nyrn
/
openclaw
mirror of https://github.com/openclaw/openclaw.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
9,590 Commits 768 Branches 79 Tags 5.1 GiB
Commit Graph

1626 Commits

Author SHA1 Message Date
Peter Steinberger a7d6e44719 perf(test): reduce test startup overhead 2026-02-13 14:48:45 +00:00
Peter Steinberger 3bcde8df32 fix: finalize vLLM onboarding integration (#12577) (thanks @gejifeng) 2026-02-13 15:48:37 +01:00
gejifeng 03c502ef31 lint: fix unused imports and onboarding preferred provider 2026-02-13 15:48:37 +01:00
gejifeng 94d5411f11 fix: remove duplicate TOGETHER_BASE_URL 2026-02-13 15:48:37 +01:00
gejifeng 3e7956b008 fix code review 2026-02-13 15:48:37 +01:00
gejifeng 0472dd68f0 fix code review 2026-02-13 15:48:37 +01:00
gejifeng e73d881c50 Onboarding: add vLLM provider support 2026-02-13 15:48:37 +01:00
Yaxuan42 54bf5d0f41
feat(web-fetch): support Cloudflare Markdown for Agents (#15376) 
Merged via /review-pr -> /prepare-pr -> /merge-pr.

Prepared head SHA: d0528dc429
Co-authored-by: Yaxuan42 <184813557+Yaxuan42@users.noreply.github.com>
Co-authored-by: steipete <58493+steipete@users.noreply.github.com>
Reviewed-by: @steipete
 2026-02-13 15:46:20 +01:00
Peter Steinberger 9131b22a28 test: migrate suites to e2e coverage layout 2026-02-13 14:28:22 +00:00
Peter Steinberger 990413534a
fix: land multi-agent session path fix + regressions (#15103) (#15448) 
Co-authored-by: Josh Lehman <josh@martian.engineering>
 2026-02-13 14:17:24 +01:00
JINNYEONG KIM 94763cd87d
Fix OpenAI/Codex tool call id sanitization for transcript policy (#15279) 2026-02-13 11:39:51 +00:00
loiie45e 07faab6ac3
openai-codex: bridge OAuth profiles into pi auth.json for model discovery (#15184) 2026-02-13 11:39:37 +00:00
Lucky e3cb2564d7
Agents: allow gpt-5.3-codex-spark in fallback and thinking (#14990) 
* Agents: allow gpt-5.3-codex-spark in fallback and thinking

* Fix: model picker issue for openai-codex/gpt-5.3-codex-spark

Fixed an issue in the model picker.
 2026-02-13 11:39:22 +00:00
青雲 fd076eb43a
fix: /status shows incorrect context percentage — totalTokens clamped to contextTokens (#15114) (#15133) 
Merged via /review-pr -> /prepare-pr -> /merge-pr.

Prepared head SHA: a489669fc7
Co-authored-by: echoVic <16428813+echoVic@users.noreply.github.com>
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Reviewed-by: @gumadeiras
 2026-02-12 23:52:19 -05:00
Gustavo Madeira Santana ac41176532
Auto-reply: fix non-default agent session transcript path resolution (#15154) 
* Auto-reply: fix non-default agent transcript path resolution

* Auto-reply: harden non-default agent transcript lookups

* Auto-reply: harden session path resolution across agent stores
 2026-02-12 23:23:12 -05:00
seheepeak 23e4183608
fix(sandbox): force network bridge for browser container (#6961) 2026-02-13 05:17:17 +01:00
George Pickett a067565db5 fix: pass sandbox docker env into containers (#15138) (thanks @stevebot-alive) 2026-02-12 19:39:22 -08:00
Steve (OpenClaw) 92567765e6 fix(sandbox): pass docker.env into sandbox container 2026-02-12 19:39:22 -08:00
Tak Hoffman 89bfe0c944
fix: add adapter-path after_tool_call coverage (follow-up to #15012) (#15105) 2026-02-12 19:39:23 -06:00
Peter Steinberger 85409e401b fix: preserve inter-session input provenance (thanks @anbecker) 2026-02-13 02:02:01 +01:00
Patrick Barletta d34138dfee
fix: dispatch before_tool_call and after_tool_call hooks from both tool execution paths (openclaw#15012) thanks @Patrick-Barletta 
Verified:
- pnpm check

Co-authored-by: Patrick-Barletta <67929313+Patrick-Barletta@users.noreply.github.com>
 2026-02-12 18:48:11 -06:00
Peter Steinberger 4199f9889f fix: harden session transcript path resolution 2026-02-13 01:28:17 +01:00
Peter Steinberger 3eb6a31b6f fix: confine sandbox skill sync destinations 2026-02-13 01:24:51 +01:00
Kyle Tse 2655041f69
fix: wire 9 unwired plugin hooks to core code (openclaw#14882) thanks @shtse8 
Verified:
- GitHub CI checks green (non-skipped)

Co-authored-by: shtse8 <8020099+shtse8@users.noreply.github.com>
 2026-02-12 18:14:14 -06:00
Vladimir Peshekhonov 957b883082
fix(agents): stabilize overflow compaction retries and session context accounting (openclaw#14102) thanks @vpesh 
Verified:
- CI checks for commit 86a7ecb45e
- Rebase conflict resolution for compatibility with latest main

Co-authored-by: vpesh <9496634+vpesh@users.noreply.github.com>
 2026-02-12 17:53:13 -06:00
Peter Steinberger da55d70fb0 fix(security): harden untrusted web tool transcripts 2026-02-13 00:46:56 +01:00
Kyle Tse a10f228a5b
fix: update totalTokens after compaction using last-call usage (#15018) 
Merged via /review-pr -> /prepare-pr -> /merge-pr.

Prepared head SHA: 9214291bf7
Co-authored-by: shtse8 <8020099+shtse8@users.noreply.github.com>
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Reviewed-by: @gumadeiras
 2026-02-12 18:02:30 -05:00
Shadow 149db5b2c2
Discord: handle thread edit params 2026-02-12 16:31:06 -06:00
Skyler Miao cb0350230c
feat(minimax): update models from M2.1 to M2.5 (#14865) 
Merged via /review-pr -> /prepare-pr -> /merge-pr.

Prepared head SHA: 1d58bc5760
Co-authored-by: adao-max <153898832+adao-max@users.noreply.github.com>
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Reviewed-by: @gumadeiras
 2026-02-12 16:48:46 -05:00
0xRain d8d8109711
fix(agents): guard against undefined path in context file entries (#14903) 
Merged via /review-pr -> /prepare-pr -> /merge-pr.

Prepared head SHA: 25856b863d
Co-authored-by: 0xRaini <190923101+0xRaini@users.noreply.github.com>
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Reviewed-by: @gumadeiras
 2026-02-12 15:27:56 -05:00
fagemx bdd0c12329
fix(providers): include provider name in billing error messages (#14697) 
Merged via /review-pr -> /prepare-pr -> /merge-pr.

Prepared head SHA: 774e0b6605
Co-authored-by: fagemx <117356295+fagemx@users.noreply.github.com>
Co-authored-by: shakkernerd <165377636+shakkernerd@users.noreply.github.com>
Reviewed-by: @shakkernerd
 2026-02-12 18:23:27 +00:00
Peter Steinberger 5e7842a41d
feat(zai): auto-detect endpoint + default glm-5 (#14786) 
* feat(zai): auto-detect endpoint + default glm-5

* test: fix Z.AI default endpoint expectation (#14786)

* test: bump embedded runner beforeAll timeout

* chore: update changelog for Z.AI GLM-5 autodetect (#14786)

* chore: resolve changelog merge conflict with main (#14786)

* chore: append changelog note for #14786 without merge conflict

* chore: sync changelog with main to resolve merge conflict
 2026-02-12 19:16:04 +01:00
Yi Liu d3aee84499
fix(security): add --ignore-scripts to skills install commands (#14659) 
Skills install runs package manager install commands (npm, pnpm, yarn,
bun) without --ignore-scripts, allowing malicious npm packages to
execute arbitrary code via postinstall/preinstall lifecycle scripts
during global installation.

This is inconsistent with the security fix in commit 92702af7a which
added --ignore-scripts to both plugin installs (src/plugins/install.ts)
and hook installs (src/hooks/install.ts). Skills install was overlooked
in that change.

Global install (-g) is particularly dangerous as scripts execute with
the user's full permissions and can modify globally-accessible binaries.
 2026-02-13 02:56:35 +09:00
Peter Steinberger d25e96637c test(agents): make grok api key test hermetic 2026-02-12 17:17:02 +00:00
Sebastian d31caa81ef fix(runtime): guard cleanup and preserve skipped cron jobs 2026-02-12 09:28:47 -05:00
0xRain 4f329f923c
fix(agents): narrow billing error 402 regex to avoid false positives on issue IDs (#13827) 
Merged via /review-pr -> /prepare-pr -> /merge-pr.

Prepared head SHA: b0501bbab7
Co-authored-by: 0xRaini <190923101+0xRaini@users.noreply.github.com>
Co-authored-by: sebslight <19554889+sebslight@users.noreply.github.com>
Reviewed-by: @sebslight
 2026-02-12 09:18:06 -05:00
Akari 455bc1ebba
fix: use last API call's cache tokens for context-size display (#13698) (#13805) 
The UsageAccumulator sums cacheRead/cacheWrite across all API calls
within a single turn. With Anthropic prompt caching, each call reports
cacheRead ≈ current_context_size, so after N tool-call round-trips the
accumulated total becomes N × actual_context, which gets clamped to
contextWindow (200k) by deriveSessionTotalTokens().

Fix: track the most recent API call's cache fields separately and use
them in toNormalizedUsage() for context-size reporting. This makes
/status Context display accurate while preserving accumulated output
token counts.

Fixes #13698
Fixes #13782

Co-authored-by: akari-musubi <259925157+akari-musubi@users.noreply.github.com>
 2026-02-12 08:01:36 -06:00
Kyle Chen 4c350bc4c8
Fix: Prevent file descriptor leaks in child process cleanup (#13565) 
* fix: prevent FD leaks in child process cleanup

- Destroy stdio streams (stdin/stdout/stderr) after process exit
- Remove event listeners to prevent memory leaks
- Clean up child process reference in moveToFinished()
- Also fixes model override handling in agent.ts

Fixes EBADF errors caused by accumulating file descriptors
from sub-agent spawns.

* Fix: allow stdin destroy in process registry cleanup

---------

Co-authored-by: Tak Hoffman <781889+Takhoffman@users.noreply.github.com>
 2026-02-12 08:01:33 -06:00
jg-noncelogic 6f74786384
fix(antigravity): opus 4.6 forward-compat model + thinking signature sanitization bypass (#14218) 
Two fixes for Google Antigravity (Cloud Code Assist) reliability:

1. Forward-compat model fallback: pi-ai's model registry doesn't include
   claude-opus-4-6-thinking. Add resolveAntigravityOpus46ForwardCompatModel()
   that clones the opus-4-5 template so the correct api ("google-gemini-cli")
   and baseUrl are preserved. Fixes #13765.

2. Fix thinking.signature rejection: The API returns Claude thinking blocks
   without signatures, then rejects them on replay. The existing sanitizer
   strips unsigned blocks, but the orphaned-user-message path in attempt.ts
   bypassed it by reading directly from disk. Now applies
   sanitizeAntigravityThinkingBlocks at that code path.

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-12 08:01:28 -06:00
Taras Lukavyi d85150357f
feat: support .agents/skills/ directory for cross-agent skill discovery (#9966) 
Adds loading from two .agents/skills/ locations:
- ~/.agents/skills/ (personal/user-level, source "agents-skills-personal")
- {workspace}/.agents/skills/ (project-level, source "agents-skills-project")

Precedence: extra < bundled < managed < personal .agents/skills < project .agents/skills < workspace.

Closes #8822
 2026-02-12 07:56:19 -06:00
taw0002 dcb921944a
fix: prevent double compaction caused by cache-ttl entry bypassing guard (#13514) 
Move appendCacheTtlTimestamp() to after prompt + compaction retry
completes instead of before. The previous placement inserted a custom
entry (openclaw.cache-ttl) between compaction and the next prompt,
which broke pi-coding-agent's prepareCompaction() guard — the guard
only checks if the last entry is type 'compaction', and the cache-ttl
custom entry made it type 'custom', allowing an immediate second
compaction at very low token counts (e.g. 5,545 tokens) that nuked
all preserved context.

Fixes #9282
Relates to #12170
 2026-02-12 07:55:32 -06:00
Tomsun28 540996f10f
feat(provider): Z.AI endpoints + model catalog (#13456) (thanks @tomsun28) (#13456) 
Co-authored-by: Tak Hoffman <781889+Takhoffman@users.noreply.github.com>
 2026-02-12 07:01:48 -06:00
0xRain 4b86c9e555
fix(telegram): surface REACTION_INVALID as non-fatal warning (#14340) 
Co-authored-by: Tak Hoffman <781889+Takhoffman@users.noreply.github.com>
 2026-02-12 00:28:47 -06:00
Rodrigo Uroz b912d3992d
(fix): handle Cloudflare 521 and transient 5xx errors gracefully (#13500) 
Merged via /review-pr -> /prepare-pr -> /merge-pr.

Prepared head SHA: a8347e95c5
Co-authored-by: rodrigouroz <384037+rodrigouroz@users.noreply.github.com>
Co-authored-by: Takhoffman <781889+Takhoffman@users.noreply.github.com>
Reviewed-by: @Takhoffman
 2026-02-11 21:42:33 -06:00
Jake 631102e714
fix(agents): scope process/exec tools to sessionKey for isolation (#4887) 
Merged via /review-pr -> /prepare-pr -> /merge-pr.

Prepared head SHA: 5d30672e75
Co-authored-by: mcinteerj <3613653+mcinteerj@users.noreply.github.com>
Co-authored-by: Takhoffman <781889+Takhoffman@users.noreply.github.com>
Reviewed-by: @Takhoffman
 2026-02-11 19:55:12 -06:00
0xRain 1d2c5783fd
fix(agents): enable tool call ID sanitization for Anthropic provider (#13830) 
Co-authored-by: 0xRaini <0xRaini@users.noreply.github.com>
 2026-02-12 08:42:24 +09:00
0xRain 43818e1583
fix(agents): re-run tool_use pairing repair after history truncation (#13926) 
Co-authored-by: 0xRaini <0xRaini@users.noreply.github.com>
 2026-02-12 08:42:05 +09:00
0xRain 729181bd06
fix(agents): exclude rate limit errors from context overflow classification (#13747) 
Co-authored-by: 0xRaini <rain@0xRaini.dev>
 2026-02-12 08:40:09 +09:00
Dario Zhang e85bbe01f2
fix: report subagent timeout as 'timed out' instead of 'completed successfully' (#13996) 
* fix: report subagent timeout as 'timed out' instead of 'completed successfully'

* fix: propagate subagent timeout status across agent.wait (#13996) (thanks @dario-github)

---------

Co-authored-by: Sebastian <19554889+sebslight@users.noreply.github.com>
 2026-02-11 12:55:30 -05:00
Kyle Tse 50a60b8be6
fix: use configured base URL for Ollama model discovery (#14131) 
Merged via /review-pr -> /prepare-pr -> /merge-pr.

Prepared head SHA: 2292d2de6d
Co-authored-by: shtse8 <8020099+shtse8@users.noreply.github.com>
Reviewed-by: @gumadeiras
 2026-02-11 10:51:59 -05:00