Summary:
- The PR removes the auto-reply compaction-failure session reset hook, adds preserved-session recovery guidance for overflow/compaction failure paths, and updates focused tests, docs, and the changelog.
- Reproducibility: yes. at source level with high confidence. Current main routes both embedded overflow paylo ... resetSessionAfterCompactionFailure, and the PR body includes before/after terminal proof of those branches.
Automerge notes:
- PR branch already contained follow-up commit before automerge: fix(auto-reply): drop dead compaction reset hook
- PR branch already contained follow-up commit before automerge: fix(auto-reply): preserve sessions after compaction failures
Validation:
- ClawSweeper review passed for head 193d3c0fdd.
- Required merge gates passed before the squash merge.
Prepared head SHA: 193d3c0fdd
Review: https://github.com/openclaw/openclaw/pull/70479#issuecomment-4325128777
Co-authored-by: FullerStackDev <263060202+fuller-stack-dev@users.noreply.github.com>
Co-authored-by: vincentkoc <25068+vincentkoc@users.noreply.github.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: takhoffman
Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>
Summary:
- The branch adds an abort-aware dispatcher-idle wait after successful same-channel and direct ACP block replies, plus regression tests and a changelog entry.
- Reproducibility: yes. Current main source shows the same-channel block callback queues dispatcher delivery w ... spatcher idle, and the PR body supplies before/after diagnostic output for the tool-start ordering failure.
Automerge notes:
- PR branch already contained follow-up commit before automerge: [AI-assisted] fix(reply): wait for block replies before tools
Validation:
- ClawSweeper review passed for head 32576209a2.
- Required merge gates passed before the squash merge.
Prepared head SHA: 32576209a2
Review: https://github.com/openclaw/openclaw/pull/83722#issuecomment-4480639845
Co-authored-by: JARVIS-Glasses <284122573+JARVIS-Glasses@users.noreply.github.com>
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: takhoffman
Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>
Eliminates the per-call auth-filter loop that every /models invocation
(Discord/Telegram pickers, CLI, status commands) was paying — 30 unique
providers × ~600 ms each of plugin-runtime / external-CLI / auth-profile
discovery, done fresh on every call (~20 s per call).
warmCurrentProviderAuthState builds a provider->boolean map once at
gateway startup against a single AuthProfileStore scoped to every
candidate provider, and hasAuthForModelProvider consults the prepared
map first and short-circuits. The map is invalidated on config reload
alongside resetModelCatalogCache so the next read after a relevant
config change rewarms.
Per /models: ~20,569 ms → ~5 ms (~4,100×).
One-time startup warm cost: ~49 s (cold catalog + auth sweep), logged
via gateway log.info on completion.
Summary:
- This replacement PR adds inbound delivery diagnostic events, gateway status counters and warnings, transport ... ut, Prometheus/OpenTelemetry metrics, docs, changelog, and regression coverage for gateway delivery health.
- Reproducibility: no. high-confidence live reproduction of the original Feishu failure was run here. Source i ... ch/turn telemetry, and the source PR supplies after-fix live output for the connected WebChat gateway path.
Automerge notes:
- PR branch already contained follow-up commit before automerge: fix(types): restore PR conflict resolution type checks
Validation:
- ClawSweeper review passed for head 6ffe08a9c7.
- Required merge gates passed before the squash merge.
Prepared head SHA: 6ffe08a9c7
Review: https://github.com/openclaw/openclaw/pull/85016#issuecomment-4510224436
Co-authored-by: Andi Liao <liaoandi95@gmail.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: takhoffman
Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>
Summary:
- This PR changes queued reply followups so user_request items no longer carry or inherit a source abort signal, preserves room_event abort signals, adds focused regression coverage, and updates CHANGELOG.md.
- Reproducibility: yes. at source level. Current main attaches and later falls back to opts.abortSignal for qu ... ore-fix regression failures for the two implicated paths; I did not execute tests in this read-only review.
Automerge notes:
- PR branch already contained follow-up commit before automerge: Preserve queued Telegram topic followups
Validation:
- ClawSweeper review passed for head 96fa0f69ba.
- Required merge gates passed before the squash merge.
Prepared head SHA: 96fa0f69ba
Review: https://github.com/openclaw/openclaw/pull/83827#issuecomment-4483451436
Co-authored-by: VACInc <3279061+VACInc@users.noreply.github.com>
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: takhoffman
Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>
Summary:
- The replacement PR adds a `watch-targets` skills snapshot invalidation when `ensureSkillsWatcher` rebuilds f ... root set, reads the snapshot version after watcher setup, adds regression tests, and updates the changelog.
- Reproducibility: yes. Source inspection shows current main rebuilds the skills watcher on changed root targe ... the version before watcher setup; I did not run a live Gateway mount reproduction in this read-only review.
Automerge notes:
- PR branch already contained follow-up commit before automerge: fix(skills): refresh snapshots when watch roots change
Validation:
- ClawSweeper review passed for head 2677dcc35a.
- Required merge gates passed before the squash merge.
Prepared head SHA: 2677dcc35a
Review: https://github.com/openclaw/openclaw/pull/83823#issuecomment-4483425019
Co-authored-by: hclsys <hclsys@openclaw.ai>
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: takhoffman
Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>
Summary:
- This PR removes the WebChat special-case from auto-reply chunk limit/mode resolution, adds WebChat override regression tests, and records the fix in the changelog.
- Reproducibility: yes. from source inspection rather than runtime execution: current main returns the fallbac ... bchat` before reading `cfg.channels`, so a configured `channels.webchat.textChunkLimit` cannot take effect.
Automerge notes:
- PR branch already contained follow-up commit before automerge: fix(auto-reply): honor webchat textChunkLimit/chunkMode config overri…
Validation:
- ClawSweeper review passed for head cd9ac01a36.
- Required merge gates passed before the squash merge.
Prepared head SHA: cd9ac01a36
Review: https://github.com/openclaw/openclaw/pull/83742#issuecomment-4481570742
Co-authored-by: luyao618 <364939526@qq.com>
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: takhoffman
Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>
Summary:
- The PR passes the effective OpenAI/Codex auth provider set into `/models` provider-header labeling, adds focused regression tests, and records the user-facing fix in the changelog.
- Reproducibility: yes. Current main lacks `acceptedProviderIds` in the shared picker header path, and the source PR's Mantis baseline/candidate proof shows the visible Telegram header mismatch and after-fix OAuth label.
Automerge notes:
- PR branch already contained follow-up commit before automerge: fix(models): label picker auth via effective provider order
Validation:
- ClawSweeper review passed for head 8ca2924adc.
- Required merge gates passed before the squash merge.
Prepared head SHA: 8ca2924adc
Review: https://github.com/openclaw/openclaw/pull/83726#issuecomment-4480805713
Co-authored-by: Stellar鱼 <2182712990@qq.com>
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: takhoffman
Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>
Summary:
- The PR changes collect-mode follow-up queue routing so unresolved-origin items can batch with a single resolved route and later compatible items can resume batching after a true cross-channel drain.
- Reproducibility: yes. at source level: current main treats unkeyed-plus-same-keyed queue items as cross-chan ... failing path is directly visible in `src/utils/queue-helpers.ts` and `src/auto-reply/reply/queue/drain.ts`.
Automerge notes:
- PR branch already contained follow-up commit before automerge: Merge remote-tracking branch 'origin/main' into maint-83701-20260518
Validation:
- ClawSweeper review passed for head e6ad029e23.
- Required merge gates passed before the squash merge.
Prepared head SHA: e6ad029e23
Review: https://github.com/openclaw/openclaw/pull/83701#issuecomment-4479943100
Co-authored-by: Andy Ye <35905412+TurboTheTurtle@users.noreply.github.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: takhoffman
Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>
Follow-up and main reply paths re-entered each embedded fallback candidate
with the same queued transcript prompt. After the first candidate persisted
that queued user message, later candidates appended it again. Failed
embedded candidates could also persist an assistant error stub on each
retry, leaving same-role transcript runs that downstream providers reject.
The fallback callers now keep two persistence latches for one fallback run:
queuedUserMessagePersistedAcrossFallback flips from onUserMessagePersisted,
and assistantErrorPersistedAcrossFallback flips only after the session guard
actually persists an assistant stopReason="error" message. Later candidates
suppress only the entries that were already written, so CLI or otherwise
non-persisting failures do not hide the first embedded error separator.
Plumb the assistant-error persistence callback through the embedded runner,
attempt params, and session guard wrapper. Add guard and runner regression
tests for all-embedded fallback retries and CLI-to-embedded fallback.
Closes#83404
Summary:
- The PR changes Discord reply delivery, sanitizer, and queued follow-up auto-reply paths so explicit verbose tool-progress payloads are delivered while final assistant replies still use the privacy sanitizer.
- Reproducibility: yes. source-level: current main strips tool-looking Discord payload text at the front-chann ... ds compaction events in queued follow-up runs. I did not run a live Discord repro in this read-only review.
Automerge notes:
- Ran the ClawSweeper repair loop before final review.
- Included post-review commit in the final squash: fix: gate queued follow-up progress when verbose is off
- Included post-review commit in the final squash: fix: preserve queued verbose progress under preview suppression
- Included post-review commit in the final squash: ci: rerun discord verbose progress PR
- Included post-review commit in the final squash: fix: preserve Discord verbose progress after rebase
- Included post-review commit in the final squash: fix: serialize discord queued progress
- Included post-review commit in the final squash: Fix Discord verbose tool progress delivery
Validation:
- ClawSweeper review passed for head fd845e773a.
- Required merge gates passed before the squash merge.
Prepared head SHA: fd845e773a
Review: https://github.com/openclaw/openclaw/pull/80042#issuecomment-4414121881
Co-authored-by: Clawsistant <clawsistant@users.noreply.github.com>
Co-authored-by: anyech <anyech@gmail.com>
Co-authored-by: OpenClaw Assistant <assistant@openclaw.local>
Co-authored-by: Shadow <hi@shadowing.dev>
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: thewilloftheshadow
Co-authored-by: thewilloftheshadow <35580099+thewilloftheshadow@users.noreply.github.com>
Summary:
- The PR adds a generic inbound debounce `cancelKey`, uses Telegram stop-like controls to cancel same-chat pen ... buffers and bypass debounce, and adds focused Telegram regression coverage plus updated channel test mocks.
- Reproducibility: yes. by source inspection: current main enqueues Telegram text through inbound debounce bef ... nly has flush semantics for pending keyed work. I did not run a live Telegram repro in this read-only pass.
Automerge notes:
- PR branch already contained follow-up commit before automerge: Fix Telegram stop debounce bypass
Validation:
- ClawSweeper review passed for head 19245a341d.
- Required merge gates passed before the squash merge.
Prepared head SHA: 19245a341d
Review: https://github.com/openclaw/openclaw/pull/83248#issuecomment-4472300906
Co-authored-by: VACInc <3279061+VACInc@users.noreply.github.com>
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: takhoffman
Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>
Jason (Json)