[Fix] Preserve deferred lifecycle errors by samzong · Pull Request #85256 · openclaw/openclaw

samzong · 2026-05-22T06:35:26Z

Summary

Problem: Gateway lifecycle errors can be deferred during the retry grace window, then a later non-terminal event can clear the only pending terminal cleanup timer.
Solution: Store pending terminal lifecycle errors with their timer, event, and options, and cancel them only when the run actually restarts with lifecycle start.
What changed: Added focused regression coverage for error -> tool -> grace expires and error -> start retry ordering.
What did NOT change (scope boundary): No Telegram, provider, watchdog, stale-row recovery, or channel-specific behavior changed.

Motivation

Closes [Bug]: Session stuck in "running" status persists in v2026.4.9 — phaseBeforeAbort fix no longer sufficient #63819. Provider timeouts can leave gateway sessions stuck in running; this fixes the lifecycle state transition that drops the terminal cleanup.

Change Type (select all)

Scope (select all touched areas)

Linked Issue/PR

Closes [Bug]: Session stuck in "running" status persists in v2026.4.9 — phaseBeforeAbort fix no longer sufficient #63819
This PR fixes a bug or regression

Real behavior proof (required for external PRs)

Behavior addressed: A Gateway run that emits lifecycle error, then later emits a non-terminal event, still reaches terminal cleanup after the retry grace window instead of remaining running.
Real environment tested: Maintainer local OpenClaw source checkout on macOS 26.4.1 with Node v25.9.0; real Gateway process started on loopback with an isolated OPENCLAW_CONFIG_PATH, isolated OPENCLAW_STATE_DIR, and isolated sessions.json.
Exact steps or command run after this patch: Ran a one-off Node script through node --import tsx --input-type=module that started startGatewayServer(...), registered a run context for agent:main:main, emitted lifecycle:start, lifecycle:error, then tool:end, waited for the 15s Gateway retry grace, and read the persisted session store from disk.
Evidence after fix: Terminal output from the real Gateway run:

openclaw real gateway lifecycle proof
gateway.process: started on 127.0.0.1:64575
event.path: real gateway agent-event subscription
event.order: lifecycle:start -> lifecycle:error -> tool:end
session.store: isolated sessions.json
session.key: agent:main:main
session.status.after.grace: failed
session.endedAt.persisted: true
session.runtimeMs.persisted: true
run.context.after.grace: cleared
result: PASS

Observed result after fix: The running Gateway kept the deferred lifecycle error through the later tool event, persisted agent:main:main as failed, recorded terminal timing fields, and cleared the run context after the grace window.
What was not tested: Live Telegram plus llama.cpp transport; this proof exercises the Gateway lifecycle/event persistence path directly.
Before evidence: The new regression failed on the old implementation with TypeError: Cannot read properties of undefined (reading 'state') because no final error payload was emitted after the later tool event cleared the pending timer.

Root Cause (if applicable)

Root cause: pendingTerminalLifecycleErrors stored only a timer, and the handler cleared that timer for any event that was not lifecycle error.
Missing detection / guardrail: Existing tests covered grace-expiry cleanup and fallback recovery, but not lifecycle error followed by a later non-terminal event with no lifecycle end.
Contributing context (if known): Retry grace handling needs to distinguish a real retry lifecycle start from ordinary tool/item/assistant events for the same run.

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/gateway/server-chat.agent-events.test.ts
Scenario the test should lock in: lifecycle error schedules terminal cleanup; a later tool event does not cancel it; a later lifecycle start still cancels it as a retry.
Why this is the smallest reliable guardrail: The bug is entirely in gateway agent-event lifecycle ordering; no channel/provider transport participates in the state transition.
Existing test that already covers this (if any): None covered this exact event ordering.
If no new test is added, why not: New tests are added.

User-visible / Behavior Changes

Gateway sessions are less likely to remain stuck in running after provider timeout/error ordering where non-terminal events arrive after lifecycle error.

Diagram (if applicable)

Before:
lifecycle start -> lifecycle error -> tool result -> pending terminal cleanup cleared -> session can stay running

After:
lifecycle start -> lifecycle error -> tool result -> grace expires -> terminal cleanup persists failed state

Security Impact (required)

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

Repro + Verification

Environment

OS: macOS 26.4.1
Runtime/container: Node v25.9.0, local source checkout
Model/provider: N/A
Integration/channel (if any): Gateway lifecycle handler
Relevant config (redacted): N/A

Steps

Emit lifecycle start.
Emit lifecycle error with retry grace enabled.
Emit a later non-terminal tool event for the same run.
Advance the retry grace timer.

Expected

Terminal error cleanup runs and the session can persist a failed terminal state.

Actual

Before this patch, the later non-terminal event cleared the only pending terminal cleanup timer.
After this patch, the terminal cleanup remains pending and runs after the grace window.

Evidence

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

Human Verification (required)

Verified scenarios: error -> tool -> grace expires; error -> start retry; existing lifecycle chat/fallback behavior in server-chat.agent-events.test.ts; real Gateway agent-event subscription persisted failed to an isolated sessions.json after the 15s grace.
Edge cases checked: Timer replacement guard, restart cancellation, persistence of terminal error after delayed cleanup.
What you did not verify: Live Telegram plus llama.cpp timeout path.

Compatibility / Migration

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

Risks and Mitigations

Risk: A recoverable retry attempt could be finalized too early.
- Mitigation: The fix keeps lifecycle start as the cancellation signal and adds regression coverage that restart still cancels the deferred error.

clawsweeper · 2026-05-22T06:37:11Z

Codex review: needs maintainer review before merge.

Latest ClawSweeper review: 2026-05-22 08:20 UTC / May 22, 2026, 4:20 AM ET.

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 PR stores pending gateway lifecycle errors as timer/event/options records, narrows cancellation to non-error lifecycle phases, and adds regression tests for error-to-tool, phase-less lifecycle, fallback, and retry-start ordering.

Reproducibility: yes. at source level. Current main schedules deferred cleanup for lifecycle errors but clears the only pending timer on later non-error events; the PR adds direct regression coverage and copied real Gateway output for the error -> tool -> grace path.

PR rating
Overall: 🐚 platinum hermit
Proof: 🦞 diamond lobster
Patch quality: 🐚 platinum hermit
Summary: The PR has solid live Gateway proof and focused regression coverage, with remaining confidence mainly dependent on current-head CI because this review did not run tests.

Rank-up moves:

Run node scripts/run-vitest.mjs src/gateway/server-chat.agent-events.test.ts on the current head before merge.

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 copied live terminal output from a real loopback Gateway run showing lifecycle:start -> lifecycle:error -> tool:end persists failed, records terminal timing, and clears run context after the grace window.

Risk before merge

I did not execute the targeted Vitest file in this read-only review checkout, so CI or a maintainer-run node scripts/run-vitest.mjs src/gateway/server-chat.agent-events.test.ts should still prove the current head.

Maintainer options:

Decide the mitigation before merge
Keep the structured pending-error record and lifecycle-only cancellation predicate, then land after current-head gateway lifecycle tests and normal maintainer review pass.
Pause or close
Do not merge this PR until maintainers decide whether the risk is worth taking.

Next step before merge
No ClawSweeper repair lane is needed; the remaining action is maintainer review and current-head validation after the author's follow-up commit appears to resolve the earlier blocking finding.

Security
Cleared: The diff only changes in-process gateway lifecycle timer bookkeeping and tests; it adds no dependencies, permissions, network calls, secret handling, or code-execution surface.

Review details

Best possible solution:

Keep the structured pending-error record and lifecycle-only cancellation predicate, then land after current-head gateway lifecycle tests and normal maintainer review pass.

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

Yes, at source level. Current main schedules deferred cleanup for lifecycle errors but clears the only pending timer on later non-error events; the PR adds direct regression coverage and copied real Gateway output for the error -> tool -> grace path.

Is this the best way to solve the issue?

Yes. Storing the original terminal lifecycle event and options with the timer, then canceling only on non-error lifecycle continuation phases, is a narrow maintainable fix that preserves fallback while preventing ordinary tool/assistant events from erasing cleanup.

Label changes:

add proof: sufficient: Contributor real behavior proof is sufficient. The PR body includes copied live terminal output from a real loopback Gateway run showing lifecycle:start -> lifecycle:error -> tool:end persists failed, records terminal timing, and clears run context after the grace window.
add rating: 🐚 platinum hermit: Current PR rating is 🐚 platinum hermit because proof is 🦞 diamond lobster, patch quality is 🐚 platinum hermit, and The PR has solid live Gateway proof and focused regression coverage, with remaining confidence mainly dependent on current-head CI because this review did not run tests.
add status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Sufficient (live_output): The PR body includes copied live terminal output from a real loopback Gateway run showing lifecycle:start -> lifecycle:error -> tool:end persists failed, records terminal timing, and clears run context after the grace window.
remove rating: 🧂 unranked krab: Current PR rating is rating: 🐚 platinum hermit, so this older rating label is no longer current.
remove merge-risk: 🚨 session-state: Current PR review selected no merge-risk labels.
remove merge-risk: 🚨 message-delivery: Current PR review selected no merge-risk labels.
remove status: ⏳ waiting on author: Current PR status label is status: 👀 ready for maintainer look.

Label justifications:

P1: The PR targets a high-impact gateway lifecycle regression that can leave sessions stuck running and block follow-up messages after provider timeouts.
rating: 🐚 platinum hermit: Current PR rating is 🐚 platinum hermit because proof is 🦞 diamond lobster, patch quality is 🐚 platinum hermit, and The PR has solid live Gateway proof and focused regression coverage, with remaining confidence mainly dependent on current-head CI because this review did not run tests.
status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Sufficient (live_output): The PR body includes copied live terminal output from a real loopback Gateway run showing lifecycle:start -> lifecycle:error -> tool:end persists failed, records terminal timing, and clears run context after the grace window.
proof: sufficient: Contributor real behavior proof is sufficient. The PR body includes copied live terminal output from a real loopback Gateway run showing lifecycle:start -> lifecycle:error -> tool:end persists failed, records terminal timing, and clears run context after the grace window.

Acceptance criteria:

node scripts/run-vitest.mjs src/gateway/server-chat.agent-events.test.ts

What I checked:

Current main bug shape: Current main stores only a timeout for pending terminal lifecycle errors and clears that timer for any later event except a lifecycle error, so a later tool or assistant event can erase the deferred terminal cleanup. (src/gateway/server-chat.ts:232, 192a782b99de)
Patch cancellation predicate: The final PR patch changes the pending-error clear predicate to lifecyclePhase !== null && lifecyclePhase !== "error", which preserves deferred cleanup across non-lifecycle events while still canceling on fallback/start/end-style lifecycle continuations. (src/gateway/server-chat.ts:814, f4f945f814a4)
Patch regression coverage: The PR adds focused tests for lifecycle error followed by tool, phase-less lifecycle events, retry start cancellation, and fallback continuing beyond the retry grace without premature error finalization. (src/gateway/server-chat.agent-events.test.ts:2050, f4f945f814a4)
Fallback contract in current tests: Current main already models error -> fallback -> end as a live continuation path that should preserve chat run remapping and avoid an error final state before the eventual lifecycle end. (src/gateway/server-chat.agent-events.test.ts:2006, 192a782b99de)
Related issue context: The linked open issue [Bug]: Session stuck in "running" status persists in v2026.4.9 — phaseBeforeAbort fix no longer sufficient #63819 reports sessions stuck in running after provider timeouts, matching the gateway lifecycle cleanup path changed by this PR.
Prior review finding addressed: The earlier ClawSweeper comment flagged start-only cancellation as a fallback regression; the second PR commit changes the predicate so lifecycle fallback-style events cancel the deferred terminal error. (src/gateway/server-chat.ts:814, f4f945f814a4)

Likely related people:

samzong: GitHub commit history for the touched gateway files shows prior merged work on agent event fanout and incremental chat delta payloads, so the current PR author also has prior main-branch history in this path. (role: recent gateway event contributor; confidence: high; commits: bb8aa0cfe2b0, 10315ce21593; files: src/gateway/server-chat.ts, src/gateway/server-chat.agent-events.test.ts)
steipete: Recent commits on src/gateway/server-chat.ts and related session-state behavior include v4 chat delta and gateway test work in the same event handling surface. (role: recent gateway/session-state contributor; confidence: high; commits: a6497b175905, 150bebcd0ce7, c3c451094282; files: src/gateway/server-chat.ts, src/gateway/server-chat.agent-events.test.ts)
jalehman: History for the gateway event files shows review/coauthor involvement on recent agent event fanout work plus adjacent chat/tool display and replay fixes. (role: reviewer and adjacent event-flow contributor; confidence: medium; commits: bb8aa0cfe2b0, 4bfd7416f0f9; files: src/gateway/server-chat.ts, src/gateway/server-chat.agent-events.test.ts)

Codex review notes: model gpt-5.5, reasoning high; reviewed against 192a782b99de.

clawsweeper · 2026-05-22T06:44:35Z

ClawSweeper PR egg

✨ Hatched: 🥚 common Tiny Shellbean

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: sniffs out flaky tests.
Image traits: location CI tidepool; accessory miniature diff map; palette moss green and polished brass; mood sparkly; pose leaning over a miniature review desk; shell starlit enamel shell; lighting cool dashboard glow; background soft code-shaped tiles.
Share on X: post this hatch
Copy: My PR egg hatched a 🥚 common Tiny Shellbean 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.

Signed-off-by: samzong <samzong.lu@gmail.com>

…@samzong

…@samzong)

steipete · 2026-05-23T22:52:10Z

Landed via rebase onto main.

PR head before merge: 92c0037
Main commit: 6394dd1
Verification: node scripts/run-vitest.mjs src/gateway/server-chat.agent-events.test.ts (71 passed); pnpm exec oxfmt --check --threads=1 src/gateway/server-chat.ts src/gateway/server-chat.agent-events.test.ts CHANGELOG.md; git diff --check
CI: PR checks were green before the maintainer changelog commit; merge completed successfully on GitHub.

Thanks @samzong!

…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…

…@samzong

…@samzong)

…@samzong

…@samzong)

…@samzong

…@samzong)

…@samzong

…@samzong)

…@samzong

…@samzong)

…@samzong

…@samzong)

…@samzong

…@samzong)

…col/test churn - wrappedStreamFn: restructure provider-error-preservation without a throw inside finally (oxlint no-unsafe-finally). Same semantics: always reacquire; prefer the original stream error over a reacquire takeover error; surface reacquire error only when the stream succeeded. - Revert src/gateway/server-methods/agent.test.ts + GatewayModels.swift to the 5.18 baseline: the openclaw#85764 cherry-pick conflict-resolution had pulled in openclaw#85256-era internal-session-effect tests + protocol fields whose implementation isn't in this backport, breaking checks-node-agentic-gateway-methods + checks-fast-bundled-protocol. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

@jalehman

* fix(agents): skip fallback for session coordination errors Preserve provider fallback metadata when session coordination errors are nested under provider failures. Co-authored-by: luyao618 <364939526@qq.com> (cherry picked from commit 6a5a135) * fix(agents): tolerate in-process session writes during prompt release (openclaw#84250) Merged via squash. Prepared head SHA: 33f88fe Co-authored-by: tianxiaochannel-oss88 <272340815+tianxiaochannel-oss88@users.noreply.github.com> Co-authored-by: jalehman <550978+jalehman@users.noreply.github.com> Reviewed-by: @jalehman (cherry picked from commit 1b77145) * fix(agents): bound embedded compaction write locks Fixes the embedded attempt session write-lock watchdog so the fallback max hold time follows the resolved compaction timeout plus the existing lock grace window, instead of inheriting the full run timeout. Adds regression coverage for the helper and settled-compaction lock lifecycle, plus a changelog entry thanking @luoyanglang. Verification: - `pnpm test src/agents/session-write-lock.test.ts src/agents/pi-embedded-runner/run/attempt.test.ts src/agents/pi-embedded-runner/run/attempt.session-lock.test.ts` - `pnpm check:changed` via Blacksmith Testbox `tbx_01ks8b6vn8se5cg1dfn3te3g47` / https://github.com/openclaw/openclaw/actions/runs/26301988670 - Autoreview clean: `/Users/steipete/Projects/agent-scripts/skills/autoreview/scripts/autoreview --mode branch --base origin/main` - PR CI green on `79e8c5f1a637981d263c0268bf5666967ff4e778`: https://github.com/openclaw/openclaw/actions/runs/26302152844 and https://github.com/openclaw/openclaw/actions/runs/26302152798 Co-authored-by: luoyanglang <hanwanlonga@gmail.com> (cherry picked from commit 46de078) * fix(session-lock): enforce maxHoldMs in shouldReclaim during lock acquisition (openclaw#85764) * fix(session-lock): enforce maxHoldMs in shouldReclaim during lock acquisition - Adds optional maxHoldMs parameter to inspectLockPayload - Inspect now marks locks as stale when held longer than maxHoldMs - Passes maxHoldMs through inspectLockPayloadForSession - acquireSessionWriteLock's shouldReclaim callback now passes maxHoldMs This ensures that when a live process holds a lock for longer than maxHoldMs (default 5min), other processes can reclaim it during acquisition — matching the watchdog's existing enforcement. Previously shouldReclaim only used staleMs (30min default), meaning a lock held for 10+ minutes by a live PID would never be reclaimable, causing 60s timeout failures and gateway freezes. Closes openclaw#85762 * fix(session-lock): add dead-PID fast-path before retry loop Adds a fast-path check at the top of acquireSessionWriteLock: if the lock file's owner PID is dead, remove it immediately before entering the retry loop. This saves up to timeoutMs (60s) of futile waiting when the previous lock holder has died. The shouldReclaim callback already handles this case, but only iteratively through the retry loop. The fast-path eliminates that unnecessary delay. * fix(session-lock): enforce max hold during acquisition * fix(session-lock): revalidate max hold safely * fix(session-lock): honor holder max-hold policy * fix(session-lock): keep cleanup from reclaiming live holders * fix(session-lock): remove stale locks only when unchanged * fix(session-lock): skip self-held max-hold reclaim * fix(ci): refresh gateway protocol checks --------- Co-authored-by: njuboy11 <njuboy11@users.noreply.github.com> Co-authored-by: Peter Steinberger <steipete@gmail.com> (cherry picked from commit a1eb765) * fix(embedded-runner): preserve provider errors on cleanup takeover (openclaw#84321) Summary: - The PR preserves provider-facing embedded-runner prompt errors when cleanup detects session takeover, keeps the takeover signal fatal for fallback, and adds focused regressions. - PR surface: Source +52, Tests +92. Total +144 across 5 files. - Reproducibility: yes. Source inspection shows current main can let cleanup takeover replace a prior prompt/p ... rror and can normalize a provider-looking takeover wrapper before fallback sees it as coordination failure. Automerge notes: - PR branch already contained follow-up commit before automerge: fix(embedded-runner): preserve takeover during fallback - PR branch already contained follow-up commit before automerge: fix(clawsweeper): address review for automerge-openclaw-openclaw-8405… Validation: - ClawSweeper review passed for head 050c779. - Required merge gates passed before the squash merge. Prepared head SHA: 050c779 Review: openclaw#84321 (comment) Co-authored-by: abnershang <abner.shang@gmail.com> Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com> Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com> Approved-by: takhoffman Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com> (cherry picked from commit 7fbca96) * fix(agents): release embedded-attempt session lock on every exit path (openclaw#86427) * fix(agents): release embedded-attempt session lock on every exit path The embedded run controller acquires its session write lock eagerly at creation and released it only inside the post-run cleanup block. An exception thrown in post-prompt processing skipped that block, so the lock leaked to the live gateway process until the watchdog reclaimed it and later requests to the session failed with SessionWriteLockTimeoutError. Add an idempotent dispose() to the lock controller and call it from the run's outer finally so the eagerly-held lock is released on every exit path. Normal/aborted/timed-out runs still hand the lock to acquireForCleanup first, so dispose() is a no-op then (no double release). Fixes openclaw#86014 * fix: keep session lock teardown comment lean * docs(changelog): note embedded session lock fix --------- Co-authored-by: Peter Steinberger <steipete@gmail.com> (cherry picked from commit 32ddfc2) * fix(agents): fence yield abort lock release (cherry picked from commit 0fe7479) * fix(agents): memoize session lock owner args Memoize owner process argv lookups per PID during `cleanStaleLockFiles`, and yield between lock entries so startup cleanup does not monopolize the event loop while inspecting many session locks. This keeps lock classification semantics unchanged while avoiding repeated synchronous process-args reads for lock clusters owned by the same PID, especially the Windows PowerShell path. Fixes openclaw#86509. Verification: - `git diff --check origin/main...HEAD` - focused TSX harness against the current-main merge result: `session-lock memo regression harness passed` Thanks @openperf. Co-authored-by: openperf <16864032@qq.com> (cherry picked from commit c430fcd) * fix(diagnostics): recover orphaned session activity Recover idle queued sessions whose diagnostic activity retained stale ownerless model or tool calls by classifying them as recoverable session.stuck after the usual recovery gates. Yield the event loop before stale session-lock process inspection so sync process lookup cannot monopolize lock contention paths. Docs now describe the widened session.stuck telemetry contract for recoverable stale bookkeeping, including ownerless activity. Thanks @samuelsoaress. Refs openclaw#84903. Co-authored-by: samuelsoaress <samuelsoares177778@gmail.com> (cherry picked from commit 286964c) * [FORK][openclaw#86584] gate owned-write publish on pre-append fingerprint (fixes openclaw#86572) Carries unmerged upstream PR openclaw#86584 (HEAD d79a3b4) onto the boon 5.18 base as the same-lane EmbeddedAttemptSessionTakeoverError fence fix for long cron turns. Fails closed: an external mutation before pi's append fails the trust gate and still trips the fence (verified by the PR's 303-line test suite incl. the mixed-interleave negative test). Backfills base symbols openclaw#86584 assumes (introduced upstream between 5.18 and the PR base, not carried by the 9 merged race-fix picks): - session-lock.ts: MAX_BENIGN_SESSION_FENCE_{ADVANCE,REWRITE,REWRITE_RESULT}_BYTES, MAX_SAFE_FILE_OFFSET, TRANSCRIPT_ONLY_OPENCLAW_ASSISTANT_MODELS, SessionFileFenceSnapshot type, fenceSnapshot state var, ActiveWriteLockState type + activeWriteLock store fix (reuse nested writes via {active:true}), node:util + string-normalization imports. - transcript-append.ts: wrap appendSessionTranscriptMessage in runWithOwnedSessionTranscriptWriteLock so low-level appends acquire the owned-context lock. - test import fixes (appendSessionTranscriptMessage, withOwned/bindOwned, __testing). Drop when upstream merges openclaw#86584. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * [FORK][openclaw#86584] wire owned-transcript-write context + typecheck cleanup CRITICAL: wrap promptActiveSession in withOwnedSessionTranscriptWrites and bind onBlockReply/onBlockReplyFlush to the owned context in attempt.ts. Without this, pi's own transcript appends during a prompt are NOT recorded as owned, so the fence trips on them (the exact takeover the backport is meant to prevent). This wiring is an intermediate-base feature (between 5.18 and openclaw#84250's base) the merged picks didn't carry. Tests passed before only because they set the context manually. Also: add releaseHeldLockForAbort to the controller type; drop incidental non-fence suppressAssistantErrorPersistence passes; remove dead async benign-rewrite cluster (sessionFence{Advance,Rewrite}IsBenign + readAppendedSessionFileText + lineMatchesLinearTranscriptMigration + helpers) — our openclaw#84250-based assertSessionFileFence uses the sync owned-write path, so the async benign-detection variants are unreachable. tsgo core: 0 errors. 384 tests pass. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * [FORK][openclaw#86584] address codex review: prefix-validate benign advance + preserve provider error Finding 2 (masking gap, P2): sessionFenceAdvanceIsBenignSync only validated the APPENDED bytes, so a writer that rewrote the existing prefix AND appended a benign delivery-mirror/gateway-injected line could be laundered as an owned advance — masking a genuine external takeover (silent message loss). Now fail closed unless the current prefix is byte-identical to the trusted readSessionFileFenceSnapshot text (readSessionFilePrefixSync); absent snapshot text => not benign. Finding 1 (provider-error masking, P2): wrappedStreamFn's finally let a reacquireAfterPrompt() takeover error mask the original provider error when the stream itself threw. Now only surface the reacquire error when the stream succeeded; otherwise preserve the original failure. tsgo core: 0 errors. 384 tests pass (benign-advance acceptance + external-mutation rejection both green). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * chore(release): 2026.5.18-boon.1 — session-takeover hardening (boon fleet build) Version bump + CHANGELOG for the fork build. Also fixes a backport test-import gap: attempt.test.ts referenced `attemptTesting` (the __testing export) without importing it. Full project typecheck (tsgo -b tsconfig.projects.json): 0 errors. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(ci): no-unsafe-finally in wrappedStreamFn + drop collateral protocol/test churn - wrappedStreamFn: restructure provider-error-preservation without a throw inside finally (oxlint no-unsafe-finally). Same semantics: always reacquire; prefer the original stream error over a reacquire takeover error; surface reacquire error only when the stream succeeded. - Revert src/gateway/server-methods/agent.test.ts + GatewayModels.swift to the 5.18 baseline: the openclaw#85764 cherry-pick conflict-resolution had pulled in openclaw#85256-era internal-session-effect tests + protocol fields whose implementation isn't in this backport, breaking checks-node-agentic-gateway-methods + checks-fast-bundled-protocol. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: remove vestigial onAssistantErrorMessagePersisted option decls Address cubic P2 review (PR #2): the option was declared on the guard and guard-wrapper option types but never forwarded or invoked, so any provided callback was silently ignored. The companion error-suppression feature (suppressAssistantErrorPersistence + the agent-runner/followup caller chain) is deliberately scoped OUT of this 5.18 backport, so the decls were dead plumbing left over from a cherry-pick. Remove them to keep the option surface honest; the load-bearing beforeMessagePersist fence checkpoint (openclaw#86572) is retained. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Yao <364939526@qq.com> Co-authored-by: xiaotian <tianxiaochannel@gmail.com> Co-authored-by: 狼哥 <hanwanlonga@gmail.com> Co-authored-by: njuboy <njuboy11@gmail.com> Co-authored-by: njuboy11 <njuboy11@users.noreply.github.com> Co-authored-by: Peter Steinberger <steipete@gmail.com> Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com> Co-authored-by: abnershang <abner.shang@gmail.com> Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com> Co-authored-by: Chunyue Wang <80630709+openperf@users.noreply.github.com> Co-authored-by: openperf <16864032@qq.com> Co-authored-by: Samuel Soares da Silva <samuelsoares177778@gmail.com> Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

…@samzong

…@samzong)

…@samzong

…@samzong)

…@samzong

…@samzong)

openclaw-barnacle Bot added gateway Gateway runtime size: S triage: mock-only-proof Candidate: PR proof only shows tests, mocks, snapshots, lint, typecheck, or CI. labels May 22, 2026

openclaw-barnacle Bot added proof: supplied External PR includes structured after-fix real behavior proof. and removed triage: mock-only-proof Candidate: PR proof only shows tests, mocks, snapshots, lint, typecheck, or CI. labels May 22, 2026

openclaw-barnacle Bot removed the proof: sufficient ClawSweeper judged the real behavior proof convincing. label May 22, 2026

steipete self-assigned this May 23, 2026

samzong and others added 3 commits May 23, 2026 23:42

fix(gateway): preserve deferred lifecycle errors

8db6d8d

fix(gateway): preserve lifecycle cleanup

7054358

Signed-off-by: samzong <samzong.lu@gmail.com>

fix: preserve gateway lifecycle error cleanup (openclaw#85256) (thanks …

92c0037

…@samzong)

steipete force-pushed the fix/lifecycle-error-cleanup branch from f4f945f to 92c0037 Compare May 23, 2026 22:49

openclaw-barnacle Bot added size: M and removed size: S labels May 23, 2026

steipete merged commit 6394dd1 into openclaw:main May 23, 2026
106 of 108 checks passed

steipete mentioned this pull request May 23, 2026

[Bug]: Session stuck in "running" status persists in v2026.4.9 — phaseBeforeAbort fix no longer sufficient #63819

Closed

SebTardif pushed a commit to SebTardif/openclaw that referenced this pull request May 24, 2026

fix: preserve gateway lifecycle error cleanup (openclaw#85256) (thanks …

40948cc

…@samzong)

SebTardif pushed a commit to SebTardif/openclaw that referenced this pull request May 24, 2026

fix: preserve gateway lifecycle error cleanup (openclaw#85256) (thanks …

973ca3d

…@samzong)

SebTardif pushed a commit to SebTardif/openclaw that referenced this pull request May 24, 2026

fix: preserve gateway lifecycle error cleanup (openclaw#85256) (thanks …

76d406d

…@samzong)

github-actions Bot pushed a commit to Desicool/openclaw that referenced this pull request May 24, 2026

fix: preserve gateway lifecycle error cleanup (openclaw#85256) (thanks …

32e7a41

…@samzong)

htuyer121 mentioned this pull request May 26, 2026

EmbeddedAttemptSessionTakeoverError cluster on 2026.5.22 — 13 events / 7 jobs / 42h #86845

Open

SebTardif pushed a commit to SebTardif/openclaw that referenced this pull request May 26, 2026

fix: preserve gateway lifecycle error cleanup (openclaw#85256) (thanks …

abf40e9

…@samzong)

SebTardif pushed a commit to SebTardif/openclaw that referenced this pull request May 26, 2026

fix: preserve gateway lifecycle error cleanup (openclaw#85256) (thanks …

8db8535

…@samzong)

SebTardif pushed a commit to SebTardif/openclaw that referenced this pull request May 26, 2026

fix: preserve gateway lifecycle error cleanup (openclaw#85256) (thanks …

934d239

…@samzong)

jameslcowan pushed a commit to jameslcowan/openclaw that referenced this pull request Jun 2, 2026

fix: preserve gateway lifecycle error cleanup (openclaw#85256) (thanks …

6eee74c

…@samzong)

SYU8384 pushed a commit to SYU8384/openclaw that referenced this pull request Jun 3, 2026

fix: preserve gateway lifecycle error cleanup (openclaw#85256) (thanks …

35f84fb

…@samzong)

sablehead pushed a commit to sablehead/openclaw that referenced this pull request Jun 10, 2026

fix: preserve gateway lifecycle error cleanup (openclaw#85256) (thanks …

60a5839

…@samzong)

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

[Fix] Preserve deferred lifecycle errors#85256

[Fix] Preserve deferred lifecycle errors#85256
steipete merged 3 commits into
openclaw:mainfrom
samzong:fix/lifecycle-error-cleanup

samzong 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!

Uh oh!

steipete commented May 23, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Uh oh!

Conversation

samzong 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)

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!

Uh oh!

steipete commented May 23, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

samzong commented May 22, 2026 •

edited

Loading

clawsweeper Bot commented May 22, 2026 •

edited

Loading

clawsweeper Bot commented May 22, 2026 •

edited

Loading