fix(agents): drop unsafe Copilot reasoning replay IDs by galiniliev · Pull Request #85198 · openclaw/openclaw

galiniliev · 2026-05-22T03:32:39Z

Summary

Problem: GitHub Copilot native Responses can reject resumed Telegram direct sessions when persisted reasoning replay item IDs exceed the provider's 64-character input[].id limit.
Solution: Drop unsafe GitHub Copilot Responses reasoning replay items in the direct request-builder path before the payload can be sent.
What changed: The regression now asserts a GitHub Copilot openai-responses payload built from a 383-character reasoning replay ID does not emit that reasoning item; assistant message replay IDs still use the shared length normalizer.
What did NOT change (scope boundary): Copilot's provider wrapper still owns connection-bound message ID rewriting and still drops unsafe reasoning items at the wrapped payload boundary.

Motivation

The affected Telegram direct session accepted inbound messages but failed before assistant output with Invalid 'input[112].id': string too long. Expected a string with maximum length 64, but got a string with length 383 instead.

Change Type (select all)

Scope (select all touched areas)

Linked Issue/PR

Closes [Bug]: Telegram direct replay can send overlong Copilot reasoning item IDs #85197
Related [Bug]: OpenAI Responses replay can send overlong tool call_id values after tool use #74665
Related [Bug]: Reasoning model thinking blocks (<thinking> tags) in conversation history cause HTTP 400 on GitHub Copilot provider #81520
Related fix(github-copilot): strip thinking blocks from latest assistant turn (#81520) #81534
This PR fixes a bug or regression

Real behavior proof (required for external PRs)

Behavior addressed: GitHub Copilot native Responses request building no longer sends overlong replayed reasoning item IDs that can trigger the provider input[].id 64-character validation error.

Real environment tested: Local OpenClaw worktree on Linux with Node v24.15.0, using the real buildOpenAIResponsesParams request-builder seam plus the existing GitHub Copilot provider-boundary sanitizer tests.

Exact steps or command run after this patch: pnpm format:fix src/agents/openai-transport-stream.ts src/agents/openai-transport-stream.test.ts; node scripts/run-vitest.mjs src/agents/openai-transport-stream.test.ts extensions/github-copilot/connection-bound-ids.test.ts extensions/github-copilot/stream.test.ts; git diff --check.

Evidence after fix: Focused Vitest output from the patched worktree:

Test Files  4 passed (4)
     Tests  363 passed (363)
  Duration  12.31s (transform 6.28s, setup 1.10s, import 9.80s, tests 1.15s, environment 0ms)

Observed result after fix: The direct GitHub Copilot Responses builder test drops the overlong reasoning replay item before send, and the existing Copilot wrapper/sanitizer tests continue to prove unsafe reasoning replay items are removed at the wrapped provider boundary.

What was not tested: No live Telegram or GitHub Copilot provider rerun was performed because the failing evidence depends on a private persisted Telegram session and credentials.

Before evidence (optional but encouraged): Redacted runtime log excerpt from the affected setup:

embedded run prompt start: provider=github-copilot api=openai-responses endpoint=github-copilot-native route=native
context-overflow-precheck: route=fits estimatedPromptTokens=56663 overflowTokens=0
embedded_run_agent_end: isError=true error="OpenAI API error (400): 400 Invalid 'input[112].id': string too long. Expected a string with maximum length 64, but got a string with length 383 instead." model=gpt-5.5 provider=github-copilot rawErrorHash=sha256:2279064209cc
message dispatch completed: channel=telegram outcome=completed

Root Cause (if applicable)

Root cause: convertResponsesMessages() parsed persisted JSON thinkingSignature blocks as replayable Responses reasoning items and preserved their id whenever Responses item ID replay was enabled. GitHub Copilot native Responses uses that replay path, so overlong historical reasoning IDs could reach input[].id in the direct request-builder path.
Missing detection / guardrail: Existing Copilot replay tests covered provider-boundary dropping, but the direct builder regression originally did not prove the production failing path was fixed.
Contributing context (if known): Prior replay fixes normalized tool/function and assistant message IDs. Reasoning IDs are different because they can reference server-side encrypted state, so unsafe Copilot reasoning items are dropped instead of rewritten.

Regression Test Plan (if applicable)

Coverage level that should have caught this:
- Unit test
- Seam / integration test
- End-to-end test
- Existing coverage already sufficient
Target test or file: src/agents/openai-transport-stream.test.ts, extensions/github-copilot/connection-bound-ids.test.ts, extensions/github-copilot/stream.test.ts
Scenario the test should lock in: A GitHub Copilot openai-responses payload built from a persisted reasoning thinkingSignature with a 383-character id does not emit that unsafe reasoning item in the direct builder path, and the Copilot wrapper/sanitizer still drops unsafe reasoning replay items before wrapped sends.
Why this is the smallest reliable guardrail: The failure happens during request construction before provider generation, and the provider wrapper has separate existing coverage for its send-boundary sanitizer.
Existing test that already covers this (if any): extensions/github-copilot/connection-bound-ids.test.ts covers dropping overlong/missing/non-string reasoning IDs; extensions/github-copilot/stream.test.ts covers the wrapper applying that sanitizer before payload send.
If no new test is added, why not: N/A

User-visible / Behavior Changes

Telegram direct sessions with overlong persisted Copilot Responses reasoning replay IDs can continue instead of failing before assistant output; unsafe replayed reasoning state is dropped.

Diagram (if applicable)

Before:
[persisted reasoning id length 383] -> [Responses input[].id unchanged] -> [provider 400]

Rejected first patch:
[persisted reasoning id length 383] -> [rs_<hash>] -> [Copilot encrypted reasoning lookup rewritten]

After:
[persisted reasoning id length 383] -> [direct builder drops unsafe Copilot reasoning item] -> [request can send]

Security Impact (required)

New permissions/capabilities? (Yes/No): No
Secrets/tokens handling changed? (Yes/No): No
New/changed network calls? (Yes/No): No
Command/tool execution surface changed? (Yes/No): No
Data access scope changed? (Yes/No): No
If any Yes, explain risk + mitigation: N/A

Repro + Verification

Environment

OS: Linux local worktree
Runtime/container: Node v24.15.0
Model/provider: github-copilot/gpt-5.5
Integration/channel (if any): Telegram direct session evidence; local request-builder and Copilot-boundary verification
Relevant config (redacted): GitHub Copilot native Responses route with a redacted private Telegram session

Steps

Build a GitHub Copilot Responses payload from an assistant message with a persisted JSON thinkingSignature reasoning item.
Use an overlong 383-character reasoning item id.
Inspect the emitted payload and run the existing Copilot wrapper/sanitizer tests.

Expected

The direct GitHub Copilot Responses builder removes unsafe overlong reasoning replay items before send.
The Copilot boundary also removes unsafe overlong reasoning replay items when wrapping provider sends.

Actual

Before this patch, the 383-character ID could reach the provider and be rejected.
After this patch, the direct builder drops the unsafe reasoning item and the focused tests pass.

Evidence

Attach at least one:

Failing test/log before + passing after
Trace/log snippets
Screenshot/recording
Perf numbers (if relevant)

Human Verification (required)

What you personally verified (not just CI), and how:

Verified scenarios: Formatted the touched files, ran the focused agent transport and GitHub Copilot wrapper/sanitizer Vitest files, and ran git diff --check.
Edge cases checked: Overlong Copilot reasoning replay items are dropped; assistant message replay IDs still normalize to short msg_ IDs; existing Copilot wrapper behavior still drops unsafe reasoning replay at the provider boundary.
What you did not verify: Live Telegram replay against the private affected session and live GitHub Copilot credentials.

Review Conversations

I replied to or resolved every bot review conversation I addressed in this PR.
I left unresolved only the conversations that still need reviewer or maintainer judgment.

If a bot review conversation is addressed by this PR, resolve that conversation yourself. Do not leave bot review conversation cleanup for maintainers.

Compatibility / Migration

Backward compatible? (Yes/No): Yes
Config/env changes? (Yes/No): No
Migration needed? (Yes/No): No
If yes, exact upgrade steps: N/A

Risks and Mitigations

Risk: Dropping unsafe reasoning replay can lose server-side reasoning continuity for that historical item.
- Mitigation: The provider already rejects the unsafe ID, and the Copilot boundary explicitly treats unsafe reasoning items as invalid or ambiguous server-state lookups.

clawsweeper · 2026-05-22T03:34:30Z

Codex review: needs maintainer review before merge.

Workflow note: Future ClawSweeper reviews update this same comment in place.

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.

Summary
The branch drops unsafe GitHub Copilot Responses reasoning replay items in the OpenAI Responses request builder and adds a regression test for an overlong persisted reasoning item ID.

Reproducibility: yes. for the source-level payload path: current main replays JSON reasoning items from thinkingSignature without a Copilot ID-length guard, and the PR body includes the redacted provider 400 plus after-fix seam output. I did not reproduce the private Telegram/Copilot session end to end.

PR rating
Overall: 🐚 platinum hermit
Proof: 🐚 platinum hermit
Patch quality: 🐚 platinum hermit
Summary: Focused bug-fix PR with usable seam proof and no blocking findings, with only the private live Telegram/Copilot replay left unproven.

Rank-up moves:

A redacted live outbound payload log or full Telegram/Copilot rerun would reduce the remaining runtime ambiguity.

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.

Real behavior proof
Sufficient (live_output): The PR body includes redacted before-failure logs plus copied after-fix focused Vitest output exercising the real request-builder seam and existing Copilot sanitizer, which is sufficient for this narrow non-visual payload fix.

Risk before merge

No live Telegram or GitHub Copilot credential rerun is attached; the runtime failure is supported by redacted logs and focused request-builder/sanitizer proof rather than an end-to-end replay.
Dropping an unsafe reasoning replay item intentionally loses continuity for that historical server-state item, although current provider-boundary sanitizer already makes the same choice and the reported payload is rejected otherwise.

Maintainer options:

Decide the mitigation before merge
Merge after maintainer review if the seam proof is accepted, keeping Copilot-specific unsafe reasoning-item dropping aligned between the request builder and provider-boundary sanitizer with regression coverage.
Pause or close
Do not merge this PR until maintainers decide whether the risk is worth taking.

Next step before merge
The PR has a protected maintainer label and no narrow automated repair blocker; maintainers should decide whether the provided seam proof is enough to merge the linked P1 fix.

Security
Cleared: The diff only changes agent transport source and a focused unit test, with no dependency, permission, secret-handling, install, release, or code-execution surface changes.

Review details

Best possible solution:

Merge after maintainer review if the seam proof is accepted, keeping Copilot-specific unsafe reasoning-item dropping aligned between the request builder and provider-boundary sanitizer with regression coverage.

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

Yes for the source-level payload path: current main replays JSON reasoning items from thinkingSignature without a Copilot ID-length guard, and the PR body includes the redacted provider 400 plus after-fix seam output. I did not reproduce the private Telegram/Copilot session end to end.

Is this the best way to solve the issue?

Yes for the narrow technical direction: dropping only unsafe Copilot reasoning replay items matches the existing provider-boundary sanitizer and avoids rewriting server-state IDs. The remaining merge question is proof tolerance, not a concrete code defect.

Label justifications:

P1: The PR targets a linked Telegram/GitHub Copilot regression where resumed direct sessions can accept inbound messages but fail before assistant output.
rating: 🐚 platinum hermit: Current PR rating is 🐚 platinum hermit because proof is 🐚 platinum hermit, patch quality is 🐚 platinum hermit, and Focused bug-fix PR with usable seam proof and no blocking findings, with only the private live Telegram/Copilot replay left unproven.
status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Sufficient (live_output): The PR body includes redacted before-failure logs plus copied after-fix focused Vitest output exercising the real request-builder seam and existing Copilot sanitizer, which is sufficient for this narrow non-visual payload fix.
proof: sufficient: Contributor real behavior proof is sufficient. The PR body includes redacted before-failure logs plus copied after-fix focused Vitest output exercising the real request-builder seam and existing Copilot sanitizer, which is sufficient for this narrow non-visual payload fix.

Acceptance criteria:

node scripts/run-vitest.mjs src/agents/openai-transport-stream.test.ts extensions/github-copilot/connection-bound-ids.test.ts extensions/github-copilot/stream.test.ts
git diff --check

What I checked:

Current main builder lacks the guard: Current main parses JSON thinkingSignature blocks into replayable Responses reasoning items and pushes them into input[] after only deleting id when replay IDs are disabled; there is no Copilot reasoning-ID length check in this builder path. (src/agents/openai-transport-stream.ts:1081, 229490a48924)
PR implements the direct-builder drop: The PR adds a 64-character replay-item ID limit helper and skips GitHub Copilot reasoning replay items whose id is not a non-empty string within that limit before adding them to the Responses payload. (src/agents/openai-transport-stream.ts:1113, 9a42f9e32fb8)
PR adds focused regression coverage: The new test builds a GitHub Copilot openai-responses payload with a 383-character rs_... reasoning replay ID and asserts the direct builder emits no reasoning item. (src/agents/openai-transport-stream.test.ts:2383, 9a42f9e32fb8)
Provider-boundary behavior already matches the PR direction: The existing GitHub Copilot sanitizer treats reasoning items as server-state lookups and drops unsafe reasoning items instead of rewriting or stripping their IDs. (extensions/github-copilot/connection-bound-ids.ts:47, 229490a48924)
Existing Copilot wrapper sanitizes payloads before send: The Copilot Responses wrapper already rewrites/drops unsafe response IDs from the onPayload hook before delegating to the underlying stream, so the PR aligns the earlier request-builder seam with that provider-boundary policy. (extensions/github-copilot/stream.ts:121, 229490a48924)
Related issue remains open and paired: The PR body uses closing syntax for the still-open linked bug report at [Bug]: Telegram direct replay can send overlong Copilot reasoning item IDs #85197, so the issue/PR pair should remain open until the fix lands or maintainers close the PR path.

Likely related people:

Vincent Koc: Introduced and refactored the OpenAI/provider transport adapter seams that this builder path sits on, including commits touching src/agents/openai-transport-stream.ts. (role: provider transport seam contributor; confidence: medium; commits: 4798e125f40c, ea4265a82063, cc1881a83846; files: src/agents/openai-transport-stream.ts, extensions/github-copilot/stream.ts)
Thomas Krohnfuß: Current checkout blame/log attributes the present transport and Copilot stream files to a recent commit that added the file contents in this shallow/grafted history, making this a useful routing signal but not sole ownership proof. (role: recent area contributor in checkout provenance; confidence: medium; commits: 98af51748d19; files: src/agents/openai-transport-stream.ts, extensions/github-copilot/connection-bound-ids.ts, extensions/github-copilot/stream.ts)
bladin: Recent merged work changed OpenAI reasoning replay parsing/tests in the same transport file, which is adjacent to the reasoning-signature path this PR hardens. (role: adjacent reasoning replay contributor; confidence: medium; commits: e0bf756b50b5; files: src/agents/openai-transport-stream.ts, src/agents/openai-transport-stream.test.ts)

Codex review notes: model gpt-5.5, reasoning high; reviewed against 229490a48924.

clawsweeper · 2026-05-22T03:40:52Z

ClawSweeper PR egg

✨ Hatched: 🥚 common Cosmic Crabkin

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: stacks clean commits.
Image traits: location CI tidepool; accessory rollback rope; palette coral, mint, and warm cream; mood determined; pose nestled inside a glowing shell; shell matte ceramic shell; lighting tiny status-light glow; background delicate sparkle particles.
Share on X: post this hatch
Copy: My PR egg hatched a 🥚 common Cosmic Crabkin 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.

galiniliev · 2026-05-22T05:07:40Z

Landed manually to main as 93c613c from source head 9a42f9e.

Verification:

git diff --check
node scripts/run-vitest.mjs src/agents/openai-transport-stream.test.ts -t 'drops oversized GitHub Copilot Responses reasoning replay items before send'
node scripts/run-vitest.mjs extensions/github-copilot/connection-bound-ids.test.ts

Known proof gap: no live Telegram/Copilot E2E was run for this landing; regression coverage exercises the unsafe replay item filtering path directly.

…026.5.22) (#645) This PR contains the following updates: | Package | Update | Change | |---|---|---| | [ghcr.io/openclaw/openclaw](https://openclaw.ai) ([source](https://github.com/openclaw/openclaw)) | patch | `2026.5.20` → `2026.5.22` | --- ### Release Notes <details> <summary>openclaw/openclaw (ghcr.io/openclaw/openclaw)</summary> ### [`v2026.5.22`](https://github.com/openclaw/openclaw/releases/tag/v2026.5.22): openclaw 2026.5.22 [Compare Source](https://github.com/openclaw/openclaw/compare/v2026.5.20...v2026.5.22) ##### 2026.5.22 ##### Changes - Gateway/perf: reuse process-stable channel catalog reads, avoid repeated bundled-channel boundary checks, and rotate gateway watch CPU profiles so benchmark runs do not accumulate unbounded artifacts. - Gateway/perf: reuse immutable plugin metadata snapshots across startup, config, model, channel, setup, and secret metadata readers so hot paths avoid repeated plugin file stats and manifest registry reloads. - Gateway/perf: lazy-load startup-idle plugin work, core gateway method handlers, and the embedded ACPX runtime so Gateway health and ready signals no longer wait on unused handler trees or ACPX probes. - Gateway/perf: cache plugin SDK public-surface alias maps and skip irrelevant macOS Linuxbrew PATH probes so Gateway startup avoids repeated filesystem walks and slow missing-directory stats. - Meeting Notes: add a source-only external meeting-notes plugin and SDK source-provider contract outside the core npm package, with auto-start capture config, manual transcript imports, read-only `openclaw meeting-notes` CLI access, and Discord voice as the first live source. - Docs/channels/config: add Signal `configPath`, Telegram wildcard topic defaults, local-time backup archive names, Termux home fallback, include-path validation, secret-scanner-safe placeholder guidance, Gemini CLI/Antigravity media guidance, and macOS VM auto-login guidance. Thanks [@NorseGaud](https://github.com/NorseGaud), [@yudistiraashadi](https://github.com/yudistiraashadi), [@huangqian8](https://github.com/huangqian8), [@VibhorGautam](https://github.com/VibhorGautam), [@maweibin](https://github.com/maweibin), [@tianxingleo](https://github.com/tianxingleo), [@IgnacioPro](https://github.com/IgnacioPro), and [@xzcxzcyy-claw](https://github.com/xzcxzcyy-claw). - Docs: clarify model-usage portability, Codex migration prerequisites, status bootstrap wording, thread-bound subagent limits, hook ownership, and config-preserving safety guidance. Thanks [@aniruddhaadak80](https://github.com/aniruddhaadak80), [@leno23](https://github.com/leno23), [@TomDjerry](https://github.com/TomDjerry), [@matthewxmurphy](https://github.com/matthewxmurphy), [@vincentkoc](https://github.com/vincentkoc), and [@stablegenius49](https://github.com/stablegenius49). - Docs: clarify README onboarding and Gateway startup paths, WhatsApp QR/408 recovery, cron output language prompts, skill advanced features, gateway upstream 403 troubleshooting, and plugin fallback override guidance. Thanks [@deepujain](https://github.com/deepujain), [@Zacxxx](https://github.com/Zacxxx), [@Jah-yee](https://github.com/Jah-yee), [@neyric](https://github.com/neyric), [@usimic](https://github.com/usimic), [@Renu-Cybe](https://github.com/Renu-Cybe), [@BigUncle](https://github.com/BigUncle), and [@SeashoreShi](https://github.com/SeashoreShi). - Docs: clarify context-pruning ratio bounds, local dashboard recovery, CLI env markers, remote onboarding token behavior, and Peekaboo Bridge permissions for subprocess agents. Thanks [@ayesha-aziz123](https://github.com/ayesha-aziz123), [@dishraters](https://github.com/dishraters), [@hougangdev](https://github.com/hougangdev), and [@brandonlipman](https://github.com/brandonlipman). - Docs: clarify browser CDP diagnostics, Plugin SDK allowlist imports, status-reaction timing defaults, queue steering behavior, limited-tool troubleshooting, cron HEARTBEAT handling, Telegram multi-agent groups, Bitwarden SecretRef setup, and EasyRunner deployments. Thanks [@Quratulain-bilal](https://github.com/Quratulain-bilal), [@mbelinky](https://github.com/mbelinky), [@Mickey-](https://github.com/Mickey-), [@vancece](https://github.com/vancece), [@xenouzik](https://github.com/xenouzik), [@posigit](https://github.com/posigit), [@surlymochan](https://github.com/surlymochan), [@janaka](https://github.com/janaka), and [@choiking](https://github.com/choiking). - Crabbox/Testbox: run clean sparse-checkout Testbox syncs from a temporary full checkout and route remote changed gates through Corepack pnpm. - Docs: clarify IPv4-only Gateway BYOH binding, trusted-proxy scope clearing, Android pairing approval, macOS Accessibility grants, Zalo profile env vars, password-store SecretRef setup, and Chinese memory navigation. Thanks [@itskai-dev](https://github.com/itskai-dev), [@gwh7078](https://github.com/gwh7078), [@longstoryscott](https://github.com/longstoryscott), [@MoeJaberr](https://github.com/MoeJaberr), and [@yuaiccc](https://github.com/yuaiccc). - Docs: consolidate GLM under Z.AI, add the Upstash Box install guide and Gateway exposure runbook, clarify MEDIA directives, Copilot and Voyage setup, config path quoting, real behavior proof, and memory-file write guidance. Thanks [@BobDu](https://github.com/BobDu), [@alitariksahin](https://github.com/alitariksahin), [@Jefsky](https://github.com/Jefsky), [@musaabhasan](https://github.com/musaabhasan), [@OmerZeyveli](https://github.com/OmerZeyveli), [@leno23](https://github.com/leno23), [@WuKongAI-CMU](https://github.com/WuKongAI-CMU), [@luoyanglang](https://github.com/luoyanglang), and [@majin1102](https://github.com/majin1102). - Docs: clarify media provider credentials, Codex/OpenClaw code-mode boundaries, Slack and Telegram ack reactions, Feishu dynamic agents, secrets plaintext boundaries, memory guidance, and Chinese glossary terms. Thanks [@nielskaspers](https://github.com/nielskaspers), [@cosmopolitan033](https://github.com/cosmopolitan033), [@drclaw-iq](https://github.com/drclaw-iq), [@alexgduarte](https://github.com/alexgduarte), [@zccyman](https://github.com/zccyman), [@chengoak](https://github.com/chengoak), and [@cassthebandit](https://github.com/cassthebandit). - Packaging: exclude documentation images and assets from the npm tarball, reducing published package size without affecting runtime docs search or CLI behavior. Thanks [@SebTardif](https://github.com/SebTardif). - Media understanding: stop auto-probing Gemini CLI and use Antigravity CLI only as a lower-priority image/video fallback after configured provider APIs. - Agents/subagents: limit default sub-agent bootstrap context to `AGENTS.md` and `TOOLS.md`, keeping persona, identity, user, memory, heartbeat, and setup files out of delegated workers by default. ([#85283](https://github.com/openclaw/openclaw/issues/85283)) Thanks [@100yenadmin](https://github.com/100yenadmin). - Maintainer skills: exclude plugin SDK/API boundary work from `openclaw-landable-bug-sweep` so bugbash sweeps stay focused on small paper-cut fixes. - QA-Lab/diagnostics: extend the OpenTelemetry smoke harness to prove trace, metric, and log export, and add first-class Prometheus and observability smoke aliases. - Plugin SDK: add a generic channel-message poll sender so channel plugins can expose poll delivery without depending on channel-specific SDK facades. - Crabbox: keep the local wrapper's provider validation synced with the installed Crabbox binary while preserving supported aliases such as `docker` and `blacksmith`. ([#85302](https://github.com/openclaw/openclaw/issues/85302)) Thanks [@hxy91819](https://github.com/hxy91819). - Maintainer skills: add `openclaw-landable-bug-sweep` for producing five small, reviewed, CI-green OpenClaw bugfix PRs from issue/PR sweeps. - Control UI/chat: add search and Load More pagination to the chat session picker, keeping initial session loads bounded while making older conversations reachable. ([#85237](https://github.com/openclaw/openclaw/issues/85237)) Thanks [@amknight](https://github.com/amknight). - CLI/onboarding: start classic onboarding when bare `openclaw` runs before an authored config exists, while keeping configured installs on Crestodian. ([#72343](https://github.com/openclaw/openclaw/issues/72343)) Thanks [@fuller-stack-dev](https://github.com/fuller-stack-dev). - Discord: allow configuring a bounded `agentComponents.ttlMs` callback registry lifetime for long-running component workflows, with per-account overrides and a 24-hour cap. ([#84189](https://github.com/openclaw/openclaw/issues/84189)) Thanks [@100menotu001](https://github.com/100menotu001). - xAI/Grok: reuse xAI OAuth auth profiles for Grok `web_search`, thread active-agent auth through web search, add Grok model aliases, and let media providers declare default operation timeouts. ([#85182](https://github.com/openclaw/openclaw/issues/85182)) Thanks [@fuller-stack-dev](https://github.com/fuller-stack-dev). - Plugin SDK: add row-level session workflow helpers and deprecate `loadSessionStore` so plugins can read and patch sessions without depending on the legacy whole-store shape. ([#84693](https://github.com/openclaw/openclaw/issues/84693)) Thanks [@efpiva](https://github.com/efpiva). - Gateway/plugins: reuse a compatible Gateway startup plugin registry during dispatch so safe plugin dispatches avoid redundant registry loading. ([#84324](https://github.com/openclaw/openclaw/issues/84324)) Thanks [@ai-hpc](https://github.com/ai-hpc). - Plugins/SDK: add a general `embeddingProviders` capability contract and registration API so embeddings can become a reusable provider surface outside memory-specific adapters. - Dependencies: refresh provider, plugin, UI, and tooling packages, update `protobufjs` to 8.4.0 to clear the current npm advisory, and carry the Claude ACP completion patch forward to `@agentclientprotocol/claude-agent-acp` 0.36.1. - Agents/tools: remove the old sender-owner tool gating path so configured tools stay visible for trusted sessions while command and channel-action auth still carry real sender identity. - QA-Lab: add curated mock JSONL replay fixtures and first-drift reporting for runtime-parity audits. ([#80323](https://github.com/openclaw/openclaw/issues/80323), refs [#80176](https://github.com/openclaw/openclaw/issues/80176)) Thanks [@100yenadmin](https://github.com/100yenadmin). - QA-Lab: add a QA bus tool-trace visibility scenario for sanitized tool-call assertions. - QA-Lab: replace generic evidence framing in seeded scenario prompts with concrete observed QA behavior. - QA-Lab: list named scenario packs in the coverage report so personal-agent privacy coverage stays visible in audits. - QA-Lab: list live transport lane membership in the coverage report so real transport checks stay separate from seeded qa-channel scenarios. - Release/package: run package integrity checks before package acceptance lanes so public install/update validation fails before private QA assets can leak into the package. - QA-Lab: include the optional 100-turn runtime parity soak in release-soak artifacts so long-run Codex/Pi transcript drift stays visible outside the default gate. ([#80395](https://github.com/openclaw/openclaw/issues/80395)) Thanks [@100yenadmin](https://github.com/100yenadmin). - QA-Lab: add a live-only long-context progress watchdog scenario for Codex app-server timeout and stalled-run sentinels. ([#80323](https://github.com/openclaw/openclaw/issues/80323)) Thanks [@100yenadmin](https://github.com/100yenadmin). - QA-Lab: tag gateway restart recovery and streaming final-integrity scenarios as live-only runtime parity lanes. ([#80323](https://github.com/openclaw/openclaw/issues/80323)) Thanks [@100yenadmin](https://github.com/100yenadmin). - QA-Lab: add a personal-agent failure recovery scenario that checks honest partial status, retry boundaries, and local recovery artifacts. ([#83872](https://github.com/openclaw/openclaw/issues/83872)) Thanks [@iFiras-Max1](https://github.com/iFiras-Max1). - QA-Lab: include an opt-in `update.run` package self-upgrade sentinel for destructive latest-package recovery checks. - QA-Lab: add Codex plugin lifecycle and auth-profile fixture coverage for missing installs, pinned-version drift, first-turn install ordering, and doctor migration safety. ([#80323](https://github.com/openclaw/openclaw/issues/80323), refs [#80174](https://github.com/openclaw/openclaw/issues/80174)) Thanks [@100yenadmin](https://github.com/100yenadmin). - Models/perf: pre-warm the provider auth-state map at gateway startup so `/models` and every model-listing call short-circuits the per-provider plugin / external-CLI discovery on the hot path. Per-call cost drops from \~20 s to \~5 ms (\~4,100×); the one-time startup warm resets and re-warms after hot reloads. ([#84816](https://github.com/openclaw/openclaw/issues/84816)) Thanks [@sjf](https://github.com/sjf). - Release/security: ship the root npm package and OpenClaw-owned npm plugins with generated shrinkwrap, support bundled plugin runtime dependencies for suitable plugin tarballs, and require review for lockfile/shrinkwrap changes so published installs use locked dependency graphs. - Tests/perf: isolate doctor core health check unit coverage from real skills/workspace discovery so `doctor-core-checks` no longer dominates unit perf while keeping one real skills-readiness smoke. ([#84493](https://github.com/openclaw/openclaw/issues/84493)) Thanks [@frankekn](https://github.com/frankekn). ##### Fixes - WebChat: summarize internal message-tool source replies so tool cards no longer duplicate the visible reply body. ([#84773](https://github.com/openclaw/openclaw/issues/84773)) Thanks [@jason-allen-oneal](https://github.com/jason-allen-oneal). - Gateway: preserve deferred lifecycle-error cleanup across later non-terminal events so provider timeouts can persist failed session state instead of leaving sessions stuck running. ([#85256](https://github.com/openclaw/openclaw/issues/85256), fixes [#63819](https://github.com/openclaw/openclaw/issues/63819)) Thanks [@samzong](https://github.com/samzong). - Agents/subagents: report tool-only child progress during timeout summaries instead of showing no visible output. - Telegram/ACP: preserve explicit `:topic:` conversation suffixes when inbound ACP targets do not carry a separate thread id. - Browser/proxy: bypass the managed proxy for the exact local managed Chrome CDP readiness and DevTools WebSocket endpoints, so `openclaw browser start` works when the operator proxy blocks loopback egress. ([#83255](https://github.com/openclaw/openclaw/issues/83255)) Thanks [@lightcap](https://github.com/lightcap). - Ollama: bypass the managed proxy for configured local embedding origins while keeping SSRF guardrails on unconfigured targets. Thanks [@Kaspre](https://github.com/Kaspre). - OpenAI/images: route Codex API-key image generation through the native OpenAI Images API instead of the Codex OAuth streaming backend, avoiding 401s from valid API keys. - Agents/OpenAI completions: omit empty tool payload fields for proxy-like OpenAI-compatible endpoints so strict vLLM-style servers accept tool-free turns. ([#85835](https://github.com/openclaw/openclaw/issues/85835)) Thanks [@rendrag-git](https://github.com/rendrag-git). - Checks/Windows: route full `pnpm check` stage commands through the managed child runner so Windows avoids Node shell-argv deprecation warnings there too. - Checks/Windows: run managed child commands through explicit `cmd.exe` wrapping instead of Node shell mode with argv, avoiding Node 24 subprocess deprecation warnings during changed checks. - Gateway: omit internal stream-error placeholder entries from agent prompt history so failed assistant turns are not replayed as model-authored text. ([#85652](https://github.com/openclaw/openclaw/issues/85652)) Thanks [@anyech](https://github.com/anyech). - Sessions: enforce the session write-lock max-hold policy during lock acquisition so long-held locks can be reclaimed before the stale-lock window. ([#85764](https://github.com/openclaw/openclaw/issues/85764)) Thanks [@njuboy11](https://github.com/njuboy11). - Models: prune retired Groq, GitHub Copilot, OpenAI, xAI, and old Claude catalog entries, with doctor migration to upgrade existing configs to current provider refs. - Doctor/update: recognize junction-backed source checkouts as git installs by comparing canonical paths before showing package-manager update guidance. Fixes [#82215](https://github.com/openclaw/openclaw/issues/82215). Thanks [@igormf](https://github.com/igormf). - Channels: honor `/verbose on` for tool/progress summaries across direct chats, groups, channels, and forum topics while preserving quiet default behavior. ([#85488](https://github.com/openclaw/openclaw/issues/85488)) Thanks [@kurplunkin](https://github.com/kurplunkin). - CLI/skills: show an all-ready note with next-step commands when skill setup has no missing dependencies to install. ([#85032](https://github.com/openclaw/openclaw/issues/85032)) Thanks [@aniruddhaadak80](https://github.com/aniruddhaadak80). - Microsoft Foundry: route DeepSeek V4 Pro and Flash models through the Foundry Responses API while keeping older DeepSeek models on their existing path. ([#85549](https://github.com/openclaw/openclaw/issues/85549)) Thanks [@roslinmahmud](https://github.com/roslinmahmud). - Status/usage: show configured cost estimates for AWS SDK models in full usage output while keeping token-only usage replies cost-free. ([#85619](https://github.com/openclaw/openclaw/issues/85619)) Thanks [@ItsOtherMauridian](https://github.com/ItsOtherMauridian). - Agents/OpenAI Responses: retry non-visible reasoning-only turns for OpenAI Responses API families instead of treating them as empty failed turns. ([#85603](https://github.com/openclaw/openclaw/issues/85603)) Thanks [@SebTardif](https://github.com/SebTardif). - Directive tags: preserve message and content-part object identity when display stripping makes no directive-tag changes. ([#85682](https://github.com/openclaw/openclaw/issues/85682)) Thanks [@willamhou](https://github.com/willamhou). - Telegram: send local `path`/`filePath` and structured attachment media from `sendMessage` actions instead of dropping them or sending text-only messages. ([#85219](https://github.com/openclaw/openclaw/issues/85219)) Thanks [@keshavbotagent](https://github.com/keshavbotagent). - Sessions/status: show the estimated context budget when fresh provider usage is unavailable and clear stale estimates across session resets and compaction boundaries. ([#84830](https://github.com/openclaw/openclaw/issues/84830)) Thanks [@giodl73-repo](https://github.com/giodl73-repo). - Gateway/config: pin relative `OPENCLAW_STATE_DIR` overrides to an absolute path at startup so later working-directory changes cannot retarget gateway state. ([#52264](https://github.com/openclaw/openclaw/issues/52264)) Thanks [@PerfectPan](https://github.com/PerfectPan). - Release/package: run npm release, prepublish, and postpublish verification through Windows-safe npm command shims so native Windows checks can execute `npm.cmd` instead of treating it as a binary. - Agents/harness: pass CLI runtime aliases through harness selection so provider-owned CLI aliases no longer get rejected before reaching the right runtime. ([#85631](https://github.com/openclaw/openclaw/issues/85631)) Thanks [@potterdigital](https://github.com/potterdigital). - Secrets: show the irreversible apply warning after interactive `secrets configure` confirmation so confirmed migrations still get the final safety prompt. ([#85638](https://github.com/openclaw/openclaw/issues/85638)) Thanks [@alkor2000](https://github.com/alkor2000). - Agents/CLI output: ignore cumulative Claude `stream-json` result usage when assistant usage events are present, preventing inflated cache-read accounting. ([#85625](https://github.com/openclaw/openclaw/issues/85625)) Thanks [@zhouhe-xydt](https://github.com/zhouhe-xydt). - CLI: keep `waitForever()` alive by leaving its keep-alive interval ref'd so the public helper no longer exits immediately with Node's unsettled-await code. ([#85694](https://github.com/openclaw/openclaw/issues/85694)) Thanks [@m1qaweb](https://github.com/m1qaweb). - Agents/bootstrap: guard bootstrap name checks against missing file names so malformed bootstrap entries warn and truncate instead of crashing. Fixes [#85523](https://github.com/openclaw/openclaw/issues/85523). ([#85615](https://github.com/openclaw/openclaw/issues/85615)) Thanks [@zhouhe-xydt](https://github.com/zhouhe-xydt). - CLI/tasks: reject partially numeric `openclaw tasks audit --limit` values so audit limits must be real positive integers instead of accepting strings like `5abc`. ([#84901](https://github.com/openclaw/openclaw/issues/84901)) Thanks [@jbetala7](https://github.com/jbetala7). - Status/diagnostics: bound deep Docker audit probes so `openclaw status --deep` reports slow container checks instead of hanging behind unbounded inspection. ([#85476](https://github.com/openclaw/openclaw/issues/85476)) Thanks [@giodl73-repo](https://github.com/giodl73-repo). - Providers/Anthropic: migrate 1M context handling to GA-capable Claude 4.x models by sizing eligible models at 1M without the retired `context-1m-2025-08-07` beta, ignoring that retired beta in older configs, and preserving OAuth-required Anthropic beta headers. ([#45613](https://github.com/openclaw/openclaw/issues/45613)) Thanks [@haoyu-haoyu](https://github.com/haoyu-haoyu). - Cron/Telegram: parse forum-topic delivery targets through the Telegram plugin instead of cron core, including `:topic:` and `:topicId` forms for announce delivery. Thanks [@etticat](https://github.com/etticat). - Twitch: keep stale message-handler cleanup callbacks from removing newer handler registrations for the same account, preserving inbound message delivery after reconnects. Fixes [#83888](https://github.com/openclaw/openclaw/issues/83888). ([#85425](https://github.com/openclaw/openclaw/issues/85425)) Thanks [@alkor2000](https://github.com/alkor2000). - Memory/LanceDB: expose public memory artifacts through the active memory provider bridge so memory-wiki imports durable memory files, daily notes, dream reports, and event logs without depending on memory-core internals. Fixes [#83604](https://github.com/openclaw/openclaw/issues/83604). ([#85060](https://github.com/openclaw/openclaw/issues/85060)) Thanks [@brokemac79](https://github.com/brokemac79). - Crabbox: keep AWS hydration compatible with local Actions replay by inlining the hydrate workflow's Node/pnpm setup instead of invoking repo-local composite actions. - Agents/subagents: simplify native sub-agent completion handoff so children report their latest visible assistant result to the requester without using `message`, while keeping parent-owned message-tool delivery policy intact. Fixes [#85070](https://github.com/openclaw/openclaw/issues/85070). ([#85089](https://github.com/openclaw/openclaw/issues/85089)) Thanks [@brokemac79](https://github.com/brokemac79). - Docker setup: stop printing the Gateway bearer token in setup logs and printed follow-up commands. - Agents: let embedded compaction fallback retries proceed when PI-compatible candidates do not need agent harness plugin preparation. - Agents/tools: honor configured custom provider API keys when deciding whether media, image-generation, video-generation, music-generation, and PDF tools are available. ([#85570](https://github.com/openclaw/openclaw/issues/85570)) - StepFun: stop advertising stale generic API key auth choices so onboarding only offers runtime-backed Standard and Step Plan choices. - Diagnostics: keep OpenTelemetry log bodies behind explicit content capture and scrub scoped agent-session keys from OpenTelemetry and Prometheus labels while preserving bounded queue-lane prefixes. - Windows installer: fail Git checkout installs when `pnpm install` or `pnpm build` fails instead of writing a wrapper to a missing CLI build. - Sessions: surface previous-transcript archive failures during `/new` rotation so disk rename errors are logged instead of silently hiding stranded transcript files. Fixes [#81984](https://github.com/openclaw/openclaw/issues/81984). ([#85586](https://github.com/openclaw/openclaw/issues/85586), from [#82081](https://github.com/openclaw/openclaw/issues/82081)) Thanks [@0xghost42](https://github.com/0xghost42). - TUI/agents: mirror internal-ui message-tool replies into final chat output so message-tool-only agents remain visible in `openclaw tui`. Fixes [#85538](https://github.com/openclaw/openclaw/issues/85538). Thanks [@danpolasek](https://github.com/danpolasek). - Agents: keep parallel OpenAI-compatible tool-call deltas in separate argument buffers so interleaved tool calls no longer corrupt streamed arguments. ([#82263](https://github.com/openclaw/openclaw/issues/82263)) Thanks [@luna-system](https://github.com/luna-system). - Memory/doctor: report missing or unusable QMD workspace directories as workspace failures instead of generic binary failures. ([#63167](https://github.com/openclaw/openclaw/issues/63167)) Thanks [@sercada](https://github.com/sercada). - Debug proxy: record CONNECT client-socket errors and destroy the paired upstream socket so abrupt client disconnects no longer leak tunnel resources. ([#82444](https://github.com/openclaw/openclaw/issues/82444)) Thanks [@SebTardif](https://github.com/SebTardif). - Diffs: continue hydrating later diff cards when one card fails so a single broken card no longer blanks the whole diff viewer. ([#84775](https://github.com/openclaw/openclaw/issues/84775)) Thanks [@cosmopolitan033](https://github.com/cosmopolitan033). - Mac app: use the native settings sidebar window chrome so the sidebar toggle stays on the left and content no longer clips under oversized titlebar padding. - QA-Lab/Codex: bundle auth/plugin fixture imports for flow scenarios and let terminal async media tools end Codex app-server turns without timing out. ([#80397](https://github.com/openclaw/openclaw/issues/80397), refs [#80323](https://github.com/openclaw/openclaw/issues/80323)) Thanks [@100yenadmin](https://github.com/100yenadmin). - Gateway/agents: preserve fresh session overrides and metadata when stale cached agent-session entries race with store updates, so subagent model/provider overrides and routing policy survive concurrent writes. ([#19328](https://github.com/openclaw/openclaw/issues/19328)) Thanks [@CodeReclaimers](https://github.com/CodeReclaimers). - Control UI/chat: keep chat session search inline with the session selector so the header no longer shows a duplicate standalone search row. - Control UI/chat: collapse focused-mode header chrome and suppress hidden-header scroll updates so focus mode no longer jumps while scrolling. Thanks [@amknight](https://github.com/amknight). - Codex app-server: restart the native app-server and retry once when server-side compaction times out, so preflight compaction stalls recover instead of failing every dispatch. ([#85500](https://github.com/openclaw/openclaw/issues/85500)) - Restore Control UI gateway token pairing \[AI]. ([#85459](https://github.com/openclaw/openclaw/issues/85459)) Thanks [@pgondhi987](https://github.com/pgondhi987). - OpenAI video: honor configured provider request private-network opt-in for local/custom video endpoints so explicitly trusted mock and self-hosted providers are not blocked. Thanks [@shakkernerd](https://github.com/shakkernerd). - OpenAI video: send uploaded video edit requests to the documented `/videos/edits` endpoint with a `video` file instead of posting MP4 references to `/videos`. Thanks [@shakkernerd](https://github.com/shakkernerd). - Agents/channels: preserve message-tool delivery evidence through gateway agent completion handoffs so successful generated media sends are not followed by false failure messages. Thanks [@shakkernerd](https://github.com/shakkernerd). - CLI/update: repair managed npm plugin `openclaw` peer links during post-core convergence and reject stale or wrong-target peer links before restart. ([#83794](https://github.com/openclaw/openclaw/issues/83794)) Thanks [@fuller-stack-dev](https://github.com/fuller-stack-dev). - CLI/agents: default new omitted-account bindings to all accounts when the channel has multiple configured accounts, and clarify account-scope docs. ([#49769](https://github.com/openclaw/openclaw/issues/49769)) Thanks [@Gcaufy](https://github.com/Gcaufy). - Codex app-server: let authorized `/codex` control commands such as `/codex detach` escape plugin-owned conversation bindings while keeping unknown or unauthorized slash text routed to the bound plugin. Fixes [#85157](https://github.com/openclaw/openclaw/issues/85157). ([#85188](https://github.com/openclaw/openclaw/issues/85188)) Thanks [@TurboTheTurtle](https://github.com/TurboTheTurtle). - Auto-reply/models: keep `/models` browse replies fast by sharing the bounded read-only catalog path with Gateway model listing. ([#84735](https://github.com/openclaw/openclaw/issues/84735)) Thanks [@safrano9999](https://github.com/safrano9999). - Codex app-server: disable native Code Mode when the effective exec host is `node` and keep OpenClaw `exec`/`process` available, so `/exec host=node` routes shell commands through the selected node instead of the gateway. Fixes [#85012](https://github.com/openclaw/openclaw/issues/85012). ([#85090](https://github.com/openclaw/openclaw/issues/85090)) Thanks [@sahilsatralkar](https://github.com/sahilsatralkar). - Agents: bound embedded auto-compaction session write-lock watchdogs to the compaction timeout instead of the full run timeout, so stuck compaction cannot hold the live session lock for the whole run window. ([#84949](https://github.com/openclaw/openclaw/issues/84949)) Thanks [@luoyanglang](https://github.com/luoyanglang). - Gateway/agents: return phase-aware `agent.wait` timeout attribution and only cool auth profiles on provider-started timeouts. Refs [#65504](https://github.com/openclaw/openclaw/issues/65504). Thanks [@100yenadmin](https://github.com/100yenadmin). - Gateway: defer provider auth-state prewarm until after startup readiness so early gateway tool/session requests are not blocked by provider auth discovery. ([#85272](https://github.com/openclaw/openclaw/issues/85272)) Thanks [@dutifulbob](https://github.com/dutifulbob). - Gateway/models: coalesce provider auth-state rewarms after auth-profile failures and log event-loop delay for warm/rewarm work, so provider auth bursts no longer stack full auth sweeps behind channel replies. - Gateway/models: stop cancelled provider auth-state prewarms from continuing full provider sweeps, so reload and auth-failure bursts no longer keep startup busy. - Agents/Codex: show the first plan update as a transient chat status notice without counting it as final assistant content. - CLI/update: walk the macOS process ancestry and honor the inherited Gateway runtime PID before package updates stop the managed Gateway service, so nested in-band updater children can refuse instead of killing the LaunchAgent-supervised Gateway that owns them. Fixes [#85120](https://github.com/openclaw/openclaw/issues/85120). - Gateway/LaunchAgent: wait for launchd reload bootout to finish and fall back to kickstart when bootstrap races, so reload handoff does not leave the service deregistered. Fixes [#84630](https://github.com/openclaw/openclaw/issues/84630). ([#84641](https://github.com/openclaw/openclaw/issues/84641)) Thanks [@NianJiuZst](https://github.com/NianJiuZst). - Gateway/LaunchAgent: treat a concurrent launchd bootstrap as a successful restart when the service is already loaded, avoiding false macOS Gateway restart failures. Fixes [#84721](https://github.com/openclaw/openclaw/issues/84721). ([#84722](https://github.com/openclaw/openclaw/issues/84722)) Thanks [@googlerest](https://github.com/googlerest). - Gateway/service: include the active `openclaw` command bin directory in managed service PATH generation and doctor audit expectations for npm-global macOS installs. Fixes [#84201](https://github.com/openclaw/openclaw/issues/84201). ([#84475](https://github.com/openclaw/openclaw/issues/84475)) Thanks [@jbetala7](https://github.com/jbetala7). - Control UI/chat: disable the thinking selector for known non-reasoning models instead of showing duplicate Off choices. Fixes [#84069](https://github.com/openclaw/openclaw/issues/84069). Thanks [@DrippingMellow](https://github.com/DrippingMellow). - Memory: expand `~` in configured extra memory paths before resolving them, so home-relative folders are not treated as workspace-relative. Fixes [#58026](https://github.com/openclaw/openclaw/issues/58026). Thanks [@stadman](https://github.com/stadman). - Skills: treat `openclaw.os: macos` as Darwin when checking skill requirements, so macOS-only skills no longer report as missing on macOS hosts. Fixes [#61338](https://github.com/openclaw/openclaw/issues/61338). Thanks [@Jessecq1995](https://github.com/Jessecq1995). - Control UI/logs: strip ANSI escape sequences from displayed Gateway log messages so color codes no longer appear as raw text. Fixes [#64399](https://github.com/openclaw/openclaw/issues/64399). Thanks [@guguangxin-eng](https://github.com/guguangxin-eng). - Docker: pre-create the workspace and auth-profile config mount points with `node` ownership so first-run named volumes do not start root-owned. Fixes [#85076](https://github.com/openclaw/openclaw/issues/85076). Thanks [@Noerr](https://github.com/Noerr). - Telegram: pass configured markdown table mode through outbound markdown chunking so chunked sends render tables consistently. Fixes [#85085](https://github.com/openclaw/openclaw/issues/85085). Thanks [@ShuaiHui](https://github.com/ShuaiHui). - CLI/update: preserve managed Gateway service environment during package cutovers so macOS LaunchAgent repair/restart reads the pre-update service state instead of caller shell state. ([#83026](https://github.com/openclaw/openclaw/issues/83026)) - Agents/providers: honor per-model `api` and `baseUrl` overrides in custom provider auth hooks and transport selection. Fixes [#80487](https://github.com/openclaw/openclaw/issues/80487). ([#80488](https://github.com/openclaw/openclaw/issues/80488)) Thanks [@huveewomg](https://github.com/huveewomg). - Gateway/restart: eager-load the lifecycle runtime before in-place upgrade signal handling so package replacement does not deadlock restart imports. ([#84890](https://github.com/openclaw/openclaw/issues/84890)) Thanks [@myps6415](https://github.com/myps6415). - CLI/update: start managed Gateway update handoff helpers from a stable existing directory and tolerate deleted cwd/package roots during macOS LaunchAgent handoff. Fixes [#83808](https://github.com/openclaw/openclaw/issues/83808). ([#83875](https://github.com/openclaw/openclaw/issues/83875)) Thanks [@jason-allen-oneal](https://github.com/jason-allen-oneal). - Skills: watch each shared skill directory once across agent workspaces instead of once per agent, preventing file-descriptor exhaustion (`EMFILE`) that disposed bundle-mcp processes and stalled sessions on multi-agent gateways. Fixes [#84968](https://github.com/openclaw/openclaw/issues/84968). ([#85130](https://github.com/openclaw/openclaw/issues/85130)) Thanks [@openperf](https://github.com/openperf). - Release/security: keep generated npm shrinkwrap package versions inside the pnpm lock graph so published package locks cannot bypass pnpm dependency age and override policy. - Cron: honor `cron.retry.retryOn: ["network"]` for common network error codes such as `EAI_AGAIN`, `EHOSTUNREACH`, and `ENETUNREACH`. - Gateway chat: broadcast returned agent-run error payloads after an agent starts so ACP/WebChat clients receive terminal idle-timeout errors. Fixes [#84945](https://github.com/openclaw/openclaw/issues/84945). - Gateway chat display: preserve OpenAI-compatible `prompt_tokens`, `completion_tokens`, and `total_tokens` usage fields in sanitized chat history so llama.cpp sessions keep context counts. Fixes [#77992](https://github.com/openclaw/openclaw/issues/77992). Thanks [@MarTT79](https://github.com/MarTT79). - Dashboard/CLI: allow macOS browser launching through `open` even when SSH environment variables are present, while preserving Linux SSH no-display protection. Fixes [#67088](https://github.com/openclaw/openclaw/issues/67088). Thanks [@theglove44](https://github.com/theglove44). - Codex app-server: keep native web search observations out of mirrored chat transcripts while preserving tool progress telemetry. Fixes [#85109](https://github.com/openclaw/openclaw/issues/85109). Thanks [@ugitmebaby](https://github.com/ugitmebaby). - OpenCode Go: strip unsupported Kimi reasoning replay fields before provider requests so repeated `kimi-k2.6` turns do not fail schema validation. Fixes [#83812](https://github.com/openclaw/openclaw/issues/83812). Thanks [@Sleeck](https://github.com/Sleeck). - Browser/CDP: add a WSL2 portproxy self-loop hint when Chrome DevTools endpoints accept connections but return an empty HTTP reply. Fixes [#59209](https://github.com/openclaw/openclaw/issues/59209). Thanks [@Owlock](https://github.com/Owlock). - Agents/OpenAI: preserve structured provider error code, type, and redacted body metadata on boundary-aware transport failures. - Doctor/Codex: point native Codex asset warnings at the canonical `openclaw migrate plan codex` preview command. Fixes [#84948](https://github.com/openclaw/openclaw/issues/84948). Thanks [@markoa](https://github.com/markoa). - CLI/models: make `capability model auth logout --agent` remove auth profiles from the selected non-default agent store. Fixes [#85092](https://github.com/openclaw/openclaw/issues/85092). Thanks [@islandpreneur007](https://github.com/islandpreneur007). - Gateway/models: reuse prepared provider auth metadata during model-listing auth checks so repeated lookups avoid broad plugin discovery while preserving synthetic local auth. - CLI/status: suppress systemd user-service setup hints when `openclaw status --deep` can already reach a running Gateway RPC service. Fixes [#85094](https://github.com/openclaw/openclaw/issues/85094). Thanks [@islandpreneur007](https://github.com/islandpreneur007). - CLI/devices: recover local approval when a same-device repair request replaces the request ID being approved. - CLI/agents: retry transient normal-close Gateway handshakes before falling back to embedded `openclaw agent` execution. - CLI/update: keep managed Gateway service stop/restart status lines out of `openclaw update --json` stdout so package-update automation can parse the JSON payload. - Plugins: resolve OpenClaw plugin SDK subpaths for native external plugin runtimes without mutating package installs or broadening process-wide module resolution. - Agents/OpenAI: preserve Responses and Chat Completions `reasoning_tokens` usage metadata without double-counting it in aggregate output tokens. ([#85319](https://github.com/openclaw/openclaw/issues/85319)) - Control UI/chat: convert pasted `data:image/...;base64,...` clipboard text into an image attachment instead of dumping the payload into the composer. Fixes [#62604](https://github.com/openclaw/openclaw/issues/62604). Thanks [@cpwilhelmi](https://github.com/cpwilhelmi). - Providers/Gemini: strip fractional seconds from web-search time range filters so Gemini accepts freshness-bound search requests. ([#85071](https://github.com/openclaw/openclaw/issues/85071)) Thanks [@Noerr](https://github.com/Noerr). - OpenAI Codex: preserve image input support for sparse `openai-codex/gpt-5.5` catalog rows. ([#85095](https://github.com/openclaw/openclaw/issues/85095)) Thanks [@sercada](https://github.com/sercada). - CLI/models: add a piped or pasted API-key path for OpenAI Codex auth and warn when API keys are pasted into token-mode auth. ([#85533](https://github.com/openclaw/openclaw/issues/85533)) Thanks [@joshavant](https://github.com/joshavant). - Telegram: dead-letter missing-harness isolated ingress failures so a poisoned spooled update no longer blocks later same-lane messages. Fixes [#85470](https://github.com/openclaw/openclaw/issues/85470). ([#85605](https://github.com/openclaw/openclaw/issues/85605)) Thanks [@joshavant](https://github.com/joshavant). - Plugins/discovery: strip `-plugin` package suffixes when deriving plugin id hints so package names line up with manifest ids. ([#85170](https://github.com/openclaw/openclaw/issues/85170)) Thanks [@JulyanXu](https://github.com/JulyanXu). - Tlon: stop advertising a non-existent agent tool contract in the plugin manifest. - Telegram: preserve fenced code block languages through Markdown rendering so Telegram receives `language-*` code classes. ([#85209](https://github.com/openclaw/openclaw/issues/85209)) Thanks [@leno23](https://github.com/leno23). - Windows installer: run npm and Corepack command shims from a Windows-local directory so installs launched from WSL2 UNC paths do not fail before OpenClaw is installed. - Windows updates: roll back git-backed updates to the previous checkout when dependency install, build, UI build, or doctor repair fails. - Windows installer: persist user-local portable Git on PATH and activate the repo-pinned pnpm version for git-backed installs and updates. - Windows installer: bootstrap a user-local portable Node.js when native Windows has no Node and no winget, Chocolatey, or Scoop, so first-run installs can continue on raw hosts. - Windows installer: extract the downloaded portable Node.js directory with native `tar` before falling back to .NET zip extraction, avoiding PowerShell 5.1 archive and path-length failures. - fix(integrations): enforce channel read target allowlists \[AI]. ([#84982](https://github.com/openclaw/openclaw/issues/84982)) Thanks [@pgondhi987](https://github.com/pgondhi987). - Agents/heartbeat: route single-owner `session.dmScope=main` direct-message exec and cron event wakes back to the agent main session so async completions no longer strand context in orphan direct-DM queues. Fixes [#71581](https://github.com/openclaw/openclaw/issues/71581). ([#83743](https://github.com/openclaw/openclaw/issues/83743)) Thanks [@Kaspre](https://github.com/Kaspre). - Agents/code-mode: expose outer code-mode `exec` source through the `command` hook alias with `toolKind`/`toolInputKind` discriminators so exec-shaped policies can distinguish code-mode cells. ([#83483](https://github.com/openclaw/openclaw/issues/83483)) Thanks [@Kaspre](https://github.com/Kaspre). - Agents/code mode: return structured timeout and runtime-unavailable error codes for known worker failures. Fixes [#83389](https://github.com/openclaw/openclaw/issues/83389). ([#83444](https://github.com/openclaw/openclaw/issues/83444)) Thanks [@Kaspre](https://github.com/Kaspre). - QA-Lab: isolate multi-scenario suite workers when scenarios need startup config patches, preventing message-routing config from leaking into unrelated scenarios. - QA-Lab: make the commitments heartbeat-target-none scenario request an immediate heartbeat instead of waiting for the next scheduled heartbeat. - Codex/Plugin SDK: deliver Codex-native subagent completions through a generic harness task runtime so harness-backed plugins can mirror durable task lifecycle and completion delivery without Codex-specific SDK imports. ([#83445](https://github.com/openclaw/openclaw/issues/83445)) Thanks [@bryanpearson](https://github.com/bryanpearson). - Gateway CLI: surface local post-challenge connect assembly failures immediately instead of waiting for the wrapper timeout. Fixes [#68944](https://github.com/openclaw/openclaw/issues/68944). ([#85253](https://github.com/openclaw/openclaw/issues/85253)) Thanks [@samzong](https://github.com/samzong). - Messages: strip unsupported web-search citation control markers from outbound replies before they reach WebChat or external channels. Fixes [#85193](https://github.com/openclaw/openclaw/issues/85193). ([#85204](https://github.com/openclaw/openclaw/issues/85204)) Thanks [@neeravmakwana](https://github.com/neeravmakwana). - Agents/exec: treat denied exec approvals as terminal instead of feeding them back into agent follow-up work, and recognize Chinese stop phrases in abort handling. Fixes [#69386](https://github.com/openclaw/openclaw/issues/69386). ([#85194](https://github.com/openclaw/openclaw/issues/85194)) Thanks [@samzong](https://github.com/samzong). - CLI/agents: abort accepted Gateway-backed `openclaw agent` runs on SIGINT/SIGTERM so cron and supervisor timeouts do not leave remote agent work alive. Fixes [#71710](https://github.com/openclaw/openclaw/issues/71710). ([#84381](https://github.com/openclaw/openclaw/issues/84381)) Thanks [@Kaspre](https://github.com/Kaspre). - Codex app-server: retry replay-safe stdio client-close turns once using structured failure metadata, while surfacing idle `turn/completed` timeouts instead of blindly replaying active shared-server turns. Thanks [@VACInc](https://github.com/VACInc). - Codex app-server: reject command overrides that embed Node or package-manager arguments and point users to `appServer.args`, so Windows startup avoids shell parsing failures. ([#84417](https://github.com/openclaw/openclaw/issues/84417)) Thanks [@TurboTheTurtle](https://github.com/TurboTheTurtle). - Agents/Copilot: drop unsafe GitHub Copilot Responses reasoning replay items before send so Telegram direct sessions no longer fail on overlong replay IDs. Fixes [#85197](https://github.com/openclaw/openclaw/issues/85197). ([#85198](https://github.com/openclaw/openclaw/issues/85198)) Thanks [@galiniliev](https://github.com/galiniliev). - UI: add accessible tooltips to the topbar color-mode buttons so System, Light, and Dark choices are labeled on hover and focus. ([#85227](https://github.com/openclaw/openclaw/issues/85227)) Thanks [@amknight](https://github.com/amknight). - fix: constrain Windows task script names \[AI]. ([#85064](https://github.com/openclaw/openclaw/issues/85064)) Thanks [@pgondhi987](https://github.com/pgondhi987). - Control UI: keep the chat session picker from hiding older or cross-agent configured conversations while preserving the bounded configured-agent refresh. ([#85211](https://github.com/openclaw/openclaw/issues/85211)) Thanks [@amknight](https://github.com/amknight). - Agents/Anthropic: preserve unsafe integer tool-call input values in streamed Anthropic tool-use JSON, preventing Discord-style IDs from being rounded before dispatch. Fixes [#47229](https://github.com/openclaw/openclaw/issues/47229). ([#83063](https://github.com/openclaw/openclaw/issues/83063)) Thanks [@leno23](https://github.com/leno23). - Agents/Codex: estimate tool-heavy prompt pressure at the LLM boundary before provider submission, so persistent sessions compact before overflowing context windows. ([#85541](https://github.com/openclaw/openclaw/issues/85541)) Thanks [@fuller-stack-dev](https://github.com/fuller-stack-dev) and [@joshavant](https://github.com/joshavant). - Agents/hooks: wait for local one-shot CLI and Codex `agent_end` plugin hooks before process cleanup so terminal observability flushes reliably. ([#85007](https://github.com/openclaw/openclaw/issues/85007)) - Providers/Google: preserve Gemini 3 cron `thinkingDefault: "low"` when stale catalog metadata says `reasoning:false`, so scheduled runs keep provider-supported thinking instead of downgrading to off. ([#85185](https://github.com/openclaw/openclaw/issues/85185)) Thanks [@neeravmakwana](https://github.com/neeravmakwana). - CLI/agents: allow `openclaw agent --session-key` to target explicit session keys, including agent-scoped legacy keys. ([#85121](https://github.com/openclaw/openclaw/issues/85121)) Thanks [@Kaspre](https://github.com/Kaspre). - Auto-reply/ACP: wait for same-channel block reply delivery before starting tool work, while still honoring ACP dispatch aborts so stopped turns do not wait on slow channel sends. ([#83722](https://github.com/openclaw/openclaw/issues/83722)) Thanks [@IWhatsskill](https://github.com/IWhatsskill). - Codex/ACP: mark required child-run completions that only report progress, omit a final deliverable, or fail requester delivery as blocked while preserving real final reports. ([#85110](https://github.com/openclaw/openclaw/issues/85110)) Thanks [@IWhatsskill](https://github.com/IWhatsskill). - Channels: treat bare abort messages such as `stop`, `abort`, and `wait` as immediate control commands in inbound debounce paths so stop requests are not delayed behind pending message coalescing. ([#83348](https://github.com/openclaw/openclaw/issues/83348)) Thanks [@IWhatsskill](https://github.com/IWhatsskill). - Channels/message tool: resolve configured external channel plugins during in-agent channel selection, so `openclaw agent --local` message-tool sends no longer report an available channel as unavailable. ([#85022](https://github.com/openclaw/openclaw/issues/85022)) Thanks [@Kaspre](https://github.com/Kaspre). - Agents/heartbeat: honor group/channel `message_tool` visible-reply policy and model-specific Codex runtime config for scheduled heartbeat runs, so failed internal tool output stays private. Fixes [#85310](https://github.com/openclaw/openclaw/issues/85310). ([#85357](https://github.com/openclaw/openclaw/issues/85357)) Thanks [@neeravmakwana](https://github.com/neeravmakwana). - Gateway/ACP: close child ACP sessions spawned via `sessions_spawn` when their parent session is reset or deleted, instead of leaving orphaned `claude-agent-acp` processes that accumulate and exhaust memory. Fixes [#68916](https://github.com/openclaw/openclaw/issues/68916). ([#85190](https://github.com/openclaw/openclaw/issues/85190)) Thanks [@openperf](https://github.com/openperf). - Codex app-server: block native execution paths when OpenClaw exec resolves to a node host while preserving the first-party CLI node binding path. Fixes [#85012](https://github.com/openclaw/openclaw/issues/85012). ([#85534](https://github.com/openclaw/openclaw/issues/85534)) Thanks [@joshavant](https://github.com/joshavant). - Diagnostics: bound cleanup timeout detail logs, emit drop summaries when async diagnostic bursts exceed the queue cap, and surface async queue drops through diagnostic telemetry. - Agents/subagents: surface blocked child-run completions as errors instead of successful subagent finishes. ([#80886](https://github.com/openclaw/openclaw/issues/80886)) Thanks [@TurboTheTurtle](https://github.com/TurboTheTurtle). - Context engines: fail closed with a descriptive error when the selected agent runtime cannot satisfy declared context-engine host requirements. - Agents/Pi: treat accepted embedded `sessions_spawn` child-session handoffs as terminal progress so parent turns no longer report false non-deliverable failures. ([#85054](https://github.com/openclaw/openclaw/issues/85054)) Thanks [@samzong](https://github.com/samzong). - CLI/models: resolve `openclaw models set` aliases from the runtime config while keeping authored aliases ahead of runtime-only defaults. ([#83262](https://github.com/openclaw/openclaw/issues/83262)) Thanks [@IWhatsskill](https://github.com/IWhatsskill). - Doctor: show personal Codex CLI asset notices as info instead of warnings. Fixes [#84859](https://github.com/openclaw/openclaw/issues/84859). - WhatsApp: update Baileys to `7.0.0-rc13` and drop the obsolete logger type patch. - CLI/update: pre-pack GitHub/git package update targets before the staged npm install, restoring `openclaw update --tag main` for one-off package updates. ([#81296](https://github.com/openclaw/openclaw/issues/81296)) Thanks [@fuller-stack-dev](https://github.com/fuller-stack-dev). - Gateway: mirror successful same-source message-tool sends into session transcripts so delivered replies stay in later history/context. ([#84837](https://github.com/openclaw/openclaw/issues/84837)) Thanks [@iFiras-Max1](https://github.com/iFiras-Max1). - Media generation: keep image, music, and video completion delivery from duplicating or losing task ownership when generated media finishes through active session replies. ([#84006](https://github.com/openclaw/openclaw/issues/84006)) Thanks [@fuller-stack-dev](https://github.com/fuller-stack-dev). - Infra/json: retry transient `File changed during read` races while loading JSON state so config and state reads recover instead of failing the turn. ([#84285](https://github.com/openclaw/openclaw/issues/84285)) - Plugins/providers: fail closed for workspace provider plugins during setup-mode discovery unless explicitly trusted, preventing untrusted workspace plugin code from running during provider setup. ([#81069](https://github.com/openclaw/openclaw/issues/81069)) Thanks [@mmaps](https://github.com/mmaps). - Providers/Ollama: resolve configured Ollama Cloud `OLLAMA_API_KEY` markers to the real discovery key so cloud provider entries keep authenticated model catalog access. ([#85037](https://github.com/openclaw/openclaw/issues/85037)) - Discord: keep persistent component registry fallback warnings actionable by forwarding structured error and cause metadata through the runtime logger. Fixes [#84185](https://github.com/openclaw/openclaw/issues/84185). ([#84190](https://github.com/openclaw/openclaw/issues/84190)) Thanks [@100menotu001](https://github.com/100menotu001). - Gateway/sessions: preserve compatible session auth profile overrides when switching models within the same provider, including provider-auth aliases. Fixes [#81837](https://github.com/openclaw/openclaw/issues/81837). ([#81886](https://github.com/openclaw/openclaw/issues/81886)) Thanks [@TurboTheTurtle](https://github.com/TurboTheTurtle). - Gateway/status: surface inbound delivery telemetry counters and transport-liveness warnings in `openclaw status --all`. Fixes [#49577](https://github.com/openclaw/openclaw/issues/49577). ([#72724](https://github.com/openclaw/openclaw/issues/72724)) - Docker: prune package-excluded plugin source workspaces and dependency closures so runtime images do not keep packages for plugins that were not opted in. - Providers/Ollama: treat Docker/OrbStack host aliases as local Ollama endpoints so `ollama-local` marker auth works when OpenClaw runs inside a VM/container and Ollama runs on the host. Fixes [#84875](https://github.com/openclaw/openclaw/issues/84875). - QA-Lab: keep explicitly searchable/deferred OpenClaw dynamic tool rows report-only by default so tool-coverage gates do not treat mock discovery gaps as hard product failures. ([#80319](https://github.com/openclaw/openclaw/issues/80319)) Thanks [@100yenadmin](https://github.com/100yenadmin). - Agents/config: keep non-Google provider model refs from being rewritten by Google Gemini preview-id normalization. ([#84762](https://github.com/openclaw/openclaw/issues/84762)) Thanks [@zhangguiping-xydt](https://github.com/zhangguiping-xydt). - Installer: require a real controlling terminal before launching onboarding so headless `curl | bash` installs finish cleanly after installing the CLI. - Agents/Codex: promote a completed final assistant response when a prompt timeout races Codex app-server completion instead of returning an empty timeout envelope. Refs [#84516](https://github.com/openclaw/openclaw/issues/84516). - Codex app-server: keep interrupted turn statuses from being treated as OpenClaw aborts by themselves, so tool-only turns remain eligible for no-visible-answer recovery. Fixes [#84492](https://github.com/openclaw/openclaw/issues/84492). - Agents: cap heartbeat model bleed context hints by the stored session window when runtime model metadata is unavailable, so overflow recovery advice does not suggest a larger window than the active session actually has. - Control UI/Web Push: use `https://openclaw.ai` as the generated default VAPID subject instead of the old localhost mailbox so iOS PWA push setup uses an Apple-acceptable subject when `OPENCLAW_VAPID_SUBJECT` is unset. Fixes [#83134](https://github.com/openclaw/openclaw/issues/83134). ([#83317](https://github.com/openclaw/openclaw/issues/83317)) Thanks [@IWhatsskill](https://github.com/IWhatsskill). - Control UI: distinguish inherited thinking-off settings from explicit Off selections so the thinking selector no longer shows two identical Off rows. ([#85223](https://github.com/openclaw/openclaw/issues/85223)) Thanks [@amknight](https://github.com/amknight). - Agents/Pi: keep embedded session transcript writes from tripping false takeover detection after packaged npm onboarding agent turns. - Codex/TUI: surface Codex-native post-turn compaction failures instead of continuing uncompacted, and keep successful native compaction serialized before local idle/next-turn handling. Fixes [#84305](https://github.com/openclaw/openclaw/issues/84305). ([#85160](https://github.com/openclaw/openclaw/issues/85160)) Thanks [@joshavant](https://github.com/joshavant). - Memory/search: stop recall tracking from writing dreaming side-effect artifacts when `dreaming.enabled=false`, while preserving normal search results. Fixes [#84436](https://github.com/openclaw/openclaw/issues/84436). ([#84444](https://github.com/openclaw/openclaw/issues/84444)) Thanks [@NianJiuZst](https://github.com/NianJiuZst). - Diffs: render viewer toolbar icons from a closed icon-name map instead of HTML strings, removing the toolbar icon XSS sink. ([#83955](https://github.com/openclaw/openclaw/issues/83955)) Thanks [@tanshanshan](https://github.com/tanshanshan). - QA: keep `pnpm qa:e2e` self-check runs inside the private QA runtime envelope even when inherited shell env disables bundled plugins. - fix(config): validate browser sandbox bind sources \[AI]. ([#84799](https://github.com/openclaw/openclaw/issues/84799)) Thanks [@pgondhi987](https://github.com/pgondhi987). - doctor: constrain legacy plugin cleanup paths \[AI]. ([#84801](https://github.com/openclaw/openclaw/issues/84801)) Thanks [@pgondhi987](https://github.com/pgondhi987). - Update/doctor: prune stale local bundled plugin install records that point at old compiled bundled output so current bundled plugin schemas win after upgrade. ([#84863](https://github.com/openclaw/openclaw/issues/84863)) Thanks [@fuller-stack-dev](https://github.com/fuller-stack-dev). - Providers/Ollama: preserve native Ollama tool-call IDs across assistant replay so Gemini over Ollama Cloud can keep its hidden function-call thought-signature handle. - Discord: keep session recovery and `/stop` abort ownership on the source dispatch lane while bound ACP turns continue routing to their target session, so stalled pre-run work and late replies are cleared instead of leaking after stop. Fixes [#84477](https://github.com/openclaw/openclaw/issues/84477). ([#85100](https://github.com/openclaw/openclaw/issues/85100)) Thanks [@joshavant](https://github.com/joshavant). - Codex app-server: mark missing turn completion after observed execution as replay-unsafe and release the session so follow-up turns can run. Fixes [#84076](https://github.com/openclaw/openclaw/issues/84076). ([#85107](https://github.com/openclaw/openclaw/issues/85107)) Thanks [@joshavant](https://github.com/joshavant). - Codex app-server: give visible `message` dynamic tool sends a longer timeout budget so slow channel delivery can return its own result or error instead of hitting the 30-second Codex wrapper. ([#85216](https://github.com/openclaw/openclaw/issues/85216)) Thanks [@amknight](https://github.com/amknight). - Codex app-server: add a dedicated post-tool raw assistant completion idle timeout config so trusted heavy turns can wait longer after tool handoff without weakening final assistant release. - Matrix: keep explicitly configured two-person rooms on the room route before stale `m.direct` or strict two-member DM fallback can bypass mention gating. Fixes [#85017](https://github.com/openclaw/openclaw/issues/85017). ([#85137](https://github.com/openclaw/openclaw/issues/85137)) Thanks [@joshavant](https://github.com/joshavant). - Agents/subagents: require explicit subagent allowlist targets to be configured agents so stale deleted-agent ids are omitted from `agents_list` and rejected by `sessions_spawn`. Fixes [#84811](https://github.com/openclaw/openclaw/issues/84811). ([#85154](https://github.com/openclaw/openclaw/issues/85154)) Thanks [@joshavant](https://github.com/joshavant). - PDF tool: time out idle remote PDF body reads after 120 seconds so stalled remote documents return an error instead of wedging the session. Fixes [#68649](https://github.com/openclaw/openclaw/issues/68649). ([#84768](https://github.com/openclaw/openclaw/issues/84768)) Thanks [@luoyanglang](https://github.com/luoyanglang). - Diagnostics/OpenTelemetry plugin: suppress handled OTLP exporter promise rejections so collector shutdowns no longer crash the Gateway. ([#81085](https://github.com/openclaw/openclaw/issues/81085)) Thanks [@luoyanglang](https://github.com/luoyanglang). - Agents/exec: omit raw command text and env values from denied exec failure logs while keeping safe correlation metadata. Fixes [#85049](https://github.com/openclaw/openclaw/issues/85049). ([#85140](https://github.com/openclaw/openclaw/issues/85140)) Thanks [@joshavant](https://github.com/joshavant). - Media/audio: skip empty structured sherpa-onnx transcripts instead of treating the raw JSON payload as spoken text. ([#84667](https://github.com/openclaw/openclaw/issues/84667)) Thanks [@TurboTheTurtle](https://github.com/TurboTheTurtle). - Agents/exec: preserve inherited XDG base-directory environment values for subprocesses while still rejecting agent-supplied XDG overrides. Fixes [#84854](https://github.com/openclaw/openclaw/issues/84854). ([#85139](https://github.com/openclaw/openclaw/issues/85139)) Thanks [@joshavant](https://github.com/joshavant). - Node/Linux: keep `OPENCLAW_GATEWAY_TOKEN` out of generated systemd unit files by writing node service token values to a node-specific env file. ([#84408](https://github.com/openclaw/openclaw/issues/84408)) - Memory-core/dreaming: reuse stable narrative subagent session keys per workspace and phase while keeping per-run idempotency and bounded cleanup, so stale `dreaming-narrative-*` sessions do not accumulate. Fixes [#68252](https://github.com/openclaw/openclaw/issues/68252), [#69187](https://github.com/openclaw/openclaw/issues/69187), and [#70402](https://github.com/openclaw/openclaw/issues/70402). ([#70464](https://github.com/openclaw/openclaw/issues/70464)) Thanks [@chiyouYCH](https://github.com/chiyouYCH). - Trajectory/support: tol…

openclaw-barnacle Bot added agents Agent runtime and tooling size: S maintainer Maintainer-authored PR labels May 22, 2026

galiniliev self-assigned this May 22, 2026

clawsweeper Bot mentioned this pull request May 22, 2026

[Bug]: Telegram direct replay can send overlong Copilot reasoning item IDs #85197

Closed

fix(agents): defer Copilot reasoning replay ID cleanup

62575c1

galiniliev force-pushed the bug-034-telegram-copilot-reasoning-ids branch from 8a0a5c7 to 62575c1 Compare May 22, 2026 03:53

galiniliev changed the title ~~fix(agents): hash oversized Responses reasoning replay IDs~~ fix(agents): defer Copilot reasoning replay ID cleanup May 22, 2026

fix: drop unsafe copilot reasoning replay ids

9a42f9e

galiniliev changed the title ~~fix(agents): defer Copilot reasoning replay ID cleanup~~ fix(agents): drop unsafe Copilot reasoning replay IDs May 22, 2026

galiniliev closed this May 22, 2026

fanyangCS mentioned this pull request Jun 21, 2026

github-copilot/gpt-5.5 still persists/replays thinkingSignature encrypted_content after #84367/#90682/#92941, causing channel/direct LLM request failed #95441

Closed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Uh oh!

fix(agents): drop unsafe Copilot reasoning replay IDs#85198

fix(agents): drop unsafe Copilot reasoning replay IDs#85198
galiniliev wants to merge 2 commits into
openclaw:mainfrom
galiniliev:bug-034-telegram-copilot-reasoning-ids

galiniliev commented May 22, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented May 22, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented May 22, 2026 •

edited

Loading

Uh oh!

galiniliev commented May 22, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

Uh oh!

Uh oh!

Conversation

galiniliev commented May 22, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Motivation

Change Type (select all)

Scope (select all touched areas)

Linked Issue/PR

Real behavior proof (required for external PRs)

Root Cause (if applicable)

Regression Test Plan (if applicable)

User-visible / Behavior Changes

Diagram (if applicable)

Security Impact (required)

Repro + Verification

Environment

Steps

Expected

Actual

Evidence

Human Verification (required)

Review Conversations

Compatibility / Migration

Risks and Mitigations

Uh oh!

clawsweeper Bot commented May 22, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

clawsweeper Bot commented May 22, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Hatch command

Uh oh!

galiniliev commented May 22, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

galiniliev commented May 22, 2026 •

edited

Loading

clawsweeper Bot commented May 22, 2026 •

edited

Loading

clawsweeper Bot commented May 22, 2026 •

edited

Loading