fix(agents): avoid session event queue self-wait by luoyanglang · Pull Request #86123 · openclaw/openclaw

luoyanglang · 2026-05-24T16:28:31Z

Embedded Pi tool-call processing can self-wait on its own session event queue entry, leaving the Gateway alive but unresponsive to channel replies and health/status probes.

Fixes #86093

Affected surface

src/agents/pi-embedded-runner/run/attempt.session-lock.ts
- waitForSessionEventQueue
- installSessionEventWriteLock
- installSessionExternalHookWriteLock interaction through beforeToolCall
src/agents/pi-embedded-runner/run/attempt.session-lock.test.ts

Scope

Adds a focused active session event processing context.
Skips waitForSessionEventQueue(session) only when the current hook is already running inside that same session's active event-processing entry.
Preserves external queue-drain behavior for cleanup, external hooks, provider hooks, and compaction paths.
No new config, flags, lock policy, timeout policy, or channel-specific behavior.

Prior art / reporter credit

Reporter de1tydev provided the production diagnostics and a candidate fork commit (e1765a6dcd fix(agents): avoid session event queue self-wait). This PR follows that same narrow fix shape and keeps the behavior boundary explicit: self-wait is skipped only for the active same-session event-processing context; all external callers still drain pending session events normally.

Real behavior proof

Behavior or issue addressed: Embedded Pi tool-call processing no longer waits on the same active session event queue entry from inside beforeToolCall; this addresses the Gateway availability hang reported in bug: Pi session event queue self-wait can hang Gateway at tool calls #86093.
Real environment tested: Local Linux OpenClaw checkout at PR head 45f14e72b8a3c34197883d8ff86d8b17cfb86442, running the actual TypeScript source module through node --import tsx. This is a runtime helper proof for the session-lock path, not a mocked unit test.
Exact steps or command run after this patch: OPENCLAW_PR_HEAD=45f14e72b8a3c34197883d8ff86d8b17cfb86442 node --import tsx /tmp/openclaw-pr86123-runtime-proof.mjs

Evidence after fix: Runtime helper console output from current PR head:

[OpenClaw #86123 runtime helper proof] head=45f14e72b8a3c34197883d8ff86d8b17cfb86442
[OpenClaw #86123 runtime helper proof] startedAt=2026-05-24T16:32:00.490Z
[OpenClaw #86123 runtime helper proof] behavior=session event hook self-wait guard
[OpenClaw #86123 runtime helper proof] command=node --import tsx /tmp/openclaw-pr86123-runtime-proof.mjs
[OpenClaw #86123 runtime helper proof] outcome=completed
[OpenClaw #86123 runtime helper proof] events=["process:tool_call","hook-lock","hook","process:end"]

Current-head runtime helper refresh after the active-state follow-up:

$ OPENCLAW_PR_HEAD=5fb473b48e875f41c8521adf8218f16cf5abb798 node --import tsx /tmp/openclaw-pr86123-runtime-proof-current.mjs
[OpenClaw #86123 runtime helper proof] head=5fb473b48e875f41c8521adf8218f16cf5abb798
[OpenClaw #86123 runtime helper proof] command=node --import tsx /tmp/openclaw-pr86123-runtime-proof-current.mjs
[OpenClaw #86123 runtime helper proof] scenario=active-same-session-event-hook outcome=completed
[OpenClaw #86123 runtime helper proof] activeEvents=["process:tool_call","hook-lock","hook","process:end"]
[OpenClaw #86123 runtime helper proof] scenario=detached-async-hook-after-event outcome=waited-then-completed
[OpenClaw #86123 runtime helper proof] detachedEvents=["process:tool_call","process:end","queue-drained","hook-lock","hook"]

Supplemental RED/GREEN regression:

$ node scripts/run-vitest.mjs run --config test/vitest/vitest.agents-pi-embedded.config.ts src/agents/pi-embedded-runner/run/attempt.session-lock.test.ts -t "does not wait on the session event queue"

RED before implementation:
FAIL src/agents/pi-embedded-runner/run/attempt.session-lock.test.ts > embedded attempt session lock lifecycle > does not wait on the session event queue from a hook running during active event processing
AssertionError: expected 'timeout' to be 'done'

GREEN after implementation:
Test Files  1 passed (1)
Tests  1 passed | 32 skipped (33)
Duration  1.45s

Observed result after fix: The actual current-head session-lock module completed the active event-processing hook path within the 250ms guard and produced events=["process:tool_call","hook-lock","hook","process:end"], showing the hook lock ran without waiting on the pending _agentEventQueue entry. Before the fix, the same regression path timed out.
What was not tested: I did not run a live Feishu/Gateway production reproduction or a full Pi model/tool-call turn against an external provider. The live production evidence remains the reporter's redacted diagnostics in bug: Pi session event queue self-wait can hang Gateway at tool calls #86093; this PR adds current-head source/runtime proof for the exact lock path.

Targeted test output

Full targeted file:

$ node scripts/run-vitest.mjs run --config test/vitest/vitest.agents-pi-embedded.config.ts src/agents/pi-embedded-runner/run/attempt.session-lock.test.ts

Test Files  1 passed (1)
Tests  33 passed (33)
Duration  3.58s

Changed checks:

$ pnpm check:changed --base origin/main
[check:changed] lanes=core, coreTests
[check:changed] src/agents/pi-embedded-runner/run/attempt.session-lock.test.ts: core test
[check:changed] src/agents/pi-embedded-runner/run/attempt.session-lock.ts: core production
...
Import cycle check: 0 runtime value cycle(s).
exit 0

Additional local checks:

$ git diff --check origin/main..HEAD
exit 0

$ node scripts/check-no-conflict-markers.mjs
exit 0

$ gitleaks protect --staged --redact
no leaks found

Coverage note

Push-before-PR open-PR search on current origin/main (5a8ce6a88572552dc7cbc1e5b9b9920d8378789d) found no competing fix:

gh search prs --repo openclaw/openclaw --state open "Fixes #86093" => []
gh search prs --repo openclaw/openclaw --state open "#86093" => []
gh search prs --repo openclaw/openclaw --state open "waitForSessionEventQueue" => []
gh search prs --repo openclaw/openclaw --state open "attempt.session-lock.ts beforeToolCall" => []
gh search prs --repo openclaw/openclaw --state open "session event queue self-wait" => []

Recent main commits touch nearby embedded session-lock behavior, but none cover this same active queue-entry self-wait. This PR deliberately avoids broad lock lifecycle changes and keeps the fix at the event queue ownership boundary.

clawsweeper · 2026-05-24T16:30:47Z

Codex review: needs real behavior proof before merge. Reviewed May 27, 2026, 3:37 PM ET / 19:37 UTC.

Summary
The PR adds an AsyncLocalStorage-backed active session-event context around embedded event handling, routes agent hook waits through that guard, and adds regression tests for active and detached hook queue behavior.

PR surface: Source +39, Tests +141. Total +180 across 2 files.

Reproducibility: yes. Source inspection and the added regression tests model the _handleAgentEvent -> _agentEventQueue -> _processAgentEvent -> beforeToolCall self-wait path, though I did not run a live Gateway reproduction in this read-only review.

Review metrics: 1 noteworthy metric.

Hook queue-drain paths: 4 hook waits changed, 2 non-hook drains preserved. The diff changes the four agent hook wait paths while compact and cleanup still use the normal queue drain, which is the key concurrency boundary to verify before merge.

Merge readiness
Overall: 🦐 gold shrimp
Proof: 🦐 gold shrimp
Patch quality: 🦞 diamond lobster
Result: blocked until stronger real behavior proof is added.

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

Rank-up moves:

Add redacted current-head terminal or live proof for 552c794 covering active same-session hook completion and detached hook queue draining.

Proof guidance:
Needs stronger real behavior proof before merge: Insufficient: the PR body contains terminal proof for older heads, but the latest head 552c794 needs redacted current-head terminal/live proof; updating the PR body should trigger re-review, or a maintainer can comment @clawsweeper re-review. After adding proof, update the PR body; ClawSweeper should re-review automatically. If it does not, the PR author or someone with repository write access can comment @clawsweeper re-review.

Risk before merge

The PR body proof is for older heads, so reviewers still need redacted current-head terminal/live proof or maintainer-owned verification for 552c794.
The changed boundary controls when session hook work bypasses or drains the per-session event queue; a wrong guard could either skip needed queue drains for detached work or reintroduce the Gateway hang.

Maintainer options:

Refresh Exact-Head Proof (recommended)
Ask for redacted terminal or live proof from head 552c794 covering active same-session hook completion and detached hook queue draining.
Maintainer-Owned Verification
A maintainer can replace contributor proof by running the targeted session-lock test plus a small current-head runtime probe and recording that verification before landing.

Next step before merge
The remaining action is current-head proof or maintainer-owned verification, not a narrow code repair for an automated worker.

Security
Cleared: The diff only changes TypeScript session-lock logic and tests; it does not add dependencies, workflows, package metadata, secret handling, or other supply-chain surface.

Review details

Best possible solution:

Land the narrow active-event guard after exact-head verification confirms active hooks complete and detached, cleanup, and external hook paths still drain correctly.

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

Yes. Source inspection and the added regression tests model the _handleAgentEvent -> _agentEventQueue -> _processAgentEvent -> beforeToolCall self-wait path, though I did not run a live Gateway reproduction in this read-only review.

Is this the best way to solve the issue?

Yes, with a proof gate. The proposed same-session active-event guard is the narrow maintainable fix, but it should not merge until exact-head proof or maintainer-owned verification covers both bypass and drain behavior.

AGENTS.md: found and applied where relevant.

Codex review notes: model gpt-5.5, reasoning high; reviewed against 90f30075aa72.

Label changes

Label justifications:

P1: The linked report describes a production Gateway hang at the tool-call boundary that can break agent and channel responsiveness for real users.
merge-risk: 🚨 session-state: The PR changes when session event hook work waits for or bypasses the per-session event queue.
merge-risk: 🚨 availability: The affected failure mode can leave the Gateway alive but unresponsive to replies and health/status probes.
rating: 🦐 gold shrimp: Overall readiness is 🦐 gold shrimp; proof is 🦐 gold shrimp and patch quality is 🦞 diamond lobster.
status: 📣 needs proof: The PR needs real behavior proof before ClawSweeper can clear the contributor ask. Needs stronger real behavior proof before merge: Insufficient: the PR body contains terminal proof for older heads, but the latest head 552c794 needs redacted current-head terminal/live proof; updating the PR body should trigger re-review, or a maintainer can comment @clawsweeper re-review. After adding proof, update the PR body; ClawSweeper should re-review automatically. If it does not, the PR author or someone with repository write access can comment @clawsweeper re-review.

Evidence reviewed

PR surface:

Source +39, Tests +141. Total +180 across 2 files.

View PR surface stats

Area	Files	Added	Removed	Net
Source	1	47	8	+39
Tests	1	141	0	+141
Docs	0	0	0	0
Config	0	0	0	0
Generated	0	0	0	0
Other	0	0	0	0
Total	2	188	8	+180

What I checked:

Current main self-wait path: On current main, external agent hooks call waitForSessionEventQueue(session) before taking the write lock, which can self-wait when a hook is invoked from the active _agentEventQueue entry. (src/agents/embedded-agent-runner/run/attempt.session-lock.ts:748, 90f30075aa72)
PR active-context guard: The PR head adds a mutable same-session active event-processing context and clears it in finally so detached async hook work does not inherit the bypass after the event returns. (src/agents/embedded-agent-runner/run/attempt.session-lock.ts:77, 552c794395e7)
PR hook wait boundary: The PR routes the four agent hook waits through waitForSessionEventQueueBeforeHook while compact and cleanup paths remain on the normal queue-drain path. (src/agents/embedded-agent-runner/run/attempt.session-lock.ts:691, 552c794395e7)
Regression coverage: The new tests cover active same-session hook completion without self-wait and detached async hook work waiting for queue drain after event processing returns. (src/agents/embedded-agent-runner/run/attempt.session-lock.test.ts:1192, 552c794395e7)
Proof is stale for the latest head: The PR body proof names older heads 45f14e7 and 5fb473b, while the live PR head is 552c794 after later force-pushes. (552c794395e7)
Current checks snapshot: At inspection time, the latest head had many successful checks and a Real behavior proof check marked success, but some current-head checks were still in progress and the public PR proof text remained tied to older heads. (552c794395e7)

Likely related people:

Vincent Koc: git blame attributes waitForSessionEventQueue and the external hook queue-drain setup to the earlier pi-embedded runner history in this checkout. (role: source-history owner signal; confidence: medium; commits: 5c20ff93e07d; files: src/agents/embedded-agent-runner/run/attempt.session-lock.ts)
Peter Steinberger: bb46b79 internalized the runner path into embedded-agent-runner, and the latest PR head was committed by steipete. (role: recent area contributor and PR branch committer; confidence: high; commits: bb46b79d3c14, 552c794395e7; files: src/agents/embedded-agent-runner/run/attempt.session-lock.ts, src/agents/embedded-agent-runner/run/attempt.session-lock.test.ts)

What the crustacean ranks mean

🦀 challenger crab: rare, exceptional readiness with strong proof, clean implementation, and convincing validation.
🦞 diamond lobster: very strong readiness with only minor maintainer review expected.
🐚 platinum hermit: good normal PR, likely mergeable with ordinary maintainer review.
🦐 gold shrimp: useful signal, but proof or patch confidence is still limited.
🦪 silver shellfish: thin signal; proof, validation, or implementation needs work.
🧂 unranked krab: not merge-ready because proof is missing/unusable or there are serious correctness or safety concerns.
🌊 off-meta tidepool: rating does not apply to this item.

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

How this review workflow works

ClawSweeper keeps one durable marker-backed review comment per issue or PR.
Re-runs edit this comment so the latest verdict, findings, and automation markers stay together instead of adding duplicate bot comments.
A fresh review can be triggered by eligible @clawsweeper re-review comments, exact-item GitHub events, scheduled/background review runs, or manual workflow dispatch.
PR/issue authors and users with repository write access can comment @clawsweeper re-review or @clawsweeper re-run on an open PR or issue to request a fresh review only.
Maintainers can also comment @clawsweeper review to request a fresh review only.
Fresh-review commands do not start repair, autofix, rebase, CI repair, or automerge.
Maintainer-only repair and merge flows require explicit commands such as @clawsweeper autofix, @clawsweeper automerge, @clawsweeper fix ci, or @clawsweeper address review.
Maintainers can comment @clawsweeper explain to ask for more context, or @clawsweeper stop to stop active automation.

clawsweeper · 2026-05-24T16:43:24Z

ClawSweeper PR egg

🎁 Pass real behavior proof to wake the egg and unlock a hatchable treat.

Where did the egg go?

The egg game starts only after the PR passes the real-behavior proof check.
Before that, no creature or rarity is rolled. The treat waits for real proof.
This is still just collectible flavor: proof affects review readiness, not creature quality.

luoyanglang · 2026-05-25T03:10:54Z

@clawsweeper re-review

Addressed the P2 finding in head 5fb473b48e.

Maintenance summary:

Changed activeSessionEventProcessing from a session-only AsyncLocalStorage value to a mutable { session, active } state.
waitForSessionEventQueue() now skips only while the same-session event entry is actively processing.
_processAgentEvent clears active in finally, so async work spawned during event processing no longer inherits a stale queue-drain bypass after the event returns.
Added regression coverage proving detached async hook work waits for the queued session event drain after event processing returns.

RED/GREEN and local validation:

RED before fix: node scripts/run-vitest.mjs run --config test/vitest/vitest.agents-pi-embedded.config.ts src/agents/pi-embedded-runner/run/attempt.session-lock.test.ts -t "drains queued session events for async hook work" failed with expected 'done' to be 'waiting'.
GREEN targeted: same command -> 1 passed / 33 skipped.
Full session-lock suite: node scripts/run-vitest.mjs run --config test/vitest/vitest.agents-pi-embedded.config.ts src/agents/pi-embedded-runner/run/attempt.session-lock.test.ts -> 34 passed.
pnpm check:changed --base origin/main -> passed.
git diff --check origin/main..HEAD -> passed.
node scripts/check-no-conflict-markers.mjs -> passed.
gitleaks protect --staged --redact -> no leaks found.

clawsweeper · 2026-05-25T03:10:57Z

🦞🧹
ClawSweeper re-review requested.

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

Re-review progress:

State: Complete
Detail: The targeted re-review finished, the durable review comment was updated, and the synced verdict was routed.
Run: https://github.com/openclaw/clawsweeper/actions/runs/26386522469
Updated: 2026-05-25T06:29:58.506Z

luoyanglang · 2026-05-25T03:29:32Z

@clawsweeper re-review

Updated the PR body with current-head runtime helper proof for head 5fb473b48e875f41c8521adf8218f16cf5abb798 after the active-state follow-up.

The refreshed helper imports the actual TypeScript source module at PR head and covers both sides of the guard:

active same-session event hook completes without self-wait: activeEvents=["process:tool_call","hook-lock","hook","process:end"]
async hook work spawned during event processing waits for queue drain after the event returns: detachedEvents=["process:tool_call","process:end","queue-drained","hook-lock","hook"]

No patch code was changed after head 5fb473b48e. The body update is proof-only.

clawsweeper · 2026-05-25T03:29:34Z

🦞👀
ClawSweeper picked this up.

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

Re-review progress:

State: Complete
Detail: The targeted re-review finished, the durable review comment was updated, and the synced verdict was routed.
Run: https://github.com/openclaw/clawsweeper/actions/runs/26381660503
Updated: 2026-05-25T03:39:36.245Z

clawsweeper · 2026-05-27T12:16:48Z

🦞🧹
ClawSweeper re-review requested.

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

Re-review progress:

State: Complete
Detail: The targeted re-review finished, the durable review comment was updated, and the synced verdict was routed.
Run: https://github.com/openclaw/clawsweeper/actions/runs/26510524780
Updated: 2026-05-27T12:29:36.338Z

@luoyanglang

Avoids a self-wait in embedded agent session event hooks by skipping the queue drain only for hooks running inside the current session event processing chain. Detached or external hook work still drains the queue before taking the session write lock. Verification: - node scripts/run-vitest.mjs run --config test/vitest/vitest.agents-embedded-agent.config.ts src/agents/embedded-agent-runner/run/attempt.session-lock.test.ts - node scripts/run-oxlint.mjs --tsconfig config/tsconfig/oxlint.core.json src/agents/embedded-agent-runner/run/attempt.session-lock.test.ts src/agents/embedded-agent-runner/run/attempt.session-lock.ts --threads=8 - .agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main - GitHub CI: https://github.com/openclaw/openclaw/actions/runs/26533883763 Thanks @luoyanglang. Co-authored-by: luoyanglang <hanwanlonga@gmail.com> (cherry picked from commit b789e71)

steipete · 2026-05-27T19:48:23Z

Backported the merged fix to release/2026.5.27 in ac825a47c6bf5a2d3ff60ac264956396821b6bfb.

Main landed as b789e71e57d9c023e91e8bbb318230bd8d0cb39a.

Release-branch verification after resolving the old pi-embedded path:

node scripts/run-vitest.mjs run --config test/vitest/vitest.agents-pi-embedded.config.ts src/agents/pi-embedded-runner/run/attempt.session-lock.test.ts -> 40 passed
node scripts/run-oxlint.mjs --tsconfig config/tsconfig/oxlint.core.json src/agents/pi-embedded-runner/run/attempt.session-lock.test.ts src/agents/pi-embedded-runner/run/attempt.session-lock.ts --threads=8 -> passed
.agents/skills/autoreview/scripts/autoreview --mode branch --base origin/release/2026.5.27 -> clean, no accepted/actionable findings

Main PR CI: https://github.com/openclaw/openclaw/actions/runs/26533883763

Thanks again @luoyanglang.

@luoyanglang

Avoids a self-wait in embedded agent session event hooks by skipping the queue drain only for hooks running inside the current session event processing chain. Detached or external hook work still drains the queue before taking the session write lock. Verification: - node scripts/run-vitest.mjs run --config test/vitest/vitest.agents-embedded-agent.config.ts src/agents/embedded-agent-runner/run/attempt.session-lock.test.ts - node scripts/run-oxlint.mjs --tsconfig config/tsconfig/oxlint.core.json src/agents/embedded-agent-runner/run/attempt.session-lock.test.ts src/agents/embedded-agent-runner/run/attempt.session-lock.ts --threads=8 - .agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main - GitHub CI: https://github.com/openclaw/openclaw/actions/runs/26533883763 Thanks @luoyanglang. Co-authored-by: luoyanglang <hanwanlonga@gmail.com>

…026.5.28) (#759) This PR contains the following updates: | Package | Update | Change | |---|---|---| | [ghcr.io/openclaw/openclaw](https://openclaw.ai) ([source](https://github.com/openclaw/openclaw)) | patch | `2026.5.27` → `2026.5.28` | --- ### Release Notes <details> <summary>openclaw/openclaw (ghcr.io/openclaw/openclaw)</summary> ### [`v2026.5.28`](https://github.com/openclaw/openclaw/blob/HEAD/CHANGELOG.md#2026528) [Compare Source](openclaw/openclaw@v2026.5.27...v2026.5.28) ##### Highlights - Agent and Codex runtime recovery is steadier: subagents keep cwd/workspace separation, hook context stays prompt-local, session locks release on timeout abort while live OpenClaw locks survive cleanup, stale restart continuations are avoided, and Codex app-server/helper failures no longer tear down shared runtime state. ([#87218](openclaw/openclaw#87218), [#86875](openclaw/openclaw#86875), [#87409](openclaw/openclaw#87409), [#87399](openclaw/openclaw#87399), [#87375](openclaw/openclaw#87375), [#88129](openclaw/openclaw#88129)) - Channel delivery and session identity got safer across outbound plugin hooks, Matrix room ids, iMessage reactions/approvals, Slack final replies, Discord recovered tool warnings, runtime-config message actions, WhatsApp profile auth roots, Telegram polling, and Microsoft Teams service URL trust checks. ([#73706](openclaw/openclaw#73706), [#75670](openclaw/openclaw#75670), [#87366](openclaw/openclaw#87366), [#87451](openclaw/openclaw#87451), [#87334](openclaw/openclaw#87334), [#84535](openclaw/openclaw#84535), [#82492](openclaw/openclaw#82492), [#83304](openclaw/openclaw#83304), [#87160](openclaw/openclaw#87160)) - Mobile and chat surfaces got a broader refresh: the iOS Pro UI, hosted push relay default, realtime Talk tab playback, Gateway chat transport, onboarding, Talk permissions, WebChat reconnect delivery, and session picker behavior now preserve more state across reconnects and empty searches. ([#87367](openclaw/openclaw#87367), [#87531](openclaw/openclaw#87531), [#87682](openclaw/openclaw#87682), [#88096](openclaw/openclaw#88096), [#88105](openclaw/openclaw#88105)) Thanks [@ngutman](https://github.com/ngutman) and [@BunsDev](https://github.com/BunsDev). - Browser, channel, and automation inputs are stricter: Browser tool timeouts, viewport/tab indices, Gateway ports, cron retry handling, Discord component ids, schema array refs, Telegram callback pages, and channel progress callbacks now reject malformed values earlier and preserve the intended delivery context. ([#82887](openclaw/openclaw#82887)) - Provider, media, and document coverage expands with Claude Opus 4.8, Fal Krea image schemas, NVIDIA featured models, MiniMax streaming music responses, encrypted PDF extraction, voice model catalogs, GitHub Copilot agent runtime support, and a Codex Supervisor plugin path for delegated Codex workflows. ([#87845](openclaw/openclaw#87845), [#87890](openclaw/openclaw#87890), [#80775](openclaw/openclaw#80775), [#84764](openclaw/openclaw#84764), [#87751](openclaw/openclaw#87751), [#87794](openclaw/openclaw#87794)) - CLI, auth, doctor, and provider paths fail faster and recover more clearly: malformed numeric/version options are rejected, workspace dotenv provider credentials are ignored, heartbeat defaults, OAuth/token lifetimes, and local service startup requests are bounded, agent auth health labels are clearer, legacy `api_key` auth profiles migrate to canonical form, and restart guidance is actionable. ([#87398](openclaw/openclaw#87398), [#86281](openclaw/openclaw#86281), [#87361](openclaw/openclaw#87361), [#88133](openclaw/openclaw#88133), [#83655](openclaw/openclaw#83655), [#87559](openclaw/openclaw#87559), [#88088](openclaw/openclaw#88088), [#85924](openclaw/openclaw#85924)) Thanks [@vincentkoc](https://github.com/vincentkoc) and [@giodl73-repo](https://github.com/giodl73-repo). - Plugin and Gateway hot paths do less repeated work while preserving cache correctness for install records, config JSON parsing, tool search catalogs, session stores, manifest model rows, auto-enabled plugin config, browser tokens, viewer assets, and release-split external plugin packages. ([#86699](openclaw/openclaw#86699)) - Release, QA, and E2E validation now bound more log, artifact, harness, and cross-OS waits so failing lanes produce proof instead of hanging or false-greening. ##### Changes - Status: show active subagent details in status output. - Diffs: split the default language pack and expand default Diffs language coverage while keeping the host floor aligned. ([#87370](openclaw/openclaw#87370), [#87372](openclaw/openclaw#87372)) Thanks [@RomneyDa](https://github.com/RomneyDa). - ClawHub: add plugin display names plus skill verification and trust surfaces. ([#87354](openclaw/openclaw#87354), [#86699](openclaw/openclaw#86699)) Thanks [@thewilloftheshadow](https://github.com/thewilloftheshadow) and [@Patrick-Erichsen](https://github.com/Patrick-Erichsen). - iOS: refresh the dev app with Pro Command, Chat, Agents, Settings, hosted push relay defaults, and realtime Talk playback wired to gateway sessions, diagnostics, chat, and realtime Talk. ([#87367](openclaw/openclaw#87367), [#88096](openclaw/openclaw#88096), [#88105](openclaw/openclaw#88105)) Thanks [@Solvely-Colin](https://github.com/Solvely-Colin) and [@ngutman](https://github.com/ngutman). - Docs: clarify Codex computer-use setup, paste-token stdin auth setup, macOS gateway sleep troubleshooting, native Codex hook relay recovery, container model auth, install deployment cards, device-token admin gating, CLI setup flow compatibility, Notte cloud browser CDP setup, and backport targets. ([#87313](openclaw/openclaw#87313), [#63050](openclaw/openclaw#63050), [#87685](openclaw/openclaw#87685)) Thanks [@bdjben](https://github.com/bdjben), [@liaoandi](https://github.com/liaoandi), and [@thewilloftheshadow](https://github.com/thewilloftheshadow). - PDF/tools: use ClawPDF for PDF extraction, support encrypted PDF extraction, and surface MCP structured content in agent tool results. ([#87670](openclaw/openclaw#87670), [#87751](openclaw/openclaw#87751)) - Providers: add Claude Opus 4.8 support, Fal Krea image model schemas, NVIDIA featured model catalogs, MiniMax streaming music responses, and provider-backed voice model catalogs. ([#87845](openclaw/openclaw#87845), [#87890](openclaw/openclaw#87890), [#80775](openclaw/openclaw#80775), [#84764](openclaw/openclaw#84764), [#87794](openclaw/openclaw#87794)) Thanks [@eleqtrizit](https://github.com/eleqtrizit) and [@vincentkoc](https://github.com/vincentkoc). - Codex/GitHub: add the GitHub Copilot agent runtime and the Codex Supervisor plugin package. - Plugins: externalize GitHub Copilot and Tokenjuice as official install-on-demand plugins with npm and ClawHub publish metadata. - Workboard: add agent coordination tools for tracking and handing off active agent work. - Discord: show commentary in progress drafts so live Discord runs expose useful in-progress context. ([#85200](openclaw/openclaw#85200)) - Plugin SDK: add a reply payload sending hook for plugins that need to deliver channel-owned replies and flatten package types for SDK declarations. ([#82823](openclaw/openclaw#82823), [#87165](openclaw/openclaw#87165)) Thanks [@piersonr](https://github.com/piersonr) and [@RomneyDa](https://github.com/RomneyDa). - Policy: add policy comparison, ingress-channel conformance, and sandbox-posture conformance checks. ([#85572](openclaw/openclaw#85572), [#85744](openclaw/openclaw#85744), [#86768](openclaw/openclaw#86768)) ##### Fixes - Agents: fall back to local config pruning when the optional `agents delete` Gateway probe cannot authenticate, so offline installs can still delete agents without removing shared workspaces. - Tighten phone-control mutation authorization \[AI]. ([#87150](openclaw/openclaw#87150)) Thanks [@pgondhi987](https://github.com/pgondhi987). - Clarify directive persistence authorization policy \[AI]. ([#86369](openclaw/openclaw#86369)) Thanks [@pgondhi987](https://github.com/pgondhi987). - Agents/Codex: keep spawned agent cwd/workspace state separated, forward ACP spawn attachments, keep hook context prompt-local, release session locks on timeout abort and runtime teardown without deleting live OpenClaw-owned locks during cleanup, avoid session event queue self-wait, clean up exec abort listeners, stream assistant deltas incrementally, recover raw missing-thread compaction failures, preserve rotated compaction session identity, keep compaction-timeout snapshots continuable, preserve shared app-server state across startup or helper failures, keep native hook relay alive across restarts and prune stale bridge files, close native hook relay replacement races, keep Claude live tool progress visible for watchdog recovery, suppress abandoned requester completion handoff, route workspace memory through tools, resolve Codex runtime models first, report quarantined dynamic tools, format `skills` command output, bind node auto-review to prepared plans, retry Claude CLI transcript probes, and bound compaction/steering retries. ([#87218](openclaw/openclaw#87218), [#86875](openclaw/openclaw#86875), [#86123](openclaw/openclaw#86123), [#88129](openclaw/openclaw#88129), [#87399](openclaw/openclaw#87399), [#87375](openclaw/openclaw#87375), [#72574](openclaw/openclaw#72574), [#87383](openclaw/openclaw#87383), [#87400](openclaw/openclaw#87400), [#83022](openclaw/openclaw#83022), [#87671](openclaw/openclaw#87671), [#87738](openclaw/openclaw#87738), [#87747](openclaw/openclaw#87747), [#87706](openclaw/openclaw#87706), [#87546](openclaw/openclaw#87546), [#87541](openclaw/openclaw#87541), [#81048](openclaw/openclaw#81048)) Thanks [@mbelinky](https://github.com/mbelinky), [@Alix-007](https://github.com/Alix-007), [@luoyanglang](https://github.com/luoyanglang), [@yetval](https://github.com/yetval), [@sjf](https://github.com/sjf), [@joshavant](https://github.com/joshavant), [@benjamin1492](https://github.com/benjamin1492), [@c19354837](https://github.com/c19354837), [@fuller-stack-dev](https://github.com/fuller-stack-dev), [@pfrederiksen](https://github.com/pfrederiksen), and [@dodge1218](https://github.com/dodge1218). - Codex Supervisor: keep real-home app-server MCP session listing on the loaded state path, bound stored history scans, and close WebSocket probes cleanly. - Channels: thread canonical session keys into outbound hooks, preserve Matrix room-id case, keep fallback tool warnings mention-inert, retain delivered Slack final replies during late cleanup, continue iMessage polling after denied reactions, suppress duplicate native exec approvals, resolve Gateway message actions against the active runtime config, preserve Telegram SecretRef prompt config and polling keepalives, preserve WhatsApp profile auth roots, QR display, document filenames, and plugin hook config, suppress Discord recovered tool warnings, preserve the Discord voice outbound helper, cap Discord/Signal/Zalo channel request and container timeouts, and block untrusted Teams service URLs while keeping TeamsSDK patterns aligned. ([#73706](openclaw/openclaw#73706), [#75670](openclaw/openclaw#75670), [#87366](openclaw/openclaw#87366), [#87451](openclaw/openclaw#87451), [#87465](openclaw/openclaw#87465), [#87334](openclaw/openclaw#87334), [#84535](openclaw/openclaw#84535), [#76262](openclaw/openclaw#76262), [#83304](openclaw/openclaw#83304), [#82492](openclaw/openclaw#82492), [#87581](openclaw/openclaw#87581), [#77114](openclaw/openclaw#77114), [#86426](openclaw/openclaw#86426), [#85529](openclaw/openclaw#85529), [#87160](openclaw/openclaw#87160)) Thanks [@zeroaltitude](https://github.com/zeroaltitude), [@lukeboyett](https://github.com/lukeboyett), [@jarvis-mns1](https://github.com/jarvis-mns1), [@xiaotian](https://github.com/xiaotian), [@funmerlin](https://github.com/funmerlin), [@joshavant](https://github.com/joshavant), [@eleqtrizit](https://github.com/eleqtrizit), [@heyitsaamir](https://github.com/heyitsaamir), [@amittell](https://github.com/amittell), [@lidge-jun](https://github.com/lidge-jun), [@liorb-mountapps](https://github.com/liorb-mountapps), [@masatohoshino](https://github.com/masatohoshino), [@bladin](https://github.com/bladin), and [@giodl73-repo](https://github.com/giodl73-repo). - CLI/auth/doctor/providers: reject malformed numeric/timeout/subcommand-version inputs, ignore workspace dotenv provider credentials, wait for respawn child shutdown, bound heartbeat defaults plus Codex, GitHub Copilot, OpenAI, Anthropic, Google, Feishu, LM Studio, MiniMax, Xiaomi TTS, and local-provider OAuth/token/model requests, harden Codex auth probes, label auth health by agent, preserve explicit agentRuntime pins during Codex model migration, warm provider auth off the main thread, honor Codex response timeouts, stop migrating current Claude Haiku 4.5 profiles to Sonnet, bound local service startup, resolve GPT-5.5 without cached catalog, migrate legacy memory auto-provider config, rewrite non-canonical `api_key` auth profiles, and make doctor restart follow-ups actionable. ([#87398](openclaw/openclaw#87398), [#86281](openclaw/openclaw#86281), [#87361](openclaw/openclaw#87361), [#88133](openclaw/openclaw#88133), [#83655](openclaw/openclaw#83655), [#87559](openclaw/openclaw#87559), [#87719](openclaw/openclaw#87719), [#88088](openclaw/openclaw#88088), [#85924](openclaw/openclaw#85924), [#84362](openclaw/openclaw#84362)) Thanks [@Patrick-Erichsen](https://github.com/Patrick-Erichsen), [@samzong](https://github.com/samzong), [@giodl73-repo](https://github.com/giodl73-repo), [@alkor2000](https://github.com/alkor2000), [@mmaps](https://github.com/mmaps), [@nxmxbbd](https://github.com/nxmxbbd), and [@vincentkoc](https://github.com/vincentkoc). - Gateway/security/session state: expire browser tokens after auth rotation, scope assistant idempotency dedupe, drain probe client closes, avoid stale restart continuation reuse, preserve retry-after fallbacks and stale rate-limit cooldown probes, bound webchat image and artifact transcript scans, include seconds in inbound metadata timestamps, clear completed session active runs, clear stale chat stream buffers, and evict current plugin-state namespaces at row caps. ([#87810](openclaw/openclaw#87810), [#87833](openclaw/openclaw#87833), [#75089](openclaw/openclaw#75089)) Thanks [@joshavant](https://github.com/joshavant) and [@litang9](https://github.com/litang9). - Config/parsing/network: reject partial numeric parsing, parse provider/Discord retry headers and dates strictly, honor IPv6 and bare IPv6 `no_proxy` entries, preserve empty plugin allowlists, canonicalize secret target array indexes, and reject malformed media content lengths, inspected TCP ports, marketplace content lengths, cron epochs, sandbox stat fields, unsafe duration values, empty config path segments, noncanonical schema array refs, unsafe Telegram callback pages, and invalid Teams attachment-fetch DNS targets. ([#87883](openclaw/openclaw#87883)) Thanks [@zhangguiping-xydt](https://github.com/zhangguiping-xydt). - Browser/input hardening: reject invalid tab indexes, excessive viewport resizes, explicit zero CDP ports, malformed geolocation options, unsafe screenshot or permission-grant timeouts, loose response-body limits, invalid cookie expiries, and non-finite Browser tool delays/timeouts. - Cron/automation: retry recurring jobs after transient model rate limits before waiting for the next scheduled slot, and preflight model fallbacks before skipping scheduled work. ([#82887](openclaw/openclaw#82887)) Thanks [@chen-zhang-cs-code](https://github.com/chen-zhang-cs-code). - Auto-reply/directives: respect provider and relayed channel metadata during directive persistence so channel-originated decisions keep their intended context. ([#87683](openclaw/openclaw#87683)) - WhatsApp: resolve the auth directory from the active profile so profile-scoped WhatsApp installs do not drift to the wrong credential root. ([#82492](openclaw/openclaw#82492)) Thanks [@lidge-jun](https://github.com/lidge-jun). - Gateway/session state: clear completed session active runs, avoid cold-loading providers for MCP inventory, cache single-session child indexes, cap handshake timers, and bound preauth, auth-guard, media, transcript, readiness, and port options. - Channels/replies: preserve channel-owned progress callbacks when verbose output is off, keep group-room progress suppression intact, prefer external session delivery context, escape Discord component id delimiters, force final TUI chat repaints, show Slack reasoning previews, and normalize Discord/Matrix/Mattermost channel numeric options. ([#87476](openclaw/openclaw#87476), [#87423](openclaw/openclaw#87423)) - Agents/tool args: harden smart-quoted argument repair for edit arrays and exact escaped arguments so model-produced tool calls recover without corrupting valid input. ([#86611](openclaw/openclaw#86611)) Thanks [@ferminquant](https://github.com/ferminquant). - Providers/agents: preserve seeded Anthropic signatures, preserve signed thinking payloads, concatenate signature-delta chunks, preserve DeepSeek `reasoning_content` replay across tier suffixes, apply OpenRouter strict9 ids to Mistral routes, promote Ollama plain-text tool calls, load NVIDIA featured model catalogs, stream MiniMax music generation responses, and recover empty preflight compaction. ([#87593](openclaw/openclaw#87593), [#87493](openclaw/openclaw#87493), [#80775](openclaw/openclaw#80775), [#84764](openclaw/openclaw#84764)) Thanks [@Pluviobyte](https://github.com/Pluviobyte) and [@eleqtrizit](https://github.com/eleqtrizit). - Media/images: skip CLI image cache refs when resolving generated images, allow trusted generated HTML attachments, and bound generated video downloads so stale refs and slow providers fail cleanly. ([#87523](openclaw/openclaw#87523), [#87982](openclaw/openclaw#87982)) - File transfer: handle late tar stdin pipe errors after archive validation or unpacking has already settled. - Performance: trust install-record caches between reloads, prefer native JSON parsing, reuse unchanged tool-search catalogs, reuse gateway session and plugin metadata paths, skip unchanged store serialization, patch single-entry session writes, add precomputed session patch writers, reduce store clone allocations, cache manifest model catalog rows and auto-enabled plugin config, avoid full session snapshots for entry reads, defer configured Slack full startup, prefer bundled plugin dist entries, and slim current metadata identity caches. ([#87760](openclaw/openclaw#87760)) - Docker/release/QA: package runtime workspace templates, stream cross-OS served artifacts, preserve sparse Crabbox run artifacts, isolate npm plugin installs per package, reject incompatible package plugin API installs, drop the leftover root Sharp dependency from package manifests after the Rastermill migration, bound OpenClaw instance logs, plugin gauntlet relay logs, MCP channel buffers, kitchen-sink scans, agent-turn assertions, QA-Lab credential broker calls, QA Matrix substrate requests, and release scenario logs, and keep release/google live guards current. ([#87647](openclaw/openclaw#87647), [#87477](openclaw/openclaw#87477)) Thanks [@rohitjavvadi](https://github.com/rohitjavvadi) and [@vincentkoc](https://github.com/vincentkoc). - Release/CI: bound manual git fetches, ClawHub verifier responses, ClawHub owner metadata, dependency-guard error bodies, Parallels limits, startup/test/memory budget parsing, and diffs viewer build warnings so release lanes fail with useful proof instead of hanging. ([#87839](openclaw/openclaw#87839)) </details> --- ### Configuration 📅 **Schedule**: Branch creation - At any time (no schedule defined), Automerge - At any time (no schedule defined). 🚦 **Automerge**: Disabled by config. Please merge this manually once you are satisfied. ♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox. 🔕 **Ignore**: Close this PR and you won't be reminded about these updates again. --- - [ ] If you want to rebase/retry this PR, check this box --- This PR has been generated by [Renovate Bot](https://github.com/renovatebot/renovate).  Reviewed-on: https://git.erwanleboucher.dev/eleboucher/homelab/pulls/759

@luoyanglang

Avoids a self-wait in embedded agent session event hooks by skipping the queue drain only for hooks running inside the current session event processing chain. Detached or external hook work still drains the queue before taking the session write lock. Verification: - node scripts/run-vitest.mjs run --config test/vitest/vitest.agents-embedded-agent.config.ts src/agents/embedded-agent-runner/run/attempt.session-lock.test.ts - node scripts/run-oxlint.mjs --tsconfig config/tsconfig/oxlint.core.json src/agents/embedded-agent-runner/run/attempt.session-lock.test.ts src/agents/embedded-agent-runner/run/attempt.session-lock.ts --threads=8 - .agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main - GitHub CI: https://github.com/openclaw/openclaw/actions/runs/26533883763 Thanks @luoyanglang. Co-authored-by: luoyanglang <hanwanlonga@gmail.com>

@luoyanglang

Avoids a self-wait in embedded agent session event hooks by skipping the queue drain only for hooks running inside the current session event processing chain. Detached or external hook work still drains the queue before taking the session write lock. Verification: - node scripts/run-vitest.mjs run --config test/vitest/vitest.agents-embedded-agent.config.ts src/agents/embedded-agent-runner/run/attempt.session-lock.test.ts - node scripts/run-oxlint.mjs --tsconfig config/tsconfig/oxlint.core.json src/agents/embedded-agent-runner/run/attempt.session-lock.test.ts src/agents/embedded-agent-runner/run/attempt.session-lock.ts --threads=8 - .agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main - GitHub CI: https://github.com/openclaw/openclaw/actions/runs/26533883763 Thanks @luoyanglang. Co-authored-by: luoyanglang <hanwanlonga@gmail.com>

openclaw-barnacle Bot added agents Agent runtime and tooling size: S triage: needs-real-behavior-proof Candidate: external PR needs after-fix proof from a real setup. labels May 24, 2026

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

openclaw-barnacle Bot removed the proof: sufficient ClawSweeper judged the real behavior proof convincing. label May 25, 2026

clawsweeper Bot added status: 📣 needs proof The PR needs real behavior proof before ClawSweeper can clear the contributor ask. and removed status: ⏳ waiting on author ClawSweeper has contributor-facing work open and is waiting for author action. labels May 25, 2026

steipete self-assigned this May 27, 2026

openclaw-barnacle Bot removed the proof: sufficient ClawSweeper judged the real behavior proof convincing. label May 27, 2026

clawsweeper Bot added rating: 🦪 silver shellfish Thin PR readiness signal; proof, validation, or implementation needs work. and removed rating: 🦐 gold shrimp Decent PR readiness signal, but merge confidence is limited. labels May 27, 2026

steipete force-pushed the wolf/session-event-queue-self-wait branch 2 times, most recently from 2c2a516 to 420c5a8 Compare May 27, 2026 19:14

clawsweeper Bot added rating: 🦐 gold shrimp Decent PR readiness signal, but merge confidence is limited. and removed rating: 🦪 silver shellfish Thin PR readiness signal; proof, validation, or implementation needs work. labels May 27, 2026

steipete force-pushed the wolf/session-event-queue-self-wait branch from 420c5a8 to 7339463 Compare May 27, 2026 19:29

fix(agents): avoid session event queue self-wait

552c794

steipete force-pushed the wolf/session-event-queue-self-wait branch from 7339463 to 552c794 Compare May 27, 2026 19:30

steipete merged commit b789e71 into openclaw:main May 27, 2026
99 checks passed

RomneyDa mentioned this pull request May 27, 2026

perf(plugins) refactor plugin SDK declarations for flat package types #87165

Merged

luoyanglang deleted the wolf/session-event-queue-self-wait branch May 27, 2026 20:01

steipete mentioned this pull request May 27, 2026

fix(agents): move session write lock into owned session runtime #87409

Merged

github-actions Bot mentioned this pull request May 27, 2026

📡 Upstream Digest — 2026-05-27 21:46 UTC curtismercier/openclaw-mods#959

Open

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

fix(agents): avoid session event queue self-wait#86123

fix(agents): avoid session event queue self-wait#86123
steipete merged 1 commit into
openclaw:mainfrom
luoyanglang:wolf/session-event-queue-self-wait

luoyanglang commented May 24, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented May 24, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented May 24, 2026 •

edited

Loading

Uh oh!

luoyanglang commented May 25, 2026

Uh oh!

clawsweeper Bot commented May 25, 2026 •

edited

Loading

Uh oh!

luoyanglang commented May 25, 2026

Uh oh!

clawsweeper Bot commented May 25, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented May 27, 2026 •

edited

Loading

Uh oh!

Uh oh!

steipete commented May 27, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Uh oh!

Conversation

luoyanglang commented May 24, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Affected surface

Scope

Prior art / reporter credit

Real behavior proof

Targeted test output

Coverage note

Uh oh!

clawsweeper Bot commented May 24, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

clawsweeper Bot commented May 24, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

luoyanglang commented May 25, 2026

Uh oh!

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

Uh oh!

Uh oh!

luoyanglang commented May 25, 2026

Uh oh!

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

Uh oh!

Uh oh!

clawsweeper Bot commented May 27, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Uh oh!

steipete commented May 27, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

luoyanglang commented May 24, 2026 •

edited

Loading

clawsweeper Bot commented May 24, 2026 •

edited

Loading

clawsweeper Bot commented May 24, 2026 •

edited

Loading

clawsweeper Bot commented May 25, 2026 •

edited

Loading

clawsweeper Bot commented May 25, 2026 •

edited

Loading

clawsweeper Bot commented May 27, 2026 •

edited

Loading