Materializes prompt-visible skills into a protected sandbox-readable workspace for rw sandboxes, refreshes Docker/SSH/OpenShell views, and hardens stale or poisoned remote skill copies. Fixes#90410.
Summary:
- The PR updates background-session command tokenization to avoid catastrophic regex backtracking and adds `deriveSessionName` regression tests for quoted and backslash-heavy commands.
- PR surface: Source 0, Tests +26. Total +26 across 2 files.
- Reproducibility: yes. with high confidence from source inspection and supplied terminal proof: current `main ... shows before/after timing for the production helper. I did not run tests because this review is read-only.
Automerge notes:
- PR branch already contained follow-up commit before automerge: fix(agents): treat backslash as literal inside single-quoted session …
- PR branch already contained follow-up commit before automerge: fix(agents): prevent ReDoS in background-session name derivation
Validation:
- ClawSweeper review passed for head 0a38952fc8.
- Required merge gates passed before the squash merge.
Prepared head SHA: 0a38952fc8
Review: https://github.com/openclaw/openclaw/pull/91233#issuecomment-4643821335
Co-authored-by: yetval <yetvald@gmail.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>
Merged via squash.
Prepared head SHA: b6fd32ed6e
Local prep note: pnpm build passed. pnpm check hit the npm shrinkwrap guard because @anthropic-ai/sdk@0.100.1 is no longer resolvable before 2026-05-24T20:18:43Z; the same shrinkwrap guard failure reproduces on current origin/main at 66b91d78fe, and this PR does not touch dependency manifests or lockfiles.
Co-authored-by: ngutman <1540134+ngutman@users.noreply.github.com>
Reviewed-by: @ngutman
* fix(infra/agents): session-routing guard for coalesced gateway restart continuations (#86742)
When two sessions issue gateway.restart with continuationMessage close
together, the scheduler Path B updatePendingRestartEmitHooks
unconditionally overwrote the existing pending hooks, silently dropping
the first sessions continuation and potentially routing the second
sessions continuation back to the first session (CWE-200 finding
flagged by aisle-research-bot on prior attempt #74443).
Add a session-routing guard: scheduleGatewaySigusr1Restart now accepts
an optional sessionKey and tracks the pending restarts owning session.
Coalesced callers from a different session are rejected at the hook-
update step and the new ScheduledRestart.emitHooksQueued: false field
surfaces the drop to the caller. The gateway tool propagates this as
continuationQueued: false in the tool response, matching #83370 narrow
report-only surface.
Same-session debounce/replace and legacy hookless callers behave the
same as before.
Refs #86742
* fix(infra): preserve queued restart continuation on forced bypass
* fix(infra): make forced restart hook preservation explicit
* fix(infra): guard restart continuation ownership before reschedule
* fix(infra): report hookless coalesced restarts accurately
* fix(infra): trust runtime session for restart sentinel routing
* fix(infra): preserve earlier restart reschedule semantics
* fix(agents): trust runtime session for update continuations
* fix(infra): preserve hookless forced restart continuations
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Completed turns with deliverable assistant text still synthesize failed
tool.result rows but no longer set promptError. Record lastToolError on
that degraded path and treat whitespace-only assistant items as non-
deliverable so orphan tools still fail closed.
Co-authored-by: Cursor <cursoragent@cursor.com>
(cherry picked from commit cb6fbe36c73982e1043186b983f0c03334989b34)
Keep synthesizing failed tool.result records for transcript consistency,
but skip promptError when a completed Codex turn has deliverable assistant
text so channel users still receive the composed reply.
Fixes#91067
Co-authored-by: Cursor <cursoragent@cursor.com>
(cherry picked from commit ffac77ce811eab528bcce81eec99fd8bd6c70cca)
Log warning memory pressure at WARN level, add readable RSS/heap/threshold units, threshold ratio, and a concrete operator next step while preserving raw byte fields for diagnostics consumers.
Fixes#90783
Fixes#90768
Incorporates the send-buffer materialization shape proposed in #90794 by @LiuwqGit, with maintainer fixes for dry-run, gateway delivery, byte-cap, target-validation, and downstream plugin dispatch paths.
* fix(qqbot): migrate group tool policy config
* test: stabilize changed check lanes
* style: format changed main files
* test: align CI matrix expectations
Move the shipped legacy shared-state agent database registry repair into doctor. Runtime now fails fast with a doctor repair hint when the old primary-key shape remains.
Merge disjoint legacy openai-codex model entries into the canonical openai provider without losing safe per-model metadata, params, or models-add markers.
Unsafe provider-level defaults, auth/header/request state, and blocked normalized legacy providers are now preserved for manual cleanup with doctor preview warnings instead of being silently copied into models or repeatedly reported as auto-fixable.
Fixes#90047
Co-authored-by: openperf <16864032@qq.com>
