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>
Addresses three ClawSweeper findings on the fs-watcher commit:
- [P1] auth-profile watcher now handles chokidar 'error' events (logs +
closes once) mirroring the gateway config-reload pattern. Without
this, an unhandled error from chokidar can crash the gateway.
- [P2] auth-profile watcher handle is pushed into postReadySidecars so
stopPostReadySidecarsAfterCloseStarted closes it on gateway shutdown.
- [P2] auth-failure and file-change invalidation paths now schedule a
background rewarm (with a 'reason=' log line). Without this, the next
/models call after an invalidation paid the slow per-provider path
until the next reload. The warmer's existing generation counter
handles concurrent rewarms safely.
Adds a chokidar watcher on every configured agent's auth-profiles.json.
Any change fires clearCurrentProviderAuthState so the next model-listing
call recomputes against the on-disk auth state. Closes the stale-FALSE
direction (user adds auth via codex login, hand-edit, etc.) that the
auth-failure hook can't catch on its own.
When markAuthProfileFailure observes an auth failure at request time
(token rotated, OAuth revoke, etc.), fire a hook that clears the
prepared provider-auth map so the next model-listing call recomputes
against the real auth state. Single mutable hook slot wired up at
gateway startup; no TTL or polling.
Addresses ClawSweeper's P1 freshness finding on #85125 without
reintroducing the TTL.
Summary:
- The PR changes shared, Feishu, Mattermost, Microsoft Teams, and WhatsApp inbound debounce predicates so bare abort text bypasses debounce, then adds focused tests and a changelog entry.
- Reproducibility: yes. source-level. Current main sends bare `stop`, `abort`, and `wait` through a `hasContro ... ()` debounce gate, while the existing abort-aware detector and trigger set already recognize those phrases.
Automerge notes:
- PR branch already contained follow-up commit before automerge: fix(channels): bypass debounce for bare abort triggers [AI-assisted]
- PR branch already contained follow-up commit before automerge: fix(clawsweeper): address review for automerge-openclaw-openclaw-8334…
Validation:
- ClawSweeper review passed for head c96bf84270.
- Required merge gates passed before the squash merge.
Prepared head SHA: c96bf84270
Review: https://github.com/openclaw/openclaw/pull/83348#issuecomment-4473176095
Co-authored-by: IWhatsskill <284122573+IWhatsskill@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 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>
Harden the Codex app-server native execution bridge for OpenClaw sandboxed runs. The change keeps core sandbox policy in OpenClaw while exposing the process, filesystem, and HTTP relay behavior Codex needs inside a scoped exec server.
The large exec-server/test files were split into focused modules before landing, and the PR was rebased onto current main with focused tests, Testbox changed checks, CI, and Codex autoreview green.
Co-authored-by: joshavant <830519+joshavant@users.noreply.github.com>
Summary:
- The PR adds shared blocked-liveness normalization, applies it to agent.wait, gateway dedupe, subagent registry, and announcement paths, and adds regression tests plus a changelog entry.
- Reproducibility: yes. from source inspection: current main accepts blocked lifecycle/wait metadata as ok thr ... gateway wait and registry completion paths. I did not run a live provider overflow in this read-only pass.
Automerge notes:
- PR branch already contained follow-up commit before automerge: fix(agents): normalize blocked wait completions
- PR branch already contained follow-up commit before automerge: fix(agents): surface blocked subagent completions
Validation:
- ClawSweeper review passed for head 224785c8a6.
- Required merge gates passed before the squash merge.
Prepared head SHA: 224785c8a6
Review: https://github.com/openclaw/openclaw/pull/80886#issuecomment-4427552621
Co-authored-by: Andy Ye <35905412+TurboTheTurtle@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>
Adds installRecords to PluginLoadOptions and PluginRuntimeLoadContext so
callers that already hold a PluginMetadataSnapshot can pass the snapshot's
in-memory records instead of forcing each downstream loader to re-read
installs.json. resolvePluginRuntimeLoadContext extracts the records from
the snapshot via extractPluginInstallRecordsFromInstalledPluginIndex,
buildPluginRuntimeLoadOptionsFromValues forwards them, and the setup +
runtime provider load paths in providers.runtime.ts pass them through
from params.pluginMetadataSnapshot. resolvePluginLoadCacheContext uses
the threaded records (falling back to the sync read) and
loader-provenance now uses params.installRecords ?? sync-read instead of
always reading and overlaying.
