* fix(cron): include job name in single-job run history
The cron.runs gateway handler enriches log entries with jobName in the all-jobs scope, but the single-job scope did not pass any job-name lookup into the SQLite run-log reader. Entries returned for one job could therefore reach Control UI without jobName, making the run-history title fall back to the raw job id.
Build a one-entry jobNameById map for the current job and pass it through the same reader enrichment path used by all-jobs history. If the job no longer exists, the map stays undefined and existing fallback behavior is unchanged.
* test(cron): cover single-job run history job name enrichment
Asserts that readCronRunLogEntriesPage stamps a supplied jobNameById map onto single-job page entries, matching the gateway data shape used for both all-jobs and single-job cron.runs responses.
Addresses review feedback on #88294.
* test(cron): preserve nullable tool schema validation
* test(cron): assert runtime nullable tool schema
* test(cron): refresh prompt snapshots
---------
Co-authored-by: Kip Claw <kip@kipclaw.com>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
* feat(browser): add optional vision understanding to screenshot tool
* fix(browser): wrap vision output as external content, enforce maxBytes, forward auth profiles
* fix(browser): remove no-op scope/attachments config, drop profile pass-through lacking runtime support
* feat(media-understanding): add profile/preferredProfile to DescribeImageFileWithModelParams and forward to describeImage
* style(browser): add curly braces to satisfy eslint curly rule
* fix(browser): correct tools.browser.enabled help text to match actual behavior
* fix(browser): thread agentDir/workspaceDir from plugin tool context into browser vision
* refactor(browser): move vision config from tools.browser to browser.models
The browser plugin's vision configuration now lives on the top-level
`browser` config namespace (browser.models, browser.visionEnabled,
browser.visionPrompt, etc.) instead of `tools.browser`. This aligns
with the plugin's existing config location and avoids confusion between
tool-level and plugin-level settings.
- Remove tools.browser from ToolsSchema and ToolsConfig
- Add models/vision* fields to BrowserConfig and its zod schema
- Update getBrowserVisionConfig to read from cfg.browser
- Update schema help, labels, and quality test
- Update vision.test.ts to use new config shape
* docs(browser): add screenshot vision configuration section
Document the new browser.models config for automatic screenshot
description via vision models, enabling text-only main models to
reason about web page content.
* fix(browser): remove deliverable media markers from vision result, drop unused import
P1: Vision-success path no longer exposes the raw screenshot as
deliverable media (removes MEDIA: line and details.media.mediaUrl).
This prevents channel delivery from auto-sending sensitive page content
when the intended output is a text description.
P2: Remove unused ToolsMediaUnderstandingSchema import that would fail
noUnusedLocals typecheck.
* fix(browser): add command/args fields to browser models schema
The browser vision model schema uses .strict(), so CLI-type entries
with command/args were rejected by TypeScript. Add these fields to
align with MediaUnderstandingModelSchema.
* chore(browser): remove debug console.log statements
* fix(browser): harden screenshot vision result against MEDIA: directive injection and restore image sanitization on failure fallback
ClawSweeper #84247 review round 2:
P1 (security, high): neutralize line-start MEDIA: directives in vision descriptions
before wrapping with wrapExternalContent. The agent media extractor scans every
browser tool-result text block via splitMediaFromOutput which treats line-start
MEDIA: as a trusted local-media delivery directive, and browser is on the
trusted-media allowlist. Without neutralization, page or vision-provider output
containing 'MEDIA:/tmp/secret.png' could synthesize a channel-deliverable media
artifact from untrusted content. wrapExternalContent itself does not strip
line-start directives. Introduce neutralizeMediaDirectives in vision.ts that
prepends '[neutralized] ' to any line whose trimStart() begins with MEDIA:
(case-insensitive), defanging the parser anchor while keeping the original
text human-readable.
P2 (compatibility): pass resolveRuntimeImageSanitization() to imageResultFromFile
in the vision-failure catch fallback. The non-vision screenshot path already
forwards this option (d5cc0d53b7) so configured agents.defaults.imageMaxDimensionPx
takes effect. Without this fix, any provider timeout/error silently bypasses the
sanitization guard and returns a raw full-resolution screenshot.
Regression coverage:
- vision.test.ts: 6 unit cases for neutralizeMediaDirectives (no-op fast path,
mid-line MEDIA: untouched, line-start defanged, leading-whitespace defanged,
case-insensitive, multiple directives per blob).
- browser-tool.test.ts: 2 integration cases that drive the full screenshot
tool execute path:
- 'neutralizes MEDIA: directives in vision text and does not attach media'
asserts no line matches /^\s*MEDIA:/i in returned text, secret path text
is preserved verbatim, details.media is absent, and imageResultFromFile
is not called on the success path.
- 'preserves screenshot image sanitization on vision failure fallback'
mocks describeImageFileWithModel to reject and asserts the fallback
imageResultFromFile call receives imageSanitization: {maxDimensionPx:1600}
plus the 'browser screenshot vision failed' extraText.
* fix(browser): apply clawsweeper fallback media fix from PR #84247
* refactor: reuse media image understanding for browser screenshots
* refactor: use structured media delivery
* test: update music completion media instruction expectation
* fix: trim buffered reply directive padding
* test: refresh codex prompt snapshots for message media aliases
---------
Co-authored-by: scotthuang <scotthuang@tencent.com>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Keep Codex post-tool assistant/commentary progress and patch snapshot updates on the post-tool completion guard so long generated edits do not fall back to terminal idle handling. Enable Codex patch streaming events for native code mode and refresh exact prompt/config expectations.
Verification:
- pnpm prompt:snapshots:check
- pnpm test extensions/codex/src/app-server/run-attempt.turn-watches.test.ts extensions/codex/src/app-server/thread-lifecycle.test.ts extensions/codex/src/app-server/thread-lifecycle.binding.test.ts extensions/codex/src/app-server/side-question.test.ts
- .agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main
- git diff --check origin/main...HEAD
- exact-head CI run 26677938955
- Real behavior proof override run 26678097960
Thanks @keshavbotagent.
Co-authored-by: Kelaw - Keshav's Agent <keshavbotagent@gmail.com>
Behavior addressed: Native Codex app-server threads now disable Codex's built-in personality on thread/start, thread/resume, turn/start, bound conversation turns, and /btw side-thread forks so OpenClaw agent workspace identity stays authoritative.
Real environment tested: Local OpenClaw source checkout plus GitHub CI on PR #85891.
Exact steps or command run after this patch: pnpm test extensions/codex/src/app-server/thread-lifecycle.test.ts extensions/codex/src/app-server/side-question.test.ts extensions/codex/src/conversation-binding.test.ts extensions/codex/src/app-server/schema-normalization-runtime-contract.test.ts; pnpm check:docs; pnpm prompt:snapshots:check; OPENCLAW_ADDITIONAL_BOUNDARY_SHARD=1/4 OPENCLAW_ADDITIONAL_BOUNDARY_CONCURRENCY=4 node scripts/run-additional-boundary-checks.mjs.
Evidence after fix: Focused Codex test shard passed 4 files / 79 tests; docs check passed; prompt snapshots are current; CI passed all code/quality checks, with only Real behavior proof failing as unrelated proof-bot gating for this non-channel change.
Observed result after fix: App-server request snapshots and unit tests include personality: "none" on native Codex start/resume/turn/fork paths.
What was not tested: A live Codex app-server model run was not executed.
Co-authored-by: Beru <beru@lastguru.lv>
* codex: surface deferred dynamic tool names
* codex: keep prompt snapshots source-backed
* style: wrap mac voice settings help text
* style: satisfy swiftformat for voice wake help text
* style: apply swiftformat to voice wake help text
* test: load codex prompt snapshots through plugin aliases
* test: type codex source surface loader
* test: avoid extra codex loader suppression
---------
Co-authored-by: pashpashpash <nik@vault77.ai>
Defer OpenClaw Codex dynamic tools behind Codex tool_search, keep required turn-control tools direct, pin the managed Codex harness to 0.129.0-alpha.15, and document the real behavior/token impact from the live dev-agent watch.
