Adds a report-only memory-core dreaming shadow-trial runner that writes inspectable artifacts without mutating durable memory. The public helper now stores default reports under daily directories with opaque content-hash filenames, so multiple same-day trials coexist without leaking candidate text into paths.
Verification:
- OPENCLAW_VITEST_MAX_WORKERS=1 node scripts/run-vitest.mjs run --config test/vitest/vitest.extension-memory.config.ts extensions/memory-core/src/dreaming-shadow-trial.test.ts --reporter=verbose --maxWorkers=1
- git diff --check
- pnpm exec oxfmt --check extensions/memory-core/src/dreaming-shadow-trial.ts extensions/memory-core/src/dreaming-shadow-trial.test.ts
- pnpm tsgo:extensions
- autoreview clean: no accepted/actionable findings
- GitHub CI run 26709794635 passed
- Real behavior proof run 26709798698 passed
- Dependency Guard run 26709794113 passed
Co-authored-by: Firas Alswihry <itzfiras@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>
Refactor OpenAI provider identity so OpenAI remains the canonical provider for API-key and OAuth-backed flows while legacy openai-codex state is doctor/migration-only.
Keeps OpenAI Codex Responses as an API/transport class rather than a provider identity, moves auth aliases through providerAuthAliases, updates doctor repair sequencing for old auth/profile state, and refreshes tests/docs around the canonical OpenAI behavior.
Adds first-class Xiaomi Token Plan provider support with regional onboarding/configuration, token-plan key prefix validation, runtime pricing/catalog metadata, and docs/test coverage.
Keeps Token Plan model catalog discovery runtime-owned so region-specific base URLs are required and the provider cannot silently fall back to the static SGP manifest catalog.
Fixes#86169.
Verification:
- node scripts/run-vitest.mjs src/plugins/provider-discovery.runtime.test.ts extensions/xiaomi/index.test.ts src/plugins/manifest-model-catalog.test.ts src/model-catalog/manifest-planner.test.ts
- git diff --check
- autoreview --mode local: clean, no accepted/actionable findings
- CI run 26678998539: all relevant checks passed; check-prod-types failed on unrelated browser unused-function issue already present on origin/main
Co-authored-by: NianJiuZst <3235467914@qq.com>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Move OpenClaw skills and the routed workspace-memory pointer out of native Codex turn user input and into turn-scoped collaboration developer instructions.
Preserve full MEMORY.md fallback prompt injection, delivery-hint rewrapping, lightweight cron exact prompts, and trajectory reporting for the rendered developer surface.
Co-authored-by: Beru <beru@lastguru.lv>
Add a general typed tool-progress contract so long-running non-exec tools can emit public channel progress without overloading model-facing tool content.
`web_fetch` now uses the generic delayed progress helper: it shows `Fetching page content...` only when the fetch is still pending after five seconds, clears the timer on completion/abort, passes the abort signal into guarded fetch, and avoids provider fallback or cached success after cancellation. The subscriber path accepts only explicit `visibility: "channel"` and `privacy: "public"` progress metadata, while untyped tool partials and exec output keep their existing behavior.
Docs now explain typed progress, delayed producer examples, and the `web_fetch` timing behavior.
Proof: `pnpm test src/agents/tools/web-tools.fetch.test.ts src/agents/embedded-agent-subscribe.handlers.tools.test.ts -- --run`; `pnpm docs:check-mdx`; changed-file `pnpm exec oxlint ...`; `git diff --check`; autoreview clean.
* feat: add Claude Opus 4.8 support
* fix: omit Vertex Opus sampling overrides
* fix: preserve Opus adaptive thinking levels
* fix: clamp Anthropic max effort support
* fix: use sha256 for QA mock call ids
* fix: type Anthropic transport test model metadata
* test: update PDF model default for Opus 4.8
Compact promoted short-term memory snippets before writing them into MEMORY.md, while keeping the full rehydrated snippet in recall state for ranking/provenance. Adds the deep-dreaming config surface and docs, with the default promoted snippet cap set to 160 estimated tokens.
Verification:
- git diff --check
- fnm exec --using v24.13.0 node scripts/run-vitest.mjs run extensions/memory-core/src/short-term-promotion.test.ts extensions/memory-core/src/dreaming.test.ts src/memory-host-sdk/dreaming.test.ts
- GitHub CI run 26605272497
- CodeQL security run 26605272404
Co-authored-by: AMARA <amara@eyeinthesky.pl>
Support grouped skill folders while keeping skill invocation flat via frontmatter names.
Includes bounded nested SKILL.md discovery, refresh/watch coverage for grouped folders, plugin symlink containment, and docs for grouped skill organization.
Verification:
- Node 24 targeted skill discovery and refresh tests passed locally.
- Docs checks passed locally and in CI.
- Autoreview clean.
- Crabbox live OpenAI proof showed nested foo/bar skills listed and visible in the agent system prompt.
- CI run 26595118581 passed.
Include second-level precision in inbound metadata and auto-reply envelope timestamps, matching the timestamp helper contract used by providers and channel adapters.
Docs now show the weekday plus seconds form in date-time and timezone examples.
Verification:
- node scripts/run-vitest.mjs src/auto-reply/envelope.test.ts src/auto-reply/reply/inbound-meta.test.ts
- pnpm docs:list >/tmp/openclaw-docs-list-87360.log
- git diff --check origin/main...HEAD
- pnpm format:docs:check
- pnpm lint:docs
- pnpm lint:extensions:bundled
- pnpm lint
- PR CI green on 495bb6c10fFixes#87257
Co-authored-by: GarlicGo <582149912@qq.com>
* fix(deepinfra): load all DeepInfra models when user wants to browse them during onboarding
* docs(deepinfra): align TTS default
* fix(deepinfra): refresh video fallbacks
* fix(deepinfra): share credential-aware catalog discovery
* test(deepinfra): narrow catalog regression types
* test(deepinfra): keep catalog narrowing across callback
* fix(deepinfra): preserve default model in live catalog
* fix(deepinfra): align default model pricing
* fix(deepinfra): keep pixverse as video default
* docs(deepinfra): match video fallback default
* fix(deepinfra): honor config api keys for live catalog
* test(e2e): wait for watchdog stdio close
* test(media): align live harness provider expectation
* fix(deepinfra): always augment custom catalogs
* test(e2e): resolve watchdog commands before spawning
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Recover idle queued sessions whose diagnostic activity retained stale ownerless model or tool calls by classifying them as recoverable session.stuck after the usual recovery gates. Yield the event loop before stale session-lock process inspection so sync process lookup cannot monopolize lock contention paths.
Docs now describe the widened session.stuck telemetry contract for recoverable stale bookkeeping, including ownerless activity. Thanks @samuelsoaress.
Refs #84903.
Co-authored-by: samuelsoaress <samuelsoares177778@gmail.com>
Harden the Codex app-server native execution bridge for OpenClaw sandboxed runs. The change keeps core sandbox policy in OpenClaw while exposing the process, filesystem, and HTTP relay behavior Codex needs inside a scoped exec server.
The large exec-server/test files were split into focused modules before landing, and the PR was rebased onto current main with focused tests, Testbox changed checks, CI, and Codex autoreview green.
Co-authored-by: joshavant <830519+joshavant@users.noreply.github.com>
