fix(imessage): surface inbound startup diagnostics by omarshahine · Pull Request #91785 · openclaw/openclaw

omarshahine · 2026-06-09T23:39:52Z

Summary

Add default-level, privacy-safe diagnostics when inbound rows are dropped for echo/reflection reasons (echo, self-chat echo, agent echo in self-chat, reflected assistant content) and for same-account from me rows. The log includes account, reason, numeric chat id when present, row/message id, GUID presence, group flag, and timestamp, but not message text, sender handles, or full GUIDs.
Throttle from me diagnostics once per account/conversation/reason so normal outbound watcher rows do not spam default logs while still surfacing the same-account group-chat drop called out by review.
Add structured watch.subscribe startup retry/failure context: account, cliPath, db path presence, remote-host presence, timeout, since_rowid, attachment/reaction flags, attempt count, and retry delay.
Keep this diagnostics-only: no inbound delivery policy, watch retry classification, retry count, teardown, or thrown error behavior changes.

Refs #89593.
Refs #87263.

Verification

Initial proof:

node scripts/run-vitest.mjs extensions/imessage/src/monitor.watch-subscribe-retry.test.ts (4 tests)
pnpm format:check -- extensions/imessage/src/monitor/monitor-provider.ts extensions/imessage/src/monitor.watch-subscribe-retry.test.ts
pnpm lint:extensions -- extensions/imessage/src/monitor/monitor-provider.ts extensions/imessage/src/monitor.watch-subscribe-retry.test.ts
pnpm tsgo:extensions
git diff --check
.agents/skills/autoreview/scripts/autoreview --mode local --prompt "Review this diagnostics-only iMessage monitor patch. It should not change inbound delivery policy or watch.subscribe retry behavior. Focus on log noise/privacy, whether echo/reflection drops are surfaced without message content/sender handles, whether watch.subscribe retry/failure diagnostics include useful startup context, and whether tests cover the new formatting." (clean)

Follow-up proof after ClawSweeper noted that from me rows also needed diagnostics:

node scripts/run-vitest.mjs extensions/imessage/src/monitor.watch-subscribe-retry.test.ts (5 tests)
pnpm format:check -- extensions/imessage/src/monitor/monitor-provider.ts extensions/imessage/src/monitor.watch-subscribe-retry.test.ts
pnpm lint:extensions -- extensions/imessage/src/monitor/monitor-provider.ts extensions/imessage/src/monitor.watch-subscribe-retry.test.ts
pnpm tsgo:extensions
git diff --check
.agents/skills/autoreview/scripts/autoreview --mode local --prompt "Review the follow-up to PR #91785. It adds privacy-safe diagnostics for iMessage 'from me' drops and throttles that reason per account/conversation so normal outbound watcher rows do not spam default logs. Focus on whether it satisfies ClawSweeper's from-me diagnostic finding without changing delivery policy or overlogging PII." (clean)

Real behavior proof

Behavior addressed: missing runtime diagnostics for iMessage inbound rows that are intentionally dropped before dispatch, plus startup context for watch.subscribe retry/failure.
Real environment tested: lobster macOS host, OpenClaw PR head 597684c3650dab508cbb1378a58b74636d581626, imsg 0.11.0, Node v26.0.0.
Exact steps or command run after this patch: checked out origin/fix/imessage-inbound-startup-diagnostics on lobster, started monitorIMessageProvider through the PR source with a redacting runtime logger, then sent a self-addressed iMessage through sendMessageIMessage using sendTransport = "bridge". Account, target, chat id, message id, and any participant details were redacted from output.
Evidence after fix:

{
  "host": "lobster",
  "proofId": "openclaw-lobster-live-monitor-proof-ada22165-6306-46b6-8ed0-6c94fcab6bbc",
  "head": "597684c3650dab508cbb1378a58b74636d581626",
  "transport": "bridge",
  "candidateKey": "account_id",
  "targetKind": "handle",
  "sendMessageIdPresent": false,
  "sendGuidPresent": true,
  "dropDiagnosticFound": true,
  "redactedDropDiagnostic": "imessage: dropped inbound message account=<redacted> reason=\"from me\" chat_id=<redacted> group=false message_id=<redacted> guid=present created_at=2026-06-10T00:20:16.169Z",
  "startupDiagnostics": [],
  "logCount": 1,
  "errorCount": 0,
  "sendError": null,
  "errorSamples": []
}

Observed result after fix: the live monitor emitted the new default-level, privacy-safe from me drop diagnostic with no message text, sender handle, target handle, or full GUID in the proof output.
What was not tested: a live watch.subscribe startup timeout on lobster; that branch remains covered by focused tests because the live monitor startup succeeded.

clawsweeper · 2026-06-09T23:42:21Z

Codex review: needs maintainer review before merge. Reviewed June 9, 2026, 8:28 PM ET / 00:28 UTC.

Summary
The PR adds privacy-safe default iMessage inbound-drop diagnostics, throttles same-account from me drop logs, and expands watch.subscribe startup retry/failure log context with focused tests.

PR surface: Source +107, Tests +72. Total +179 across 2 files.

Reproducibility: not applicable. as a PR review: the patch adds diagnostics around existing iMessage drop/startup paths. The contributor supplied a live after-fix monitor proof for the visible inbound-drop diagnostic plus focused tests for the startup failure branch.

Review metrics: none identified.

Merge readiness
Overall: 🐚 platinum hermit
Proof: 🐚 platinum hermit
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:

none.

Risk before merge

[P1] The PR has the protected maintainer label, so it should stay in the human maintainer path even with no blocking review findings.
[P2] The live proof covers the inbound from me drop diagnostic; the watch.subscribe startup-timeout branch remains covered by focused tests rather than a live timeout reproduction.

Maintainer options:

Decide the mitigation before merge
Land the diagnostics-only patch after maintainer review accepts the default-log privacy/noise tradeoff and normal CI or equivalent scoped proof is clean.
Pause or close
Do not merge this PR until maintainers decide whether the risk is worth taking.

Next step before merge

[P2] Human maintainer review remains appropriate because the PR carries a protected maintainer label and the remaining decision is acceptance of log privacy/noise tradeoffs, not an automated code repair.

Security
Cleared: The diff only changes diagnostic formatting, runtime logging, and focused tests; it does not broaden dependency, CI, credential, install, package, or code-execution surfaces.

Review details

Best possible solution:

Land the diagnostics-only patch after maintainer review accepts the default-log privacy/noise tradeoff and normal CI or equivalent scoped proof is clean.

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

Not applicable as a PR review: the patch adds diagnostics around existing iMessage drop/startup paths. The contributor supplied a live after-fix monitor proof for the visible inbound-drop diagnostic plus focused tests for the startup failure branch.

Is this the best way to solve the issue?

Yes, this is the best narrow fix shape: log privacy-safe metadata at the existing drop/retry decisions instead of changing iMessage delivery policy, retry classification, or transport behavior.

AGENTS.md: found and applied where relevant.

Codex review notes: model gpt-5.5, reasoning high; reviewed against 48ec58a5844f.

Label changes

Label changes:

add proof: sufficient: Contributor real behavior proof is sufficient. The PR body now includes redacted live macOS iMessage monitor logs from the PR head showing the new from me inbound-drop diagnostic after the patch.
add rating: 🐚 platinum hermit: Overall readiness is 🐚 platinum hermit; proof is 🐚 platinum hermit and patch quality is 🐚 platinum hermit.
add status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Sufficient (logs): The PR body now includes redacted live macOS iMessage monitor logs from the PR head showing the new from me inbound-drop diagnostic after the patch.
remove rating: 🦪 silver shellfish: Current PR rating is rating: 🐚 platinum hermit, so this older rating label is no longer current.
remove status: 📣 needs proof: Current PR status label is status: 👀 ready for maintainer look.

Label justifications:

P2: This is a normal-priority iMessage diagnostics fix for message-loss/startup debugging with limited blast radius and no delivery-policy change.
rating: 🐚 platinum hermit: Overall readiness is 🐚 platinum hermit; proof is 🐚 platinum hermit 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 now includes redacted live macOS iMessage monitor logs from the PR head showing the new from me inbound-drop diagnostic after the patch.
proof: sufficient: Contributor real behavior proof is sufficient. The PR body now includes redacted live macOS iMessage monitor logs from the PR head showing the new from me inbound-drop diagnostic after the patch.

Evidence reviewed

PR surface:

Source +107, Tests +72. Total +179 across 2 files.

View PR surface stats

Area	Files	Added	Removed	Net
Source	1	109	2	+107
Tests	1	77	5	+72
Docs	0	0	0	0
Config	0	0	0	0
Generated	0	0	0	0
Other	0	0	0	0
Total	2	186	7	+179

Acceptance criteria:

[P1] node scripts/run-vitest.mjs extensions/imessage/src/monitor.watch-subscribe-retry.test.ts.
[P1] pnpm format:check -- extensions/imessage/src/monitor/monitor-provider.ts extensions/imessage/src/monitor.watch-subscribe-retry.test.ts.
[P1] pnpm lint:extensions -- extensions/imessage/src/monitor/monitor-provider.ts extensions/imessage/src/monitor.watch-subscribe-retry.test.ts.
[P1] pnpm tsgo:extensions.
[P1] git diff --check.

What I checked:

Repository policy read: Read the full root AGENTS.md and applied its OpenClaw PR review, maintainer-label, read-only, proof, security, and channel/plugin guidance. (AGENTS.md:1, 48ec58a5844f)
Scoped policy read: Read the extension-scoped AGENTS.md; the PR remains within the owning bundled plugin and does not cross plugin/core boundaries. (extensions/AGENTS.md:1, 48ec58a5844f)
Diff inspected: The PR head changes only monitor-provider.ts and one focused test file, adding diagnostic formatting/throttling and startup log context without changing retry count, delivery predicates, teardown, or thrown-error behavior. (extensions/imessage/src/monitor/monitor-provider.ts:260, 597684c3650d)
Inbound decision contract checked: Current main already returns the exact drop reasons this PR surfaces (from me, agent echo in self-chat, self-chat echo, echo, and reflected assistant content), so the patch wraps existing decisions instead of redefining delivery policy. (extensions/imessage/src/monitor/inbound-processing.ts:511, 48ec58a5844f)
Runtime entry point checked: channel.runtime.ts starts monitorIMessageProvider for the active account, so the added logs sit at the plugin-owned iMessage monitor boundary used by real gateway runtime. (extensions/imessage/src/channel.runtime.ts:98, 48ec58a5844f)
Startup retry path checked: The current monitor loop already retries bounded watch.subscribe startup failures and logs retry/failure messages; the PR enriches the string with account/config/presence fields while preserving the same control flow. (extensions/imessage/src/monitor/monitor-provider.ts:1420, 48ec58a5844f)

Likely related people:

vincentkoc: Introduced the bounded iMessage watch.subscribe startup retry path and adjacent focused retry test that this PR now enriches with structured diagnostics. (role: startup retry feature owner; confidence: high; commits: 35a784c16563; files: extensions/imessage/src/monitor/monitor-provider.ts, extensions/imessage/src/monitor.watch-subscribe-retry.test.ts)
obviyus: Recent history shows work on inbound echo IDs and reflected self-chat drop behavior, which are central to the diagnostic reasons surfaced by this PR. (role: inbound echo/self-chat contributor; confidence: high; commits: e3e2a19ab7f1, 4a5885df3a36; files: extensions/imessage/src/monitor/inbound-processing.ts, extensions/imessage/src/monitor/self-chat-dedupe.test.ts)
steipete: Shortlog and file history show repeated refactors and fixes across the iMessage monitor and inbound-processing surfaces, including monitor retry type alignment and plugin boundary work. (role: heavy adjacent contributor; confidence: medium; commits: fa87c6334aa6, 625fd5b3e3e2, e4b5027c5e29; files: extensions/imessage/src/monitor/monitor-provider.ts, extensions/imessage/src/monitor/inbound-processing.ts)
shakkernerd: Current line blame for the monitor/drop and startup retry regions points to a recent commit that touched the central iMessage monitor files, making this a useful routing signal despite the broad commit title. (role: recent area contributor; confidence: medium; commits: d48778994fb2; files: extensions/imessage/src/monitor/monitor-provider.ts, extensions/imessage/src/monitor/inbound-processing.ts, extensions/imessage/src/monitor.watch-subscribe-retry.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.

omarshahine · 2026-06-09T23:52:34Z

Addressed ClawSweeper's from me diagnostic finding in 597684c365.

What changed:

Added from me to the privacy-safe diagnostic surface.
Throttled from me diagnostics once per account/conversation/reason so normal outbound watcher rows do not spam default logs.
Kept GUIDs presence-only and still logs no sender handle or message content.

Verification after this patch:

node scripts/run-vitest.mjs extensions/imessage/src/monitor.watch-subscribe-retry.test.ts (5 tests)
pnpm format:check -- extensions/imessage/src/monitor/monitor-provider.ts extensions/imessage/src/monitor.watch-subscribe-retry.test.ts
pnpm lint:extensions -- extensions/imessage/src/monitor/monitor-provider.ts extensions/imessage/src/monitor.watch-subscribe-retry.test.ts
pnpm tsgo:extensions
git diff --check
.agents/skills/autoreview/scripts/autoreview --mode local --prompt "Review the follow-up to PR #91785. It adds privacy-safe diagnostics for iMessage 'from me' drops and throttles that reason per account/conversation so normal outbound watcher rows do not spam default logs. Focus on whether it satisfies ClawSweeper's from-me diagnostic finding without changing delivery policy or overlogging PII." (clean)

@clawsweeper re-review

clawsweeper · 2026-06-09T23:52:36Z

🦞🧹
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.

omarshahine · 2026-06-10T00:20:55Z

Added the requested live diagnostics proof to the PR body.

Lobster proof summary:

Host: lobster
PR head: 597684c3650dab508cbb1378a58b74636d581626
Runtime path: live monitorIMessageProvider plus self-addressed sendMessageIMessage using sendTransport = "bridge"
Result: monitor emitted the new redacted reason="from me" drop diagnostic.
Redaction: account, target, chat id, message id, participant details, message text, and full GUID are not present in the proof output.

Proof id: openclaw-lobster-live-monitor-proof-ada22165-6306-46b6-8ed0-6c94fcab6bbc

@clawsweeper re-review

clawsweeper · 2026-06-10T00:20:58Z

🦞👀
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/27244550756
Updated: 2026-06-10T00:29:23.665Z

omarshahine · 2026-06-10T02:09:02Z

Land-ready maintainer check before merge.

Head: 597684c3650dab508cbb1378a58b74636d581626
State: open, non-draft, mergeable
Checks: no non-green material checks reported in gh pr checks
ClawSweeper: proof sufficient / ready for maintainer review after lobster live monitor proof
Maintainer decision: accepting the diagnostics-only default-log privacy/noise tradeoff for this PR

Lobster proof id: openclaw-lobster-live-monitor-proof-ada22165-6306-46b6-8ed0-6c94fcab6bbc

@omarshahine

Merged via squash. Prepared head SHA: 597684c Proof: - Focused tests, lint/type/diff checks, and autoreview passed before merge. - ClawSweeper re-review marked proof and patch quality platinum after lobster live monitor proof. - Maintainer accepted the diagnostics-only default-log privacy/noise tradeoff. Lobster proof id: openclaw-lobster-live-monitor-proof-ada22165-6306-46b6-8ed0-6c94fcab6bbc Reviewed-by: @omarshahine

…26.6.6) (#1040) This PR contains the following updates: | Package | Update | Change | |---|---|---| | [ghcr.io/openclaw/openclaw](https://openclaw.ai) ([source](https://github.com/openclaw/openclaw)) | patch | `2026.6.5` → `2026.6.6` | --- ### Release Notes <details> <summary>openclaw/openclaw (ghcr.io/openclaw/openclaw)</summary> ### [`v2026.6.6`](https://github.com/openclaw/openclaw/blob/HEAD/CHANGELOG.md#202666) [Compare Source](openclaw/openclaw@v2026.6.5...v2026.6.6) ##### Highlights - Security boundaries are substantially tighter across transcripts, sandbox binds, host environment inheritance, MCP stdio, Codex HTTP access, native search policy, elevated sender checks, deleted-agent ACP bypasses, loopback tools, Discord moderation, and Teams group actions; exec approvals now fail closed on timeout. ([#91529](openclaw/openclaw#91529), [#91618](openclaw/openclaw#91618), [#91615](openclaw/openclaw#91615), [#91619](openclaw/openclaw#91619), [#91741](openclaw/openclaw#91741), [#91745](openclaw/openclaw#91745), [#91746](openclaw/openclaw#91746), [#91748](openclaw/openclaw#91748), [#91749](openclaw/openclaw#91749), [#91750](openclaw/openclaw#91750), [#91751](openclaw/openclaw#91751), [#91752](openclaw/openclaw#91752), [#91763](openclaw/openclaw#91763), [#89938](openclaw/openclaw#89938)) Thanks [@joshavant](https://github.com/joshavant), [@pgondhi987](https://github.com/pgondhi987), [@mmaps](https://github.com/mmaps), [@eleqtrizit](https://github.com/eleqtrizit), [@shakkernerd](https://github.com/shakkernerd), and [@drobison00](https://github.com/drobison00). - Telegram delivery is safer and more coherent: account-scoped topics route to the right agent, streamed text survives tool calls, `/compact` works on generic ingress, callback handling uses concrete APIs, draft chunking is shared, durable dispatch dedupe moved into the SDK, and unauthorized DM text stays out of cache and prompt context. ([#91189](openclaw/openclaw#91189), [#88682](openclaw/openclaw#88682), [#89588](openclaw/openclaw#89588), [#90212](openclaw/openclaw#90212), [#91876](openclaw/openclaw#91876), [#91874](openclaw/openclaw#91874), [#91904](openclaw/openclaw#91904), [#91478](openclaw/openclaw#91478), [#91915](openclaw/openclaw#91915)) Thanks [@codysai001](https://github.com/codysai001), [@alexzhu0](https://github.com/alexzhu0), [@joelnishanth](https://github.com/joelnishanth), [@snowzlm](https://github.com/snowzlm), [@obviyus](https://github.com/obviyus), and [@sallyom](https://github.com/sallyom). - iMessage recovery and delivery now cover always-on inbound restart, durable echo markers, block streaming, idle approval discovery, hardened outbound transport, and actionable inbound startup diagnostics. ([#91335](openclaw/openclaw#91335), [#91449](openclaw/openclaw#91449), [#88969](openclaw/openclaw#88969), [#88530](openclaw/openclaw#88530), [#91783](openclaw/openclaw#91783), [#91785](openclaw/openclaw#91785)) Thanks [@omarshahine](https://github.com/omarshahine), [@jmissig](https://github.com/jmissig), and [@colmbrogan](https://github.com/colmbrogan). - Browser and MCP connectivity gained existing-session CDP support, discovered WebSocket validation, default-profile `cdpUrl` handling, safer browser-output boundaries, Streamable HTTP loopback transport, corrected OAuth/SSE authorization handling, and broader schema compatibility. ([#91422](openclaw/openclaw#91422), [#89851](openclaw/openclaw#89851), [#91736](openclaw/openclaw#91736), [#91747](openclaw/openclaw#91747), [#91451](openclaw/openclaw#91451), [#80143](openclaw/openclaw#80143)) Thanks [@pgondhi987](https://github.com/pgondhi987), [@anagnorisis2peripeteia](https://github.com/anagnorisis2peripeteia), [@lifuyue](https://github.com/lifuyue), [@eleqtrizit](https://github.com/eleqtrizit), [@LiuwqGit](https://github.com/LiuwqGit), and [@HemantSudarshan](https://github.com/HemantSudarshan). - Control UI startup and first-reply latency are lower through cached model metadata, removal of the startup catalog wait, lazy slash-command loading, and first-event tracing with slow-reply diagnostics. ([#91531](openclaw/openclaw#91531), [#91538](openclaw/openclaw#91538), [#91568](openclaw/openclaw#91568), [#91583](openclaw/openclaw#91583), [#91598](openclaw/openclaw#91598)) - Provider support expands with OpenRouter OAuth onboarding and Claude Fable 5 adaptive thinking, while Codex sessions keep correct compaction ownership, local models skip guardian review, dynamic tool progress normalizes cleanly, and Gemma 4 reasoning replay is preserved. ([#91830](openclaw/openclaw#91830), [#91882](openclaw/openclaw#91882), [#91590](openclaw/openclaw#91590), [#88630](openclaw/openclaw#88630), [#88768](openclaw/openclaw#88768), [#91696](openclaw/openclaw#91696)) Thanks [@Patrick-Erichsen](https://github.com/Patrick-Erichsen), [@joshavant](https://github.com/joshavant), [@bdjben](https://github.com/bdjben), and [@Coder-Wangyankun](https://github.com/Coder-Wangyankun). ##### Changes - CLI progress: emit Claude CLI commentary progress events and bridge inter-tool commentary into channel progress without exposing internal protocol scaffolding. ([#89834](openclaw/openclaw#89834), [#90883](openclaw/openclaw#90883)) Thanks [@anagnorisis2peripeteia](https://github.com/anagnorisis2peripeteia). - Observability: allow trusted diagnostics channels to capture tool input/output content, add first-assistant-event traces, and warn on slow initial replies. ([#91256](openclaw/openclaw#91256), [#91568](openclaw/openclaw#91568), [#91583](openclaw/openclaw#91583)) Thanks [@amknight](https://github.com/amknight). - Plugins/ClawHub: dogfood reusable package publishing, let dry runs skip publish approval, allow declared installed trusted hooks, report managed plugin version drift, and warn instead of failing on retired Skill Workshop configuration. ([#91574](openclaw/openclaw#91574), [#91591](openclaw/openclaw#91591), [#90004](openclaw/openclaw#90004), [#90927](openclaw/openclaw#90927), [#90838](openclaw/openclaw#90838)) Thanks [@Patrick-Erichsen](https://github.com/Patrick-Erichsen), [@brokemac79](https://github.com/brokemac79), and [@lonexreb](https://github.com/lonexreb). - Memory/providers: move the local llama.cpp runtime into its provider plugin, batch embeddings across files, persist the agent model catalog cache, and keep QMD JSON search one-shot while filtering stale REM recall previews. ([#91324](openclaw/openclaw#91324), [#89138](openclaw/openclaw#89138), [#90457](openclaw/openclaw#90457), [#91837](openclaw/openclaw#91837), [#91851](openclaw/openclaw#91851)) Thanks [@osolmaz](https://github.com/osolmaz), [@mushuiyu886](https://github.com/mushuiyu886), [@ai-hpc](https://github.com/ai-hpc), and [@TurboTheTurtle](https://github.com/TurboTheTurtle). - Channels/mobile: add the QQBot group mention toggle, improve iPad and iPhone control surfaces, and expose the active connection host in the TUI footer. ([#91423](openclaw/openclaw#91423), [#91557](openclaw/openclaw#91557), [#89909](openclaw/openclaw#89909)) Thanks [@cxyhhhhh](https://github.com/cxyhhhhh), [@Solvely-Colin](https://github.com/Solvely-Colin), and [@baskduf](https://github.com/baskduf). - Performance: prewarm TUI runtime plugins, deduplicate plugin auto-enable fanout, trim dense text-delta snapshots, and reuse prepared startup model metadata. ([#90782](openclaw/openclaw#90782), [#89978](openclaw/openclaw#89978), [#91580](openclaw/openclaw#91580), [#91531](openclaw/openclaw#91531)) Thanks [@RomneyDa](https://github.com/RomneyDa) and [@ai-hpc](https://github.com/ai-hpc). ##### Fixes - Agent/session recovery: drop stale approval follow-ups after session rebind, remove drained reply-queue items by identity, recover stale main and visible replies, preserve Codex context-engine compaction ownership, lower the default compaction timeout to 180 seconds while respecting explicit configuration, and keep provider-failure terminal lifecycle state correct. ([#85679](openclaw/openclaw#85679), [#91450](openclaw/openclaw#91450), [#91566](openclaw/openclaw#91566), [#91840](openclaw/openclaw#91840), [#91590](openclaw/openclaw#91590), [#91361](openclaw/openclaw#91361), [#91895](openclaw/openclaw#91895)) Thanks [@openperf](https://github.com/openperf), [@yetval](https://github.com/yetval), [@joshavant](https://github.com/joshavant), [@wangmiao0668000666](https://github.com/wangmiao0668000666), and [@TurboTheTurtle](https://github.com/TurboTheTurtle). - User-visible content boundaries: suppress Codex/Harmony protocol artifacts, neutralize browser and LanceDB memory media directives, redact transcript images, and preserve native `/compact` replies through source suppression. ([#89151](openclaw/openclaw#89151), [#91422](openclaw/openclaw#91422), [#91425](openclaw/openclaw#91425), [#91529](openclaw/openclaw#91529), [#90212](openclaw/openclaw#90212)) Thanks [@joelnishanth](https://github.com/joelnishanth), [@pgondhi987](https://github.com/pgondhi987), [@joshavant](https://github.com/joshavant), and [@snowzlm](https://github.com/snowzlm). - Channel delivery: keep WhatsApp captured replies attached to the successor controller after restart, retry Feishu rate limits, preserve Mattermost thread replies, canonicalize LINE webhook paths, restore Discord reply hydration and runtime timeout exports, and show OpenAI Realtime WebRTC assistant transcripts. ([#85823](openclaw/openclaw#85823), [#89659](openclaw/openclaw#89659), [#91684](openclaw/openclaw#91684), [#91649](openclaw/openclaw#91649), [#90263](openclaw/openclaw#90263), [#91686](openclaw/openclaw#91686), [#90426](openclaw/openclaw#90426)) Thanks [@itsuzef](https://github.com/itsuzef), [@ladygege](https://github.com/ladygege), [@jacobtomlinson](https://github.com/jacobtomlinson), [@fuller-stack-dev](https://github.com/fuller-stack-dev), and [@shushushv](https://github.com/shushushv). - Cron: cancel active task runs cleanly, preserve terminal timeout/cancel state, and recover no-deliver tool warnings instead of silently losing the outcome. ([#90666](openclaw/openclaw#90666), [#90678](openclaw/openclaw#90678)) Thanks [@ai-hpc](https://github.com/ai-hpc). - Gateway/config/auth: share the approval runtime socket token, replace arrays explicitly in `config.patch`, skip the deleted-agent guard only for valid ACP harness sessions, surface headless LaunchAgent state, verify SQLite auth migration before cleanup, and arm QMD startup maintenance. ([#87105](openclaw/openclaw#87105), [#91551](openclaw/openclaw#91551), [#91219](openclaw/openclaw#91219), [#91614](openclaw/openclaw#91614), [#91740](openclaw/openclaw#91740), [#91978](openclaw/openclaw#91978)) Thanks [@fuller-stack-dev](https://github.com/fuller-stack-dev) and [@scotthuang](https://github.com/scotthuang). - Providers/Codex: clarify quota errors, restore the Codex synthetic usage line, canonicalize Codex protocol assets, require API-key auth for realtime voice, normalize ACP model refs, preserve Gemma 4 `reasoning_content`, and avoid guardian review for local models. ([#91390](openclaw/openclaw#91390), [#91709](openclaw/openclaw#91709), [#91507](openclaw/openclaw#91507), [#91567](openclaw/openclaw#91567), [#88630](openclaw/openclaw#88630), [#91696](openclaw/openclaw#91696)) Thanks [@hxy91819](https://github.com/hxy91819), [@brokemac79](https://github.com/brokemac79), [@RomneyDa](https://github.com/RomneyDa), [@joshavant](https://github.com/joshavant), and [@Coder-Wangyankun](https://github.com/Coder-Wangyankun). - Updates/builds: recover package Gateway restarts after refresh failure, expose plugin convergence repair, fall back to Corepack in PATH-less pnpm environments, seed the correct Docker store packages, and keep ClawHub dry-run and publish paths reusable. ([#91581](openclaw/openclaw#91581), [#91599](openclaw/openclaw#91599), [#91547](openclaw/openclaw#91547), [#91591](openclaw/openclaw#91591)) Thanks [@fuller-stack-dev](https://github.com/fuller-stack-dev), [@sallyom](https://github.com/sallyom), and [@Patrick-Erichsen](https://github.com/Patrick-Erichsen). - UI: require explicit user intent before opening chat sessions and drain restored chat queues after session switches. ([#91480](openclaw/openclaw#91480)) Thanks [@TurboTheTurtle](https://github.com/TurboTheTurtle). - Android: avoid the `dataSync` foreground-service type for persistent nodes. ([#80082](openclaw/openclaw#80082)) Thanks [@davelutztx](https://github.com/davelutztx). - Native hooks: bound relay lifetimes so abandoned native hook connections cannot linger indefinitely. ([#91550](openclaw/openclaw#91550)) Thanks [@joshavant](https://github.com/joshavant). </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/1040

fix(imessage): surface inbound startup diagnostics

5dbea4e

openclaw-barnacle Bot added channel: imessage Channel integration: imessage size: S maintainer Maintainer-authored PR labels Jun 9, 2026

clawsweeper Bot added rating: 🦐 gold shrimp Decent PR readiness signal, but merge confidence is limited. status: ⏳ waiting on author ClawSweeper has contributor-facing work open and is waiting for author action. P2 Normal backlog priority with limited blast radius. labels Jun 9, 2026

fix(imessage): include from-me drop diagnostics

597684c

This comment has been minimized.

Sign in to view

omarshahine merged commit 6c045c5 into main Jun 10, 2026
328 of 340 checks passed

omarshahine deleted the fix/imessage-inbound-startup-diagnostics branch June 10, 2026 02:10

Haderach-Ram mentioned this pull request Jun 10, 2026

Ecosystem Digest — 2026-06-10 Haderach-Ram/openclaw-radar#35

Open

github-actions Bot mentioned this pull request Jun 10, 2026

📡 Upstream Digest — 2026-06-10 02:39 UTC curtismercier/openclaw-mods#1050

Open

omarshahine mentioned this pull request Jun 10, 2026

iMessage send can wedge on long-lived RPC; add one-shot send-rich fallback and receive-side troubleshooting #90850

Closed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

fix(imessage): surface inbound startup diagnostics#91785

fix(imessage): surface inbound startup diagnostics#91785
omarshahine merged 2 commits into
mainfrom
fix/imessage-inbound-startup-diagnostics

omarshahine commented Jun 9, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented Jun 9, 2026 •

edited

Loading

Uh oh!

omarshahine commented Jun 9, 2026

Uh oh!

clawsweeper Bot commented Jun 9, 2026 •

edited

Loading

Uh oh!

This comment has been minimized.

omarshahine commented Jun 10, 2026

Uh oh!

clawsweeper Bot commented Jun 10, 2026 •

edited

Loading

Uh oh!

omarshahine commented Jun 10, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

Uh oh!

Conversation

omarshahine commented Jun 9, 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 Jun 9, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

omarshahine commented Jun 9, 2026

Uh oh!

clawsweeper Bot commented Jun 9, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

This comment has been minimized.

omarshahine commented Jun 10, 2026

Uh oh!

clawsweeper Bot commented Jun 10, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

omarshahine commented Jun 10, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

omarshahine commented Jun 9, 2026 •

edited

Loading

clawsweeper Bot commented Jun 9, 2026 •

edited

Loading

clawsweeper Bot commented Jun 9, 2026 •

edited

Loading

clawsweeper Bot commented Jun 10, 2026 •

edited

Loading