fix(qqbot): sanitize outbound text to strip reasoning/thinking content by openperf · Pull Request #90132 · openclaw/openclaw

openperf · 2026-06-04T02:50:03Z

Summary

Problem: After upgrading to OpenClaw 2026.5.28, QQBot users see raw model reasoning/thinking text (e.g. <thinking>…</thinking> blocks) in QQBot replies when using MiniMax-M3 with explicit thinking enabled via the anthropic-messages API.
Root Cause: extensions/qqbot/src/channel.ts outbound descriptor has no sanitizeText hook. The shared delivery layer (src/infra/outbound/deliver.ts:791) only invokes the reasoning/scaffolding sanitizer when the channel provides one. Without it, any reasoning content that surfaces as tagged text in the reply passes through raw to senderSendText. The MiniMax thinking-disabled wrapper (stream-wrappers/minimax.ts:67) skips its override when thinking is already explicitly set by the user — so MiniMax can still emit reasoning content when thinking is explicitly configured.
Fix: Wire sanitizeAssistantVisibleText (the canonical "delivery"-profile sanitizer) as QQBot's sanitizeText hook. This strips <thinking>, <think>, <thought>, <antthinking> tags, tool-call scaffolding, and internal trace lines before native platform send — the same pattern already used by Discord, iMessage, SMS, WhatsApp, IRC, and GoogleChat.
What changed: extensions/qqbot/src/channel.ts — one import from openclaw/plugin-sdk/text-chunking and one sanitizeText field in the outbound descriptor. extensions/qqbot/src/channel.message-adapter.test.ts — regression test verifying <thinking> and <think> tag stripping end-to-end through the hook.
What did NOT change (scope boundary): No config surface (no schema, defaults, doctor migrations, or docs/reference/config). No plugin surface (no plugin SDK, manifest, extensions/* api/runtime-api, registry/loader). Delivery mode, chunking, textChunkLimit, and all other outbound fields are unchanged.

Reproduction

Configure MiniMax-M3 (minimax/MiniMax-M3) via anthropic-messages API with explicit thinking enabled.
Send a message via QQBot DM or group.
Observe the reply in the QQBot client.
Before this PR: Reply contains raw <thinking>…</thinking> reasoning content alongside the final answer — internal model narration is visible to users.
After this PR: Only the final answer text is delivered; sanitizeAssistantVisibleText strips the reasoning block before platform send.

Real behavior proof

Behavior addressed (#89913): QQBot users receiving raw <thinking> reasoning/thinking content in channel replies after upgrading to 2026.5.28, regression of prior reasoning-stripping behavior (#6470).

Real environment tested (Linux, Node 22, Vitest against production delivery-layer and sanitizer functions): extensions/qqbot/src/channel.ts outbound descriptor verified at channel.ts:252 — no sanitizeText field pre-patch. src/infra/outbound/deliver.ts:791 confirmed: sanitizer is only invoked when handler.sanitizeText is set. src/plugin-sdk/text-chunking.ts exports sanitizeAssistantVisibleText from src/shared/text/assistant-visible-text.ts "delivery" profile, which calls stripReasoningTagsFromText with reasoningMode: "strict". Sibling channel pattern confirmed in extensions/discord/src/outbound-adapter.ts:114, extensions/imessage/src/channel.ts:333, extensions/sms/src/channel.ts:326.

Exact steps or command run after this patch: node scripts/run-vitest.mjs extensions/qqbot/src/channel.message-adapter.test.ts; node scripts/run-oxlint.mjs extensions/qqbot/src/channel.ts extensions/qqbot/src/channel.message-adapter.test.ts; pnpm format:check.

Evidence after fix:

 Test Files  1 passed (1)
      Tests  2 passed (2)

New strips reasoning/thinking tags before delivery test covers <thinking> and <think> stripping end-to-end through the outbound sanitizeText hook.

Observed result after fix: sanitizeText({ text: "<thinking>internal reasoning</thinking>final answer", payload: { text: ... } }) returns "final answer"; plain text without tags passes through unchanged.

What was not tested: Live QQBot + MiniMax-M3 end-to-end delivery on a real Tencent QQBot account (no test credentials available in this read-only source review). The delivery hook, sanitizer pipeline, and reasoning-tag stripping are covered deterministically against the production functions.

Repro confirmation: The regression test fails before the patch (expect(sanitize).toBeDefined() fails because no sanitizeText field exists) and passes with the patch, confirming the production change is what makes the test pass.

Risk / Mitigation

Risk: Sanitizer could accidentally strip non-reasoning content. Mitigation: sanitizeAssistantVisibleText "delivery" profile uses reasoningMode: "strict" — only strips content strictly enclosed in <thinking>, <think>, <thought>, <antthinking> tags; normal prose passes through unchanged.
Risk: QQBot-specific content formatting could be altered. Mitigation: The sanitizer does not convert HTML or reformat markdown; it strips only model reasoning tags and internal scaffolding — QQBot's native markdown rendering is preserved.

Change Type (select all)

Bug fix

Scope (select all touched areas)

extensions/qqbot

Linked Issue/PR

Fixes #89913

clawsweeper · 2026-06-04T02:51:30Z

Codex review: passed. Reviewed June 5, 2026, 2:56 AM ET / 06:56 UTC.

Summary
Adds QQBot outbound sanitizeText wired to sanitizeAssistantVisibleText plus a regression test for stripping <thinking> and <think> blocks.

PR surface: Source +2, Tests +19. Total +21 across 2 files.

Reproducibility: yes. source-reproducible: current main QQBot outbound lacks sanitizeText, and shared delivery only invokes channel text sanitization when that hook exists. I did not run a live Tencent QQBot plus MiniMax reproduction.

Review metrics: none identified.

Merge readiness
Overall: 🦞 diamond lobster
Proof: 🌊 off-meta tidepool
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.

Risk before merge

[P1] Live Tencent QQBot plus MiniMax-M3 delivery was not exercised here; confidence comes from source tracing and deterministic production-function test proof.

Maintainer options:

Decide the mitigation before merge
Land the bounded QQBot-owned sanitizer hook if exact-head checks stay green; keep any broader default-sanitizer policy discussion separate from this channel regression fix.
Pause or close
Do not merge this PR until maintainers decide whether the risk is worth taking.

Next step before merge

[P2] No repair job is needed; this automerge-opted PR has no actionable review findings, so exact-head checks and maintainer merge policy should decide landing.

Security
Cleared: The diff adds no dependency, workflow, credential, or supply-chain surface and improves the privacy boundary by removing hidden reasoning text before QQBot delivery.

Review details

Best possible solution:

Land the bounded QQBot-owned sanitizer hook if exact-head checks stay green; keep any broader default-sanitizer policy discussion separate from this channel regression fix.

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

Yes, source-reproducible: current main QQBot outbound lacks sanitizeText, and shared delivery only invokes channel text sanitization when that hook exists. I did not run a live Tencent QQBot plus MiniMax reproduction.

Is this the best way to solve the issue?

Yes, this is the best bounded fix for this PR: channel-owned sanitization matches the existing outbound contract and sibling-channel pattern without adding a new core fallback or config surface.

AGENTS.md: found and applied where relevant.

Codex review notes: model gpt-5.5, reasoning high; reviewed against 560b77a4aff7.

Label changes

Label justifications:

P1: The PR addresses a reported user-visible reasoning/thinking leak in QQBot replies, which is an urgent channel privacy and message-content regression.
rating: 🦞 diamond lobster: Overall readiness is 🦞 diamond lobster; proof is 🌊 off-meta tidepool and patch quality is 🦞 diamond lobster.
status: 🚀 automerge armed: This PR is in ClawSweeper's automerge lane. Not applicable: The PR author association is MEMBER, so the external-contributor real-behavior-proof gate does not apply; the PR body includes deterministic production-function proof but no live Tencent QQBot run.

Evidence reviewed

PR surface:

Source +2, Tests +19. Total +21 across 2 files.

View PR surface stats

Area	Files	Added	Net
Source	1	2	+2
Tests	1	19	+19
Docs	0	0	0
Config	0	0	0
Generated	0	0	0
Other	0	0	0
Total	2	21	+21

What I checked:

PR diff applies the hook at the QQBot outbound boundary: The PR head imports sanitizeAssistantVisibleText and sets qqbotPlugin.outbound.sanitizeText before sendText, so shared delivery can sanitize QQBot text before native send. (extensions/qqbot/src/channel.ts:257, 17cf140183e8)
Regression test covers the new hook: The PR head test asserts the QQBot outbound sanitizer exists, strips <thinking> and <think> blocks, and preserves ordinary text. (extensions/qqbot/src/channel.message-adapter.test.ts:6, 17cf140183e8)
Current delivery only uses channel sanitizer when provided: Current main calls handler.sanitizeText only when the outbound handler exposes it, which explains why QQBot needed its own hook. (src/infra/outbound/deliver.ts:795, 560b77a4aff7)
Sanitizer contract strips reasoning tags in delivery profile: sanitizeAssistantVisibleText uses the delivery profile, which runs strict reasoning-tag stripping and internal scaffolding cleanup before final trim. (src/shared/text/assistant-visible-text.ts:824, 560b77a4aff7)
QQBot media-tag contract remains source-preserved: QQBot sendText normalizes and parses private <qqimg>, <qqvoice>, <qqvideo>, <qqfile>, and <qqmedia> tags after delivery, while the sanitizer reasoning tag matcher only targets thinking/final tags and tool-call scaffolding. (extensions/qqbot/src/engine/messaging/outbound.ts:134, 560b77a4aff7)
History/provenance check: Available blame/log history ties the central QQBot outbound and delivery files in this checkout to commit d23558e; the PR patch itself is commits 9160990 and 17cf140. (extensions/qqbot/src/channel.ts:252, d23558e69150)

Likely related people:

Peter Steinberger: Available blame/log history in this checkout points the current QQBot outbound descriptor, shared delivery sanitizer call site, and assistant-visible sanitizer source to the same recent current-main commit; deeper authorship is ambiguous from the available grafted history. (role: recent area contributor; confidence: low; commits: d23558e69150; files: extensions/qqbot/src/channel.ts, extensions/qqbot/src/engine/messaging/outbound.ts, src/infra/outbound/deliver.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.

Takhoffman · 2026-06-05T03:18:32Z

@clawsweeper automerge

clawsweeper · 2026-06-05T03:18:34Z

🦞✅
ClawSweeper merged this PR after the passing review.

Source: clawsweeper[bot]
Feedback: structured ClawSweeper verdict: pass (sha=17cf140183e84fbca47325746dea3afa2005b6d3)
Merge status: merged by ClawSweeper automerge
Merged at: 2026-06-05T06:57:17Z
Merge commit: 1a3ce7c2a8da

What merged:

Adds QQBot outbound sanitizeText wired to sanitizeAssistantVisibleText plus a regression test for stripping <thinking> and <think> blocks.
PR surface: Source +2, Tests +19. Total +21 across 2 files.
Reproducibility: yes. source-reproducible: current main QQBot outbound lacks sanitizeText, and shared deli ... nnel text sanitization when that hook exists. I did not run a live Tencent QQBot plus MiniMax reproduction.

Automerge notes:

PR branch already contained follow-up commit before automerge: fix(qqbot): add curly braces for eslint(curly) compliance

The automerge loop is complete.

Automerge progress:

2026-06-05 03:42:33 UTC review queued 17cf140183e8 (queued)

2026-06-05 06:57:00 UTC review passed 17cf140183e8 (structured ClawSweeper verdict: pass (sha=17cf140183e84fbca47325746dea3afa2005b...)

2026-06-05 03:27:04 UTC repair queued 17cf140183e8 (autonomous) Run: https://github.com/openclaw/clawsweeper/actions/runs/26993498793

2026-06-05 03:28:45 UTC repair started (running) in 1s Run: https://github.com/openclaw/clawsweeper/actions/runs/26993498793 automerge-openclaw-openclaw-90132

2026-06-05 03:29:03 UTC validation plan (passed) in 19s Run: https://github.com/openclaw/clawsweeper/actions/runs/26993498793 pnpm check:changed; pnpm lint; pnpm check:test-types

2026-06-05 03:29:12 UTC Codex write preflight (passed) in 27s Run: https://github.com/openclaw/clawsweeper/actions/runs/26993498793 danger-full-access

2026-06-05 03:33:14 UTC Codex edit 1 9b5e5c233f6d (complete) in 4m 29s Run: https://github.com/openclaw/clawsweeper/actions/runs/26993498793 exit 0

2026-06-05 03:33:15 UTC validation and review 1 4d557f179ad5 (running) in 4m 31s Run: https://github.com/openclaw/clawsweeper/actions/runs/26993498793 repair

2026-06-05 04:07:17 UTC repair completed (no branch change) in 38m 33s Run: https://github.com/openclaw/clawsweeper/actions/runs/26993498793 Codex /review timed out after 128679ms

2026-06-05 04:07:19 UTC repair finished (blocked) in 38m 35s Run: https://github.com/openclaw/clawsweeper/actions/runs/26993498793 Codex /review timed out after 128679ms

2026-06-05 06:49:58 UTC review queued 17cf140183e8 (queued)

2026-06-05 06:57:20 UTC merged 17cf140183e8 (merged by ClawSweeper automerge)

openclaw#90132) Summary: - Adds QQBot outbound `sanitizeText` wired to `sanitizeAssistantVisibleText` plus a regression test for stripping `<thinking>` and `<think>` blocks. - PR surface: Source +2, Tests +19. Total +21 across 2 files. - Reproducibility: yes. source-reproducible: current main QQBot outbound lacks `sanitizeText`, and shared deli ... nnel text sanitization when that hook exists. I did not run a live Tencent QQBot plus MiniMax reproduction. Automerge notes: - PR branch already contained follow-up commit before automerge: fix(qqbot): add curly braces for eslint(curly) compliance Validation: - ClawSweeper review passed for head 17cf140. - Required merge gates passed before the squash merge. Prepared head SHA: 17cf140 Review: openclaw#90132 (comment) Co-authored-by: openperf <16864032@qq.com> Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com> Approved-by: takhoffman Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>

…26.6.5) (#963) This PR contains the following updates: | Package | Update | Change | |---|---|---| | [ghcr.io/openclaw/openclaw](https://openclaw.ai) ([source](https://github.com/openclaw/openclaw)) | patch | `2026.6.1` → `2026.6.5` | --- ### Release Notes <details> <summary>openclaw/openclaw (ghcr.io/openclaw/openclaw)</summary> ### [`v2026.6.5`](https://github.com/openclaw/openclaw/blob/HEAD/CHANGELOG.md#202665) [Compare Source](openclaw/openclaw@v2026.6.1...v2026.6.5) ##### Highlights - QQBot now strips model reasoning/thinking scaffolding before native delivery, preventing raw `<thinking>` content from leaking into channel replies. ([#89913](openclaw/openclaw#89913), [#90132](openclaw/openclaw#90132)) Thanks [@openperf](https://github.com/openperf). - MCP tool results now coerce `resource_link`, `resource`, `audio`, malformed image, and future non-text/image blocks at the materialize boundary, preventing Anthropic 400s and poisoned session history after a tool returns richer MCP content. ([#90710](openclaw/openclaw#90710), [#90728](openclaw/openclaw#90728)) Thanks [@RanSHammer](https://github.com/RanSHammer) and [@849261680](https://github.com/849261680). - Anthropic extended-thinking sessions recover after prompt-cache expiry or Gateway restart because stream start events wait for `message_start`, letting pre-generation signature errors trigger the existing recovery retry. ([#90667](openclaw/openclaw#90667), [#90697](openclaw/openclaw#90697)) Thanks [@openperf](https://github.com/openperf). - Parallel is now a bundled `web_search` provider with `PARALLEL_API_KEY` discovery, guarded endpoint handling, cache-safe session ids, onboarding picker support, and docs. ([#85158](openclaw/openclaw#85158)) Thanks [@NormallyGaussian](https://github.com/NormallyGaussian). - Google Vertex ADC users get static catalog rows and runtime model resolution again, while single-provider cooldown recovery and memory adapter status checks are more reliable. ([#90506](openclaw/openclaw#90506), [#90609](openclaw/openclaw#90609), [#90717](openclaw/openclaw#90717), [#90816](openclaw/openclaw#90816)) Thanks [@849261680](https://github.com/849261680). - Matrix can preflight voice notes before mention gating, preserve thread reads/replies through Matrix relations pagination, and carry QA coverage for voice and thread flows. ([#78016](openclaw/openclaw#78016), [#90415](openclaw/openclaw#90415)) - Auth and plugin install state is more durable: auth profiles now live in SQLite, official npm plugin install records keep their trusted pins, and prerelease fallback integrity checks avoid carrying stale integrity forward. ([#89102](openclaw/openclaw#89102), [#88585](openclaw/openclaw#88585)) - macOS node mode no longer silently self-reconnects away from a healthy direct Gateway session, reducing unexpected companion app session churn. ([#90668](openclaw/openclaw#90668), [#90815](openclaw/openclaw#90815)) Thanks [@vrurg](https://github.com/vrurg). - Upgrade and service paths are safer: cron legacy JSON stores migrate during doctor preflight, service env placeholders no longer mask state-dir secrets, WhatsApp startup waits are bounded, and disabled WhatsApp accounts tear down on config reload. ([#90072](openclaw/openclaw#90072), [#90208](openclaw/openclaw#90208), [#90277](openclaw/openclaw#90277), [#90488](openclaw/openclaw#90488), [#90486](openclaw/openclaw#90486), [#87951](openclaw/openclaw#87951), [#87965](openclaw/openclaw#87965)) Thanks [@MonkeyLeeT](https://github.com/MonkeyLeeT), [@sallyom](https://github.com/sallyom), [@mcaxtr](https://github.com/mcaxtr), and [@MukundaKatta](https://github.com/MukundaKatta). ##### Changes - Search/providers: add the Parallel bundled web-search plugin, live provider tests, registration contracts, onboarding/docs wiring, and guarded `api.parallel.ai/v1/search` support. ([#85158](openclaw/openclaw#85158)) Thanks [@NormallyGaussian](https://github.com/NormallyGaussian). - Matrix/channels: add voice-message preflight and thread-aware read/reply behavior, including Matrix QA scenario wiring and docs for voice-message behavior. ([#78016](openclaw/openclaw#78016), [#90415](openclaw/openclaw#90415)) - Skills/ClawHub: install ClawHub skills backed by GitHub repositories through the resolved install API, download the pinned GitHub commit, keep install-policy checks, and report install telemetry after success. ([#90478](openclaw/openclaw#90478)) Thanks [@Patrick-Erichsen](https://github.com/Patrick-Erichsen). - Google Chat/channels: add native approval card actions and click handling so Google Chat approvals use platform-native cards instead of generic message flow. - Mobile: Android provider/model screens now surface expiring, unavailable, unresolved, and attention states more clearly, while iOS settings and Talk tabs keep diagnostics, gateway rows, attachment labels, and unavailable Talk controls reachable. - Memory: QMD search can use the new rerank toggle, and memory adapter status uses the resolved default model identity when checking plain status. ([#61834](openclaw/openclaw#61834)) - Docs/tooling: add Parallel search docs, refresh weather-skill guidance toward `web_fetch`, clarify legacy `openai-codex` auth, document release/test helper scripts, and tighten changed-test routing docs for CI/debugging work. ([#90028](openclaw/openclaw#90028), [#90250](openclaw/openclaw#90250)) Thanks [@fuller-stack-dev](https://github.com/fuller-stack-dev). - Release/process: switch release trains to `YYYY.M.PATCH` monthly patch numbering, keep pre-transition tags compatible, and pin the June 2026 floor at `2026.6.5` after the published beta. - Platform maintenance: refresh Android, Swift/macOS, Docker, CodeQL, Buildx, Docker build/push, and Codex Action dependencies for this release train. ([#74980](openclaw/openclaw#74980), [#81757](openclaw/openclaw#81757), [#86481](openclaw/openclaw#86481), [#86483](openclaw/openclaw#86483), [#90601](openclaw/openclaw#90601)) - QQBot: add `/bot-group-allways on|off` slash command (with named-account and default-account support) to toggle whether group messages require an `@mention` before the bot replies, and clear the runtime config snapshot after the write so the new account-level `defaultRequireMention` takes effect immediately without restart. ([#91423](openclaw/openclaw#91423)) Thanks [@cxyhhhhh](https://github.com/cxyhhhhh). ##### Fixes - Channel content boundaries: QQBot now strips reasoning/thinking tags before sending, preserving final answers while hiding internal model narration from users. ([#89913](openclaw/openclaw#89913), [#90132](openclaw/openclaw#90132)) Thanks [@openperf](https://github.com/openperf). - Agents/MCP/providers: coerce non-text/image MCP tool-result blocks before they reach provider converters, preserving valid images and turning richer MCP content into text instead of malformed image blocks. ([#90710](openclaw/openclaw#90710), [#90728](openclaw/openclaw#90728)) Thanks [@RanSHammer](https://github.com/RanSHammer) and [@849261680](https://github.com/849261680). - Anthropic/Codex/ACP/agent recovery: defer Anthropic stream start events until `message_start`, strip stale compaction thinking signatures before Anthropic replay, detect unsigned thinking-only stalls, refresh prompt fences after compaction writes, reject empty completion handoffs, preserve parent streaming-off overrides/shared progress commentary, forward heartbeat metadata to context-engine hooks, and cover Codex session/thread migration edge cases. ([#90667](openclaw/openclaw#90667), [#90697](openclaw/openclaw#90697), [#90163](openclaw/openclaw#90163), [#90108](openclaw/openclaw#90108), [#89874](openclaw/openclaw#89874), [#89505](openclaw/openclaw#89505), [#90632](openclaw/openclaw#90632), [#89302](openclaw/openclaw#89302), [#90729](openclaw/openclaw#90729), [#90317](openclaw/openclaw#90317), [#90319](openclaw/openclaw#90319)) Thanks [@openperf](https://github.com/openperf), [@100yenadmin](https://github.com/100yenadmin), and [@ooiuuii](https://github.com/ooiuuii). - Provider/model resolution: preserve Google Vertex ADC auth markers in generated catalogs, re-probe a single-provider primary after cooldown, share Codex model visibility, fail closed for unknown model auth, preserve Codex alias availability, keep unresolved profile refs unknown, and avoid resolving auth while listing models. ([#90506](openclaw/openclaw#90506), [#90609](openclaw/openclaw#90609), [#90717](openclaw/openclaw#90717), [#90702](openclaw/openclaw#90702)) Thanks [@849261680](https://github.com/849261680). - Gateway/macOS/mobile: avoid duplicate Gateway probe warnings by identity, rate-limit node pairing requests while preserving paired-node reconnects, keep macOS node mode on a healthy direct Gateway session, keep iOS diagnostics and gateway rows reachable, and avoid Linux ARM Gradle resource tasks during Android builds. ([#85791](openclaw/openclaw#85791), [#90147](openclaw/openclaw#90147), [#90668](openclaw/openclaw#90668), [#90815](openclaw/openclaw#90815)) Thanks [@giodl73-repo](https://github.com/giodl73-repo) and [@vrurg](https://github.com/vrurg). - TUI/chat/Workboard/auto-reply: optimistic user messages stay stable across stale history reloads, runId reassignment, and abort windows instead of disappearing, jumping, or lingering as ghost rows; Workboard stale lifecycle bulk updates no longer overwrite newer status/provenance; message-tool sends now count as delivery. ([#86205](openclaw/openclaw#86205), [#89600](openclaw/openclaw#89600), [#88592](openclaw/openclaw#88592), [#90123](openclaw/openclaw#90123)) Thanks [@RomneyDa](https://github.com/RomneyDa). - Cron/update/service env: doctor config preflight now migrates legacy cron JSON stores into SQLite before runtime reads, service env planning skips unresolved placeholders that would mask state-dir `.env` values, and session transcript rewrites keep registry markers/discriminants consistent. ([#90072](openclaw/openclaw#90072), [#90208](openclaw/openclaw#90208), [#90277](openclaw/openclaw#90277), [#90488](openclaw/openclaw#90488)) Thanks [@MonkeyLeeT](https://github.com/MonkeyLeeT) and [@sallyom](https://github.com/sallyom). - Security/config/tooling: guard MCP HTTP redirects, protect global agent config defaults, and keep release/test/tooling proof failures bounded and explicit. ([#89732](openclaw/openclaw#89732), [#90145](openclaw/openclaw#90145)) - Channels: WhatsApp restarts when per-account config changes, bounds background startup waits, closes failed sockets, and preserves reconnect behavior; Mattermost slash commands keep their state on `globalThis`; Feishu streaming cards preserve full merged content; voice-call tracks Twilio streams after connect; ClickClack reply tools respect `toolsAllow`. ([#87951](openclaw/openclaw#87951), [#87965](openclaw/openclaw#87965), [#90486](openclaw/openclaw#90486), [#68113](openclaw/openclaw#68113), [#90534](openclaw/openclaw#90534), [#90181](openclaw/openclaw#90181), [#90607](openclaw/openclaw#90607), [#89500](openclaw/openclaw#89500)) Thanks [@MukundaKatta](https://github.com/MukundaKatta), [@mcaxtr](https://github.com/mcaxtr), [@infoanton](https://github.com/infoanton), [@mushuiyu886](https://github.com/mushuiyu886), and [@sahibzada-allahyar](https://github.com/sahibzada-allahyar). - Feishu: retry transient send rate-limit errors (HTTP 429, per-chat code 230020, tenant-level code 11232) with linear backoff, including SDK responses that fulfill with rate-limit bodies instead of throwing, and route streaming-card sends through the retry wrapper. ([#89659](openclaw/openclaw#89659)) Thanks [@ladygege](https://github.com/ladygege). - Release/CI/E2E: main CI guard drift, PR merge diff scoping, live Docker credential staging, base-image qualification, installer Docker classification, Playwright dependency install recovery, API-key auth for Codex live Docker lanes, Parallels option terminators, and JSON-mode progress handling are tighter so release proof fails cleaner. ([#90532](openclaw/openclaw#90532), [#90287](openclaw/openclaw#90287), [#90058](openclaw/openclaw#90058)) Thanks [@RomneyDa](https://github.com/RomneyDa), [@hxy91819](https://github.com/hxy91819), and [@mrunalp](https://github.com/mrunalp). - Release/CI/E2E: Docker E2E and live Docker harness runs now apply default memory, CPU, and process ceilings while preserving explicit per-lane overrides. - Release/CI/E2E: plugin lifecycle matrix resource sampling now fails phases that exceed RSS, wall-clock, or CPU ceilings instead of only logging the measurements. - Release/CI/E2E: Codex npm plugin live assertions now cap transcript discovery and diagnostic log reads so failure proof stays bounded. - Tests/state isolation: QA Lab valid-tool-call metrics now require runtime tool-call evidence when runtime parity data is available instead of counting tool-backed scenario pass status alone. - Tests/state isolation: QA Lab runtime parity now fails planned-only tool-call rows without matching tool results instead of treating matching mock plans as real tool evidence. - Tests/state isolation: provider, media, auth, cron, task, session, sandbox, Gateway, and Codex timeout fixtures now scope more home/state/env data per test, reducing cross-test leakage and making release validation failures less noisy. ([#90027](openclaw/openclaw#90027), [#89974](openclaw/openclaw#89974)) </details> --- ### Configuration 📅 **Schedule**: Branch creation - At any time (no schedule defined), Automerge - At any time (no schedule defined). 🚦 **Automerge**: Disabled by config. Please merge this manually once you are satisfied. ♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox. 🔕 **Ignore**: Close this PR and you won't be reminded about these updates again. --- - [ ] If you want to rebase/retry this PR, check this box --- This PR has been generated by [Renovate Bot](https://github.com/renovatebot/renovate).  Reviewed-on: https://git.erwanleboucher.dev/eleboucher/homelab/pulls/963

fix(qqbot): sanitize outbound text to strip reasoning/thinking content

9160990

openclaw-barnacle Bot added channel: qqbot size: XS labels Jun 4, 2026

fix(qqbot): add curly braces for eslint(curly) compliance

17cf140

clawsweeper Bot added rating: 🦞 diamond lobster Very strong PR readiness with only minor maintainer review expected. and removed rating: 🐚 platinum hermit Good normal PR readiness with ordinary maintainer review expected. labels Jun 4, 2026

clawsweeper Bot mentioned this pull request Jun 4, 2026

fix(qqbot): sanitize outbound reasoning text #90189

Closed

clawsweeper Bot merged commit 1a3ce7c into openclaw:main Jun 5, 2026
205 of 213 checks passed

github-actions Bot mentioned this pull request Jun 5, 2026

📡 Upstream Digest — 2026-06-05 08:00 UTC curtismercier/openclaw-mods#1018

Open

github-actions Bot mentioned this pull request Jun 7, 2026

🦞 OpenClaw 生态日报 2026-06-07 zx0828/big_model_radar#91

Open

github-actions Bot mentioned this pull request Jun 9, 2026

🦞 OpenClaw 生态日报 2026-06-09 jasonalang/big_model_radar#62

Open

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

fix(qqbot): sanitize outbound text to strip reasoning/thinking content#90132

fix(qqbot): sanitize outbound text to strip reasoning/thinking content#90132
clawsweeper[bot] merged 2 commits into
openclaw:mainfrom
openperf:fix/89913-qqbot-reasoning-sanitize

openperf commented Jun 4, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented Jun 4, 2026 •

edited

Loading

Uh oh!

Takhoffman commented Jun 5, 2026

Uh oh!

clawsweeper Bot commented Jun 5, 2026 •

edited

Loading

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Uh oh!

Conversation

openperf commented Jun 4, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Reproduction

Real behavior proof

Risk / Mitigation

Change Type (select all)

Scope (select all touched areas)

Linked Issue/PR

Uh oh!

clawsweeper Bot commented Jun 4, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Takhoffman commented Jun 5, 2026

Uh oh!

clawsweeper Bot commented Jun 5, 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

openperf commented Jun 4, 2026 •

edited

Loading

clawsweeper Bot commented Jun 4, 2026 •

edited

Loading

clawsweeper Bot commented Jun 5, 2026 •

edited

Loading