Summary:
- The PR removes the auto-reply runtime warning for visible-reply defaults, adds doctor preview warnings and tests for message-tool visibility policy mismatches, and updates the group/channel docs and changelog wording.
ClawSweeper fixups:
- No separate fixup commits were needed after automerge opt-in.
Validation:
- ClawSweeper review passed for head 1f96b3b568.
- Required merge gates passed before the squash merge.
Prepared head SHA: 1f96b3b568
Review: https://github.com/openclaw/openclaw/pull/75367#issuecomment-4357475980
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Keep async music generation completions on the requester-session wake path even when direct-send completion is enabled.
Also aligns config help, generated schema text, public docs, and the changelog so tools.media.asyncCompletion.directSend no longer claims to direct-send music completions.
Verification:
- pnpm test src/agents/tools/music-generate-background.test.ts src/agents/tools/video-generate-background.test.ts
- pnpm exec oxfmt --check --threads=1 src/agents/tools/media-generate-background-shared.ts src/agents/tools/music-generate-background.ts src/agents/tools/music-generate-background.test.ts src/config/schema.help.ts src/config/types.tools.ts docs/automation/tasks.md docs/gateway/config-tools.md CHANGELOG.md
- pnpm config:schema:check
- pnpm config:docs:check
- pnpm check:changelog-attributions
- git diff --check
- OPENCLAW_TESTBOX=1 pnpm check:changed
Derive context-window guard thresholds from the effective model window, keeping 10% hard-min and 20% warning ratios with 4k/8k floors.
Stop the embedded runner from forcing old fixed guard overrides so runtime admission uses the dynamic resolver.
Validation:
- CI run 25151866833 passed, including build-artifacts and checks-node-channels.
- Parity gate 25151866868 passed.
- Testbox pnpm test:channels passed: 54 files / 433 tests.
Fixes#42999.
Prepared head SHA: 9c80383639
* fix(skills): scan nested subdirectories for grouped skill layouts
Previously, skill discovery only checked immediate children of the
skills root for SKILL.md files. Skills organized in subdirectories
(e.g. ~/.openclaw/skills/coze/koze-retrieval/SKILL.md) were silently
ignored.
Now, when an immediate child directory does not contain a SKILL.md,
its own children are checked one level deeper. This supports grouped
skill layouts while keeping the scan depth bounded (max 2 levels) to
avoid unbounded filesystem traversal.
The existing per-source skill count limits and containment checks
still apply to nested discoveries.
Fixes#56915
* test(skills): cover nested grouped skill discovery
* fix(skills): cache contained-path checks and cap nested scans
- Reuse skillDirRealPath captured during the collection phase so the load
loop no longer re-runs resolveContainedSkillPath on the same directory.
- Apply the per-root candidate cap (and the matching warning log) when
descending into nested grouped skill directories, matching the outer
scan's behavior.
Addresses Greptile P2 feedback on PR #72534.
* fix(skills): load grouped skill directories under skills roots
* fix(clownfish): address review for ghcrawl-156697-autonomous-smoke (1)
---------
Co-authored-by: Otto Deng <otto@ottodeng.com>
Co-authored-by: vincentkoc <25068+vincentkoc@users.noreply.github.com>
Co-authored-by: Otto Deng <ottodeng2@github.local>
Adds the memory runtime quality shard to the PR CodeQL guard while preserving provider/plugin overlap only for the memory files that share those contracts.
Adds the Plugin SDK reply runtime quality shard to the PR CodeQL guard while keeping reply runtime changes on the existing plugin and package-contract shards.
