Skip to content

docs(memory): align descriptors and docs with recursive memory/**/*.md#85899

Closed
leafbird wants to merge 2 commits into
openclaw:mainfrom
leafbird:docs/memory-recursive-wording
Closed

docs(memory): align descriptors and docs with recursive memory/**/*.md#85899
leafbird wants to merge 2 commits into
openclaw:mainfrom
leafbird:docs/memory-recursive-wording

Conversation

@leafbird

@leafbird leafbird commented May 24, 2026 •
edited
Loading

Copy link
Copy Markdown

Summary

  • The runtime already walks memory/ recursively via collectMemoryFilesFromDir (packages/memory-host-sdk/src/host/internal.ts), so nested files like memory/YYYY-MM/YYYY-MM-DD.md are indexed and searched. But several agent-facing descriptors and public docs still said memory/*.md, which can mislead agents into thinking the index is flat.
  • This PR updates the remaining stale references to memory/**/*.md. No runtime behavior change.

Files touched

  • extensions/memory-core/index.ts — lazy memory_search / memory_get descriptors
  • extensions/memory-core/src/tools.ts — concrete memory_search / memory_get descriptions
  • extensions/memory-core/src/prompt-section.ts — system-prompt recall guidance
  • src/config/schema.help.ts — agents.defaults.memorySearch help text
  • docs/concepts/memory-builtin.md, memory.md, system-prompt.md
  • docs/gateway/config-agents.md, docs/reference/token-use.md
  • docs/.generated/config-baseline.sha256 regenerated via pnpm config:docs:gen

Note

This supersedes #72748. That PR also carried QMD watcher changes that were independently resolved upstream by #81802 (watch-settle.ts), so the surviving value was just this wording alignment. Splitting it out as a small, behavior-neutral PR for easier review.

Real behavior proof

Behavior or issue addressed: Agent-facing descriptors and public docs said memory/*.md even though the runtime already walks memory/ recursively and indexes nested files such as memory/YYYY-MM/YYYY-MM-DD.md. This PR aligns the wording to memory/**/*.md so agents and readers see what is actually indexed. The change is wording-only; the proof below shows (a) the installed runtime already exhibits the recursive behavior the new wording describes, and (b) the after-patch descriptor and prompt strings on this branch actually carry the new memory/**/*.md wording when imported at runtime.

Real environment tested: Installed OpenClaw 2026.5.20 (npm global, current latest published build, ahead of the acf265d base this PR branches from), against the live workspace ~/.openclaw/workspace-moku used by the gateway. Agent main, local embedding provider, per-agent SQLite memory store at ~/.openclaw/memory/main.sqlite. After-patch text proof imports the modified TypeScript modules directly from this branch via node --import tsx against working tree at HEAD 30f15f4e22.

Exact steps or command run after this patch:

Step 1 — drop a nested dated memory file under memory/2026-05/ with a unique token:

cat > ~/.openclaw/workspace-moku/memory/2026-05/2026-05-24-recursive-proof.md <<'EOF'
Recursive memory search proof.
Unique token for PR 85899 smoke test: PROOFTOKEN_QXZ7K_NESTED_RECURSIVE_MEMORY
This file lives at memory/2026-05/2026-05-24-recursive-proof.md
EOF

Step 2 — reindex the live agent's memory store:

openclaw memory index

Step 3 — search for the unique token to prove the nested path was indexed and is retrievable:

openclaw memory search "PROOFTOKEN_QXZ7K_NESTED_RECURSIVE_MEMORY" --max-results 3

Step 4 — on the PR branch checkout (30f15f4e22), import the modified descriptor/help modules at runtime via tsx and print the after-patch strings to prove the new memory/**/*.md wording is observable from a real runtime call site (not just the diff):

node --import tsx _proof-c.mjs   # imports FIELD_HELP and buildPromptSection from this branch

After-fix evidence: Terminal output from the installed openclaw 2026.5.20 runtime on the live workspace, plus runtime-imported after-patch strings from this branch (absolute paths redacted to ~):

$ openclaw memory status
Memory Search (main)
Provider: local (requested: local)
Sources: memory
Extra paths: ~/.openclaw/shared-memory
Indexed: 105/105 files . 933 chunks
Workspace: ~/.openclaw/workspace-moku
By source:
  memory . 105/105 files . 933 chunks

$ openclaw memory index
[node-llama-cpp] ... falling back to using no GPU
Memory index updated (main).

$ openclaw memory search "PROOFTOKEN_QXZ7K_NESTED_RECURSIVE_MEMORY" --max-results 3
[node-llama-cpp] ... falling back to using no GPU
0.812 memory/2026-05/2026-05-24-recursive-proof.md:1-9
    Recursive memory search proof.
    Unique token for PR 85899 smoke test: PROOFTOKEN_QXZ7K_NESTED_RECURSIVE_MEMORY
    This file lives at memory/2026-05/2026-05-24-recursive-proof.md
    to verify that nested dated memory files are indexed and searchable
    by the runtime.

0.450 memory/fix-openclaw/memory-recursive-search/smoke/2026-04-27.md:1-6
0.432 memory/fix-openclaw/memory-recursive-search/pr-draft.md:1-32

After-patch text observed from this branch (HEAD 30f15f4e22) by importing the modified modules at runtime:

$ node --import tsx _proof-c.mjs
=== schema.help.ts: FIELD_HELP['agents.defaults.memorySearch'] ===
Vector search over MEMORY.md and memory/**/*.md (per-agent overrides supported).

=== prompt-section.ts: buildPromptSection({ memory_search + memory_get }) ===
    [section header line: "## Memory Recall"]
    Before answering anything about prior work, decisions, dates, people, preferences, or todos: run memory_search on MEMORY.md + memory/**/*.md + indexed session transcripts; then use memory_get to pull only the needed lines. If low confidence after search, say you checked.
    Citations are disabled: do not mention file paths or line numbers in replies unless the user explicitly asks.

=== prompt-section.ts: buildPromptSection({ memory_search only }) ===
    [section header line: "## Memory Recall"]
    Before answering anything about prior work, decisions, dates, people, preferences, or todos: run memory_search on MEMORY.md + memory/**/*.md + indexed session transcripts and answer from the matching results. If low confidence after search, say you checked.
    Citations are disabled: do not mention file paths or line numbers in replies unless the user explicitly asks.

=== extensions/memory-core/index.ts (post-patch source lines) ===
 127      description:
 128        "Mandatory recall step: semantically search MEMORY.md + memory/**/*.md (and optional session transcripts) before answering questions about prior work, decisions, dates, people, preferences, or todos. ...",

 139      description:
 140        "Safe exact excerpt read from MEMORY.md or memory/**/*.md. Defaults to a bounded excerpt when lines are omitted, includes truncation/continuation info when more content exists, and `corpus=wiki` reads from registered compiled-wiki supplements.",

=== extensions/memory-core/src/tools.ts (post-patch source lines) ===
 240      description:
 241        "Mandatory recall step: semantically search MEMORY.md + memory/**/*.md (and optional session transcripts) before answering questions about prior work, decisions, dates, people, preferences, or todos. ...",

 410      description:
 411        "Safe exact excerpt read from MEMORY.md or memory/**/*.md. Defaults to a bounded excerpt when lines are omitted, includes truncation/continuation info when more content exists, and `corpus=wiki` reads from registered compiled-wiki supplements.",

Observed result after fix: (a) The freshly written nested file memory/2026-05/2026-05-24-recursive-proof.md (two levels deep under memory/) was indexed by openclaw memory index and returned as the top match (score 0.812) for the unique token. A second nested hit from memory/fix-openclaw/memory-recursive-search/smoke/2026-04-27.md (three levels deep) confirms recursion is not limited to one level. (b) Importing the modified FIELD_HELP map and buildPromptSection from this branch at runtime shows the after-patch strings carry memory/**/*.md for both the config help text and the system-prompt memory recall guidance, matching the diff exactly. (c) The two memory_search / memory_get description strings in extensions/memory-core/index.ts and extensions/memory-core/src/tools.ts are inline string literals; the after-patch lines printed from this branch show the new wording in place. No runtime code paths are modified, only the descriptor and doc strings plus the regenerated docs/.generated/config-baseline.sha256.

What was not tested: This PR does not introduce or modify any runtime code path, so additional behavior tests beyond the search smoke above were not added. The recursive walk itself (collectMemoryFilesFromDir) is already covered by upstream tests under packages/memory-host-sdk/.

Test plan

  • pnpm config:docs:gen regenerates baseline cleanly (no other drift)
  • Nested memory smoke search on installed 2026.5.20 returns the new nested file at score 0.812
  • On-branch runtime import shows FIELD_HELP['agents.defaults.memorySearch'], buildPromptSection(...) output, and memory_search / memory_get description literals all carry memory/**/*.md
  • CI: lint / type / config-baseline check

@openclaw-barnacle openclaw-barnacle Bot added docs Improvements or additions to documentation gateway Gateway runtime extensions: memory-core Extension: memory-core size: XS triage: needs-real-behavior-proof Candidate: external PR needs after-fix proof from a real setup. labels May 24, 2026
@leafbird leafbird mentioned this pull request May 24, 2026
Closed
@clawsweeper

clawsweeper Bot commented May 24, 2026 •
edited
Loading

Copy link
Copy Markdown
Contributor

Codex review: needs maintainer review before merge. Reviewed June 29, 2026, 7:24 AM ET / 11:24 UTC.

Summary
Updates memory-core tool descriptors, prompt guidance, config help, public memory docs, and generated config-baseline checksums from flat memory/*.md wording to recursive memory/**/*.md wording while preserving root-level startup daily-memory wording.

PR surface: Source 0, Docs 0, Generated 0. Total 0 across 10 files.

Reproducibility: yes. Source inspection of current main shows recursive memory collection through listMemoryFiles/collectMemoryFilesFromDir while the affected descriptors and docs still say memory/*.md.

Review metrics: 1 noteworthy metric.

  • Generated baseline refresh: 1 checksum file changed on stale base. Config docs checks need the checksum regenerated after the branch is refreshed against current main.

Stored data model
Persistent data-model change detected: unknown-data-model-change: extensions/memory-core/index.ts, unknown-data-model-change: extensions/memory-core/src/tools.ts, vector/embedding metadata: extensions/memory-core/index.ts, vector/embedding metadata: extensions/memory-core/src/prompt-section.ts, vector/embedding metadata: extensions/memory-core/src/tools.ts, vector/embedding metadata: src/config/schema.help.ts. Confirm migration or upgrade compatibility proof before merge.

Root-cause cluster
Relationship: canonical
Canonical: #85899
Summary: This PR is the narrow canonical item for the remaining recursive-memory wording alignment; older runtime and watcher work is closed, merged, or adjacent.

Members:

Proposal only: this assessment does not dispatch repair, suppress jobs, mutate sibling items, close, or merge anything.

Merge readiness
Overall: 🦐 gold shrimp
Proof: 🦞 diamond lobster
Patch quality: 🦐 gold shrimp
Result: needs maintainer review before merge.

Overall follows the weaker of proof and patch quality, so missing proof can cap an otherwise strong patch.

Rank-up moves:

  • Resolve the branch against current main while preserving Native Codex and root-level startup-context wording.
  • Regenerate docs/.generated/config-baseline.sha256 after the refresh.
  • Rerun narrow docs/config validation on the refreshed head.

Risk before merge

  • [P1] GitHub reports the PR head as CONFLICTING/DIRTY, so it cannot merge until the branch is refreshed against current main.
  • [P1] Conflict resolution needs to preserve newer main text for Native Codex token-use behavior, memory_search unavailable-warning wording, and the root-level startup daily-memory distinction while applying recursive search wording.
  • [P1] The generated config-baseline checksum change was made on an older base and needs regeneration after refresh before docs/config checks are meaningful.
  • [P1] Relevant CI is from May 24, 2026 on the old head/base and should rerun after conflict resolution.

Maintainer options:

  1. Refresh The Contributor Branch (recommended)
    Resolve the branch against current main, preserve the recursive-search versus root-level-startup wording split, regenerate the config baseline, and rerun the relevant docs/config checks.
  2. Pause For Maintainer Wording Review
    Keep the PR paused if maintainers want to manually inspect the wording split before allowing automerge to continue.

Next step before merge

  • [P2] The remaining action is maintainer refresh/review of a conflicting automerge-armed PR, not a new autonomous repair job.

Security
Cleared: The diff changes docs, descriptor/help strings, and generated config checksums only; it adds no dependency, workflow, credential, package, install, or executable runtime path.

Review details

Best possible solution:

Land a refreshed version of this wording-only change that preserves newer main docs/descriptors, keeps startup-context root-level wording, regenerates the config baseline, and reruns narrow docs/config checks.

Do we have a high-confidence way to reproduce the issue?

Yes. Source inspection of current main shows recursive memory collection through listMemoryFiles/collectMemoryFilesFromDir while the affected descriptors and docs still say memory/*.md.

Is this the best way to solve the issue?

Yes after refresh. A wording-only docs/descriptor update is the narrowest maintainable fix because runtime indexing already recurses; the branch just needs conflict resolution and regenerated baseline proof.

AGENTS.md: found and applied where relevant.

Codex review notes: model internal, reasoning high; reviewed against cfd8ba8fc81d.

Label changes

Label justifications:

  • P3: This is a low-risk docs and descriptor wording alignment with no runtime behavior change.
  • merge-risk: 🚨 other: The PR is currently conflicting, and an incorrect refresh could overwrite newer main wording or stale generated config metadata.
  • rating: 🦐 gold shrimp: Overall readiness is 🦐 gold shrimp; proof is 🦞 diamond lobster and patch quality is 🦐 gold shrimp.
  • status: 🚀 automerge armed: This PR is in ClawSweeper's automerge lane. Sufficient (terminal): The PR body includes terminal proof from an installed runtime showing nested memory search works and runtime-imported branch strings showing the updated wording.
  • proof: sufficient: Contributor real behavior proof is sufficient. The PR body includes terminal proof from an installed runtime showing nested memory search works and runtime-imported branch strings showing the updated wording.
Evidence reviewed

PR surface:

Source 0, Docs 0, Generated 0. Total 0 across 10 files.

View PR surface stats
Area Files Added Removed Net
Source 4 7 7 0
Tests 0 0 0 0
Docs 5 7 7 0
Config 0 0 0 0
Generated 1 2 2 0
Other 0 0 0 0
Total 10 16 16 0

What I checked:

Likely related people:

  • steipete: Recent history includes memory-core helper refactors, docs work, and this PR branch has a maintainer commit preserving the startup-context wording distinction. (role: recent memory-core and docs area contributor; confidence: high; commits: 02ae79f9b4ce, d0ce2d104443, 3d0050c306ac; files: extensions/memory-core/index.ts, extensions/memory-core/src/tools.ts, extensions/memory-core/src/prompt-section.ts)
  • vincentkoc: History shows memory docs/config-help work in this area, and a member comment opted this PR into the automerge lane. (role: recent docs/config contributor and automerge requester; confidence: medium; commits: c5baf63fa5e5, 3584a893e8ac, aa69b12d0086; files: docs/concepts/memory-builtin.md, docs/concepts/memory.md, src/config/schema.help.ts)
  • Tak Hoffman: Startup-context behavior and related docs history trace through recent commits by this contributor, and that root-level startup invariant is the main conflict-resolution concern. (role: adjacent startup-context contributor; confidence: medium; commits: 94340b959830, 4f00b769251d, 847739d82c60; files: src/auto-reply/reply/startup-context.ts, docs/concepts/system-prompt.md, docs/reference/token-use.md)
  • Mariano: The recursive memory listing path is tied to the root-memory unification work that changed packages/memory-host-sdk/src/host/internal.ts. (role: recursive memory host behavior contributor; confidence: medium; commits: 3d06d90e835e; files: packages/memory-host-sdk/src/host/internal.ts, packages/memory-host-sdk/src/host/internal.test.ts)
What the crustacean ranks mean
  • 🦀 challenger crab: rare, exceptional readiness with strong proof, clean implementation, and convincing validation.
  • 🦞 diamond lobster: very strong readiness with only minor maintainer review expected.
  • 🐚 platinum hermit: good normal PR, likely mergeable with ordinary maintainer review.
  • 🦐 gold shrimp: useful signal, but proof or patch confidence is still limited.
  • 🦪 silver shellfish: thin signal; proof, validation, or implementation needs work.
  • 🧂 unranked krab: not merge-ready because proof is missing/unusable or there are serious correctness or safety concerns.
  • 🌊 off-meta tidepool: rating does not apply to this item.

Shiny media proof means a screenshot, video, or linked artifact directly shows the changed behavior. Runtime, network, CSP, and security claims still need visible diagnostics.

How this review workflow works
  • ClawSweeper keeps one durable marker-backed review comment per issue or PR.
  • Re-runs edit this comment so the latest verdict, findings, and automation markers stay together instead of adding duplicate bot comments.
  • A fresh review can be triggered by eligible @clawsweeper re-review comments, exact-item GitHub events, scheduled/background review runs, or manual workflow dispatch.
  • PR/issue authors and users with repository write access can comment @clawsweeper re-review or @clawsweeper re-run on an open PR or issue to request a fresh review only.
  • Maintainers can also comment @clawsweeper review to request a fresh review only.
  • Fresh-review commands do not start repair, autofix, rebase, CI repair, or automerge.
  • Maintainer-only repair and merge flows require explicit commands such as @clawsweeper autofix, @clawsweeper automerge, @clawsweeper fix ci, or @clawsweeper address review.
  • Maintainers can comment @clawsweeper explain to ask for more context, or @clawsweeper stop to stop active automation.
Review history (1 earlier review cycle)
  • reviewed 2026-06-24T20:37:16.762Z sha 02ae79f :: needs maintainer review before merge. :: none

@clawsweeper clawsweeper Bot added rating: 🧂 unranked krab Not merge-ready due to missing proof or serious correctness/safety concerns. status: 📣 needs proof The PR needs real behavior proof before ClawSweeper can clear the contributor ask. P3 Low-priority cleanup, docs, polish, ergonomics, or speculative work. labels May 24, 2026
@leafbird
leafbird force-pushed the docs/memory-recursive-wording branch from 4d4e734 to 30f15f4 Compare May 24, 2026 02:34
@clawsweeper

clawsweeper Bot commented May 24, 2026 •
edited
Loading

Copy link
Copy Markdown
Contributor

ClawSweeper PR egg

✨ Hatched: 💎 rare Brave Clawlet

Hatch command

Comment @clawsweeper hatch when this PR is hatchable.

Hatchability rules:

  • Merged PRs are hatchable.
  • Open PRs are hatchable when they are status: 👀 ready for maintainer look, status: 🚀 automerge armed, or labeled clawsweeper:automerge.
  • Closed unmerged PRs are hatchable only when one of those hatchable labels is still present in the durable record.

Rarity: 💎 rare.
Trait: hums during re-review.
Image traits: location merge queue dock; accessory commit compass; palette sunrise gold and clean white; mood calm; pose guarding a tiny green check; shell translucent glimmer shell; lighting gentle morning glow; background tiny shells and proof notes.
Share on X: post this hatch
Copy: My PR egg hatched a 💎 rare Brave Clawlet in ClawSweeper.

What is this egg doing here?
  • Eggs appear after the PR passes real-behavior proof. It is here for vibes, not verdicts: it does not change labels, ratings, merge decisions, or automation.
  • The shell reacts to review momentum: open follow-up work warms it up, re-review makes it wobble, and a clean final review lets it hatch.
  • Hatchability usually comes from sufficient real-behavior proof, no blocking P0/P1/P2 findings, no security attention needed, and clean correctness. A merged PR is already final, so merge makes the egg hatchable independently.
  • The hatch is seeded from this repository and PR number, so the same PR keeps the same creature; the reviewed head SHA can only change safe visual details.
  • Rarity is just collectible sparkle: 🥚 common, 🌱 uncommon, 💎 rare, ✨ glimmer, and 🌈 legendary.

@openclaw-barnacle openclaw-barnacle Bot added proof: supplied External PR includes structured after-fix real behavior proof. and removed triage: needs-real-behavior-proof Candidate: external PR needs after-fix proof from a real setup. labels May 24, 2026
@leafbird

leafbird commented May 24, 2026

Copy link
Copy Markdown
Author

@clawsweeper re-review

@clawsweeper

clawsweeper Bot commented May 24, 2026 •
edited
Loading

Copy link
Copy Markdown
Contributor

🦞🧹
ClawSweeper re-review requested.

I asked ClawSweeper to review this item again.
Action: item re-review queued (workflow sweep.yml, event repository_dispatch).
Result: the existing ClawSweeper review comment will be edited in place when the review finishes.

Re-review progress:

@clawsweeper clawsweeper Bot added rating: 🦪 silver shellfish Thin PR readiness signal; proof, validation, or implementation needs work. and removed rating: 🧂 unranked krab Not merge-ready due to missing proof or serious correctness/safety concerns. labels May 24, 2026
@leafbird

leafbird commented May 24, 2026

Copy link
Copy Markdown
Author

@clawsweeper re-review

@clawsweeper

clawsweeper Bot commented May 24, 2026 •
edited
Loading

Copy link
Copy Markdown
Contributor

🦞👀
ClawSweeper picked this up.

Command router queued. I will update this comment with the next step.

Re-review progress:

@openclaw-barnacle openclaw-barnacle Bot added triage: needs-real-behavior-proof Candidate: external PR needs after-fix proof from a real setup. and removed proof: supplied External PR includes structured after-fix real behavior proof. labels May 24, 2026
@leafbird

leafbird commented May 24, 2026

Copy link
Copy Markdown
Author

@clawsweeper re-review

@openclaw-barnacle openclaw-barnacle Bot added proof: supplied External PR includes structured after-fix real behavior proof. and removed triage: needs-real-behavior-proof Candidate: external PR needs after-fix proof from a real setup. labels May 24, 2026
@clawsweeper clawsweeper Bot added proof: sufficient ClawSweeper judged the real behavior proof convincing. rating: 🦞 diamond lobster Very strong PR readiness with only minor maintainer review expected. status: 👀 ready for maintainer look ClawSweeper has no concrete contributor-facing blocker left for this PR. and removed rating: 🦪 silver shellfish Thin PR readiness signal; proof, validation, or implementation needs work. status: 📣 needs proof The PR needs real behavior proof before ClawSweeper can clear the contributor ask. labels May 24, 2026
@clawsweeper clawsweeper Bot added status: 👀 ready for maintainer look ClawSweeper has no concrete contributor-facing blocker left for this PR. and removed status: ⏳ waiting on author ClawSweeper has contributor-facing work open and is waiting for author action. labels May 24, 2026
@clawsweeper

clawsweeper Bot commented May 24, 2026 •
edited
Loading

Copy link
Copy Markdown
Contributor

🦞🧹
ClawSweeper re-review requested.

I asked ClawSweeper to review this item again.
Action: item re-review queued (workflow sweep.yml, event repository_dispatch).
Result: the existing ClawSweeper review comment will be edited in place when the review finishes.

@lukeboyett lukeboyett mentioned this pull request May 26, 2026
Merged
18 tasks
@mushuiyu886 mushuiyu886 mentioned this pull request Jun 13, 2026
Merged
@clawsweeper clawsweeper Bot added rating: 🐚 platinum hermit Good normal PR readiness with ordinary maintainer review expected. and removed rating: 🦞 diamond lobster Very strong PR readiness with only minor maintainer review expected. labels Jun 15, 2026
@clawsweeper clawsweeper Bot mentioned this pull request Jun 16, 2026
Open
@vincentkoc

vincentkoc commented Jun 19, 2026

Copy link
Copy Markdown
Member

/clownfish automerge

@openclaw-clownfish openclaw-clownfish Bot added clownfish:automerge Maintainer opted this Clownfish PR into bounded ClawSweeper-reviewed automerge clawsweeper:automerge Maintainer opted this PR into bounded ClawSweeper-reviewed automerge labels Jun 19, 2026
@openclaw-clownfish

openclaw-clownfish Bot commented Jun 19, 2026

Copy link
Copy Markdown
Contributor

Clownfish is on the reef for this PR. 🐠

I tagged clownfish:automerge and sent ClawSweeper over this exact head. If the sweep finds rough coral, failing checks, or needs-human, I will take another bounded repair lap and ask for a fresh review.

A maintainer can call /clownfish stop any time and I will drift this back to human review.

@clawsweeper clawsweeper Bot added rating: 🦐 gold shrimp Decent PR readiness signal, but merge confidence is limited. status: 🚀 automerge armed This PR is in ClawSweeper's automerge lane. clawsweeper:human-review Needs maintainer review before ClawSweeper can continue and removed rating: 🐚 platinum hermit Good normal PR readiness with ordinary maintainer review expected. status: 👀 ready for maintainer look ClawSweeper has no concrete contributor-facing blocker left for this PR. labels Jun 19, 2026
@clawsweeper

clawsweeper Bot commented Jun 19, 2026 •
edited
Loading

Copy link
Copy Markdown
Contributor

🦞✅
ClawSweeper is pausing this repair loop for human review.

Source: clawsweeper[bot]
Reason: - [P2] The remaining action is maintainer refresh/review of a conflicting automerge-armed PR, not a new autonomous repair job.; Cleared: The diff changes docs, descriptor/help strings, and generated config checksums only; it adds no dependency, workflow, credential, package, install, or executable runtime path. (sha=02ae79f9b4ceaa898ecc8794a580d8b6c22cdf1c)

Why human review is needed:
This item has security-sensitive risk. ClawSweeper is pausing instead of making an autonomous change that could affect trust, credentials, permissions, or exposure.

What the maintainer can do as a next step:
If the maintainer accepts the current risk and wants ClawSweeper to continue merge gates, comment @clawsweeper approve. If the security-sensitive detail still needs changes, describe the safe path or push the fix, then comment @clawsweeper automerge. If the risk should not be automated, keep the PR paused for manual review or comment @clawsweeper stop.

I added clawsweeper:human-review and left the final call with a maintainer.

@clawsweeper clawsweeper Bot added rating: 🐚 platinum hermit Good normal PR readiness with ordinary maintainer review expected. and removed rating: 🦐 gold shrimp Decent PR readiness signal, but merge confidence is limited. labels Jun 19, 2026
@openclaw-clownfish

openclaw-clownfish Bot commented Jun 19, 2026

Copy link
Copy Markdown
Contributor

Thanks, ClawSweeper. Clownfish picked up the reef notes and is starting a guarded repair pass. 🐠

Source: clawsweeper[bot]
Feedback: ClawSweeper review comment asks to keep repairing this PR
Action: dispatched cluster-worker.yml for jobs/openclaw/inbox/automerge-openclaw-openclaw-85899.md in autonomous mode.
Model: gpt-5.5

I will update this PR branch when I can. If GitHub branch permissions block that swim lane, I will open a safe credited replacement instead and keep it narrow.

@clawsweeper clawsweeper Bot added the merge-risk: 🚨 other 🚨 Merging this PR has meaningful risk outside the owned taxonomy. label Jun 19, 2026
@vincentkoc

vincentkoc commented Jun 20, 2026

Copy link
Copy Markdown
Member

Clownfish 🐠 reef automerge status

Clownfish took another look: no safe branch change to make on this pass.

Target: #85899
Executor outcome: fix artifact is too broad for autonomous execution; split into narrower jobs or explicitly set CLOWNFISH_ALLOW_BROAD_FIX_ARTIFACTS=1.
Worker summary: Canonical PR #85899 is the maintainer-opted automerge candidate. It is useful, narrow, non-security, and maintainer-editable, but it is not merge-ready because the hydrated PR state is dirty against main. Plan a repair of the contributor branch, then rerun review and changed checks. No close or merge actions are planned because the job blocks both.

Worker actions:

  • fix_needed on #85899: planned - Repair the canonical contributor PR branch because it is the narrow opted-in fix path and only needs rebase/review validation before the applicator can consider final merge routing.
  • build_fix_artifact on cluster:automerge-openclaw-openclaw-85899: planned - Automerge job allows fix and raise_pr, blocks merge/close, and requires a contributor-branch repair artifact when the useful canonical PR is stale or dirty.
  • keep_related on #60048: planned - Same memory docs area, different deliverable and unresolved review findings; keep open outside this cluster.
  • keep_closed on #72748: skipped - Closed historical context only.
  • keep_closed on #81802: skipped - Closed merged runtime fix, independent of this docs repair cluster.
  • keep_closed on #86701: skipped - Closed merged runtime fix, independent of this docs repair cluster.

Clownfish left the PR as-is: no push, no rebase, no replacement PR, no merge, and no fresh ClawSweeper pass.

fish notes: model gpt-5.5, reasoning medium.

@clawsweeper clawsweeper Bot added rating: 🦐 gold shrimp Decent PR readiness signal, but merge confidence is limited. rating: 🐚 platinum hermit Good normal PR readiness with ordinary maintainer review expected. and removed rating: 🐚 platinum hermit Good normal PR readiness with ordinary maintainer review expected. rating: 🦐 gold shrimp Decent PR readiness signal, but merge confidence is limited. labels Jun 21, 2026
@leafbird leafbird closed this Jul 20, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

clawsweeper:automerge Maintainer opted this PR into bounded ClawSweeper-reviewed automerge clawsweeper:human-review Needs maintainer review before ClawSweeper can continue clownfish:automerge Maintainer opted this Clownfish PR into bounded ClawSweeper-reviewed automerge docs Improvements or additions to documentation extensions: memory-core Extension: memory-core gateway Gateway runtime merge-risk: 🚨 other 🚨 Merging this PR has meaningful risk outside the owned taxonomy. P3 Low-priority cleanup, docs, polish, ergonomics, or speculative work. proof: sufficient ClawSweeper judged the real behavior proof convincing. proof: supplied External PR includes structured after-fix real behavior proof. rating: 🦐 gold shrimp Decent PR readiness signal, but merge confidence is limited. size: XS status: 🚀 automerge armed This PR is in ClawSweeper's automerge lane.

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

3 participants

@leafbird @vincentkoc @steipete