* fix(config): keep flat streaming keys resolving for canonical-flat channels and pin discord preview default in doctor migration
* fix(discord): pin inherited streaming mode for account alias migration and align core streaming test
* feat(channels): narrated progress drafts + activity receipt on the final answer
Progress mode replaces raw tool lines with short utility-model narration of
what the agent is doing (streaming.progress.narration, default on, requires
an explicit utilityModel). On Discord the final answer now carries the
-# activity receipt and the working draft is deleted once the answer lands,
so busy channels keep no orphaned tool log above the reply.
Formatting verified remotely via Testbox oxfmt --check (hook bypassed:
no node_modules in this worktree).
* fix(channels): keep narration toggle independent of channel-default stream mode
Discord resolves its own progress default, so the resolver must not re-derive
mode with the generic partial fallback (narration was off for unset config).
* fix(auto-reply): honor status-only command text in narration model input
streaming.progress.commandText: "status" hides raw exec/bash text from the
channel draft; narration input now mirrors that policy so the utility model
never receives more command detail than the draft shows (Codex review P2).
Formatting verified remotely via Testbox oxfmt --check.
* fix(auto-reply): share the draft's command-tool set for narration and regen channel metadata
Reuse isCommandToolName (exec|shell|bash) so narration's commandText policy
matches the draft formatter exactly, and regenerate bundled channel config
metadata for the new streaming.progress.narration key (Codex review round 2).
Gates verified on Testbox: config:channels:check, oxfmt --check, 4 test shards.
* fix(channels): clear stale narration when the narrator stops mid-turn
An empty narration update now falls the draft back to raw tool lines, and the
narrator emits that clear when it disables after consecutive failures or the
per-turn cap, so drafts never pin stale status text (Codex review round 3).
Gates verified on Testbox: oxfmt --check + 4 test shards.
* chore(config): regen bundled channel metadata after rebase onto main
* chore: CI fixups — lint nits, test harness types, docs map, SDK surface budget
Two deliberate public SDK additions (resolveChannelStreamingProgressNarration,
isCommandToolName via the streaming wildcard re-export) bump the pinned
public-surface budgets to current counts (exports 10488, callable 5235).
Gates verified on Testbox: oxfmt, targeted oxlint, docs:map:check,
config:channels:check, check:test-types, 5 test shards.
* 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>
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.
Document that channels.telegram.streaming.preview.toolProgress requires
channels.telegram.replyToMode: 'off'. Quote-reply requires the final message
reference at send time, which is incompatible with preview-edit streaming, so
the two features are mutually exclusive on Telegram.
Adds:
- Note callout in docs/channels/telegram.md after the existing toolProgress
guidance, explaining the exclusion and how to restore visibility.
- Cross-link bullet in docs/concepts/streaming.md pointing to the Telegram
channel doc for the full note.
Surfaces a doc/runtime gap that has been silent since v2026.4.22.
Summary:
- The PR enables Slack draft preview streaming for flat DMs in all non-off modes, updates Slack streaming tests/docs/config metadata/changelog, and refreshes small guard baselines.
- Reproducibility: yes. source-reproducible on current main: the helper returns false for `mode: "partial"` in ... current test asserts that disabled path. I did not run tests because this review was explicitly read-only.
Automerge notes:
- Ran the ClawSweeper repair loop before final review.
- Included post-review commit in the final squash: fix(slack): enable preview streaming in flat DMs (replyToMode: off)
- Included post-review commit in the final squash: fix(clawsweeper): address review for automerge-openclaw-openclaw-5654…
Validation:
- ClawSweeper review passed for head 52e5d74ef9.
- Required merge gates passed before the squash merge.
Prepared head SHA: 52e5d74ef9
Review: https://github.com/openclaw/openclaw/pull/76330#issuecomment-4365017023
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Co-authored-by: bob <637186+HangGlidersRule@users.noreply.github.com>
* fix(telegram): send fresh finals for stale previews
* test(telegram): cover stale preview send fallback
* fix(telegram): keep stale archived preview fallback
* fix(telegram): clear stale active previews
* fix(telegram): reset preview state after fresh finals
Fix Telegram partial-stream preview finalization so ambiguous final edit failures fall back to a final send when the visible preview is a strict prefix of the answer.
Includes archived-preview regression coverage and generated config metadata refresh.
Thanks @sahilsatralkar.
Co-authored-by: Sahil Satralkar <62758655+sahilsatralkar@users.noreply.github.com>
- concepts/streaming.md: remove '# Streaming + chunking'.
- reference/session-management-compaction.md: remove Title Case H1
'# Session Management & Compaction (Deep Dive)'.
- plugins/voice-call.md: remove '# Voice Call (plugin)'.
CLI pages keep their command-formatted body H1s since that is the repo
convention and the formatting is not expressible in frontmatter.
Clarify the canonical Slack streaming config keys and legacy migration notes
across the Slack docs and shared streaming concept docs.
Document that native Slack streaming and assistant thread status require a
reply thread, and call out the top-level DM fallback behavior.
Add cross-linking Related sections to concept pages that were dead ends:
- model-providers, models, context, context-engine, agent-workspace,
architecture, messages, streaming, compaction, oauth
Each page now links to 3-4 related topics for navigation continuity.
