fix(auto-reply): guard missing dispatcher getFailedCounts without weakening the SDK type

[clawsweeper]

Makes #89148 merge-ready for the ClawSweeper automerge loop.
The edit pass should inspect the live PR diff, review comments, and failing checks; rebase if needed; keep the contributor branch credited; and stop only when validation is green or an external blocker is proven.

ClawSweeper 🐠 replacement reef notes:

• Cluster: automerge-openclaw-openclaw-89148
• Source PRs: fix(auto-reply): guard missing dispatcher getFailedCounts without weakening the SDK type #89148
• Credit: Source PR: fix(auto-reply): guard missing dispatcher getFailedCounts without weakening the SDK type #89148
• Validation: pnpm check:changed
• Replacement reason: ClawSweeper could not update the source PR branch directly, so it opened a writable replacement PR instead.
• Automerge requested by: @Takhoffman

• Repair fallback: GitHub rejected the repair branch push because it updates workflow files and the ClawSweeper app token does not have workflows permission

Inherited issue-closing references from the source PR:
Fixes #89116

Co-author credit kept:

• @Alix-007: Co-authored-by: Alix-007 267018309+Alix-007@users.noreply.github.com

fish notes: model gpt-5.5, reasoning high; reviewed against 0bdfb4a.

[clawsweeper]

Codex review: passed. Reviewed June 2, 2026, 12:16 AM ET / 04:16 UTC.

Summary
Adds defensive failed-count reads in auto-reply/ACP accounting and Feishu fallback paths, plus a focused regression test, while keeping ReplyDispatcher.getFailedCounts required.

PR surface: Source +24, Tests +35. Total +59 across 5 files.

Reproducibility: yes. from source inspection. Current main calls dispatcher.getFailedCounts().final and sibling Feishu/ACP paths call getFailedCounts() directly, so a runtime dispatcher missing that method follows a clear TypeError path; the source PR also supplied terminal before/after proof.

Review metrics: 1 noteworthy metric.

• Dispatcher API surface: 0 public fields changed; 1 internal counts view added. This matters because the reported crash needs tolerant runtime accounting, but changing the exported dispatcher contract would be plugin SDK compatibility risk.

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

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

Next step before merge

• [P2] No repair lane is needed; review findings are empty and the opted-in PR can proceed through automerge or maintainer landing gates.

Security
Cleared: The diff only changes TypeScript dispatcher count reads and a focused test; it does not add dependency, CI, secret, install, workflow, or code-execution surface.

Review details

Best possible solution:

Land the narrow internal guard with the focused regression coverage while keeping the plugin-facing dispatcher API unchanged.

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

Yes from source inspection. Current main calls dispatcher.getFailedCounts().final and sibling Feishu/ACP paths call getFailedCounts() directly, so a runtime dispatcher missing that method follows a clear TypeError path; the source PR also supplied terminal before/after proof.

Is this the best way to solve the issue?

Yes. The PR fixes the crash at the internal count-reading boundary and covers sibling direct call sites without weakening the SDK-visible ReplyDispatcher type.

AGENTS.md: found and applied where relevant.

Codex review notes: model gpt-5.5, reasoning high; reviewed against ffbd02fe8ed9.

Label changes

Label justifications:

• P1: The PR fixes a reported auto-reply/Feishu dispatch crash affecting real users on the latest release.
• rating: 🦞 diamond lobster: Overall readiness is 🦞 diamond lobster; proof is 🦞 diamond lobster and patch quality is 🦞 diamond lobster.
• status: 🚀 automerge armed: This PR is in ClawSweeper's automerge lane. Sufficient (terminal): The linked source PR body includes after-fix terminal proof against the production helper plus focused Vitest/Feishu output, and the replacement head has a successful Real behavior proof check.
• proof: sufficient: Contributor real behavior proof is sufficient. The linked source PR body includes after-fix terminal proof against the production helper plus focused Vitest/Feishu output, and the replacement head has a successful Real behavior proof check.

Evidence reviewed

PR surface:

Source +24, Tests +35. Total +59 across 5 files.

View PR surface stats

Area	Files	Added	Removed	Net
Source	4	31	7	+24
Tests	1	35	0	+35
Docs	0	0	0	0
Config	0	0	0	0
Generated	0	0	0	0
Other	0	0	0	0
Total	5	66	7	+59

What I checked:

• Repository policy read: Root policy and the extensions scoped policy were read; the relevant guidance is to review beyond the diff and treat plugin SDK compatibility as upgrade-sensitive. (AGENTS.md:1, ffbd02fe8ed9)
• Scoped extensions policy read: The Feishu path is under extensions/, whose scoped policy keeps plugin code on SDK/local boundaries and treats bundled plugins like third-party plugins. (extensions/AGENTS.md:1, ffbd02fe8ed9)
• Current-main crash point: Current main calls dispatcher.getFailedCounts().final in final-outcome accounting, so a runtime dispatcher missing the method follows the reported TypeError path. (src/auto-reply/reply/dispatch-from-config.ts:783, ffbd02fe8ed9)
• SDK-visible contract remains required on main: ReplyDispatcher.getFailedCounts is required in the dispatcher type, and that type is exported through the plugin SDK reply runtime, so making it optional would be a compatibility-sensitive API change. (src/auto-reply/reply/reply-dispatcher.types.ts:18, ffbd02fe8ed9)
• Plugin SDK export checked: The plugin SDK reply runtime exports ReplyDispatcher, confirming the dispatcher type is plugin-facing. (src/plugin-sdk/reply-runtime.ts:48, ffbd02fe8ed9)
• PR keeps public type and adds internal view: The PR leaves ReplyDispatcher.getFailedCounts required and adds DispatcherOutcomeCountsView plus readDispatcherFailedCounts for tolerant internal reads. (src/auto-reply/reply/reply-dispatcher.types.ts:22, 0bdfb4adebc6)

Likely related people:

• Rob Pierson: Remote history shows commit b474f429ee4b added the plugin SDK reply payload hook work and modified dispatch-from-config.ts, dispatch-acp-delivery.ts, and reply-dispatcher.types.ts, including the dispatcher count contract area. (role: introduced dispatcher/counting surface; confidence: high; commits: b474f429ee4b; files: src/auto-reply/reply/dispatch-from-config.ts, src/auto-reply/reply/dispatch-acp-delivery.ts, src/auto-reply/reply/reply-dispatcher.types.ts)
• ArthurNie: Remote history shows commit 7c15c2765ebb added and refined the Feishu no-visible-reply fallback behavior that contains the two guarded Feishu call sites in this PR. (role: recent Feishu fallback contributor; confidence: high; commits: 7c15c2765ebb; files: extensions/feishu/src/bot.ts, src/auto-reply/reply/dispatch-from-config.ts)
• Ted Li: Remote history shows recent reply-routing work in dispatch-from-config.ts and dispatch-acp-delivery.ts, making this a useful adjacent routing signal for review or follow-up. (role: recent auto-reply routing contributor; confidence: medium; commits: 6cb06f5fbcf5; files: src/auto-reply/reply/dispatch-from-config.ts, src/auto-reply/reply/dispatch-acp-delivery.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]

🦞✅
ClawSweeper merged this PR after the passing review.

Source: clawsweeper[bot]
Feedback: structured ClawSweeper verdict: pass (sha=0bdfb4adebc64c0bf4700516e6d3e118ef6519bd)
Merge status: merged by ClawSweeper automerge
Merged at: 2026-06-02T04:16:58Z
Merge commit: 63ed9adfe90a

What merged:

• Adds defensive failed-count reads in auto-reply/ACP accounting and Feishu fallback paths, plus a focused regression test, while keeping ReplyDispatcher.getFailedCounts required.
• PR surface: Source +24, Tests +35. Total +59 across 5 files.
• Reproducibility: yes. from source inspection. Current main calls dispatcher.getFailedCounts().final and si ... issing that method follows a clear TypeError path; the source PR also supplied terminal before/after proof.

Automerge notes:

• PR branch already contained follow-up commit before automerge: fix(auto-reply): guard missing dispatcher getFailedCounts without wea…

The automerge loop is complete.

Automerge progress:

• 2026-06-02 04:16:45 UTC review passed 0bdfb4adebc6 (structured ClawSweeper verdict: pass (sha=0bdfb4adebc64c0bf4700516e6d3e118ef651...)

• 2026-06-02 04:17:01 UTC merged 0bdfb4adebc6 (merged by ClawSweeper automerge)