Fix Claude live tool progress for watchdog recovery by joshavant · Pull Request #87546 · openclaw/openclaw

joshavant · 2026-05-28T06:22:43Z

Summary

Claude live sessions now feed parsed stream-json progress into diagnostic run activity. The runner tracks Claude-native tool_use / tool_result lifecycle events, emits trusted diagnostic tool events for Claude CLI tools, and sends a bounded active-tool heartbeat while a native Claude tool is running silently.

This keeps the Gateway stuck-session watchdog from aborting a valid long-running Claude-native foreground tool as an apparently stale embedded run.

Verification

.agents/skills/autoreview/scripts/autoreview --mode local
OPENCLAW_VITEST_MAX_WORKERS=1 node scripts/run-vitest.mjs src/agents/cli-runner.spawn.test.ts
node scripts/run-oxlint.mjs src/agents/cli-runner/claude-live-session.ts src/agents/cli-runner.spawn.test.ts
AWS Crabbox canonical before/after proof: run_311599d1ceae, provider aws, lease cbx_db022c6f0c82, exit 0

Real behavior proof

Behavior addressed: Claude live chat.send turns that emit a native tool_result before a later silent foreground Claude-native Bash tool no longer get recovered as stale embedded runs while the later tool is still running.

Real environment tested: AWS Crabbox Linux, Claude Code CLI 2.1.152, Claude Opus 4.6 via claude-cli, Gateway chat.send webchat path. The before/after proof compared current main at 744da7e6bdea60dc33fb96d2ca5c1739d6c2e73e with this PR at 5b73eeb9cdcfb5f8891db172e9c00c8fab3fe761.

Exact steps or command run after this patch: Ran the same live chat.send repro on current main and on this PR with diagnostics enabled, stuckSessionWarnMs=5000, and stuckSessionAbortMs=15000. The prompt required two Claude-native Bash calls: a quick first tool, then after that first tool result a foreground second tool: python3 -c "import time; time.sleep(45); print('OC86895-SECOND-TOOL-DONE')".

Evidence after fix: AWS Crabbox run_311599d1ceae on cbx_db022c6f0c82 exited 0. On current main, the raw Claude stream showed toolUseCount=2 and toolResultCount=1, while Gateway diagnostics showed recoveryAbortEmbeddedRun=1, stalledEvents=1, streamProgress=0, and toolRunningProgress=0. On this PR, the raw Claude stream showed toolUseCount=2 and toolResultCount=2, while Gateway diagnostics showed recoveryAbortEmbeddedRun=0, toolStarted=2, toolCompleted=2, toolErrored=0, toolRunningProgress=4, streamProgress=44, resultProgress=1, and stalledEvents=0.

Observed result after fix: Current main aborted the live turn as a stuck embedded run after the second foreground Claude-native tool had started. This PR completed the same live turn in about 57s, classified the active work as Claude-native Bash tool work with recent cli_live:tool_running progress while the foreground tool was silent, and did not invoke stuck-session recovery.

What was not tested: Non-Claude live-session providers, and the exact reporter account/session data. This patch is scoped to the Claude live stream-json runner path.

clawsweeper · 2026-05-28T06:29:08Z

Codex review: needs maintainer review before merge. Reviewed May 28, 2026, 4:27 AM ET / 08:27 UTC.

Summary
The PR adds Claude live stream-json diagnostic progress/tool lifecycle tracking and a bounded active-tool heartbeat, plus a CLI runner regression test.

PR surface: Source +243, Tests +170. Total +413 across 2 files.

Reproducibility: yes. for the scoped bug: the PR body gives a live Crabbox before/after repro, and current main still lacks diagnostic progress emission in the Claude live line handler. I did not independently rerun the live Claude scenario on b005f01c1304e1f491f58d7a6036ec21df47e69e.

Review metrics: 1 noteworthy metric.

Linked-issue closure surface: 1 closing reference to an open issue. This matters before merge because GitHub automation can close the broader linked issue even if maintainers only accept the scoped watchdog fix.

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

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

Rank-up moves:

[P2] Have a maintainer decide whether the linked issue should auto-close or retarget the PR body before merge.

Risk before merge

[P1] Merging with the current PR body can auto-close Webchat: substantive tool turns intermittently hang in post-tool-result generation → ~365s abort_embedded_run while the host event loop stays healthy, and the turn is silently lost — v2026.5.22 (a374c3a) #86895 even though the proof is scoped to Claude live native-tool heartbeat behavior, while the linked issue also records broader intermittent session-identity stall and silent-turn-loss symptoms.

Maintainer options:

Resolve issue closure before merge (recommended)
Before merge, either retarget the issue reference to a non-closing mention or have a maintainer explicitly confirm that the broader linked issue is fully covered.
Accept intentional auto-close
Maintainers can keep the closing reference if they intentionally want this scoped Claude-live proof to close the broader issue.

Next step before merge

[P2] Human maintainer review is needed for the protected label and linked-issue closure decision; I did not find a narrow mechanical code repair for ClawSweeper to apply.

Security
Cleared: The diff only touches Claude live diagnostic runtime code and a focused test; it adds summarized tool metadata but does not expose raw tool inputs, secrets, dependencies, CI, or package execution paths.

Review details

Best possible solution:

Land the scoped Claude-live watchdog fix after a maintainer either confirms the linked issue should close or retargets the PR body so the broader remaining issue stays open.

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

Yes for the scoped bug: the PR body gives a live Crabbox before/after repro, and current main still lacks diagnostic progress emission in the Claude live line handler. I did not independently rerun the live Claude scenario on b005f01c1304e1f491f58d7a6036ec21df47e69e.

Is this the best way to solve the issue?

Yes for the scoped watchdog failure: feeding Claude-native tool lifecycle/progress into existing diagnostic activity is the narrow owner-boundary fix. The open question is not code shape, but whether this scoped fix should close the broader linked issue.

AGENTS.md: found and applied where relevant.

Codex review notes: model gpt-5.5, reasoning high; reviewed against b005f01c1304.

Label changes

Label justifications:

P1: The PR addresses a real Claude webchat workflow where a valid long-running native tool turn can be aborted and lost by stuck-session recovery.
merge-risk: 🚨 automation: The PR body can trigger GitHub auto-closure of a broader still-open linked issue when merged.
rating: 🐚 platinum hermit: Overall readiness is 🐚 platinum hermit; proof is 🦞 diamond lobster and patch quality is 🐚 platinum hermit.
status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Sufficient (logs): The PR body includes structured AWS Crabbox live before/after proof with environment, exact scenario, diagnostics, and observed after-fix completion.
proof: sufficient: Contributor real behavior proof is sufficient. The PR body includes structured AWS Crabbox live before/after proof with environment, exact scenario, diagnostics, and observed after-fix completion.

Evidence reviewed

PR surface:

Source +243, Tests +170. Total +413 across 2 files.

View PR surface stats

Area	Files	Added	Removed	Net
Source	1	243	0	+243
Tests	1	171	1	+170
Docs	0	0	0	0
Config	0	0	0	0
Generated	0	0	0	0
Other	0	0	0	0
Total	2	414	1	+413

What I checked:

Current-main behavior: Current main parses Claude live JSONL into the streaming parser and control/result handlers, but has no diagnostic progress/tool lifecycle emission in this path before the PR change. (src/agents/cli-runner/claude-live-session.ts:671, b005f01c1304)
PR implementation: The PR reads Claude stream-json tool_use and tool_result content blocks, emits diagnostic tool events and run.progress, and starts a 10s active-tool heartbeat while native Claude tools are running. (src/agents/cli-runner/claude-live-session.ts:659, 5b73eeb9cdcf)
Watchdog contract: The diagnostic watchdog classifies active tool work by lastProgressAgeMs; fresh run.progress during a tool call prevents active-work recovery until the tool itself and last progress both exceed the abort threshold. (src/logging/diagnostic-session-attention.ts:52, b005f01c1304)
Regression coverage: The added test simulates Claude live tool_use, advances the active-tool interval, verifies cli_live:tool_running freshness, then completes on tool_result and final result. (src/agents/cli-runner.spawn.test.ts:1619, 5b73eeb9cdcf)
Real behavior proof: The PR body reports AWS Crabbox before/after proof run_311599d1ceae: main aborted a live Claude chat.send turn as stale while the second native Bash tool was running, while the PR completed with recoveryAbortEmbeddedRun=0, toolCompleted=2, and heartbeat progress. (5b73eeb9cdcf)
Dependency contract check: Official Claude Code documentation lists stream-json as an output format and stream-json as an input format; Anthropic tool-use docs describe tool_use blocks in responses and tool_result blocks in requests. (docs.anthropic.com)

Likely related people:

Peter Steinberger: Path shortlog shows the strongest historical signal on the CLI runner files, and recent history includes several Claude CLI/cli-runner commits. (role: recent area contributor; confidence: high; commits: 89d7a24a3523, 7e7a8d6b0f67, 628681038831; files: src/agents/cli-runner/claude-live-session.ts, src/agents/cli-runner.spawn.test.ts)
Dallin Romney: Current shallow blame for the Claude live session and diagnostic activity paths points at commit 647e18a, so this is a recent routing signal even though the grafted history limits deeper provenance. (role: recent current-line contributor; confidence: medium; commits: 647e18aa04a2; files: src/agents/cli-runner/claude-live-session.ts, src/logging/diagnostic-run-activity.ts, src/logging/diagnostic.ts)
joshavant: Beyond authoring this PR, git history shows recent merged work across src/agents and src/logging, including agent and diagnostic-adjacent fixes. (role: adjacent agents/logging contributor; confidence: medium; commits: 4a45a259ec1e, 1769fb2aa1d6, 5e4a64848f35; files: src/agents, src/logging)

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 · 2026-05-28T06:37:33Z

ClawSweeper PR egg: ✨ hatched 🌱 uncommon Clockwork Diff Drake. Rarity: 🌱 uncommon. Trait: guards the happy path.

Details

Share on X: post this hatch
Copy: My PR egg hatched a 🌱 uncommon Clockwork Diff Drake in ClawSweeper.
Hatchability:

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.

About:

Eggs appear after real-behavior proof passes. They are collectible flavor only.
Review momentum changes the shell state: follow-up work warms it, re-review makes it wobble, and a clean final review lets it hatch.
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.

joshavant · 2026-05-28T08:18:40Z

@clawsweeper re-review

clawsweeper · 2026-05-28T08:18:44Z

🦞🧹
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.

clawsweeper · 2026-05-28T08:19:15Z

🦞🧹
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/26563293305
Updated: 2026-05-28T08:28:20.289Z

* fix: keep claude live tools fresh for watchdog * fix: avoid claude live active tool spread

…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

* fix: keep claude live tools fresh for watchdog * fix: avoid claude live active tool spread

fix: keep claude live tools fresh for watchdog

980a643

openclaw-barnacle Bot added agents Agent runtime and tooling size: M maintainer Maintainer-authored PR labels May 28, 2026

fix: avoid claude live active tool spread

5b73eeb

joshavant merged commit 4c3a029 into main May 28, 2026
208 of 216 checks passed

joshavant deleted the fix/86895-claude-live-diagnostics branch May 28, 2026 08:37

joshavant mentioned this pull request May 28, 2026

Webchat: substantive tool turns intermittently hang in post-tool-result generation → ~365s abort_embedded_run while the host event loop stays healthy, and the turn is silently lost — v2026.5.22 (a374c3a) #86895

Closed

github-actions Bot mentioned this pull request May 28, 2026

📡 Upstream Digest — 2026-05-28 11:30 UTC curtismercier/openclaw-mods#963

Open

RyanSandoval mentioned this pull request May 28, 2026

[Bug]: GitHub Copilot anthropic-messages transport silently hangs ~365s in isolated cron sessions (2026.5.27) #87692

Open

github-actions Bot pushed a commit to Desicool/openclaw that referenced this pull request May 29, 2026

Fix Claude live tool progress for watchdog recovery (openclaw#87546)

e00fb02

* fix: keep claude live tools fresh for watchdog * fix: avoid claude live active tool spread

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

Fix Claude live tool progress for watchdog recovery (openclaw#87546)

4f0f251

* fix: keep claude live tools fresh for watchdog * fix: avoid claude live active tool spread

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

Fix Claude live tool progress for watchdog recovery (openclaw#87546)

d86e697

* fix: keep claude live tools fresh for watchdog * fix: avoid claude live active tool spread

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Fix Claude live tool progress for watchdog recovery#87546

Fix Claude live tool progress for watchdog recovery#87546
joshavant merged 2 commits into
mainfrom
fix/86895-claude-live-diagnostics

joshavant commented May 28, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented May 28, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented May 28, 2026

Uh oh!

joshavant commented May 28, 2026

Uh oh!

clawsweeper Bot commented May 28, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented May 28, 2026 •

edited

Loading

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

Uh oh!

Conversation

joshavant commented May 28, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Verification

Real behavior proof

Uh oh!

clawsweeper Bot commented May 28, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

clawsweeper Bot commented May 28, 2026

Uh oh!

joshavant commented May 28, 2026

Uh oh!

clawsweeper Bot commented May 28, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

clawsweeper Bot commented May 28, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

joshavant commented May 28, 2026 •

edited

Loading

clawsweeper Bot commented May 28, 2026 •

edited

Loading

clawsweeper Bot commented May 28, 2026 •

edited

Loading

clawsweeper Bot commented May 28, 2026 •

edited

Loading