------------------------------- | -------------------------------------------------------------------- |
| 📝 **Kahilingan + Proxy Logging** | Buong kahilingan/tugon at proxy logging |
| 📉 **Streamed Detailed Logs** 🆕 | Reconstructs SSE payload streams cleanly into the UI |
| 📋 **Unified Logs Dashboard** | Kahilingan, proxy, audit, at console view sa isang page |
| 🔍 **Humiling ng Telemetry** | p50/p95/p99 latency at kahilingan sa pagsubaybay |
| 🏥 **Dashboard ng Kalusugan** | Uptime, breaker states, lockouts, cache stats |
@@ -1239,6 +1241,7 @@ Ang OmniRoute v2.0 ay binuo bilang isang operating platform, hindi lamang isang
| 🔏 **CLI Fingerprint Toggle** | Pagtutugma ng fingerprint ng bawat provider sa Mga Setting > Seguridad |
| 🌐 **i18n (30 wika)** | Buong dashboard + suporta sa wika ng mga doc na may saklaw ng RTL |
| 🧹 **I-clear ang Lahat ng Modelo** | Isang-click na pag-clear ng listahan ng modelo sa mga detalye ng provider |
| 👁️ **Sidebar Controls** 🆕 | Hide components and integrations from Appearance Settings |
| 📋 **Mga Template ng Isyu** | Standardized GitHub template para sa mga bug at feature |
| 📂 **Custom na Direktoryo ng Data** | `DATA_DIR` override para sa lokasyon ng storage |
@@ -1534,11 +1537,11 @@ Models:
<details>
<summary><b>🆓 LIBRENG Provider (Emergency Backup)</b></summary>
### iFlow (5 LIBRENG modelo sa pamamagitan ng OAuth)
### Qoder (5 LIBRENG modelo sa pamamagitan ng OAuth)
```bash
Dashboard → Connect iFlow
iFlow OAuth login
Dashboard → Connect Qoder
Qoder OAuth login
→ Unlimited usage
Models:
@@ -1736,7 +1739,7 @@ opencode
- Suriin ang mga istatistika ng paggamit sa Dashboard → Mga Gastos
- Ilipat ang pangunahing modelo sa GLM/MiniMax
- Gumamit ng libreng tier (Gemini CLI, iFlow) para sa mga hindi kritikal na gawain
- Gumamit ng libreng tier (Gemini CLI, Qoder) para sa mga hindi kritikal na gawain
**Mali ang mga dashboard/API port**
+16 -13
View File
@@ -36,6 +36,7 @@ _Twój uniwersalny serwer proxy API — jeden punkt końcowy, ponad 67 dostawcó
| ✅ **Weryfikacja trasy** | Wszystkie 176 tras API zostało teraz zweryfikowanych przy użyciu schematów Zoda + `validateBody()` — CI `check:route-validation:t06` karnety |
| 🐛 **Wyciek tagu omniModel** | Wewnętrzne tagi `<omniModel>` nie wyciekają już do klientów w odpowiedziach strumieniowych SSE (#585) |
| 🔑 **API kluczy zarejestrowanych** | Automatyczne udostępnianie kluczy API za pośrednictwem `POST /api/v1/registered-keys` z egzekwowaniem limitów dla dostawcy/konta, idempotencją, pamięcią SHA-256 i opcjonalnym raportowaniem problemów w serwisie GitHub |
| 👁️ **Scoped API Key Reveal** 🆕 | Opt-in recovery of API keys via `ALLOW_API_KEY_REVEAL` |
| 🎨 **Ikony dostawców** | Ponad 130 logo dostawców za pośrednictwem `@lobehub/icons` (SVG) w formacie PNG → ogólny łańcuch awaryjny |
| 🔄 **Automatyczna synchronizacja modelu** | 24-godzinny harmonogram i ręczny przełącznik interfejsu użytkownika do synchronizacji list modeli dla wbudowanych i niestandardowych dostawców kompatybilnych z OpenAI |
| 🌐 **OpenCode Zen/Go** | Dwóch nowych dostawców od @kang-heewon poprzez PR #530: poziom bezpłatny + poziom subskrypcji przez `OpencodeExecutor` |
@@ -199,7 +200,7 @@ Otwierając zgłoszenie, uruchom komendę system-info i załącz wygenerowany pl
npm run system-info
```
Spowoduje to wygenerowanie pliku `system-info.txt` z wersją Node.js, wersją OmniRoute, szczegółami systemu operacyjnego, zainstalowanymi narzędziami CLI (iflow, gemini, claude, codex, antygrawitacja, droid itp.), statusem Docker/PM2 i pakietami systemowymi — wszystko, czego potrzebujemy, aby szybko odtworzyć problem. Dołącz plik bezpośrednio do swojego zgłoszenia w GitHubie.
Spowoduje to wygenerowanie pliku `system-info.txt` z wersją Node.js, wersją OmniRoute, szczegółami systemu operacyjnego, zainstalowanymi narzędziami CLI (qoder, gemini, claude, codex, antygrawitacja, droid itp.), statusem Docker/PM2 i pakietami systemowymi — wszystko, czego potrzebujemy, aby szybko odtworzyć problem. Dołącz plik bezpośrednio do swojego zgłoszenia w GitHubie.
---
@@ -225,7 +226,7 @@ Spowoduje to wygenerowanie pliku `system-info.txt` z wersją Node.js, wersją Om
│ ↓ budget limit
├─→ [Tier 3: CHEAP] GLM ($0.6/1M), MiniMax ($0.2/1M)
│ ↓ budget limit
└─→ [Tier 4: FREE] iFlow, Qwen, Kiro (unlimited)
└─→ [Tier 4: FREE] Qoder, Qwen, Kiro (unlimited)
Result: Never stop coding, minimal cost
```
@@ -292,7 +293,7 @@ Nie każdy może zapłacić 20200 USD miesięcznie za subskrypcje AI. Studenc
**Jak rozwiązuje to OmniRoute:**
- **Wbudowani dostawcy Free Tier** — Natywne wsparcie dla w 100% darmowych dostawców: iFlow (5 nieograniczonych modeli przez OAuth: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2), Qwen (4 nieograniczone modele: qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next, Vision-model), Kiro (Claude + AWS Builder ID za darmo), Gemini CLI (180 tys. tokenów miesięcznie za darmo)
- **Wbudowani dostawcy Free Tier** — Natywne wsparcie dla w 100% darmowych dostawców: Qoder (5 nieograniczonych modeli przez OAuth: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2), Qwen (4 nieograniczone modele: qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next, Vision-model), Kiro (Claude + AWS Builder ID za darmo), Gemini CLI (180 tys. tokenów miesięcznie za darmo)
- **Ollama Cloud** — modele Ollama hostowane w chmurze pod adresem `api.ollama.com` z bezpłatnym poziomem „Lekkie użycie”; użyj przedrostka `ollamacloud/<model>`
- **Kombinacje dostępne wyłącznie bezpłatnie** — Łańcuch `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = 0 USD/miesiąc z zerowymi przestojami
- **Bezpłatny dostęp do NVIDIA NIM** — bezpłatny dostęp dla deweloperów przy ~40 obr./min na zawsze do ponad 70 modeli na stronie build.nvidia.com (przejście z kredytów na same limity szybkości)
@@ -356,7 +357,7 @@ Claude Code, Codex, Gemini CLI, Copilot — wszystkie korzystają z OAuth 2.0 z
**Jak rozwiązuje to OmniRoute:**
- **Automatyczne odświeżanie tokenu** — tokeny OAuth odświeżają się w tle przed wygaśnięciem
- **Wbudowany OAuth 2.0 (PKCE)** — Automatyczny przepływ dla Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
- **Wbudowany OAuth 2.0 (PKCE)** — Automatyczny przepływ dla Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, Qoder
- **Wielokontowy OAuth** — wiele kont na dostawcę poprzez ekstrakcję tokenów JWT/ID
- **OAuth LAN/Remote Fix** — Wykrywanie prywatnego adresu IP dla `redirect_uri` + ręczny tryb adresu URL dla serwerów zdalnych
- **OAuth Behind Nginx** — Używa `window.location.origin` w celu zapewnienia zgodności z odwrotnym proxy
@@ -733,7 +734,7 @@ Outcome: deep fallback depth for deadline-critical workloads
| Krok | Akcja | Dostawcy odblokowani |
| ---- | --------------------------------------------------------- | ----------------------------------------------------------------------- |
| 1 | Połącz **Kiro** (identyfikator AWS Builder OAuth) | Claude Sonnet 4.5, Haiku 4.5 — **bez ograniczeń** |
| 2 | Połącz **iFlow** (Google OAuth) | myślenie kimi-k2, qwen3-coder-plus, deepseek-r1... — **bez ograniczeń** |
| 2 | Połącz **Qoder** (Google OAuth) | myślenie kimi-k2, qwen3-coder-plus, deepseek-r1... — **bez ograniczeń** |
| 3 | Połącz **Qwen** (kod urządzenia) | qwen3-coder-plus, qwen3-coder-flash... — **bez ograniczeń** |
| 4 | Połącz **Gemini CLI** (Google OAuth) | gemini-3-flash, gemini-2.5-pro — **180 tys./mc za darmo** |
| 5 | `/dashboard/combos`**Szablon darmowego stosu (0 USD)** | Automatycznie okrężnie wszystkich bezpłatnych dostawców |
@@ -942,7 +943,7 @@ Po zminimalizowaniu OmniRoute znajduje się w zasobniku systemowym i oferuje szy
| | MiniMax M2.1 | 0,2 USD/1 mln | 5-godzinne toczenie | Najtańsza opcja |
| | Kimi K2.5 (Moonshot API) 🆕 | Płatność za użycie | Brak | Bezpośredni dostęp do API Moonshot |
| | Kimi K2 | 9 USD miesięcznie | 10 mln tokenów/mies. | Przewidywalny koszt |
| **🆓 DARMOWE** | iFlow | **$0** | Nieograniczony | 5 modeli bez ograniczeń |
| **🆓 DARMOWE** | Qoder | **$0** | Nieograniczony | 5 modeli bez ograniczeń |
| | Qwen | **$0** | Nieograniczony | 4 modele bez ograniczeń |
| | Kiro | **$0** | Nieograniczony | Claude Sonnet/Haiku (konstruktor AWS) |
| | LongCat Flash-Lite 🆕 | **0 $** (50 mln tok/dzień 🔥) | 1 RPS | Największy darmowy limit na Ziemi |
@@ -957,7 +958,7 @@ Po zminimalizowaniu OmniRoute znajduje się w zasobniku systemowym i oferuje szy
```
# 🆓 Ultimate Free Stack 2026 — 11 Providers, $0 Forever
Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
Qwen (qw/) → qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next UNLIMITED
@@ -987,7 +988,7 @@ Cerebras (cerebras/) → Llama/Qwen world-fastest — 1M tok/day
| `claude-haiku-4.5` | `kr/` | **Nieograniczony** | Brak raportu dziennego limitu |
| `claude-opus-4.6` | `kr/` | **Nieograniczony** | Najnowsze Opus przez Kiro |
### 🟢 MODELE IFLOW (bezpłatny OAuth — bez karty kredytowej)
### 🟢 MODELE QODER (bezpłatny OAuth — bez karty kredytowej)
| Modelka | Przedrostek | Limit | Limit stawki |
| ------------------ | ----------- | ------------------ | ----------------------- |
@@ -1086,7 +1087,7 @@ Dostępne bezpłatnie: `qwen3-235b-a22b-instruct-2507` (Qwen3 235B!), `llama-3.1
>
> ```
> Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
> iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
> Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
> Qwen (qw/) → qwen3-coder models UNLIMITED
@@ -1219,6 +1220,7 @@ OmniRoute v2.0 został zbudowany jako platforma operacyjna, a nie tylko pośredn
| Funkcja | Co to robi |
| ------------------------------------ | --------------------------------------------------------------------- |
| 📝 **Żądanie + rejestrowanie proxy** | Pełne rejestrowanie żądań/odpowiedzi i proxy |
| 📉 **Streamed Detailed Logs** 🆕 | Reconstructs SSE payload streams cleanly into the UI |
| 📋 **Ujednolicony panel dzienników** | Widoki żądań, proxy, audytu i konsoli na jednej stronie |
| 🔍 **Poproś o telemetrię** | Opóźnienie p50/p95/p99 i śledzenie żądań |
| 🏥 **Panel zdrowia** | Czas pracy, stany wyłączników, blokady, statystyki pamięci podręcznej |
@@ -1239,6 +1241,7 @@ OmniRoute v2.0 został zbudowany jako platforma operacyjna, a nie tylko pośredn
| 🔏 **Przełączanie linii papilarnych CLI** | Dopasowywanie odcisków palców poszczególnych dostawców w Ustawieniach > Bezpieczeństwo |
| 🌐 **i18n (30 języków)** | Pełny pulpit nawigacyjny + obsługa języków dokumentów z pokryciem RTL |
| 🧹 **Wyczyść wszystkie modele** | Czyszczenie listy modeli jednym kliknięciem w szczegółach dostawcy |
| 👁️ **Sidebar Controls** 🆕 | Hide components and integrations from Appearance Settings |
| 📋 **Szablony wydania** | Standaryzowane szablony GitHub dla błędów i funkcji |
| 📂 **Niestandardowy katalog danych** | `DATA_DIR` zastąpienie lokalizacji przechowywania |
@@ -1534,11 +1537,11 @@ Models:
<details>
<summary><b>🆓 BEZPŁATNI dostawcy (awaryjna kopia zapasowa)</b></summary>
### iFlow (5 DARMOWYCH modeli przez OAuth)
### Qoder (5 DARMOWYCH modeli przez OAuth)
```bash
Dashboard → Connect iFlow
iFlow OAuth login
Dashboard → Connect Qoder
Qoder OAuth login
→ Unlimited usage
Models:
@@ -1736,7 +1739,7 @@ opencode
- Sprawdź statystyki użytkowania w Panelu → Koszty
- Zmień model podstawowy na GLM/MiniMax
- Korzystaj z bezpłatnej warstwy (Gemini CLI, iFlow) do zadań niekrytycznych
- Korzystaj z bezpłatnej warstwy (Gemini CLI, Qoder) do zadań niekrytycznych
**Porty pulpitu nawigacyjnego/API są nieprawidłowe**
+16 -13
View File
@@ -36,6 +36,7 @@ _Seu proxy de API universal — um endpoint, mais de 67 provedores, zero tempo d
| ✅ **Validação de Rota** | Todas as 176 rotas de API agora validadas com esquemas Zod + `validateBody()` — CI `check:route-validation:t06` passa |
| 🐛 ** Vazamento de tag omniModel ** | Tags internas `<omniModel>` não vazam mais para clientes em respostas de streaming SSE (#585) |
| 🔑 **API de chaves registradas** | Provisionamento automático de chaves de API via `POST /api/v1/registered-keys` com aplicação de cota por provedor/conta, idempotência, armazenamento SHA-256 e relatório opcional de problemas do GitHub |
| 👁️ **Scoped API Key Reveal** 🆕 | Opt-in recovery of API keys via `ALLOW_API_KEY_REVEAL` |
| 🎨 **Ícones de provedor** | Mais de 130 logotipos de provedores via `@lobehub/icons` (SVG) com PNG → cadeia de fallback genérica |
| 🔄 **Sincronização automática do modelo** | Agendador 24h e alternância manual da interface do usuário para sincronizar listas de modelos para provedores integrados e personalizados compatíveis com OpenAI |
| 🌐 **OpenCode Zen/Go** | Dois novos provedores de @kang-heewon via PR #530: nível gratuito + nível de assinatura via `OpencodeExecutor` |
@@ -199,7 +200,7 @@ Ao abrir um problema, execute o comando system-info e anexe o arquivo gerado:
npm run system-info
```
Isso gera um `system-info.txt` com sua versão do Node.js, versão do OmniRoute, detalhes do sistema operacional, ferramentas CLI instaladas (iflow, gemini, claude, codex, antigravity, droid, etc.), status do Docker/PM2 e pacotes do sistema — tudo o que precisamos para reproduzir seu problema rapidamente. Anexe o arquivo diretamente ao seu problema do GitHub.
Isso gera um `system-info.txt` com sua versão do Node.js, versão do OmniRoute, detalhes do sistema operacional, ferramentas CLI instaladas (qoder, gemini, claude, codex, antigravity, droid, etc.), status do Docker/PM2 e pacotes do sistema — tudo o que precisamos para reproduzir seu problema rapidamente. Anexe o arquivo diretamente ao seu problema do GitHub.
---
@@ -225,7 +226,7 @@ Isso gera um `system-info.txt` com sua versão do Node.js, versão do OmniRoute,
│ ↓ budget limit
├─→ [Tier 3: CHEAP] GLM ($0.6/1M), MiniMax ($0.2/1M)
│ ↓ budget limit
└─→ [Tier 4: FREE] iFlow, Qwen, Kiro (unlimited)
└─→ [Tier 4: FREE] Qoder, Qwen, Kiro (unlimited)
Result: Never stop coding, minimal cost
```
@@ -292,7 +293,7 @@ Nem todos podem pagar US$ 20200/mês por assinaturas de IA. Estudantes, desen
**Como o OmniRoute resolve isso:**
- **Provedores de nível gratuito integrados** — Suporte nativo para provedores 100% gratuitos: iFlow (5 modelos ilimitados via OAuth: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2), Qwen (4 modelos ilimitados: qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next, vision-model), Kiro (Claude + AWS Builder ID gratuitamente), Gemini CLI (180 mil tokens/mês grátis)
- **Provedores de nível gratuito integrados** — Suporte nativo para provedores 100% gratuitos: Qoder (5 modelos ilimitados via OAuth: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2), Qwen (4 modelos ilimitados: qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next, vision-model), Kiro (Claude + AWS Builder ID gratuitamente), Gemini CLI (180 mil tokens/mês grátis)
- **Ollama Cloud** — Modelos Ollama hospedados na nuvem em `api.ollama.com` com nível gratuito de "uso leve"; use o prefixo `ollamacloud/<model>`
- **Combos somente gratuitos** — Cadeia `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = US$ 0/mês com tempo de inatividade zero
- **NVIDIA NIM Free Access** — ~40 RPM de acesso gratuito para desenvolvedores para sempre a mais de 70 modelos em build.nvidia.com (transição de créditos para limites de taxa pura)
@@ -356,7 +357,7 @@ Claude Code, Codex, Gemini CLI, Copilot — todos usam OAuth 2.0 com tokens expi
**Como o OmniRoute resolve isso:**
- **Atualização automática de token** — Os tokens OAuth são atualizados em segundo plano antes da expiração
- **OAuth 2.0 (PKCE) integrado ** — Fluxo automático para Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
- **OAuth 2.0 (PKCE) integrado ** — Fluxo automático para Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, Qoder
- **OAuth de várias contas** — Várias contas por provedor por meio de extração de token JWT/ID
- **OAuth LAN/Remote Fix** — Detecção de IP privado para `redirect_uri` + modo URL manual para servidores remotos
- **OAuth por trás do Nginx** — Usa `window.location.origin` para compatibilidade de proxy reverso
@@ -733,7 +734,7 @@ Outcome: deep fallback depth for deadline-critical workloads
| Etapa | Ação | Provedores desbloqueados |
| ----- | -------------------------------------------------- | ------------------------------------------------------------------ |
| 1 | Conectar **Kiro** (ID do AWS Builder OAuth) | Claude Soneto 4.5, Haiku 4.5 — **ilimitado** |
| 2 | Conecte **iFlow** (Google OAuth) | kimi-k2-thinking, qwen3-coder-plus, deepseek-r1... — **ilimitado** |
| 2 | Conecte **Qoder** (Google OAuth) | kimi-k2-thinking, qwen3-coder-plus, deepseek-r1... — **ilimitado** |
| 3 | Conecte **Qwen** (código do dispositivo) | qwen3-coder-plus, qwen3-coder-flash... — **ilimitado** |
| 4 | Conecte **Gemini CLI** (Google OAuth) | gemini-3-flash, gemini-2.5-pro — **180K/mês grátis** |
| 5 | `/dashboard/combos`**Pilha grátis ($0)** modelo | Round-robin todos os provedores gratuitos automaticamente |
@@ -942,7 +943,7 @@ Quando minimizado, o OmniRoute fica na bandeja do sistema com ações rápidas:
| | MiniMax M2.1 | US$ 0,2/1 milhão | Rolamento de 5 horas | Opção mais barata |
| | Kimi K2.5 (API Moonshot) 🆕 | Pagamento conforme uso | Nenhum | Acesso direto à API Moonshot |
| | Kimi K2 | $ 9 / mês fixo | 10 milhões de tokens/mês | Custo previsível |
| **🆓 GRÁTIS** | iFlow | **$0** | Ilimitado | 5 modelos ilimitados |
| **🆓 GRÁTIS** | Qoder | **$0** | Ilimitado | 5 modelos ilimitados |
| | Qwen | **$0** | Ilimitado | 4 modelos ilimitados |
| | Kiro | **$0** | Ilimitado | Claude Sonnet/Haiku (Construtor AWS) |
| | LongCat Flash Lite 🆕 | **$0** (50 milhões de dólares/dia 🔥) | 1RPS | Maior cota gratuita do planeta |
@@ -957,7 +958,7 @@ Quando minimizado, o OmniRoute fica na bandeja do sistema com ações rápidas:
```
# 🆓 Ultimate Free Stack 2026 — 11 Providers, $0 Forever
Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
Qwen (qw/) → qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next UNLIMITED
@@ -987,7 +988,7 @@ Cerebras (cerebras/) → Llama/Qwen world-fastest — 1M tok/day
| `claude-haiku-4.5` | `kr/` | **Ilimitado** | Nenhum limite diário comunicado |
| `claude-opus-4.6` | `kr/` | **Ilimitado** | Último Opus via Kiro |
### 🟢 MODELOS IFLOW (OAuth grátis — sem cartão de crédito)
### 🟢 MODELOS QODER (OAuth grátis — sem cartão de crédito)
| Modelo | Prefixo | Limite | Limite de taxa |
| ------------------ | ------- | ------------- | ------------------------------- |
@@ -1086,7 +1087,7 @@ Disponível gratuitamente: `qwen3-235b-a22b-instruct-2507` (Qwen3 235B!), `llama
>
> ```
> Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
> iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
> Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
> Qwen (qw/) → qwen3-coder models UNLIMITED
@@ -1219,6 +1220,7 @@ OmniRoute v2.0 é construído como uma plataforma operacional, não apenas um pr
| Recurso | O que faz |
| -------------------------------------- | ---------------------------------------------------------------------------- |
| 📝 **Solicitação + Registro de Proxy** | Solicitação/resposta completa e registro de proxy |
| 📉 **Streamed Detailed Logs** 🆕 | Reconstructs SSE payload streams cleanly into the UI |
| 📋 **Painel de registros unificado** | Visualizações de solicitação, proxy, auditoria e console em uma página |
| 🔍 **Solicitar Telemetria** | Latência p50/p95/p99 e rastreamento de solicitação |
| 🏥 **Painel de saúde** | Tempo de atividade, estados de disjuntores, bloqueios, estatísticas de cache |
@@ -1239,6 +1241,7 @@ OmniRoute v2.0 é construído como uma plataforma operacional, não apenas um pr
| 🔏 **Alternar impressão digital CLI** | Correspondência de impressão digital por provedor em Configurações > Segurança |
| 🌐 **i18n (30 idiomas)** | Painel completo + suporte a idiomas de documentos com cobertura RTL |
| 🧹 **Limpar todos os modelos** | Limpeza da lista de modelos com um clique nos detalhes do provedor |
| 👁️ **Sidebar Controls** 🆕 | Hide components and integrations from Appearance Settings |
| 📋 **Modelos de problemas** | Modelos padronizados do GitHub para bugs e recursos |
| 📂 **Diretório de dados personalizado** | Substituição de `DATA_DIR` para local de armazenamento |
@@ -1534,11 +1537,11 @@ Models:
<details>
<summary><b>🆓 Provedores GRATUITOS (backup de emergência)</b></summary>
### iFlow (5 modelos GRATUITOS via OAuth)
### Qoder (5 modelos GRATUITOS via OAuth)
```bash
Dashboard → Connect iFlow
iFlow OAuth login
Dashboard → Connect Qoder
Qoder OAuth login
→ Unlimited usage
Models:
@@ -1736,7 +1739,7 @@ opencode
- Verifique as estatísticas de uso em Painel → Custos
- Mude o modelo primário para GLM/MiniMax
- Use o nível gratuito (Gemini CLI, iFlow) para tarefas não críticas
- Use o nível gratuito (Gemini CLI, Qoder) para tarefas não críticas
**As portas do painel/API estão erradas**
+16 -13
View File
@@ -36,6 +36,7 @@ _Proxy-ul dvs. universal API — un punct final, peste 67 de furnizori, zero tim
| ✅ **Validare traseu** | Toate cele 176 de rute API validate acum cu scheme Zod + treceri `validateBody()` — CI `check:route-validation:t06` |
| 🐛 **OmniModel Tag Leak** | Etichetele interne `<omniModel>` nu mai curg către clienți în răspunsurile în flux SSE (#585) |
| 🔑 **Registered Keys API** | Furnizarea automată a cheilor API prin `POST /api/v1/registered-keys` cu aplicarea cotei pentru fiecare furnizor/cont, idempotity, stocare SHA-256 și raportare opțională a problemelor GitHub |
| 👁️ **Scoped API Key Reveal** 🆕 | Opt-in recovery of API keys via `ALLOW_API_KEY_REVEAL` |
| 🎨 **Icoane furnizor** | Peste 130 de sigle ale furnizorului prin `@lobehub/icons` (SVG) cu PNG → lanț de rezervă generic |
| 🔄 **Sincronizare automată a modelului** | Programator 24 de ore și comutare manuală a interfeței de utilizare pentru a sincroniza listele de modele pentru furnizorii încorporați și personalizați compatibili cu OpenAI |
| 🌐 **OpenCode Zen/Go** | Doi furnizori noi de la @kang-heewon prin PR #530: nivel gratuit + nivel de abonament prin `OpencodeExecutor` |
@@ -199,7 +200,7 @@ Când deschideți o problemă, rulați comanda system-info și atașați fișier
npm run system-info
```
Aceasta generează un `system-info.txt` cu versiunea dvs. Node.js, versiunea OmniRoute, detaliile sistemului de operare, instrumentele CLI instalate (iflow, gemini, claude, codex, antigravity, droid etc.), starea Docker/PM2 și pachetele de sistem - tot ce avem nevoie pentru a reproduce problema rapid. Atașați fișierul direct la problema dvs. GitHub.
Aceasta generează un `system-info.txt` cu versiunea dvs. Node.js, versiunea OmniRoute, detaliile sistemului de operare, instrumentele CLI instalate (qoder, gemini, claude, codex, antigravity, droid etc.), starea Docker/PM2 și pachetele de sistem - tot ce avem nevoie pentru a reproduce problema rapid. Atașați fișierul direct la problema dvs. GitHub.
---
@@ -225,7 +226,7 @@ Aceasta generează un `system-info.txt` cu versiunea dvs. Node.js, versiunea Omn
│ ↓ budget limit
├─→ [Tier 3: CHEAP] GLM ($0.6/1M), MiniMax ($0.2/1M)
│ ↓ budget limit
└─→ [Tier 4: FREE] iFlow, Qwen, Kiro (unlimited)
└─→ [Tier 4: FREE] Qoder, Qwen, Kiro (unlimited)
Result: Never stop coding, minimal cost
```
@@ -292,7 +293,7 @@ Nu toată lumea poate plăti 20200 USD/lună pentru abonamentele AI. Studenț
**Cum o rezolvă OmniRoute:**
- **Free Tier Providers Built-in** — Suport nativ pentru furnizori 100% gratuiti: iFlow (5 modele nelimitate prin OAuth: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2), Qwen (4 modele nelimitate: q-coder-3-fwen: qwen3-coder-next, vision-model), Kiro (Claude + AWS Builder ID gratuit), Gemini CLI (180.000 de jetoane/lună gratuit)
- **Free Tier Providers Built-in** — Suport nativ pentru furnizori 100% gratuiti: Qoder (5 modele nelimitate prin OAuth: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2), Qwen (4 modele nelimitate: q-coder-3-fwen: qwen3-coder-next, vision-model), Kiro (Claude + AWS Builder ID gratuit), Gemini CLI (180.000 de jetoane/lună gratuit)
- **Ollama Cloud** — Modele Ollama găzduite în cloud la `api.ollama.com` cu nivelul gratuit „Utilizare ușoară”; utilizați prefixul `ollamacloud/<model>`
- **Combo-uri numai gratuite** — Lanț `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = 0 USD/lună fără timp de nefuncționare
- **NVIDIA NIM Free Access** — ~40 RPM dev-forever acces gratuit la peste 70 de modele la build.nvidia.com (tranziție de la credite la limitele de rate pur)
@@ -356,7 +357,7 @@ Claude Code, Codex, Gemini CLI, Copilot - toate folosesc OAuth 2.0 cu token-uri
**Cum o rezolvă OmniRoute:**
- **Reîmprospătare automată a simbolurilor** — jetoanele OAuth se reîmprospătează în fundal înainte de expirare
- **OAuth 2.0 (PKCE) încorporat** — Flux automat pentru Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
- **OAuth 2.0 (PKCE) încorporat** — Flux automat pentru Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, Qoder
- **OAuth cu mai multe conturi** — Conturi multiple per furnizor prin extragerea jetonului JWT/ID
- **OAuth LAN/Remediere la distanță** — Detectare IP privată pentru `redirect_uri` + modul URL manual pentru servere la distanță
- **OAuth în spatele Nginx** — Utilizează `window.location.origin` pentru compatibilitatea cu proxy invers
@@ -733,7 +734,7 @@ Outcome: deep fallback depth for deadline-critical workloads
| Pasul | Acțiune | Furnizori deblocați |
| ----- | ---------------------------------------------------- | ------------------------------------------------------------------ |
| 1 | Conectați **Kiro** (AWS Builder ID OAuth) | Claude Sonnet 4.5, Haiku 4.5 — **nelimitat** |
| 2 | Conectați **iFlow** (Google OAuth) | kimi-k2-thinking, qwen3-coder-plus, deepseek-r1... — **nelimitat** |
| 2 | Conectați **Qoder** (Google OAuth) | kimi-k2-thinking, qwen3-coder-plus, deepseek-r1... — **nelimitat** |
| 3 | Conectați **Qwen** (Codul dispozitivului) | qwen3-coder-plus, qwen3-coder-flash... — **nelimitat** |
| 4 | Conectați **Gemini CLI** (Google OAuth) | gemini-3-flash, gemini-2.5-pro — **180K/lună gratuit** |
| 5 | `/dashboard/combos` → șablon **Stiva gratuită ($0)** | Round-robin toți furnizorii gratuiti în mod automat |
@@ -942,7 +943,7 @@ Când este minimizat, OmniRoute se află în bara de sistem cu acțiuni rapide:
| | MiniMax M2.1 | 0,2 USD/1 milion | rulare de 5 ore | Cea mai ieftină opțiune |
| | Kimi K2.5 (API Moonshot) 🆕 | Plată-pe-utilizare | Niciuna | Acces direct API Moonshot |
| | Kimi K2 | 9 USD/lună plat | 10 milioane de jetoane/lună | Cost previzibil |
| **🆓 GRATUIT** | iFlow | **$0** | Nelimitat | 5 modele nelimitat |
| **🆓 GRATUIT** | Qoder | **$0** | Nelimitat | 5 modele nelimitat |
| | Qwen | **$0** | Nelimitat | 4 modele nelimitat |
| | Kiro | **$0** | Nelimitat | Claude Sonnet/Haiku (AWS Builder) |
| | LongCat Flash-Lite 🆕 | **$0** (50 M tok/zi 🔥) | 1 RPS | Cea mai mare cotă gratuită de pe Pământ |
@@ -957,7 +958,7 @@ Când este minimizat, OmniRoute se află în bara de sistem cu acțiuni rapide:
```
# 🆓 Ultimate Free Stack 2026 — 11 Providers, $0 Forever
Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
Qwen (qw/) → qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next UNLIMITED
@@ -987,7 +988,7 @@ Cerebras (cerebras/) → Llama/Qwen world-fastest — 1M tok/day
| `claude-haiku-4.5` | `kr/` | **Nelimitat** | Niciun plafon zilnic raportat |
| `claude-opus-4.6` | `kr/` | **Nelimitat** | Ultimul Opus prin Kiro |
### 🟢 MODELE IFLOW (OAuth gratuit — fără card de credit)
### 🟢 MODELE QODER (OAuth gratuit — fără card de credit)
| Model | Prefix | Limită | Limită de rată |
| ------------------ | ------ | ------------- | ---------------------- |
@@ -1086,7 +1087,7 @@ Disponibil gratuit: `qwen3-235b-a22b-instruct-2507` (Qwen3 235B!), `llama-3.1-70
>
> ```
> Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
> iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
> Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
> Qwen (qw/) → qwen3-coder models UNLIMITED
@@ -1219,6 +1220,7 @@ OmniRoute v2.0 este construit ca o platformă operațională, nu doar un proxy-r
| Caracteristica | Ce face |
| ------------------------------------------------- | ---------------------------------------------------------------------------------- |
| 📝 **Solicitare + Înregistrare proxy** | Cerere/răspuns complet și înregistrare proxy |
| 📉 **Streamed Detailed Logs** 🆕 | Reconstructs SSE payload streams cleanly into the UI |
| 📋 **Tabloul de bord pentru jurnalele unificate** | Vizualizări de solicitare, proxy, audit și consolă într-o singură pagină |
| 🔍 **Solicitare telemetrie** | latența p50/p95/p99 și urmărirea solicitărilor |
| 🏥 **Tabloul de bord pentru sănătate** | Uptime, stări de întrerupere, blocări, statistici cache |
@@ -1239,6 +1241,7 @@ OmniRoute v2.0 este construit ca o platformă operațională, nu doar un proxy-r
| 🔏 **CLI Fingerprint Toggle** | Potrivirea amprentelor pentru fiecare furnizor în Setări > Securitate |
| 🌐 **i18n (30 de limbi)** | Tabloul de bord complet + suport pentru limbajul documentelor cu acoperire RTL |
| 🧹 **Șterge toate modelele** | Ștergerea listei de modele cu un singur clic în detaliile furnizorului |
| 👁️ **Sidebar Controls** 🆕 | Hide components and integrations from Appearance Settings |
| 📋 **Șabloane de probleme** | Șabloane GitHub standardizate pentru erori și caracteristici |
| 📂 **Director de date personalizate** | `DATA_DIR` anulează pentru locația de stocare |
@@ -1534,11 +1537,11 @@ Models:
<details>
<summary><b>🆓 Furnizori GRATUITI (Backup de urgență)</b></summary>
### iFlow (5 modele GRATUITE prin OAuth)
### Qoder (5 modele GRATUITE prin OAuth)
```bash
Dashboard → Connect iFlow
iFlow OAuth login
Dashboard → Connect Qoder
Qoder OAuth login
→ Unlimited usage
Models:
@@ -1736,7 +1739,7 @@ opencode
- Verificați statisticile de utilizare în Tabloul de bord → Costuri
- Comutați modelul principal la GLM/MiniMax
- Utilizați nivelul gratuit (Gemini CLI, iFlow) pentru sarcini necritice
- Utilizați nivelul gratuit (Gemini CLI, Qoder) pentru sarcini necritice
**Tabloul de bord/porturile API sunt greșite**
+16 -13
View File
@@ -36,6 +36,7 @@ _Váš univerzálny proxy server API jeden koncový bod, 67+ poskytovateľov
| ✅ **Overenie trasy** | Všetkých 176 trás API je teraz overených pomocou schém Zod + `validateBody()` preukazy CI `check:route-validation:t06` |
| 🐛 **Únik značky omniModel** | Interné značky `<omniModel>` už neunikajú klientom v odpovediach na streamovanie SSE (#585) |
| 🔑 **Registrované kľúče API** | Kľúče API automatického poskytovania prostredníctvom `POST /api/v1/registered-keys` s presadzovaním kvót pre jednotlivých poskytovateľov/účet, idempotenciou, úložiskom SHA-256 a voliteľným hlásením problémov GitHub |
| 👁️ **Scoped API Key Reveal** 🆕 | Opt-in recovery of API keys via `ALLOW_API_KEY_REVEAL` |
| 🎨 **Ikony poskytovateľa** | Viac ako 130 log poskytovateľov prostredníctvom `@lobehub/icons` (SVG) s PNG → všeobecný záložný reťazec |
| 🔄 **Automatická synchronizácia modelu** | 24-hodinový plánovač a manuálne prepínanie používateľského rozhrania na synchronizáciu zoznamov modelov pre vstavaných a vlastných poskytovateľov kompatibilných s OpenAI |
| 🌐 **OpenCode Zen/Go** | Dvaja noví poskytovatelia od @kang-heewon cez PR #530: bezplatná úroveň + úroveň predplatného cez `OpencodeExecutor` |
@@ -199,7 +200,7 @@ Pri otváraní problému spustite príkaz system-info a pripojte vygenerovaný s
npm run system-info
```
Toto vygeneruje `system-info.txt` s vašou verziou Node.js, verziou OmniRoute, podrobnosťami o OS, nainštalovanými nástrojmi CLI (iflow, gemini, claude, codex, antigravity, droid atď.), stavom Docker/PM2 a systémovými balíkmi všetko, čo potrebujeme na rýchlu reprodukciu vášho problému. Pripojte súbor priamo k vášmu problému na GitHub.
Toto vygeneruje `system-info.txt` s vašou verziou Node.js, verziou OmniRoute, podrobnosťami o OS, nainštalovanými nástrojmi CLI (qoder, gemini, claude, codex, antigravity, droid atď.), stavom Docker/PM2 a systémovými balíkmi všetko, čo potrebujeme na rýchlu reprodukciu vášho problému. Pripojte súbor priamo k vášmu problému na GitHub.
---
@@ -225,7 +226,7 @@ Toto vygeneruje `system-info.txt` s vašou verziou Node.js, verziou OmniRoute, p
│ ↓ budget limit
├─→ [Tier 3: CHEAP] GLM ($0.6/1M), MiniMax ($0.2/1M)
│ ↓ budget limit
└─→ [Tier 4: FREE] iFlow, Qwen, Kiro (unlimited)
└─→ [Tier 4: FREE] Qoder, Qwen, Kiro (unlimited)
Result: Never stop coding, minimal cost
```
@@ -292,7 +293,7 @@ Nie každý môže platiť 20 200 $ mesačne za predplatné AI. Študenti, v
**Ako to rieši OmniRoute:**
- **Zabudovaní poskytovatelia bezplatnej úrovne** — Natívna podpora pre 100 % bezplatných poskytovateľov: iFlow (5 neobmedzených modelov cez OAuth: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2), Qwen (4 neobmedzené modely: qco,3-qwender-lash, qwen3-coder-next, vision-model), Kiro (Claude + AWS Builder ID zadarmo), Gemini CLI (180 000 tokenov mesačne zadarmo)
- **Zabudovaní poskytovatelia bezplatnej úrovne** — Natívna podpora pre 100 % bezplatných poskytovateľov: Qoder (5 neobmedzených modelov cez OAuth: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2), Qwen (4 neobmedzené modely: qco,3-qwender-lash, qwen3-coder-next, vision-model), Kiro (Claude + AWS Builder ID zadarmo), Gemini CLI (180 000 tokenov mesačne zadarmo)
- **Ollama Cloud** modely Ollama hostené v cloude na `api.ollama.com` s bezplatnou úrovňou „Light use“; použite predponu `ollamacloud/<model>`
**len bezplatné kombá** reťazec `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = 0 USD mesačne s nulovými prestojmi
- **Voľný prístup NVIDIA NIM** — ~40 RPM pre vývojárov - navždy bezplatný prístup k viac ako 70 modelom na stránke build.nvidia.com (prechod z kreditov na limity čistej sadzby)
@@ -357,7 +358,7 @@ Claude Code, Codex, Gemini CLI, Copilot všetky používajú OAuth 2.0 s tok
**Ako to rieši OmniRoute:**
- **Automatická obnova tokenov** Tokeny OAuth sa pred vypršaním platnosti obnovujú na pozadí
- **Vstavaný OAuth 2.0 (PKCE)** Automatický tok pre Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
- **Vstavaný OAuth 2.0 (PKCE)** Automatický tok pre Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, Qoder
**Multi-Auth OAuth** Viaceré účty na poskytovateľa prostredníctvom extrakcie tokenov JWT/ID
- **OAuth LAN/Remote Fix** — Detekcia súkromnej adresy IP pre `redirect_uri` + manuálny režim adresy URL pre vzdialené servery
**OAuth Behind Nginx** Používa `window.location.origin` na reverznú kompatibilitu proxy
@@ -739,7 +740,7 @@ Outcome: deep fallback depth for deadline-critical workloads
| Krok | Akcia | Poskytovatelia odblokovaní |
| ---- | --------------------------------------------------------- | -------------------------------------------------------------------- |
| 1 | Pripojiť **Kiro** (AWS Builder ID OAuth) | Claude Sonnet 4.5, Haiku 4.5 — **neobmedzene** |
| 2 | Pripojte **iFlow** (Google OAuth) | kimi-k2-myslenie, qwen3-coder-plus, deepseek-r1... — **neobmedzené** |
| 2 | Pripojte **Qoder** (Google OAuth) | kimi-k2-myslenie, qwen3-coder-plus, deepseek-r1... — **neobmedzené** |
| 3 | Pripojte **Qwen** (kód zariadenia) | qwen3-coder-plus, qwen3-coder-flash... — **neobmedzene** |
| 4 | Pripojte **Gemini CLI** (Google OAuth) | gemini-3-flash, gemini-2.5-pro — **180 000/mesiac zadarmo** |
| 5 | `/dashboard/combos` → Šablóna **Bezplatný balík (0 USD)** | Round-robin všetkých bezplatných poskytovateľov automaticky |
@@ -948,7 +949,7 @@ Keď je minimalizovaný, OmniRoute žije vo vašej systémovej lište s rýchlym
| | MiniMax M2.1 | 0,2 USD/1 milión | 5-hodinové valcovanie | Najlacnejšia možnosť |
| | Kimi K2.5 (Moonshot API) 🆕 | Platba za použitie | Žiadne | Priamy prístup Moonshot API |
| | Kimi K2 | 9 USD/mesiac byt | 10 miliónov tokenov/mesiac | Predvídateľné náklady |
| **🆓 ZDARMA** | iFlow | **$0** | Neobmedzené | 5 modelov neobmedzene |
| **🆓 ZDARMA** | Qoder | **$0** | Neobmedzené | 5 modelov neobmedzene |
| | Qwen | **$0** | Neobmedzené | 4 modely neobmedzene |
| | Kiro | **$0** | Neobmedzené | Claude Sonnet/Haiku (staviteľ AWS) |
| | LongCat Flash-Lite 🆕 | **$0** (50 miliónov tok/deň 🔥) | 1 RPS | Najväčšia bezplatná kvóta na Zemi |
@@ -963,7 +964,7 @@ Keď je minimalizovaný, OmniRoute žije vo vašej systémovej lište s rýchlym
```
# 🆓 Ultimate Free Stack 2026 — 11 Providers, $0 Forever
Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
Qwen (qw/) → qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next UNLIMITED
@@ -993,7 +994,7 @@ Cerebras (cerebras/) → Llama/Qwen world-fastest — 1M tok/day
| `claude-haiku-4.5` | `kr/` | **Neobmedzené** | Žiadny hlásený denný limit |
| `claude-opus-4.6` | `kr/` | **Neobmedzené** | Najnovší Opus cez Kiro |
### 🢢 MODELY IFLOW (bezplatný protokol OAuth žiadna kreditná karta)
### 🢢 MODELY QODER (bezplatný protokol OAuth žiadna kreditná karta)
| Model | Predpona | Limit | Limit sadzby |
| ------------------ | -------- | --------------- | ---------------------- |
@@ -1092,7 +1093,7 @@ Dostupné zadarmo: `qwen3-235b-a22b-instruct-2507` (Qwen3 235B!), `llama-3.1-70b
>
> ```
> Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
> iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
> Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
> Qwen (qw/) → qwen3-coder models UNLIMITED
@@ -1225,6 +1226,7 @@ OmniRoute v2.0 je postavený ako operačná platforma, nie len ako relé proxy.
| Funkcia | Čo to robí |
| ------------------------------------- | ---------------------------------------------------------------------------------------- |
| 📝 **Žiadosť + protokolovanie proxy** | Úplná žiadosť/odpoveď a protokolovanie proxy |
| 📉 **Streamed Detailed Logs** 🆕 | Reconstructs SSE payload streams cleanly into the UI |
| 📋 **Unified Logs Dashboard** | Požiadavka, proxy, audit a zobrazenie konzoly na jednej stránke |
| 🔍 **Požiadať o telemetriu** | p50/p95/p99 latencia a sledovanie požiadaviek |
| 🏥 **Panel zdravia** | Doba prevádzkyschopnosti, stavy prerušovačov, uzamknutia, štatistiky vyrovnávacej pamäte |
@@ -1245,6 +1247,7 @@ OmniRoute v2.0 je postavený ako operačná platforma, nie len ako relé proxy.
| 🔏 **CLI Fingerprint Toggle** | Zhoda odtlačkov prstov jednotlivých poskytovateľov v časti Nastavenia > Zabezpečenie |
| 🌐 **i18n (30 jazykov)** | Úplná podpora dashboardu + dokumentov s podporou RTL |
| 🧹 **Vymazať všetky modely** | Vymazanie zoznamu modelov jedným kliknutím v detailoch poskytovateľa |
| 👁️ **Sidebar Controls** 🆕 | Hide components and integrations from Appearance Settings |
| 📋 **Šablóny vydaní** | Štandardizované šablóny GitHub pre chyby a funkcie |
| 📂 **Custom Data Directory** | `DATA_DIR` prepísanie miesta uloženia |
@@ -1540,11 +1543,11 @@ Models:
<details>
<summary><b>🆓 BEZPLATNÍ poskytovatelia (núdzové zálohovanie)</b></summary>
### iFlow (5 BEZPLATNÝCH modelov cez OAuth)
### Qoder (5 BEZPLATNÝCH modelov cez OAuth)
```bash
Dashboard → Connect iFlow
iFlow OAuth login
Dashboard → Connect Qoder
Qoder OAuth login
→ Unlimited usage
Models:
@@ -1742,7 +1745,7 @@ opencode
- Skontrolujte štatistiky používania v hlavnom paneli → Náklady
- Prepnite primárny model na GLM/MiniMax
- Používajte bezplatnú vrstvu (Gemini CLI, iFlow) pre nekritické úlohy
- Používajte bezplatnú vrstvu (Gemini CLI, Qoder) pre nekritické úlohy
**Porty palubnej dosky/API sú nesprávne**
+16 -13
View File
@@ -199,7 +199,7 @@ När du öppnar ett problem, kör kommandot system-info och bifoga den genererad
npm run system-info
```
Detta genererar en `system-info.txt` med din Node.js-version, OmniRoute-version, OS-detaljer, installerade CLI-verktyg (iflow, gemini, claude, codex, antigravity, droid, etc.), Docker/PM2-status och systempaket allt vi behöver för att snabbt återskapa ditt problem. Bifoga filen direkt till ditt GitHub-problem.
Detta genererar en `system-info.txt` med din Node.js-version, OmniRoute-version, OS-detaljer, installerade CLI-verktyg (qoder, gemini, claude, codex, antigravity, droid, etc.), Docker/PM2-status och systempaket allt vi behöver för att snabbt återskapa ditt problem. Bifoga filen direkt till ditt GitHub-problem.
---
@@ -225,7 +225,7 @@ Detta genererar en `system-info.txt` med din Node.js-version, OmniRoute-version,
│ ↓ budget limit
├─→ [Tier 3: CHEAP] GLM ($0.6/1M), MiniMax ($0.2/1M)
│ ↓ budget limit
└─→ [Tier 4: FREE] iFlow, Qwen, Kiro (unlimited)
└─→ [Tier 4: FREE] Qoder, Qwen, Kiro (unlimited)
Result: Never stop coding, minimal cost
```
@@ -292,7 +292,7 @@ Alla kan inte betala $20200/månad för AI-prenumerationer. Studenter, utveck
**Hur OmniRoute löser det:**
- **Gratis leverantörer inbyggda** — Inbyggt stöd för 100 % gratis leverantörer: iFlow (5 obegränsade modeller via OAuth: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2), Qwen: 4 unlimited-modeller,-r qwen3-coder-flash, qwen3-coder-next, vision-model), Kiro (Claude + AWS Builder ID gratis), Gemini CLI (180K tokens/månad gratis)
- **Gratis leverantörer inbyggda** — Inbyggt stöd för 100 % gratis leverantörer: Qoder (5 obegränsade modeller via OAuth: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2), Qwen: 4 unlimited-modeller,-r qwen3-coder-flash, qwen3-coder-next, vision-model), Kiro (Claude + AWS Builder ID gratis), Gemini CLI (180K tokens/månad gratis)
- **Ollama Cloud** — Molnvärdade Ollama-modeller på `api.ollama.com` med gratis nivå "Lätt användning"; använd `ollamacloud/<model>` prefix
- **Free-Only Combos** — Chain `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = $0/månad utan stilleståndstid
- **NVIDIA NIM fri tillgång** — ~40 RPM dev-för evigt fri tillgång till 70+ modeller på build.nvidia.com (övergång från krediter till rena hastighetsgränser)
@@ -356,7 +356,7 @@ Claude Code, Codex, Gemini CLI, Copilot — alla använder OAuth 2.0 med utgåen
**Hur OmniRoute löser det:**
- **Automatisk uppdatering av token** — OAuth-tokens uppdateras i bakgrunden innan de löper ut
- **OAuth 2.0 (PKCE) Inbyggd** — Automatiskt flöde för Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
- **OAuth 2.0 (PKCE) Inbyggd** — Automatiskt flöde för Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, Qoder
- **Multi-Account OAuth** — Flera konton per leverantör via JWT/ID-tokenextraktion
- **OAuth LAN/Remote Fix** — Privat IP-detektering för `redirect_uri` + manuellt URL-läge för fjärrservrar
- **OAuth Behind Nginx** — Använder `window.location.origin` för omvänd proxykompatibilitet
@@ -733,7 +733,7 @@ Outcome: deep fallback depth for deadline-critical workloads
| Steg | Åtgärd | Leverantörer olåsta |
| ---- | ------------------------------------------------ | ------------------------------------------------------------------- |
| 1 | Anslut **Kiro** (AWS Builder ID OAuth) | Claude Sonnet 4.5, Haiku 4.5 — **obegränsad** |
| 2 | Anslut **iFlow** (Google OAuth) | kimi-k2-tänkande, qwen3-coder-plus, deepseek-r1... — **obegränsat** |
| 2 | Anslut **Qoder** (Google OAuth) | kimi-k2-tänkande, qwen3-coder-plus, deepseek-r1... — **obegränsat** |
| 3 | Anslut **Qwen** (enhetskod) | qwen3-coder-plus, qwen3-coder-flash... — **obegränsat** |
| 4 | Anslut **Gemini CLI** (Google OAuth) | gemini-3-flash, gemini-2.5-pro — **180K/månad gratis** |
| 5 | `/dashboard/combos`**Gratis stack ($0)** mall | Round-robin alla gratis leverantörer automatiskt |
@@ -942,7 +942,7 @@ När den är minimerad, finns OmniRoute i systemfältet med snabba åtgärder:
| | MiniMax M2.1 | $0,2/1M | 5-timmars rullande | Billigaste alternativet |
| | Kimi K2.5 (Moonshot API) 🆕 | Betala per användning | Inga | Direkt åtkomst till Moonshot API |
| | Kimi K2 | 9 USD/mån lägenhet | 10 miljoner tokens/mån | Förutsägbar kostnad |
| **🆓 GRATIS** | iFlow | **$0** | Obegränsad | 5 modeller obegränsat |
| **🆓 GRATIS** | Qoder | **$0** | Obegränsad | 5 modeller obegränsat |
| | Qwen | **$0** | Obegränsad | 4 modeller obegränsat |
| | Kiro | **$0** | Obegränsad | Claude Sonnet/Haiku (AWS Builder) |
| | LongCat Flash-Lite 🆕 | **$0** (50 miljoner tok/dag 🔥) | 1 RPS | Största gratiskvoten på jorden |
@@ -957,7 +957,7 @@ När den är minimerad, finns OmniRoute i systemfältet med snabba åtgärder:
```
# 🆓 Ultimate Free Stack 2026 — 11 Providers, $0 Forever
Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
Qwen (qw/) → qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next UNLIMITED
@@ -987,7 +987,7 @@ Cerebras (cerebras/) → Llama/Qwen world-fastest — 1M tok/day
| `claude-haiku-4.5` | `kr/` | **Obegränsat** | Inget rapporterat dagligt tak |
| `claude-opus-4.6` | `kr/` | **Obegränsat** | Senaste Opus via Kiro |
### IFLOW-MODELLER (gratis OAuth inget kreditkort)
### QODER-MODELLER (gratis OAuth inget kreditkort)
| Modell | Prefix | Begränsa | Prisgräns |
| ------------------ | ------ | -------------- | --------------------- |
@@ -1086,7 +1086,7 @@ Tillgänglig gratis: `qwen3-235b-a22b-instruct-2507` (Qwen3 235B!), `llama-3.1-7
>
> ```
> Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
> iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
> Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
> Qwen (qw/) → qwen3-coder models UNLIMITED
@@ -1212,6 +1212,7 @@ OmniRoute v2.0 är byggd som en operativ plattform, inte bara en reläproxy.
| 🌐 **IP-filtrering** | Kontroll av tillåtelse/blockeringslista för exponerade distributioner |
| 📊 **Redigerbara hastighetsgränser** | Konfigurerbara globala/leverantörsnivågränser med beständighet |
| 🔑 **API Key Management + Scoping** | Säker nyckelutgivning/rotation och modell/leverantörskontroller |
| 👁️ **Scoped API Key Reveal** 🆕 | Opt-in recovery of API keys via `ALLOW_API_KEY_REVEAL` |
| 🛡️ **Skyddad `/models`** | Valfri autentisering och leverantörsdöljning för modellkatalog |
### 📊 Observerbarhet och analys
@@ -1219,6 +1220,7 @@ OmniRoute v2.0 är byggd som en operativ plattform, inte bara en reläproxy.
| Funktion | Vad det gör |
| --------------------------------- | ------------------------------------------------------ |
| 📝 **Begäran + proxyloggning** | Fullständig begäran/svar och proxyloggning |
| 📉 **Streamed Detailed Logs** 🆕 | Reconstructs SSE payload streams cleanly into the UI |
| 📋 **Unified Logs Dashboard** | Begäran, proxy, revision och konsolvyer på en sida |
| 🔍 **Begär telemetri** | p50/p95/p99 latens och spårning av begäran |
| 🏥 **Hälsoinstrumentpanel** | Drifttid, brytartillstånd, lockouter, cachestatistik |
@@ -1239,6 +1241,7 @@ OmniRoute v2.0 är byggd som en operativ plattform, inte bara en reläproxy.
| 🔏 **CLI Fingerprint Toggle** | Fingeravtrycksmatchning per leverantör i Inställningar > Säkerhet |
| 🌐 **i18n (30 språk)** | Fullständig instrumentpanel + stöd för dokumentspråk med RTL-täckning |
| 🧹 **Rensa alla modeller** | Rensa modelllistan med ett klick i leverantörsinformation |
| 👁️ **Sidebar Controls** 🆕 | Hide components and integrations from Appearance Settings |
| 📋 **Utgåvamallar** | Standardiserade GitHub-mallar för buggar och funktioner |
| 📂 **Anpassad datakatalog** | `DATA_DIR` åsidosättning för lagringsplats |
@@ -1534,11 +1537,11 @@ Models:
<details>
<summary><b>🆓 GRATIS leverantörer (nödbackup)</b></summary>
### iFlow (5 GRATIS modeller via OAuth)
### Qoder (5 GRATIS modeller via OAuth)
```bash
Dashboard → Connect iFlow
iFlow OAuth login
Dashboard → Connect Qoder
Qoder OAuth login
→ Unlimited usage
Models:
@@ -1736,7 +1739,7 @@ opencode
- Kontrollera användningsstatistik i Dashboard → Kostnader
- Byt primär modell till GLM/MiniMax
- Använd gratis nivå (Gemini CLI, iFlow) för icke-kritiska uppgifter
- Använd gratis nivå (Gemini CLI, Qoder) för icke-kritiska uppgifter
**Dashboard/API-portar är fel**
+24 -21
View File
@@ -36,6 +36,7 @@ _พร็อกซี API สากลของคุณ — จุดสิ้
| ✅ **การตรวจสอบเส้นทาง** | ขณะนี้เส้นทาง API ทั้ง 176 เส้นทางได้รับการตรวจสอบความถูกต้องด้วย Zod schema + `validateBody()` — CI `check:route-validation:t06` pass |
| 🐛 **แท็ก omniModel รั่ว** | แท็ก `<omniModel>` ภายในจะไม่รั่วไหลไปยังไคลเอนต์อีกต่อไปในการตอบกลับการสตรีม SSE (#585) |
| 🔑 **API คีย์ที่ลงทะเบียน** | คีย์ API การจัดสรรอัตโนมัติผ่าน `POST /api/v1/registered-keys` พร้อมการบังคับใช้โควต้าต่อผู้ให้บริการ/บัญชี ความสามารถในการระบุตำแหน่ง พื้นที่เก็บข้อมูล SHA-256 และการรายงานปัญหา GitHub ที่เป็นตัวเลือก |
| 👁️ **Scoped API Key Reveal** 🆕 | Opt-in recovery of API keys via `ALLOW_API_KEY_REVEAL` |
| 🎨 **ไอคอนผู้ให้บริการ** | โลโก้ผู้ให้บริการมากกว่า 130+ รายการผ่าน `@lobehub/icons` (SVG) พร้อม PNG → ห่วงโซ่ทางเลือกทั่วไป |
| 🔄 **โมเดลซิงค์อัตโนมัติ** | ตัวกำหนดเวลา 24 ชั่วโมงและสลับ UI แบบแมนนวลเพื่อซิงค์รายการโมเดลสำหรับผู้ให้บริการที่เข้ากันได้กับ OpenAI ในตัวและแบบกำหนดเอง |
| 🌐 **OpenCode Zen/Go** | ผู้ให้บริการใหม่สองรายจาก @kang-heewon ผ่าน PR #530: ระดับฟรี + ระดับการสมัครสมาชิกผ่าน `OpencodeExecutor` |
@@ -199,7 +200,7 @@ _เชื่อมต่อเครื่องมือ IDE หรือ CLI
npm run system-info
```
สิ่งนี้จะสร้าง `system-info.txt` ด้วยเวอร์ชัน Node.js ของคุณ เวอร์ชัน OmniRoute รายละเอียดระบบปฏิบัติการ เครื่องมือ CLI ที่ติดตั้ง (iflow, gemini, claude, codex, antigravity, droid ฯลฯ) สถานะ Docker/PM2 และแพ็คเกจระบบ ทุกสิ่งที่เราต้องการในการทำซ้ำปัญหาของคุณอย่างรวดเร็ว แนบไฟล์โดยตรงกับปัญหา GitHub ของคุณ
สิ่งนี้จะสร้าง `system-info.txt` ด้วยเวอร์ชัน Node.js ของคุณ เวอร์ชัน OmniRoute รายละเอียดระบบปฏิบัติการ เครื่องมือ CLI ที่ติดตั้ง (qoder, gemini, claude, codex, antigravity, droid ฯลฯ) สถานะ Docker/PM2 และแพ็คเกจระบบ ทุกสิ่งที่เราต้องการในการทำซ้ำปัญหาของคุณอย่างรวดเร็ว แนบไฟล์โดยตรงกับปัญหา GitHub ของคุณ
---
@@ -225,7 +226,7 @@ npm run system-info
│ ↓ budget limit
├─→ [Tier 3: CHEAP] GLM ($0.6/1M), MiniMax ($0.2/1M)
│ ↓ budget limit
└─→ [Tier 4: FREE] iFlow, Qwen, Kiro (unlimited)
└─→ [Tier 4: FREE] Qoder, Qwen, Kiro (unlimited)
Result: Never stop coding, minimal cost
```
@@ -292,7 +293,7 @@ OpenAI ใช้รูปแบบหนึ่ง Claude (Anthropic) ใช้
**OmniRoute แก้ปัญหาอย่างไร:**
- **Free Tier Providers ในตัว** — รองรับเนทิฟสำหรับผู้ให้บริการฟรี 100%: iFlow (5 โมเดลไม่จำกัดผ่าน OAuth: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2), Qwen (4 โมเดลไม่จำกัด: qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next, vision-model) Kiro (Claude + AWS Builder ID ฟรี), Gemini CLI (ฟรี 180,000 โทเค็น/เดือน)
- **Free Tier Providers ในตัว** — รองรับเนทิฟสำหรับผู้ให้บริการฟรี 100%: Qoder (5 โมเดลไม่จำกัดผ่าน OAuth: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2), Qwen (4 โมเดลไม่จำกัด: qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next, vision-model) Kiro (Claude + AWS Builder ID ฟรี), Gemini CLI (ฟรี 180,000 โทเค็น/เดือน)
- **Ollama Cloud** — โมเดล Ollama ที่โฮสต์บนคลาวด์ที่ `api.ollama.com` พร้อมระดับ "การใช้งานระดับเบา" ฟรี ใช้คำนำหน้า `ollamacloud/<model>`
- **คอมโบฟรีเท่านั้น** — Chain `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = $0/เดือน โดยไม่มีการหยุดทำงาน
- **NVIDIA NIM Free Access** — ~40 RPM dev-เข้าถึงฟรีตลอดกาลสำหรับโมเดลกว่า 70 รุ่นที่ build.nvidia.com (เปลี่ยนจากเครดิตเป็นการจำกัดอัตราที่แท้จริง)
@@ -356,7 +357,7 @@ Claude Code, Codex, Gemini CLI, Copilot — ทั้งหมดใช้ OAuth
**OmniRoute แก้ปัญหาอย่างไร:**
- **รีเฟรชโทเค็นอัตโนมัติ** — โทเค็น OAuth รีเฟรชในพื้นหลังก่อนหมดอายุ
- **OAuth 2.0 (PKCE) ในตัว** — โฟลว์อัตโนมัติสำหรับ Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
- **OAuth 2.0 (PKCE) ในตัว** — โฟลว์อัตโนมัติสำหรับ Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, Qoder
- **OAuth หลายบัญชี** — หลายบัญชีต่อผู้ให้บริการผ่านการดึงโทเค็น JWT/ID
- **OAuth LAN/Remote Fix** — การตรวจจับ IP ส่วนตัวสำหรับ `redirect_uri` + โหมด URL แบบกำหนดเองสำหรับเซิร์ฟเวอร์ระยะไกล
- **OAuth หลัง Nginx** — ใช้ `window.location.origin` สำหรับความเข้ากันได้ของพร็อกซีย้อนกลับ
@@ -733,7 +734,7 @@ Outcome: deep fallback depth for deadline-critical workloads
| ขั้นตอน | การกระทำ | ผู้ให้บริการปลดล็อคแล้ว |
| ------- | ----------------------------------------------- | ------------------------------------------------------------ |
| 1 | เชื่อมต่อ **Kiro** (AWS Builder ID OAuth) | Claude Sonnet 4.5, Haiku 4.5 — **ไม่จำกัด** |
| 2 | เชื่อมต่อ **iFlow** (Google OAuth) | kimi-k2-คิด, qwen3-coder-plus, deepseek-r1... — **ไม่จำกัด** |
| 2 | เชื่อมต่อ **Qoder** (Google OAuth) | kimi-k2-คิด, qwen3-coder-plus, deepseek-r1... — **ไม่จำกัด** |
| 3 | เชื่อมต่อ **Qwen** (รหัสอุปกรณ์) | qwen3-coder-plus, qwen3-coder-flash... — **ไม่จำกัด** |
| 4 | เชื่อมต่อ **Gemini CLI** (Google OAuth) | gemini-3-flash, gemini-2.5-pro — **ฟรี 180K/เดือน** |
| 5 | `/dashboard/combos`**สแต็คฟรี ($0)** เทมเพลต | Round-robin ผู้ให้บริการฟรีทั้งหมดโดยอัตโนมัติ |
@@ -957,7 +958,7 @@ npm run electron:build:linux # Linux (.AppImage)
```
# 🆓 Ultimate Free Stack 2026 — 11 Providers, $0 Forever
Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
Qwen (qw/) → qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next UNLIMITED
@@ -987,7 +988,7 @@ Cerebras (cerebras/) → Llama/Qwen world-fastest — 1M tok/day
| `claude-haiku-4.5` | `kr/` | **ไม่จำกัด** | ไม่มีรายงานสูงสุดรายวัน |
| `claude-opus-4.6` | `kr/` | **ไม่จำกัด** | บทประพันธ์ล่าสุดผ่าน Kiro |
### 🟢 IFLOW MODELS (OAuth ฟรี — ไม่มีบัตรเครดิต)
### 🟢 QODER MODELS (OAuth ฟรี — ไม่มีบัตรเครดิต)
| รุ่น | คำนำหน้า | ขีดจำกัด | ขีดจำกัดอัตรา |
| ------------------ | -------- | ------------ | --------------- |
@@ -1086,7 +1087,7 @@ Cerebras (cerebras/) → Llama/Qwen world-fastest — 1M tok/day
>
> ```
> Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
> iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
> Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
> Qwen (qw/) → qwen3-coder models UNLIMITED
@@ -1216,15 +1217,16 @@ OmniRoute v2.0 ถูกสร้างขึ้นเพื่อเป็น
### 📊 ความสามารถในการสังเกตและการวิเคราะห์
| คุณสมบัติ | มันทำอะไร |
| ------------------------------ | -------------------------------------------------------- |
| 📝 **คำขอ + การบันทึกพร็อกซี** | คำขอ/ตอบกลับแบบเต็มและการบันทึกพร็อกซี |
| 📋 **แดชบอร์ดบันทึกแบบรวม** | มุมมองคำขอ พร็อกซี การตรวจสอบ และคอนโซลในหน้าเดียว |
| 🔍 **ขอโทรมาตร** | เวลาแฝง p50/p95/p99 และคำขอการติดตาม |
| 🏥 **แดชบอร์ดสุขภาพ** | เวลาทำงาน สถานะของเบรกเกอร์ การล็อก สถิติแคช |
| 💰 **ติดตามต้นทุน** | การควบคุมงบประมาณและการเปิดเผยราคาต่อรุ่น |
| 📈 **การแสดงภาพการวิเคราะห์** | ข้อมูลเชิงลึกการใช้งานโมเดล/ผู้ให้บริการและมุมมองแนวโน้ม |
| 🧪 **กรอบการประเมินผล** | การทดสอบชุดทองพร้อมกลยุทธ์การจับคู่ที่กำหนดค่าได้ |
| คุณสมบัติ | มันทำอะไร |
| -------------------------------- | -------------------------------------------------------- |
| 📝 **คำขอ + การบันทึกพร็อกซี** | คำขอ/ตอบกลับแบบเต็มและการบันทึกพร็อกซี |
| 📉 **Streamed Detailed Logs** 🆕 | Reconstructs SSE payload streams cleanly into the UI |
| 📋 **แดชบอร์ดบันทึกแบบรวม** | มุมมองคำขอ พร็อกซี การตรวจสอบ และคอนโซลในหน้าเดียว |
| 🔍 **ขอโทรมาตร** | เวลาแฝง p50/p95/p99 และคำขอการติดตาม |
| 🏥 **แดชบอร์ดสุขภาพ** | เวลาทำงาน สถานะของเบรกเกอร์ การล็อก สถิติแคช |
| 💰 **ติดตามต้นทุน** | การควบคุมงบประมาณและการเปิดเผยราคาต่อรุ่น |
| 📈 **การแสดงภาพการวิเคราะห์** | ข้อมูลเชิงลึกการใช้งานโมเดล/ผู้ให้บริการและมุมมองแนวโน้ม |
| 🧪 **กรอบการประเมินผล** | การทดสอบชุดทองพร้อมกลยุทธ์การจับคู่ที่กำหนดค่าได้ |
### ☁️ การปรับใช้และแพลตฟอร์ม
@@ -1239,6 +1241,7 @@ OmniRoute v2.0 ถูกสร้างขึ้นเพื่อเป็น
| 🔏 **สลับลายนิ้วมือ CLI** | การจับคู่ลายนิ้วมือของแต่ละผู้ให้บริการในการตั้งค่า > ความปลอดภัย |
| 🌐 **i18n (30 ภาษา)** | รองรับภาษาแดชบอร์ด + เอกสารแบบเต็มพร้อมการครอบคลุม RTL |
| 🧹 **ล้างทุกรุ่น** | การล้างรายการโมเดลในคลิกเดียวในรายละเอียดผู้ให้บริการ |
| 👁️ **Sidebar Controls** 🆕 | Hide components and integrations from Appearance Settings |
| 📋 **เทมเพลตปัญหา** | เทมเพลต GitHub มาตรฐานสำหรับข้อบกพร่องและฟีเจอร์ |
| 📂 **ไดเรกทอรีข้อมูลที่กำหนดเอง** | `DATA_DIR` แทนที่ตำแหน่งที่เก็บข้อมูล |
@@ -1534,11 +1537,11 @@ Models:
<details>
<summary><b>🆓 ผู้ให้บริการฟรี (การสำรองข้อมูลฉุกเฉิน)</b>OMNI_TOKEN_688__
### iFlow (5 รุ่นฟรีผ่าน OAuth)
### Qoder (5 รุ่นฟรีผ่าน OAuth)
```bash
Dashboard → Connect iFlow
iFlow OAuth login
Dashboard → Connect Qoder
Qoder OAuth login
→ Unlimited usage
Models:
@@ -1736,7 +1739,7 @@ opencode
- ตรวจสอบสถิติการใช้งานในแดชบอร์ด → ต้นทุน
- เปลี่ยนโมเดลหลักเป็น GLM/MiniMax
- ใช้ระดับฟรี (Gemini CLI, iFlow) สำหรับงานที่ไม่สำคัญ
- ใช้ระดับฟรี (Gemini CLI, Qoder) สำหรับงานที่ไม่สำคัญ
**พอร์ตแดชบอร์ด/API ไม่ถูกต้อง**
+16 -13
View File
@@ -199,7 +199,7 @@ _Підключіть будь-який інструмент IDE або CLI на
npm run system-info
```
Це генерує `system-info.txt` з вашою версією Node.js, версією OmniRoute, деталями ОС, встановленими інструментами CLI (iflow, gemini, claude, codex, antigravity, droid тощо), статусом Docker/PM2 і системними пакетами — усім, що нам потрібно для швидкого відтворення вашої проблеми. Прикріпіть файл безпосередньо до свого випуску GitHub.
Це генерує `system-info.txt` з вашою версією Node.js, версією OmniRoute, деталями ОС, встановленими інструментами CLI (qoder, gemini, claude, codex, antigravity, droid тощо), статусом Docker/PM2 і системними пакетами — усім, що нам потрібно для швидкого відтворення вашої проблеми. Прикріпіть файл безпосередньо до свого випуску GitHub.
---
@@ -225,7 +225,7 @@ npm run system-info
│ ↓ budget limit
├─→ [Tier 3: CHEAP] GLM ($0.6/1M), MiniMax ($0.2/1M)
│ ↓ budget limit
└─→ [Tier 4: FREE] iFlow, Qwen, Kiro (unlimited)
└─→ [Tier 4: FREE] Qoder, Qwen, Kiro (unlimited)
Result: Never stop coding, minimal cost
```
@@ -292,7 +292,7 @@ OpenAI використовує один формат, Claude (Anthropic) вик
**Як це вирішує OmniRoute:**
- **Вбудовані безкоштовні постачальники рівня** — Вбудована підтримка 100% безкоштовних постачальників: iFlow (5 необмежених моделей через OAuth: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2), Qwen (4 необмежені моделі: qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next, vision-model), Kiro (Claude + AWS Builder ID безкоштовно), Gemini CLI (180K токенів/місяць безкоштовно)
- **Вбудовані безкоштовні постачальники рівня** — Вбудована підтримка 100% безкоштовних постачальників: Qoder (5 необмежених моделей через OAuth: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2), Qwen (4 необмежені моделі: qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next, vision-model), Kiro (Claude + AWS Builder ID безкоштовно), Gemini CLI (180K токенів/місяць безкоштовно)
- **Ollama Cloud** — хмарні моделі Ollama на `api.ollama.com` з безкоштовним рівнем «Light usage»; використовуйте префікс `ollamacloud/<model>`
- **Безкоштовні комбінації** — ланцюжок `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = 0 доларів США на місяць без простоїв
- **Безкоштовний доступ до NVIDIA NIM** — ~40 об./хв. для розробників назавжди безкоштовний доступ до 70+ моделей на build.nvidia.com (перехід від кредитів до чистих обмежень швидкості)
@@ -356,7 +356,7 @@ Claude Code, Codex, Gemini CLI, Copilot — усі використовують
**Як це вирішує OmniRoute:**
- **Auto Token Refresh** — маркери OAuth оновлюються у фоновому режимі до завершення терміну дії
- **Вбудований OAuth 2.0 (PKCE)** — автоматичний потік для Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
- **Вбудований OAuth 2.0 (PKCE)** — автоматичний потік для Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, Qoder
- **Multi-Account OAuth** — кілька облікових записів на постачальника за допомогою вилучення токенів JWT/ID
- **OAuth LAN/Remote Fix** — виявлення приватної IP-адреси для `redirect_uri` + ручний режим URL-адреси для віддалених серверів
- **OAuth за Nginx** — використовує `window.location.origin` для зворотної сумісності проксі
@@ -736,7 +736,7 @@ Outcome: deep fallback depth for deadline-critical workloads
| Крок | Дія | Постачальники розблоковано |
| ---- | ------------------------------------------------------- | ------------------------------------------------------------------- |
| 1 | Підключіть **Kiro** (AWS Builder ID OAuth) | Клод Сонет 4.5, Хайку 4.5 — **необмежений** |
| 2 | Підключіть **iFlow** (Google OAuth) | kimi-k2-thinking, qwen3-coder-plus, deepseek-r1... — **необмежено** |
| 2 | Підключіть **Qoder** (Google OAuth) | kimi-k2-thinking, qwen3-coder-plus, deepseek-r1... — **необмежено** |
| 3 | Підключіть **Qwen** (код пристрою) | qwen3-coder-plus, qwen3-coder-flash... — **необмежено** |
| 4 | Підключіть **Gemini CLI** (Google OAuth) | gemini-3-flash, gemini-2.5-pro — **180K/міс безкоштовно** |
| 5 | `/dashboard/combos` → Шаблон **Безкоштовний стек ($0)** | Циклічний цикл усіх безкоштовних постачальників автоматично |
@@ -945,7 +945,7 @@ npm run electron:build:linux # Linux (.AppImage)
| | MiniMax M2.1 | $0,2/1 млн | 5-годинний роликовий | Найдешевший варіант |
| | Kimi K2.5 (Moonshot API) 🆕 | Оплата за використання | Жодного | Прямий доступ до Moonshot API |
| | Кімі К2 | 9 $/міс квартира | 10 млн токенів/міс | Передбачувана вартість |
| **🆓 БЕЗКОШТОВНО** | iFlow | **$0** | Необмежений | 5 моделей без обмежень |
| **🆓 БЕЗКОШТОВНО** | Qoder | **$0** | Необмежений | 5 моделей без обмежень |
| | Квен | **$0** | Необмежений | 4 моделі без обмежень |
| | Кіро | **$0** | Необмежений | Клод Сонет/Хайку (AWS Builder) |
| | LongCat Flash-Lite 🆕 | **$0** (50 млн ток/день 🔥) | 1 RPS | Найбільша безкоштовна квота на Землі |
@@ -960,7 +960,7 @@ npm run electron:build:linux # Linux (.AppImage)
```
# 🆓 Ultimate Free Stack 2026 — 11 Providers, $0 Forever
Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
Qwen (qw/) → qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next UNLIMITED
@@ -990,7 +990,7 @@ Cerebras (cerebras/) → Llama/Qwen world-fastest — 1M tok/day
| `claude-haiku-4.5` | `kr/` | **Необмежений** | Немає повідомлень про щоденне обмеження |
| `claude-opus-4.6` | `kr/` | **Необмежений** | Останній Opus через Kiro |
### 🟢 МОДЕЛІ IFLOW (безкоштовний OAuth — без кредитної картки)
### 🟢 МОДЕЛІ QODER (безкоштовний OAuth — без кредитної картки)
| Модель | Префікс | Ліміт | Обмеження швидкості |
| ------------------ | ------- | --------------- | ------------------------------- |
@@ -1089,7 +1089,7 @@ Cerebras (cerebras/) → Llama/Qwen world-fastest — 1M tok/day
>
> ```
> Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
> iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
> Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
> Qwen (qw/) → qwen3-coder models UNLIMITED
@@ -1215,6 +1215,7 @@ OmniRoute v2.0 створено як операційну платформу, а
| 🌐 **IP-фільтрація** | Керування білим/чорним списком для відкритих розгортань |
| 📊 **Редаговані ліміти ставок** | Конфігуровані глобальні обмеження/ліміти на рівні постачальника з постійністю |
| 🔑 **API Key Management + Scoping** | Безпечна видача/ротація ключів і засоби керування моделлю/постачальником |
| 👁️ **Scoped API Key Reveal** 🆕 | Opt-in recovery of API keys via `ALLOW_API_KEY_REVEAL` |
| 🛡️ **Захищено `/models`** | Додаткова автентифікація та приховування постачальника для каталогу моделей |
### 📊 Спостережливість і аналітика
@@ -1222,6 +1223,7 @@ OmniRoute v2.0 створено як операційну платформу, а
| Особливість | Що він робить |
| ------------------------------------------ | ------------------------------------------------------------------- |
| 📝 **Запит + реєстрація проксі** | Повний журнал запитів/відповідей і проксі |
| 📉 **Streamed Detailed Logs** 🆕 | Reconstructs SSE payload streams cleanly into the UI |
| 📋 **Інформаційна панель єдиних журналів** | Перегляди запитів, проксі, аудиту та консолі на одній сторінці |
| 🔍 **Надіслати запит на телеметрію** | p50/p95/p99 затримка та відстеження запитів |
| 🏥 **Інформаційна панель здоров’я** | Час роботи, стани поломки, блокування, статистика кешу |
@@ -1242,6 +1244,7 @@ OmniRoute v2.0 створено як операційну платформу, а
| 🔏 **Перемикач відбитків пальців CLI** | Зіставлення відбитків пальців кожного постачальника в Налаштуваннях > Безпека |
| 🌐 **i18n (30 мов)** | Повна інформаційна панель + підтримка мови документів із покриттям RTL |
| 🧹 **Очистити всі моделі** | Очищення списку моделей одним натисканням у деталях провайдера |
| 👁️ **Sidebar Controls** 🆕 | Hide components and integrations from Appearance Settings |
| 📋 **Шаблони проблем** | Стандартизовані шаблони GitHub для помилок і функцій |
| 📂 **Каталог користувацьких даних** | `DATA_DIR` замінити місце зберігання |
@@ -1537,11 +1540,11 @@ Models:
<details>
<summary><b>🆓 БЕЗКОШТОВНІ постачальники (аварійне резервне копіювання)</b></summary>
### iFlow (5 БЕЗКОШТОВНИХ моделей через OAuth)
### Qoder (5 БЕЗКОШТОВНИХ моделей через OAuth)
```bash
Dashboard → Connect iFlow
iFlow OAuth login
Dashboard → Connect Qoder
Qoder OAuth login
→ Unlimited usage
Models:
@@ -1741,7 +1744,7 @@ opencode
- Перевірте статистику використання в Інформаційній панелі → Витрати
- Переключіть основну модель на GLM/MiniMax
- Використовуйте безкоштовний рівень (Gemini CLI, iFlow) для некритичних завдань
- Використовуйте безкоштовний рівень (Gemini CLI, Qoder) для некритичних завдань
**Порти приладової панелі/API неправильні**
+16 -13
View File
@@ -36,6 +36,7 @@ _Proxy API phổ quát của bạn — một điểm cuối, hơn 67 nhà cung c
| ✅ **Xác thực lộ trình** | Tất cả 176 tuyến API hiện đã được xác thực bằng lược đồ Zod + `validateBody()` — CI `check:route-validation:t06` vượt qua |
| 🐛 **Rò rỉ thẻ omniModel** | Thẻ `<omniModel>` nội bộ không còn bị rò rỉ tới máy khách trong phản hồi phát trực tuyến SSE (#585) |
| 🔑 **API khóa đã đăng ký** | Tự động cung cấp khóa API thông qua `POST /api/v1/registered-keys` với việc thực thi hạn ngạch cho mỗi nhà cung cấp/tài khoản, tính tạm thời, bộ nhớ SHA-256 và báo cáo sự cố GitHub tùy chọn |
| 👁️ **Scoped API Key Reveal** 🆕 | Opt-in recovery of API keys via `ALLOW_API_KEY_REVEAL` |
| 🎨 **Biểu tượng nhà cung cấp** | Hơn 130 logo nhà cung cấp thông qua `@lobehub/icons` (SVG) với PNG → chuỗi dự phòng chung |
| 🔄 **Tự động đồng bộ hóa mô hình** | Bộ lập lịch 24 giờ và chuyển đổi giao diện người dùng thủ công để đồng bộ hóa danh sách mô hình cho các nhà cung cấp tương thích OpenAI tích hợp và tùy chỉnh |
| 🌐 **OpenCode Zen/Go** | Hai nhà cung cấp mới từ @kang-heewon qua PR #530: bậc miễn phí + bậc đăng ký qua `OpencodeExecutor` |
@@ -199,7 +200,7 @@ Khi mở một vấn đề, vui lòng chạy lệnh system-info và đính kèm
npm run system-info
```
Điều này tạo ra `system-info.txt` với phiên bản Node.js, phiên bản OmniRoute, chi tiết hệ điều hành, các công cụ CLI đã cài đặt (iflow, gemini, claude, codex, antiGravity, droid, v.v.), trạng thái Docker/PM2 và các gói hệ thống — mọi thứ chúng tôi cần để tái tạo vấn đề của bạn một cách nhanh chóng. Đính kèm tệp trực tiếp vào vấn đề GitHub của bạn.
Điều này tạo ra `system-info.txt` với phiên bản Node.js, phiên bản OmniRoute, chi tiết hệ điều hành, các công cụ CLI đã cài đặt (qoder, gemini, claude, codex, antiGravity, droid, v.v.), trạng thái Docker/PM2 và các gói hệ thống — mọi thứ chúng tôi cần để tái tạo vấn đề của bạn một cách nhanh chóng. Đính kèm tệp trực tiếp vào vấn đề GitHub của bạn.
---
@@ -225,7 +226,7 @@ npm run system-info
│ ↓ budget limit
├─→ [Tier 3: CHEAP] GLM ($0.6/1M), MiniMax ($0.2/1M)
│ ↓ budget limit
└─→ [Tier 4: FREE] iFlow, Qwen, Kiro (unlimited)
└─→ [Tier 4: FREE] Qoder, Qwen, Kiro (unlimited)
Result: Never stop coding, minimal cost
```
@@ -292,7 +293,7 @@ Không phải ai cũng có thể trả 20200 USD/tháng để đăng ký AI.
**Cách OmniRoute giải quyết vấn đề này:**
- **Tích hợp sẵn nhà cung cấp cấp miễn phí** — Hỗ trợ riêng cho nhà cung cấp miễn phí 100%: iFlow (5 mô hình không giới hạn qua OAuth: kimi-k2-thinking, qwen3-code-plus, deepseek-r1, minimax-m2, kimi-k2), Qwen (4 mô hình không giới hạn: qwen3-code-plus, qwen3-code-flash, qwen3-code-next, Vision-model), Kiro (Claude + AWS Builder ID miễn phí), Gemini CLI (miễn phí 180K token/tháng)
- **Tích hợp sẵn nhà cung cấp cấp miễn phí** — Hỗ trợ riêng cho nhà cung cấp miễn phí 100%: Qoder (5 mô hình không giới hạn qua OAuth: kimi-k2-thinking, qwen3-code-plus, deepseek-r1, minimax-m2, kimi-k2), Qwen (4 mô hình không giới hạn: qwen3-code-plus, qwen3-code-flash, qwen3-code-next, Vision-model), Kiro (Claude + AWS Builder ID miễn phí), Gemini CLI (miễn phí 180K token/tháng)
- **Ollama Cloud** — Các mô hình Ollama được lưu trữ trên đám mây tại `api.ollama.com` với bậc "Sử dụng nhẹ" miễn phí; sử dụng tiền tố `ollamacloud/<model>`
- **Combo chỉ miễn phí** — Chuỗi `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = $0/tháng mà không có thời gian ngừng hoạt động
- **Truy cập miễn phí NVIDIA NIM** — ~40 RPM dành cho nhà phát triển - truy cập miễn phí vĩnh viễn vào hơn 70 mẫu tại build.nvidia.com (chuyển từ tín dụng sang giới hạn tỷ lệ thuần túy)
@@ -356,7 +357,7 @@ Claude Code, Codex, Gemini CLI, Copilot — tất cả đều sử dụng OAuth
**Cách OmniRoute giải quyết vấn đề này:**
- **Tự động làm mới mã thông báo** — Làm mới mã thông báo OAuth ở chế độ nền trước khi hết hạn
- **Tích hợp OAuth 2.0 (PKCE)** — Luồng tự động cho Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
- **Tích hợp OAuth 2.0 (PKCE)** — Luồng tự động cho Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, Qoder
- **OAuth nhiều tài khoản** — Nhiều tài khoản cho mỗi nhà cung cấp thông qua trích xuất mã thông báo JWT/ID
- **OAuth LAN/Remote Fix** — Phát hiện IP riêng cho `redirect_uri` + chế độ URL thủ công cho máy chủ từ xa
- **OAuth đằng sau Nginx** — Sử dụng `window.location.origin` để tương thích với proxy ngược
@@ -733,7 +734,7 @@ Outcome: deep fallback depth for deadline-critical workloads
| Bước | Hành động | Nhà cung cấp đã được mở khóa |
| ---- | ---------------------------------------------------- | ---------------------------------------------------------------------- |
| 1 | Kết nối **Kiro** (ID AWS Builder OAuth) | Claude Sonnet 4.5, Haiku 4.5 — **không giới hạn** |
| 2 | Kết nối **iFlow** (Google OAuth) | kimi-k2-thinking, qwen3-code-plus, deepseek-r1... — **không giới hạn** |
| 2 | Kết nối **Qoder** (Google OAuth) | kimi-k2-thinking, qwen3-code-plus, deepseek-r1... — **không giới hạn** |
| 3 | Kết nối **Qwen** (Mã thiết bị) | qwen3-code-plus, qwen3-code-flash... — **không giới hạn** |
| 4 | Kết nối **Gemini CLI** (Google OAuth) | gemini-3-flash, gemini-2.5-pro — **180K/tháng miễn phí** |
| 5 | `/dashboard/combos`**Mẫu ngăn xếp miễn phí ($0)** | Tự động quay vòng tất cả các nhà cung cấp miễn phí |
@@ -942,7 +943,7 @@ Khi được thu nhỏ, OmniRoute sẽ tồn tại trong khay hệ thống của
| | MiniMax M2.1 | 0,2 USD/1 triệu USD | lăn 5 giờ | Lựa chọn rẻ nhất |
| | Kimi K2.5 (API Moonshot) 🆕 | Trả tiền cho mỗi lần sử dụng | Không có | Truy cập API Moonshot trực tiếp |
| | Kimi K2 | $9/tháng căn hộ | 10 triệu token/tháng | Chi phí dự đoán |
| **🆓 MIỄN PHÍ** | iFlow | **$0** | Không giới hạn | 5 mẫu không giới hạn |
| **🆓 MIỄN PHÍ** | Qoder | **$0** | Không giới hạn | 5 mẫu không giới hạn |
| | Qwen | **$0** | Không giới hạn | 4 mẫu không giới hạn |
| | Kiro | **$0** | Không giới hạn | Claude Sonnet/Haiku (Người xây dựng AWS) |
| | LongCat Flash-Lite 🆕 | **$0** (50 triệu tok/ngày 🔥) | 1 RPS | Hạn ngạch miễn phí lớn nhất trên Trái đất |
@@ -957,7 +958,7 @@ Khi được thu nhỏ, OmniRoute sẽ tồn tại trong khay hệ thống của
```
# 🆓 Ultimate Free Stack 2026 — 11 Providers, $0 Forever
Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
Qwen (qw/) → qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next UNLIMITED
@@ -987,7 +988,7 @@ Cerebras (cerebras/) → Llama/Qwen world-fastest — 1M tok/day
| `claude-haiku-4.5` | `kr/` | **Không giới hạn** | Không có giới hạn hàng ngày được báo cáo |
| `claude-opus-4.6` | `kr/` | **Không giới hạn** | Opus mới nhất qua Kiro |
### 🟢 MÔ HÌNH IFLOW (OAuth miễn phí - Không có thẻ tín dụng)
### 🟢 MÔ HÌNH QODER (OAuth miễn phí - Không có thẻ tín dụng)
| Người mẫu | Tiền tố | Giới hạn | Giới hạn tỷ lệ |
| ------------------ | ------- | ------------------ | ------------------------------ |
@@ -1086,7 +1087,7 @@ Có sẵn miễn phí: `qwen3-235b-a22b-instruct-2507` (Qwen3 235B!), `llama-3.1
>
> ```
> Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
> iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
> Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
> Qwen (qw/) → qwen3-coder models UNLIMITED
@@ -1219,6 +1220,7 @@ OmniRoute v2.0 được xây dựng như một nền tảng hoạt động, khô
| Tính năng | Nó làm gì |
| --------------------------------------- | ---------------------------------------------------------------------------- |
| 📝 **Yêu cầu + Ghi nhật ký proxy** | Yêu cầu/phản hồi đầy đủ và ghi nhật ký proxy |
| 📉 **Streamed Detailed Logs** 🆕 | Reconstructs SSE payload streams cleanly into the UI |
| 📋 **Bảng điều khiển nhật ký hợp nhất** | Chế độ xem yêu cầu, proxy, kiểm tra và bảng điều khiển trong một trang |
| 🔍 **Yêu cầu đo từ xa** | độ trễ p50/p95/p99 và theo dõi yêu cầu |
| 🏥 **Bảng thông tin sức khỏe** | Thời gian hoạt động, trạng thái ngắt, khóa, số liệu thống kê bộ đệm |
@@ -1239,6 +1241,7 @@ OmniRoute v2.0 được xây dựng như một nền tảng hoạt động, khô
| 🔏 **Chuyển đổi vân tay CLI** | So khớp dấu vân tay của mỗi nhà cung cấp trong Cài đặt > Bảo mật |
| 🌐 **i18n (30 ngôn ngữ)** | Hỗ trợ ngôn ngữ tài liệu + bảng điều khiển đầy đủ với phạm vi bảo hiểm RTL |
| 🧹 **Xóa tất cả các mẫu** | Xóa danh sách mô hình bằng một cú nhấp chuột trong chi tiết nhà cung cấp |
| 👁️ **Sidebar Controls** 🆕 | Hide components and integrations from Appearance Settings |
| 📋 **Mẫu vấn đề** | Mẫu GitHub được chuẩn hóa cho các lỗi và tính năng |
| 📂 **Thư mục dữ liệu tùy chỉnh** | `DATA_DIR` ghi đè vị trí lưu trữ |
@@ -1534,11 +1537,11 @@ Models:
<details>
<summary><b>🆓 Nhà cung cấp MIỄN PHÍ (Dự phòng khẩn cấp)</b></summary>
### iFlow (5 mô hình MIỄN PHÍ qua OAuth)
### Qoder (5 mô hình MIỄN PHÍ qua OAuth)
```bash
Dashboard → Connect iFlow
iFlow OAuth login
Dashboard → Connect Qoder
Qoder OAuth login
→ Unlimited usage
Models:
@@ -1736,7 +1739,7 @@ opencode
- Kiểm tra số liệu thống kê sử dụng trong Bảng điều khiển → Chi phí
- Chuyển mô hình chính sang GLM/MiniMax
- Sử dụng bậc miễn phí (Gemini CLI, iFlow) cho các tác vụ không quan trọng
- Sử dụng bậc miễn phí (Gemini CLI, Qoder) cho các tác vụ không quan trọng
**Cổng bảng điều khiển/API bị sai**
+5
View File
@@ -59,6 +59,11 @@ services:
ports:
- "${DASHBOARD_PORT:-${PORT:-20128}}:${DASHBOARD_PORT:-${PORT:-20128}}"
- "${API_PORT:-20129}:${API_PORT:-20129}"
volumes:
- omniroute-data:/app/data
- /var/run/docker.sock:/var/run/docker.sock
- /usr/libexec/docker/cli-plugins:/usr/libexec/docker/cli-plugins:ro
- ${AUTO_UPDATE_HOST_REPO_DIR:-.}:/workspace/omniroute:rw
profiles:
- cli
+26 -19
View File
@@ -216,23 +216,23 @@ Response example:
### Settings
| Endpoint | Method | Description |
| ------------------------------- | ------- | ---------------------- |
| `/api/settings` | GET/PUT/PATCH | General settings |
| `/api/settings/proxy` | GET/PUT | Network proxy config |
| `/api/settings/proxy/test` | POST | Test proxy connection |
| `/api/settings/ip-filter` | GET/PUT | IP allowlist/blocklist |
| `/api/settings/thinking-budget` | GET/PUT | Reasoning token budget |
| `/api/settings/system-prompt` | GET/PUT | Global system prompt |
| Endpoint | Method | Description |
| ------------------------------- | ------------- | ---------------------- |
| `/api/settings` | GET/PUT/PATCH | General settings |
| `/api/settings/proxy` | GET/PUT | Network proxy config |
| `/api/settings/proxy/test` | POST | Test proxy connection |
| `/api/settings/ip-filter` | GET/PUT | IP allowlist/blocklist |
| `/api/settings/thinking-budget` | GET/PUT | Reasoning token budget |
| `/api/settings/system-prompt` | GET/PUT | Global system prompt |
### Monitoring
| Endpoint | Method | Description |
| ------------------------ | ---------- | ----------------------- |
| `/api/sessions` | GET | Active session tracking |
| `/api/rate-limits` | GET | Per-account rate limits |
| Endpoint | Method | Description |
| ------------------------ | ---------- | ---------------------------------------------------------------------------------------------------- |
| `/api/sessions` | GET | Active session tracking |
| `/api/rate-limits` | GET | Per-account rate limits |
| `/api/monitoring/health` | GET | Health check + provider summary (`catalogCount`, `configuredCount`, `activeCount`, `monitoredCount`) |
| `/api/cache/stats` | GET/DELETE | Cache stats / clear |
| `/api/cache/stats` | GET/DELETE | Cache stats / clear |
### Backup & Export/Import
@@ -253,6 +253,13 @@ Response example:
| `/api/sync/initialize` | POST | Initialize sync |
| `/api/cloud/*` | Various | Cloud management |
### Tunnels
| Endpoint | Method | Description |
| -------------------------- | ------ | ----------------------------------------------------------------------- |
| `/api/tunnels/cloudflared` | GET | Read Cloudflare Quick Tunnel install/runtime status for the dashboard |
| `/api/tunnels/cloudflared` | POST | Enable or disable the Cloudflare Quick Tunnel (`action=enable/disable`) |
### CLI Tools
| Endpoint | Method | Description |
@@ -277,12 +284,12 @@ GET response includes `agents[]` (id, name, binary, version, installed, protocol
### Resilience & Rate Limits
| Endpoint | Method | Description |
| ----------------------- | ------- | ------------------------------- |
| `/api/resilience` | GET/PATCH | Get/update resilience profiles |
| `/api/resilience/reset` | POST | Reset circuit breakers |
| `/api/rate-limits` | GET | Per-account rate limit status |
| `/api/rate-limit` | GET | Global rate limit configuration |
| Endpoint | Method | Description |
| ----------------------- | --------- | ------------------------------- |
| `/api/resilience` | GET/PATCH | Get/update resilience profiles |
| `/api/resilience/reset` | POST | Reset circuit breakers |
| `/api/rate-limits` | GET | Per-account rate limit status |
| `/api/rate-limit` | GET | Global rate limit configuration |
### Evals
+25 -25
View File
@@ -106,7 +106,7 @@ flowchart LR
end
subgraph Upstreams[Upstream Providers]
P1[OAuth Providers\nClaude/Codex/Gemini/Qwen/iFlow/GitHub/Kiro/Cursor/Antigravity]
P1[OAuth Providers\nClaude/Codex/Gemini/Qwen/Qoder/GitHub/Kiro/Cursor/Antigravity]
P2[API Key Providers\nOpenAI/Anthropic/OpenRouter/GLM/Kimi/MiniMax\nDeepSeek/Groq/xAI/Mistral/Perplexity\nTogether/Fireworks/Cerebras/Cohere/NVIDIA]
P3[Compatible Nodes\nOpenAI-compatible / Anthropic-compatible]
end
@@ -240,7 +240,7 @@ Domain layer modules:
OAuth provider modules (12 individual files under `src/lib/oauth/providers/`):
- Registry index: `src/lib/oauth/providers/index.ts`
- Individual providers: `claude.ts`, `codex.ts`, `gemini.ts`, `antigravity.ts`, `iflow.ts`, `qwen.ts`, `kimi-coding.ts`, `github.ts`, `kiro.ts`, `cursor.ts`, `kilocode.ts`, `cline.ts`
- Individual providers: `claude.ts`, `codex.ts`, `gemini.ts`, `antigravity.ts`, `qoder.ts`, `qwen.ts`, `kimi-coding.ts`, `github.ts`, `kiro.ts`, `cursor.ts`, `kilocode.ts`, `cline.ts`
- Thin wrapper: `src/lib/oauth/providers.ts` — re-exports from individual modules
## 3) Persistence Layer
@@ -614,7 +614,7 @@ Each provider has a specialized executor extending `BaseExecutor` (in `open-sse/
| Executor | Provider(s) | Special Handling |
| --------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------- |
| `DefaultExecutor` | OpenAI, Claude, Gemini, Qwen, iFlow, OpenRouter, GLM, Kimi, MiniMax, DeepSeek, Groq, xAI, Mistral, Perplexity, Together, Fireworks, Cerebras, Cohere, NVIDIA | Dynamic URL/header config per provider |
| `DefaultExecutor` | OpenAI, Claude, Gemini, Qwen, Qoder, OpenRouter, GLM, Kimi, MiniMax, DeepSeek, Groq, xAI, Mistral, Perplexity, Together, Fireworks, Cerebras, Cohere, NVIDIA | Dynamic URL/header config per provider |
| `AntigravityExecutor` | Google Antigravity | Custom project/session IDs, Retry-After parsing |
| `CodexExecutor` | OpenAI Codex | Injects system instructions, forces reasoning effort |
| `CursorExecutor` | Cursor IDE | ConnectRPC protocol, Protobuf encoding, request signing via checksum |
@@ -638,7 +638,7 @@ All other providers (including custom compatible nodes) use the `DefaultExecutor
| Cursor | cursor | Custom checksum | ✅ | ✅ | ❌ | ❌ |
| Kiro | kiro | AWS SSO OIDC | ✅ (EventStream) | ❌ | ✅ | ✅ Usage limits |
| Qwen | openai | OAuth | ✅ | ✅ | ✅ | ⚠️ Per request |
| iFlow | openai | OAuth (Basic) | ✅ | ✅ | ✅ | ⚠️ Per request |
| Qoder | openai | OAuth (Basic) | ✅ | ✅ | ✅ | ⚠️ Per request |
| OpenRouter | openai | API Key | ✅ | ✅ | ❌ | ❌ |
| GLM/Kimi/MiniMax | claude | API Key | ✅ | ✅ | ❌ | ❌ |
| DeepSeek | openai | API Key | ✅ | ✅ | ❌ | ❌ |
@@ -686,25 +686,25 @@ Additional processing layers in the translation pipeline:
## Supported API Endpoints
| Endpoint | Format | Handler |
| -------------------------------------------------- | ------------------ | ---------------------------------------------------- |
| `POST /v1/chat/completions` | OpenAI Chat | `src/sse/handlers/chat.ts` |
| `POST /v1/messages` | Claude Messages | Same handler (auto-detected) |
| `POST /v1/responses` | OpenAI Responses | `open-sse/handlers/responsesHandler.ts` |
| `POST /v1/embeddings` | OpenAI Embeddings | `open-sse/handlers/embeddings.ts` |
| `GET /v1/embeddings` | Model listing | API route |
| `POST /v1/images/generations` | OpenAI Images | `open-sse/handlers/imageGeneration.ts` |
| `GET /v1/images/generations` | Model listing | API route |
| `POST /v1/providers/{provider}/chat/completions` | OpenAI Chat | Dedicated per-provider with model validation |
| `POST /v1/providers/{provider}/embeddings` | OpenAI Embeddings | Dedicated per-provider with model validation |
| `POST /v1/providers/{provider}/images/generations` | OpenAI Images | Dedicated per-provider with model validation |
| `POST /v1/messages/count_tokens` | Claude Token Count | API route |
| `GET /v1/models` | OpenAI Models list | API route (chat + embedding + image + custom models) |
| `GET /api/models/catalog` | Catalog | All models grouped by provider + type |
| `POST /v1beta/models/*:streamGenerateContent` | Gemini native | API route |
| `GET/PUT/DELETE /api/settings/proxy` | Proxy Config | Network proxy configuration |
| `POST /api/settings/proxy/test` | Proxy Connectivity | Proxy health/connectivity test endpoint |
| `GET/POST/DELETE /api/provider-models` | Custom Models | Custom model management per provider |
| Endpoint | Format | Handler |
| -------------------------------------------------- | ------------------ | ------------------------------------------------------------------- |
| `POST /v1/chat/completions` | OpenAI Chat | `src/sse/handlers/chat.ts` |
| `POST /v1/messages` | Claude Messages | Same handler (auto-detected) |
| `POST /v1/responses` | OpenAI Responses | `open-sse/handlers/responsesHandler.ts` |
| `POST /v1/embeddings` | OpenAI Embeddings | `open-sse/handlers/embeddings.ts` |
| `GET /v1/embeddings` | Model listing | API route |
| `POST /v1/images/generations` | OpenAI Images | `open-sse/handlers/imageGeneration.ts` |
| `GET /v1/images/generations` | Model listing | API route |
| `POST /v1/providers/{provider}/chat/completions` | OpenAI Chat | Dedicated per-provider with model validation |
| `POST /v1/providers/{provider}/embeddings` | OpenAI Embeddings | Dedicated per-provider with model validation |
| `POST /v1/providers/{provider}/images/generations` | OpenAI Images | Dedicated per-provider with model validation |
| `POST /v1/messages/count_tokens` | Claude Token Count | API route |
| `GET /v1/models` | OpenAI Models list | API route (chat + embedding + image + custom models) |
| `GET /api/models/catalog` | Catalog | All models grouped by provider + type |
| `POST /v1beta/models/*:streamGenerateContent` | Gemini native | API route |
| `GET/PUT/DELETE /api/settings/proxy` | Proxy Config | Network proxy configuration |
| `POST /api/settings/proxy/test` | Proxy Connectivity | Proxy health/connectivity test endpoint |
| `GET/POST/DELETE /api/provider-models` | Provider Models | Provider model metadata backing custom and managed available models |
## Bypass Handler
@@ -765,8 +765,8 @@ Detailed request payload capture stores up to four JSON payload stages per route
- raw request received from the client
- translated request actually sent upstream
- provider response reconstructed as JSON (including streamed event sequences when applicable)
- final client response returned by OmniRoute
- provider response reconstructed as JSON; streamed responses are compacted to the final summary plus stream metadata
- final client response returned by OmniRoute; streamed responses are stored in the same compact summary form
## Security-Sensitive Boundaries
+2 -2
View File
@@ -267,7 +267,7 @@ Business logic that supports the handlers and executors.
| `provider.ts` | **Format detection** (`detectFormat`): analyzes request body structure to identify Claude/OpenAI/Gemini/Antigravity/Responses formats (includes `max_tokens` heuristic for Claude). Also: URL building, header building, thinking config normalization. Supports `openai-compatible-*` and `anthropic-compatible-*` dynamic providers. |
| `model.ts` | Model string parsing (`claude/model-name``{provider: "claude", model: "model-name"}`), alias resolution with collision detection, input sanitization (rejects path traversal/control chars), and model info resolution with async alias getter support. |
| `accountFallback.ts` | Rate-limit handling: exponential backoff (1s → 2s → 4s → max 2min), account cooldown management, error classification (which errors trigger fallback vs. not). |
| `tokenRefresh.ts` | OAuth token refresh for **every provider**: Google (Gemini, Antigravity), Claude, Codex, Qwen, iFlow, GitHub (OAuth + Copilot dual-token), Kiro (AWS SSO OIDC + Social Auth). Includes in-flight promise deduplication cache and retry with exponential backoff. |
| `tokenRefresh.ts` | OAuth token refresh for **every provider**: Google (Gemini, Antigravity), Claude, Codex, Qwen, Qoder, GitHub (OAuth + Copilot dual-token), Kiro (AWS SSO OIDC + Social Auth). Includes in-flight promise deduplication cache and retry with exponential backoff. |
| `combo.ts` | **Combo models**: chains of fallback models. If model A fails with a fallback-eligible error, try model B, then C, etc. Returns actual upstream status codes. |
| `usage.ts` | Fetches quota/usage data from provider APIs (GitHub Copilot quotas, Antigravity model quotas, Codex rate limits, Kiro usage breakdowns, Claude settings). |
| `accountSelector.ts` | Smart account selection with scoring algorithm: considers priority, health status, round-robin position, and cooldown state to pick the optimal account for each request. |
@@ -539,7 +539,7 @@ A 2000-token buffer is added to reported usage to prevent clients from hitting c
| Kiro (AWS) | AWS SSO OIDC or Social | Kiro | Binary EventStream parsing |
| Cursor IDE | Checksum auth | Cursor | Protobuf encoding, SHA-256 checksums |
| Qwen | OAuth | Default | Standard auth |
| iFlow | OAuth (Basic + Bearer) | Default | Dual auth header |
| Qoder | OAuth (Basic + Bearer) | Default | Dual auth header |
| OpenRouter | API key | Default | Standard Bearer auth |
| GLM, Kimi, MiniMax | API key | Default | Claude-compatible, use `x-api-key` |
| `openai-compatible-*` | API key | Default | Dynamic: any OpenAI-compatible endpoint |
+5 -5
View File
@@ -8,7 +8,7 @@ Visual guide to every section of the OmniRoute dashboard.
## 🔌 Providers
Manage AI provider connections: OAuth providers (Claude Code, Codex, Gemini CLI), API key providers (Groq, DeepSeek, OpenRouter), and free providers (iFlow, Qwen, Kiro). Kiro accounts include credit balance tracking — remaining credits, total allowance, and renewal date visible in Dashboard → Usage.
Manage AI provider connections: OAuth providers (Claude Code, Codex, Gemini CLI), API key providers (Groq, DeepSeek, OpenRouter), and free providers (Qoder, Qwen, Kiro). Kiro accounts include credit balance tracking — remaining credits, total allowance, and renewal date visible in Dashboard → Usage.
![Providers Dashboard](screenshots/01-providers.png)
@@ -63,11 +63,11 @@ Customizable color themes for the entire dashboard. Choose from 7 preset colors
Comprehensive settings panel with tabs:
- **General** — System storage, backup management (export/import database)
- **Appearance** — Theme selector (dark/light/system), color theme presets and custom colors, health log visibility
- **Appearance** — Theme selector (dark/light/system), color theme presets and custom colors, health log visibility, sidebar item visibility controls
- **Security** — API endpoint protection, custom provider blocking, IP filtering, session info
- **Routing** — Model aliases, background task degradation
- **Resilience** — Rate limit persistence, circuit breaker tuning
- **Advanced** — Configuration overrides
- **Resilience** — Rate limit persistence, circuit breaker tuning, auto-disable banned accounts, provider expiration monitoring
- **Advanced** — Configuration overrides, configuration audit trail, fallback degradation mode
![Settings Dashboard](screenshots/06-settings.png)
@@ -108,7 +108,7 @@ Real-time request logging with filtering by provider, model, account, and API ke
## 🌐 API Endpoint
Your unified API endpoint with capability breakdown: Chat Completions, Responses API, Embeddings, Image Generation, Reranking, Audio Transcription, Text-to-Speech, Moderations, and registered API keys. Cloud proxy support for remote access.
Your unified API endpoint with capability breakdown: Chat Completions, Responses API, Embeddings, Image Generation, Reranking, Audio Transcription, Text-to-Speech, Moderations, and registered API keys. Cloudflare Quick Tunnel integration and cloud proxy support for remote access.
![Endpoint Dashboard](screenshots/09-endpoint.png)
+10 -10
View File
@@ -38,16 +38,16 @@ See [IDE Configs](integrations/ide-configs.md) for Antigravity, Cursor, Copilot,
## Advanced Tools (8)
| Tool | Description |
| :--------------------------------- | :---------------------------------------------- |
| `omniroute_simulate_route` | Dry-run routing simulation with fallback tree |
| `omniroute_set_budget_guard` | Session budget with degrade/block/alert actions |
| `omniroute_set_resilience_profile` | Apply conservative/balanced/aggressive preset |
| `omniroute_test_combo` | Live-test all models in a combo |
| `omniroute_get_provider_metrics` | Detailed metrics for one provider |
| `omniroute_best_combo_for_task` | Task-fitness recommendation with alternatives |
| `omniroute_explain_route` | Explain a past routing decision |
| `omniroute_get_session_snapshot` | Full session state: costs, tokens, errors |
| Tool | Description |
| :--------------------------------- | :---------------------------------------------------------- |
| `omniroute_simulate_route` | Dry-run routing simulation with fallback tree |
| `omniroute_set_budget_guard` | Session budget with degrade/block/alert actions |
| `omniroute_set_resilience_profile` | Apply conservative/balanced/aggressive preset |
| `omniroute_test_combo` | Live-test all models in a combo via a real upstream request |
| `omniroute_get_provider_metrics` | Detailed metrics for one provider |
| `omniroute_best_combo_for_task` | Task-fitness recommendation with alternatives |
| `omniroute_explain_route` | Explain a past routing decision |
| `omniroute_get_session_snapshot` | Full session state: costs, tokens, errors |
## Authentication
+1 -1
View File
@@ -97,7 +97,7 @@ curl -s http://localhost:20128/api/cli-tools/openclaw-settings | jq '{installed,
1. Check usage stats in Dashboard → Usage
2. Switch primary model to GLM/MiniMax
3. Use free tier (Gemini CLI, iFlow) for non-critical tasks
3. Use free tier (Gemini CLI, Qoder) for non-critical tasks
4. Set cost budgets per API key: Dashboard → API Keys → Budget
---
+139 -23
View File
@@ -39,11 +39,11 @@ Complete guide for configuring providers, creating combos, integrating CLI tools
| **💰 CHEAP** | GLM-4.7 | $0.6/1M | Daily 10AM | Budget backup |
| | MiniMax M2.1 | $0.2/1M | 5-hour rolling | Cheapest option |
| | Kimi K2 | $9/mo flat | 10M tokens/mo | Predictable cost |
| **🆓 FREE** | iFlow | $0 | Unlimited | 8 models free |
| **🆓 FREE** | Qoder | $0 | Unlimited | 8 models free |
| | Qwen | $0 | Unlimited | 3 models free |
| | Kiro | $0 | Unlimited | Claude free |
**💡 Pro Tip:** Start with Gemini CLI (180K free/month) + iFlow (unlimited free) combo = $0 cost!
**💡 Pro Tip:** Start with Gemini CLI (180K free/month) + Qoder (unlimited free) combo = $0 cost!
---
@@ -193,10 +193,10 @@ Models:
### 🆓 FREE Providers
#### iFlow (8 FREE models)
#### Qoder (8 FREE models)
```bash
Dashboard → Connect iFlow → OAuth login → Unlimited usage
Dashboard → Connect Qoder → OAuth login → Unlimited usage
Models: if/kimi-k2-thinking, if/qwen3-coder-plus, if/glm-4.7, if/minimax-m2, if/deepseek-r1
```
@@ -405,25 +405,127 @@ docker run -d --name omniroute -p 20128:20128 --env-file ./.env -v omniroute-dat
For host-integrated mode with CLI binaries, see the Docker section in the main docs.
### Void Linux (xbps-src)
Void Linux users can package and install OmniRoute natively using the `xbps-src` cross-compilation framework. This automates the Node.js standalone build along with the required `better-sqlite3` native bindings.
<details>
<summary><b>View xbps-src template</b></summary>
```bash
# Template file for 'omniroute'
pkgname=omniroute
version=3.2.4
revision=1
hostmakedepends="nodejs python3 make"
depends="openssl"
short_desc="Universal AI gateway with smart routing for multiple LLM providers"
maintainer="zenobit <zenobit@disroot.org>"
license="MIT"
homepage="https://github.com/diegosouzapw/OmniRoute"
distfiles="https://github.com/diegosouzapw/OmniRoute/archive/refs/tags/v${version}.tar.gz"
checksum=009400afee90a9f32599d8fe734145cfd84098140b7287990183dde45ae2245b
system_accounts="_omniroute"
omniroute_homedir="/var/lib/omniroute"
export NODE_ENV=production
export npm_config_engine_strict=false
export npm_config_loglevel=error
export npm_config_fund=false
export npm_config_audit=false
do_build() {
# Determine target CPU arch for node-gyp
local _gyp_arch
case "$XBPS_TARGET_MACHINE" in
aarch64*) _gyp_arch=arm64 ;;
armv7*|armv6*) _gyp_arch=arm ;;
i686*) _gyp_arch=ia32 ;;
*) _gyp_arch=x64 ;;
esac
# 1) Install all deps skip scripts
NODE_ENV=development npm ci --ignore-scripts
# 2) Build the Next.js standalone bundle
npm run build
# 3) Copy static assets into standalone
cp -r .next/static .next/standalone/.next/static
[ -d public ] && cp -r public .next/standalone/public || true
# 4) Compile better-sqlite3 native binding
local _node_gyp=/usr/lib/node_modules/npm/node_modules/node-gyp/bin/node-gyp.js
(cd node_modules/better-sqlite3 && node "$_node_gyp" rebuild --arch="$_gyp_arch")
# 5) Place the compiled binding into the standalone bundle
local _bs3_release=.next/standalone/node_modules/better-sqlite3/build/Release
mkdir -p "$_bs3_release"
cp node_modules/better-sqlite3/build/Release/better_sqlite3.node "$_bs3_release/"
# 6) Remove arch-specific sharp bundles
rm -rf .next/standalone/node_modules/@img
# 7) Copy pino runtime deps omitted by Next.js static analysis:
for _mod in pino-abstract-transport split2 process-warning; do
cp -r "node_modules/$_mod" .next/standalone/node_modules/
done
}
do_check() {
npm run test:unit
}
do_install() {
vmkdir usr/lib/omniroute/.next
vcopy .next/standalone/. usr/lib/omniroute/.next/standalone
# Prevent removal of empty Next.js app router dirs by the post-install hook
for _d in \
.next/standalone/.next/server/app/dashboard \
.next/standalone/.next/server/app/dashboard/settings \
.next/standalone/.next/server/app/dashboard/providers; do
touch "${DESTDIR}/usr/lib/omniroute/${_d}/.keep"
done
cat > "${WRKDIR}/omniroute" <<'EOF'
#!/bin/sh
export PORT="${PORT:-20128}"
export DATA_DIR="${DATA_DIR:-${XDG_DATA_HOME:-${HOME}/.local/share}/omniroute}"
export LOG_TO_FILE="${LOG_TO_FILE:-false}"
mkdir -p "${DATA_DIR}"
exec node /usr/lib/omniroute/.next/standalone/server.js "$@"
EOF
vbin "${WRKDIR}/omniroute"
}
post_install() {
vlicense LICENSE
}
```
</details>
### Environment Variables
| Variable | Default | Description |
| ------------------------- | ------------------------------------ | ------------------------------------------------------- |
| `JWT_SECRET` | `omniroute-default-secret-change-me` | JWT signing secret (**change in production**) |
| `INITIAL_PASSWORD` | `123456` | First login password |
| `DATA_DIR` | `~/.omniroute` | Data directory (db, usage, logs) |
| `PORT` | framework default | Service port (`20128` in examples) |
| `HOSTNAME` | framework default | Bind host (Docker defaults to `0.0.0.0`) |
| `NODE_ENV` | runtime default | Set `production` for deploy |
| `BASE_URL` | `http://localhost:20128` | Server-side internal base URL |
| `CLOUD_URL` | `https://omniroute.dev` | Cloud sync endpoint base URL |
| `API_KEY_SECRET` | `endpoint-proxy-api-key-secret` | HMAC secret for generated API keys |
| `REQUIRE_API_KEY` | `false` | Enforce Bearer API key on `/v1/*` |
| `ENABLE_REQUEST_LOGS` | `false` | Enables request/response logs |
| `AUTH_COOKIE_SECURE` | `false` | Force `Secure` auth cookie (behind HTTPS reverse proxy) |
| `OMNIROUTE_MEMORY_MB` | `512` | Node.js heap limit in MB |
| `PROMPT_CACHE_MAX_SIZE` | `50` | Max prompt cache entries |
| `SEMANTIC_CACHE_MAX_SIZE` | `100` | Max semantic cache entries |
| Variable | Default | Description |
| ------------------------- | ------------------------------------ | ---------------------------------------------------------------- |
| `JWT_SECRET` | `omniroute-default-secret-change-me` | JWT signing secret (**change in production**) |
| `INITIAL_PASSWORD` | `123456` | First login password |
| `DATA_DIR` | `~/.omniroute` | Data directory (db, usage, logs) |
| `PORT` | framework default | Service port (`20128` in examples) |
| `HOSTNAME` | framework default | Bind host (Docker defaults to `0.0.0.0`) |
| `NODE_ENV` | runtime default | Set `production` for deploy |
| `BASE_URL` | `http://localhost:20128` | Server-side internal base URL |
| `CLOUD_URL` | `https://omniroute.dev` | Cloud sync endpoint base URL |
| `API_KEY_SECRET` | `endpoint-proxy-api-key-secret` | HMAC secret for generated API keys |
| `REQUIRE_API_KEY` | `false` | Enforce Bearer API key on `/v1/*` |
| `ALLOW_API_KEY_REVEAL` | `false` | Allow Api Manager to copy full API keys on demand |
| `ENABLE_REQUEST_LOGS` | `false` | Enables request/response logs |
| `AUTH_COOKIE_SECURE` | `false` | Force `Secure` auth cookie (behind HTTPS reverse proxy) |
| `CLOUDFLARED_BIN` | unset | Use an existing `cloudflared` binary instead of managed download |
| `OMNIROUTE_MEMORY_MB` | `512` | Node.js heap limit in MB |
| `PROMPT_CACHE_MAX_SIZE` | `50` | Max prompt cache entries |
| `SEMANTIC_CACHE_MAX_SIZE` | `100` | Max semantic cache entries |
For the full environment variable reference, see the [README](../README.md).
@@ -446,7 +548,7 @@ For the full environment variable reference, see the [README](../README.md).
**MiniMax (`minimax/`)** — $0.2/1M: `minimax/MiniMax-M2.1`
**iFlow (`if/`)** — FREE: `if/kimi-k2-thinking`, `if/qwen3-coder-plus`, `if/deepseek-r1`
**Qoder (`if/`)** — FREE: `if/kimi-k2-thinking`, `if/qwen3-coder-plus`, `if/deepseek-r1`
**Qwen (`qw/`)** — FREE: `qw/qwen3-coder-plus`, `qw/qwen3-coder-flash`
@@ -494,6 +596,11 @@ curl -X POST http://localhost:20128/api/provider-models \
Or use Dashboard: **Providers → [Provider] → Custom Models**.
Notes:
- OpenRouter and OpenAI/Anthropic-compatible providers are managed from **Available Models** only. Manual add, import, and auto-sync all land in the same available-model list, so there is no separate Custom Models section for those providers.
- The **Custom Models** section is intended for providers that do not expose managed available-model imports.
### Dedicated Provider Routes
Route requests directly to a specific provider with model validation:
@@ -538,6 +645,14 @@ Returns models grouped by provider with types (`chat`, `embedding`, `image`).
- Automatic background sync with timeout + fail-fast
- Prefer server-side `BASE_URL`/`CLOUD_URL` in production
### Cloudflare Quick Tunnel
- Available in **Dashboard → Endpoints** for Docker and other self-hosted deployments
- Creates a temporary `https://*.trycloudflare.com` URL that forwards to your current OpenAI-compatible `/v1` endpoint
- First enable installs `cloudflared` only when needed; later restarts reuse the same managed binary
- Tunnel URLs are ephemeral and change every time you stop/start the tunnel
- Set `CLOUDFLARED_BIN` if you prefer using a preinstalled `cloudflared` binary instead of the managed download
### LLM Gateway Intelligence (Phase 9)
- **Semantic Cache** — Auto-caches non-streaming, temperature=0 responses (bypass with `X-OmniRoute-No-Cache: true`)
@@ -683,10 +798,11 @@ curl -X POST http://localhost:20128/api/db-backups/import \
### Settings Dashboard
The settings page is organized into 5 tabs for easy navigation:
The settings page is organized into 6 tabs for easy navigation:
| Tab | Contents |
| -------------- | ---------------------------------------------------------------------------------------------- |
| **General** | System storage tools, appearance settings, theme controls, and per-item sidebar visibility |
| **Security** | Login/Password settings, IP Access Control, API auth for `/models`, and Provider Blocking |
| **Routing** | Global routing strategy (6 options), wildcard model aliases, fallback chains, combo defaults |
| **Resilience** | Provider profiles, editable rate limits, circuit breaker status, policies & locked identifiers |
+32 -10
View File
@@ -1,13 +1,35 @@
# Multilingual Documentation
# 🌐 Multilingual Documentation — 9router
This directory contains machine-assisted translations based on the English docs.
Translations of documentation into 30 languages. Code blocks remain in English.
- **API_REFERENCE.md**: 🇺🇸 [English](../API_REFERENCE.md) | 🇧🇷 [Português (Brasil)](./pt-BR/API_REFERENCE.md) | 🇪🇸 [Español](./es/API_REFERENCE.md) | 🇫🇷 [Français](./fr/API_REFERENCE.md) | 🇮🇹 [Italiano](./it/API_REFERENCE.md) | 🇷🇺 [Русский](./ru/API_REFERENCE.md) | 🇨🇳 [中文 (简体)](./zh-CN/API_REFERENCE.md) | 🇩🇪 [Deutsch](./de/API_REFERENCE.md) | 🇮🇳 [हिन्दी](./in/API_REFERENCE.md) | 🇹🇭 [ไทย](./th/API_REFERENCE.md) | 🇺🇦 [Українська](./uk-UA/API_REFERENCE.md) | 🇸🇦 [العربية](./ar/API_REFERENCE.md) | 🇯🇵 [日本語](./ja/API_REFERENCE.md) | 🇻🇳 [Tiếng Việt](./vi/API_REFERENCE.md) | 🇧🇬 [Български](./bg/API_REFERENCE.md) | 🇩🇰 [Dansk](./da/API_REFERENCE.md) | 🇫🇮 [Suomi](./fi/API_REFERENCE.md) | 🇮🇱 [עברית](./he/API_REFERENCE.md) | 🇭🇺 [Magyar](./hu/API_REFERENCE.md) | 🇮🇩 [Bahasa Indonesia](./id/API_REFERENCE.md) | 🇰🇷 [한국어](./ko/API_REFERENCE.md) | 🇲🇾 [Bahasa Melayu](./ms/API_REFERENCE.md) | 🇳🇱 [Nederlands](./nl/API_REFERENCE.md) | 🇳🇴 [Norsk](./no/API_REFERENCE.md) | 🇵🇹 [Português (Portugal)](./pt/API_REFERENCE.md) | 🇷🇴 [Română](./ro/API_REFERENCE.md) | 🇵🇱 [Polski](./pl/API_REFERENCE.md) | 🇸🇰 [Slovenčina](./sk/API_REFERENCE.md) | 🇸🇪 [Svenska](./sv/API_REFERENCE.md) | 🇵🇭 [Filipino](./phi/API_REFERENCE.md) | 🇨🇿 [Čeština](./cs/API_REFERENCE.md)
- **ARCHITECTURE.md**: 🇺🇸 [English](../ARCHITECTURE.md) | 🇧🇷 [Português (Brasil)](./pt-BR/ARCHITECTURE.md) | 🇪🇸 [Español](./es/ARCHITECTURE.md) | 🇫🇷 [Français](./fr/ARCHITECTURE.md) | 🇮🇹 [Italiano](./it/ARCHITECTURE.md) | 🇷🇺 [Русский](./ru/ARCHITECTURE.md) | 🇨🇳 [中文 (简体)](./zh-CN/ARCHITECTURE.md) | 🇩🇪 [Deutsch](./de/ARCHITECTURE.md) | 🇮🇳 [हिन्दी](./in/ARCHITECTURE.md) | 🇹🇭 [ไทย](./th/ARCHITECTURE.md) | 🇺🇦 [Українська](./uk-UA/ARCHITECTURE.md) | 🇸🇦 [العربية](./ar/ARCHITECTURE.md) | 🇯🇵 [日本語](./ja/ARCHITECTURE.md) | 🇻🇳 [Tiếng Việt](./vi/ARCHITECTURE.md) | 🇧🇬 [Български](./bg/ARCHITECTURE.md) | 🇩🇰 [Dansk](./da/ARCHITECTURE.md) | 🇫🇮 [Suomi](./fi/ARCHITECTURE.md) | 🇮🇱 [עברית](./he/ARCHITECTURE.md) | 🇭🇺 [Magyar](./hu/ARCHITECTURE.md) | 🇮🇩 [Bahasa Indonesia](./id/ARCHITECTURE.md) | 🇰🇷 [한국어](./ko/ARCHITECTURE.md) | 🇲🇾 [Bahasa Melayu](./ms/ARCHITECTURE.md) | 🇳🇱 [Nederlands](./nl/ARCHITECTURE.md) | 🇳🇴 [Norsk](./no/ARCHITECTURE.md) | 🇵🇹 [Português (Portugal)](./pt/ARCHITECTURE.md) | 🇷🇴 [Română](./ro/ARCHITECTURE.md) | 🇵🇱 [Polski](./pl/ARCHITECTURE.md) | 🇸🇰 [Slovenčina](./sk/ARCHITECTURE.md) | 🇸🇪 [Svenska](./sv/ARCHITECTURE.md) | 🇵🇭 [Filipino](./phi/ARCHITECTURE.md) | 🇨🇿 [Čeština](./cs/ARCHITECTURE.md)
- **CODEBASE_DOCUMENTATION.md**: 🇺🇸 [English](../CODEBASE_DOCUMENTATION.md) | 🇧🇷 [Português (Brasil)](./pt-BR/CODEBASE_DOCUMENTATION.md) | 🇪🇸 [Español](./es/CODEBASE_DOCUMENTATION.md) | 🇫🇷 [Français](./fr/CODEBASE_DOCUMENTATION.md) | 🇮🇹 [Italiano](./it/CODEBASE_DOCUMENTATION.md) | 🇷🇺 [Русский](./ru/CODEBASE_DOCUMENTATION.md) | 🇨🇳 [中文 (简体)](./zh-CN/CODEBASE_DOCUMENTATION.md) | 🇩🇪 [Deutsch](./de/CODEBASE_DOCUMENTATION.md) | 🇮🇳 [हिन्दी](./in/CODEBASE_DOCUMENTATION.md) | 🇹🇭 [ไทย](./th/CODEBASE_DOCUMENTATION.md) | 🇺🇦 [Українська](./uk-UA/CODEBASE_DOCUMENTATION.md) | 🇸🇦 [العربية](./ar/CODEBASE_DOCUMENTATION.md) | 🇯🇵 [日本語](./ja/CODEBASE_DOCUMENTATION.md) | 🇻🇳 [Tiếng Việt](./vi/CODEBASE_DOCUMENTATION.md) | 🇧🇬 [Български](./bg/CODEBASE_DOCUMENTATION.md) | 🇩🇰 [Dansk](./da/CODEBASE_DOCUMENTATION.md) | 🇫🇮 [Suomi](./fi/CODEBASE_DOCUMENTATION.md) | 🇮🇱 [עברית](./he/CODEBASE_DOCUMENTATION.md) | 🇭🇺 [Magyar](./hu/CODEBASE_DOCUMENTATION.md) | 🇮🇩 [Bahasa Indonesia](./id/CODEBASE_DOCUMENTATION.md) | 🇰🇷 [한국어](./ko/CODEBASE_DOCUMENTATION.md) | 🇲🇾 [Bahasa Melayu](./ms/CODEBASE_DOCUMENTATION.md) | 🇳🇱 [Nederlands](./nl/CODEBASE_DOCUMENTATION.md) | 🇳🇴 [Norsk](./no/CODEBASE_DOCUMENTATION.md) | 🇵🇹 [Português (Portugal)](./pt/CODEBASE_DOCUMENTATION.md) | 🇷🇴 [Română](./ro/CODEBASE_DOCUMENTATION.md) | 🇵🇱 [Polski](./pl/CODEBASE_DOCUMENTATION.md) | 🇸🇰 [Slovenčina](./sk/CODEBASE_DOCUMENTATION.md) | 🇸🇪 [Svenska](./sv/CODEBASE_DOCUMENTATION.md) | 🇵🇭 [Filipino](./phi/CODEBASE_DOCUMENTATION.md) | 🇨🇿 [Čeština](./cs/CODEBASE_DOCUMENTATION.md)
- **FEATURES.md**: 🇺🇸 [English](../FEATURES.md) | 🇧🇷 [Português (Brasil)](./pt-BR/FEATURES.md) | 🇪🇸 [Español](./es/FEATURES.md) | 🇫🇷 [Français](./fr/FEATURES.md) | 🇮🇹 [Italiano](./it/FEATURES.md) | 🇷🇺 [Русский](./ru/FEATURES.md) | 🇨🇳 [中文 (简体)](./zh-CN/FEATURES.md) | 🇩🇪 [Deutsch](./de/FEATURES.md) | 🇮🇳 [हिन्दी](./in/FEATURES.md) | 🇹🇭 [ไทย](./th/FEATURES.md) | 🇺🇦 [Українська](./uk-UA/FEATURES.md) | 🇸🇦 [العربية](./ar/FEATURES.md) | 🇯🇵 [日本語](./ja/FEATURES.md) | 🇻🇳 [Tiếng Việt](./vi/FEATURES.md) | 🇧🇬 [Български](./bg/FEATURES.md) | 🇩🇰 [Dansk](./da/FEATURES.md) | 🇫🇮 [Suomi](./fi/FEATURES.md) | 🇮🇱 [עברית](./he/FEATURES.md) | 🇭🇺 [Magyar](./hu/FEATURES.md) | 🇮🇩 [Bahasa Indonesia](./id/FEATURES.md) | 🇰🇷 [한국어](./ko/FEATURES.md) | 🇲🇾 [Bahasa Melayu](./ms/FEATURES.md) | 🇳🇱 [Nederlands](./nl/FEATURES.md) | 🇳🇴 [Norsk](./no/FEATURES.md) | 🇵🇹 [Português (Portugal)](./pt/FEATURES.md) | 🇷🇴 [Română](./ro/FEATURES.md) | 🇵🇱 [Polski](./pl/FEATURES.md) | 🇸🇰 [Slovenčina](./sk/FEATURES.md) | 🇸🇪 [Svenska](./sv/FEATURES.md) | 🇵🇭 [Filipino](./phi/FEATURES.md) | 🇨🇿 [Čeština](./cs/FEATURES.md)
- **TROUBLESHOOTING.md**: 🇺🇸 [English](../TROUBLESHOOTING.md) | 🇧🇷 [Português (Brasil)](./pt-BR/TROUBLESHOOTING.md) | 🇪🇸 [Español](./es/TROUBLESHOOTING.md) | 🇫🇷 [Français](./fr/TROUBLESHOOTING.md) | 🇮🇹 [Italiano](./it/TROUBLESHOOTING.md) | 🇷🇺 [Русский](./ru/TROUBLESHOOTING.md) | 🇨🇳 [中文 (简体)](./zh-CN/TROUBLESHOOTING.md) | 🇩🇪 [Deutsch](./de/TROUBLESHOOTING.md) | 🇮🇳 [हिन्दी](./in/TROUBLESHOOTING.md) | 🇹🇭 [ไทย](./th/TROUBLESHOOTING.md) | 🇺🇦 [Українська](./uk-UA/TROUBLESHOOTING.md) | 🇸🇦 [العربية](./ar/TROUBLESHOOTING.md) | 🇯🇵 [日本語](./ja/TROUBLESHOOTING.md) | 🇻🇳 [Tiếng Việt](./vi/TROUBLESHOOTING.md) | 🇧🇬 [Български](./bg/TROUBLESHOOTING.md) | 🇩🇰 [Dansk](./da/TROUBLESHOOTING.md) | 🇫🇮 [Suomi](./fi/TROUBLESHOOTING.md) | 🇮🇱 [עברית](./he/TROUBLESHOOTING.md) | 🇭🇺 [Magyar](./hu/TROUBLESHOOTING.md) | 🇮🇩 [Bahasa Indonesia](./id/TROUBLESHOOTING.md) | 🇰🇷 [한국어](./ko/TROUBLESHOOTING.md) | 🇲🇾 [Bahasa Melayu](./ms/TROUBLESHOOTING.md) | 🇳🇱 [Nederlands](./nl/TROUBLESHOOTING.md) | 🇳🇴 [Norsk](./no/TROUBLESHOOTING.md) | 🇵🇹 [Português (Portugal)](./pt/TROUBLESHOOTING.md) | 🇷🇴 [Română](./ro/TROUBLESHOOTING.md) | 🇵🇱 [Polski](./pl/TROUBLESHOOTING.md) | 🇸🇰 [Slovenčina](./sk/TROUBLESHOOTING.md) | 🇸🇪 [Svenska](./sv/TROUBLESHOOTING.md) | 🇵🇭 [Filipino](./phi/TROUBLESHOOTING.md) | 🇨🇿 [Čeština](./cs/TROUBLESHOOTING.md)
- **USER_GUIDE.md**: 🇺🇸 [English](../USER_GUIDE.md) | 🇧🇷 [Português (Brasil)](./pt-BR/USER_GUIDE.md) | 🇪🇸 [Español](./es/USER_GUIDE.md) | 🇫🇷 [Français](./fr/USER_GUIDE.md) | 🇮🇹 [Italiano](./it/USER_GUIDE.md) | 🇷🇺 [Русский](./ru/USER_GUIDE.md) | 🇨🇳 [中文 (简体)](./zh-CN/USER_GUIDE.md) | 🇩🇪 [Deutsch](./de/USER_GUIDE.md) | 🇮🇳 [हिन्दी](./in/USER_GUIDE.md) | 🇹🇭 [ไทย](./th/USER_GUIDE.md) | 🇺🇦 [Українська](./uk-UA/USER_GUIDE.md) | 🇸🇦 [العربية](./ar/USER_GUIDE.md) | 🇯🇵 [日本語](./ja/USER_GUIDE.md) | 🇻🇳 [Tiếng Việt](./vi/USER_GUIDE.md) | 🇧🇬 [Български](./bg/USER_GUIDE.md) | 🇩🇰 [Dansk](./da/USER_GUIDE.md) | 🇫🇮 [Suomi](./fi/USER_GUIDE.md) | 🇮🇱 [עברית](./he/USER_GUIDE.md) | 🇭🇺 [Magyar](./hu/USER_GUIDE.md) | 🇮🇩 [Bahasa Indonesia](./id/USER_GUIDE.md) | 🇰🇷 [한국어](./ko/USER_GUIDE.md) | 🇲🇾 [Bahasa Melayu](./ms/USER_GUIDE.md) | 🇳🇱 [Nederlands](./nl/USER_GUIDE.md) | 🇳🇴 [Norsk](./no/USER_GUIDE.md) | 🇵🇹 [Português (Portugal)](./pt/USER_GUIDE.md) | 🇷🇴 [Română](./ro/USER_GUIDE.md) | 🇵🇱 [Polski](./pl/USER_GUIDE.md) | 🇸🇰 [Slovenčina](./sk/USER_GUIDE.md) | 🇸🇪 [Svenska](./sv/USER_GUIDE.md) | 🇵🇭 [Filipino](./phi/USER_GUIDE.md) | 🇨🇿 [Čeština](./cs/USER_GUIDE.md)
- **VM_DEPLOYMENT_GUIDE.md**: 🇺🇸 [English](../VM_DEPLOYMENT_GUIDE.md) | 🇧🇷 [Português (Brasil)](./pt-BR/VM_DEPLOYMENT_GUIDE.md) | 🇪🇸 [Español](./es/VM_DEPLOYMENT_GUIDE.md) | 🇫🇷 [Français](./fr/VM_DEPLOYMENT_GUIDE.md) | 🇮🇹 [Italiano](./it/VM_DEPLOYMENT_GUIDE.md) | 🇷🇺 [Русский](./ru/VM_DEPLOYMENT_GUIDE.md) | 🇨🇳 [中文 (简体)](./zh-CN/VM_DEPLOYMENT_GUIDE.md) | 🇩🇪 [Deutsch](./de/VM_DEPLOYMENT_GUIDE.md) | 🇮🇳 [हिन्दी](./in/VM_DEPLOYMENT_GUIDE.md) | 🇹🇭 [ไทย](./th/VM_DEPLOYMENT_GUIDE.md) | 🇺🇦 [Українська](./uk-UA/VM_DEPLOYMENT_GUIDE.md) | 🇸🇦 [العربية](./ar/VM_DEPLOYMENT_GUIDE.md) | 🇯🇵 [日本語](./ja/VM_DEPLOYMENT_GUIDE.md) | 🇻🇳 [Tiếng Việt](./vi/VM_DEPLOYMENT_GUIDE.md) | 🇧🇬 [Български](./bg/VM_DEPLOYMENT_GUIDE.md) | 🇩🇰 [Dansk](./da/VM_DEPLOYMENT_GUIDE.md) | 🇫🇮 [Suomi](./fi/VM_DEPLOYMENT_GUIDE.md) | 🇮🇱 [עברית](./he/VM_DEPLOYMENT_GUIDE.md) | 🇭🇺 [Magyar](./hu/VM_DEPLOYMENT_GUIDE.md) | 🇮🇩 [Bahasa Indonesia](./id/VM_DEPLOYMENT_GUIDE.md) | 🇰🇷 [한국어](./ko/VM_DEPLOYMENT_GUIDE.md) | 🇲🇾 [Bahasa Melayu](./ms/VM_DEPLOYMENT_GUIDE.md) | 🇳🇱 [Nederlands](./nl/VM_DEPLOYMENT_GUIDE.md) | 🇳🇴 [Norsk](./no/VM_DEPLOYMENT_GUIDE.md) | 🇵🇹 [Português (Portugal)](./pt/VM_DEPLOYMENT_GUIDE.md) | 🇷🇴 [Română](./ro/VM_DEPLOYMENT_GUIDE.md) | 🇵🇱 [Polski](./pl/VM_DEPLOYMENT_GUIDE.md) | 🇸🇰 [Slovenčina](./sk/VM_DEPLOYMENT_GUIDE.md) | 🇸🇪 [Svenska](./sv/VM_DEPLOYMENT_GUIDE.md) | 🇵🇭 [Filipino](./phi/VM_DEPLOYMENT_GUIDE.md) | 🇨🇿 [Čeština](./cs/VM_DEPLOYMENT_GUIDE.md)
---
Generated on 2026-03-19.
- 🇪🇸 **Español** (`es`): [Docs Root](./es/README.md)
- 🇫🇷 **Français** (`fr`): [Docs Root](./fr/README.md)
- 🇩🇪 **Deutsch** (`de`): [Docs Root](./de/README.md)
- 🇮🇹 **Italiano** (`it`): [Docs Root](./it/README.md)
- 🇷🇺 **Русский** (`ru`): [Docs Root](./ru/README.md)
- 🇨🇳 **中文(简体)** (`zh-CN`): [Docs Root](./zh-CN/README.md)
- 🇯🇵 **日本語** (`ja`): [Docs Root](./ja/README.md)
- 🇰🇷 **한국어** (`ko`): [Docs Root](./ko/README.md)
- 🇸🇦 **العربية** (`ar`): [Docs Root](./ar/README.md)
- 🇮🇳 **हिन्दी** (`in`): [Docs Root](./in/README.md)
- 🇹🇭 **ไทย** (`th`): [Docs Root](./th/README.md)
- 🇻🇳 **Tiếng Việt** (`vi`): [Docs Root](./vi/README.md)
- 🇮🇩 **Bahasa Indonesia** (`id`): [Docs Root](./id/README.md)
- 🇲🇾 **Bahasa Melayu** (`ms`): [Docs Root](./ms/README.md)
- 🇳🇱 **Nederlands** (`nl`): [Docs Root](./nl/README.md)
- 🇵🇱 **Polski** (`pl`): [Docs Root](./pl/README.md)
- 🇸🇪 **Svenska** (`sv`): [Docs Root](./sv/README.md)
- 🇳🇴 **Norsk** (`no`): [Docs Root](./no/README.md)
- 🇩🇰 **Dansk** (`da`): [Docs Root](./da/README.md)
- 🇫🇮 **Suomi** (`fi`): [Docs Root](./fi/README.md)
- 🇵🇹 **Português (Portugal)** (`pt`): [Docs Root](./pt/README.md)
- 🇷🇴 **Română** (`ro`): [Docs Root](./ro/README.md)
- 🇭🇺 **Magyar** (`hu`): [Docs Root](./hu/README.md)
- 🇧🇬 **Български** (`bg`): [Docs Root](./bg/README.md)
- 🇸🇰 **Slovenčina** (`sk`): [Docs Root](./sk/README.md)
- 🇺🇦 **Українська** (`uk-UA`): [Docs Root](./uk-UA/README.md)
- 🇮🇱 **עברית** (`he`): [Docs Root](./he/README.md)
- 🇵🇭 **Filipino** (`phi`): [Docs Root](./phi/README.md)
- 🇧🇷 **Português (Brasil)** (`pt-BR`): [Docs Root](./pt-BR/README.md)
+4 -4
View File
@@ -90,7 +90,7 @@ flowchart LR
end
subgraph Upstreams[Upstream Providers]
P1[OAuth Providers\nClaude/Codex/Gemini/Qwen/iFlow/GitHub/Kiro/Cursor/Antigravity]
P1[OAuth Providers\nClaude/Codex/Gemini/Qwen/Qoder/GitHub/Kiro/Cursor/Antigravity]
P2[API Key Providers\nOpenAI/Anthropic/OpenRouter/GLM/Kimi/MiniMax\nDeepSeek/Groq/xAI/Mistral/Perplexity\nTogether/Fireworks/Cerebras/Cohere/NVIDIA]
P3[Compatible Nodes\nOpenAI-compatible / Anthropic-compatible]
end
@@ -224,7 +224,7 @@ Domain layer modules:
OAuth provider modules (12 individual files under `src/lib/oauth/providers/`):
- Registry index: `src/lib/oauth/providers/index.ts`
- Individual providers: `claude.ts`, `codex.ts`, `gemini.ts`, `antigravity.ts`, `iflow.ts`, `qwen.ts`, `kimi-coding.ts`, `github.ts`, `kiro.ts`, `cursor.ts`, `kilocode.ts`, `cline.ts`
- Individual providers: `claude.ts`, `codex.ts`, `gemini.ts`, `antigravity.ts`, `qoder.ts`, `qwen.ts`, `kimi-coding.ts`, `github.ts`, `kiro.ts`, `cursor.ts`, `kilocode.ts`, `cline.ts`
- Thin wrapper: `src/lib/oauth/providers.ts` — re-exports from individual modules
## 3) Persistence Layer
@@ -597,7 +597,7 @@ Each provider has a specialized executor extending `BaseExecutor` (in `open-sse/
| Executor | Provider(s) | Special Handling |
| --------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------- |
| `DefaultExecutor` | OpenAI, Claude, Gemini, Qwen, iFlow, OpenRouter, GLM, Kimi, MiniMax, DeepSeek, Groq, xAI, Mistral, Perplexity, Together, Fireworks, Cerebras, Cohere, NVIDIA | Dynamic URL/header config per provider |
| `DefaultExecutor` | OpenAI, Claude, Gemini, Qwen, Qoder, OpenRouter, GLM, Kimi, MiniMax, DeepSeek, Groq, xAI, Mistral, Perplexity, Together, Fireworks, Cerebras, Cohere, NVIDIA | Dynamic URL/header config per provider |
| `AntigravityExecutor` | Google Antigravity | Custom project/session IDs, Retry-After parsing |
| `CodexExecutor` | OpenAI Codex | Injects system instructions, forces reasoning effort |
| `CursorExecutor` | Cursor IDE | ConnectRPC protocol, Protobuf encoding, request signing via checksum |
@@ -621,7 +621,7 @@ All other providers (including custom compatible nodes) use the `DefaultExecutor
| Cursor | cursor | Custom checksum | ✅ | ✅ | ❌ | ❌ |
| Kiro | kiro | AWS SSO OIDC | ✅ (EventStream) | ❌ | ✅ | ✅ Usage limits |
| Qwen | openai | OAuth | ✅ | ✅ | ✅ | ⚠️ Per request |
| iFlow | openai | OAuth (Basic) | ✅ | ✅ | ✅ | ⚠️ Per request |
| Qoder | openai | OAuth (Basic) | ✅ | ✅ | ✅ | ⚠️ Per request |
| OpenRouter | openai | API Key | ✅ | ✅ | ❌ | ❌ |
| GLM/Kimi/MiniMax | claude | API Key | ✅ | ✅ | ❌ | ❌ |
| DeepSeek | openai | API Key | ✅ | ✅ | ❌ | ❌ |
+2 -2
View File
@@ -271,7 +271,7 @@ Business logic that supports the handlers and executors.
| `provider.ts` | **Format detection** (`detectFormat`): analyzes request body structure to identify Claude/OpenAI/Gemini/Antigravity/Responses formats (includes `max_tokens` heuristic for Claude). Also: URL building, header building, thinking config normalization. Supports `openai-compatible-*` and `anthropic-compatible-*` dynamic providers. |
| `model.ts` | Model string parsing (`claude/model-name``{provider: "claude", model: "model-name"}`), alias resolution with collision detection, input sanitization (rejects path traversal/control chars), and model info resolution with async alias getter support. |
| `accountFallback.ts` | Rate-limit handling: exponential backoff (1s → 2s → 4s → max 2min), account cooldown management, error classification (which errors trigger fallback vs. not). |
| `tokenRefresh.ts` | OAuth token refresh for **every provider**: Google (Gemini, Antigravity), Claude, Codex, Qwen, iFlow, GitHub (OAuth + Copilot dual-token), Kiro (AWS SSO OIDC + Social Auth). Includes in-flight promise deduplication cache and retry with exponential backoff. |
| `tokenRefresh.ts` | OAuth token refresh for **every provider**: Google (Gemini, Antigravity), Claude, Codex, Qwen, Qoder, GitHub (OAuth + Copilot dual-token), Kiro (AWS SSO OIDC + Social Auth). Includes in-flight promise deduplication cache and retry with exponential backoff. |
| `combo.ts` | **Combo models**: chains of fallback models. If model A fails with a fallback-eligible error, try model B, then C, etc. Returns actual upstream status codes. |
| `usage.ts` | Fetches quota/usage data from provider APIs (GitHub Copilot quotas, Antigravity model quotas, Codex rate limits, Kiro usage breakdowns, Claude settings). |
| `accountSelector.ts` | Smart account selection with scoring algorithm: considers priority, health status, round-robin position, and cooldown state to pick the optimal account for each request. |
@@ -543,7 +543,7 @@ A 2000-token buffer is added to reported usage to prevent clients from hitting c
| Kiro (AWS) | AWS SSO OIDC or Social | Kiro | Binary EventStream parsing |
| Cursor IDE | Checksum auth | Cursor | Protobuf encoding, SHA-256 checksums |
| Qwen | OAuth | Default | Standard auth |
| iFlow | OAuth (Basic + Bearer) | Default | Dual auth header |
| Qoder | OAuth (Basic + Bearer) | Default | Dual auth header |
| OpenRouter | API key | Default | Standard Bearer auth |
| GLM, Kimi, MiniMax | API key | Default | Claude-compatible, use `x-api-key` |
| `openai-compatible-*` | API key | Default | Dynamic: any OpenAI-compatible endpoint |
+2 -2
View File
@@ -12,7 +12,7 @@ Visual guide to every section of the OmniRoute dashboard.
## 🔌 Providers
Manage AI provider connections: OAuth providers (Claude Code, Codex, Gemini CLI), API key providers (Groq, DeepSeek, OpenRouter), and free providers (iFlow, Qwen, Kiro). Kiro accounts include credit balance tracking — remaining credits, total allowance, and renewal date visible in Dashboard → Usage.
Manage AI provider connections: OAuth providers (Claude Code, Codex, Gemini CLI), API key providers (Groq, DeepSeek, OpenRouter), and free providers (Qoder, Qwen, Kiro). Kiro accounts include credit balance tracking — remaining credits, total allowance, and renewal date visible in Dashboard → Usage.
![Providers Dashboard](screenshots/01-providers.png)
@@ -67,7 +67,7 @@ Customizable color themes for the entire dashboard. Choose from 7 preset colors
Comprehensive settings panel with tabs:
- **General** — System storage, backup management (export/import database)
- **Appearance** — Theme selector (dark/light/system), color theme presets and custom colors, health log visibility
- **Appearance** — Theme selector (dark/light/system), color theme presets and custom colors, health log visibility, sidebar item visibility controls
- **Security** — API endpoint protection, custom provider blocking, IP filtering, session info
- **Routing** — Model aliases, background task degradation
- **Resilience** — Rate limit persistence, circuit breaker tuning
+1190 -713
View File
File diff suppressed because it is too large Load Diff
+1 -1
View File
@@ -101,7 +101,7 @@ curl -s http://localhost:20128/api/cli-tools/openclaw-settings | jq '{installed,
1. Check usage stats in Dashboard → Usage
2. Switch primary model to GLM/MiniMax
3. Use free tier (Gemini CLI, iFlow) for non-critical tasks
3. Use free tier (Gemini CLI, Qoder) for non-critical tasks
4. Set cost budgets per API key: Dashboard → API Keys → Budget
---
+127 -11
View File
@@ -1,11 +1,11 @@
🌐 **Languages:** 🇺🇸 [English](../../README.md) · 🇧🇷 [pt-BR](../pt-BR/USER_GUIDE.md) · 🇪🇸 [es](../es/USER_GUIDE.md) · 🇫🇷 [fr](../fr/USER_GUIDE.md) · 🇩🇪 [de](../de/USER_GUIDE.md) · 🇮🇹 [it](../it/USER_GUIDE.md) · 🇷🇺 [ru](../ru/USER_GUIDE.md) · 🇨🇳 [zh-CN](../zh-CN/USER_GUIDE.md) · 🇯🇵 [ja](../ja/USER_GUIDE.md) · 🇰🇷 [ko](../ko/USER_GUIDE.md) · 🇸🇦 [ar](../ar/USER_GUIDE.md) · 🇮🇳 [in](../in/USER_GUIDE.md) · 🇹🇭 [th](../th/USER_GUIDE.md) · 🇻🇳 [vi](../vi/USER_GUIDE.md) · 🇮🇩 [id](../id/USER_GUIDE.md) · 🇲🇾 [ms](../ms/USER_GUIDE.md) · 🇳🇱 [nl](../nl/USER_GUIDE.md) · 🇵🇱 [pl](../pl/USER_GUIDE.md) · 🇸🇪 [sv](../sv/USER_GUIDE.md) · 🇳🇴 [no](../no/USER_GUIDE.md) · 🇩🇰 [da](../da/USER_GUIDE.md) · 🇫🇮 [fi](../fi/USER_GUIDE.md) · 🇵🇹 [pt](../pt/USER_GUIDE.md) · 🇷🇴 [ro](../ro/USER_GUIDE.md) · 🇭🇺 [hu](../hu/USER_GUIDE.md) · 🇧🇬 [bg](../bg/USER_GUIDE.md) · 🇸🇰 [sk](../sk/USER_GUIDE.md) · 🇺🇦 [uk-UA](../uk-UA/USER_GUIDE.md) · 🇮🇱 [he](../he/USER_GUIDE.md) · 🇵🇭 [phi](../phi/USER_GUIDE.md)
# User Guide (العربية)
🌐 **Languages:** 🇺🇸 [English](../../USER_GUIDE.md) · 🇧🇷 [pt-BR](../pt-BR/USER_GUIDE.md) · 🇪🇸 [es](../es/USER_GUIDE.md) · 🇫🇷 [fr](../fr/USER_GUIDE.md) · 🇩🇪 [de](../de/USER_GUIDE.md) · 🇮🇹 [it](../it/USER_GUIDE.md) · 🇷🇺 [ru](../ru/USER_GUIDE.md) · 🇨🇳 [zh-CN](../zh-CN/USER_GUIDE.md) · 🇯🇵 [ja](../ja/USER_GUIDE.md) · 🇰🇷 [ko](../ko/USER_GUIDE.md) · 🇸🇦 [ar](../ar/USER_GUIDE.md) · 🇮🇳 [in](../in/USER_GUIDE.md) · 🇹🇭 [th](../th/USER_GUIDE.md) · 🇻🇳 [vi](../vi/USER_GUIDE.md) · 🇮🇩 [id](../id/USER_GUIDE.md) · 🇲🇾 [ms](../ms/USER_GUIDE.md) · 🇳🇱 [nl](../nl/USER_GUIDE.md) · 🇵🇱 [pl](../pl/USER_GUIDE.md) · 🇸🇪 [sv](../sv/USER_GUIDE.md) · 🇳🇴 [no](../no/USER_GUIDE.md) · 🇩🇰 [da](../da/USER_GUIDE.md) · 🇫🇮 [fi](../fi/USER_GUIDE.md) · 🇵🇹 [pt](../pt/USER_GUIDE.md) · 🇷🇴 [ro](../ro/USER_GUIDE.md) · 🇭🇺 [hu](../hu/USER_GUIDE.md) · 🇧🇬 [bg](../bg/USER_GUIDE.md) · 🇸🇰 [sk](../sk/USER_GUIDE.md) · 🇺🇦 [uk-UA](../uk-UA/USER_GUIDE.md) · 🇮🇱 [he](../he/USER_GUIDE.md) · 🇵🇭 [phi](../phi/USER_GUIDE.md)
> 🇺🇸 [English](../../USER_GUIDE.md)
---
# User Guide
🌐 **Languages:** 🇺🇸 [English](USER_GUIDE.md) | 🇧🇷 [Português (Brasil)](i18n/pt-BR/USER_GUIDE.md) | 🇪🇸 [Español](i18n/es/USER_GUIDE.md) | 🇫🇷 [Français](i18n/fr/USER_GUIDE.md) | 🇮🇹 [Italiano](i18n/it/USER_GUIDE.md) | 🇷🇺 [Русский](i18n/ru/USER_GUIDE.md) | 🇨🇳 [中文 (简体)](i18n/zh-CN/USER_GUIDE.md) | 🇩🇪 [Deutsch](i18n/de/USER_GUIDE.md) | 🇮🇳 [हिन्दी](i18n/in/USER_GUIDE.md) | 🇹🇭 [ไทย](i18n/th/USER_GUIDE.md) | 🇺🇦 [Українська](i18n/uk-UA/USER_GUIDE.md) | 🇸🇦 [العربية](i18n/ar/USER_GUIDE.md) | 🇯🇵 [日本語](i18n/ja/USER_GUIDE.md) | 🇻🇳 [Tiếng Việt](i18n/vi/USER_GUIDE.md) | 🇧🇬 [Български](i18n/bg/USER_GUIDE.md) | 🇩🇰 [Dansk](i18n/da/USER_GUIDE.md) | 🇫🇮 [Suomi](i18n/fi/USER_GUIDE.md) | 🇮🇱 [עברית](i18n/he/USER_GUIDE.md) | 🇭🇺 [Magyar](i18n/hu/USER_GUIDE.md) | 🇮🇩 [Bahasa Indonesia](i18n/id/USER_GUIDE.md) | 🇰🇷 [한국어](i18n/ko/USER_GUIDE.md) | 🇲🇾 [Bahasa Melayu](i18n/ms/USER_GUIDE.md) | 🇳🇱 [Nederlands](i18n/nl/USER_GUIDE.md) | 🇳🇴 [Norsk](i18n/no/USER_GUIDE.md) | 🇵🇹 [Português (Portugal)](i18n/pt/USER_GUIDE.md) | 🇷🇴 [Română](i18n/ro/USER_GUIDE.md) | 🇵🇱 [Polski](i18n/pl/USER_GUIDE.md) | 🇸🇰 [Slovenčina](i18n/sk/USER_GUIDE.md) | 🇸🇪 [Svenska](i18n/sv/USER_GUIDE.md) | 🇵🇭 [Filipino](i18n/phi/USER_GUIDE.md)
Complete guide for configuring providers, creating combos, integrating CLI tools, and deploying OmniRoute.
---
@@ -43,11 +43,11 @@ Complete guide for configuring providers, creating combos, integrating CLI tools
| **💰 CHEAP** | GLM-4.7 | $0.6/1M | Daily 10AM | Budget backup |
| | MiniMax M2.1 | $0.2/1M | 5-hour rolling | Cheapest option |
| | Kimi K2 | $9/mo flat | 10M tokens/mo | Predictable cost |
| **🆓 FREE** | iFlow | $0 | Unlimited | 8 models free |
| **🆓 FREE** | Qoder | $0 | Unlimited | 8 models free |
| | Qwen | $0 | Unlimited | 3 models free |
| | Kiro | $0 | Unlimited | Claude free |
**💡 Pro Tip:** Start with Gemini CLI (180K free/month) + iFlow (unlimited free) combo = $0 cost!
**💡 Pro Tip:** Start with Gemini CLI (180K free/month) + Qoder (unlimited free) combo = $0 cost!
---
@@ -197,10 +197,10 @@ Models:
### 🆓 FREE Providers
#### iFlow (8 FREE models)
#### Qoder (8 FREE models)
```bash
Dashboard → Connect iFlow → OAuth login → Unlimited usage
Dashboard → Connect Qoder → OAuth login → Unlimited usage
Models: if/kimi-k2-thinking, if/qwen3-coder-plus, if/glm-4.7, if/minimax-m2, if/deepseek-r1
```
@@ -409,6 +409,106 @@ docker run -d --name omniroute -p 20128:20128 --env-file ./.env -v omniroute-dat
For host-integrated mode with CLI binaries, see the Docker section in the main docs.
### Void Linux (xbps-src)
Void Linux users can package and install OmniRoute natively using the `xbps-src` cross-compilation framework. This automates the Node.js standalone build along with the required `better-sqlite3` native bindings.
<details>
<summary><b>View xbps-src template</b></summary>
```bash
# Template file for 'omniroute'
pkgname=omniroute
version=3.2.4
revision=1
hostmakedepends="nodejs python3 make"
depends="openssl"
short_desc="Universal AI gateway with smart routing for multiple LLM providers"
maintainer="zenobit <zenobit@disroot.org>"
license="MIT"
homepage="https://github.com/diegosouzapw/OmniRoute"
distfiles="https://github.com/diegosouzapw/OmniRoute/archive/refs/tags/v${version}.tar.gz"
checksum=009400afee90a9f32599d8fe734145cfd84098140b7287990183dde45ae2245b
system_accounts="_omniroute"
omniroute_homedir="/var/lib/omniroute"
export NODE_ENV=production
export npm_config_engine_strict=false
export npm_config_loglevel=error
export npm_config_fund=false
export npm_config_audit=false
do_build() {
# Determine target CPU arch for node-gyp
local _gyp_arch
case "$XBPS_TARGET_MACHINE" in
aarch64*) _gyp_arch=arm64 ;;
armv7*|armv6*) _gyp_arch=arm ;;
i686*) _gyp_arch=ia32 ;;
*) _gyp_arch=x64 ;;
esac
# 1) Install all deps skip scripts
NODE_ENV=development npm ci --ignore-scripts
# 2) Build the Next.js standalone bundle
npm run build
# 3) Copy static assets into standalone
cp -r .next/static .next/standalone/.next/static
[ -d public ] && cp -r public .next/standalone/public || true
# 4) Compile better-sqlite3 native binding
local _node_gyp=/usr/lib/node_modules/npm/node_modules/node-gyp/bin/node-gyp.js
(cd node_modules/better-sqlite3 && node "$_node_gyp" rebuild --arch="$_gyp_arch")
# 5) Place the compiled binding into the standalone bundle
local _bs3_release=.next/standalone/node_modules/better-sqlite3/build/Release
mkdir -p "$_bs3_release"
cp node_modules/better-sqlite3/build/Release/better_sqlite3.node "$_bs3_release/"
# 6) Remove arch-specific sharp bundles
rm -rf .next/standalone/node_modules/@img
# 7) Copy pino runtime deps omitted by Next.js static analysis:
for _mod in pino-abstract-transport split2 process-warning; do
cp -r "node_modules/$_mod" .next/standalone/node_modules/
done
}
do_check() {
npm run test:unit
}
do_install() {
vmkdir usr/lib/omniroute/.next
vcopy .next/standalone/. usr/lib/omniroute/.next/standalone
# Prevent removal of empty Next.js app router dirs by the post-install hook
for _d in \
.next/standalone/.next/server/app/dashboard \
.next/standalone/.next/server/app/dashboard/settings \
.next/standalone/.next/server/app/dashboard/providers; do
touch "${DESTDIR}/usr/lib/omniroute/${_d}/.keep"
done
cat > "${WRKDIR}/omniroute" <<'EOF'
#!/bin/sh
export PORT="${PORT:-20128}"
export DATA_DIR="${DATA_DIR:-${XDG_DATA_HOME:-${HOME}/.local/share}/omniroute}"
export LOG_TO_FILE="${LOG_TO_FILE:-false}"
mkdir -p "${DATA_DIR}"
exec node /usr/lib/omniroute/.next/standalone/server.js "$@"
EOF
vbin "${WRKDIR}/omniroute"
}
post_install() {
vlicense LICENSE
}
```
</details>
### Environment Variables
| Variable | Default | Description |
@@ -450,7 +550,7 @@ For the full environment variable reference, see the [README](../README.md).
**MiniMax (`minimax/`)** — $0.2/1M: `minimax/MiniMax-M2.1`
**iFlow (`if/`)** — FREE: `if/kimi-k2-thinking`, `if/qwen3-coder-plus`, `if/deepseek-r1`
**Qoder (`if/`)** — FREE: `if/kimi-k2-thinking`, `if/qwen3-coder-plus`, `if/deepseek-r1`
**Qwen (`qw/`)** — FREE: `qw/qwen3-coder-plus`, `qw/qwen3-coder-flash`
@@ -582,6 +682,22 @@ Configure via **Dashboard → Settings → Routing**.
| **Least Used** | Routes to the account with the oldest `lastUsedAt` timestamp, distributing traffic evenly |
| **Cost Optimized** | Routes to the account with the lowest priority value, optimizing for lowest-cost providers |
#### External Sticky Session Header
For external session affinity (for example, Claude Code/Codex agents behind reverse proxies), send:
```http
X-Session-Id: your-session-key
```
OmniRoute also accepts `x_session_id` and returns the effective session key in `X-OmniRoute-Session-Id`.
If you use Nginx and send underscore-form headers, enable:
```nginx
underscores_in_headers on;
```
#### Wildcard Model Aliases
Create wildcard patterns to remap model names:
@@ -766,7 +882,7 @@ Access via **Dashboard → Health**. Real-time system health overview with 6 car
OmniRoute is available as a native desktop application for Windows, macOS, and Linux.
### Installation
### تثبيت
```bash
# From the electron directory:
+145
View File
@@ -0,0 +1,145 @@
# OmniRoute — Dashboard Features Gallery (العربية)
🌐 **Languages:** 🇺🇸 [English](../../../../docs/FEATURES.md) · 🇪🇸 [es](../../es/docs/FEATURES.md) · 🇫🇷 [fr](../../fr/docs/FEATURES.md) · 🇩🇪 [de](../../de/docs/FEATURES.md) · 🇮🇹 [it](../../it/docs/FEATURES.md) · 🇷🇺 [ru](../../ru/docs/FEATURES.md) · 🇨🇳 [zh-CN](../../zh-CN/docs/FEATURES.md) · 🇯🇵 [ja](../../ja/docs/FEATURES.md) · 🇰🇷 [ko](../../ko/docs/FEATURES.md) · 🇸🇦 [ar](../../ar/docs/FEATURES.md) · 🇮🇳 [in](../../in/docs/FEATURES.md) · 🇹🇭 [th](../../th/docs/FEATURES.md) · 🇻🇳 [vi](../../vi/docs/FEATURES.md) · 🇮🇩 [id](../../id/docs/FEATURES.md) · 🇲🇾 [ms](../../ms/docs/FEATURES.md) · 🇳🇱 [nl](../../nl/docs/FEATURES.md) · 🇵🇱 [pl](../../pl/docs/FEATURES.md) · 🇸🇪 [sv](../../sv/docs/FEATURES.md) · 🇳🇴 [no](../../no/docs/FEATURES.md) · 🇩🇰 [da](../../da/docs/FEATURES.md) · 🇫🇮 [fi](../../fi/docs/FEATURES.md) · 🇵🇹 [pt](../../pt/docs/FEATURES.md) · 🇷🇴 [ro](../../ro/docs/FEATURES.md) · 🇭🇺 [hu](../../hu/docs/FEATURES.md) · 🇧🇬 [bg](../../bg/docs/FEATURES.md) · 🇸🇰 [sk](../../sk/docs/FEATURES.md) · 🇺🇦 [uk-UA](../../uk-UA/docs/FEATURES.md) · 🇮🇱 [he](../../he/docs/FEATURES.md) · 🇵🇭 [phi](../../phi/docs/FEATURES.md) · 🇧🇷 [pt-BR](../../pt-BR/docs/FEATURES.md)
---
Visual guide to every section of the OmniRoute dashboard.
---
## 🔌 Providers
Manage AI provider connections: OAuth providers (Claude Code, Codex, Gemini CLI), API key providers (Groq, DeepSeek, OpenRouter), and free providers (iFlow, Qwen, Kiro). Kiro accounts include credit balance tracking — remaining credits, total allowance, and renewal date visible in Dashboard → Usage.
![Providers Dashboard](screenshots/01-providers.png)
---
## 🎨 Combos
Create model routing combos with 6 strategies: priority, weighted, round-robin, random, least-used, and cost-optimized. Each combo chains multiple models with automatic fallback and includes quick templates and readiness checks.
![Combos Dashboard](screenshots/02-combos.png)
---
## 📊 Analytics
Comprehensive usage analytics with token consumption, cost estimates, activity heatmaps, weekly distribution charts, and per-provider breakdowns.
![Analytics Dashboard](screenshots/03-analytics.png)
---
## 🏥 System Health
Real-time monitoring: uptime, memory, version, latency percentiles (p50/p95/p99), cache statistics, and provider circuit breaker states.
![Health Dashboard](screenshots/04-health.png)
---
## 🔧 Translator Playground
Four modes for debugging API translations: **Playground** (format converter), **Chat Tester** (live requests), **Test Bench** (batch tests), and **Live Monitor** (real-time stream).
![Translator Playground](screenshots/05-translator.png)
---
## 🎮 Model Playground _(v2.0.9+)_
Test any model directly from the dashboard. Select provider, model, and endpoint, write prompts with Monaco Editor, stream responses in real-time, abort mid-stream, and view timing metrics.
---
## 🎨 Themes _(v2.0.5+)_
Customizable color themes for the entire dashboard. Choose from 7 preset colors (Coral, Blue, Red, Green, Violet, Orange, Cyan) or create a custom theme by picking any hex color. Supports light, dark, and system mode.
---
## ⚙️ Settings
Comprehensive settings panel with tabs:
- **General** — System storage, backup management (export/import database)
- **Appearance** — Theme selector (dark/light/system), color theme presets and custom colors, health log visibility, sidebar item visibility controls
- **Security** — API endpoint protection, custom provider blocking, IP filtering, session info
- **Routing** — Model aliases, background task degradation
- **Resilience** — Rate limit persistence, circuit breaker tuning, auto-disable banned accounts, provider expiration monitoring
- **Advanced** — Configuration overrides, configuration audit trail, fallback degradation mode
![Settings Dashboard](screenshots/06-settings.png)
---
## 🔧 CLI Tools
One-click configuration for AI coding tools: Claude Code, Codex CLI, Gemini CLI, OpenClaw, Kilo Code, Antigravity, Cline, Continue, Cursor, and Factory Droid. Features automated config apply/reset, connection profiles, and model mapping.
![CLI Tools Dashboard](screenshots/07-cli-tools.png)
---
## 🤖 CLI Agents _(v2.0.11+)_
Dashboard for discovering and managing CLI agents. Shows a grid of 14 built-in agents (Codex, Claude, Goose, Gemini CLI, OpenClaw, Aider, OpenCode, Cline, Qwen Code, ForgeCode, Amazon Q, Open Interpreter, Cursor CLI, Warp) with:
- **Installation status** — Installed / Not Found with version detection
- **Protocol badges** — stdio, HTTP, etc.
- **Custom agents** — Register any CLI tool via form (name, binary, version command, spawn args)
- **CLI Fingerprint Matching** — Per-provider toggle to match native CLI request signatures, reducing ban risk while preserving proxy IP
---
## 🖼️ Media _(v2.0.3+)_
Generate images, videos, and music from the dashboard. Supports OpenAI, xAI, Together, Hyperbolic, SD WebUI, ComfyUI, AnimateDiff, Stable Audio Open, and MusicGen.
---
## 📝 Request Logs
Real-time request logging with filtering by provider, model, account, and API key. Shows status codes, token usage, latency, and response details.
![Usage Logs](screenshots/08-usage.png)
---
## 🌐 API Endpoint
Your unified API endpoint with capability breakdown: Chat Completions, Responses API, Embeddings, Image Generation, Reranking, Audio Transcription, Text-to-Speech, Moderations, and registered API keys. Cloudflare Quick Tunnel integration and cloud proxy support for remote access.
![Endpoint Dashboard](screenshots/09-endpoint.png)
---
## 🔑 API Key Management
Create, scope, and revoke API keys. Each key can be restricted to specific models/providers with full access or read-only permissions. Visual key management with usage tracking.
---
## 📋 Audit Log
Administrative action tracking with filtering by action type, actor, target, IP address, and timestamp. Full security event history.
---
## 🖥️ Desktop Application
Native Electron desktop app for Windows, macOS, and Linux. Run OmniRoute as a standalone application with system tray integration, offline support, auto-update, and one-click install.
Key features:
- Server readiness polling (no blank screen on cold start)
- System tray with port management
- Content Security Policy
- Single-instance lock
- Auto-update on restart
- Platform-conditional UI (macOS traffic lights, Windows/Linux default titlebar)
- Hardened Electron build packaging — symlinked `node_modules` in the standalone bundle is detected and rejected before packaging, preventing runtime dependency on the build machine (v2.5.5+)
📖 See [`electron/README.md`](../electron/README.md) for full documentation.
+4 -4
View File
@@ -90,7 +90,7 @@ flowchart LR
end
subgraph Upstreams[Upstream Providers]
P1[OAuth Providers\nClaude/Codex/Gemini/Qwen/iFlow/GitHub/Kiro/Cursor/Antigravity]
P1[OAuth Providers\nClaude/Codex/Gemini/Qwen/Qoder/GitHub/Kiro/Cursor/Antigravity]
P2[API Key Providers\nOpenAI/Anthropic/OpenRouter/GLM/Kimi/MiniMax\nDeepSeek/Groq/xAI/Mistral/Perplexity\nTogether/Fireworks/Cerebras/Cohere/NVIDIA]
P3[Compatible Nodes\nOpenAI-compatible / Anthropic-compatible]
end
@@ -224,7 +224,7 @@ Domain layer modules:
OAuth provider modules (12 individual files under `src/lib/oauth/providers/`):
- Registry index: `src/lib/oauth/providers/index.ts`
- Individual providers: `claude.ts`, `codex.ts`, `gemini.ts`, `antigravity.ts`, `iflow.ts`, `qwen.ts`, `kimi-coding.ts`, `github.ts`, `kiro.ts`, `cursor.ts`, `kilocode.ts`, `cline.ts`
- Individual providers: `claude.ts`, `codex.ts`, `gemini.ts`, `antigravity.ts`, `qoder.ts`, `qwen.ts`, `kimi-coding.ts`, `github.ts`, `kiro.ts`, `cursor.ts`, `kilocode.ts`, `cline.ts`
- Thin wrapper: `src/lib/oauth/providers.ts` — re-exports from individual modules
## 3) Persistence Layer
@@ -597,7 +597,7 @@ Each provider has a specialized executor extending `BaseExecutor` (in `open-sse/
| Executor | Provider(s) | Special Handling |
| --------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------- |
| `DefaultExecutor` | OpenAI, Claude, Gemini, Qwen, iFlow, OpenRouter, GLM, Kimi, MiniMax, DeepSeek, Groq, xAI, Mistral, Perplexity, Together, Fireworks, Cerebras, Cohere, NVIDIA | Dynamic URL/header config per provider |
| `DefaultExecutor` | OpenAI, Claude, Gemini, Qwen, Qoder, OpenRouter, GLM, Kimi, MiniMax, DeepSeek, Groq, xAI, Mistral, Perplexity, Together, Fireworks, Cerebras, Cohere, NVIDIA | Dynamic URL/header config per provider |
| `AntigravityExecutor` | Google Antigravity | Custom project/session IDs, Retry-After parsing |
| `CodexExecutor` | OpenAI Codex | Injects system instructions, forces reasoning effort |
| `CursorExecutor` | Cursor IDE | ConnectRPC protocol, Protobuf encoding, request signing via checksum |
@@ -621,7 +621,7 @@ All other providers (including custom compatible nodes) use the `DefaultExecutor
| Cursor | cursor | Custom checksum | ✅ | ✅ | ❌ | ❌ |
| Kiro | kiro | AWS SSO OIDC | ✅ (EventStream) | ❌ | ✅ | ✅ Usage limits |
| Qwen | openai | OAuth | ✅ | ✅ | ✅ | ⚠️ Per request |
| iFlow | openai | OAuth (Basic) | ✅ | ✅ | ✅ | ⚠️ Per request |
| Qoder | openai | OAuth (Basic) | ✅ | ✅ | ✅ | ⚠️ Per request |
| OpenRouter | openai | API Key | ✅ | ✅ | ❌ | ❌ |
| GLM/Kimi/MiniMax | claude | API Key | ✅ | ✅ | ❌ | ❌ |
| DeepSeek | openai | API Key | ✅ | ✅ | ❌ | ❌ |
+2 -2
View File
@@ -271,7 +271,7 @@ Business logic that supports the handlers and executors.
| `provider.ts` | **Format detection** (`detectFormat`): analyzes request body structure to identify Claude/OpenAI/Gemini/Antigravity/Responses formats (includes `max_tokens` heuristic for Claude). Also: URL building, header building, thinking config normalization. Supports `openai-compatible-*` and `anthropic-compatible-*` dynamic providers. |
| `model.ts` | Model string parsing (`claude/model-name``{provider: "claude", model: "model-name"}`), alias resolution with collision detection, input sanitization (rejects path traversal/control chars), and model info resolution with async alias getter support. |
| `accountFallback.ts` | Rate-limit handling: exponential backoff (1s → 2s → 4s → max 2min), account cooldown management, error classification (which errors trigger fallback vs. not). |
| `tokenRefresh.ts` | OAuth token refresh for **every provider**: Google (Gemini, Antigravity), Claude, Codex, Qwen, iFlow, GitHub (OAuth + Copilot dual-token), Kiro (AWS SSO OIDC + Social Auth). Includes in-flight promise deduplication cache and retry with exponential backoff. |
| `tokenRefresh.ts` | OAuth token refresh for **every provider**: Google (Gemini, Antigravity), Claude, Codex, Qwen, Qoder, GitHub (OAuth + Copilot dual-token), Kiro (AWS SSO OIDC + Social Auth). Includes in-flight promise deduplication cache and retry with exponential backoff. |
| `combo.ts` | **Combo models**: chains of fallback models. If model A fails with a fallback-eligible error, try model B, then C, etc. Returns actual upstream status codes. |
| `usage.ts` | Fetches quota/usage data from provider APIs (GitHub Copilot quotas, Antigravity model quotas, Codex rate limits, Kiro usage breakdowns, Claude settings). |
| `accountSelector.ts` | Smart account selection with scoring algorithm: considers priority, health status, round-robin position, and cooldown state to pick the optimal account for each request. |
@@ -543,7 +543,7 @@ A 2000-token buffer is added to reported usage to prevent clients from hitting c
| Kiro (AWS) | AWS SSO OIDC or Social | Kiro | Binary EventStream parsing |
| Cursor IDE | Checksum auth | Cursor | Protobuf encoding, SHA-256 checksums |
| Qwen | OAuth | Default | Standard auth |
| iFlow | OAuth (Basic + Bearer) | Default | Dual auth header |
| Qoder | OAuth (Basic + Bearer) | Default | Dual auth header |
| OpenRouter | API key | Default | Standard Bearer auth |
| GLM, Kimi, MiniMax | API key | Default | Claude-compatible, use `x-api-key` |
| `openai-compatible-*` | API key | Default | Dynamic: any OpenAI-compatible endpoint |
+2 -2
View File
@@ -12,7 +12,7 @@ Visual guide to every section of the OmniRoute dashboard.
## 🔌 Providers
Manage AI provider connections: OAuth providers (Claude Code, Codex, Gemini CLI), API key providers (Groq, DeepSeek, OpenRouter), and free providers (iFlow, Qwen, Kiro). Kiro accounts include credit balance tracking — remaining credits, total allowance, and renewal date visible in Dashboard → Usage.
Manage AI provider connections: OAuth providers (Claude Code, Codex, Gemini CLI), API key providers (Groq, DeepSeek, OpenRouter), and free providers (Qoder, Qwen, Kiro). Kiro accounts include credit balance tracking — remaining credits, total allowance, and renewal date visible in Dashboard → Usage.
![Providers Dashboard](screenshots/01-providers.png)
@@ -67,7 +67,7 @@ Customizable color themes for the entire dashboard. Choose from 7 preset colors
Comprehensive settings panel with tabs:
- **General** — System storage, backup management (export/import database)
- **Appearance** — Theme selector (dark/light/system), color theme presets and custom colors, health log visibility
- **Appearance** — Theme selector (dark/light/system), color theme presets and custom colors, health log visibility, sidebar item visibility controls
- **Security** — API endpoint protection, custom provider blocking, IP filtering, session info
- **Routing** — Model aliases, background task degradation
- **Resilience** — Rate limit persistence, circuit breaker tuning
+1167 -698
View File
File diff suppressed because it is too large Load Diff
+1 -1
View File
@@ -101,7 +101,7 @@ curl -s http://localhost:20128/api/cli-tools/openclaw-settings | jq '{installed,
1. Check usage stats in Dashboard → Usage
2. Switch primary model to GLM/MiniMax
3. Use free tier (Gemini CLI, iFlow) for non-critical tasks
3. Use free tier (Gemini CLI, Qoder) for non-critical tasks
4. Set cost budgets per API key: Dashboard → API Keys → Budget
---
+127 -11
View File
@@ -1,11 +1,11 @@
🌐 **Languages:** 🇺🇸 [English](../../README.md) · 🇧🇷 [pt-BR](../pt-BR/USER_GUIDE.md) · 🇪🇸 [es](../es/USER_GUIDE.md) · 🇫🇷 [fr](../fr/USER_GUIDE.md) · 🇩🇪 [de](../de/USER_GUIDE.md) · 🇮🇹 [it](../it/USER_GUIDE.md) · 🇷🇺 [ru](../ru/USER_GUIDE.md) · 🇨🇳 [zh-CN](../zh-CN/USER_GUIDE.md) · 🇯🇵 [ja](../ja/USER_GUIDE.md) · 🇰🇷 [ko](../ko/USER_GUIDE.md) · 🇸🇦 [ar](../ar/USER_GUIDE.md) · 🇮🇳 [in](../in/USER_GUIDE.md) · 🇹🇭 [th](../th/USER_GUIDE.md) · 🇻🇳 [vi](../vi/USER_GUIDE.md) · 🇮🇩 [id](../id/USER_GUIDE.md) · 🇲🇾 [ms](../ms/USER_GUIDE.md) · 🇳🇱 [nl](../nl/USER_GUIDE.md) · 🇵🇱 [pl](../pl/USER_GUIDE.md) · 🇸🇪 [sv](../sv/USER_GUIDE.md) · 🇳🇴 [no](../no/USER_GUIDE.md) · 🇩🇰 [da](../da/USER_GUIDE.md) · 🇫🇮 [fi](../fi/USER_GUIDE.md) · 🇵🇹 [pt](../pt/USER_GUIDE.md) · 🇷🇴 [ro](../ro/USER_GUIDE.md) · 🇭🇺 [hu](../hu/USER_GUIDE.md) · 🇧🇬 [bg](../bg/USER_GUIDE.md) · 🇸🇰 [sk](../sk/USER_GUIDE.md) · 🇺🇦 [uk-UA](../uk-UA/USER_GUIDE.md) · 🇮🇱 [he](../he/USER_GUIDE.md) · 🇵🇭 [phi](../phi/USER_GUIDE.md)
# User Guide (Български)
🌐 **Languages:** 🇺🇸 [English](../../USER_GUIDE.md) · 🇧🇷 [pt-BR](../pt-BR/USER_GUIDE.md) · 🇪🇸 [es](../es/USER_GUIDE.md) · 🇫🇷 [fr](../fr/USER_GUIDE.md) · 🇩🇪 [de](../de/USER_GUIDE.md) · 🇮🇹 [it](../it/USER_GUIDE.md) · 🇷🇺 [ru](../ru/USER_GUIDE.md) · 🇨🇳 [zh-CN](../zh-CN/USER_GUIDE.md) · 🇯🇵 [ja](../ja/USER_GUIDE.md) · 🇰🇷 [ko](../ko/USER_GUIDE.md) · 🇸🇦 [ar](../ar/USER_GUIDE.md) · 🇮🇳 [in](../in/USER_GUIDE.md) · 🇹🇭 [th](../th/USER_GUIDE.md) · 🇻🇳 [vi](../vi/USER_GUIDE.md) · 🇮🇩 [id](../id/USER_GUIDE.md) · 🇲🇾 [ms](../ms/USER_GUIDE.md) · 🇳🇱 [nl](../nl/USER_GUIDE.md) · 🇵🇱 [pl](../pl/USER_GUIDE.md) · 🇸🇪 [sv](../sv/USER_GUIDE.md) · 🇳🇴 [no](../no/USER_GUIDE.md) · 🇩🇰 [da](../da/USER_GUIDE.md) · 🇫🇮 [fi](../fi/USER_GUIDE.md) · 🇵🇹 [pt](../pt/USER_GUIDE.md) · 🇷🇴 [ro](../ro/USER_GUIDE.md) · 🇭🇺 [hu](../hu/USER_GUIDE.md) · 🇧🇬 [bg](../bg/USER_GUIDE.md) · 🇸🇰 [sk](../sk/USER_GUIDE.md) · 🇺🇦 [uk-UA](../uk-UA/USER_GUIDE.md) · 🇮🇱 [he](../he/USER_GUIDE.md) · 🇵🇭 [phi](../phi/USER_GUIDE.md)
> 🇺🇸 [English](../../USER_GUIDE.md)
---
# User Guide
🌐 **Languages:** 🇺🇸 [English](USER_GUIDE.md) | 🇧🇷 [Português (Brasil)](i18n/pt-BR/USER_GUIDE.md) | 🇪🇸 [Español](i18n/es/USER_GUIDE.md) | 🇫🇷 [Français](i18n/fr/USER_GUIDE.md) | 🇮🇹 [Italiano](i18n/it/USER_GUIDE.md) | 🇷🇺 [Русский](i18n/ru/USER_GUIDE.md) | 🇨🇳 [中文 (简体)](i18n/zh-CN/USER_GUIDE.md) | 🇩🇪 [Deutsch](i18n/de/USER_GUIDE.md) | 🇮🇳 [हिन्दी](i18n/in/USER_GUIDE.md) | 🇹🇭 [ไทย](i18n/th/USER_GUIDE.md) | 🇺🇦 [Українська](i18n/uk-UA/USER_GUIDE.md) | 🇸🇦 [العربية](i18n/ar/USER_GUIDE.md) | 🇯🇵 [日本語](i18n/ja/USER_GUIDE.md) | 🇻🇳 [Tiếng Việt](i18n/vi/USER_GUIDE.md) | 🇧🇬 [Български](i18n/bg/USER_GUIDE.md) | 🇩🇰 [Dansk](i18n/da/USER_GUIDE.md) | 🇫🇮 [Suomi](i18n/fi/USER_GUIDE.md) | 🇮🇱 [עברית](i18n/he/USER_GUIDE.md) | 🇭🇺 [Magyar](i18n/hu/USER_GUIDE.md) | 🇮🇩 [Bahasa Indonesia](i18n/id/USER_GUIDE.md) | 🇰🇷 [한국어](i18n/ko/USER_GUIDE.md) | 🇲🇾 [Bahasa Melayu](i18n/ms/USER_GUIDE.md) | 🇳🇱 [Nederlands](i18n/nl/USER_GUIDE.md) | 🇳🇴 [Norsk](i18n/no/USER_GUIDE.md) | 🇵🇹 [Português (Portugal)](i18n/pt/USER_GUIDE.md) | 🇷🇴 [Română](i18n/ro/USER_GUIDE.md) | 🇵🇱 [Polski](i18n/pl/USER_GUIDE.md) | 🇸🇰 [Slovenčina](i18n/sk/USER_GUIDE.md) | 🇸🇪 [Svenska](i18n/sv/USER_GUIDE.md) | 🇵🇭 [Filipino](i18n/phi/USER_GUIDE.md)
Complete guide for configuring providers, creating combos, integrating CLI tools, and deploying OmniRoute.
---
@@ -43,11 +43,11 @@ Complete guide for configuring providers, creating combos, integrating CLI tools
| **💰 CHEAP** | GLM-4.7 | $0.6/1M | Daily 10AM | Budget backup |
| | MiniMax M2.1 | $0.2/1M | 5-hour rolling | Cheapest option |
| | Kimi K2 | $9/mo flat | 10M tokens/mo | Predictable cost |
| **🆓 FREE** | iFlow | $0 | Unlimited | 8 models free |
| **🆓 FREE** | Qoder | $0 | Unlimited | 8 models free |
| | Qwen | $0 | Unlimited | 3 models free |
| | Kiro | $0 | Unlimited | Claude free |
**💡 Pro Tip:** Start with Gemini CLI (180K free/month) + iFlow (unlimited free) combo = $0 cost!
**💡 Pro Tip:** Start with Gemini CLI (180K free/month) + Qoder (unlimited free) combo = $0 cost!
---
@@ -197,10 +197,10 @@ Models:
### 🆓 FREE Providers
#### iFlow (8 FREE models)
#### Qoder (8 FREE models)
```bash
Dashboard → Connect iFlow → OAuth login → Unlimited usage
Dashboard → Connect Qoder → OAuth login → Unlimited usage
Models: if/kimi-k2-thinking, if/qwen3-coder-plus, if/glm-4.7, if/minimax-m2, if/deepseek-r1
```
@@ -409,6 +409,106 @@ docker run -d --name omniroute -p 20128:20128 --env-file ./.env -v omniroute-dat
For host-integrated mode with CLI binaries, see the Docker section in the main docs.
### Void Linux (xbps-src)
Void Linux users can package and install OmniRoute natively using the `xbps-src` cross-compilation framework. This automates the Node.js standalone build along with the required `better-sqlite3` native bindings.
<details>
<summary><b>View xbps-src template</b></summary>
```bash
# Template file for 'omniroute'
pkgname=omniroute
version=3.2.4
revision=1
hostmakedepends="nodejs python3 make"
depends="openssl"
short_desc="Universal AI gateway with smart routing for multiple LLM providers"
maintainer="zenobit <zenobit@disroot.org>"
license="MIT"
homepage="https://github.com/diegosouzapw/OmniRoute"
distfiles="https://github.com/diegosouzapw/OmniRoute/archive/refs/tags/v${version}.tar.gz"
checksum=009400afee90a9f32599d8fe734145cfd84098140b7287990183dde45ae2245b
system_accounts="_omniroute"
omniroute_homedir="/var/lib/omniroute"
export NODE_ENV=production
export npm_config_engine_strict=false
export npm_config_loglevel=error
export npm_config_fund=false
export npm_config_audit=false
do_build() {
# Determine target CPU arch for node-gyp
local _gyp_arch
case "$XBPS_TARGET_MACHINE" in
aarch64*) _gyp_arch=arm64 ;;
armv7*|armv6*) _gyp_arch=arm ;;
i686*) _gyp_arch=ia32 ;;
*) _gyp_arch=x64 ;;
esac
# 1) Install all deps skip scripts
NODE_ENV=development npm ci --ignore-scripts
# 2) Build the Next.js standalone bundle
npm run build
# 3) Copy static assets into standalone
cp -r .next/static .next/standalone/.next/static
[ -d public ] && cp -r public .next/standalone/public || true
# 4) Compile better-sqlite3 native binding
local _node_gyp=/usr/lib/node_modules/npm/node_modules/node-gyp/bin/node-gyp.js
(cd node_modules/better-sqlite3 && node "$_node_gyp" rebuild --arch="$_gyp_arch")
# 5) Place the compiled binding into the standalone bundle
local _bs3_release=.next/standalone/node_modules/better-sqlite3/build/Release
mkdir -p "$_bs3_release"
cp node_modules/better-sqlite3/build/Release/better_sqlite3.node "$_bs3_release/"
# 6) Remove arch-specific sharp bundles
rm -rf .next/standalone/node_modules/@img
# 7) Copy pino runtime deps omitted by Next.js static analysis:
for _mod in pino-abstract-transport split2 process-warning; do
cp -r "node_modules/$_mod" .next/standalone/node_modules/
done
}
do_check() {
npm run test:unit
}
do_install() {
vmkdir usr/lib/omniroute/.next
vcopy .next/standalone/. usr/lib/omniroute/.next/standalone
# Prevent removal of empty Next.js app router dirs by the post-install hook
for _d in \
.next/standalone/.next/server/app/dashboard \
.next/standalone/.next/server/app/dashboard/settings \
.next/standalone/.next/server/app/dashboard/providers; do
touch "${DESTDIR}/usr/lib/omniroute/${_d}/.keep"
done
cat > "${WRKDIR}/omniroute" <<'EOF'
#!/bin/sh
export PORT="${PORT:-20128}"
export DATA_DIR="${DATA_DIR:-${XDG_DATA_HOME:-${HOME}/.local/share}/omniroute}"
export LOG_TO_FILE="${LOG_TO_FILE:-false}"
mkdir -p "${DATA_DIR}"
exec node /usr/lib/omniroute/.next/standalone/server.js "$@"
EOF
vbin "${WRKDIR}/omniroute"
}
post_install() {
vlicense LICENSE
}
```
</details>
### Environment Variables
| Variable | Default | Description |
@@ -450,7 +550,7 @@ For the full environment variable reference, see the [README](../README.md).
**MiniMax (`minimax/`)** — $0.2/1M: `minimax/MiniMax-M2.1`
**iFlow (`if/`)** — FREE: `if/kimi-k2-thinking`, `if/qwen3-coder-plus`, `if/deepseek-r1`
**Qoder (`if/`)** — FREE: `if/kimi-k2-thinking`, `if/qwen3-coder-plus`, `if/deepseek-r1`
**Qwen (`qw/`)** — FREE: `qw/qwen3-coder-plus`, `qw/qwen3-coder-flash`
@@ -582,6 +682,22 @@ Configure via **Dashboard → Settings → Routing**.
| **Least Used** | Routes to the account with the oldest `lastUsedAt` timestamp, distributing traffic evenly |
| **Cost Optimized** | Routes to the account with the lowest priority value, optimizing for lowest-cost providers |
#### External Sticky Session Header
For external session affinity (for example, Claude Code/Codex agents behind reverse proxies), send:
```http
X-Session-Id: your-session-key
```
OmniRoute also accepts `x_session_id` and returns the effective session key in `X-OmniRoute-Session-Id`.
If you use Nginx and send underscore-form headers, enable:
```nginx
underscores_in_headers on;
```
#### Wildcard Model Aliases
Create wildcard patterns to remap model names:
@@ -766,7 +882,7 @@ Access via **Dashboard → Health**. Real-time system health overview with 6 car
OmniRoute is available as a native desktop application for Windows, macOS, and Linux.
### Installation
### Инсталиране
```bash
# From the electron directory:
+145
View File
@@ -0,0 +1,145 @@
# OmniRoute — Dashboard Features Gallery (Български)
🌐 **Languages:** 🇺🇸 [English](../../../../docs/FEATURES.md) · 🇪🇸 [es](../../es/docs/FEATURES.md) · 🇫🇷 [fr](../../fr/docs/FEATURES.md) · 🇩🇪 [de](../../de/docs/FEATURES.md) · 🇮🇹 [it](../../it/docs/FEATURES.md) · 🇷🇺 [ru](../../ru/docs/FEATURES.md) · 🇨🇳 [zh-CN](../../zh-CN/docs/FEATURES.md) · 🇯🇵 [ja](../../ja/docs/FEATURES.md) · 🇰🇷 [ko](../../ko/docs/FEATURES.md) · 🇸🇦 [ar](../../ar/docs/FEATURES.md) · 🇮🇳 [in](../../in/docs/FEATURES.md) · 🇹🇭 [th](../../th/docs/FEATURES.md) · 🇻🇳 [vi](../../vi/docs/FEATURES.md) · 🇮🇩 [id](../../id/docs/FEATURES.md) · 🇲🇾 [ms](../../ms/docs/FEATURES.md) · 🇳🇱 [nl](../../nl/docs/FEATURES.md) · 🇵🇱 [pl](../../pl/docs/FEATURES.md) · 🇸🇪 [sv](../../sv/docs/FEATURES.md) · 🇳🇴 [no](../../no/docs/FEATURES.md) · 🇩🇰 [da](../../da/docs/FEATURES.md) · 🇫🇮 [fi](../../fi/docs/FEATURES.md) · 🇵🇹 [pt](../../pt/docs/FEATURES.md) · 🇷🇴 [ro](../../ro/docs/FEATURES.md) · 🇭🇺 [hu](../../hu/docs/FEATURES.md) · 🇧🇬 [bg](../../bg/docs/FEATURES.md) · 🇸🇰 [sk](../../sk/docs/FEATURES.md) · 🇺🇦 [uk-UA](../../uk-UA/docs/FEATURES.md) · 🇮🇱 [he](../../he/docs/FEATURES.md) · 🇵🇭 [phi](../../phi/docs/FEATURES.md) · 🇧🇷 [pt-BR](../../pt-BR/docs/FEATURES.md)
---
Visual guide to every section of the OmniRoute dashboard.
---
## 🔌 Providers
Manage AI provider connections: OAuth providers (Claude Code, Codex, Gemini CLI), API key providers (Groq, DeepSeek, OpenRouter), and free providers (iFlow, Qwen, Kiro). Kiro accounts include credit balance tracking — remaining credits, total allowance, and renewal date visible in Dashboard → Usage.
![Providers Dashboard](screenshots/01-providers.png)
---
## 🎨 Combos
Create model routing combos with 6 strategies: priority, weighted, round-robin, random, least-used, and cost-optimized. Each combo chains multiple models with automatic fallback and includes quick templates and readiness checks.
![Combos Dashboard](screenshots/02-combos.png)
---
## 📊 Analytics
Comprehensive usage analytics with token consumption, cost estimates, activity heatmaps, weekly distribution charts, and per-provider breakdowns.
![Analytics Dashboard](screenshots/03-analytics.png)
---
## 🏥 System Health
Real-time monitoring: uptime, memory, version, latency percentiles (p50/p95/p99), cache statistics, and provider circuit breaker states.
![Health Dashboard](screenshots/04-health.png)
---
## 🔧 Translator Playground
Four modes for debugging API translations: **Playground** (format converter), **Chat Tester** (live requests), **Test Bench** (batch tests), and **Live Monitor** (real-time stream).
![Translator Playground](screenshots/05-translator.png)
---
## 🎮 Model Playground _(v2.0.9+)_
Test any model directly from the dashboard. Select provider, model, and endpoint, write prompts with Monaco Editor, stream responses in real-time, abort mid-stream, and view timing metrics.
---
## 🎨 Themes _(v2.0.5+)_
Customizable color themes for the entire dashboard. Choose from 7 preset colors (Coral, Blue, Red, Green, Violet, Orange, Cyan) or create a custom theme by picking any hex color. Supports light, dark, and system mode.
---
## ⚙️ Settings
Comprehensive settings panel with tabs:
- **General** — System storage, backup management (export/import database)
- **Appearance** — Theme selector (dark/light/system), color theme presets and custom colors, health log visibility, sidebar item visibility controls
- **Security** — API endpoint protection, custom provider blocking, IP filtering, session info
- **Routing** — Model aliases, background task degradation
- **Resilience** — Rate limit persistence, circuit breaker tuning, auto-disable banned accounts, provider expiration monitoring
- **Advanced** — Configuration overrides, configuration audit trail, fallback degradation mode
![Settings Dashboard](screenshots/06-settings.png)
---
## 🔧 CLI Tools
One-click configuration for AI coding tools: Claude Code, Codex CLI, Gemini CLI, OpenClaw, Kilo Code, Antigravity, Cline, Continue, Cursor, and Factory Droid. Features automated config apply/reset, connection profiles, and model mapping.
![CLI Tools Dashboard](screenshots/07-cli-tools.png)
---
## 🤖 CLI Agents _(v2.0.11+)_
Dashboard for discovering and managing CLI agents. Shows a grid of 14 built-in agents (Codex, Claude, Goose, Gemini CLI, OpenClaw, Aider, OpenCode, Cline, Qwen Code, ForgeCode, Amazon Q, Open Interpreter, Cursor CLI, Warp) with:
- **Installation status** — Installed / Not Found with version detection
- **Protocol badges** — stdio, HTTP, etc.
- **Custom agents** — Register any CLI tool via form (name, binary, version command, spawn args)
- **CLI Fingerprint Matching** — Per-provider toggle to match native CLI request signatures, reducing ban risk while preserving proxy IP
---
## 🖼️ Media _(v2.0.3+)_
Generate images, videos, and music from the dashboard. Supports OpenAI, xAI, Together, Hyperbolic, SD WebUI, ComfyUI, AnimateDiff, Stable Audio Open, and MusicGen.
---
## 📝 Request Logs
Real-time request logging with filtering by provider, model, account, and API key. Shows status codes, token usage, latency, and response details.
![Usage Logs](screenshots/08-usage.png)
---
## 🌐 API Endpoint
Your unified API endpoint with capability breakdown: Chat Completions, Responses API, Embeddings, Image Generation, Reranking, Audio Transcription, Text-to-Speech, Moderations, and registered API keys. Cloudflare Quick Tunnel integration and cloud proxy support for remote access.
![Endpoint Dashboard](screenshots/09-endpoint.png)
---
## 🔑 API Key Management
Create, scope, and revoke API keys. Each key can be restricted to specific models/providers with full access or read-only permissions. Visual key management with usage tracking.
---
## 📋 Audit Log
Administrative action tracking with filtering by action type, actor, target, IP address, and timestamp. Full security event history.
---
## 🖥️ Desktop Application
Native Electron desktop app for Windows, macOS, and Linux. Run OmniRoute as a standalone application with system tray integration, offline support, auto-update, and one-click install.
Key features:
- Server readiness polling (no blank screen on cold start)
- System tray with port management
- Content Security Policy
- Single-instance lock
- Auto-update on restart
- Platform-conditional UI (macOS traffic lights, Windows/Linux default titlebar)
- Hardened Electron build packaging — symlinked `node_modules` in the standalone bundle is detected and rejected before packaging, preventing runtime dependency on the build machine (v2.5.5+)
📖 See [`electron/README.md`](../electron/README.md) for full documentation.
+4 -4
View File
@@ -85,7 +85,7 @@ flowchart LR
end
subgraph Upstreams[Upstream Providers]
P1[OAuth Providers\nClaude/Codex/Gemini/Qwen/iFlow/GitHub/Kiro/Cursor/Antigravity]
P1[OAuth Providers\nClaude/Codex/Gemini/Qwen/Qoder/GitHub/Kiro/Cursor/Antigravity]
P2[API Key Providers\nOpenAI/Anthropic/OpenRouter/GLM/Kimi/MiniMax\nDeepSeek/Groq/xAI/Mistral/Perplexity\nTogether/Fireworks/Cerebras/Cohere/NVIDIA]
P3[Compatible Nodes\nOpenAI-compatible / Anthropic-compatible]
end
@@ -219,7 +219,7 @@ Moduly doménové vrstvy:
Moduly poskytovatelů OAuth (12 jednotlivých souborů v adresáři `src/lib/oauth/providers/` ):
- Index registru: `src/lib/oauth/providers/index.ts`
- Jednotliví poskytovatelé: `claude.ts` , `codex.ts` , `gemini.ts` , `antigravity.ts` , `iflow.ts` , `qwen.ts` , `kimi-coding.ts` , `github.ts` , `kiro.ts` , `cursor.ts` , `kilocode.ts` , `cline.ts`
- Jednotliví poskytovatelé: `claude.ts` , `codex.ts` , `gemini.ts` , `antigravity.ts` , `qoder.ts` , `qwen.ts` , `kimi-coding.ts` , `github.ts` , `kiro.ts` , `cursor.ts` , `kilocode.ts` , `cline.ts`
- Thin wrapper: `src/lib/oauth/providers.ts` — reexporty z jednotlivých modulů
## 3) Vrstva perzistence
@@ -592,7 +592,7 @@ Každý poskytovatel má specializovaný exekutor rozšiřující `BaseExecutor`
| Vykonavatel | Poskytovatel(é) | Speciální manipulace |
| --------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------- |
| `DefaultExecutor` | OpenAI, Claude, Gemini, Qwen, iFlow, OpenRouter, GLM, Kimi, MiniMax, DeepSeek, Groq, xAI, Mistral, Perplexity, Together, Fireworks, Cerebras, Cohere, NVIDIA | Konfigurace dynamické adresy URL/záhlaví pro každého poskytovatele |
| `DefaultExecutor` | OpenAI, Claude, Gemini, Qwen, Qoder, OpenRouter, GLM, Kimi, MiniMax, DeepSeek, Groq, xAI, Mistral, Perplexity, Together, Fireworks, Cerebras, Cohere, NVIDIA | Konfigurace dynamické adresy URL/záhlaví pro každého poskytovatele |
| `AntigravityExecutor` | Google Antigravity | Vlastní ID projektů/relací, analýza Opakování po |
| `CodexExecutor` | OpenAI Codex | Vkládá systémové instrukce, vynucuje úsilí k uvažování |
| `CursorExecutor` | IDE kurzoru | Protokol ConnectRPC, kódování Protobuf, podepisování požadavků pomocí kontrolního součtu |
@@ -616,7 +616,7 @@ Všichni ostatní poskytovatelé (včetně uzlů kompatibilních s vlastními fu
| Kurzor | kurzor | Vlastní kontrolní součet | ✅ | ✅ | ❌ | ❌ |
| Kiro | Kiro | OIDC pro jednotné přihlašování AWS | ✅ (Stream událostí) | ❌ | ✅ | ✅ Limity použití |
| Qwen | otevřeno | OAuth | ✅ | ✅ | ✅ | ⚠️ Na vyžádání |
| iFlow | otevřeno | OAuth (základní) | ✅ | ✅ | ✅ | ⚠️ Na vyžádání |
| Qoder | otevřeno | OAuth (základní) | ✅ | ✅ | ✅ | ⚠️ Na vyžádání |
| OpenRouter | otevřeno | Klíč API | ✅ | ✅ | ❌ | ❌ |
| GLM/Kimi/MiniMax | Claude | Klíč API | ✅ | ✅ | ❌ | ❌ |
| Hluboké vyhledávání | otevřeno | Klíč API | ✅ | ✅ | ❌ | ❌ |
+50 -50
View File
@@ -52,11 +52,11 @@
### 🚀 Vlastnosti
- **feat(search)** : Přidáno hřiště pro vyhledávání (10. koncový bod), stránka s nástroji pro vyhledávání s porovnáním poskytovatelů/kanálovým přeřazením/historií vyhledávání, lokální směrování pro přeřazení, ochrana autorizace ve vyhledávacím API (#443 od @Regis-RCR)
- Nová trasa: `/dashboard/search-tools`
- Položka postranního panelu v sekci Ladění
- `GET /api/search/providers` a `GET /api/search/stats` s ochranou autorizace
- Lokální směrování provider_nodes pro `/v1/rerank`
- 30+ klíčů i18n ve vyhledávacím jmenném prostoru
- Nová trasa: `/dashboard/search-tools`
- Položka postranního panelu v sekci Ladění
- `GET /api/search/providers` a `GET /api/search/stats` s ochranou autorizace
- Lokální směrování provider_nodes pro `/v1/rerank`
- 30+ klíčů i18n ve vyhledávacím jmenném prostoru
### 🐛 Opravy chyb
@@ -74,9 +74,9 @@
### 🐛 Opravy chyb
- **oprava(codex)** : Blokování týdenních vyčerpávajících účtů v přímém záložním rozhraní API (#440)
- Porovnávání prefixů `resolveQuotaWindow()` : `"weekly"` nyní odpovídá klíčům mezipaměti `"weekly (7d)"`
- `applyCodexWindowPolicy()` správně vynucuje přepínání `useWeekly` / `use5h`
- 4 nové regresní testy (celkem 766)
- Porovnávání prefixů `resolveQuotaWindow()` : `"weekly"` nyní odpovídá klíčům mezipaměti `"weekly (7d)"`
- `applyCodexWindowPolicy()` správně vynucuje přepínání `useWeekly` / `use5h`
- 4 nové regresní testy (celkem 766)
---
@@ -87,8 +87,8 @@
### 🐛 Opravy chyb
- **fix(logs)** : Oprava kontrastu světelného režimu v protokolech požadavků, tlačítek filtrů a kombinovaného odznaku (#378)
- Tlačítka filtrů Chyba/Úspěch/Kombinace jsou nyní čitelná i ve světlém režimu.
- Odznak kombinované řady používá ve světlém režimu silnější fialovou barvu
- Tlačítka filtrů Chyba/Úspěch/Kombinace jsou nyní čitelná i ve světlém režimu.
- Odznak kombinované řady používá ve světlém režimu silnější fialovou barvu
---
@@ -99,32 +99,32 @@
### ✨ Nové funkce
- **feat(search)** : Sjednocené směrování webového vyhledávání — `POST /v1/search` s 5 poskytovateli (Serper, Brave, Perplexity, Exa, Tavily)
- Automatické přepnutí napříč poskytovateli, více než 6 500 bezplatných vyhledávání/měsíc
- Mezipaměť v paměti se slučováním požadavků (konfigurovatelné TTL)
- Dashboard: Karta Analytika vyhledávání v `/dashboard/analytics` s rozpisem poskytovatelů, mírou zásahů do mezipaměti a sledováním nákladů
- Nové API: `GET /api/v1/search/analytics` pro statistiky vyhledávacích požadavků
- Migrace databáze: sloupec `request_type` v `call_logs` pro sledování požadavků mimo chat
- Ověření Zod ( `v1SearchSchema` ), chráněné autorizací, náklady zaznamenány pomocí `recordCost()`
- Automatické přepnutí napříč poskytovateli, více než 6 500 bezplatných vyhledávání/měsíc
- Mezipaměť v paměti se slučováním požadavků (konfigurovatelné TTL)
- Dashboard: Karta Analytika vyhledávání v `/dashboard/analytics` s rozpisem poskytovatelů, mírou zásahů do mezipaměti a sledováním nákladů
- Nové API: `GET /api/v1/search/analytics` pro statistiky vyhledávacích požadavků
- Migrace databáze: sloupec `request_type` v `call_logs` pro sledování požadavků mimo chat
- Ověření Zod ( `v1SearchSchema` ), chráněné autorizací, náklady zaznamenány pomocí `recordCost()`
### 🔒 Bezpečnost
- **deps** : Next.js 16.1.6 → 16.1.7 — opravuje 6 CVE:
- **Kritické** : CVE-2026-29057 (pašování HTTP požadavků přes http-proxy)
- **Vysoká** : CVE-2026-27977, CVE-2026-27978 (WebSocket + akce serveru)
- **Médium** : CVE-2026-27979, CVE-2026-27980, CVE-2026-jcc7
- **Kritické** : CVE-2026-29057 (pašování HTTP požadavků přes http-proxy)
- **Vysoká** : CVE-2026-27977, CVE-2026-27978 (WebSocket + akce serveru)
- **Médium** : CVE-2026-27979, CVE-2026-27980, CVE-2026-jcc7
### 📁 Nové soubory
Soubor | Účel
--- | ---
`open-sse/handlers/search.ts` | Vyhledávací obslužná rutina s routováním 5 poskytovatelů
`open-sse/config/searchRegistry.ts` | Registr poskytovatelů (autorizace, náklady, kvóta, TTL)
`open-sse/services/searchCache.ts` | Mezipaměť v paměti se slučováním požadavků
`src/app/api/v1/search/route.ts` | Trasa Next.js (POST + GET)
`src/app/api/v1/search/analytics/route.ts` | API pro statistiky vyhledávání
`src/app/(dashboard)/dashboard/analytics/SearchAnalyticsTab.tsx` | Karta analytického panelu
`src/lib/db/migrations/007_search_request_type.sql` | Migrace databáze
`tests/unit/search-registry.test.mjs` | 277 řádků jednotkových testů
| Soubor | Účel |
| ---------------------------------------------------------------- | -------------------------------------------------------- |
| `open-sse/handlers/search.ts` | Vyhledávací obslužná rutina s routováním 5 poskytovatelů |
| `open-sse/config/searchRegistry.ts` | Registr poskytovatelů (autorizace, náklady, kvóta, TTL) |
| `open-sse/services/searchCache.ts` | Mezipaměť v paměti se slučováním požadavků |
| `src/app/api/v1/search/route.ts` | Trasa Next.js (POST + GET) |
| `src/app/api/v1/search/analytics/route.ts` | API pro statistiky vyhledávání |
| `src/app/(dashboard)/dashboard/analytics/SearchAnalyticsTab.tsx` | Karta analytického panelu |
| `src/lib/db/migrations/007_search_request_type.sql` | Migrace databáze |
| `tests/unit/search-registry.test.mjs` | 277 řádků jednotkových testů |
---
@@ -283,10 +283,10 @@ Soubor | Účel
### 🐛 Opravy chyb
- **fix(providers)** : Odstraněny neexistující názvy modelů u 5 poskytovatelů:
- **gemini / gemini-cli** : odstraněny `gemini-3.1-pro/flash` a `gemini-3-*-preview` (neexistují v Google API v1beta); nahrazeny `gemini-2.5-pro` , `gemini-2.5-flash` , `gemini-2.0-flash` , `gemini-1.5-pro/flash`
- **antigravity** : odstraněny `gemini-3.1-pro-high/low` a `gemini-3-flash` (neplatné interní aliasy); nahrazeny skutečnými modely z verze 2.x
- **github (Copilot)** : odstraněny `gemini-3-flash-preview` a `gemini-3-pro-preview` ; nahrazeny `gemini-2.5-flash`
- **nvidia** : opraveno `nvidia/llama-3.3-70b-instruct``meta/llama-3.3-70b-instruct` (NVIDIA NIM používá pro modely Meta jmenný prostor `meta/` /); přidány `nvidia/llama-3.1-70b-instruct` a `nvidia/llama-3.1-405b-instruct`
- **gemini / gemini-cli** : odstraněny `gemini-3.1-pro/flash` a `gemini-3-*-preview` (neexistují v Google API v1beta); nahrazeny `gemini-2.5-pro` , `gemini-2.5-flash` , `gemini-2.0-flash` , `gemini-1.5-pro/flash`
- **antigravity** : odstraněny `gemini-3.1-pro-high/low` a `gemini-3-flash` (neplatné interní aliasy); nahrazeny skutečnými modely z verze 2.x
- **github (Copilot)** : odstraněny `gemini-3-flash-preview` a `gemini-3-pro-preview` ; nahrazeny `gemini-2.5-flash`
- **nvidia** : opraveno `nvidia/llama-3.3-70b-instruct``meta/llama-3.3-70b-instruct` (NVIDIA NIM používá pro modely Meta jmenný prostor `meta/` /); přidány `nvidia/llama-3.1-70b-instruct` a `nvidia/llama-3.1-405b-instruct`
- **fix(db/combo)** : Aktualizováno `free-stack` combo na vzdálené databázi: odstraněno `qw/qwen3-coder-plus` (prošlý obnovovací token), opraveno `nvidia/llama-3.3-70b-instruct``nvidia/meta/llama-3.3-70b-instruct` , opraveno `gemini/gemini-3.1-flash``gemini/gemini-2.5-flash` , přidáno `if/deepseek-v3.2`
---
@@ -356,7 +356,7 @@ Soubor | Účel
- **oprava(média)** : ComfyUI a SD WebUI se již nezobrazují v seznamu poskytovatelů na stránce Média, pokud nejsou nakonfigurovány — při připojení načtou `/api/providers` a skryjí lokální poskytovatele bez připojení (#390)
- **oprava(auth)** : Round-robin již po zpoždění znovu nevybírá účty s omezenou rychlostí ihned `backoffLevel` se nyní používá jako primární třídicí klíč v rotaci LRU (#340)
- **oprava(oauth)** : iFlow (a další poskytovatelé, kteří přesměrovávají na své vlastní uživatelské rozhraní) již nenechávají modální okno OAuth zaseknuté na „Čekání na autorizaci“ detektor zavřených vyskakovacích oken automaticky přechází do režimu ručního zadávání URL (#344)
- **oprava(oauth)** : Qoder (a další poskytovatelé, kteří přesměrovávají na své vlastní uživatelské rozhraní) již nenechávají modální okno OAuth zaseknuté na „Čekání na autorizaci“ detektor zavřených vyskakovacích oken automaticky přechází do režimu ručního zadávání URL (#344)
- **oprava(logy)** : Tabulka protokolů požadavků je nyní čitelná ve světlém režimu stavové odznaky, počty tokenů a kombinované tagy používají adaptivní `dark:` barevné třídy (#378)
### ✨ Funkce
@@ -508,7 +508,7 @@ Soubor | Účel
### ✨ Nové funkce
- **Strategie směrování Fill-First a P2C** : Do výběru kombinované strategie přidány strategie `fill-first` (vyčerpání kvóty před přesunem) a `p2c` (výběr Power-of-Two-Choices s nízkou latencí) s kompletními panely s pokyny a barevně odlišenými odznaky.
- **Přednastavené modely Free Stack** : Vytvoření kombinace pomocí šablony Free Stack nyní automaticky vyplní 7 nejlepších modelů bezplatných poskytovatelů ve své třídě (Gemini CLI, Kiro, iFlow×2, Qwen, NVIDIA NIM, Groq). Uživatelé stačí aktivovat poskytovatele a ihned získají kombinaci 0 $/měsíc.
- **Přednastavené modely Free Stack** : Vytvoření kombinace pomocí šablony Free Stack nyní automaticky vyplní 7 nejlepších modelů bezplatných poskytovatelů ve své třídě (Gemini CLI, Kiro, Qoder×2, Qwen, NVIDIA NIM, Groq). Uživatelé stačí aktivovat poskytovatele a ihned získají kombinaci 0 $/měsíc.
- **Širší kombo modální okno** : Modální okno pro vytvoření/úpravu komba nyní používá `max-w-4xl` pro pohodlnou úpravu velkých komb.
### 🐛 Opravy chyb
@@ -554,13 +554,13 @@ Soubor | Účel
### 📁 Nové soubory
Soubor | Účel
--- | ---
`open-sse/services/taskAwareRouter.ts` | Logika směrování s ohledem na úlohy (7 typů úloh)
`src/app/api/settings/task-routing/route.ts` | API pro konfiguraci směrování úloh
`src/app/api/providers/[id]/refresh/route.ts` | Ruční aktualizace tokenu OAuth
`src/lib/db/readCache.ts` | Efektivní mezipaměť pro čtení databáze
`src/shared/utils/clipboard.ts` | Zpevněná schránka s funkcí
| Soubor | Účel |
| --------------------------------------------- | ------------------------------------------------- |
| `open-sse/services/taskAwareRouter.ts` | Logika směrování s ohledem na úlohy (7 typů úloh) |
| `src/app/api/settings/task-routing/route.ts` | API pro konfiguraci směrování úloh |
| `src/app/api/providers/[id]/refresh/route.ts` | Ruční aktualizace tokenu OAuth |
| `src/lib/db/readCache.ts` | Efektivní mezipaměť pro čtení databáze |
| `src/shared/utils/clipboard.ts` | Zpevněná schránka s funkcí |
## [2.4.1] - 13. 3. 2026
@@ -574,7 +574,7 @@ Soubor | Účel
### ✨ Funkce
- **Kombinace: Šablona Free Stack** — Nová 4. šablona „Free Stack (0 $)“ využívající round-robin napříč Kiro + iFlow + Qwen + Gemini CLI. Při prvním použití doporučuje předpřipravenou kombinaci s nulovými náklady.
- **Kombinace: Šablona Free Stack** — Nová 4. šablona „Free Stack (0 $)“ využívající round-robin napříč Kiro + Qoder + Qwen + Gemini CLI. Při prvním použití doporučuje předpřipravenou kombinaci s nulovými náklady.
- **Média/Přepis: Deepgram jako výchozí** Deepgram (Nova 3, 200 dolarů zdarma) je nyní výchozím poskytovatelem přepisu. AssemblyAI (50 dolarů zdarma) a Groq Whisper (navždy zdarma) jsou zobrazeny s odznaky bezplatného kreditu.
- **README: Sekce „Začít zdarma“** Nová tabulka s 5 kroky v předběžném souboru README, která ukazuje, jak nastavit umělou inteligenci s nulovými náklady během několika minut.
- **README: Kombinace bezplatného přepisu** Nová sekce s návrhem kombinací Deepgram/AssemblyAI/Groq a informacemi o bezplatném kreditu pro každého poskytovatele.
@@ -586,9 +586,9 @@ Soubor | Účel
### 📖 Dokumentace
- **README: 44+ poskytovatelů** — Všechny 3 výskyty výrazu „36+ poskytovatelů“ byly aktualizovány na „44+“, což odráží skutečný počet kódové základny (44 poskytovatelů v souboru providers.ts).
- **README: Nová sekce „🆓 Bezplatné modely Co skutečně získáte“** Přidána tabulka 7 poskytovatelů s limity rychlosti pro každý model pro: Kiro (Claude neomezeně přes AWS Builder ID), iFlow (5 modelů neomezeně), Qwen (4 modely neomezeně), Gemini CLI (180K/měsíc), NVIDIA NIM (~40 RPM dev-forever), Cerebras (1M tok/den / 60K TPM), Groq (30 RPM / 14.4K RPD). Zahrnuje doporučení pro kombinaci /usr/bin/bash Ultimate Free Stack.
- **Soubor README: Aktualizace cenové tabulky** přidán Cerebras do úrovně API KEY, opravena změna NVIDIA z „1000 kreditů“ na „navždy zdarma pro vývojáře“, aktualizovány počty a názvy modelů iFlow/Qwen
- **README: Modely iFlow 8→5** (s názvy: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2)
- **README: Nová sekce „🆓 Bezplatné modely Co skutečně získáte“** Přidána tabulka 7 poskytovatelů s limity rychlosti pro každý model pro: Kiro (Claude neomezeně přes AWS Builder ID), Qoder (5 modelů neomezeně), Qwen (4 modely neomezeně), Gemini CLI (180K/měsíc), NVIDIA NIM (~40 RPM dev-forever), Cerebras (1M tok/den / 60K TPM), Groq (30 RPM / 14.4K RPD). Zahrnuje doporučení pro kombinaci /usr/bin/bash Ultimate Free Stack.
- **Soubor README: Aktualizace cenové tabulky** přidán Cerebras do úrovně API KEY, opravena změna NVIDIA z „1000 kreditů“ na „navždy zdarma pro vývojáře“, aktualizovány počty a názvy modelů Qoder/Qwen
- **README: Modely Qoder 8→5** (s názvy: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2)
- **README: Modely Qwen 3→4** (s názvy: qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next, vision-model)
## [2.3.15] - 13. 3. 2026
@@ -602,7 +602,7 @@ Soubor | Účel
### 🐛 Opravy chyb
- **iFlow OAuth (#339)** : Obnoven platný výchozí `clientSecret` dříve to byl prázdný řetězec, který při každém pokusu o připojení způsoboval chybu „Chybné přihlašovací údaje klienta“. Veřejné přihlašovací údaje jsou nyní výchozím záložním nastavením (lze je přepsat pomocí proměnné prostředí `IFLOW_OAUTH_CLIENT_SECRET` ).
- **Qoder OAuth (#339)** : Obnoven platný výchozí `clientSecret` dříve to byl prázdný řetězec, který při každém pokusu o připojení způsoboval chybu „Chybné přihlašovací údaje klienta“. Veřejné přihlašovací údaje jsou nyní výchozím záložním nastavením (lze je přepsat pomocí proměnné prostředí `QODER_OAUTH_CLIENT_SECRET` ).
- **MITM server nenalezen (#335)** : `prepublish.mjs` nyní kompiluje `src/mitm/*.ts` do JavaScriptu pomocí `tsc` před zkopírováním do npm balíčku. Dříve se kopírovaly pouze nezpracované soubory `.ts` což znamenalo, že `server.js` nikdy neexistoval v globálních instalacích npm/Volta.
- **Chybí projectId v GeminiCLI (#338)** : Namísto vyvolání hardwarové chyby 500, když v uložených přihlašovacích údajích chybí `projectId` (např. po restartu Dockeru), OmniRoute nyní zaznamená varování a pokusí se o požadavek vrátí smysluplnou chybu na straně poskytovatele místo pádu OmniRoute.
- **Neshoda verzí balíčku Electron (#323)** : Synchronizována verze `electron/package.json` s verzí `2.3.13` (dříve `2.0.13` ), takže binární verze pro stolní počítače odpovídá balíčku npm.
@@ -640,9 +640,9 @@ Soubor | Účel
### 📁 Nové soubory
Soubor | Účel
--- | ---
`open-sse/services/modelFamilyFallback.ts` | Definice modelových rodin a logika záložních řešení v rámci rodiny
| Soubor | Účel |
| ------------------------------------------ | ------------------------------------------------------------------ |
| `open-sse/services/modelFamilyFallback.ts` | Definice modelových rodin a logika záložních řešení v rámci rodiny |
### Opraveno
+2 -2
View File
@@ -267,7 +267,7 @@ Obchodní logika, která podporuje obslužné rutiny a vykonavatele.
| `provider.ts` | **Detekce formátu** ( `detectFormat` ): analyzuje strukturu těla požadavku a identifikuje formáty Claude/OpenAI/Gemini/Antigravity/Responses (včetně heuristiky `max_tokens` pro Claude). Dále: tvorba URL, tvorba hlaviček, normalizace konfigurace thinking. Podporuje dynamické poskytovatele kompatibilní `openai-compatible-*` a `anthropic-compatible-*` . |
| `model.ts` | Analýza řetězců modelu ( `claude/model-name``{provider: "claude", model: "model-name"}` ), rozlišení aliasů s detekcí kolizí, sanitizace vstupu (odmítá průchod cestou/řídicí znaky) a rozlišení informací o modelu s podporou asynchronních metod pro získávání aliasů. |
| `accountFallback.ts` | Ovládání limitů rychlosti: exponenciální upomínka (1 s → 2 s → 4 s → max. 2 min), správa doby zpoždění účtu, klasifikace chyb (které chyby spouštějí fallback a které ne). |
| `tokenRefresh.ts` | Aktualizace tokenu OAuth pro **všechny poskytovatele** : Google (Gemini, Antigravity), Claude, Codex, Qwen, iFlow, GitHub (duální token OAuth + Copilot), Kiro (AWS SSO OIDC + sociální ověřování). Zahrnuje mezipaměť deduplikace promise za provozu a opakování s exponenciálním zpožděním. |
| `tokenRefresh.ts` | Aktualizace tokenu OAuth pro **všechny poskytovatele** : Google (Gemini, Antigravity), Claude, Codex, Qwen, Qoder, GitHub (duální token OAuth + Copilot), Kiro (AWS SSO OIDC + sociální ověřování). Zahrnuje mezipaměť deduplikace promise za provozu a opakování s exponenciálním zpožděním. |
| `combo.ts` | **Kombinované modely** : řetězce záložních modelů. Pokud model A selže s chybou způsobilou pro záložní model, zkuste model B, poté C atd. Vrací skutečné stavové kódy upstreamu. |
| `usage.ts` | Načítá data o kvótách/využití z API poskytovatelů (kvóty GitHub Copilot, kvóty modelu Antigravity, limity rychlosti Codexu, rozpisy využití Kiro, nastavení Claude). |
| `accountSelector.ts` | Inteligentní výběr účtu s algoritmem bodování: pro výběr optimálního účtu pro každý požadavek se zohledňuje priorita, zdravotní stav, pozice v systému round robin a stav ochlazování. |
@@ -539,7 +539,7 @@ K hlášenému využití je přidána vyrovnávací paměť o kapacitě 2000 tok
| Kiro (AWS) | AWS SSO OIDC nebo Social | Kiro | Analýza binárního EventStreamu |
| Cursor IDE | Checksum auth | Cursor | Kódování Protobuf, kontrolní součty SHA-256 |
| Qwen | OAuth | Výchozí | Standardní ověřování |
| iFlow | OAuth (Basic + Bearer) | Výchozí | Duální hlavička pro autorizaci |
| Qoder | OAuth (Basic + Bearer) | Výchozí | Duální hlavička pro autorizaci |
| OpenRouter | API klíč | Výchozí | Autorizace standardního nosiče |
| GLM, Kimi, MiniMax | API klíč | Výchozí | Kompatibilní s Claude, použijte `x-api-key` |
| `openai-compatible-*` | API klíč | Výchozí | Dynamické: jakýkoli OpenAI kompatibilní |
+5 -5
View File
@@ -8,7 +8,7 @@ Vizuální průvodce všemi částmi ovládacího panelu OmniRoute.
## 🔌 Poskytovatelé
Spravujte připojení poskytovatelů AI: poskytovatelé OAuth (Claude Code, Codex, Gemini CLI), poskytovatelé klíčů API (Groq, DeepSeek, OpenRouter) a bezplatní poskytovatelé (iFlow, Qwen, Kiro). Účty Kiro zahrnují sledování zůstatku kreditů zbývající kredity, celkový limit a datum obnovení jsou viditelné v Dashboard → Usage.
Spravujte připojení poskytovatelů AI: poskytovatelé OAuth (Claude Code, Codex, Gemini CLI), poskytovatelé klíčů API (Groq, DeepSeek, OpenRouter) a bezplatní poskytovatelé (Qoder, Qwen, Kiro). Účty Kiro zahrnují sledování zůstatku kreditů zbývající kredity, celkový limit a datum obnovení jsou viditelné v Dashboard → Usage.
![Dashboard poskytovatelů](screenshots/01-providers.png)
@@ -46,13 +46,13 @@ Monitorování v reálném čase: dostupnost, paměť, verze, percentily latence
---
## 🎮 Modelové hřiště *(v2.0.9+)*
## 🎮 Modelové hřiště _(v2.0.9+)_
Otestujte libovolný model přímo z řídicího panelu. Vyberte poskytovatele, model a koncový bod, pište výzvy pomocí editoru Monaco, streamujte odpovědi v reálném čase, přerušte stream a zobrazte metriky časování.
---
## 🎨 Témata *(v2.0.5+)*
## 🎨 Témata _(v2.0.5+)_
Přizpůsobitelná barevná témata pro celý dashboard. Vyberte si ze 7 přednastavených barev (korálová, modrá, červená, zelená, fialová, oranžová, azurová) nebo si vytvořte vlastní téma výběrem libovolné hexadecimální barvy. Podporuje světlý, tmavý a systémový režim.
@@ -81,7 +81,7 @@ Konfigurace nástrojů pro kódování s umělou inteligencí jedním kliknutím
---
## 🤖 Agenti CLI *(v2.0.11+)*
## 🤖 Agenti CLI _(v2.0.11+)_
Ovládací panel pro vyhledávání a správu agentů CLI. Zobrazuje mřížku 14 vestavěných agentů (Codex, Claude, Goose, Gemini CLI, OpenClaw, Aider, OpenCode, Cline, Qwen Code, ForgeCode, Amazon Q, Open Interpreter, Cursor CLI, Warp) s:
@@ -92,7 +92,7 @@ Ovládací panel pro vyhledávání a správu agentů CLI. Zobrazuje mřížku 1
---
## 🖼️ Média *(v2.0.3+)*
## 🖼️ Média _(v2.0.3+)_
Generujte obrázky, videa a hudbu z řídicího panelu. Podporuje OpenAI, xAI, Together, Hyperbolic, SD WebUI, ComfyUI, AnimateDiff, Stable Audio Open a MusicGen.
+26 -23
View File
@@ -20,16 +20,17 @@ _Váš univerzální API proxy jeden endpoint, více než 44 poskytovatelů,
### 🆕 What's New in v3.0.0
| Area | Change |
| -------------------------- | --------------------------------------------------------------------------------- |
| 🔒 **CodeQL Security** | Fixed 10+ CodeQL alerts: polynomial-redos, insecure-randomness, shell-injection |
| ✅ **Route Validation** | All 176 API routes validated with Zod schemas + `validateBody()` |
| 🐛 **omniModel Tag Leak** | Internal `<omniModel>` tags no longer leak to clients in SSE streams (#585) |
| 🔑 **Registered Keys API** | Auto-provision API keys via `POST /api/v1/registered-keys` with quota enforcement |
| 🎨 **Provider Icons** | 130+ provider logos via `@lobehub/icons` (SVG) with PNG fallback |
| 🔄 **Model Auto-Sync** | 24h scheduler refreshes model lists for 16 providers |
| 🌐 **OpenCode Zen/Go** | Two new providers: free tier + subscription tier |
| 🔧 **926 Tests** | Full test suite passes with 0 failures |
| Area | Change |
| ------------------------------- | --------------------------------------------------------------------------------- |
| 🔒 **CodeQL Security** | Fixed 10+ CodeQL alerts: polynomial-redos, insecure-randomness, shell-injection |
| ✅ **Route Validation** | All 176 API routes validated with Zod schemas + `validateBody()` |
| 🐛 **omniModel Tag Leak** | Internal `<omniModel>` tags no longer leak to clients in SSE streams (#585) |
| 🔑 **Registered Keys API** | Auto-provision API keys via `POST /api/v1/registered-keys` with quota enforcement |
| 👁️ **Scoped API Key Reveal** 🆕 | Opt-in recovery of API keys via `ALLOW_API_KEY_REVEAL` |
| 🎨 **Provider Icons** | 130+ provider logos via `@lobehub/icons` (SVG) with PNG fallback |
| 🔄 **Model Auto-Sync** | 24h scheduler refreshes model lists for 16 providers |
| 🌐 **OpenCode Zen/Go** | Two new providers: free tier + subscription tier |
| 🔧 **926 Tests** | Full test suite passes with 0 failures |
### 🆕 What's New in v3.0.0
@@ -134,7 +135,7 @@ Při otevírání problému spusťte příkaz system-info a přiložte vygenerov
npm run system-info
```
Tím se vygeneruje soubor `system-info.txt` s verzí Node.js, verzí OmniRoute, podrobnostmi o operačním systému, nainstalovanými nástroji CLI (iflow, gemini, claude, codex, antigravity, droid atd.), stavem Dockeru/PM2 a systémovými balíčky vše, co potřebujeme k rychlé reprodukci vašeho problému. Soubor přiložte přímo k vašemu problému na GitHubu.
Tím se vygeneruje soubor `system-info.txt` s verzí Node.js, verzí OmniRoute, podrobnostmi o operačním systému, nainstalovanými nástroji CLI (qoder, gemini, claude, codex, antigravity, droid atd.), stavem Dockeru/PM2 a systémovými balíčky vše, co potřebujeme k rychlé reprodukci vašeho problému. Soubor přiložte přímo k vašemu problému na GitHubu.
---
@@ -160,7 +161,7 @@ Tím se vygeneruje soubor `system-info.txt` s verzí Node.js, verzí OmniRoute,
│ ↓ budget limit
├─→ [Tier 3: CHEAP] GLM ($0.6/1M), MiniMax ($0.2/1M)
│ ↓ budget limit
└─→ [Tier 4: FREE] iFlow, Qwen, Kiro (unlimited)
└─→ [Tier 4: FREE] Qoder, Qwen, Kiro (unlimited)
Result: Never stop coding, minimal cost
```
@@ -225,7 +226,7 @@ Ne každý si může dovolit zaplatit 20200 dolarů měsíčně za předplatn
**Jak to OmniRoute řeší:**
- **Vestavění poskytovatelé bezplatné úrovně** — Nativní podpora pro 100% bezplatné poskytovatele: iFlow (5 neomezených modelů přes OAuth: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2), Qwen (4 neomezené modely: qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next, vision-model), Kiro (Claude + AWS Builder ID zdarma), Gemini CLI (180 tisíc tokenů/měsíc zdarma)
- **Vestavění poskytovatelé bezplatné úrovně** — Nativní podpora pro 100% bezplatné poskytovatele: Qoder (5 neomezených modelů přes OAuth: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2), Qwen (4 neomezené modely: qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next, vision-model), Kiro (Claude + AWS Builder ID zdarma), Gemini CLI (180 tisíc tokenů/měsíc zdarma)
- **Ollama Cloud** — Cloudově hostované modely Ollama na `api.ollama.com` s bezplatnou úrovní „Light usage“; použijte prefix `ollamacloud/<model>`
- **Kombinace pouze zdarma** — Chain `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = 0 $/měsíc s nulovými prostoji
- **NVIDIA NIM Free Access** — ~40 RPM developerský přístup k více než 70 modelům na build.nvidia.com (přechod z kreditů na čisté limity rychlosti)
@@ -285,7 +286,7 @@ Claude Code, Codex, Gemini CLI, Copilot všechny používají OAuth 2.0 s to
**Jak to OmniRoute řeší:**
- **Automatická aktualizace tokenů** Tokeny OAuth se obnovují na pozadí před vypršením platnosti.
- **Vestavěný OAuth 2.0 (PKCE)** Automatický tok pro Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
- **Vestavěný OAuth 2.0 (PKCE)** Automatický tok pro Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, Qoder
- **Multi-Account OAuth** — Více účtů na poskytovatele prostřednictvím extrakce tokenů JWT/ID
- **OAuth LAN/Remote Fix** — Detekce privátní IP adresy pro `redirect_uri` + manuální režim URL pro vzdálené servery
- **OAuth Behind Nginx** — Používá `window.location.origin` pro kompatibilitu s reverzní proxy
@@ -638,7 +639,7 @@ Outcome: deep fallback depth for deadline-critical workloads
| Krok | Akce | Poskytovatelé odemčeni |
| ---- | -------------------------------------------------------------- | ----------------------------------------------------------------- |
| 1 | Připojení **Kiro** (AWS Builder ID OAuth) | Claude Sonnet 4.5, Haiku 4.5 **neomezeně** |
| 2 | Připojení k **iFlow** (Google OAuth) | kimi-k2-myšlení, qwen3-coder-plus, deepseek-r1... — **neomezeně** |
| 2 | Připojení k **Qoder** (Google OAuth) | kimi-k2-myšlení, qwen3-coder-plus, deepseek-r1... — **neomezeně** |
| 3 | Připojení **Qwen** (kód zařízení) | qwen3-coder-plus, qwen3-coder-flash... — **neomezeně** |
| 4 | Připojení **rozhraní příkazového řádku Gemini** (Google OAuth) | gemini-3-flash, gemini-2.5-pro — **180 000 GBP/měsíc zdarma** |
| 5 | `/dashboard/combos` → Šablona **Free Stack (0 $)** | Automatické zařazení všech bezplatných poskytovatelů do routingu |
@@ -847,7 +848,7 @@ Po minimalizaci se OmniRoute nachází v systémové liště a nabízí rychlé
| MiniMax M2.1 | 0,2 USD/1 milion | 5hodinové válcování | Nejlevnější varianta |
| Kimi K2.5 (Moonshot API) 🆕 | Platba za použití | Žádný | Přímý přístup k Moonshot API |
| Kimi K2 | 9 dolarů měsíčně bez závazků | 10 milionů tokenů/měsíc | Předvídatelné náklady |
| **🆓 ZDARMA** | iFlow | **0 dolarů** | Neomezený | 5 modelů neomezeně |
| **🆓 ZDARMA** | Qoder | **0 dolarů** | Neomezený | 5 modelů neomezeně |
| Qwen | **0 dolarů** | Neomezený | 4 modely neomezeně |
| Kiro | **0 dolarů** | Neomezený | Claude Sonnet/Haiku (tvorce AWS) |
@@ -858,7 +859,7 @@ Po minimalizaci se OmniRoute nachází v systémové liště a nabízí rychlé
```
# 🆓 Ultimate Free Stack 2026 — 11 Providers, $0 Forever
Kiro (kr/) → Claude Sonnet/Haiku UNLIMITED
iFlow (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
Qoder (if/) → kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
LongCat Lite (lc/) → LongCat-Flash-Lite — 50M tokens/day 🔥
Pollinations (pol/) → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
Qwen (qw/) → qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next UNLIMITED
@@ -888,7 +889,7 @@ Cerebras (cerebras/) → Llama/Qwen world-fastest — 1M tok/day
| `claude-haiku-4.5` | `kr/` | **Neomezený** | Žádný hlášený denní limit |
| `claude-opus-4.6` | `kr/` | **Neomezený** | Nejnovější opus od Kira |
### 🟢 MODELY IFLOW (Bezplatné OAuth — bez nutnosti platit kreditní kartou)
### 🟢 MODELY QODER (Bezplatné OAuth — bez nutnosti platit kreditní kartou)
| Model | Předpona | Omezit | Limit rychlosti |
| ------------------ | -------- | ------------- | ------------------- |
@@ -942,7 +943,7 @@ K dispozici zdarma: `llama-3.3-70b-versatile` , `gemma2-9b-it` , `mixtral-8x7b`
>
> ```
> Kiro (Claude, unlimited)
> → iFlow (5 models, unlimited)
> → Qoder (5 models, unlimited)
> → Qwen (4 models, unlimited)
> → Gemini CLI (180K/mo)
> → Cerebras (1M tok/day)
@@ -1048,6 +1049,7 @@ OmniRoute v2.0 je navržen jako operační platforma, nikoli pouze jako proxy pr
| Funkce | Co to dělá |
| ----------------------------------- | ---------------------------------------------------------------------- |
| 📝 **Žádost + protokolování proxy** | Úplné protokolování požadavků/odpovědí a proxy |
| 📉 **Streamed Detailed Logs** 🆕 | Reconstructs SSE payload streams cleanly into the UI |
| 📋 **Sjednocený panel protokolů** | Zobrazení požadavků, proxy, auditu a konzole na jedné stránce |
| 🔍 **Vyžádat si telemetrii** | Latence p50/p95/p99 a trasování požadavků |
| 🏥 **Panel zdraví** | Doba provozuschopnosti, stavy jističů, uzamčení, statistiky mezipaměti |
@@ -1068,6 +1070,7 @@ OmniRoute v2.0 je navržen jako operační platforma, nikoli pouze jako proxy pr
| 🔏 **Přepínač otisků prstů v příkazovém řádku** | Porovnávání otisků prstů podle poskytovatele v Nastavení &gt; Zabezpečení |
| 🌐 **i18n (30 jazyků)** | Plná jazyková podpora dashboardu a dokumentace s psaním zprava doleva |
| 🧹 **Clear All Models** | One-click model list clearing in provider details |
| 👁️ **Sidebar Controls** 🆕 | Hide components and integrations from Appearance Settings |
| 📋 **Issue Templates** | Standardized GitHub templates for bugs and features |
| 📂 **Adresář vlastních dat** | Přepsání `DATA_DIR` pro umístění úložiště |
@@ -1358,11 +1361,11 @@ Models:
<summary><b>🆓 BEZPLATNÍ poskytovatelé (nouzové zálohování)</b></summary>
</details>
### iFlow (5 BEZPLATNÝCH modelů přes OAuth)
### Qoder (5 BEZPLATNÝCH modelů přes OAuth)
```bash
Dashboard → Connect iFlow
iFlow OAuth login
Dashboard → Connect Qoder
Qoder OAuth login
→ Unlimited usage
Models:
@@ -1557,7 +1560,7 @@ opencode
- Zkontrolujte statistiky využití v sekci Nástěnka → Náklady
- Přepnout primární model na GLM/MiniMax
- Pro nekritické úlohy použijte bezplatnou úroveň (Gemini CLI, iFlow).
- Pro nekritické úlohy použijte bezplatnou úroveň (Gemini CLI, Qoder).
**Porty řídicího panelu/API jsou nesprávné**
+17 -17
View File
@@ -8,13 +8,13 @@ Běžné problémy a řešení pro OmniRoute.
## Rychlé opravy
Problém | Řešení
--- | ---
První přihlášení nefunguje | Nastavit `INITIAL_PASSWORD` v `.env` (bez pevně zakódovaného výchozího nastavení)
Dashboard se otevírá na nesprávném portu | Nastavte `PORT=20128` a `NEXT_PUBLIC_BASE_URL=http://localhost:20128`
Žádné protokoly požadavků v sekci `logs/` | Nastavte `ENABLE_REQUEST_LOGS=true`
PŘÍSTUP: povolení zamítnuto | Nastavením `DATA_DIR=/path/to/writable/dir` přepíšete `~/.omniroute`
Strategie směrování se neukládá | Aktualizace na v1.4.11+ (oprava schématu Zod pro perzistenci nastavení)
| Problém | Řešení |
| ----------------------------------------- | --------------------------------------------------------------------------------- |
| První přihlášení nefunguje | Nastavit `INITIAL_PASSWORD` v `.env` (bez pevně zakódovaného výchozího nastavení) |
| Dashboard se otevírá na nesprávném portu | Nastavte `PORT=20128` a `NEXT_PUBLIC_BASE_URL=http://localhost:20128` |
| Žádné protokoly požadavků v sekci `logs/` | Nastavte `ENABLE_REQUEST_LOGS=true` |
| PŘÍSTUP: povolení zamítnuto | Nastavením `DATA_DIR=/path/to/writable/dir` přepíšete `~/.omniroute` |
| Strategie směrování se neukládá | Aktualizace na v1.4.11+ (oprava schématu Zod pro perzistenci nastavení) |
---
@@ -97,7 +97,7 @@ curl -s http://localhost:20128/api/cli-tools/openclaw-settings | jq '{installed,
1. Zkontrolujte statistiky využití v sekci Nástěnka → Využití
2. Přepnout primární model na GLM/MiniMax
3. Pro nekritické úlohy použijte bezplatnou úroveň (Gemini CLI, iFlow).
3. Pro nekritické úlohy použijte bezplatnou úroveň (Gemini CLI, Qoder).
4. Nastavení rozpočtů nákladů pro každý klíč API: Dashboard → API klíče → Rozpočet
---
@@ -169,12 +169,12 @@ Pokud poskytovatel opakovaně přechází do stavu OTEVŘENO:
Pro ladění problémů s překladem formátu použijte **Dashboard → Translator** :
Režim | Kdy použít
--- | ---
**Dětské hřiště** | Porovnejte vstupní/výstupní formáty vedle sebe vložte neúspěšný požadavek a podívejte se, jak se přeloží
**Tester chatu** | Odesílejte živé zprávy a kontrolujte kompletní datovou část požadavků/odpovědí včetně záhlaví
**Zkušební stolice** | Spusťte dávkové testy napříč kombinacemi formátů a zjistěte, které překlady jsou poškozené.
**Živý monitor** | Sledujte tok požadavků v reálném čase a zachyťte občasné problémy s překladem
| Režim | Kdy použít |
| -------------------- | ---------------------------------------------------------------------------------------------------------- |
| **Dětské hřiště** | Porovnejte vstupní/výstupní formáty vedle sebe vložte neúspěšný požadavek a podívejte se, jak se přeloží |
| **Tester chatu** | Odesílejte živé zprávy a kontrolujte kompletní datovou část požadavků/odpovědí včetně záhlaví |
| **Zkušební stolice** | Spusťte dávkové testy napříč kombinacemi formátů a zjistěte, které překlady jsou poškozené. |
| **Živý monitor** | Sledujte tok požadavků v reálném čase a zachyťte občasné problémy s překladem |
### Běžné problémy s formátováním
@@ -230,9 +230,9 @@ Pokud chcete sdílenou slovní zásobu pro popis těchto selhání, můžete pou
Myšlenka je jednoduchá:
1. Při vyšetřování špatné odpovědi zaznamenejte:
- úkol a požadavek uživatele
- Kombinace trasy nebo poskytovatele v OmniRoute
- jakýkoli kontext RAG použitý v následných fázích (načtené dokumenty, volání nástrojů atd.)
- úkol a požadavek uživatele
- Kombinace trasy nebo poskytovatele v OmniRoute
- jakýkoli kontext RAG použitý v následných fázích (načtené dokumenty, volání nástrojů atd.)
2. Namapujte incident na jedno nebo dvě čísla z WFGY ProblemMap ( `No.1``No.16` ).
3. Uložte číslo do vlastního řídicího panelu, runbooku nebo sledovače incidentů vedle protokolů OmniRoute.
4. Pro rozhodnutí, zda je potřeba změnit RAG stack, retriever nebo směrovací strategii, použijte odpovídající stránku WFGY.
+5 -5
View File
@@ -39,11 +39,11 @@ Kompletní průvodce konfigurací poskytovatelů, vytvářením kombinací, inte
| **💰 LEVNÉ** | GLM-4.7 | $0.6/1M | Denně 10:00 | Levná záloha |
| | MiniMax M2.1 | $0.2/1M | 5hodinové válcování | Nejlevnější varianta |
| | Kimi K2 | 9 USD měsíc | 10M tokens/měsíc | Předvídatelné náklady |
| **🆓 ZDARMA** | iFlow | $0 | Neomezený | 8 modelů zdarma |
| **🆓 ZDARMA** | Qoder | $0 | Neomezený | 8 modelů zdarma |
| | Qwen | $0 | Neomezený | 3 modely zdarma |
| | Kiro | $0 | Neomezený | Claude zdarma |
**💡 Pro Tip:** Začněte s kombinací Gemini CLI (180K zdarma/měsíc) + iFlow (neomezeně zdarma) = $0!
**💡 Pro Tip:** Začněte s kombinací Gemini CLI (180K zdarma/měsíc) + Qoder (neomezeně zdarma) = $0!
---
@@ -193,10 +193,10 @@ Models:
### 🆓 Poskytovatelé ZDARMA
#### iFlow (8 modelů ZDARMA)
#### Qoder (8 modelů ZDARMA)
```bash
Dashboard → Connect iFlow → OAuth login → Unlimited usage
Dashboard → Connect Qoder → OAuth login → Unlimited usage
Models: if/kimi-k2-thinking, if/qwen3-coder-plus, if/glm-4.7, if/minimax-m2, if/deepseek-r1
```
@@ -447,7 +447,7 @@ Informace o režimu integrovaném s hostitelem s binárními soubory CLI nalezne
**MiniMax ( `minimax/` )** — 0,2 USD/1 milion: `minimax/MiniMax-M2.1`
**iFlow ( `if/` )** — ZDARMA: `if/kimi-k2-thinking` , `if/qwen3-coder-plus` , `if/deepseek-r1`
**Qoder ( `if/` )** — ZDARMA: `if/kimi-k2-thinking` , `if/qwen3-coder-plus` , `if/deepseek-r1`
**Qwen ( `qw/` )** — ZDARMA: `qw/qwen3-coder-plus` , `qw/qwen3-coder-flash`
+4 -4
View File
@@ -90,7 +90,7 @@ flowchart LR
end
subgraph Upstreams[Upstream Providers]
P1[OAuth Providers\nClaude/Codex/Gemini/Qwen/iFlow/GitHub/Kiro/Cursor/Antigravity]
P1[OAuth Providers\nClaude/Codex/Gemini/Qwen/Qoder/GitHub/Kiro/Cursor/Antigravity]
P2[API Key Providers\nOpenAI/Anthropic/OpenRouter/GLM/Kimi/MiniMax\nDeepSeek/Groq/xAI/Mistral/Perplexity\nTogether/Fireworks/Cerebras/Cohere/NVIDIA]
P3[Compatible Nodes\nOpenAI-compatible / Anthropic-compatible]
end
@@ -224,7 +224,7 @@ Domain layer modules:
OAuth provider modules (12 individual files under `src/lib/oauth/providers/`):
- Registry index: `src/lib/oauth/providers/index.ts`
- Individual providers: `claude.ts`, `codex.ts`, `gemini.ts`, `antigravity.ts`, `iflow.ts`, `qwen.ts`, `kimi-coding.ts`, `github.ts`, `kiro.ts`, `cursor.ts`, `kilocode.ts`, `cline.ts`
- Individual providers: `claude.ts`, `codex.ts`, `gemini.ts`, `antigravity.ts`, `qoder.ts`, `qwen.ts`, `kimi-coding.ts`, `github.ts`, `kiro.ts`, `cursor.ts`, `kilocode.ts`, `cline.ts`
- Thin wrapper: `src/lib/oauth/providers.ts` — re-exports from individual modules
## 3) Persistence Layer
@@ -597,7 +597,7 @@ Each provider has a specialized executor extending `BaseExecutor` (in `open-sse/
| Executor | Provider(s) | Special Handling |
| --------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------- |
| `DefaultExecutor` | OpenAI, Claude, Gemini, Qwen, iFlow, OpenRouter, GLM, Kimi, MiniMax, DeepSeek, Groq, xAI, Mistral, Perplexity, Together, Fireworks, Cerebras, Cohere, NVIDIA | Dynamic URL/header config per provider |
| `DefaultExecutor` | OpenAI, Claude, Gemini, Qwen, Qoder, OpenRouter, GLM, Kimi, MiniMax, DeepSeek, Groq, xAI, Mistral, Perplexity, Together, Fireworks, Cerebras, Cohere, NVIDIA | Dynamic URL/header config per provider |
| `AntigravityExecutor` | Google Antigravity | Custom project/session IDs, Retry-After parsing |
| `CodexExecutor` | OpenAI Codex | Injects system instructions, forces reasoning effort |
| `CursorExecutor` | Cursor IDE | ConnectRPC protocol, Protobuf encoding, request signing via checksum |
@@ -621,7 +621,7 @@ All other providers (including custom compatible nodes) use the `DefaultExecutor
| Cursor | cursor | Custom checksum | ✅ | ✅ | ❌ | ❌ |
| Kiro | kiro | AWS SSO OIDC | ✅ (EventStream) | ❌ | ✅ | ✅ Usage limits |
| Qwen | openai | OAuth | ✅ | ✅ | ✅ | ⚠️ Per request |
| iFlow | openai | OAuth (Basic) | ✅ | ✅ | ✅ | ⚠️ Per request |
| Qoder | openai | OAuth (Basic) | ✅ | ✅ | ✅ | ⚠️ Per request |
| OpenRouter | openai | API Key | ✅ | ✅ | ❌ | ❌ |
| GLM/Kimi/MiniMax | claude | API Key | ✅ | ✅ | ❌ | ❌ |
| DeepSeek | openai | API Key | ✅ | ✅ | ❌ | ❌ |
+2 -2
View File
@@ -271,7 +271,7 @@ Business logic that supports the handlers and executors.
| `provider.ts` | **Format detection** (`detectFormat`): analyzes request body structure to identify Claude/OpenAI/Gemini/Antigravity/Responses formats (includes `max_tokens` heuristic for Claude). Also: URL building, header building, thinking config normalization. Supports `openai-compatible-*` and `anthropic-compatible-*` dynamic providers. |
| `model.ts` | Model string parsing (`claude/model-name``{provider: "claude", model: "model-name"}`), alias resolution with collision detection, input sanitization (rejects path traversal/control chars), and model info resolution with async alias getter support. |
| `accountFallback.ts` | Rate-limit handling: exponential backoff (1s → 2s → 4s → max 2min), account cooldown management, error classification (which errors trigger fallback vs. not). |
| `tokenRefresh.ts` | OAuth token refresh for **every provider**: Google (Gemini, Antigravity), Claude, Codex, Qwen, iFlow, GitHub (OAuth + Copilot dual-token), Kiro (AWS SSO OIDC + Social Auth). Includes in-flight promise deduplication cache and retry with exponential backoff. |
| `tokenRefresh.ts` | OAuth token refresh for **every provider**: Google (Gemini, Antigravity), Claude, Codex, Qwen, Qoder, GitHub (OAuth + Copilot dual-token), Kiro (AWS SSO OIDC + Social Auth). Includes in-flight promise deduplication cache and retry with exponential backoff. |
| `combo.ts` | **Combo models**: chains of fallback models. If model A fails with a fallback-eligible error, try model B, then C, etc. Returns actual upstream status codes. |
| `usage.ts` | Fetches quota/usage data from provider APIs (GitHub Copilot quotas, Antigravity model quotas, Codex rate limits, Kiro usage breakdowns, Claude settings). |
| `accountSelector.ts` | Smart account selection with scoring algorithm: considers priority, health status, round-robin position, and cooldown state to pick the optimal account for each request. |
@@ -543,7 +543,7 @@ A 2000-token buffer is added to reported usage to prevent clients from hitting c
| Kiro (AWS) | AWS SSO OIDC or Social | Kiro | Binary EventStream parsing |
| Cursor IDE | Checksum auth | Cursor | Protobuf encoding, SHA-256 checksums |
| Qwen | OAuth | Default | Standard auth |
| iFlow | OAuth (Basic + Bearer) | Default | Dual auth header |
| Qoder | OAuth (Basic + Bearer) | Default | Dual auth header |
| OpenRouter | API key | Default | Standard Bearer auth |
| GLM, Kimi, MiniMax | API key | Default | Claude-compatible, use `x-api-key` |
| `openai-compatible-*` | API key | Default | Dynamic: any OpenAI-compatible endpoint |
+2 -2
View File
@@ -12,7 +12,7 @@ Visual guide to every section of the OmniRoute dashboard.
## 🔌 Providers
Manage AI provider connections: OAuth providers (Claude Code, Codex, Gemini CLI), API key providers (Groq, DeepSeek, OpenRouter), and free providers (iFlow, Qwen, Kiro). Kiro accounts include credit balance tracking — remaining credits, total allowance, and renewal date visible in Dashboard → Usage.
Manage AI provider connections: OAuth providers (Claude Code, Codex, Gemini CLI), API key providers (Groq, DeepSeek, OpenRouter), and free providers (Qoder, Qwen, Kiro). Kiro accounts include credit balance tracking — remaining credits, total allowance, and renewal date visible in Dashboard → Usage.
![Providers Dashboard](screenshots/01-providers.png)
@@ -67,7 +67,7 @@ Customizable color themes for the entire dashboard. Choose from 7 preset colors
Comprehensive settings panel with tabs:
- **General** — System storage, backup management (export/import database)
- **Appearance** — Theme selector (dark/light/system), color theme presets and custom colors, health log visibility
- **Appearance** — Theme selector (dark/light/system), color theme presets and custom colors, health log visibility, sidebar item visibility controls
- **Security** — API endpoint protection, custom provider blocking, IP filtering, session info
- **Routing** — Model aliases, background task degradation
- **Resilience** — Rate limit persistence, circuit breaker tuning
+1157 -689
View File
File diff suppressed because it is too large Load Diff
+1 -1
View File
@@ -101,7 +101,7 @@ curl -s http://localhost:20128/api/cli-tools/openclaw-settings | jq '{installed,
1. Check usage stats in Dashboard → Usage
2. Switch primary model to GLM/MiniMax
3. Use free tier (Gemini CLI, iFlow) for non-critical tasks
3. Use free tier (Gemini CLI, Qoder) for non-critical tasks
4. Set cost budgets per API key: Dashboard → API Keys → Budget
---
+127 -11
View File
@@ -1,11 +1,11 @@
🌐 **Languages:** 🇺🇸 [English](../../README.md) · 🇧🇷 [pt-BR](../pt-BR/USER_GUIDE.md) · 🇪🇸 [es](../es/USER_GUIDE.md) · 🇫🇷 [fr](../fr/USER_GUIDE.md) · 🇩🇪 [de](../de/USER_GUIDE.md) · 🇮🇹 [it](../it/USER_GUIDE.md) · 🇷🇺 [ru](../ru/USER_GUIDE.md) · 🇨🇳 [zh-CN](../zh-CN/USER_GUIDE.md) · 🇯🇵 [ja](../ja/USER_GUIDE.md) · 🇰🇷 [ko](../ko/USER_GUIDE.md) · 🇸🇦 [ar](../ar/USER_GUIDE.md) · 🇮🇳 [in](../in/USER_GUIDE.md) · 🇹🇭 [th](../th/USER_GUIDE.md) · 🇻🇳 [vi](../vi/USER_GUIDE.md) · 🇮🇩 [id](../id/USER_GUIDE.md) · 🇲🇾 [ms](../ms/USER_GUIDE.md) · 🇳🇱 [nl](../nl/USER_GUIDE.md) · 🇵🇱 [pl](../pl/USER_GUIDE.md) · 🇸🇪 [sv](../sv/USER_GUIDE.md) · 🇳🇴 [no](../no/USER_GUIDE.md) · 🇩🇰 [da](../da/USER_GUIDE.md) · 🇫🇮 [fi](../fi/USER_GUIDE.md) · 🇵🇹 [pt](../pt/USER_GUIDE.md) · 🇷🇴 [ro](../ro/USER_GUIDE.md) · 🇭🇺 [hu](../hu/USER_GUIDE.md) · 🇧🇬 [bg](../bg/USER_GUIDE.md) · 🇸🇰 [sk](../sk/USER_GUIDE.md) · 🇺🇦 [uk-UA](../uk-UA/USER_GUIDE.md) · 🇮🇱 [he](../he/USER_GUIDE.md) · 🇵🇭 [phi](../phi/USER_GUIDE.md)
# User Guide (Dansk)
🌐 **Languages:** 🇺🇸 [English](../../USER_GUIDE.md) · 🇧🇷 [pt-BR](../pt-BR/USER_GUIDE.md) · 🇪🇸 [es](../es/USER_GUIDE.md) · 🇫🇷 [fr](../fr/USER_GUIDE.md) · 🇩🇪 [de](../de/USER_GUIDE.md) · 🇮🇹 [it](../it/USER_GUIDE.md) · 🇷🇺 [ru](../ru/USER_GUIDE.md) · 🇨🇳 [zh-CN](../zh-CN/USER_GUIDE.md) · 🇯🇵 [ja](../ja/USER_GUIDE.md) · 🇰🇷 [ko](../ko/USER_GUIDE.md) · 🇸🇦 [ar](../ar/USER_GUIDE.md) · 🇮🇳 [in](../in/USER_GUIDE.md) · 🇹🇭 [th](../th/USER_GUIDE.md) · 🇻🇳 [vi](../vi/USER_GUIDE.md) · 🇮🇩 [id](../id/USER_GUIDE.md) · 🇲🇾 [ms](../ms/USER_GUIDE.md) · 🇳🇱 [nl](../nl/USER_GUIDE.md) · 🇵🇱 [pl](../pl/USER_GUIDE.md) · 🇸🇪 [sv](../sv/USER_GUIDE.md) · 🇳🇴 [no](../no/USER_GUIDE.md) · 🇩🇰 [da](../da/USER_GUIDE.md) · 🇫🇮 [fi](../fi/USER_GUIDE.md) · 🇵🇹 [pt](../pt/USER_GUIDE.md) · 🇷🇴 [ro](../ro/USER_GUIDE.md) · 🇭🇺 [hu](../hu/USER_GUIDE.md) · 🇧🇬 [bg](../bg/USER_GUIDE.md) · 🇸🇰 [sk](../sk/USER_GUIDE.md) · 🇺🇦 [uk-UA](../uk-UA/USER_GUIDE.md) · 🇮🇱 [he](../he/USER_GUIDE.md) · 🇵🇭 [phi](../phi/USER_GUIDE.md)
> 🇺🇸 [English](../../USER_GUIDE.md)
---
# User Guide
🌐 **Languages:** 🇺🇸 [English](USER_GUIDE.md) | 🇧🇷 [Português (Brasil)](i18n/pt-BR/USER_GUIDE.md) | 🇪🇸 [Español](i18n/es/USER_GUIDE.md) | 🇫🇷 [Français](i18n/fr/USER_GUIDE.md) | 🇮🇹 [Italiano](i18n/it/USER_GUIDE.md) | 🇷🇺 [Русский](i18n/ru/USER_GUIDE.md) | 🇨🇳 [中文 (简体)](i18n/zh-CN/USER_GUIDE.md) | 🇩🇪 [Deutsch](i18n/de/USER_GUIDE.md) | 🇮🇳 [हिन्दी](i18n/in/USER_GUIDE.md) | 🇹🇭 [ไทย](i18n/th/USER_GUIDE.md) | 🇺🇦 [Українська](i18n/uk-UA/USER_GUIDE.md) | 🇸🇦 [العربية](i18n/ar/USER_GUIDE.md) | 🇯🇵 [日本語](i18n/ja/USER_GUIDE.md) | 🇻🇳 [Tiếng Việt](i18n/vi/USER_GUIDE.md) | 🇧🇬 [Български](i18n/bg/USER_GUIDE.md) | 🇩🇰 [Dansk](i18n/da/USER_GUIDE.md) | 🇫🇮 [Suomi](i18n/fi/USER_GUIDE.md) | 🇮🇱 [עברית](i18n/he/USER_GUIDE.md) | 🇭🇺 [Magyar](i18n/hu/USER_GUIDE.md) | 🇮🇩 [Bahasa Indonesia](i18n/id/USER_GUIDE.md) | 🇰🇷 [한국어](i18n/ko/USER_GUIDE.md) | 🇲🇾 [Bahasa Melayu](i18n/ms/USER_GUIDE.md) | 🇳🇱 [Nederlands](i18n/nl/USER_GUIDE.md) | 🇳🇴 [Norsk](i18n/no/USER_GUIDE.md) | 🇵🇹 [Português (Portugal)](i18n/pt/USER_GUIDE.md) | 🇷🇴 [Română](i18n/ro/USER_GUIDE.md) | 🇵🇱 [Polski](i18n/pl/USER_GUIDE.md) | 🇸🇰 [Slovenčina](i18n/sk/USER_GUIDE.md) | 🇸🇪 [Svenska](i18n/sv/USER_GUIDE.md) | 🇵🇭 [Filipino](i18n/phi/USER_GUIDE.md)
Complete guide for configuring providers, creating combos, integrating CLI tools, and deploying OmniRoute.
---
@@ -43,11 +43,11 @@ Complete guide for configuring providers, creating combos, integrating CLI tools
| **💰 CHEAP** | GLM-4.7 | $0.6/1M | Daily 10AM | Budget backup |
| | MiniMax M2.1 | $0.2/1M | 5-hour rolling | Cheapest option |
| | Kimi K2 | $9/mo flat | 10M tokens/mo | Predictable cost |
| **🆓 FREE** | iFlow | $0 | Unlimited | 8 models free |
| **🆓 FREE** | Qoder | $0 | Unlimited | 8 models free |
| | Qwen | $0 | Unlimited | 3 models free |
| | Kiro | $0 | Unlimited | Claude free |
**💡 Pro Tip:** Start with Gemini CLI (180K free/month) + iFlow (unlimited free) combo = $0 cost!
**💡 Pro Tip:** Start with Gemini CLI (180K free/month) + Qoder (unlimited free) combo = $0 cost!
---
@@ -197,10 +197,10 @@ Models:
### 🆓 FREE Providers
#### iFlow (8 FREE models)
#### Qoder (8 FREE models)
```bash
Dashboard → Connect iFlow → OAuth login → Unlimited usage
Dashboard → Connect Qoder → OAuth login → Unlimited usage
Models: if/kimi-k2-thinking, if/qwen3-coder-plus, if/glm-4.7, if/minimax-m2, if/deepseek-r1
```
@@ -409,6 +409,106 @@ docker run -d --name omniroute -p 20128:20128 --env-file ./.env -v omniroute-dat
For host-integrated mode with CLI binaries, see the Docker section in the main docs.
### Void Linux (xbps-src)
Void Linux users can package and install OmniRoute natively using the `xbps-src` cross-compilation framework. This automates the Node.js standalone build along with the required `better-sqlite3` native bindings.
<details>
<summary><b>View xbps-src template</b></summary>
```bash
# Template file for 'omniroute'
pkgname=omniroute
version=3.2.4
revision=1
hostmakedepends="nodejs python3 make"
depends="openssl"
short_desc="Universal AI gateway with smart routing for multiple LLM providers"
maintainer="zenobit <zenobit@disroot.org>"
license="MIT"
homepage="https://github.com/diegosouzapw/OmniRoute"
distfiles="https://github.com/diegosouzapw/OmniRoute/archive/refs/tags/v${version}.tar.gz"
checksum=009400afee90a9f32599d8fe734145cfd84098140b7287990183dde45ae2245b
system_accounts="_omniroute"
omniroute_homedir="/var/lib/omniroute"
export NODE_ENV=production
export npm_config_engine_strict=false
export npm_config_loglevel=error
export npm_config_fund=false
export npm_config_audit=false
do_build() {
# Determine target CPU arch for node-gyp
local _gyp_arch
case "$XBPS_TARGET_MACHINE" in
aarch64*) _gyp_arch=arm64 ;;
armv7*|armv6*) _gyp_arch=arm ;;
i686*) _gyp_arch=ia32 ;;
*) _gyp_arch=x64 ;;
esac
# 1) Install all deps skip scripts
NODE_ENV=development npm ci --ignore-scripts
# 2) Build the Next.js standalone bundle
npm run build
# 3) Copy static assets into standalone
cp -r .next/static .next/standalone/.next/static
[ -d public ] && cp -r public .next/standalone/public || true
# 4) Compile better-sqlite3 native binding
local _node_gyp=/usr/lib/node_modules/npm/node_modules/node-gyp/bin/node-gyp.js
(cd node_modules/better-sqlite3 && node "$_node_gyp" rebuild --arch="$_gyp_arch")
# 5) Place the compiled binding into the standalone bundle
local _bs3_release=.next/standalone/node_modules/better-sqlite3/build/Release
mkdir -p "$_bs3_release"
cp node_modules/better-sqlite3/build/Release/better_sqlite3.node "$_bs3_release/"
# 6) Remove arch-specific sharp bundles
rm -rf .next/standalone/node_modules/@img
# 7) Copy pino runtime deps omitted by Next.js static analysis:
for _mod in pino-abstract-transport split2 process-warning; do
cp -r "node_modules/$_mod" .next/standalone/node_modules/
done
}
do_check() {
npm run test:unit
}
do_install() {
vmkdir usr/lib/omniroute/.next
vcopy .next/standalone/. usr/lib/omniroute/.next/standalone
# Prevent removal of empty Next.js app router dirs by the post-install hook
for _d in \
.next/standalone/.next/server/app/dashboard \
.next/standalone/.next/server/app/dashboard/settings \
.next/standalone/.next/server/app/dashboard/providers; do
touch "${DESTDIR}/usr/lib/omniroute/${_d}/.keep"
done
cat > "${WRKDIR}/omniroute" <<'EOF'
#!/bin/sh
export PORT="${PORT:-20128}"
export DATA_DIR="${DATA_DIR:-${XDG_DATA_HOME:-${HOME}/.local/share}/omniroute}"
export LOG_TO_FILE="${LOG_TO_FILE:-false}"
mkdir -p "${DATA_DIR}"
exec node /usr/lib/omniroute/.next/standalone/server.js "$@"
EOF
vbin "${WRKDIR}/omniroute"
}
post_install() {
vlicense LICENSE
}
```
</details>
### Environment Variables
| Variable | Default | Description |
@@ -450,7 +550,7 @@ For the full environment variable reference, see the [README](../README.md).
**MiniMax (`minimax/`)** — $0.2/1M: `minimax/MiniMax-M2.1`
**iFlow (`if/`)** — FREE: `if/kimi-k2-thinking`, `if/qwen3-coder-plus`, `if/deepseek-r1`
**Qoder (`if/`)** — FREE: `if/kimi-k2-thinking`, `if/qwen3-coder-plus`, `if/deepseek-r1`
**Qwen (`qw/`)** — FREE: `qw/qwen3-coder-plus`, `qw/qwen3-coder-flash`
@@ -582,6 +682,22 @@ Configure via **Dashboard → Settings → Routing**.
| **Least Used** | Routes to the account with the oldest `lastUsedAt` timestamp, distributing traffic evenly |
| **Cost Optimized** | Routes to the account with the lowest priority value, optimizing for lowest-cost providers |
#### External Sticky Session Header
For external session affinity (for example, Claude Code/Codex agents behind reverse proxies), send:
```http
X-Session-Id: your-session-key
```
OmniRoute also accepts `x_session_id` and returns the effective session key in `X-OmniRoute-Session-Id`.
If you use Nginx and send underscore-form headers, enable:
```nginx
underscores_in_headers on;
```
#### Wildcard Model Aliases
Create wildcard patterns to remap model names:
@@ -766,7 +882,7 @@ Access via **Dashboard → Health**. Real-time system health overview with 6 car
OmniRoute is available as a native desktop application for Windows, macOS, and Linux.
### Installation
### Installer
```bash
# From the electron directory:
+145
View File
@@ -0,0 +1,145 @@
# OmniRoute — Dashboard Features Gallery (Dansk)
🌐 **Languages:** 🇺🇸 [English](../../../../docs/FEATURES.md) · 🇪🇸 [es](../../es/docs/FEATURES.md) · 🇫🇷 [fr](../../fr/docs/FEATURES.md) · 🇩🇪 [de](../../de/docs/FEATURES.md) · 🇮🇹 [it](../../it/docs/FEATURES.md) · 🇷🇺 [ru](../../ru/docs/FEATURES.md) · 🇨🇳 [zh-CN](../../zh-CN/docs/FEATURES.md) · 🇯🇵 [ja](../../ja/docs/FEATURES.md) · 🇰🇷 [ko](../../ko/docs/FEATURES.md) · 🇸🇦 [ar](../../ar/docs/FEATURES.md) · 🇮🇳 [in](../../in/docs/FEATURES.md) · 🇹🇭 [th](../../th/docs/FEATURES.md) · 🇻🇳 [vi](../../vi/docs/FEATURES.md) · 🇮🇩 [id](../../id/docs/FEATURES.md) · 🇲🇾 [ms](../../ms/docs/FEATURES.md) · 🇳🇱 [nl](../../nl/docs/FEATURES.md) · 🇵🇱 [pl](../../pl/docs/FEATURES.md) · 🇸🇪 [sv](../../sv/docs/FEATURES.md) · 🇳🇴 [no](../../no/docs/FEATURES.md) · 🇩🇰 [da](../../da/docs/FEATURES.md) · 🇫🇮 [fi](../../fi/docs/FEATURES.md) · 🇵🇹 [pt](../../pt/docs/FEATURES.md) · 🇷🇴 [ro](../../ro/docs/FEATURES.md) · 🇭🇺 [hu](../../hu/docs/FEATURES.md) · 🇧🇬 [bg](../../bg/docs/FEATURES.md) · 🇸🇰 [sk](../../sk/docs/FEATURES.md) · 🇺🇦 [uk-UA](../../uk-UA/docs/FEATURES.md) · 🇮🇱 [he](../../he/docs/FEATURES.md) · 🇵🇭 [phi](../../phi/docs/FEATURES.md) · 🇧🇷 [pt-BR](../../pt-BR/docs/FEATURES.md)
---
Visual guide to every section of the OmniRoute dashboard.
---
## 🔌 Providers
Manage AI provider connections: OAuth providers (Claude Code, Codex, Gemini CLI), API key providers (Groq, DeepSeek, OpenRouter), and free providers (iFlow, Qwen, Kiro). Kiro accounts include credit balance tracking — remaining credits, total allowance, and renewal date visible in Dashboard → Usage.
![Providers Dashboard](screenshots/01-providers.png)
---
## 🎨 Combos
Create model routing combos with 6 strategies: priority, weighted, round-robin, random, least-used, and cost-optimized. Each combo chains multiple models with automatic fallback and includes quick templates and readiness checks.
![Combos Dashboard](screenshots/02-combos.png)
---
## 📊 Analytics
Comprehensive usage analytics with token consumption, cost estimates, activity heatmaps, weekly distribution charts, and per-provider breakdowns.
![Analytics Dashboard](screenshots/03-analytics.png)
---
## 🏥 System Health
Real-time monitoring: uptime, memory, version, latency percentiles (p50/p95/p99), cache statistics, and provider circuit breaker states.
![Health Dashboard](screenshots/04-health.png)
---
## 🔧 Translator Playground
Four modes for debugging API translations: **Playground** (format converter), **Chat Tester** (live requests), **Test Bench** (batch tests), and **Live Monitor** (real-time stream).
![Translator Playground](screenshots/05-translator.png)
---
## 🎮 Model Playground _(v2.0.9+)_
Test any model directly from the dashboard. Select provider, model, and endpoint, write prompts with Monaco Editor, stream responses in real-time, abort mid-stream, and view timing metrics.
---
## 🎨 Themes _(v2.0.5+)_
Customizable color themes for the entire dashboard. Choose from 7 preset colors (Coral, Blue, Red, Green, Violet, Orange, Cyan) or create a custom theme by picking any hex color. Supports light, dark, and system mode.
---
## ⚙️ Settings
Comprehensive settings panel with tabs:
- **General** — System storage, backup management (export/import database)
- **Appearance** — Theme selector (dark/light/system), color theme presets and custom colors, health log visibility, sidebar item visibility controls
- **Security** — API endpoint protection, custom provider blocking, IP filtering, session info
- **Routing** — Model aliases, background task degradation
- **Resilience** — Rate limit persistence, circuit breaker tuning, auto-disable banned accounts, provider expiration monitoring
- **Advanced** — Configuration overrides, configuration audit trail, fallback degradation mode
![Settings Dashboard](screenshots/06-settings.png)
---
## 🔧 CLI Tools
One-click configuration for AI coding tools: Claude Code, Codex CLI, Gemini CLI, OpenClaw, Kilo Code, Antigravity, Cline, Continue, Cursor, and Factory Droid. Features automated config apply/reset, connection profiles, and model mapping.
![CLI Tools Dashboard](screenshots/07-cli-tools.png)
---
## 🤖 CLI Agents _(v2.0.11+)_
Dashboard for discovering and managing CLI agents. Shows a grid of 14 built-in agents (Codex, Claude, Goose, Gemini CLI, OpenClaw, Aider, OpenCode, Cline, Qwen Code, ForgeCode, Amazon Q, Open Interpreter, Cursor CLI, Warp) with:
- **Installation status** — Installed / Not Found with version detection
- **Protocol badges** — stdio, HTTP, etc.
- **Custom agents** — Register any CLI tool via form (name, binary, version command, spawn args)
- **CLI Fingerprint Matching** — Per-provider toggle to match native CLI request signatures, reducing ban risk while preserving proxy IP
---
## 🖼️ Media _(v2.0.3+)_
Generate images, videos, and music from the dashboard. Supports OpenAI, xAI, Together, Hyperbolic, SD WebUI, ComfyUI, AnimateDiff, Stable Audio Open, and MusicGen.
---
## 📝 Request Logs
Real-time request logging with filtering by provider, model, account, and API key. Shows status codes, token usage, latency, and response details.
![Usage Logs](screenshots/08-usage.png)
---
## 🌐 API Endpoint
Your unified API endpoint with capability breakdown: Chat Completions, Responses API, Embeddings, Image Generation, Reranking, Audio Transcription, Text-to-Speech, Moderations, and registered API keys. Cloudflare Quick Tunnel integration and cloud proxy support for remote access.
![Endpoint Dashboard](screenshots/09-endpoint.png)
---
## 🔑 API Key Management
Create, scope, and revoke API keys. Each key can be restricted to specific models/providers with full access or read-only permissions. Visual key management with usage tracking.
---
## 📋 Audit Log
Administrative action tracking with filtering by action type, actor, target, IP address, and timestamp. Full security event history.
---
## 🖥️ Desktop Application
Native Electron desktop app for Windows, macOS, and Linux. Run OmniRoute as a standalone application with system tray integration, offline support, auto-update, and one-click install.
Key features:
- Server readiness polling (no blank screen on cold start)
- System tray with port management
- Content Security Policy
- Single-instance lock
- Auto-update on restart
- Platform-conditional UI (macOS traffic lights, Windows/Linux default titlebar)
- Hardened Electron build packaging — symlinked `node_modules` in the standalone bundle is detected and rejected before packaging, preventing runtime dependency on the build machine (v2.5.5+)
📖 See [`electron/README.md`](../electron/README.md) for full documentation.
+4 -4
View File
@@ -90,7 +90,7 @@ flowchart LR
end
subgraph Upstreams[Upstream Providers]
P1[OAuth Providers\nClaude/Codex/Gemini/Qwen/iFlow/GitHub/Kiro/Cursor/Antigravity]
P1[OAuth Providers\nClaude/Codex/Gemini/Qwen/Qoder/GitHub/Kiro/Cursor/Antigravity]
P2[API Key Providers\nOpenAI/Anthropic/OpenRouter/GLM/Kimi/MiniMax\nDeepSeek/Groq/xAI/Mistral/Perplexity\nTogether/Fireworks/Cerebras/Cohere/NVIDIA]
P3[Compatible Nodes\nOpenAI-compatible / Anthropic-compatible]
end
@@ -224,7 +224,7 @@ Domain layer modules:
OAuth provider modules (12 individual files under `src/lib/oauth/providers/`):
- Registry index: `src/lib/oauth/providers/index.ts`
- Individual providers: `claude.ts`, `codex.ts`, `gemini.ts`, `antigravity.ts`, `iflow.ts`, `qwen.ts`, `kimi-coding.ts`, `github.ts`, `kiro.ts`, `cursor.ts`, `kilocode.ts`, `cline.ts`
- Individual providers: `claude.ts`, `codex.ts`, `gemini.ts`, `antigravity.ts`, `qoder.ts`, `qwen.ts`, `kimi-coding.ts`, `github.ts`, `kiro.ts`, `cursor.ts`, `kilocode.ts`, `cline.ts`
- Thin wrapper: `src/lib/oauth/providers.ts` — re-exports from individual modules
## 3) Persistence Layer
@@ -597,7 +597,7 @@ Each provider has a specialized executor extending `BaseExecutor` (in `open-sse/
| Executor | Provider(s) | Special Handling |
| --------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------- |
| `DefaultExecutor` | OpenAI, Claude, Gemini, Qwen, iFlow, OpenRouter, GLM, Kimi, MiniMax, DeepSeek, Groq, xAI, Mistral, Perplexity, Together, Fireworks, Cerebras, Cohere, NVIDIA | Dynamic URL/header config per provider |
| `DefaultExecutor` | OpenAI, Claude, Gemini, Qwen, Qoder, OpenRouter, GLM, Kimi, MiniMax, DeepSeek, Groq, xAI, Mistral, Perplexity, Together, Fireworks, Cerebras, Cohere, NVIDIA | Dynamic URL/header config per provider |
| `AntigravityExecutor` | Google Antigravity | Custom project/session IDs, Retry-After parsing |
| `CodexExecutor` | OpenAI Codex | Injects system instructions, forces reasoning effort |
| `CursorExecutor` | Cursor IDE | ConnectRPC protocol, Protobuf encoding, request signing via checksum |
@@ -621,7 +621,7 @@ All other providers (including custom compatible nodes) use the `DefaultExecutor
| Cursor | cursor | Custom checksum | ✅ | ✅ | ❌ | ❌ |
| Kiro | kiro | AWS SSO OIDC | ✅ (EventStream) | ❌ | ✅ | ✅ Usage limits |
| Qwen | openai | OAuth | ✅ | ✅ | ✅ | ⚠️ Per request |
| iFlow | openai | OAuth (Basic) | ✅ | ✅ | ✅ | ⚠️ Per request |
| Qoder | openai | OAuth (Basic) | ✅ | ✅ | ✅ | ⚠️ Per request |
| OpenRouter | openai | API Key | ✅ | ✅ | ❌ | ❌ |
| GLM/Kimi/MiniMax | claude | API Key | ✅ | ✅ | ❌ | ❌ |
| DeepSeek | openai | API Key | ✅ | ✅ | ❌ | ❌ |
+2 -2
View File
@@ -271,7 +271,7 @@ Business logic that supports the handlers and executors.
| `provider.ts` | **Format detection** (`detectFormat`): analyzes request body structure to identify Claude/OpenAI/Gemini/Antigravity/Responses formats (includes `max_tokens` heuristic for Claude). Also: URL building, header building, thinking config normalization. Supports `openai-compatible-*` and `anthropic-compatible-*` dynamic providers. |
| `model.ts` | Model string parsing (`claude/model-name``{provider: "claude", model: "model-name"}`), alias resolution with collision detection, input sanitization (rejects path traversal/control chars), and model info resolution with async alias getter support. |
| `accountFallback.ts` | Rate-limit handling: exponential backoff (1s → 2s → 4s → max 2min), account cooldown management, error classification (which errors trigger fallback vs. not). |
| `tokenRefresh.ts` | OAuth token refresh for **every provider**: Google (Gemini, Antigravity), Claude, Codex, Qwen, iFlow, GitHub (OAuth + Copilot dual-token), Kiro (AWS SSO OIDC + Social Auth). Includes in-flight promise deduplication cache and retry with exponential backoff. |
| `tokenRefresh.ts` | OAuth token refresh for **every provider**: Google (Gemini, Antigravity), Claude, Codex, Qwen, Qoder, GitHub (OAuth + Copilot dual-token), Kiro (AWS SSO OIDC + Social Auth). Includes in-flight promise deduplication cache and retry with exponential backoff. |
| `combo.ts` | **Combo models**: chains of fallback models. If model A fails with a fallback-eligible error, try model B, then C, etc. Returns actual upstream status codes. |
| `usage.ts` | Fetches quota/usage data from provider APIs (GitHub Copilot quotas, Antigravity model quotas, Codex rate limits, Kiro usage breakdowns, Claude settings). |
| `accountSelector.ts` | Smart account selection with scoring algorithm: considers priority, health status, round-robin position, and cooldown state to pick the optimal account for each request. |
@@ -543,7 +543,7 @@ A 2000-token buffer is added to reported usage to prevent clients from hitting c
| Kiro (AWS) | AWS SSO OIDC or Social | Kiro | Binary EventStream parsing |
| Cursor IDE | Checksum auth | Cursor | Protobuf encoding, SHA-256 checksums |
| Qwen | OAuth | Default | Standard auth |
| iFlow | OAuth (Basic + Bearer) | Default | Dual auth header |
| Qoder | OAuth (Basic + Bearer) | Default | Dual auth header |
| OpenRouter | API key | Default | Standard Bearer auth |
| GLM, Kimi, MiniMax | API key | Default | Claude-compatible, use `x-api-key` |
| `openai-compatible-*` | API key | Default | Dynamic: any OpenAI-compatible endpoint |
+2 -2
View File
@@ -12,7 +12,7 @@ Visual guide to every section of the OmniRoute dashboard.
## 🔌 Providers
Manage AI provider connections: OAuth providers (Claude Code, Codex, Gemini CLI), API key providers (Groq, DeepSeek, OpenRouter), and free providers (iFlow, Qwen, Kiro). Kiro accounts include credit balance tracking — remaining credits, total allowance, and renewal date visible in Dashboard → Usage.
Manage AI provider connections: OAuth providers (Claude Code, Codex, Gemini CLI), API key providers (Groq, DeepSeek, OpenRouter), and free providers (Qoder, Qwen, Kiro). Kiro accounts include credit balance tracking — remaining credits, total allowance, and renewal date visible in Dashboard → Usage.
![Providers Dashboard](screenshots/01-providers.png)
@@ -67,7 +67,7 @@ Customizable color themes for the entire dashboard. Choose from 7 preset colors
Comprehensive settings panel with tabs:
- **General** — System storage, backup management (export/import database)
- **Appearance** — Theme selector (dark/light/system), color theme presets and custom colors, health log visibility
- **Appearance** — Theme selector (dark/light/system), color theme presets and custom colors, health log visibility, sidebar item visibility controls
- **Security** — API endpoint protection, custom provider blocking, IP filtering, session info
- **Routing** — Model aliases, background task degradation
- **Resilience** — Rate limit persistence, circuit breaker tuning
+1164 -700
View File
File diff suppressed because it is too large Load Diff
+1 -1
View File
@@ -101,7 +101,7 @@ curl -s http://localhost:20128/api/cli-tools/openclaw-settings | jq '{installed,
1. Check usage stats in Dashboard → Usage
2. Switch primary model to GLM/MiniMax
3. Use free tier (Gemini CLI, iFlow) for non-critical tasks
3. Use free tier (Gemini CLI, Qoder) for non-critical tasks
4. Set cost budgets per API key: Dashboard → API Keys → Budget
---
+127 -11
View File
@@ -1,11 +1,11 @@
🌐 **Languages:** 🇺🇸 [English](../../README.md) · 🇧🇷 [pt-BR](../pt-BR/USER_GUIDE.md) · 🇪🇸 [es](../es/USER_GUIDE.md) · 🇫🇷 [fr](../fr/USER_GUIDE.md) · 🇩🇪 [de](../de/USER_GUIDE.md) · 🇮🇹 [it](../it/USER_GUIDE.md) · 🇷🇺 [ru](../ru/USER_GUIDE.md) · 🇨🇳 [zh-CN](../zh-CN/USER_GUIDE.md) · 🇯🇵 [ja](../ja/USER_GUIDE.md) · 🇰🇷 [ko](../ko/USER_GUIDE.md) · 🇸🇦 [ar](../ar/USER_GUIDE.md) · 🇮🇳 [in](../in/USER_GUIDE.md) · 🇹🇭 [th](../th/USER_GUIDE.md) · 🇻🇳 [vi](../vi/USER_GUIDE.md) · 🇮🇩 [id](../id/USER_GUIDE.md) · 🇲🇾 [ms](../ms/USER_GUIDE.md) · 🇳🇱 [nl](../nl/USER_GUIDE.md) · 🇵🇱 [pl](../pl/USER_GUIDE.md) · 🇸🇪 [sv](../sv/USER_GUIDE.md) · 🇳🇴 [no](../no/USER_GUIDE.md) · 🇩🇰 [da](../da/USER_GUIDE.md) · 🇫🇮 [fi](../fi/USER_GUIDE.md) · 🇵🇹 [pt](../pt/USER_GUIDE.md) · 🇷🇴 [ro](../ro/USER_GUIDE.md) · 🇭🇺 [hu](../hu/USER_GUIDE.md) · 🇧🇬 [bg](../bg/USER_GUIDE.md) · 🇸🇰 [sk](../sk/USER_GUIDE.md) · 🇺🇦 [uk-UA](../uk-UA/USER_GUIDE.md) · 🇮🇱 [he](../he/USER_GUIDE.md) · 🇵🇭 [phi](../phi/USER_GUIDE.md)
# User Guide (Deutsch)
🌐 **Languages:** 🇺🇸 [English](../../USER_GUIDE.md) · 🇧🇷 [pt-BR](../pt-BR/USER_GUIDE.md) · 🇪🇸 [es](../es/USER_GUIDE.md) · 🇫🇷 [fr](../fr/USER_GUIDE.md) · 🇩🇪 [de](../de/USER_GUIDE.md) · 🇮🇹 [it](../it/USER_GUIDE.md) · 🇷🇺 [ru](../ru/USER_GUIDE.md) · 🇨🇳 [zh-CN](../zh-CN/USER_GUIDE.md) · 🇯🇵 [ja](../ja/USER_GUIDE.md) · 🇰🇷 [ko](../ko/USER_GUIDE.md) · 🇸🇦 [ar](../ar/USER_GUIDE.md) · 🇮🇳 [in](../in/USER_GUIDE.md) · 🇹🇭 [th](../th/USER_GUIDE.md) · 🇻🇳 [vi](../vi/USER_GUIDE.md) · 🇮🇩 [id](../id/USER_GUIDE.md) · 🇲🇾 [ms](../ms/USER_GUIDE.md) · 🇳🇱 [nl](../nl/USER_GUIDE.md) · 🇵🇱 [pl](../pl/USER_GUIDE.md) · 🇸🇪 [sv](../sv/USER_GUIDE.md) · 🇳🇴 [no](../no/USER_GUIDE.md) · 🇩🇰 [da](../da/USER_GUIDE.md) · 🇫🇮 [fi](../fi/USER_GUIDE.md) · 🇵🇹 [pt](../pt/USER_GUIDE.md) · 🇷🇴 [ro](../ro/USER_GUIDE.md) · 🇭🇺 [hu](../hu/USER_GUIDE.md) · 🇧🇬 [bg](../bg/USER_GUIDE.md) · 🇸🇰 [sk](../sk/USER_GUIDE.md) · 🇺🇦 [uk-UA](../uk-UA/USER_GUIDE.md) · 🇮🇱 [he](../he/USER_GUIDE.md) · 🇵🇭 [phi](../phi/USER_GUIDE.md)
> 🇺🇸 [English](../../USER_GUIDE.md)
---
# User Guide
🌐 **Languages:** 🇺🇸 [English](USER_GUIDE.md) | 🇧🇷 [Português (Brasil)](i18n/pt-BR/USER_GUIDE.md) | 🇪🇸 [Español](i18n/es/USER_GUIDE.md) | 🇫🇷 [Français](i18n/fr/USER_GUIDE.md) | 🇮🇹 [Italiano](i18n/it/USER_GUIDE.md) | 🇷🇺 [Русский](i18n/ru/USER_GUIDE.md) | 🇨🇳 [中文 (简体)](i18n/zh-CN/USER_GUIDE.md) | 🇩🇪 [Deutsch](i18n/de/USER_GUIDE.md) | 🇮🇳 [हिन्दी](i18n/in/USER_GUIDE.md) | 🇹🇭 [ไทย](i18n/th/USER_GUIDE.md) | 🇺🇦 [Українська](i18n/uk-UA/USER_GUIDE.md) | 🇸🇦 [العربية](i18n/ar/USER_GUIDE.md) | 🇯🇵 [日本語](i18n/ja/USER_GUIDE.md) | 🇻🇳 [Tiếng Việt](i18n/vi/USER_GUIDE.md) | 🇧🇬 [Български](i18n/bg/USER_GUIDE.md) | 🇩🇰 [Dansk](i18n/da/USER_GUIDE.md) | 🇫🇮 [Suomi](i18n/fi/USER_GUIDE.md) | 🇮🇱 [עברית](i18n/he/USER_GUIDE.md) | 🇭🇺 [Magyar](i18n/hu/USER_GUIDE.md) | 🇮🇩 [Bahasa Indonesia](i18n/id/USER_GUIDE.md) | 🇰🇷 [한국어](i18n/ko/USER_GUIDE.md) | 🇲🇾 [Bahasa Melayu](i18n/ms/USER_GUIDE.md) | 🇳🇱 [Nederlands](i18n/nl/USER_GUIDE.md) | 🇳🇴 [Norsk](i18n/no/USER_GUIDE.md) | 🇵🇹 [Português (Portugal)](i18n/pt/USER_GUIDE.md) | 🇷🇴 [Română](i18n/ro/USER_GUIDE.md) | 🇵🇱 [Polski](i18n/pl/USER_GUIDE.md) | 🇸🇰 [Slovenčina](i18n/sk/USER_GUIDE.md) | 🇸🇪 [Svenska](i18n/sv/USER_GUIDE.md) | 🇵🇭 [Filipino](i18n/phi/USER_GUIDE.md)
Complete guide for configuring providers, creating combos, integrating CLI tools, and deploying OmniRoute.
---
@@ -43,11 +43,11 @@ Complete guide for configuring providers, creating combos, integrating CLI tools
| **💰 CHEAP** | GLM-4.7 | $0.6/1M | Daily 10AM | Budget backup |
| | MiniMax M2.1 | $0.2/1M | 5-hour rolling | Cheapest option |
| | Kimi K2 | $9/mo flat | 10M tokens/mo | Predictable cost |
| **🆓 FREE** | iFlow | $0 | Unlimited | 8 models free |
| **🆓 FREE** | Qoder | $0 | Unlimited | 8 models free |
| | Qwen | $0 | Unlimited | 3 models free |
| | Kiro | $0 | Unlimited | Claude free |
**💡 Pro Tip:** Start with Gemini CLI (180K free/month) + iFlow (unlimited free) combo = $0 cost!
**💡 Pro Tip:** Start with Gemini CLI (180K free/month) + Qoder (unlimited free) combo = $0 cost!
---
@@ -197,10 +197,10 @@ Models:
### 🆓 FREE Providers
#### iFlow (8 FREE models)
#### Qoder (8 FREE models)
```bash
Dashboard → Connect iFlow → OAuth login → Unlimited usage
Dashboard → Connect Qoder → OAuth login → Unlimited usage
Models: if/kimi-k2-thinking, if/qwen3-coder-plus, if/glm-4.7, if/minimax-m2, if/deepseek-r1
```
@@ -409,6 +409,106 @@ docker run -d --name omniroute -p 20128:20128 --env-file ./.env -v omniroute-dat
For host-integrated mode with CLI binaries, see the Docker section in the main docs.
### Void Linux (xbps-src)
Void Linux users can package and install OmniRoute natively using the `xbps-src` cross-compilation framework. This automates the Node.js standalone build along with the required `better-sqlite3` native bindings.
<details>
<summary><b>View xbps-src template</b></summary>
```bash
# Template file for 'omniroute'
pkgname=omniroute
version=3.2.4
revision=1
hostmakedepends="nodejs python3 make"
depends="openssl"
short_desc="Universal AI gateway with smart routing for multiple LLM providers"
maintainer="zenobit <zenobit@disroot.org>"
license="MIT"
homepage="https://github.com/diegosouzapw/OmniRoute"
distfiles="https://github.com/diegosouzapw/OmniRoute/archive/refs/tags/v${version}.tar.gz"
checksum=009400afee90a9f32599d8fe734145cfd84098140b7287990183dde45ae2245b
system_accounts="_omniroute"
omniroute_homedir="/var/lib/omniroute"
export NODE_ENV=production
export npm_config_engine_strict=false
export npm_config_loglevel=error
export npm_config_fund=false
export npm_config_audit=false
do_build() {
# Determine target CPU arch for node-gyp
local _gyp_arch
case "$XBPS_TARGET_MACHINE" in
aarch64*) _gyp_arch=arm64 ;;
armv7*|armv6*) _gyp_arch=arm ;;
i686*) _gyp_arch=ia32 ;;
*) _gyp_arch=x64 ;;
esac
# 1) Install all deps skip scripts
NODE_ENV=development npm ci --ignore-scripts
# 2) Build the Next.js standalone bundle
npm run build
# 3) Copy static assets into standalone
cp -r .next/static .next/standalone/.next/static
[ -d public ] && cp -r public .next/standalone/public || true
# 4) Compile better-sqlite3 native binding
local _node_gyp=/usr/lib/node_modules/npm/node_modules/node-gyp/bin/node-gyp.js
(cd node_modules/better-sqlite3 && node "$_node_gyp" rebuild --arch="$_gyp_arch")
# 5) Place the compiled binding into the standalone bundle
local _bs3_release=.next/standalone/node_modules/better-sqlite3/build/Release
mkdir -p "$_bs3_release"
cp node_modules/better-sqlite3/build/Release/better_sqlite3.node "$_bs3_release/"
# 6) Remove arch-specific sharp bundles
rm -rf .next/standalone/node_modules/@img
# 7) Copy pino runtime deps omitted by Next.js static analysis:
for _mod in pino-abstract-transport split2 process-warning; do
cp -r "node_modules/$_mod" .next/standalone/node_modules/
done
}
do_check() {
npm run test:unit
}
do_install() {
vmkdir usr/lib/omniroute/.next
vcopy .next/standalone/. usr/lib/omniroute/.next/standalone
# Prevent removal of empty Next.js app router dirs by the post-install hook
for _d in \
.next/standalone/.next/server/app/dashboard \
.next/standalone/.next/server/app/dashboard/settings \
.next/standalone/.next/server/app/dashboard/providers; do
touch "${DESTDIR}/usr/lib/omniroute/${_d}/.keep"
done
cat > "${WRKDIR}/omniroute" <<'EOF'
#!/bin/sh
export PORT="${PORT:-20128}"
export DATA_DIR="${DATA_DIR:-${XDG_DATA_HOME:-${HOME}/.local/share}/omniroute}"
export LOG_TO_FILE="${LOG_TO_FILE:-false}"
mkdir -p "${DATA_DIR}"
exec node /usr/lib/omniroute/.next/standalone/server.js "$@"
EOF
vbin "${WRKDIR}/omniroute"
}
post_install() {
vlicense LICENSE
}
```
</details>
### Environment Variables
| Variable | Default | Description |
@@ -450,7 +550,7 @@ For the full environment variable reference, see the [README](../README.md).
**MiniMax (`minimax/`)** — $0.2/1M: `minimax/MiniMax-M2.1`
**iFlow (`if/`)** — FREE: `if/kimi-k2-thinking`, `if/qwen3-coder-plus`, `if/deepseek-r1`
**Qoder (`if/`)** — FREE: `if/kimi-k2-thinking`, `if/qwen3-coder-plus`, `if/deepseek-r1`
**Qwen (`qw/`)** — FREE: `qw/qwen3-coder-plus`, `qw/qwen3-coder-flash`
@@ -582,6 +682,22 @@ Configure via **Dashboard → Settings → Routing**.
| **Least Used** | Routes to the account with the oldest `lastUsedAt` timestamp, distributing traffic evenly |
| **Cost Optimized** | Routes to the account with the lowest priority value, optimizing for lowest-cost providers |
#### External Sticky Session Header
For external session affinity (for example, Claude Code/Codex agents behind reverse proxies), send:
```http
X-Session-Id: your-session-key
```
OmniRoute also accepts `x_session_id` and returns the effective session key in `X-OmniRoute-Session-Id`.
If you use Nginx and send underscore-form headers, enable:
```nginx
underscores_in_headers on;
```
#### Wildcard Model Aliases
Create wildcard patterns to remap model names:
@@ -766,7 +882,7 @@ Access via **Dashboard → Health**. Real-time system health overview with 6 car
OmniRoute is available as a native desktop application for Windows, macOS, and Linux.
### Installation
### Installieren
```bash
# From the electron directory:
+145
View File
@@ -0,0 +1,145 @@
# OmniRoute — Dashboard Features Gallery (Deutsch)
🌐 **Languages:** 🇺🇸 [English](../../../../docs/FEATURES.md) · 🇪🇸 [es](../../es/docs/FEATURES.md) · 🇫🇷 [fr](../../fr/docs/FEATURES.md) · 🇩🇪 [de](../../de/docs/FEATURES.md) · 🇮🇹 [it](../../it/docs/FEATURES.md) · 🇷🇺 [ru](../../ru/docs/FEATURES.md) · 🇨🇳 [zh-CN](../../zh-CN/docs/FEATURES.md) · 🇯🇵 [ja](../../ja/docs/FEATURES.md) · 🇰🇷 [ko](../../ko/docs/FEATURES.md) · 🇸🇦 [ar](../../ar/docs/FEATURES.md) · 🇮🇳 [in](../../in/docs/FEATURES.md) · 🇹🇭 [th](../../th/docs/FEATURES.md) · 🇻🇳 [vi](../../vi/docs/FEATURES.md) · 🇮🇩 [id](../../id/docs/FEATURES.md) · 🇲🇾 [ms](../../ms/docs/FEATURES.md) · 🇳🇱 [nl](../../nl/docs/FEATURES.md) · 🇵🇱 [pl](../../pl/docs/FEATURES.md) · 🇸🇪 [sv](../../sv/docs/FEATURES.md) · 🇳🇴 [no](../../no/docs/FEATURES.md) · 🇩🇰 [da](../../da/docs/FEATURES.md) · 🇫🇮 [fi](../../fi/docs/FEATURES.md) · 🇵🇹 [pt](../../pt/docs/FEATURES.md) · 🇷🇴 [ro](../../ro/docs/FEATURES.md) · 🇭🇺 [hu](../../hu/docs/FEATURES.md) · 🇧🇬 [bg](../../bg/docs/FEATURES.md) · 🇸🇰 [sk](../../sk/docs/FEATURES.md) · 🇺🇦 [uk-UA](../../uk-UA/docs/FEATURES.md) · 🇮🇱 [he](../../he/docs/FEATURES.md) · 🇵🇭 [phi](../../phi/docs/FEATURES.md) · 🇧🇷 [pt-BR](../../pt-BR/docs/FEATURES.md)
---
Visual guide to every section of the OmniRoute dashboard.
---
## 🔌 Providers
Manage AI provider connections: OAuth providers (Claude Code, Codex, Gemini CLI), API key providers (Groq, DeepSeek, OpenRouter), and free providers (iFlow, Qwen, Kiro). Kiro accounts include credit balance tracking — remaining credits, total allowance, and renewal date visible in Dashboard → Usage.
![Providers Dashboard](screenshots/01-providers.png)
---
## 🎨 Combos
Create model routing combos with 6 strategies: priority, weighted, round-robin, random, least-used, and cost-optimized. Each combo chains multiple models with automatic fallback and includes quick templates and readiness checks.
![Combos Dashboard](screenshots/02-combos.png)
---
## 📊 Analytics
Comprehensive usage analytics with token consumption, cost estimates, activity heatmaps, weekly distribution charts, and per-provider breakdowns.
![Analytics Dashboard](screenshots/03-analytics.png)
---
## 🏥 System Health
Real-time monitoring: uptime, memory, version, latency percentiles (p50/p95/p99), cache statistics, and provider circuit breaker states.
![Health Dashboard](screenshots/04-health.png)
---
## 🔧 Translator Playground
Four modes for debugging API translations: **Playground** (format converter), **Chat Tester** (live requests), **Test Bench** (batch tests), and **Live Monitor** (real-time stream).
![Translator Playground](screenshots/05-translator.png)
---
## 🎮 Model Playground _(v2.0.9+)_
Test any model directly from the dashboard. Select provider, model, and endpoint, write prompts with Monaco Editor, stream responses in real-time, abort mid-stream, and view timing metrics.
---
## 🎨 Themes _(v2.0.5+)_
Customizable color themes for the entire dashboard. Choose from 7 preset colors (Coral, Blue, Red, Green, Violet, Orange, Cyan) or create a custom theme by picking any hex color. Supports light, dark, and system mode.
---
## ⚙️ Settings
Comprehensive settings panel with tabs:
- **General** — System storage, backup management (export/import database)
- **Appearance** — Theme selector (dark/light/system), color theme presets and custom colors, health log visibility, sidebar item visibility controls
- **Security** — API endpoint protection, custom provider blocking, IP filtering, session info
- **Routing** — Model aliases, background task degradation
- **Resilience** — Rate limit persistence, circuit breaker tuning, auto-disable banned accounts, provider expiration monitoring
- **Advanced** — Configuration overrides, configuration audit trail, fallback degradation mode
![Settings Dashboard](screenshots/06-settings.png)
---
## 🔧 CLI Tools
One-click configuration for AI coding tools: Claude Code, Codex CLI, Gemini CLI, OpenClaw, Kilo Code, Antigravity, Cline, Continue, Cursor, and Factory Droid. Features automated config apply/reset, connection profiles, and model mapping.
![CLI Tools Dashboard](screenshots/07-cli-tools.png)
---
## 🤖 CLI Agents _(v2.0.11+)_
Dashboard for discovering and managing CLI agents. Shows a grid of 14 built-in agents (Codex, Claude, Goose, Gemini CLI, OpenClaw, Aider, OpenCode, Cline, Qwen Code, ForgeCode, Amazon Q, Open Interpreter, Cursor CLI, Warp) with:
- **Installation status** — Installed / Not Found with version detection
- **Protocol badges** — stdio, HTTP, etc.
- **Custom agents** — Register any CLI tool via form (name, binary, version command, spawn args)
- **CLI Fingerprint Matching** — Per-provider toggle to match native CLI request signatures, reducing ban risk while preserving proxy IP
---
## 🖼️ Media _(v2.0.3+)_
Generate images, videos, and music from the dashboard. Supports OpenAI, xAI, Together, Hyperbolic, SD WebUI, ComfyUI, AnimateDiff, Stable Audio Open, and MusicGen.
---
## 📝 Request Logs
Real-time request logging with filtering by provider, model, account, and API key. Shows status codes, token usage, latency, and response details.
![Usage Logs](screenshots/08-usage.png)
---
## 🌐 API Endpoint
Your unified API endpoint with capability breakdown: Chat Completions, Responses API, Embeddings, Image Generation, Reranking, Audio Transcription, Text-to-Speech, Moderations, and registered API keys. Cloudflare Quick Tunnel integration and cloud proxy support for remote access.
![Endpoint Dashboard](screenshots/09-endpoint.png)
---
## 🔑 API Key Management
Create, scope, and revoke API keys. Each key can be restricted to specific models/providers with full access or read-only permissions. Visual key management with usage tracking.
---
## 📋 Audit Log
Administrative action tracking with filtering by action type, actor, target, IP address, and timestamp. Full security event history.
---
## 🖥️ Desktop Application
Native Electron desktop app for Windows, macOS, and Linux. Run OmniRoute as a standalone application with system tray integration, offline support, auto-update, and one-click install.
Key features:
- Server readiness polling (no blank screen on cold start)
- System tray with port management
- Content Security Policy
- Single-instance lock
- Auto-update on restart
- Platform-conditional UI (macOS traffic lights, Windows/Linux default titlebar)
- Hardened Electron build packaging — symlinked `node_modules` in the standalone bundle is detected and rejected before packaging, preventing runtime dependency on the build machine (v2.5.5+)
📖 See [`electron/README.md`](../electron/README.md) for full documentation.
+4 -4
View File
@@ -90,7 +90,7 @@ flowchart LR
end
subgraph Upstreams[Upstream Providers]
P1[OAuth Providers\nClaude/Codex/Gemini/Qwen/iFlow/GitHub/Kiro/Cursor/Antigravity]
P1[OAuth Providers\nClaude/Codex/Gemini/Qwen/Qoder/GitHub/Kiro/Cursor/Antigravity]
P2[API Key Providers\nOpenAI/Anthropic/OpenRouter/GLM/Kimi/MiniMax\nDeepSeek/Groq/xAI/Mistral/Perplexity\nTogether/Fireworks/Cerebras/Cohere/NVIDIA]
P3[Compatible Nodes\nOpenAI-compatible / Anthropic-compatible]
end
@@ -224,7 +224,7 @@ Domain layer modules:
OAuth provider modules (12 individual files under `src/lib/oauth/providers/`):
- Registry index: `src/lib/oauth/providers/index.ts`
- Individual providers: `claude.ts`, `codex.ts`, `gemini.ts`, `antigravity.ts`, `iflow.ts`, `qwen.ts`, `kimi-coding.ts`, `github.ts`, `kiro.ts`, `cursor.ts`, `kilocode.ts`, `cline.ts`
- Individual providers: `claude.ts`, `codex.ts`, `gemini.ts`, `antigravity.ts`, `qoder.ts`, `qwen.ts`, `kimi-coding.ts`, `github.ts`, `kiro.ts`, `cursor.ts`, `kilocode.ts`, `cline.ts`
- Thin wrapper: `src/lib/oauth/providers.ts` — re-exports from individual modules
## 3) Persistence Layer
@@ -597,7 +597,7 @@ Each provider has a specialized executor extending `BaseExecutor` (in `open-sse/
| Executor | Provider(s) | Special Handling |
| --------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------- |
| `DefaultExecutor` | OpenAI, Claude, Gemini, Qwen, iFlow, OpenRouter, GLM, Kimi, MiniMax, DeepSeek, Groq, xAI, Mistral, Perplexity, Together, Fireworks, Cerebras, Cohere, NVIDIA | Dynamic URL/header config per provider |
| `DefaultExecutor` | OpenAI, Claude, Gemini, Qwen, Qoder, OpenRouter, GLM, Kimi, MiniMax, DeepSeek, Groq, xAI, Mistral, Perplexity, Together, Fireworks, Cerebras, Cohere, NVIDIA | Dynamic URL/header config per provider |
| `AntigravityExecutor` | Google Antigravity | Custom project/session IDs, Retry-After parsing |
| `CodexExecutor` | OpenAI Codex | Injects system instructions, forces reasoning effort |
| `CursorExecutor` | Cursor IDE | ConnectRPC protocol, Protobuf encoding, request signing via checksum |
@@ -621,7 +621,7 @@ All other providers (including custom compatible nodes) use the `DefaultExecutor
| Cursor | cursor | Custom checksum | ✅ | ✅ | ❌ | ❌ |
| Kiro | kiro | AWS SSO OIDC | ✅ (EventStream) | ❌ | ✅ | ✅ Usage limits |
| Qwen | openai | OAuth | ✅ | ✅ | ✅ | ⚠️ Per request |
| iFlow | openai | OAuth (Basic) | ✅ | ✅ | ✅ | ⚠️ Per request |
| Qoder | openai | OAuth (Basic) | ✅ | ✅ | ✅ | ⚠️ Per request |
| OpenRouter | openai | API Key | ✅ | ✅ | ❌ | ❌ |
| GLM/Kimi/MiniMax | claude | API Key | ✅ | ✅ | ❌ | ❌ |
| DeepSeek | openai | API Key | ✅ | ✅ | ❌ | ❌ |
+2 -2
View File
@@ -271,7 +271,7 @@ Business logic that supports the handlers and executors.
| `provider.ts` | **Format detection** (`detectFormat`): analyzes request body structure to identify Claude/OpenAI/Gemini/Antigravity/Responses formats (includes `max_tokens` heuristic for Claude). Also: URL building, header building, thinking config normalization. Supports `openai-compatible-*` and `anthropic-compatible-*` dynamic providers. |
| `model.ts` | Model string parsing (`claude/model-name``{provider: "claude", model: "model-name"}`), alias resolution with collision detection, input sanitization (rejects path traversal/control chars), and model info resolution with async alias getter support. |
| `accountFallback.ts` | Rate-limit handling: exponential backoff (1s → 2s → 4s → max 2min), account cooldown management, error classification (which errors trigger fallback vs. not). |
| `tokenRefresh.ts` | OAuth token refresh for **every provider**: Google (Gemini, Antigravity), Claude, Codex, Qwen, iFlow, GitHub (OAuth + Copilot dual-token), Kiro (AWS SSO OIDC + Social Auth). Includes in-flight promise deduplication cache and retry with exponential backoff. |
| `tokenRefresh.ts` | OAuth token refresh for **every provider**: Google (Gemini, Antigravity), Claude, Codex, Qwen, Qoder, GitHub (OAuth + Copilot dual-token), Kiro (AWS SSO OIDC + Social Auth). Includes in-flight promise deduplication cache and retry with exponential backoff. |
| `combo.ts` | **Combo models**: chains of fallback models. If model A fails with a fallback-eligible error, try model B, then C, etc. Returns actual upstream status codes. |
| `usage.ts` | Fetches quota/usage data from provider APIs (GitHub Copilot quotas, Antigravity model quotas, Codex rate limits, Kiro usage breakdowns, Claude settings). |
| `accountSelector.ts` | Smart account selection with scoring algorithm: considers priority, health status, round-robin position, and cooldown state to pick the optimal account for each request. |
@@ -543,7 +543,7 @@ A 2000-token buffer is added to reported usage to prevent clients from hitting c
| Kiro (AWS) | AWS SSO OIDC or Social | Kiro | Binary EventStream parsing |
| Cursor IDE | Checksum auth | Cursor | Protobuf encoding, SHA-256 checksums |
| Qwen | OAuth | Default | Standard auth |
| iFlow | OAuth (Basic + Bearer) | Default | Dual auth header |
| Qoder | OAuth (Basic + Bearer) | Default | Dual auth header |
| OpenRouter | API key | Default | Standard Bearer auth |
| GLM, Kimi, MiniMax | API key | Default | Claude-compatible, use `x-api-key` |
| `openai-compatible-*` | API key | Default | Dynamic: any OpenAI-compatible endpoint |
+2 -2
View File
@@ -12,7 +12,7 @@ Visual guide to every section of the OmniRoute dashboard.
## 🔌 Providers
Manage AI provider connections: OAuth providers (Claude Code, Codex, Gemini CLI), API key providers (Groq, DeepSeek, OpenRouter), and free providers (iFlow, Qwen, Kiro). Kiro accounts include credit balance tracking — remaining credits, total allowance, and renewal date visible in Dashboard → Usage.
Manage AI provider connections: OAuth providers (Claude Code, Codex, Gemini CLI), API key providers (Groq, DeepSeek, OpenRouter), and free providers (Qoder, Qwen, Kiro). Kiro accounts include credit balance tracking — remaining credits, total allowance, and renewal date visible in Dashboard → Usage.
![Providers Dashboard](screenshots/01-providers.png)
@@ -67,7 +67,7 @@ Customizable color themes for the entire dashboard. Choose from 7 preset colors
Comprehensive settings panel with tabs:
- **General** — System storage, backup management (export/import database)
- **Appearance** — Theme selector (dark/light/system), color theme presets and custom colors, health log visibility
- **Appearance** — Theme selector (dark/light/system), color theme presets and custom colors, health log visibility, sidebar item visibility controls
- **Security** — API endpoint protection, custom provider blocking, IP filtering, session info
- **Routing** — Model aliases, background task degradation
- **Resilience** — Rate limit persistence, circuit breaker tuning
+1403 -726
View File
File diff suppressed because it is too large Load Diff
+1 -1
View File
@@ -101,7 +101,7 @@ curl -s http://localhost:20128/api/cli-tools/openclaw-settings | jq '{installed,
1. Check usage stats in Dashboard → Usage
2. Switch primary model to GLM/MiniMax
3. Use free tier (Gemini CLI, iFlow) for non-critical tasks
3. Use free tier (Gemini CLI, Qoder) for non-critical tasks
4. Set cost budgets per API key: Dashboard → API Keys → Budget
---
+127 -11
View File
@@ -1,11 +1,11 @@
🌐 **Languages:** 🇺🇸 [English](../../README.md) · 🇧🇷 [pt-BR](../pt-BR/USER_GUIDE.md) · 🇪🇸 [es](../es/USER_GUIDE.md) · 🇫🇷 [fr](../fr/USER_GUIDE.md) · 🇩🇪 [de](../de/USER_GUIDE.md) · 🇮🇹 [it](../it/USER_GUIDE.md) · 🇷🇺 [ru](../ru/USER_GUIDE.md) · 🇨🇳 [zh-CN](../zh-CN/USER_GUIDE.md) · 🇯🇵 [ja](../ja/USER_GUIDE.md) · 🇰🇷 [ko](../ko/USER_GUIDE.md) · 🇸🇦 [ar](../ar/USER_GUIDE.md) · 🇮🇳 [in](../in/USER_GUIDE.md) · 🇹🇭 [th](../th/USER_GUIDE.md) · 🇻🇳 [vi](../vi/USER_GUIDE.md) · 🇮🇩 [id](../id/USER_GUIDE.md) · 🇲🇾 [ms](../ms/USER_GUIDE.md) · 🇳🇱 [nl](../nl/USER_GUIDE.md) · 🇵🇱 [pl](../pl/USER_GUIDE.md) · 🇸🇪 [sv](../sv/USER_GUIDE.md) · 🇳🇴 [no](../no/USER_GUIDE.md) · 🇩🇰 [da](../da/USER_GUIDE.md) · 🇫🇮 [fi](../fi/USER_GUIDE.md) · 🇵🇹 [pt](../pt/USER_GUIDE.md) · 🇷🇴 [ro](../ro/USER_GUIDE.md) · 🇭🇺 [hu](../hu/USER_GUIDE.md) · 🇧🇬 [bg](../bg/USER_GUIDE.md) · 🇸🇰 [sk](../sk/USER_GUIDE.md) · 🇺🇦 [uk-UA](../uk-UA/USER_GUIDE.md) · 🇮🇱 [he](../he/USER_GUIDE.md) · 🇵🇭 [phi](../phi/USER_GUIDE.md)
# User Guide (Español)
🌐 **Languages:** 🇺🇸 [English](../../USER_GUIDE.md) · 🇧🇷 [pt-BR](../pt-BR/USER_GUIDE.md) · 🇪🇸 [es](../es/USER_GUIDE.md) · 🇫🇷 [fr](../fr/USER_GUIDE.md) · 🇩🇪 [de](../de/USER_GUIDE.md) · 🇮🇹 [it](../it/USER_GUIDE.md) · 🇷🇺 [ru](../ru/USER_GUIDE.md) · 🇨🇳 [zh-CN](../zh-CN/USER_GUIDE.md) · 🇯🇵 [ja](../ja/USER_GUIDE.md) · 🇰🇷 [ko](../ko/USER_GUIDE.md) · 🇸🇦 [ar](../ar/USER_GUIDE.md) · 🇮🇳 [in](../in/USER_GUIDE.md) · 🇹🇭 [th](../th/USER_GUIDE.md) · 🇻🇳 [vi](../vi/USER_GUIDE.md) · 🇮🇩 [id](../id/USER_GUIDE.md) · 🇲🇾 [ms](../ms/USER_GUIDE.md) · 🇳🇱 [nl](../nl/USER_GUIDE.md) · 🇵🇱 [pl](../pl/USER_GUIDE.md) · 🇸🇪 [sv](../sv/USER_GUIDE.md) · 🇳🇴 [no](../no/USER_GUIDE.md) · 🇩🇰 [da](../da/USER_GUIDE.md) · 🇫🇮 [fi](../fi/USER_GUIDE.md) · 🇵🇹 [pt](../pt/USER_GUIDE.md) · 🇷🇴 [ro](../ro/USER_GUIDE.md) · 🇭🇺 [hu](../hu/USER_GUIDE.md) · 🇧🇬 [bg](../bg/USER_GUIDE.md) · 🇸🇰 [sk](../sk/USER_GUIDE.md) · 🇺🇦 [uk-UA](../uk-UA/USER_GUIDE.md) · 🇮🇱 [he](../he/USER_GUIDE.md) · 🇵🇭 [phi](../phi/USER_GUIDE.md)
> 🇺🇸 [English](../../USER_GUIDE.md)
---
# User Guide
🌐 **Languages:** 🇺🇸 [English](USER_GUIDE.md) | 🇧🇷 [Português (Brasil)](i18n/pt-BR/USER_GUIDE.md) | 🇪🇸 [Español](i18n/es/USER_GUIDE.md) | 🇫🇷 [Français](i18n/fr/USER_GUIDE.md) | 🇮🇹 [Italiano](i18n/it/USER_GUIDE.md) | 🇷🇺 [Русский](i18n/ru/USER_GUIDE.md) | 🇨🇳 [中文 (简体)](i18n/zh-CN/USER_GUIDE.md) | 🇩🇪 [Deutsch](i18n/de/USER_GUIDE.md) | 🇮🇳 [हिन्दी](i18n/in/USER_GUIDE.md) | 🇹🇭 [ไทย](i18n/th/USER_GUIDE.md) | 🇺🇦 [Українська](i18n/uk-UA/USER_GUIDE.md) | 🇸🇦 [العربية](i18n/ar/USER_GUIDE.md) | 🇯🇵 [日本語](i18n/ja/USER_GUIDE.md) | 🇻🇳 [Tiếng Việt](i18n/vi/USER_GUIDE.md) | 🇧🇬 [Български](i18n/bg/USER_GUIDE.md) | 🇩🇰 [Dansk](i18n/da/USER_GUIDE.md) | 🇫🇮 [Suomi](i18n/fi/USER_GUIDE.md) | 🇮🇱 [עברית](i18n/he/USER_GUIDE.md) | 🇭🇺 [Magyar](i18n/hu/USER_GUIDE.md) | 🇮🇩 [Bahasa Indonesia](i18n/id/USER_GUIDE.md) | 🇰🇷 [한국어](i18n/ko/USER_GUIDE.md) | 🇲🇾 [Bahasa Melayu](i18n/ms/USER_GUIDE.md) | 🇳🇱 [Nederlands](i18n/nl/USER_GUIDE.md) | 🇳🇴 [Norsk](i18n/no/USER_GUIDE.md) | 🇵🇹 [Português (Portugal)](i18n/pt/USER_GUIDE.md) | 🇷🇴 [Română](i18n/ro/USER_GUIDE.md) | 🇵🇱 [Polski](i18n/pl/USER_GUIDE.md) | 🇸🇰 [Slovenčina](i18n/sk/USER_GUIDE.md) | 🇸🇪 [Svenska](i18n/sv/USER_GUIDE.md) | 🇵🇭 [Filipino](i18n/phi/USER_GUIDE.md)
Complete guide for configuring providers, creating combos, integrating CLI tools, and deploying OmniRoute.
---
@@ -43,11 +43,11 @@ Complete guide for configuring providers, creating combos, integrating CLI tools
| **💰 CHEAP** | GLM-4.7 | $0.6/1M | Daily 10AM | Budget backup |
| | MiniMax M2.1 | $0.2/1M | 5-hour rolling | Cheapest option |
| | Kimi K2 | $9/mo flat | 10M tokens/mo | Predictable cost |
| **🆓 FREE** | iFlow | $0 | Unlimited | 8 models free |
| **🆓 FREE** | Qoder | $0 | Unlimited | 8 models free |
| | Qwen | $0 | Unlimited | 3 models free |
| | Kiro | $0 | Unlimited | Claude free |
**💡 Pro Tip:** Start with Gemini CLI (180K free/month) + iFlow (unlimited free) combo = $0 cost!
**💡 Pro Tip:** Start with Gemini CLI (180K free/month) + Qoder (unlimited free) combo = $0 cost!
---
@@ -197,10 +197,10 @@ Models:
### 🆓 FREE Providers
#### iFlow (8 FREE models)
#### Qoder (8 FREE models)
```bash
Dashboard → Connect iFlow → OAuth login → Unlimited usage
Dashboard → Connect Qoder → OAuth login → Unlimited usage
Models: if/kimi-k2-thinking, if/qwen3-coder-plus, if/glm-4.7, if/minimax-m2, if/deepseek-r1
```
@@ -409,6 +409,106 @@ docker run -d --name omniroute -p 20128:20128 --env-file ./.env -v omniroute-dat
For host-integrated mode with CLI binaries, see the Docker section in the main docs.
### Void Linux (xbps-src)
Void Linux users can package and install OmniRoute natively using the `xbps-src` cross-compilation framework. This automates the Node.js standalone build along with the required `better-sqlite3` native bindings.
<details>
<summary><b>View xbps-src template</b></summary>
```bash
# Template file for 'omniroute'
pkgname=omniroute
version=3.2.4
revision=1
hostmakedepends="nodejs python3 make"
depends="openssl"
short_desc="Universal AI gateway with smart routing for multiple LLM providers"
maintainer="zenobit <zenobit@disroot.org>"
license="MIT"
homepage="https://github.com/diegosouzapw/OmniRoute"
distfiles="https://github.com/diegosouzapw/OmniRoute/archive/refs/tags/v${version}.tar.gz"
checksum=009400afee90a9f32599d8fe734145cfd84098140b7287990183dde45ae2245b
system_accounts="_omniroute"
omniroute_homedir="/var/lib/omniroute"
export NODE_ENV=production
export npm_config_engine_strict=false
export npm_config_loglevel=error
export npm_config_fund=false
export npm_config_audit=false
do_build() {
# Determine target CPU arch for node-gyp
local _gyp_arch
case "$XBPS_TARGET_MACHINE" in
aarch64*) _gyp_arch=arm64 ;;
armv7*|armv6*) _gyp_arch=arm ;;
i686*) _gyp_arch=ia32 ;;
*) _gyp_arch=x64 ;;
esac
# 1) Install all deps skip scripts
NODE_ENV=development npm ci --ignore-scripts
# 2) Build the Next.js standalone bundle
npm run build
# 3) Copy static assets into standalone
cp -r .next/static .next/standalone/.next/static
[ -d public ] && cp -r public .next/standalone/public || true
# 4) Compile better-sqlite3 native binding
local _node_gyp=/usr/lib/node_modules/npm/node_modules/node-gyp/bin/node-gyp.js
(cd node_modules/better-sqlite3 && node "$_node_gyp" rebuild --arch="$_gyp_arch")
# 5) Place the compiled binding into the standalone bundle
local _bs3_release=.next/standalone/node_modules/better-sqlite3/build/Release
mkdir -p "$_bs3_release"
cp node_modules/better-sqlite3/build/Release/better_sqlite3.node "$_bs3_release/"
# 6) Remove arch-specific sharp bundles
rm -rf .next/standalone/node_modules/@img
# 7) Copy pino runtime deps omitted by Next.js static analysis:
for _mod in pino-abstract-transport split2 process-warning; do
cp -r "node_modules/$_mod" .next/standalone/node_modules/
done
}
do_check() {
npm run test:unit
}
do_install() {
vmkdir usr/lib/omniroute/.next
vcopy .next/standalone/. usr/lib/omniroute/.next/standalone
# Prevent removal of empty Next.js app router dirs by the post-install hook
for _d in \
.next/standalone/.next/server/app/dashboard \
.next/standalone/.next/server/app/dashboard/settings \
.next/standalone/.next/server/app/dashboard/providers; do
touch "${DESTDIR}/usr/lib/omniroute/${_d}/.keep"
done
cat > "${WRKDIR}/omniroute" <<'EOF'
#!/bin/sh
export PORT="${PORT:-20128}"
export DATA_DIR="${DATA_DIR:-${XDG_DATA_HOME:-${HOME}/.local/share}/omniroute}"
export LOG_TO_FILE="${LOG_TO_FILE:-false}"
mkdir -p "${DATA_DIR}"
exec node /usr/lib/omniroute/.next/standalone/server.js "$@"
EOF
vbin "${WRKDIR}/omniroute"
}
post_install() {
vlicense LICENSE
}
```
</details>
### Environment Variables
| Variable | Default | Description |
@@ -450,7 +550,7 @@ For the full environment variable reference, see the [README](../README.md).
**MiniMax (`minimax/`)** — $0.2/1M: `minimax/MiniMax-M2.1`
**iFlow (`if/`)** — FREE: `if/kimi-k2-thinking`, `if/qwen3-coder-plus`, `if/deepseek-r1`
**Qoder (`if/`)** — FREE: `if/kimi-k2-thinking`, `if/qwen3-coder-plus`, `if/deepseek-r1`
**Qwen (`qw/`)** — FREE: `qw/qwen3-coder-plus`, `qw/qwen3-coder-flash`
@@ -582,6 +682,22 @@ Configure via **Dashboard → Settings → Routing**.
| **Least Used** | Routes to the account with the oldest `lastUsedAt` timestamp, distributing traffic evenly |
| **Cost Optimized** | Routes to the account with the lowest priority value, optimizing for lowest-cost providers |
#### External Sticky Session Header
For external session affinity (for example, Claude Code/Codex agents behind reverse proxies), send:
```http
X-Session-Id: your-session-key
```
OmniRoute also accepts `x_session_id` and returns the effective session key in `X-OmniRoute-Session-Id`.
If you use Nginx and send underscore-form headers, enable:
```nginx
underscores_in_headers on;
```
#### Wildcard Model Aliases
Create wildcard patterns to remap model names:
@@ -766,7 +882,7 @@ Access via **Dashboard → Health**. Real-time system health overview with 6 car
OmniRoute is available as a native desktop application for Windows, macOS, and Linux.
### Installation
### Instalar
```bash
# From the electron directory:
+145
View File
@@ -0,0 +1,145 @@
# OmniRoute — Dashboard Features Gallery (Español)
🌐 **Languages:** 🇺🇸 [English](../../../../docs/FEATURES.md) · 🇪🇸 [es](../../es/docs/FEATURES.md) · 🇫🇷 [fr](../../fr/docs/FEATURES.md) · 🇩🇪 [de](../../de/docs/FEATURES.md) · 🇮🇹 [it](../../it/docs/FEATURES.md) · 🇷🇺 [ru](../../ru/docs/FEATURES.md) · 🇨🇳 [zh-CN](../../zh-CN/docs/FEATURES.md) · 🇯🇵 [ja](../../ja/docs/FEATURES.md) · 🇰🇷 [ko](../../ko/docs/FEATURES.md) · 🇸🇦 [ar](../../ar/docs/FEATURES.md) · 🇮🇳 [in](../../in/docs/FEATURES.md) · 🇹🇭 [th](../../th/docs/FEATURES.md) · 🇻🇳 [vi](../../vi/docs/FEATURES.md) · 🇮🇩 [id](../../id/docs/FEATURES.md) · 🇲🇾 [ms](../../ms/docs/FEATURES.md) · 🇳🇱 [nl](../../nl/docs/FEATURES.md) · 🇵🇱 [pl](../../pl/docs/FEATURES.md) · 🇸🇪 [sv](../../sv/docs/FEATURES.md) · 🇳🇴 [no](../../no/docs/FEATURES.md) · 🇩🇰 [da](../../da/docs/FEATURES.md) · 🇫🇮 [fi](../../fi/docs/FEATURES.md) · 🇵🇹 [pt](../../pt/docs/FEATURES.md) · 🇷🇴 [ro](../../ro/docs/FEATURES.md) · 🇭🇺 [hu](../../hu/docs/FEATURES.md) · 🇧🇬 [bg](../../bg/docs/FEATURES.md) · 🇸🇰 [sk](../../sk/docs/FEATURES.md) · 🇺🇦 [uk-UA](../../uk-UA/docs/FEATURES.md) · 🇮🇱 [he](../../he/docs/FEATURES.md) · 🇵🇭 [phi](../../phi/docs/FEATURES.md) · 🇧🇷 [pt-BR](../../pt-BR/docs/FEATURES.md)
---
Visual guide to every section of the OmniRoute dashboard.
---
## 🔌 Providers
Manage AI provider connections: OAuth providers (Claude Code, Codex, Gemini CLI), API key providers (Groq, DeepSeek, OpenRouter), and free providers (iFlow, Qwen, Kiro). Kiro accounts include credit balance tracking — remaining credits, total allowance, and renewal date visible in Dashboard → Usage.
![Providers Dashboard](screenshots/01-providers.png)
---
## 🎨 Combos
Create model routing combos with 6 strategies: priority, weighted, round-robin, random, least-used, and cost-optimized. Each combo chains multiple models with automatic fallback and includes quick templates and readiness checks.
![Combos Dashboard](screenshots/02-combos.png)
---
## 📊 Analytics
Comprehensive usage analytics with token consumption, cost estimates, activity heatmaps, weekly distribution charts, and per-provider breakdowns.
![Analytics Dashboard](screenshots/03-analytics.png)
---
## 🏥 System Health
Real-time monitoring: uptime, memory, version, latency percentiles (p50/p95/p99), cache statistics, and provider circuit breaker states.
![Health Dashboard](screenshots/04-health.png)
---
## 🔧 Translator Playground
Four modes for debugging API translations: **Playground** (format converter), **Chat Tester** (live requests), **Test Bench** (batch tests), and **Live Monitor** (real-time stream).
![Translator Playground](screenshots/05-translator.png)
---
## 🎮 Model Playground _(v2.0.9+)_
Test any model directly from the dashboard. Select provider, model, and endpoint, write prompts with Monaco Editor, stream responses in real-time, abort mid-stream, and view timing metrics.
---
## 🎨 Themes _(v2.0.5+)_
Customizable color themes for the entire dashboard. Choose from 7 preset colors (Coral, Blue, Red, Green, Violet, Orange, Cyan) or create a custom theme by picking any hex color. Supports light, dark, and system mode.
---
## ⚙️ Settings
Comprehensive settings panel with tabs:
- **General** — System storage, backup management (export/import database)
- **Appearance** — Theme selector (dark/light/system), color theme presets and custom colors, health log visibility, sidebar item visibility controls
- **Security** — API endpoint protection, custom provider blocking, IP filtering, session info
- **Routing** — Model aliases, background task degradation
- **Resilience** — Rate limit persistence, circuit breaker tuning, auto-disable banned accounts, provider expiration monitoring
- **Advanced** — Configuration overrides, configuration audit trail, fallback degradation mode
![Settings Dashboard](screenshots/06-settings.png)
---
## 🔧 CLI Tools
One-click configuration for AI coding tools: Claude Code, Codex CLI, Gemini CLI, OpenClaw, Kilo Code, Antigravity, Cline, Continue, Cursor, and Factory Droid. Features automated config apply/reset, connection profiles, and model mapping.
![CLI Tools Dashboard](screenshots/07-cli-tools.png)
---
## 🤖 CLI Agents _(v2.0.11+)_
Dashboard for discovering and managing CLI agents. Shows a grid of 14 built-in agents (Codex, Claude, Goose, Gemini CLI, OpenClaw, Aider, OpenCode, Cline, Qwen Code, ForgeCode, Amazon Q, Open Interpreter, Cursor CLI, Warp) with:
- **Installation status** — Installed / Not Found with version detection
- **Protocol badges** — stdio, HTTP, etc.
- **Custom agents** — Register any CLI tool via form (name, binary, version command, spawn args)
- **CLI Fingerprint Matching** — Per-provider toggle to match native CLI request signatures, reducing ban risk while preserving proxy IP
---
## 🖼️ Media _(v2.0.3+)_
Generate images, videos, and music from the dashboard. Supports OpenAI, xAI, Together, Hyperbolic, SD WebUI, ComfyUI, AnimateDiff, Stable Audio Open, and MusicGen.
---
## 📝 Request Logs
Real-time request logging with filtering by provider, model, account, and API key. Shows status codes, token usage, latency, and response details.
![Usage Logs](screenshots/08-usage.png)
---
## 🌐 API Endpoint
Your unified API endpoint with capability breakdown: Chat Completions, Responses API, Embeddings, Image Generation, Reranking, Audio Transcription, Text-to-Speech, Moderations, and registered API keys. Cloudflare Quick Tunnel integration and cloud proxy support for remote access.
![Endpoint Dashboard](screenshots/09-endpoint.png)
---
## 🔑 API Key Management
Create, scope, and revoke API keys. Each key can be restricted to specific models/providers with full access or read-only permissions. Visual key management with usage tracking.
---
## 📋 Audit Log
Administrative action tracking with filtering by action type, actor, target, IP address, and timestamp. Full security event history.
---
## 🖥️ Desktop Application
Native Electron desktop app for Windows, macOS, and Linux. Run OmniRoute as a standalone application with system tray integration, offline support, auto-update, and one-click install.
Key features:
- Server readiness polling (no blank screen on cold start)
- System tray with port management
- Content Security Policy
- Single-instance lock
- Auto-update on restart
- Platform-conditional UI (macOS traffic lights, Windows/Linux default titlebar)
- Hardened Electron build packaging — symlinked `node_modules` in the standalone bundle is detected and rejected before packaging, preventing runtime dependency on the build machine (v2.5.5+)
📖 See [`electron/README.md`](../electron/README.md) for full documentation.
+4 -4
View File
@@ -90,7 +90,7 @@ flowchart LR
end
subgraph Upstreams[Upstream Providers]
P1[OAuth Providers\nClaude/Codex/Gemini/Qwen/iFlow/GitHub/Kiro/Cursor/Antigravity]
P1[OAuth Providers\nClaude/Codex/Gemini/Qwen/Qoder/GitHub/Kiro/Cursor/Antigravity]
P2[API Key Providers\nOpenAI/Anthropic/OpenRouter/GLM/Kimi/MiniMax\nDeepSeek/Groq/xAI/Mistral/Perplexity\nTogether/Fireworks/Cerebras/Cohere/NVIDIA]
P3[Compatible Nodes\nOpenAI-compatible / Anthropic-compatible]
end
@@ -224,7 +224,7 @@ Domain layer modules:
OAuth provider modules (12 individual files under `src/lib/oauth/providers/`):
- Registry index: `src/lib/oauth/providers/index.ts`
- Individual providers: `claude.ts`, `codex.ts`, `gemini.ts`, `antigravity.ts`, `iflow.ts`, `qwen.ts`, `kimi-coding.ts`, `github.ts`, `kiro.ts`, `cursor.ts`, `kilocode.ts`, `cline.ts`
- Individual providers: `claude.ts`, `codex.ts`, `gemini.ts`, `antigravity.ts`, `qoder.ts`, `qwen.ts`, `kimi-coding.ts`, `github.ts`, `kiro.ts`, `cursor.ts`, `kilocode.ts`, `cline.ts`
- Thin wrapper: `src/lib/oauth/providers.ts` — re-exports from individual modules
## 3) Persistence Layer
@@ -597,7 +597,7 @@ Each provider has a specialized executor extending `BaseExecutor` (in `open-sse/
| Executor | Provider(s) | Special Handling |
| --------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------- |
| `DefaultExecutor` | OpenAI, Claude, Gemini, Qwen, iFlow, OpenRouter, GLM, Kimi, MiniMax, DeepSeek, Groq, xAI, Mistral, Perplexity, Together, Fireworks, Cerebras, Cohere, NVIDIA | Dynamic URL/header config per provider |
| `DefaultExecutor` | OpenAI, Claude, Gemini, Qwen, Qoder, OpenRouter, GLM, Kimi, MiniMax, DeepSeek, Groq, xAI, Mistral, Perplexity, Together, Fireworks, Cerebras, Cohere, NVIDIA | Dynamic URL/header config per provider |
| `AntigravityExecutor` | Google Antigravity | Custom project/session IDs, Retry-After parsing |
| `CodexExecutor` | OpenAI Codex | Injects system instructions, forces reasoning effort |
| `CursorExecutor` | Cursor IDE | ConnectRPC protocol, Protobuf encoding, request signing via checksum |
@@ -621,7 +621,7 @@ All other providers (including custom compatible nodes) use the `DefaultExecutor
| Cursor | cursor | Custom checksum | ✅ | ✅ | ❌ | ❌ |
| Kiro | kiro | AWS SSO OIDC | ✅ (EventStream) | ❌ | ✅ | ✅ Usage limits |
| Qwen | openai | OAuth | ✅ | ✅ | ✅ | ⚠️ Per request |
| iFlow | openai | OAuth (Basic) | ✅ | ✅ | ✅ | ⚠️ Per request |
| Qoder | openai | OAuth (Basic) | ✅ | ✅ | ✅ | ⚠️ Per request |
| OpenRouter | openai | API Key | ✅ | ✅ | ❌ | ❌ |
| GLM/Kimi/MiniMax | claude | API Key | ✅ | ✅ | ❌ | ❌ |
| DeepSeek | openai | API Key | ✅ | ✅ | ❌ | ❌ |
+2 -2
View File
@@ -271,7 +271,7 @@ Business logic that supports the handlers and executors.
| `provider.ts` | **Format detection** (`detectFormat`): analyzes request body structure to identify Claude/OpenAI/Gemini/Antigravity/Responses formats (includes `max_tokens` heuristic for Claude). Also: URL building, header building, thinking config normalization. Supports `openai-compatible-*` and `anthropic-compatible-*` dynamic providers. |
| `model.ts` | Model string parsing (`claude/model-name``{provider: "claude", model: "model-name"}`), alias resolution with collision detection, input sanitization (rejects path traversal/control chars), and model info resolution with async alias getter support. |
| `accountFallback.ts` | Rate-limit handling: exponential backoff (1s → 2s → 4s → max 2min), account cooldown management, error classification (which errors trigger fallback vs. not). |
| `tokenRefresh.ts` | OAuth token refresh for **every provider**: Google (Gemini, Antigravity), Claude, Codex, Qwen, iFlow, GitHub (OAuth + Copilot dual-token), Kiro (AWS SSO OIDC + Social Auth). Includes in-flight promise deduplication cache and retry with exponential backoff. |
| `tokenRefresh.ts` | OAuth token refresh for **every provider**: Google (Gemini, Antigravity), Claude, Codex, Qwen, Qoder, GitHub (OAuth + Copilot dual-token), Kiro (AWS SSO OIDC + Social Auth). Includes in-flight promise deduplication cache and retry with exponential backoff. |
| `combo.ts` | **Combo models**: chains of fallback models. If model A fails with a fallback-eligible error, try model B, then C, etc. Returns actual upstream status codes. |
| `usage.ts` | Fetches quota/usage data from provider APIs (GitHub Copilot quotas, Antigravity model quotas, Codex rate limits, Kiro usage breakdowns, Claude settings). |
| `accountSelector.ts` | Smart account selection with scoring algorithm: considers priority, health status, round-robin position, and cooldown state to pick the optimal account for each request. |
@@ -543,7 +543,7 @@ A 2000-token buffer is added to reported usage to prevent clients from hitting c
| Kiro (AWS) | AWS SSO OIDC or Social | Kiro | Binary EventStream parsing |
| Cursor IDE | Checksum auth | Cursor | Protobuf encoding, SHA-256 checksums |
| Qwen | OAuth | Default | Standard auth |
| iFlow | OAuth (Basic + Bearer) | Default | Dual auth header |
| Qoder | OAuth (Basic + Bearer) | Default | Dual auth header |
| OpenRouter | API key | Default | Standard Bearer auth |
| GLM, Kimi, MiniMax | API key | Default | Claude-compatible, use `x-api-key` |
| `openai-compatible-*` | API key | Default | Dynamic: any OpenAI-compatible endpoint |
+2 -2
View File
@@ -12,7 +12,7 @@ Visual guide to every section of the OmniRoute dashboard.
## 🔌 Providers
Manage AI provider connections: OAuth providers (Claude Code, Codex, Gemini CLI), API key providers (Groq, DeepSeek, OpenRouter), and free providers (iFlow, Qwen, Kiro). Kiro accounts include credit balance tracking — remaining credits, total allowance, and renewal date visible in Dashboard → Usage.
Manage AI provider connections: OAuth providers (Claude Code, Codex, Gemini CLI), API key providers (Groq, DeepSeek, OpenRouter), and free providers (Qoder, Qwen, Kiro). Kiro accounts include credit balance tracking — remaining credits, total allowance, and renewal date visible in Dashboard → Usage.
![Providers Dashboard](screenshots/01-providers.png)
@@ -67,7 +67,7 @@ Customizable color themes for the entire dashboard. Choose from 7 preset colors
Comprehensive settings panel with tabs:
- **General** — System storage, backup management (export/import database)
- **Appearance** — Theme selector (dark/light/system), color theme presets and custom colors, health log visibility
- **Appearance** — Theme selector (dark/light/system), color theme presets and custom colors, health log visibility, sidebar item visibility controls
- **Security** — API endpoint protection, custom provider blocking, IP filtering, session info
- **Routing** — Model aliases, background task degradation
- **Resilience** — Rate limit persistence, circuit breaker tuning
+1271 -742
View File
File diff suppressed because it is too large Load Diff
+1 -1
View File
@@ -101,7 +101,7 @@ curl -s http://localhost:20128/api/cli-tools/openclaw-settings | jq '{installed,
1. Check usage stats in Dashboard → Usage
2. Switch primary model to GLM/MiniMax
3. Use free tier (Gemini CLI, iFlow) for non-critical tasks
3. Use free tier (Gemini CLI, Qoder) for non-critical tasks
4. Set cost budgets per API key: Dashboard → API Keys → Budget
---
+127 -11
View File
@@ -1,11 +1,11 @@
🌐 **Languages:** 🇺🇸 [English](../../README.md) · 🇧🇷 [pt-BR](../pt-BR/USER_GUIDE.md) · 🇪🇸 [es](../es/USER_GUIDE.md) · 🇫🇷 [fr](../fr/USER_GUIDE.md) · 🇩🇪 [de](../de/USER_GUIDE.md) · 🇮🇹 [it](../it/USER_GUIDE.md) · 🇷🇺 [ru](../ru/USER_GUIDE.md) · 🇨🇳 [zh-CN](../zh-CN/USER_GUIDE.md) · 🇯🇵 [ja](../ja/USER_GUIDE.md) · 🇰🇷 [ko](../ko/USER_GUIDE.md) · 🇸🇦 [ar](../ar/USER_GUIDE.md) · 🇮🇳 [in](../in/USER_GUIDE.md) · 🇹🇭 [th](../th/USER_GUIDE.md) · 🇻🇳 [vi](../vi/USER_GUIDE.md) · 🇮🇩 [id](../id/USER_GUIDE.md) · 🇲🇾 [ms](../ms/USER_GUIDE.md) · 🇳🇱 [nl](../nl/USER_GUIDE.md) · 🇵🇱 [pl](../pl/USER_GUIDE.md) · 🇸🇪 [sv](../sv/USER_GUIDE.md) · 🇳🇴 [no](../no/USER_GUIDE.md) · 🇩🇰 [da](../da/USER_GUIDE.md) · 🇫🇮 [fi](../fi/USER_GUIDE.md) · 🇵🇹 [pt](../pt/USER_GUIDE.md) · 🇷🇴 [ro](../ro/USER_GUIDE.md) · 🇭🇺 [hu](../hu/USER_GUIDE.md) · 🇧🇬 [bg](../bg/USER_GUIDE.md) · 🇸🇰 [sk](../sk/USER_GUIDE.md) · 🇺🇦 [uk-UA](../uk-UA/USER_GUIDE.md) · 🇮🇱 [he](../he/USER_GUIDE.md) · 🇵🇭 [phi](../phi/USER_GUIDE.md)
# User Guide (Suomi)
🌐 **Languages:** 🇺🇸 [English](../../USER_GUIDE.md) · 🇧🇷 [pt-BR](../pt-BR/USER_GUIDE.md) · 🇪🇸 [es](../es/USER_GUIDE.md) · 🇫🇷 [fr](../fr/USER_GUIDE.md) · 🇩🇪 [de](../de/USER_GUIDE.md) · 🇮🇹 [it](../it/USER_GUIDE.md) · 🇷🇺 [ru](../ru/USER_GUIDE.md) · 🇨🇳 [zh-CN](../zh-CN/USER_GUIDE.md) · 🇯🇵 [ja](../ja/USER_GUIDE.md) · 🇰🇷 [ko](../ko/USER_GUIDE.md) · 🇸🇦 [ar](../ar/USER_GUIDE.md) · 🇮🇳 [in](../in/USER_GUIDE.md) · 🇹🇭 [th](../th/USER_GUIDE.md) · 🇻🇳 [vi](../vi/USER_GUIDE.md) · 🇮🇩 [id](../id/USER_GUIDE.md) · 🇲🇾 [ms](../ms/USER_GUIDE.md) · 🇳🇱 [nl](../nl/USER_GUIDE.md) · 🇵🇱 [pl](../pl/USER_GUIDE.md) · 🇸🇪 [sv](../sv/USER_GUIDE.md) · 🇳🇴 [no](../no/USER_GUIDE.md) · 🇩🇰 [da](../da/USER_GUIDE.md) · 🇫🇮 [fi](../fi/USER_GUIDE.md) · 🇵🇹 [pt](../pt/USER_GUIDE.md) · 🇷🇴 [ro](../ro/USER_GUIDE.md) · 🇭🇺 [hu](../hu/USER_GUIDE.md) · 🇧🇬 [bg](../bg/USER_GUIDE.md) · 🇸🇰 [sk](../sk/USER_GUIDE.md) · 🇺🇦 [uk-UA](../uk-UA/USER_GUIDE.md) · 🇮🇱 [he](../he/USER_GUIDE.md) · 🇵🇭 [phi](../phi/USER_GUIDE.md)
> 🇺🇸 [English](../../USER_GUIDE.md)
---
# User Guide
🌐 **Languages:** 🇺🇸 [English](USER_GUIDE.md) | 🇧🇷 [Português (Brasil)](i18n/pt-BR/USER_GUIDE.md) | 🇪🇸 [Español](i18n/es/USER_GUIDE.md) | 🇫🇷 [Français](i18n/fr/USER_GUIDE.md) | 🇮🇹 [Italiano](i18n/it/USER_GUIDE.md) | 🇷🇺 [Русский](i18n/ru/USER_GUIDE.md) | 🇨🇳 [中文 (简体)](i18n/zh-CN/USER_GUIDE.md) | 🇩🇪 [Deutsch](i18n/de/USER_GUIDE.md) | 🇮🇳 [हिन्दी](i18n/in/USER_GUIDE.md) | 🇹🇭 [ไทย](i18n/th/USER_GUIDE.md) | 🇺🇦 [Українська](i18n/uk-UA/USER_GUIDE.md) | 🇸🇦 [العربية](i18n/ar/USER_GUIDE.md) | 🇯🇵 [日本語](i18n/ja/USER_GUIDE.md) | 🇻🇳 [Tiếng Việt](i18n/vi/USER_GUIDE.md) | 🇧🇬 [Български](i18n/bg/USER_GUIDE.md) | 🇩🇰 [Dansk](i18n/da/USER_GUIDE.md) | 🇫🇮 [Suomi](i18n/fi/USER_GUIDE.md) | 🇮🇱 [עברית](i18n/he/USER_GUIDE.md) | 🇭🇺 [Magyar](i18n/hu/USER_GUIDE.md) | 🇮🇩 [Bahasa Indonesia](i18n/id/USER_GUIDE.md) | 🇰🇷 [한국어](i18n/ko/USER_GUIDE.md) | 🇲🇾 [Bahasa Melayu](i18n/ms/USER_GUIDE.md) | 🇳🇱 [Nederlands](i18n/nl/USER_GUIDE.md) | 🇳🇴 [Norsk](i18n/no/USER_GUIDE.md) | 🇵🇹 [Português (Portugal)](i18n/pt/USER_GUIDE.md) | 🇷🇴 [Română](i18n/ro/USER_GUIDE.md) | 🇵🇱 [Polski](i18n/pl/USER_GUIDE.md) | 🇸🇰 [Slovenčina](i18n/sk/USER_GUIDE.md) | 🇸🇪 [Svenska](i18n/sv/USER_GUIDE.md) | 🇵🇭 [Filipino](i18n/phi/USER_GUIDE.md)
Complete guide for configuring providers, creating combos, integrating CLI tools, and deploying OmniRoute.
---
@@ -43,11 +43,11 @@ Complete guide for configuring providers, creating combos, integrating CLI tools
| **💰 CHEAP** | GLM-4.7 | $0.6/1M | Daily 10AM | Budget backup |
| | MiniMax M2.1 | $0.2/1M | 5-hour rolling | Cheapest option |
| | Kimi K2 | $9/mo flat | 10M tokens/mo | Predictable cost |
| **🆓 FREE** | iFlow | $0 | Unlimited | 8 models free |
| **🆓 FREE** | Qoder | $0 | Unlimited | 8 models free |
| | Qwen | $0 | Unlimited | 3 models free |
| | Kiro | $0 | Unlimited | Claude free |
**💡 Pro Tip:** Start with Gemini CLI (180K free/month) + iFlow (unlimited free) combo = $0 cost!
**💡 Pro Tip:** Start with Gemini CLI (180K free/month) + Qoder (unlimited free) combo = $0 cost!
---
@@ -197,10 +197,10 @@ Models:
### 🆓 FREE Providers
#### iFlow (8 FREE models)
#### Qoder (8 FREE models)
```bash
Dashboard → Connect iFlow → OAuth login → Unlimited usage
Dashboard → Connect Qoder → OAuth login → Unlimited usage
Models: if/kimi-k2-thinking, if/qwen3-coder-plus, if/glm-4.7, if/minimax-m2, if/deepseek-r1
```
@@ -409,6 +409,106 @@ docker run -d --name omniroute -p 20128:20128 --env-file ./.env -v omniroute-dat
For host-integrated mode with CLI binaries, see the Docker section in the main docs.
### Void Linux (xbps-src)
Void Linux users can package and install OmniRoute natively using the `xbps-src` cross-compilation framework. This automates the Node.js standalone build along with the required `better-sqlite3` native bindings.
<details>
<summary><b>View xbps-src template</b></summary>
```bash
# Template file for 'omniroute'
pkgname=omniroute
version=3.2.4
revision=1
hostmakedepends="nodejs python3 make"
depends="openssl"
short_desc="Universal AI gateway with smart routing for multiple LLM providers"
maintainer="zenobit <zenobit@disroot.org>"
license="MIT"
homepage="https://github.com/diegosouzapw/OmniRoute"
distfiles="https://github.com/diegosouzapw/OmniRoute/archive/refs/tags/v${version}.tar.gz"
checksum=009400afee90a9f32599d8fe734145cfd84098140b7287990183dde45ae2245b
system_accounts="_omniroute"
omniroute_homedir="/var/lib/omniroute"
export NODE_ENV=production
export npm_config_engine_strict=false
export npm_config_loglevel=error
export npm_config_fund=false
export npm_config_audit=false
do_build() {
# Determine target CPU arch for node-gyp
local _gyp_arch
case "$XBPS_TARGET_MACHINE" in
aarch64*) _gyp_arch=arm64 ;;
armv7*|armv6*) _gyp_arch=arm ;;
i686*) _gyp_arch=ia32 ;;
*) _gyp_arch=x64 ;;
esac
# 1) Install all deps skip scripts
NODE_ENV=development npm ci --ignore-scripts
# 2) Build the Next.js standalone bundle
npm run build
# 3) Copy static assets into standalone
cp -r .next/static .next/standalone/.next/static
[ -d public ] && cp -r public .next/standalone/public || true
# 4) Compile better-sqlite3 native binding
local _node_gyp=/usr/lib/node_modules/npm/node_modules/node-gyp/bin/node-gyp.js
(cd node_modules/better-sqlite3 && node "$_node_gyp" rebuild --arch="$_gyp_arch")
# 5) Place the compiled binding into the standalone bundle
local _bs3_release=.next/standalone/node_modules/better-sqlite3/build/Release
mkdir -p "$_bs3_release"
cp node_modules/better-sqlite3/build/Release/better_sqlite3.node "$_bs3_release/"
# 6) Remove arch-specific sharp bundles
rm -rf .next/standalone/node_modules/@img
# 7) Copy pino runtime deps omitted by Next.js static analysis:
for _mod in pino-abstract-transport split2 process-warning; do
cp -r "node_modules/$_mod" .next/standalone/node_modules/
done
}
do_check() {
npm run test:unit
}
do_install() {
vmkdir usr/lib/omniroute/.next
vcopy .next/standalone/. usr/lib/omniroute/.next/standalone
# Prevent removal of empty Next.js app router dirs by the post-install hook
for _d in \
.next/standalone/.next/server/app/dashboard \
.next/standalone/.next/server/app/dashboard/settings \
.next/standalone/.next/server/app/dashboard/providers; do
touch "${DESTDIR}/usr/lib/omniroute/${_d}/.keep"
done
cat > "${WRKDIR}/omniroute" <<'EOF'
#!/bin/sh
export PORT="${PORT:-20128}"
export DATA_DIR="${DATA_DIR:-${XDG_DATA_HOME:-${HOME}/.local/share}/omniroute}"
export LOG_TO_FILE="${LOG_TO_FILE:-false}"
mkdir -p "${DATA_DIR}"
exec node /usr/lib/omniroute/.next/standalone/server.js "$@"
EOF
vbin "${WRKDIR}/omniroute"
}
post_install() {
vlicense LICENSE
}
```
</details>
### Environment Variables
| Variable | Default | Description |
@@ -450,7 +550,7 @@ For the full environment variable reference, see the [README](../README.md).
**MiniMax (`minimax/`)** — $0.2/1M: `minimax/MiniMax-M2.1`
**iFlow (`if/`)** — FREE: `if/kimi-k2-thinking`, `if/qwen3-coder-plus`, `if/deepseek-r1`
**Qoder (`if/`)** — FREE: `if/kimi-k2-thinking`, `if/qwen3-coder-plus`, `if/deepseek-r1`
**Qwen (`qw/`)** — FREE: `qw/qwen3-coder-plus`, `qw/qwen3-coder-flash`
@@ -582,6 +682,22 @@ Configure via **Dashboard → Settings → Routing**.
| **Least Used** | Routes to the account with the oldest `lastUsedAt` timestamp, distributing traffic evenly |
| **Cost Optimized** | Routes to the account with the lowest priority value, optimizing for lowest-cost providers |
#### External Sticky Session Header
For external session affinity (for example, Claude Code/Codex agents behind reverse proxies), send:
```http
X-Session-Id: your-session-key
```
OmniRoute also accepts `x_session_id` and returns the effective session key in `X-OmniRoute-Session-Id`.
If you use Nginx and send underscore-form headers, enable:
```nginx
underscores_in_headers on;
```
#### Wildcard Model Aliases
Create wildcard patterns to remap model names:
@@ -766,7 +882,7 @@ Access via **Dashboard → Health**. Real-time system health overview with 6 car
OmniRoute is available as a native desktop application for Windows, macOS, and Linux.
### Installation
### Asenna
```bash
# From the electron directory:
+145
View File
@@ -0,0 +1,145 @@
# OmniRoute — Dashboard Features Gallery (Suomi)
🌐 **Languages:** 🇺🇸 [English](../../../../docs/FEATURES.md) · 🇪🇸 [es](../../es/docs/FEATURES.md) · 🇫🇷 [fr](../../fr/docs/FEATURES.md) · 🇩🇪 [de](../../de/docs/FEATURES.md) · 🇮🇹 [it](../../it/docs/FEATURES.md) · 🇷🇺 [ru](../../ru/docs/FEATURES.md) · 🇨🇳 [zh-CN](../../zh-CN/docs/FEATURES.md) · 🇯🇵 [ja](../../ja/docs/FEATURES.md) · 🇰🇷 [ko](../../ko/docs/FEATURES.md) · 🇸🇦 [ar](../../ar/docs/FEATURES.md) · 🇮🇳 [in](../../in/docs/FEATURES.md) · 🇹🇭 [th](../../th/docs/FEATURES.md) · 🇻🇳 [vi](../../vi/docs/FEATURES.md) · 🇮🇩 [id](../../id/docs/FEATURES.md) · 🇲🇾 [ms](../../ms/docs/FEATURES.md) · 🇳🇱 [nl](../../nl/docs/FEATURES.md) · 🇵🇱 [pl](../../pl/docs/FEATURES.md) · 🇸🇪 [sv](../../sv/docs/FEATURES.md) · 🇳🇴 [no](../../no/docs/FEATURES.md) · 🇩🇰 [da](../../da/docs/FEATURES.md) · 🇫🇮 [fi](../../fi/docs/FEATURES.md) · 🇵🇹 [pt](../../pt/docs/FEATURES.md) · 🇷🇴 [ro](../../ro/docs/FEATURES.md) · 🇭🇺 [hu](../../hu/docs/FEATURES.md) · 🇧🇬 [bg](../../bg/docs/FEATURES.md) · 🇸🇰 [sk](../../sk/docs/FEATURES.md) · 🇺🇦 [uk-UA](../../uk-UA/docs/FEATURES.md) · 🇮🇱 [he](../../he/docs/FEATURES.md) · 🇵🇭 [phi](../../phi/docs/FEATURES.md) · 🇧🇷 [pt-BR](../../pt-BR/docs/FEATURES.md)
---
Visual guide to every section of the OmniRoute dashboard.
---
## 🔌 Providers
Manage AI provider connections: OAuth providers (Claude Code, Codex, Gemini CLI), API key providers (Groq, DeepSeek, OpenRouter), and free providers (iFlow, Qwen, Kiro). Kiro accounts include credit balance tracking — remaining credits, total allowance, and renewal date visible in Dashboard → Usage.
![Providers Dashboard](screenshots/01-providers.png)
---
## 🎨 Combos
Create model routing combos with 6 strategies: priority, weighted, round-robin, random, least-used, and cost-optimized. Each combo chains multiple models with automatic fallback and includes quick templates and readiness checks.
![Combos Dashboard](screenshots/02-combos.png)
---
## 📊 Analytics
Comprehensive usage analytics with token consumption, cost estimates, activity heatmaps, weekly distribution charts, and per-provider breakdowns.
![Analytics Dashboard](screenshots/03-analytics.png)
---
## 🏥 System Health
Real-time monitoring: uptime, memory, version, latency percentiles (p50/p95/p99), cache statistics, and provider circuit breaker states.
![Health Dashboard](screenshots/04-health.png)
---
## 🔧 Translator Playground
Four modes for debugging API translations: **Playground** (format converter), **Chat Tester** (live requests), **Test Bench** (batch tests), and **Live Monitor** (real-time stream).
![Translator Playground](screenshots/05-translator.png)
---
## 🎮 Model Playground _(v2.0.9+)_
Test any model directly from the dashboard. Select provider, model, and endpoint, write prompts with Monaco Editor, stream responses in real-time, abort mid-stream, and view timing metrics.
---
## 🎨 Themes _(v2.0.5+)_
Customizable color themes for the entire dashboard. Choose from 7 preset colors (Coral, Blue, Red, Green, Violet, Orange, Cyan) or create a custom theme by picking any hex color. Supports light, dark, and system mode.
---
## ⚙️ Settings
Comprehensive settings panel with tabs:
- **General** — System storage, backup management (export/import database)
- **Appearance** — Theme selector (dark/light/system), color theme presets and custom colors, health log visibility, sidebar item visibility controls
- **Security** — API endpoint protection, custom provider blocking, IP filtering, session info
- **Routing** — Model aliases, background task degradation
- **Resilience** — Rate limit persistence, circuit breaker tuning, auto-disable banned accounts, provider expiration monitoring
- **Advanced** — Configuration overrides, configuration audit trail, fallback degradation mode
![Settings Dashboard](screenshots/06-settings.png)
---
## 🔧 CLI Tools
One-click configuration for AI coding tools: Claude Code, Codex CLI, Gemini CLI, OpenClaw, Kilo Code, Antigravity, Cline, Continue, Cursor, and Factory Droid. Features automated config apply/reset, connection profiles, and model mapping.
![CLI Tools Dashboard](screenshots/07-cli-tools.png)
---
## 🤖 CLI Agents _(v2.0.11+)_
Dashboard for discovering and managing CLI agents. Shows a grid of 14 built-in agents (Codex, Claude, Goose, Gemini CLI, OpenClaw, Aider, OpenCode, Cline, Qwen Code, ForgeCode, Amazon Q, Open Interpreter, Cursor CLI, Warp) with:
- **Installation status** — Installed / Not Found with version detection
- **Protocol badges** — stdio, HTTP, etc.
- **Custom agents** — Register any CLI tool via form (name, binary, version command, spawn args)
- **CLI Fingerprint Matching** — Per-provider toggle to match native CLI request signatures, reducing ban risk while preserving proxy IP
---
## 🖼️ Media _(v2.0.3+)_
Generate images, videos, and music from the dashboard. Supports OpenAI, xAI, Together, Hyperbolic, SD WebUI, ComfyUI, AnimateDiff, Stable Audio Open, and MusicGen.
---
## 📝 Request Logs
Real-time request logging with filtering by provider, model, account, and API key. Shows status codes, token usage, latency, and response details.
![Usage Logs](screenshots/08-usage.png)
---
## 🌐 API Endpoint
Your unified API endpoint with capability breakdown: Chat Completions, Responses API, Embeddings, Image Generation, Reranking, Audio Transcription, Text-to-Speech, Moderations, and registered API keys. Cloudflare Quick Tunnel integration and cloud proxy support for remote access.
![Endpoint Dashboard](screenshots/09-endpoint.png)
---
## 🔑 API Key Management
Create, scope, and revoke API keys. Each key can be restricted to specific models/providers with full access or read-only permissions. Visual key management with usage tracking.
---
## 📋 Audit Log
Administrative action tracking with filtering by action type, actor, target, IP address, and timestamp. Full security event history.
---
## 🖥️ Desktop Application
Native Electron desktop app for Windows, macOS, and Linux. Run OmniRoute as a standalone application with system tray integration, offline support, auto-update, and one-click install.
Key features:
- Server readiness polling (no blank screen on cold start)
- System tray with port management
- Content Security Policy
- Single-instance lock
- Auto-update on restart
- Platform-conditional UI (macOS traffic lights, Windows/Linux default titlebar)
- Hardened Electron build packaging — symlinked `node_modules` in the standalone bundle is detected and rejected before packaging, preventing runtime dependency on the build machine (v2.5.5+)
📖 See [`electron/README.md`](../electron/README.md) for full documentation.
+4 -4
View File
@@ -90,7 +90,7 @@ flowchart LR
end
subgraph Upstreams[Upstream Providers]
P1[OAuth Providers\nClaude/Codex/Gemini/Qwen/iFlow/GitHub/Kiro/Cursor/Antigravity]
P1[OAuth Providers\nClaude/Codex/Gemini/Qwen/Qoder/GitHub/Kiro/Cursor/Antigravity]
P2[API Key Providers\nOpenAI/Anthropic/OpenRouter/GLM/Kimi/MiniMax\nDeepSeek/Groq/xAI/Mistral/Perplexity\nTogether/Fireworks/Cerebras/Cohere/NVIDIA]
P3[Compatible Nodes\nOpenAI-compatible / Anthropic-compatible]
end
@@ -224,7 +224,7 @@ Domain layer modules:
OAuth provider modules (12 individual files under `src/lib/oauth/providers/`):
- Registry index: `src/lib/oauth/providers/index.ts`
- Individual providers: `claude.ts`, `codex.ts`, `gemini.ts`, `antigravity.ts`, `iflow.ts`, `qwen.ts`, `kimi-coding.ts`, `github.ts`, `kiro.ts`, `cursor.ts`, `kilocode.ts`, `cline.ts`
- Individual providers: `claude.ts`, `codex.ts`, `gemini.ts`, `antigravity.ts`, `qoder.ts`, `qwen.ts`, `kimi-coding.ts`, `github.ts`, `kiro.ts`, `cursor.ts`, `kilocode.ts`, `cline.ts`
- Thin wrapper: `src/lib/oauth/providers.ts` — re-exports from individual modules
## 3) Persistence Layer
@@ -597,7 +597,7 @@ Each provider has a specialized executor extending `BaseExecutor` (in `open-sse/
| Executor | Provider(s) | Special Handling |
| --------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------- |
| `DefaultExecutor` | OpenAI, Claude, Gemini, Qwen, iFlow, OpenRouter, GLM, Kimi, MiniMax, DeepSeek, Groq, xAI, Mistral, Perplexity, Together, Fireworks, Cerebras, Cohere, NVIDIA | Dynamic URL/header config per provider |
| `DefaultExecutor` | OpenAI, Claude, Gemini, Qwen, Qoder, OpenRouter, GLM, Kimi, MiniMax, DeepSeek, Groq, xAI, Mistral, Perplexity, Together, Fireworks, Cerebras, Cohere, NVIDIA | Dynamic URL/header config per provider |
| `AntigravityExecutor` | Google Antigravity | Custom project/session IDs, Retry-After parsing |
| `CodexExecutor` | OpenAI Codex | Injects system instructions, forces reasoning effort |
| `CursorExecutor` | Cursor IDE | ConnectRPC protocol, Protobuf encoding, request signing via checksum |
@@ -621,7 +621,7 @@ All other providers (including custom compatible nodes) use the `DefaultExecutor
| Cursor | cursor | Custom checksum | ✅ | ✅ | ❌ | ❌ |
| Kiro | kiro | AWS SSO OIDC | ✅ (EventStream) | ❌ | ✅ | ✅ Usage limits |
| Qwen | openai | OAuth | ✅ | ✅ | ✅ | ⚠️ Per request |
| iFlow | openai | OAuth (Basic) | ✅ | ✅ | ✅ | ⚠️ Per request |
| Qoder | openai | OAuth (Basic) | ✅ | ✅ | ✅ | ⚠️ Per request |
| OpenRouter | openai | API Key | ✅ | ✅ | ❌ | ❌ |
| GLM/Kimi/MiniMax | claude | API Key | ✅ | ✅ | ❌ | ❌ |
| DeepSeek | openai | API Key | ✅ | ✅ | ❌ | ❌ |
+2 -2
View File
@@ -271,7 +271,7 @@ Business logic that supports the handlers and executors.
| `provider.ts` | **Format detection** (`detectFormat`): analyzes request body structure to identify Claude/OpenAI/Gemini/Antigravity/Responses formats (includes `max_tokens` heuristic for Claude). Also: URL building, header building, thinking config normalization. Supports `openai-compatible-*` and `anthropic-compatible-*` dynamic providers. |
| `model.ts` | Model string parsing (`claude/model-name``{provider: "claude", model: "model-name"}`), alias resolution with collision detection, input sanitization (rejects path traversal/control chars), and model info resolution with async alias getter support. |
| `accountFallback.ts` | Rate-limit handling: exponential backoff (1s → 2s → 4s → max 2min), account cooldown management, error classification (which errors trigger fallback vs. not). |
| `tokenRefresh.ts` | OAuth token refresh for **every provider**: Google (Gemini, Antigravity), Claude, Codex, Qwen, iFlow, GitHub (OAuth + Copilot dual-token), Kiro (AWS SSO OIDC + Social Auth). Includes in-flight promise deduplication cache and retry with exponential backoff. |
| `tokenRefresh.ts` | OAuth token refresh for **every provider**: Google (Gemini, Antigravity), Claude, Codex, Qwen, Qoder, GitHub (OAuth + Copilot dual-token), Kiro (AWS SSO OIDC + Social Auth). Includes in-flight promise deduplication cache and retry with exponential backoff. |
| `combo.ts` | **Combo models**: chains of fallback models. If model A fails with a fallback-eligible error, try model B, then C, etc. Returns actual upstream status codes. |
| `usage.ts` | Fetches quota/usage data from provider APIs (GitHub Copilot quotas, Antigravity model quotas, Codex rate limits, Kiro usage breakdowns, Claude settings). |
| `accountSelector.ts` | Smart account selection with scoring algorithm: considers priority, health status, round-robin position, and cooldown state to pick the optimal account for each request. |
@@ -543,7 +543,7 @@ A 2000-token buffer is added to reported usage to prevent clients from hitting c
| Kiro (AWS) | AWS SSO OIDC or Social | Kiro | Binary EventStream parsing |
| Cursor IDE | Checksum auth | Cursor | Protobuf encoding, SHA-256 checksums |
| Qwen | OAuth | Default | Standard auth |
| iFlow | OAuth (Basic + Bearer) | Default | Dual auth header |
| Qoder | OAuth (Basic + Bearer) | Default | Dual auth header |
| OpenRouter | API key | Default | Standard Bearer auth |
| GLM, Kimi, MiniMax | API key | Default | Claude-compatible, use `x-api-key` |
| `openai-compatible-*` | API key | Default | Dynamic: any OpenAI-compatible endpoint |
+2 -2
View File
@@ -12,7 +12,7 @@ Visual guide to every section of the OmniRoute dashboard.
## 🔌 Providers
Manage AI provider connections: OAuth providers (Claude Code, Codex, Gemini CLI), API key providers (Groq, DeepSeek, OpenRouter), and free providers (iFlow, Qwen, Kiro). Kiro accounts include credit balance tracking — remaining credits, total allowance, and renewal date visible in Dashboard → Usage.
Manage AI provider connections: OAuth providers (Claude Code, Codex, Gemini CLI), API key providers (Groq, DeepSeek, OpenRouter), and free providers (Qoder, Qwen, Kiro). Kiro accounts include credit balance tracking — remaining credits, total allowance, and renewal date visible in Dashboard → Usage.
![Providers Dashboard](screenshots/01-providers.png)
@@ -67,7 +67,7 @@ Customizable color themes for the entire dashboard. Choose from 7 preset colors
Comprehensive settings panel with tabs:
- **General** — System storage, backup management (export/import database)
- **Appearance** — Theme selector (dark/light/system), color theme presets and custom colors, health log visibility
- **Appearance** — Theme selector (dark/light/system), color theme presets and custom colors, health log visibility, sidebar item visibility controls
- **Security** — API endpoint protection, custom provider blocking, IP filtering, session info
- **Routing** — Model aliases, background task degradation
- **Resilience** — Rate limit persistence, circuit breaker tuning
+1416 -738
View File
File diff suppressed because it is too large Load Diff
+1 -1
View File
@@ -101,7 +101,7 @@ curl -s http://localhost:20128/api/cli-tools/openclaw-settings | jq '{installed,
1. Check usage stats in Dashboard → Usage
2. Switch primary model to GLM/MiniMax
3. Use free tier (Gemini CLI, iFlow) for non-critical tasks
3. Use free tier (Gemini CLI, Qoder) for non-critical tasks
4. Set cost budgets per API key: Dashboard → API Keys → Budget
---
+127 -11
View File
@@ -1,11 +1,11 @@
🌐 **Languages:** 🇺🇸 [English](../../README.md) · 🇧🇷 [pt-BR](../pt-BR/USER_GUIDE.md) · 🇪🇸 [es](../es/USER_GUIDE.md) · 🇫🇷 [fr](../fr/USER_GUIDE.md) · 🇩🇪 [de](../de/USER_GUIDE.md) · 🇮🇹 [it](../it/USER_GUIDE.md) · 🇷🇺 [ru](../ru/USER_GUIDE.md) · 🇨🇳 [zh-CN](../zh-CN/USER_GUIDE.md) · 🇯🇵 [ja](../ja/USER_GUIDE.md) · 🇰🇷 [ko](../ko/USER_GUIDE.md) · 🇸🇦 [ar](../ar/USER_GUIDE.md) · 🇮🇳 [in](../in/USER_GUIDE.md) · 🇹🇭 [th](../th/USER_GUIDE.md) · 🇻🇳 [vi](../vi/USER_GUIDE.md) · 🇮🇩 [id](../id/USER_GUIDE.md) · 🇲🇾 [ms](../ms/USER_GUIDE.md) · 🇳🇱 [nl](../nl/USER_GUIDE.md) · 🇵🇱 [pl](../pl/USER_GUIDE.md) · 🇸🇪 [sv](../sv/USER_GUIDE.md) · 🇳🇴 [no](../no/USER_GUIDE.md) · 🇩🇰 [da](../da/USER_GUIDE.md) · 🇫🇮 [fi](../fi/USER_GUIDE.md) · 🇵🇹 [pt](../pt/USER_GUIDE.md) · 🇷🇴 [ro](../ro/USER_GUIDE.md) · 🇭🇺 [hu](../hu/USER_GUIDE.md) · 🇧🇬 [bg](../bg/USER_GUIDE.md) · 🇸🇰 [sk](../sk/USER_GUIDE.md) · 🇺🇦 [uk-UA](../uk-UA/USER_GUIDE.md) · 🇮🇱 [he](../he/USER_GUIDE.md) · 🇵🇭 [phi](../phi/USER_GUIDE.md)
# User Guide (Français)
🌐 **Languages:** 🇺🇸 [English](../../USER_GUIDE.md) · 🇧🇷 [pt-BR](../pt-BR/USER_GUIDE.md) · 🇪🇸 [es](../es/USER_GUIDE.md) · 🇫🇷 [fr](../fr/USER_GUIDE.md) · 🇩🇪 [de](../de/USER_GUIDE.md) · 🇮🇹 [it](../it/USER_GUIDE.md) · 🇷🇺 [ru](../ru/USER_GUIDE.md) · 🇨🇳 [zh-CN](../zh-CN/USER_GUIDE.md) · 🇯🇵 [ja](../ja/USER_GUIDE.md) · 🇰🇷 [ko](../ko/USER_GUIDE.md) · 🇸🇦 [ar](../ar/USER_GUIDE.md) · 🇮🇳 [in](../in/USER_GUIDE.md) · 🇹🇭 [th](../th/USER_GUIDE.md) · 🇻🇳 [vi](../vi/USER_GUIDE.md) · 🇮🇩 [id](../id/USER_GUIDE.md) · 🇲🇾 [ms](../ms/USER_GUIDE.md) · 🇳🇱 [nl](../nl/USER_GUIDE.md) · 🇵🇱 [pl](../pl/USER_GUIDE.md) · 🇸🇪 [sv](../sv/USER_GUIDE.md) · 🇳🇴 [no](../no/USER_GUIDE.md) · 🇩🇰 [da](../da/USER_GUIDE.md) · 🇫🇮 [fi](../fi/USER_GUIDE.md) · 🇵🇹 [pt](../pt/USER_GUIDE.md) · 🇷🇴 [ro](../ro/USER_GUIDE.md) · 🇭🇺 [hu](../hu/USER_GUIDE.md) · 🇧🇬 [bg](../bg/USER_GUIDE.md) · 🇸🇰 [sk](../sk/USER_GUIDE.md) · 🇺🇦 [uk-UA](../uk-UA/USER_GUIDE.md) · 🇮🇱 [he](../he/USER_GUIDE.md) · 🇵🇭 [phi](../phi/USER_GUIDE.md)
> 🇺🇸 [English](../../USER_GUIDE.md)
---
# User Guide
🌐 **Languages:** 🇺🇸 [English](USER_GUIDE.md) | 🇧🇷 [Português (Brasil)](i18n/pt-BR/USER_GUIDE.md) | 🇪🇸 [Español](i18n/es/USER_GUIDE.md) | 🇫🇷 [Français](i18n/fr/USER_GUIDE.md) | 🇮🇹 [Italiano](i18n/it/USER_GUIDE.md) | 🇷🇺 [Русский](i18n/ru/USER_GUIDE.md) | 🇨🇳 [中文 (简体)](i18n/zh-CN/USER_GUIDE.md) | 🇩🇪 [Deutsch](i18n/de/USER_GUIDE.md) | 🇮🇳 [हिन्दी](i18n/in/USER_GUIDE.md) | 🇹🇭 [ไทย](i18n/th/USER_GUIDE.md) | 🇺🇦 [Українська](i18n/uk-UA/USER_GUIDE.md) | 🇸🇦 [العربية](i18n/ar/USER_GUIDE.md) | 🇯🇵 [日本語](i18n/ja/USER_GUIDE.md) | 🇻🇳 [Tiếng Việt](i18n/vi/USER_GUIDE.md) | 🇧🇬 [Български](i18n/bg/USER_GUIDE.md) | 🇩🇰 [Dansk](i18n/da/USER_GUIDE.md) | 🇫🇮 [Suomi](i18n/fi/USER_GUIDE.md) | 🇮🇱 [עברית](i18n/he/USER_GUIDE.md) | 🇭🇺 [Magyar](i18n/hu/USER_GUIDE.md) | 🇮🇩 [Bahasa Indonesia](i18n/id/USER_GUIDE.md) | 🇰🇷 [한국어](i18n/ko/USER_GUIDE.md) | 🇲🇾 [Bahasa Melayu](i18n/ms/USER_GUIDE.md) | 🇳🇱 [Nederlands](i18n/nl/USER_GUIDE.md) | 🇳🇴 [Norsk](i18n/no/USER_GUIDE.md) | 🇵🇹 [Português (Portugal)](i18n/pt/USER_GUIDE.md) | 🇷🇴 [Română](i18n/ro/USER_GUIDE.md) | 🇵🇱 [Polski](i18n/pl/USER_GUIDE.md) | 🇸🇰 [Slovenčina](i18n/sk/USER_GUIDE.md) | 🇸🇪 [Svenska](i18n/sv/USER_GUIDE.md) | 🇵🇭 [Filipino](i18n/phi/USER_GUIDE.md)
Complete guide for configuring providers, creating combos, integrating CLI tools, and deploying OmniRoute.
---
@@ -43,11 +43,11 @@ Complete guide for configuring providers, creating combos, integrating CLI tools
| **💰 CHEAP** | GLM-4.7 | $0.6/1M | Daily 10AM | Budget backup |
| | MiniMax M2.1 | $0.2/1M | 5-hour rolling | Cheapest option |
| | Kimi K2 | $9/mo flat | 10M tokens/mo | Predictable cost |
| **🆓 FREE** | iFlow | $0 | Unlimited | 8 models free |
| **🆓 FREE** | Qoder | $0 | Unlimited | 8 models free |
| | Qwen | $0 | Unlimited | 3 models free |
| | Kiro | $0 | Unlimited | Claude free |
**💡 Pro Tip:** Start with Gemini CLI (180K free/month) + iFlow (unlimited free) combo = $0 cost!
**💡 Pro Tip:** Start with Gemini CLI (180K free/month) + Qoder (unlimited free) combo = $0 cost!
---
@@ -197,10 +197,10 @@ Models:
### 🆓 FREE Providers
#### iFlow (8 FREE models)
#### Qoder (8 FREE models)
```bash
Dashboard → Connect iFlow → OAuth login → Unlimited usage
Dashboard → Connect Qoder → OAuth login → Unlimited usage
Models: if/kimi-k2-thinking, if/qwen3-coder-plus, if/glm-4.7, if/minimax-m2, if/deepseek-r1
```
@@ -409,6 +409,106 @@ docker run -d --name omniroute -p 20128:20128 --env-file ./.env -v omniroute-dat
For host-integrated mode with CLI binaries, see the Docker section in the main docs.
### Void Linux (xbps-src)
Void Linux users can package and install OmniRoute natively using the `xbps-src` cross-compilation framework. This automates the Node.js standalone build along with the required `better-sqlite3` native bindings.
<details>
<summary><b>View xbps-src template</b></summary>
```bash
# Template file for 'omniroute'
pkgname=omniroute
version=3.2.4
revision=1
hostmakedepends="nodejs python3 make"
depends="openssl"
short_desc="Universal AI gateway with smart routing for multiple LLM providers"
maintainer="zenobit <zenobit@disroot.org>"
license="MIT"
homepage="https://github.com/diegosouzapw/OmniRoute"
distfiles="https://github.com/diegosouzapw/OmniRoute/archive/refs/tags/v${version}.tar.gz"
checksum=009400afee90a9f32599d8fe734145cfd84098140b7287990183dde45ae2245b
system_accounts="_omniroute"
omniroute_homedir="/var/lib/omniroute"
export NODE_ENV=production
export npm_config_engine_strict=false
export npm_config_loglevel=error
export npm_config_fund=false
export npm_config_audit=false
do_build() {
# Determine target CPU arch for node-gyp
local _gyp_arch
case "$XBPS_TARGET_MACHINE" in
aarch64*) _gyp_arch=arm64 ;;
armv7*|armv6*) _gyp_arch=arm ;;
i686*) _gyp_arch=ia32 ;;
*) _gyp_arch=x64 ;;
esac
# 1) Install all deps skip scripts
NODE_ENV=development npm ci --ignore-scripts
# 2) Build the Next.js standalone bundle
npm run build
# 3) Copy static assets into standalone
cp -r .next/static .next/standalone/.next/static
[ -d public ] && cp -r public .next/standalone/public || true
# 4) Compile better-sqlite3 native binding
local _node_gyp=/usr/lib/node_modules/npm/node_modules/node-gyp/bin/node-gyp.js
(cd node_modules/better-sqlite3 && node "$_node_gyp" rebuild --arch="$_gyp_arch")
# 5) Place the compiled binding into the standalone bundle
local _bs3_release=.next/standalone/node_modules/better-sqlite3/build/Release
mkdir -p "$_bs3_release"
cp node_modules/better-sqlite3/build/Release/better_sqlite3.node "$_bs3_release/"
# 6) Remove arch-specific sharp bundles
rm -rf .next/standalone/node_modules/@img
# 7) Copy pino runtime deps omitted by Next.js static analysis:
for _mod in pino-abstract-transport split2 process-warning; do
cp -r "node_modules/$_mod" .next/standalone/node_modules/
done
}
do_check() {
npm run test:unit
}
do_install() {
vmkdir usr/lib/omniroute/.next
vcopy .next/standalone/. usr/lib/omniroute/.next/standalone
# Prevent removal of empty Next.js app router dirs by the post-install hook
for _d in \
.next/standalone/.next/server/app/dashboard \
.next/standalone/.next/server/app/dashboard/settings \
.next/standalone/.next/server/app/dashboard/providers; do
touch "${DESTDIR}/usr/lib/omniroute/${_d}/.keep"
done
cat > "${WRKDIR}/omniroute" <<'EOF'
#!/bin/sh
export PORT="${PORT:-20128}"
export DATA_DIR="${DATA_DIR:-${XDG_DATA_HOME:-${HOME}/.local/share}/omniroute}"
export LOG_TO_FILE="${LOG_TO_FILE:-false}"
mkdir -p "${DATA_DIR}"
exec node /usr/lib/omniroute/.next/standalone/server.js "$@"
EOF
vbin "${WRKDIR}/omniroute"
}
post_install() {
vlicense LICENSE
}
```
</details>
### Environment Variables
| Variable | Default | Description |
@@ -450,7 +550,7 @@ For the full environment variable reference, see the [README](../README.md).
**MiniMax (`minimax/`)** — $0.2/1M: `minimax/MiniMax-M2.1`
**iFlow (`if/`)** — FREE: `if/kimi-k2-thinking`, `if/qwen3-coder-plus`, `if/deepseek-r1`
**Qoder (`if/`)** — FREE: `if/kimi-k2-thinking`, `if/qwen3-coder-plus`, `if/deepseek-r1`
**Qwen (`qw/`)** — FREE: `qw/qwen3-coder-plus`, `qw/qwen3-coder-flash`
@@ -582,6 +682,22 @@ Configure via **Dashboard → Settings → Routing**.
| **Least Used** | Routes to the account with the oldest `lastUsedAt` timestamp, distributing traffic evenly |
| **Cost Optimized** | Routes to the account with the lowest priority value, optimizing for lowest-cost providers |
#### External Sticky Session Header
For external session affinity (for example, Claude Code/Codex agents behind reverse proxies), send:
```http
X-Session-Id: your-session-key
```
OmniRoute also accepts `x_session_id` and returns the effective session key in `X-OmniRoute-Session-Id`.
If you use Nginx and send underscore-form headers, enable:
```nginx
underscores_in_headers on;
```
#### Wildcard Model Aliases
Create wildcard patterns to remap model names:
@@ -766,7 +882,7 @@ Access via **Dashboard → Health**. Real-time system health overview with 6 car
OmniRoute is available as a native desktop application for Windows, macOS, and Linux.
### Installation
### Installer
```bash
# From the electron directory:

Some files were not shown because too many files have changed in this diff Show More