* fix(agents): suppress Write/Edit failed warning on response-timeout false-failure (#55424)
Reporter sees '⚠️ Write failed' / '⚠️ Edit failed' warnings on Feishu (and other channels) even though the file was 100% saved successfully (8 of 8 verified writes succeeded; warning shown for all 8). Source path: tool-mutation records lastToolError.timedOut=true with a fileTarget when a write/edit tool ack reply times out after the disk mutation has already completed, then resolveToolErrorWarningPolicy goes through the default mutating-tool branch and emits the misleading failure summary.
Add a narrow gate inside resolveToolErrorWarningPolicy that suppresses the warning only when both lastToolError.timedOut is true AND lastToolError.fileTarget is defined. fileTarget is set by tool-mutation.ts only for the write/edit family (FILE_MUTATING_TOOL_NAMES), so this branch never matches exec/message/cron/gateway mutating-tool timeouts where the disk-write idempotency reasoning does not apply. Real file failures (no timeout) and timeouts without recorded fileTarget keep their visible warnings.
* fix: recover completed write timeouts safely
* fix: bound write timeout recovery precheck
* fix: type write recovery precheck fallback
* test: complete write recovery result mock
* test: isolate e2e timeout fixture shims
* test: stabilize e2e timeout fixture path
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Clarify that OpenAI Realtime voice is billed through OpenAI Platform credits, not Codex/ChatGPT subscription quota, for Voice Call and Control UI Talk.
Document the direct Platform API key path, the `openai-codex` OAuth client-secret path, the quota symptom, and the Platform billing fix. Keep the changelog note crediting @lonexreb.
Closes#76498.
Co-authored-by: lonexreb <reach2shubhankar@gmail.com>
Keep the Codex app-server full attempt watchdog armed after a terminal turn notification is queued, so a wedged notification projector cannot leave a run stuck indefinitely.
Proof:
- `git diff --check origin/main...HEAD`
- `node scripts/run-oxlint.mjs extensions/codex/src/app-server/run-attempt.ts extensions/codex/src/app-server/run-attempt.test.ts`
- `node scripts/run-vitest.mjs run extensions/codex/src/app-server/run-attempt.test.ts --testNamePattern "keeps the attempt watchdog armed"` passed in PR proof (`1 passed | 232 skipped`)
- `OPENCLAW_TESTBOX=1 pnpm check:changed` passed in `tbx_01kskyg44ej461k574jee8ffjc`
- CI required checks green after `build-artifacts` rerun job `78031279635` passed
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
Fix Claude CLI skill prompt handling so native skill plugin materialization is prepared before prompt suppression, with the prompt fallback preserved when plugin args are unavailable. Also keeps direct prepared-run callers covered by an execute-time fallback.
Fixes#87063.
Co-authored-by: uday <udaymanish.thumma@gmail.com>
Regression test for the binary stall fix: when rawResponseItem/completed
arrives with a non-assistant type (e.g. "reasoning") and all tracked
items have completed, the completion idle watch must stay armed so the
stall is caught in 60s, not 30 minutes.
Refs openclaw/openclaw#87071
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When the codex binary emits rawResponseItem/completed and all tracked
items have completed (activeTurnItemIds empty, no active requests), the
binary should deliver turn/completed imminently. Previously, a
rawResponseItem/completed that didn't qualify as a post-tool assistant
completion would actively disarm the completion idle watch, leaving only
the 30-minute terminal timeout to catch a stalled binary. This caused
turns to hang for up to 30 minutes when the OpenAI Responses API fails
to deliver response.completed to the binary.
Now, rawResponseItem/completed with no active items arms the 60s
completion idle watch and is excluded from the disarm path, so stalled
binaries are detected in 60s instead of 30 minutes.
Refs openclaw/openclaw#87071
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Restart stale local node-host processes when they reconnect to a newer gateway with a released-version mismatch, so launchd/systemd can restart them with updated code instead of leaving old dynamic imports alive.
Adds gateway mismatch detail propagation, node-host terminal pause handling, and regression coverage for the GatewayClient reconnect-pause path.
Verification:
- node scripts/run-vitest.mjs run src/gateway/client.test.ts -t 'CLIENT_VERSION_MISMATCH' --reporter=verbose
- node scripts/run-vitest.mjs run src/gateway/server.node-version-mismatch.test.ts src/node-host/runner.credentials.test.ts src/gateway/client.test.ts --reporter=verbose
- /Users/steipete/Projects/agent-skills/skills/autoreview/scripts/autoreview --mode local
- Crabbox AWS run_292dcbfd78d9: focused GatewayClient mismatch regression plus server/node-host mismatch tests passed
Co-authored-by: scotthuang <scotthuang@tencent.com>
