Commit Graph

26 Commits

Author SHA1 Message Date
Diego Rodrigues de Sa e Souza 9691469987 Update docs/openapi.yaml
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2026-03-05 08:42:21 -03:00
diegosouzapw bddec84f4e feat: add MCP server, A2A protocol, auto-combo engine & VS Code extension
Introduce full AI orchestration ecosystem:
- MCP Server with 16 tools, scoped auth, and audit logging
- A2A v0.3 server with JSON-RPC 2.0, SSE streaming, and task manager
- Auto-Combo engine with 6-factor scoring and self-healing
- VS Code extension with smart dispatch and budget tracking
- Harden CI pipeline: add static checks, remove continue-on-error
- Add translator schema validation tests
- Update .gitignore and CHANGELOG for release checklist
2026-03-04 18:45:02 -03:00
diegosouzapw 52221488d0 docs: sync all 30 language READMEs with v1.7.3 features + create workflow files
- Synced feature tables across all 28 translated READMEs (Model Aliases, Background Degradation, Rate Limit Persistence, Token Refresh Resilience)
- Updated 6 docs/i18n/*/FEATURES.md with new Settings description
- Created workflows: update-docs.md (with multi-language sync step), generate-release.md, issue-triage.md
2026-03-01 22:02:38 -03:00
diegosouzapw 4a1acb1446 feat(release): v1.7.3 — model deprecation, background degradation, rate limit persistence, thinking improvements, circuit breaker
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
Features:
- Model Deprecation Auto-Forward (10+ built-in aliases + custom via UI)
- Background Task Smart Degradation (19 patterns, degradation map)
- Rate Limit Persistence (SQLite, 60s debounce, 24h staleness)
- thinkingLevel string → budget conversion (high/medium/low/none)
- Claude -thinking model auto-injection
- Gemini 3.0/3.1 model registry distinction
- Token Refresh Circuit Breaker (5 failures → 30min cooldown)

Tests: 561 total (40+ new), 0 failures
2026-03-01 21:42:39 -03:00
Diego Rodrigues de Sa e Souza 0488f0536e Update docs/TROUBLESHOOTING.md
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-03-01 06:33:22 -03:00
PSBigBig × MiniPS 61e09d545f docs: add optional RAG failure taxonomy to troubleshooting 2026-03-01 10:56:51 +08:00
diegosouzapw e4d83e91bb chore(release): prepare release v1.6.7
- CHANGELOG: add v1.6.7 entry (Copilot Config Generator #142)
- FEATURES.md: add Copilot to CLI Tools section
- Version bump: 1.6.6 → 1.6.7 (package.json + electron/package.json)
2026-02-28 11:53:39 -03:00
diegosouzapw 9a3d72c6a2 docs: update electron/README.md, USER_GUIDE.md, FEATURES.md with desktop app docs 2026-02-28 08:33:55 -03:00
diegosouzapw d3ace8d611 fix: security hardening, tests, docs for Electron desktop & memory optimization
## Security Fixes
- Sanitize OMNIROUTE_MEMORY_MB with parseInt + range validation (64-16384)
  to prevent command injection via spawn() args
- Validate URL protocol in shell.openExternal (http/https only)
  to prevent RCE in Electron renderer compromise
- Bump default memory from 256MB to 512MB

## Electron package-lock.json
- Added to .gitignore (5278 lines removed from tracking)

## Test Suite (64 tests, 9 suites)
- electron-main.test.mjs: URL validation, IPC channels, window handler
- electron-preload.test.mjs: channel whitelist, API surface, open-external
- cli-memory.test.mjs: injection prevention, boundary values, .env parsing

## Documentation
- Desktop App section added to all 30 READMEs (9 fully translated)
- USER_GUIDE.md updated with 512MB default
- .env.example reflects new defaults
2026-02-28 07:59:38 -03:00
benzntech a3d15cf971 fix: address PR review comments
- Fix server restart logic to use event-based termination
- Use app.getPath('userData') for cross-platform data directory
- Implement VALID_CHANNELS validation in preload script
- Fix incorrect copy command in user guide
- Fix broken markdown table formatting

Refs: #150
2026-02-28 11:54:41 +05:30
benzntech 6ed98fb21c Merge branch 'main' of https://github.com/diegosouzapw/OmniRoute into feat/memory-optimization 2026-02-28 09:52:39 +05:30
diegosouzapw 7feac7a158 docs: Remove OMNI_TOKEN placeholders and malformed tokens from internationalized documentation and READMEs. 2026-02-26 17:12:52 -03:00
diegosouzapw 952b0b22c7 docs(i18n): add Swedish locale translations and i18n QA tooling
Add complete Swedish (sv) translation for all documentation files
including API Reference, README, and guides. Introduce automated
i18n QA infrastructure with visual regression testing across
multiple viewports and locales to validate translations.
2026-02-26 16:28:29 -03:00
diegosouzapw 4cfd1b94e1 docs: add multi-language i18n documentation translations
Add translated documentation (API Reference, Guide, README) for 30+
languages under docs/i18n/, including pt-BR, es, fr, de, it, ru, zh-CN,
ja, ko, ar, and many others to improve international accessibility.
2026-02-26 16:27:43 -03:00
diegosouzapw 1647005d6e docs(i18n): add multilingual documentation translations
Add translated documentation files for multiple languages including
Korean, Polish, and others under docs/i18n/. Translations cover
API reference, quickstart guides, and project documentation to
improve accessibility for non-English speaking contributors.
2026-02-26 16:26:59 -03:00
diegosouzapw 369a0141de docs(i18n): add Hungarian translation of ARCHITECTURE.md
Add Magyar (hu) translation of the architecture documentation
to support Hungarian-speaking contributors and users.
2026-02-26 16:26:35 -03:00
diegosouzapw cc97917ee2 docs(i18n): add Bulgarian translation for TROUBLESHOOTING.md
Add complete Bulgarian (bg) localization of the troubleshooting guide,
covering provider issues, cloud sync, Docker, CLI tools, routing,
environment variables, and debugging instructions.
2026-02-26 16:25:54 -03:00
diegosouzapw 0f49f82405 feat(docs): add i18n multi-language support for documentation
Add language selector banners to all English documentation files
linking to translations in 30+ languages. Update .gitignore to
track docs/i18n/ directory and fix path patterns for node_modules,
coverage, and .next directories.
2026-02-26 16:24:36 -03:00
diegosouzapw 77a3eece32 docs: update README, README.pt-BR, TROUBLESHOOTING with v1.4.9-v1.4.11 features
- Added proxy visibility + 3-level proxy config to feature tables
- Added language selector and DATA_DIR env var entries
- Added EACCES and routing strategy fix to troubleshooting quick fixes
- Equivalent changes in both EN and PT-BR READMEs
2026-02-26 03:09:09 -03:00
diegosouzapw 88d5986ac1 docs: add per-page i18n translation task files with string inventories 2026-02-25 13:20:33 -03:00
benzntech 5a2fdacebe feat(memory): optimize RAM usage for low-memory deployments
- Add Node.js heap limit (256MB default) via OMNIROUTE_MEMORY_MB
- Convert LRU caches to byte-based limits (2-4MB)
- Reduce in-memory buffer sizes: 500→200 entries
- Add .env file loading in CLI for global npm installs
- Add PM2 ecosystem.config.js example for deployment
- Document memory tuning env vars in USER_GUIDE.md

Estimated RAM reduction: ~60-70% (from ~512MB+ to ~150-200MB)
2026-02-23 14:16:47 +05:30
diegosouzapw 340dcf9515 feat(core): api key protection, provider blocking, windows fix, ui and docs 2026-02-21 09:05:59 -03:00
diegosouzapw 4c93f0618c feat: Add dashboard loading and error UIs, introduce standardized API response utilities, enhance call log redaction and configurable retention, and document architectural decisions. 2026-02-18 11:34:05 -03:00
diegosouzapw ed05599cdd feat(api-compat): response sanitization, role normalization, structured output for Gemini
- Add responseSanitizer.ts: strips non-standard fields (x_groq, usage_breakdown, service_tier),
  extracts <think> tags into reasoning_content, normalizes id/object/usage for strict OpenAI SDK v1.83+ compatibility
- Add roleNormalizer.ts: developer→system for non-OpenAI providers, system→user merging for GLM/ERNIE models
- Integrate sanitizer into chatCore.ts (non-streaming) and stream.ts (streaming passthrough)
- Integrate role normalizer into translator/index.ts pipeline
- Add response_format (json_schema/json_object) → Gemini responseMimeType/responseSchema conversion
- Update CHANGELOG.md with v1.1.0 entry
- Update README.md, ARCHITECTURE.md, TROUBLESHOOTING.md with new capabilities
2026-02-18 08:38:44 -03:00
diegosouzapw 983920b735 chore: update hero image to MainOmniRoute.png in all READMEs
Replaced ./images/omniroute.png → ./docs/screenshots/MainOmniRoute.png
2026-02-18 00:10:39 -03:00
diegosouzapw 71d14209a4 feat: OmniRoute v1.0.0 — Intelligent AI Gateway & Universal LLM Proxy
OmniRoute is an intelligent API gateway that unifies 20+ AI providers behind a single
OpenAI-compatible endpoint. Features include intelligent routing with 6 strategies,
multi-format translation (OpenAI/Claude/Gemini/Responses API), circuit breakers,
semantic caching, combo fallback chains, real-time health monitoring, and a full
dashboard with provider management, analytics, and CLI tool integration.

Key highlights:
- 20+ providers (Claude Code, Codex, Gemini CLI, GitHub Copilot, iFlow, Qwen, Kiro, etc.)
- 6 routing strategies (Fill First, Round Robin, P2C, Random, Least Used, Cost Optimized)
- Export/Import database backup with full archive support
- Translator Playground with 4 modes (Playground, Chat Tester, Test Bench, Live Monitor)
- 100% TypeScript across src/ and open-sse/
- Docker support with multi-stage builds
- Comprehensive documentation and 9 dashboard screenshots
2026-02-18 00:02:15 -03:00