fix(qqbot): derive outbound watchdog from configured timeouts (#85267) by clawsweeper[bot] · Pull Request #86500 · openclaw/openclaw

clawsweeper · 2026-05-25T13:31:54Z

Makes #85271 merge-ready for the ClawSweeper automerge loop.
The edit pass should inspect the live PR diff, review comments, and failing checks; rebase if needed; keep the contributor branch credited; and stop only when validation is green or an external blocker is proven.

ClawSweeper 🐠 replacement reef notes:

Cluster: automerge-openclaw-openclaw-85271
Source PRs: fix(qqbot): derive outbound watchdog from configured timeouts (#85267) #85271
Credit: Source PR: fix(qqbot): derive outbound watchdog from configured timeouts (#85267) #85271
Validation: pnpm check:changed
Replacement reason: ClawSweeper could not update the source PR branch directly, so it opened a writable replacement PR instead.
Automerge requested by: @osolmaz

Repair fallback: GitHub rejected the repair branch push because it updates workflow files and the ClawSweeper app token does not have workflows permission

Inherited issue-closing references from the source PR:
Fixes #85267

Co-author credit kept:

@SymbolStar: Co-authored-by: SymbolStar 24540119+SymbolStar@users.noreply.github.com

fish notes: model gpt-5.5, reasoning high; reviewed against d8e0937.

clawsweeper · 2026-05-25T13:33:46Z

Codex review: passed. Reviewed May 25, 2026, 10:48 AM ET / 14:48 UTC.

Summary
The branch replaces QQBot's hardcoded outbound response watchdog with a resolver based on existing agent/provider timeoutSeconds settings, adds regression tests, and updates the changelog.

PR surface: Source +113, Tests +116, Docs +1. Total +230 across 5 files.

Reproducibility: yes. at source level: current main and the latest release use a hardcoded 300000 ms QQBot outbound watchdog while the linked report configures an 1800s provider timeout. I did not run the reporter's live QQBot/Ollama setup in this read-only review.

Review metrics: 1 noteworthy metric.

Timeout Config Inputs Reused: 2 existing inputs honored, 0 new keys added. QQBot outbound waiting now depends on existing agent and provider timeout config, which is compatibility-relevant even without adding a new setting.

Merge readiness
Overall: 🐚 platinum hermit
Proof: 🐚 platinum hermit
Patch quality: 🦞 diamond lobster
Result: ready for maintainer review.

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

Rank-up moves:

Maintainers should accept the max-across-configured-providers behavior or ask for active-provider narrowing before merge.

Risk before merge

Existing QQBot deployments with long agents.defaults.timeoutSeconds or provider timeoutSeconds values will now wait past the historical five-minute channel watchdog before surfacing a no-response timeout.
The resolver uses the maximum timeout across configured providers, so a long timeout on a configured but inactive provider can lengthen QQBot outbound waits.
The strongest live proof uses loopback QQ Gateway/REST stubs and a controlled Ollama-compatible provider rather than real Tencent QQ credentials or the reporter's exact model.

Maintainer options:

Accept Config-Derived Waits (recommended)
Land once maintainers accept that existing long agent/provider timeout config can extend QQBot waits, including the max-across-configured-providers behavior.
Narrow To Active Provider
Before merge, change the resolver or call site so QQBot uses the active routed provider/model timeout instead of the maximum across all configured providers.

Next step before merge
No repair lane is needed; the exact head has no blocking findings and the remaining action is maintainer/automerge acceptance of the compatibility-visible timeout semantics.

Security
Cleared: No concrete security or supply-chain concern found; the diff changes QQBot timeout logic, tests, and changelog only.

Review details

Best possible solution:

Land this resolver-based fix if maintainers accept longer configured QQBot waits; otherwise narrow the timeout source to the active routed provider before merge.

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

Yes, at source level: current main and the latest release use a hardcoded 300000 ms QQBot outbound watchdog while the linked report configures an 1800s provider timeout. I did not run the reporter's live QQBot/Ollama setup in this read-only review.

Is this the best way to solve the issue?

Yes, the PR reuses existing agent/provider timeout settings and preserves the historical five-minute floor instead of adding a QQBot-only knob. The main maintainer choice is whether max-across-configured-providers is the desired bound.

AGENTS.md: found and applied where relevant.

Codex review notes: model gpt-5.5, reasoning high; reviewed against 277d8fece2e3.

Label changes

Label justifications:

P1: This fixes a reported QQBot regression that can cut off slow local Ollama replies despite an explicit longer provider timeout.
merge-risk: 🚨 compatibility: Merging changes QQBot timeout behavior for existing configs that already set long agent or provider timeout values.
rating: 🐚 platinum hermit: Overall readiness is 🐚 platinum hermit; proof is 🐚 platinum hermit and patch quality is 🦞 diamond lobster.
status: 🚀 automerge armed: This PR is in ClawSweeper's automerge lane. Sufficient (logs): The replacement inherits source PR proof with after-fix logs showing the QQBot gateway/runtime path resolving an 1800000 ms watchdog and delivering through a controlled slow-provider setup.
proof: sufficient: Contributor real behavior proof is sufficient. The replacement inherits source PR proof with after-fix logs showing the QQBot gateway/runtime path resolving an 1800000 ms watchdog and delivering through a controlled slow-provider setup.

Evidence reviewed

PR surface:

Source +113, Tests +116, Docs +1. Total +230 across 5 files.

View PR surface stats

Area	Files	Added	Removed	Net
Source	2	115	2	+113
Tests	2	116	0	+116
Docs	1	1	0	+1
Config	0	0	0	0
Generated	0	0	0	0
Other	0	0	0	0
Total	5	232	2	+230

What I checked:

Repository policy read: Read the full root AGENTS.md and scoped extensions policy; the review applied plugin-boundary, compatibility-risk, proof, changelog, and PR-review guidance. (AGENTS.md:1, 277d8fece2e3)
Current main still has the bug: origin/main keeps RESPONSE_TIMEOUT = 300_000 and races outbound dispatch against that fixed timeout, so the requested fix is not already implemented on main. (extensions/qqbot/src/engine/gateway/outbound-dispatch.ts:45, 277d8fece2e3)
Latest release still has the bug: The latest release tag v2026.5.22 also has the hardcoded 300000 ms QQBot response timeout, so this has not shipped yet. (extensions/qqbot/src/engine/gateway/outbound-dispatch.ts:45, a374c3a5bfd5)
PR wires dispatcher to derived timeout: The PR computes responseTimeoutMs = resolveResponseTimeoutMs(cfg) and uses it for the outbound timeout race instead of the fixed constant. (extensions/qqbot/src/engine/gateway/outbound-dispatch.ts:161, 7bd829292af0)
Resolver reuses existing config: The new resolver starts from the historical 5-minute floor, reads agents.defaults.timeoutSeconds and configured provider timeoutSeconds values, and clamps to the safe setTimeout ceiling. (extensions/qqbot/src/engine/gateway/response-timeout.ts:81, 7bd829292af0)
Regression coverage added: The dispatch-level test configures models.providers.ollama.timeoutSeconds: 1800, advances to 300 seconds without settlement, then verifies the late block reply is delivered after 301 seconds. (extensions/qqbot/src/engine/gateway/outbound-dispatch.test.ts:174, 7bd829292af0)

Likely related people:

cxyhhhhh: GitHub path history shows major QQBot gateway/outbound-dispatch architecture work in the affected file. (role: QQBot feature owner; confidence: high; commits: 5ccf179a34a9, 62fb87641eca; files: extensions/qqbot/src/engine/gateway/outbound-dispatch.ts)
steipete: Recent path history shows QQBot gateway/runtime refactors and adjacent channel-turn changes on the affected dispatcher surface. (role: recent area contributor; confidence: high; commits: 694ca50e9775, ffe67e9cdc9e, 9a9cd0c0abdf; files: extensions/qqbot/src/engine/gateway/outbound-dispatch.ts, src/agents/pi-embedded-runner/run/llm-idle-timeout.ts)
yujiawei: Authored the provider-timeout change that made models.providers.<id>.timeoutSeconds the relevant idle-timeout ceiling this PR reuses. (role: adjacent timeout contract author; confidence: high; commits: 9e9feb52f43c; files: src/agents/pi-embedded-runner/run/llm-idle-timeout.ts)
shakkernerd: Committed the provider-timeout contract update and has recent QQBot outbound test work in the affected test surface. (role: adjacent merger and test contributor; confidence: medium; commits: 9e9feb52f43c, 5a9e8a29e52e, 4702d2bff595; files: src/agents/pi-embedded-runner/run/llm-idle-timeout.ts, extensions/qqbot/src/engine/gateway/outbound-dispatch.test.ts)
osolmaz: The linked issue discussion records this user taking the issue, and the replacement PR body records their automerge request for this fix path. (role: follow-up owner; confidence: medium; commits: 858c205834bf; files: extensions/qqbot/src/engine/gateway/outbound-dispatch.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.

clawsweeper · 2026-05-25T13:47:47Z

ClawSweeper PR egg

✨ Hatched: 🥚 common Clockwork Lint Imp

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: 🥚 common.
Trait: finds missing screenshots.
Image traits: location review cove; accessory proof snapshot camera; palette cobalt, lime, and pearl; mood determined; pose leaning over a miniature review desk; shell woven fiber shell; lighting moonlit rim light; background tiny artifact crates.
Share on X: post this hatch
Copy: My PR egg hatched a 🥚 common Clockwork Lint Imp 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.

clawsweeper · 2026-05-25T13:48:04Z

🦞✅
ClawSweeper merged this PR after the passing review.

Source: clawsweeper[bot]
Feedback: structured ClawSweeper verdict: pass (sha=7bd829292af0f9cd48fb0f48a379ecc27a11a97c)
Merge status: merged by ClawSweeper automerge
Merged at: 2026-05-25T14:52:43Z
Merge commit: aa702cf3dbe7

What merged:

The branch replaces QQBot's hardcoded outbound response watchdog with a resolver based on existing agent/provider timeoutSeconds settings, adds regression tests, and updates the changelog.
PR surface: Source +113, Tests +116, Docs +1. Total +230 across 5 files.
Reproducibility: yes. at source level: current main and the latest release use a hardcoded 300000 ms QQBot o ... s an 1800s provider timeout. I did not run the reporter's live QQBot/Ollama setup in this read-only review.

Automerge notes:

PR branch already contained follow-up commit before automerge: test(qqbot): cover slow provider response watchdog
PR branch already contained follow-up commit before automerge: fix(qqbot): derive outbound watchdog from configured timeouts ([Bug]: report LLM request timed out in openclaw + ollama + qwen3.5:27b. But it's ok ollama + qwen3.5:27b. #85267)
PR branch already contained follow-up commit before automerge: fix(clawsweeper): address review for automerge-openclaw-openclaw-8527…

The automerge loop is complete.

Automerge progress:

2026-05-25 13:47:45 UTC review passed d8e093755dce (structured ClawSweeper verdict: pass (sha=d8e093755dcee6541099f8bd4ceb247753abd...)

2026-05-25 13:48:03 UTC repair queued d8e093755dce (autonomous) Run: https://github.com/openclaw/clawsweeper/actions/runs/26403783890

2026-05-25 13:50:43 UTC repair started (running) in 1s Run: https://github.com/openclaw/clawsweeper/actions/runs/26403783890 automerge-openclaw-openclaw-85271

2026-05-25 13:50:59 UTC validation plan (passed) in 17s Run: https://github.com/openclaw/clawsweeper/actions/runs/26403783890 node scripts/run-vitest.mjs extensions/qqbot/src/engine/gateway/outbound-dispatch.test.ts extensions/qqbot/src/engine/gateway/response-timeout.test.ts src/agen...

2026-05-25 13:51:13 UTC Codex write preflight (passed) in 30s Run: https://github.com/openclaw/clawsweeper/actions/runs/26403783890 danger-full-access

2026-05-25 13:56:09 UTC Codex edit 1 83546753479e (complete) in 5m 26s Run: https://github.com/openclaw/clawsweeper/actions/runs/26403783890 exit 0

2026-05-25 13:53:49 UTC review queued d8e093755dce (queued)

2026-05-25 14:27:49 UTC validation and review 1 7bd829292af0 (base moved) in 37m 7s Run: https://github.com/openclaw/clawsweeper/actions/runs/26403783890 codex-reconciled

2026-05-25 14:24:28 UTC review passed 18d72093daa7 (structured ClawSweeper verdict: pass (sha=18d72093daa70a7cec5d17d51ef8f3a1869b0...)

2026-05-25 14:28:23 UTC repair finished 7bd829292af0 (opened) in 37m 40s Run: https://github.com/openclaw/clawsweeper/actions/runs/26403783890 open_fix_pr

2026-05-25 14:52:29 UTC review passed 7bd829292af0 (structured ClawSweeper verdict: pass (sha=7bd829292af0f9cd48fb0f48a379ecc27a11a...)

2026-05-25 14:37:44 UTC repair queued 7bd829292af0 (autonomous) Run: https://github.com/openclaw/clawsweeper/actions/runs/26405908803

2026-05-25 14:40:44 UTC repair started (running) in 0s Run: https://github.com/openclaw/clawsweeper/actions/runs/26405908803 automerge-openclaw-openclaw-85271

2026-05-25 14:40:47 UTC repair completed 7bd829292af0 (no branch change) in 4s Run: https://github.com/openclaw/clawsweeper/actions/runs/26405908803 no planned fix actions

2026-05-25 14:40:47 UTC review queued 7bd829292af0 (after no-op repair)

2026-05-25 14:52:45 UTC merged 7bd829292af0 (merged by ClawSweeper automerge)

The QQBot outbound dispatcher held an independent hardcoded 300_000ms response watchdog. When users ran a slow local provider (e.g. ollama + qwen3.5:27b) with models.providers.ollama.timeoutSeconds: 1800, the embedded-runner idle-timeout honored the longer ceiling but the QQBot watchdog still aborted at 5 minutes with 'LLM request timed out', even though a direct ollama call to the same model succeeded. Replace the hardcoded constant with resolveResponseTimeoutMs(cfg) that takes the maximum of: - the historical 5-minute floor (preserves prior behavior when nothing is configured) - agents.defaults.timeoutSeconds - models.providers.<id>.timeoutSeconds across configured providers Bounded by MAX_SAFE_TIMEOUT_MS so the value is always a safe setTimeout argument. No new QQBot-only knob; reuses existing configured ceilings.

…1 (2) Co-authored-by: SymbolStar <24540119+SymbolStar@users.noreply.github.com> Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>

…aw#85267) (openclaw#86500) Summary: - The branch replaces QQBot's hardcoded outbound response watchdog with a resolver based on existing agent/provider `timeoutSeconds` settings, adds regression tests, and updates the changelog. - PR surface: Source +113, Tests +116, Docs +1. Total +230 across 5 files. - Reproducibility: yes. at source level: current main and the latest release use a hardcoded 300000 ms QQBot o ... s an 1800s provider timeout. I did not run the reporter's live QQBot/Ollama setup in this read-only review. Automerge notes: - PR branch already contained follow-up commit before automerge: test(qqbot): cover slow provider response watchdog - PR branch already contained follow-up commit before automerge: fix(qqbot): derive outbound watchdog from configured timeouts (openclaw#85267) - PR branch already contained follow-up commit before automerge: fix(clawsweeper): address review for automerge-openclaw-openclaw-8527… Validation: - ClawSweeper review passed for head 7bd8292. - Required merge gates passed before the squash merge. Prepared head SHA: 7bd8292 Review: openclaw#86500 (comment) Co-authored-by: SymbolStar <symbolstar@users.noreply.github.com> Co-authored-by: Onur Solmaz <2453968+osolmaz@users.noreply.github.com> Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com> Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com> Approved-by: osolmaz Co-authored-by: osolmaz <2453968+osolmaz@users.noreply.github.com>

clawsweeper Bot mentioned this pull request May 25, 2026

fix(qqbot): derive outbound watchdog from configured timeouts (#85267) #85271

Closed

openclaw-barnacle Bot removed the proof: supplied External PR includes structured after-fix real behavior proof. label May 25, 2026

clawsweeper Bot force-pushed the clawsweeper/automerge-openclaw-openclaw-85271 branch from d8e0937 to 18d7209 Compare May 25, 2026 14:13

SymbolStar and others added 4 commits May 25, 2026 14:25

test(qqbot): cover slow provider response watchdog

858c205

fix(qqbot): derive outbound watchdog from configured timeouts (#85267)

d23020a

fix(clawsweeper): address review for automerge-openclaw-openclaw-8527…

7bd8292

…1 (2) Co-authored-by: SymbolStar <24540119+SymbolStar@users.noreply.github.com> Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>

clawsweeper Bot force-pushed the clawsweeper/automerge-openclaw-openclaw-85271 branch from 18d7209 to 7bd8292 Compare May 25, 2026 14:27

openclaw-barnacle Bot removed the proof: supplied External PR includes structured after-fix real behavior proof. label May 25, 2026

clawsweeper Bot removed the rating: 🦞 diamond lobster Very strong PR readiness with only minor maintainer review expected. label May 25, 2026

clawsweeper Bot removed the status: 👀 ready for maintainer look ClawSweeper has no concrete contributor-facing blocker left for this PR. label May 25, 2026

clawsweeper Bot merged commit aa702cf into main May 25, 2026
121 of 129 checks passed

clawsweeper Bot deleted the clawsweeper/automerge-openclaw-openclaw-85271 branch May 25, 2026 14:52

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

fix(qqbot): derive outbound watchdog from configured timeouts (#85267)#86500

fix(qqbot): derive outbound watchdog from configured timeouts (#85267)#86500
clawsweeper[bot] merged 4 commits into
mainfrom
clawsweeper/automerge-openclaw-openclaw-85271

clawsweeper Bot commented May 25, 2026

Uh oh!

clawsweeper Bot commented May 25, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented May 25, 2026

Uh oh!

clawsweeper Bot commented May 25, 2026 •

edited

Loading

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Uh oh!

Conversation

clawsweeper Bot commented May 25, 2026

Uh oh!

clawsweeper Bot commented May 25, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

clawsweeper Bot commented May 25, 2026

Hatch command

Uh oh!

clawsweeper Bot commented May 25, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

clawsweeper Bot commented May 25, 2026 •

edited

Loading

clawsweeper Bot commented May 25, 2026 •

edited

Loading