Ayuriel/openclaw
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
16,977 Commits 756 Branches 79 Tags
Commit Graph

27 Commits

Author SHA1 Message Date
Peter Steinberger
ced267c5cb fix(moonshot): apply native thinking payload compatibility 2026-03-03 01:05:24 +00:00
Peter Steinberger
6b85ec3022 docs: tighten subscription guidance and update MiniMax M2.5 refs 2026-03-03 00:02:37 +00:00
scoootscooob
6c7d012320 fix(openrouter): skip reasoning.effort injection for x-ai/grok models 
x-ai/grok models on OpenRouter do not support the reasoning.effort
parameter and reject payloads containing it with "Invalid arguments
passed to the model." Skip reasoning injection for these models, the
same way we already skip it for the dynamic "auto" routing model.

Closes #32039

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-02 19:20:11 +00:00
Nikolay Petrov
a9f1188785
sessions_spawn: inline attachments with redaction, lifecycle cleanup, and docs (#16761) 
Add inline file attachment support for sessions_spawn (subagent runtime only):

- Schema: attachments[] (name, content, encoding, mimeType) and attachAs.mountPath hint
- Materialization: files written to .openclaw/attachments/<uuid>/ with manifest.json
- Validation: strict base64 decode, filename checks, size limits, duplicate detection
- Transcript redaction: sanitizeToolCallInputs redacts attachment content from persisted transcripts
- Lifecycle cleanup: safeRemoveAttachmentsDir with symlink-safe path containment check
- Config: tools.sessions_spawn.attachments (enabled, maxFiles, maxFileBytes, maxTotalBytes, retainOnSessionKeep)
- Registry: attachmentsDir/attachmentsRootDir/retainAttachmentsOnKeep on SubagentRunRecord
- ACP rejection: attachments rejected for runtime=acp with clear error message
- Docs: updated tools/index.md, concepts/session-tool.md, configuration-reference.md
- Tests: 85 new/updated tests across 5 test files

Fixes:
- Guard fs.rm in materialization catch block with try/catch (review concern #1)
- Remove unreachable fallback in safeRemoveAttachmentsDir (review concern #7)
- Move attachment cleanup out of retry path to avoid timing issues with announce loop

Co-authored-by: Tyler Yust <TYTYYUST@YAHOO.COM>
Co-authored-by: napetrov <napetrov@users.noreply.github.com>
 2026-03-01 21:33:51 -08:00
Peter Steinberger
d1615eb35f feat(openai): add websocket warm-up with configurable toggle 2026-03-01 22:45:03 +00:00
Agent
063c4f00ea docs: clarify Anthropic context1m long-context requirements 2026-03-01 22:35:26 +00:00
Peter Steinberger
8da86f6995 chore(changelog): note openai websocket-first streaming 2026-03-01 22:33:21 +00:00
Peter Steinberger
7ced38b5ef feat(agents): make openai responses websocket-first with fallback 2026-03-01 22:32:37 +00:00
Philipp Spiess
12618c333c tests: complete openai-responses model fixture typing 2026-02-27 22:30:30 +01:00
Peter Steinberger
8da3a9a92d fix(agents): auto-enable OpenAI Responses server-side compaction (#16930, #22441, #25088) 
Landed from contributor PRs #16930, #22441, and #25088.

Co-authored-by: liweiguang <codingpunk@gmail.com>
Co-authored-by: EdwardWu7 <wuzhiyuan7@gmail.com>
Co-authored-by: MoerAI <friendnt@g.skku.edu>
 2026-02-27 16:15:50 +00:00
Peter Steinberger
03d7641b0e feat(agents): default codex transport to websocket-first 2026-02-26 16:22:53 +01:00
Peter Steinberger
b35d00aaf8 fix: sanitize Gemini 3.1 Google reasoning payloads 2026-02-25 01:40:14 +00:00
Peter Steinberger
bd213cf2ad fix(agents): normalize SiliconFlow Pro thinking=off payload (#25435) 
Land PR #25435 from @Zjianru.
Changelog: add 2026.2.24 fix entry with contributor credit.

Co-authored-by: codez <codezhujr@gmail.com>
 2026-02-25 01:11:34 +00:00
Peter Steinberger
de0e01259a fix: expand openrouter thinking-off regression coverage (#24863) (thanks @DevSecTim) 2026-02-24 03:54:29 +00:00
Tim Jones
b96d32c1c2 chore: fix oxfmt formatting in extraparams test 
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-02-24 03:54:29 +00:00
Tim Jones
3e974dc93f fix: don't inject reasoning: { effort: "none" } for OpenRouter when thinking is off 
"off" is a truthy string, so the existing guard `if (thinkingLevel && ...)`
was always entering the injection block and sending `reasoning: { effort: "none" }`
to every OpenRouter request — even when thinking wasn't enabled. Models that
require reasoning (e.g. deepseek/deepseek-r1) reject this with:
  400 Reasoning is mandatory for this endpoint and cannot be disabled.

Fix: skip the reasoning injection entirely when thinkingLevel is "off".
The reasoning_effort flat-field cleanup still runs. Omitting the reasoning
field lets each model use its own default behavior.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-02-24 03:54:29 +00:00
Peter Steinberger
160bd61fff feat(agents): add per-agent stream params overrides for cache tuning (#17470) (thanks @rrenamed) 2026-02-23 18:46:40 +00:00
Peter Steinberger
be6f0b8c84 fix(providers): support Bedrock Anthropic cacheRetention defaults/pass-through (#22303) (thanks @snese) 2026-02-23 18:46:40 +00:00
Peter Steinberger
ca5c0bc02b fix(providers): disable Bedrock prompt caching for non-Anthropic models (#20866) (thanks @pierreeurope) 2026-02-23 18:46:40 +00:00
Vincent Koc
f03ff39754
Providers: skip context1m beta for Anthropic OAuth tokens (#24620) 
* Providers: skip context1m beta for Anthropic OAuth tokens

* Tests: cover OAuth context1m beta skip behavior

* Docs: note context1m OAuth incompatibility

* Agents: add context1m-aware context token resolver

* Agents: cover context1m context-token resolver

* Commands: apply context1m-aware context tokens in session store

* Commands: apply context1m-aware context tokens in status summary

* Status: resolve context tokens with context1m model params

* Status: test context1m status context display
 2026-02-23 12:29:09 -05:00
Peter Steinberger
ad1072842e test: dedupe agent tests and session helpers 2026-02-22 17:11:54 +00:00
Peter Steinberger
fcb86408fd test: move embedded and tool agent suites out of e2e 2026-02-22 11:17:47 +00:00
Peter Steinberger
9131b22a28 test: migrate suites to e2e coverage layout 2026-02-13 14:28:22 +00:00
Peter Steinberger
083ec9325e fix: cover OpenRouter attribution headers 2026-02-01 19:30:33 +00:00
Peter Steinberger
500c75b4f0 fix: align ZAI thinking toggles 2026-01-16 22:26:43 +00:00
Peter Steinberger
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
mneves75
f7b32195cb feat(agent): auto-enable GLM-4.7 thinking mode 
Add automatic thinking mode support for Z.AI GLM-4.x models:
- GLM-4.7: Preserved thinking (clear_thinking: false)
- GLM-4.5/4.6: Interleaved thinking (clear_thinking: true)

Uses Z.AI Cloud API format: thinking: { type: "enabled", clear_thinking: boolean }

Includes patches for pi-ai, pi-agent-core, and pi-coding-agent to pass
extraParams through the stream pipeline. User can override via config
or disable via --thinking off.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-08 04:10:56 +01:00