a705845e18
feat(agents): add experimental structured plan updates
2026-04-05 14:08:43 +01:00
760c4be438
feat(agents): add provider-owned system prompt contributions
2026-04-05 14:05:41 +01:00
38e54f488a
docs: refresh native approval ui mirrors
2026-04-04 21:44:30 +01:00
4f9804ec24
docs: refresh config schema and gateway tool mirrors
2026-04-04 21:43:09 +01:00
13396fa99e
docs: refresh gateway tool safe-edit mirrors
2026-04-04 20:31:34 +01:00
3b109c3419
docs: refresh push-based orchestration refs
2026-04-04 19:22:39 +01:00
db2cc5c28a
docs: refresh clawhub mirror refs
2026-04-04 13:29:07 +01:00
c5b2b69f94
docs: refresh live model switch docs
2026-04-04 11:49:23 +01:00
b59ce0903c
docs: add SOUL personality guide
2026-04-04 14:59:35 +09:00
1f660bf930
Docs: document agent skill allowlists
2026-04-03 14:23:05 -04:00
a3eed2b70f
fix(agents): avoid injecting memory file twice on case-insensitive mounts ( #26054 )
...
* fix(agents): avoid injecting memory file twice on case-insensitive mounts
On case-insensitive file systems mounted into Docker from macOS, both
MEMORY.md and memory.md pass fs.access() even when they are the same
underlying file. The previous dedup via fs.realpath() failed in this
scenario because realpath does not normalise case through the Docker
mount layer, so both paths were treated as distinct entries and the
same content was injected into the bootstrap context twice, wasting
tokens.
Fix by replacing the collect-then-dedup approach with an early-exit:
try MEMORY.md first; fall back to memory.md only when MEMORY.md is
absent. This makes the function return at most one entry regardless
of filesystem case-sensitivity.
* docs: clarify singular memory bootstrap fallback
* fix: note memory bootstrap fallback docs and changelog (#26054 ) (thanks @Lanfei)
---------
Co-authored-by: Ayaan Zaidi <hi@obviy.us >
2026-03-13 14:39:51 +05:30
e4b4486a96
Agent: unify bootstrap truncation warning handling ( #32769 )
...
Merged via squash.
Prepared head SHA: 5d6d4ddfa620011e267d892b402751847d5ac0c3
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com >
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com >
Reviewed-by: @gumadeiras
2026-03-03 16:28:38 -05:00
8a67016646
Agents: raise bootstrap total cap and warn on /context truncation ( #18229 )
...
Merged via /review-pr -> /prepare-pr -> /merge-pr.
Prepared head SHA: f6620526df231b571a8821edf9fc5f76c3994583
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com >
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com >
Reviewed-by: @gumadeiras
2026-02-16 12:04:53 -05:00
5b23999404
docs: document bootstrap total cap and exec log/notify behavior
2026-02-14 18:36:35 -05:00
aa1dbd34a1
docs: fix typo p-coding-agent -> pi-coding-agent
2026-02-14 16:30:48 +01:00
6ac56baf8e
docs: clarify which workspace files are injected into context window ( #12937 )
...
* docs: clarify which workspace files are injected into context window (#12909 )
The system prompt docs listed bootstrap files but omitted MEMORY.md,
which IS injected when present. This led users to assume memory files
are on-demand only and not consuming context tokens.
Changes:
- Add MEMORY.md to the bootstrap file list
- Note that all listed files consume tokens on every turn
- Clarify that memory/*.md daily files are NOT injected (on-demand only)
- Document sub-agent bootstrap filtering (AGENTS.md + TOOLS.md only)
Closes #12909
* docs: mention memory.md alternate filename in bootstrap list
Address review feedback: the runtime also injects lowercase memory.md
(DEFAULT_MEMORY_ALT_FILENAME) when present.
* docs: align memory bootstrap docs (#12937 ) (thanks @omair445)
---------
Co-authored-by: Luna AI <luna@coredirection.ai >
Co-authored-by: Sebastian <19554889+sebslight@users.noreply.github.com >
2026-02-10 10:06:23 -05:00
578a6e27aa
Docs: enable markdownlint autofixables except list numbering ( #10476 )
...
* docs(markdownlint): enable autofixable rules except list numbering
* docs(zalo): fix malformed bot platform link
2026-02-06 10:08:59 -05:00
0a1f4f666a
revert(docs): undo markdownlint autofix churn
2026-02-06 10:00:08 -05:00
c7aec0660e
docs(markdownlint): enable autofixable rules and normalize links
2026-02-06 09:55:12 -05:00
abcaa8c7a9
Docs: add nav titles across docs ( #5689 )
2026-01-31 15:04:03 -06:00
7a6c40872d
Agents: add system prompt safety guardrails ( #5445 )
...
* 🤖 agents: add system prompt safety guardrails
What:
- add safety guardrails to system prompt
- update system prompt docs
- update prompt tests
Why:
- discourage power-seeking or self-modification behavior
- clarify safety/oversight priority when conflicts arise
Tests:
- pnpm lint (pass)
- pnpm build (fails: DefaultResourceLoader missing in pi-coding-agent)
- pnpm test (not run; build failed)
* 🤖 agents: tighten safety wording for prompt guardrails
What:
- scope safety wording to system prompts/safety/tool policy changes
- document Safety inclusion in minimal prompt mode
- update safety prompt tests
Why:
- avoid blocking normal code changes or PR workflows
- keep prompt mode docs consistent with implementation
Tests:
- pnpm lint (pass)
- pnpm build (fails: DefaultResourceLoader missing in pi-coding-agent)
- pnpm test (not run; build failed)
* 🤖 docs: note safety guardrails are soft
What:
- document system prompt safety guardrails as advisory
- add security note on prompt guardrails vs hard controls
Why:
- clarify threat model and operator expectations
- avoid implying prompt text is an enforcement layer
Tests:
- pnpm lint (pass)
- pnpm build (fails: DefaultResourceLoader missing in pi-coding-agent)
- pnpm test (not run; build failed)
2026-01-31 15:50:15 +01:00
8cab78abbc
chore: Run pnpm format:fix.
2026-01-31 21:13:13 +09:00
fd00d5688a
chore: update openclaw naming
2026-01-30 21:03:11 +01:00
9a7160786a
refactor: rename to openclaw
2026-01-30 03:16:21 +01:00
6d16a658e5
refactor: rename clawdbot to moltbot with legacy compat
2026-01-27 12:21:02 +00:00
66eec295b8
perf: stabilize system prompt time
2026-01-24 06:24:04 +00:00
e0896de2bf
feat: surface repo root in runtime prompt
2026-01-22 05:20:42 +00:00
e9a08dc507
feat: enrich system prompt docs guidance
2026-01-18 15:00:36 +00:00
ad3c12a43a
feat: add bootstrap hook and soul-evil hook
2026-01-18 05:24:47 +00:00
bca5c0d569
refactor: system prompt sections + docs/tests
2026-01-16 00:28:43 +00:00
8b89980a89
feat(date-time): standardize time context and tool timestamps
2026-01-15 22:27:06 +00:00
c91c85532a
docs: add context concept page
2026-01-15 01:12:59 +00:00
755a7e1b20
feat: add configurable bootstrap truncation
2026-01-13 04:27:03 +00:00
98337a14b3
fix: rename bash tool to exec ( #748 ) (thanks @myfunc)
2026-01-12 02:49:55 +00:00
6d70524aa8
fix: add reasoning visibility hint
2026-01-10 22:24:22 +01:00
46e00ad5e7
fix: describe sandboxed elevated in prompt
2026-01-10 21:37:15 +01:00
24605379b9
refactor: centralize skills prompt resolution
2026-01-09 21:27:20 +01:00
4861f09f78
fix: inject skills prompt list
2026-01-09 21:20:51 +01:00
7b81d97ec2
feat: wire multi-agent config and routing
...
Co-authored-by: Mark Pors <1078320+pors@users.noreply.github.com >
2026-01-09 12:48:42 +00:00
3965c5b4d2
docs: naming sweep and platform wording
2026-01-08 23:25:51 +01:00
a6c309824e
docs: refresh and simplify docs
2026-01-08 23:07:20 +01:00
cad853b547
refactor: rebuild agent system prompt
2026-01-08 02:20:30 +01:00
Peter Steinberger