Summary:
- The PR exports `ensureAbsoluteDirectory` through the fs-safe/SDK runtime facades and routes browser download ... through safe output directory/file helpers with focused tests, a changelog entry, and SDK API hash updates.
- Reproducibility: yes. at source level: current main creates browser download/output roots with raw recursive ... jection coverage for that path. I did not run a live browser runtime reproduction in this read-only review.
Automerge notes:
- PR branch already contained follow-up commit before automerge: fix(browser): use fs-safe output directory helper
- PR branch already contained follow-up commit before automerge: docs(changelog): mention browser fs-safe hardening
- PR branch already contained follow-up commit before automerge: fix(browser): harden download output writes
Validation:
- ClawSweeper review passed for head a9c9570f66.
- Required merge gates passed before the squash merge.
Prepared head SHA: a9c9570f66
Review: https://github.com/openclaw/openclaw/pull/78780#issuecomment-4394146682
Co-authored-by: jesse-merhi <79823012+jesse-merhi@users.noreply.github.com>
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Summary:
- The PR adds a `before_agent_run` plugin hook with pass/block decisions, redacted blocked-turn persistence, diagnostics/docs/changelog updates, and focused runner, gateway, session, and plugin tests.
- Reproducibility: not applicable. as a feature PR rather than a current-main bug report. Current main lacks ` ... un`, while the PR head adds source coverage and copied live Gateway/WebChat log proof for the new behavior.
Automerge notes:
- PR branch already contained follow-up commit before automerge: fix: trim before agent hook PR scope
- PR branch already contained follow-up commit before automerge: fix: keep before-agent blocks redacted
- PR branch already contained follow-up commit before automerge: fix: keep runtime context out of model prompt
- PR branch already contained follow-up commit before automerge: docs: refresh config baseline after rebase
- PR branch already contained follow-up commit before automerge: fix: align blocked turn clients with redacted content
- PR branch already contained follow-up commit before automerge: fix: remove out-of-scope client block UI changes
Validation:
- ClawSweeper review passed for head 767e46fde8.
- Required merge gates passed before the squash merge.
Prepared head SHA: 767e46fde8
Review: https://github.com/openclaw/openclaw/pull/75035#issuecomment-4351843275
Co-authored-by: Jesse Merhi <jessejmerhi@gmail.com>
Co-authored-by: jesse-merhi <79823012+jesse-merhi@users.noreply.github.com>
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Adds bounded Talk lifecycle/audio diagnostics and session recovery metrics for OTEL, Prometheus, and stability snapshots after the Talk SDK/session refactor. Includes changelog/docs updates and Testbox/live proof.
Two correctness fixes from code review.
1. Zod schema (src/config/zod-schema.agent-runtime.ts) was strict and
rejected tools.loopDetection.postCompactionGuard.* keys at validation
time, making the guard's documented configurability inaccessible at
gateway startup. Adds ToolLoopPostCompactionGuardSchema with both
optional fields and wires it into ToolLoopDetectionSchema.
2. The runner observation cursor in pi-embedded-runner/run.ts used
absolute indices into state.toolCallHistory, but that array is
trimmed at historySize (default 30). Once the buffer was full, new
records shifted out from under the cursor and the guard silently
missed every loop in long-running sessions. Replaces the index
cursor with a monotonic toolOutcomeSeq on SessionState that
recordToolCallOutcome bumps on each observable push (unmatched
branch only, mirroring the prior cursor's effective semantics).
The runner now reads the most recent (currentSeq - lastSeq) entries
from the tail of toolCallHistory, which is trim-resilient.
Adds zod parse tests for the new config keys (valid, empty, unknown
key, non-positive, non-integer) and a runner regression test that
seeds toolCallHistory at the trim cap before triggering a
post-compaction loop, asserting the abort still fires.
Refs #77474
Summary:
- Adds a plugin-owned CLI backend argument rewrite hook and wires Anthropic `claude-cli` to translate non-off `/think` levels into Claude Code `--effort`, with docs, changelog, API baseline, and tests.
- Reproducibility: yes. Current main has a high-confidence source reproduction: choose `claude-cli`, set a non ... builds argv from backend args that contain no `--effort` even though `thinkLevel` exists on the run params.
Automerge notes:
- No ClawSweeper repair was needed after automerge opt-in.
Validation:
- ClawSweeper review passed for head be17754009.
- Required merge gates passed before the squash merge.
Prepared head SHA: be17754009
Review: https://github.com/openclaw/openclaw/pull/77410#issuecomment-4372812685
Co-authored-by: stainlu <stainlu@newtype-ai.org>
