Move Workboard durable data into a relational SQLite database and add extension doctor migration for .28 plugin-state rows. Preserve attachment lifecycle behavior, SQLite permissions/WAL settings, and scoped plugin migration access.
* 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>
Preserve Slack Agents & Assistants DM root thread context for tool and subagent replies even when Slack omits or misreports `channel_type`, while leaving non-DM self-thread roots top-level.
Fixes#63659.
Thanks @zozo123.
Move MSTeams conversation and poll plugin-local stores to plugin-state SQLite. Legacy JSON stores import once without overwriting existing SQLite state; conversation and poll IDs are hashed for plugin-state keys; poll votes are sharded with bounded row-cap headroom and prune cleanup; MSTeams docs now describe SQLite storage. SSO and delegated token stores are unchanged. Verified with focused MSTeams tests, docs sanity, autoreview, Testbox check:changed, and green PR CI.
Move model catalog normalization and package-owned catalog schema/types into model-catalog-core while keeping public plugin SDK model catalog declarations on the existing SDK surface. Verified focused tests, package-boundary compile, full build, changed gate, declaration leak grep, CI, and autoreview.
Keep Codex app-server continuation turns alive after post-tool, raw assistant, and progress notifications, and reschedule continuation idle watches when shorter progress timeouts apply.
Add regression coverage for the plugin-sdk child_process mock helper deadlock that blocked CI shards on this PR.
Co-authored-by: abnershang <abner.shang@gmail.com>
Move model catalog ref helpers into @openclaw/model-catalog-core/model-catalog-refs and update internal callers/package-boundary aliases. Also fix the timestamp predicate typing that blocked prod type checks on current main.
Feishu `channels.feishu.streaming=true` now streams ordinary assistant replies through CardKit in auto mode, while keeping tool-summary delivery on the existing message path.
Also discards stale partial previews when final delivery intentionally suppresses text for voice media or duplicate final text, and preserves streamed partial text for regular media-only finals.
Verification:
- `node scripts/run-vitest.mjs run extensions/feishu/src/reply-dispatcher.test.ts`
- `pnpm tsgo:extensions`
- `pnpm test:extensions:package-boundary:compile`
- `pnpm exec oxfmt --check extensions/feishu/src/reply-dispatcher.ts extensions/feishu/src/reply-dispatcher.test.ts extensions/feishu/src/streaming-card.ts`
- `git diff --check`
- `.agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main`
- GitHub PR checks on run 26689677607 passed except repeated unrelated broad Vitest no-output timeouts in `checks-node-agentic-commands-doctor` and `checks-node-core-runtime-infra-state`.
Co-authored-by: 传妈 <chuanmother@chuanMac-Mini.local>
Carry Discord reply typing feedback through preflight, queued dispatch, and cleanup so delayed accepted replies keep typing alive at the actual dispatch target without duplicate keepalives. Adds focused Discord queue/process policy coverage and stronger lifecycle invariant comments.
Prunes undefined Discord component and modal registry metadata before persisting it so SQLite-backed plugin state never receives JSON-incompatible undefined values. Adds direct regression coverage for undefined own properties on component, modal, and nested field entries.
