Allow users to save credentials securely without exposing values in AI
context. When AI calls saveCreds with `fields` but no `values`, a secure
form renders via the intervention system for direct user input.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* ✨ feat(brief): show artifacts in card and extract DocumentModal
Wire `brief.artifacts` (already populated by topic-brief synthesis) into
TaskBriefCard and the home BriefCard so completed-topic deliverables
show up inline; clicking a doc card opens it in a modal.
The per-task PageModal becomes a reusable `DocumentModal` (props-based:
documentId/open/onClose), and the preview trigger state moves from task
store to a new `preview` slice in document store — any surface can now
call `useDocumentStore.openDocumentPreview(id)`.
Also:
- PageAgentPanelOverrideProvider: ephemeral right-panel state for
PageEditor in transient surfaces (modal); defaults collapsed and
doesn't write the persisted global preference.
- PageEditor.fullWidthHeader: layout flag so the modal's header spans
both columns instead of the left pane only.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 💄 style(shared-tool-ui): unify label-to-content spacing in file inspectors
Replace trailing-space spacing with explicit 6px marginInlineEnd on the label
span in Read/Edit/Write/List inspectors so they match the 6px gap already used
by chip-based renderers (Bash, Grep, Glob).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🐛 fix(brief): clear preview state on document modal teardown
`previewDocumentId` is global (`useDocumentStore`) and the modal opens on
any truthy value. Without cleanup, navigating away with the modal open
left a stale id behind, and the next surface that mounted a preview
modal (e.g. /home daily brief) would immediately reopen the old doc.
Extract a `<DocumentPreviewModal />` connector that resets the preview
state on unmount, and use it everywhere the global preview should be
rendered (TaskDetailPage, DailyBrief). Future mount points get the
cleanup for free.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🐛 fix(brief): coerce globalExpand to boolean in panel control hook
`systemStatusSelectors.showPageAgentPanel` returns `boolean | undefined`
(zenMode short-circuit ANDs with an optional flag), but
`PageAgentPanelControl.expand` is `boolean`. Coerce with `!!` so the
non-override branch satisfies the type.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
✨ feat(mobile-router): add task and brief routers to mobile tRPC router
Expose task and brief endpoints to the mobile client so the React Native
app can manage tasks and daily briefs via the same tRPC contract used by
the web client.
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Automatic sync from main to canary. Merge conflicts detected.
**Resolution steps:**
```bash
git fetch origin
git checkout sync/main-to-canary-20260429-25113686179
git merge origin/main
# Resolve conflicts
git add -A && git commit
git push
```
> Do NOT merge canary into a main-based branch — always merge main INTO
the canary-based branch to keep a clean commit graph.
* 🐛 fix(model-runtime): preserve LLM finishReason through callbacks transformer
Soft interrupts from providers (Gemini RECITATION / MAX_TOKENS, etc.)
emit a `type: 'stop'` chunk carrying the finishReason string, but
`createCallbacksTransformer` was only using it as a terminal-event flag
and never aggregating the value. Downstream the `OnFinishData` payload
had no `finishReason` field, so RuntimeExecutors recorded an `llm_result`
event without it — the harness silently rendered an empty assistant
message even though tokens were billed.
Capture the value in the callbacks aggregator, surface it on
`OnFinishData`, and write it into the `llm_result` tracing event so
soft-interrupt cases are diagnosable.
Fixes LOBE-8403
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🐛 fix(model-runtime): keep first finishReason across multi-stop streams
Anthropic emits two `'stop'` chunks per stream — `message_delta` with
the real `stop_reason` (`end_turn` / `max_tokens` / `tool_use`) followed
by a `message_stop` sentinel. Last-write-wins clobbered the meaningful
reason with the sentinel string, defeating the very tracing signal this
fix is meant to provide.
Switch to first-non-empty-wins so the real provider reason survives.
The empty-string fallback covers cases where an early provider chunk
arrives before the reason is known.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
**Hotfix Scope:** Topic preservation across cold chat-entry routes
> Keeps newly created Topics visible when a first message is sent before
the destination chat route has fully hydrated.
- **Page Agent empty-session regression** — Sending the first message in
an empty Page Agent panel no longer clears the newly created Topic and
returns the panel to an empty state. (Resolves LOBE-8351)
- **Home cold-route send regression** — Sending from the Home default
Chat Input now routes to the newly created Inbox Topic even when
`/agent/:aid` has never been opened and the route chunk has no warm
cache.
- **Page-scoped Copilot consistency** — Page Copilot and File Copilot
share the same provider-level topic reset behavior, so stale Topics are
cleared only when entering or switching the scoped Agent.
- **Regression coverage** — Added focused unit coverage for Home default
sends, route parity coverage remains intact, and added an E2E scenario
for the no-cache Home send path.
- `bunx vitest run --silent='passed-only'
'src/routes/(main)/home/features/InputArea/useSend.test.ts'
'src/spa/router/desktopRouter.sync.test.tsx'
'src/routes/(main)/agent/features/Conversation/ChatHydration/index.test.tsx'
'src/routes/(main)/agent/_layout/AgentIdSync.test.tsx'`
- `BASE_URL=http://localhost:3007
DATABASE_URL=postgresql://postgres:postgres@localhost:5433/postgres bun
run test -- --tags '@HOME-CHAT-COLD-001'` from `e2e/`
- Self-hosted: pull the new image and restart. No schema or environment
changes.
- Cloud: ships through the normal hotfix deployment after merge.
@Innei
Fixes LOBE-8351
* ✨ feat(creds): add local/desktop credential injection guidance
Teach AI how to use credentials in non-sandbox (desktop/local) environments via
getPlaintextCred + runCommand inline env vars, alongside the existing sandbox flow.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* 🔒 fix(creds): use runCommand env param for secure credential passing
Inline secrets in the command string would be visible in the Intervention UI
and logs. Use runCommand's env parameter instead, and correct the misleading
file credential guidance (getPlaintextCred returns a fileUrl, not a local path).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
✨ feat(agent,working-sidebar): add Review tab with bulk git working-tree diffs
Adds a Codex-style Review tab to the agent working sidebar (peer to the
existing Resources content, surfaced as Space). When the active topic has a
working directory bound, the sidebar shows two chip-style tabs — Space (left)
and Review (right) — and the Review pane lists every dirty file with its
unified diff rendered via PatchDiff.
A single new IPC method `git.getGitWorkingTreePatches(dirPath)` enumerates
the working tree once via `git status --porcelain -z`, then runs every
per-file `git diff` in parallel inside main; tracked entries hit
`git diff HEAD -- <file>` while pure untracked files use
`git diff --no-index /dev/null <file>`. Each patch is capped at 256 KB and
classified into added / modified / deleted with additions/deletions counts
parsed off the patch text, so the renderer needs exactly one round trip and
zero per-file fetches.
The Review pane defaults to all files expanded, with PatchDiff render gated
on the panel's expanded state so collapsed entries don't pay the shiki
highlight cost. Adds a unified/split viewMode toggle in the Review subheader,
shows an Unstaged-N chip alongside it, and ships a custom small expand caret.
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
💄 style(daily-brief): add skeleton loading state for DailyBrief component
LOBE-8400
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* ✨ feat(task): add start-scheduling button in automation popover
Lets users mark a configured task as "scheduled" without firing an
immediate run, so the cron/heartbeat tick owns the first execution.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🐛 fix(task): hide start-scheduling button in heartbeat mode
Heartbeat tasks are re-armed only by maybeRearmHeartbeat after a topic
completes — there is no dispatcher that picks up `scheduled` heartbeat
tasks, so the button would leave a paused/backlog task dormant.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ✨ feat(task-lifecycle): auto-synthesize topic briefs (LOBE-8333)
Replaces agent-driven createBrief on the non-review "done" path with a
programmatic synthesis: rule-based decision + DB-collected artifacts +
a dedicated LLM for user-facing title/summary. Handoff and brief stay
separate (agent-internal vs user-facing language) and the new path is
gated behind task.config.brief.mode === 'auto' so existing tasks keep
the legacy tool-driven behavior until the GrowthBook flag flips.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ✨ feat(generate-brief): let LLM gate emission per topic content
Pure rules can only skip the obvious cases (error, judge-handled,
automation tick, trivial content). They can't tell that "I clarified
my understanding and will start drafting next" is a working note, not
a delivery. Add an `emit: boolean` to GENERATE_BRIEF_SCHEMA and have
the prompt instruct the model to judge — emit=false discards the
brief without writing to the table.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ♻️ refactor(task-model): move topic-artifact query into TaskModel
DB queries belong on the model, not in a service helper. Replaces
the standalone collectTopicArtifacts() with TaskModel.getDocumentsPinnedSince(),
which lives next to pinDocument / getPinnedDocuments and returns
joined { id, kind, title } rows. synthesize.ts is now pure decision
logic — no more drizzle imports.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🐛 fix: support UTF-16 encoded text files in TextLoader
The TextLoader previously hardcoded UTF-8 encoding when reading files,
causing UTF-16 encoded CSVs (e.g. Google Ads Keyword Planner exports)
to be parsed with null bytes, producing garbled content and database
insert failures.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* ♻️ refactor(file-loaders): tighten TextLoader UTF-16 detection
- Use TextDecoder('utf-16be') instead of manual byte-swap loop, which
also avoided in-place mutation of the read buffer.
- Replace the 2-byte heuristic with a 512-byte sample, count ASCII-pair
shape on both halves so UTF-16BE without BOM is detected too, and
files whose first character is non-ASCII no longer slip through.
- Add tests for UTF-8 BOM, UTF-16LE no-BOM, and UTF-16BE no-BOM.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* ✨ feat(agent-marketplace): implement onboarding agent marketplace picker
Adds a new builtin tool `@lobechat/builtin-tool-agent-marketplace` that
opens a categorized agent picker UI during web onboarding. The picker
fetches the live curated catalog from the marketplace API
(`/api/v1/agents/onboarding-full`) via a TRPC procedure that injects the
trust-token, and lets the user select template agents to install.
Highlights:
- Self-contained marketplace package with manifest, system role, executor,
and ExecutionRuntime
- React intervention component with category sidebar, skeleton loading
state, and avatar/empty/error UI; all user-visible strings i18n-driven
- Dependency-inverted fetcher: package exports `setAgentTemplatesFetcher`,
app registers a TRPC-backed implementation in AgentOnboardingPage
- New TRPC `market.agent.getOnboardingFull` proxies the upstream API with
trust-token authentication; client never sees secrets
- Splits the existing `saveUserQuestion` intervention into agent identity
and user profile cards for clearer onboarding approval UX
- Wires marketplace into `builtin-tools` registry, executor map, and
onboarding metrics; web-onboarding agent system prompt updated to
reference the picker
Closes LOBE-7801
* ✨ feat(onboarding): enhance early exit handling and marketplace integration in onboarding flow
Signed-off-by: Innei <tukon479@gmail.com>
* 🐛 fix(agent-marketplace): register server runtime, scope picks per-topic, and harden onboarding handoff prompts
The summary phase silently skipped the marketplace handoff because the
server toolExecution registry had no runtime for `lobe-agent-marketplace`,
so every `showAgentMarketplace` call returned "not implemented" and the
agent fell through to `finishOnboarding`. The runtime-injected phase
guidance and action hints also instructed the agent to call
finishOnboarding directly after the summary, contradicting the new
system role.
- Register `agentMarketplaceRuntime` in
`src/server/services/toolExecution/serverRuntimes` so the executor
can actually run.
- Scope the in-memory `picks` map by `topicId` and reject a second
`showAgentMarketplace` call in the same conversation with a clear
"already opened, finish on next turn" message.
- Tighten the success content to instruct the model to STOP the current
turn after opening the picker and run closing + finishOnboarding on
the FOLLOWING user turn.
- Update `OnboardingActionHintInjector`, `PHASE_GUIDANCE.summary`,
`toolSystemRole` and `web-onboarding/systemRole` so all four prompt
layers agree: open the picker exactly once during summary, do not
call finishOnboarding in the same turn, and do not call the
submit/skip/cancel APIs ourselves.
- Stop treating short affirmations like "好的" / "行" / "ok" as
early-exit signals; they are confirmation of the summary and should
let the picker handoff proceed normally.
Verified end-to-end with `bun run agent-evals run onboarding/web-onboarding-v3
--case-id fe-intj-crud-v1 --model deepseek-v4-pro`: hard assertions all
pass, judge moves from 7/10 (premature finishOnboarding in same turn)
to 8/10 with picker opened once and finishOnboarding deferred to the
next turn.
* fix(ci): attempt 1 for PR #14286
Auto-generated by pr-dispatcher (task: 01KQBY8GAC1MNQCJ6T6X5DEP2F, attempt: 1).
Co-Authored-By: Claude <noreply@anthropic.com>
* 🐛 fix(agent-marketplace): wire picker submit + fix marketplace-already-opened detection
The marketplace picker confirm flow was sending the user's selection back as a
synthetic user message, and the action hint kept telling the model to open the
marketplace again — leading to a death loop where the agent re-opened the
picker instead of summarizing + persisting + finishing onboarding.
Two issues:
1. Pick confirm forwarded the selection as a user message instead of forking
the agents and resuming from the tool result. Wire `prepareCustomInteractionSubmit`
into the intervention's submit branch so it runs `installMarketplaceAgents`
client-side and returns a descriptive `toolResultContent`. Plumb a
`createUserMessage: false` + `toolResultContent` option through
`submitToolInteraction` (slice + chat store): when set, skip the synthetic
user message, override the tool message content, and resume runtime from the
tool message (`parentMessageType: 'tool'`) so the LLM sees the install
result and continues from there.
2. `OnboardingActionHintInjector.marketplaceAlreadyOpened` read `msg.tool_calls`,
but this provider runs in pipeline phase 4.5 (virtual tail guidance) BEFORE
`ToolCallProcessor` (phase 5) converts DB-shape `tools` → OpenAI-shape
`tool_calls`. Detection always returned false → the hint kept saying
"call showAgentMarketplace" → death loop. Fix: match on `tools[].apiName`
(with `tool_calls` kept as a fallback). Also rewrote the Summary-phase hints
to reflect the new flow (picker resolves directly via tool result, no
synthetic user reply needed).
Includes intervention bar portal-target plumbing for approval actions.
* ✨ feat(onboarding): wire marketplace picker analytics on agent onboarding page
Mount AnalyticsBridge under AgentOnboardingPage to inject useAnalytics() into
setOnboardingAnalyticsClient, so onboarding_marketplace_shown/picked events
emit through PostHog instead of being silently dropped. Adds spm fields to
align with onboardingFeedback's telemetry shape.
* ♻️ refactor: move DEFAULT_ONBOARDING_MODEL to business-const
Made-with: Cursor
* ✨ test(customInteractionHandlers): add tests for persisting marketplace picks and resolutions
Signed-off-by: Innei <tukon479@gmail.com>
* ✨ feat(onboarding): enhance agent marketplace integration with metadata persistence
Signed-off-by: Innei <tukon479@gmail.com>
* ✨ feat(agent): add web onboarding agent selectors and integrate into Actions and Usage components
Signed-off-by: Innei <tukon479@gmail.com>
---------
Signed-off-by: Innei <tukon479@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
KnowledgeRepo queries use COALESCE(d.id, f.id) as id, which returns the
document's `docs_xxx` ID when a document exists for the file. Using this
as the proxy URL path (`/f/docs_xxx`) fails because the file proxy route
looks up the `files` table by `file_xxx` ID.
Fix: use `item.fileId` (always the actual file ID) for proxy URLs in
`getKnowledgeItems` and `recentFiles` handlers.
Closes#12196
* feat: support Line
* chore: update Line docs
* feat: support line platform
* chore: update markdown files
* fix: lint error
* fix: home padding block
Daily/weekly schedules dedup'd by calendar day, so a manual "run now"
earlier in the day would advance lastHeartbeatAt and make the dispatcher
skip today's scheduled tick. Dedup now compares against today's target
H:M instead — a 21:00 schedule still fires after a 18:00 manual run,
while post-target runs and same-tick re-dispatch are still skipped.
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Azure / OpenAI strict structured outputs require every key in `properties`
to appear in `required`; the schema only listed `title` and `summary`,
so every generateHandoff call returned 400 "Missing 'keyFindings'".
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
♻️ refactor(context-engine): drop ____builtin suffix from tool names
Builtin tools now generate two-segment names like documents____upsertDocumentByFilename instead of documents____upsertDocumentByFilename____builtin. The "default" plugin type was already suffix-less, and "default" is no longer in active use, so collapsing builtin into the same shape removes redundant LLM-facing tokens. resolve() falls back to type 'builtin' for two-segment names and still parses legacy three-segment ____builtin names from message history.
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* docs(lobehub-skill): add video/image model lookup guide to generate reference
* docs(lobehub-skill): add full model type list and default-type warning to model reference
* docs(lobehub-skill): fix incorrect tip about lh model list default behavior
* 🐛 fix(builtin-skills): close template literal in model reference
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ♻️ refactor: remove schedule config popup from task list item
The task list row should only display the schedule trigger tag, not act
as an entry point for editing the automation. Configuration stays
available on the task detail page via TaskProperties.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 💄 style: mute BriefIcon when task is resolved
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 💄 style: flatten task markdown card, drop container background and padding
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ✨ feat: expose task topic operationId and add copy menu item
Surfaces the persisted `task_topics.operationId` through the task detail API
so the topic card menu can offer a "Copy operation ID" entry alongside
"Copy topic ID", aiding debugging of completed runs.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🐛 fix: skip empty text block when Claude Code prompt is image-only
Anthropic rejects `{ text: '', type: 'text' }` with "messages: text content blocks must be non-empty", so uploading an image with no text would 400.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ✨ feat: add topic actions menu and share button to task topic drawer
- Add "..." dropdown next to title with Copy topic ID / Copy operation ID
- Add Share icon next to close button, reusing SharePopover and ShareModal
- Pass topicId through SharePopover so it works outside the chat store scope
- Use getContainer={false} on Drawer to escape App's isolation stacking context, letting popups render above the drawer
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* feat: refactor home
* feat: add home agent id switch
* fix: useSend ensure agent map init
* feat: add custom image/video generation menu item
* chore: remove agent list ,group list and modetag
* fix: default home agent fallback
* fix: built in agent builder creation
* feat: add deepseek pro v4 hot picks
* chore: support agent select scrolling
* feat: add bot integration banner
* fix: lint error
* chore: update home page styles
* chore: adjust padding
* test: add image item to sidebar items test fixtures
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* test: remove obsolete home starter e2e tests
The mode-tag buttons (Create Agent / Create Group / Write) no longer
exist after the Home refactor, so these scenarios cannot run.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 💄 style(home): collapse empty suggest questions wrapper on default home
Why: when enableAgentTask is on, SuggestQuestions and CommunityRecommend both render null on the default home view, but the AnimatePresence wrapper still mounted with marginTop:24 and produced a large empty gap between StarterList and DailyBrief.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ✨ feat(task): add cron-based task schedule dispatcher
Wires up backend execution for task-level cron schedules. Adds two
QStash workflows-hono routes:
- POST /api/workflows/task/schedule-dispatch — central sweep, point a
QStash Schedule (e.g. */30 * * * *) here. Loads all schedule-mode
tasks, filters by cron pattern + timezone + lastHeartbeatAt dedup,
and fans out per-task messages.
- POST /api/workflows/task/schedule-execute — internal per-task handler
that re-validates DB state and runs the task via TaskRunnerService.
Reuses existing schedulePattern / scheduleTimezone columns and
lastHeartbeatAt for dedup — no migration needed. Failure paths fall
through to the existing onTopicComplete error handling (urgent brief
+ paused).
* 💄 style(task): collapse resolved brief card on detail by default
Why: resolved briefs on the detail page rarely need re-reading; matching
home's collapse-when-resolved behavior keeps the activity feed compact.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ✨ feat(agent-profile): make popup header navigate to agent profile
Click on the avatar/title in AgentProfilePopup now closes the popup and routes to /agent/:id/profile.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ✨ feat(task): render task XML as a card in topic chat drawer
Why: the topic drawer's first user message is the task run prompt — a `<task>...</task>` XML blob (identifier, status, instruction, agent, …). Rendering it as raw XML buries the structure the user actually cares about.
- Add a `Task` markdown plugin (scope: user) that parses the `<task>` payload and renders an Artifacts-style card.
- Use a custom remark plugin so the block survives mdast splitting it across html + paragraph nodes.
- Gate the card UI behind a `TaskCardScope` React Context so it only activates inside `TopicChatDrawer`; everywhere else falls back to a plain `<pre>`.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ✨ feat(claude-code): reuse result renders during streaming via wrapRender
Why: while a CC tool is still executing, the detail view fell back to a generic argument table for everything except `Agent`. Read/Write/Edit/Glob/Grep/Skill/Bash/TodoWrite already gracefully degrade their result Render when `content`/`pluginState` are absent, so the same component works for the live phase too.
- Add `wrapRender` helper that adapts a `BuiltinRender` into a `BuiltinStreaming` by passing `content: null`.
- Register Bash/Edit/Glob/Grep/Read/Skill/TodoWrite/Write streaming entries through `wrapRender`. `Agent` keeps its bespoke streaming view.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ♻️ refactor(task-subtasks): drop legacy blockedBy flattening branch
Why: subtasks now always arrive as a real tree from the upstream service, so the fallback that re-built the tree from a flat list via `blockedBy` is dead code.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🐛 fix(view-switcher): hide chat/task switcher for heterogeneous agents
Why: the chat/task view switcher in the agent header doesn't apply when the agent is heterogeneous (Claude Code / Codex / etc.) — those agents don't share the task topic flow, so showing the switch surfaces a non-functional control.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ✨ feat(task-topic): show elapsed duration on completed topic runs
Mirror task_topics terminal transitions (completed / failed / canceled / timeout)
onto topics.completedAt so the activity feed can render elapsed time for
finished runs, not just for the live one. Thread completedAt through
findWithHandoff and the TaskDetailActivity payload, then extend TopicCard
to render formatDuration(completedAt - createdAt) for non-running statuses.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🐛 fix(task-trigger-tag): respect automationMode when rendering schedule label
Heartbeat tasks were displaying cron schedule text when the DB still carried
a schedulePattern from a previous mode. Switch to automationMode as the
source of truth in TaskTriggerTag and pass it from all three call sites.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🐛 fix(conversation): stop topic scroll restore from corrupting itself
The restore path called scrollTo(snapshot.offset) one rAF after a fresh
VList mount, when only viewport-visible items had laid out. virtua
clamped the target against the still-incomplete scrollSize and landed
at offset 0, then the resulting onScroll fed back into recordScroll and
overwrote the snapshot to offset 0 — locking the user at the top on
every revisit.
Two fixes:
- Add a restoringRef guard that suppresses recordScroll while a
programmatic restore is in flight, released after two rAFs.
- Poll virtua's scrollSize for up to 30 frames until it can accommodate
the target offset before issuing scrollTo, with a safety bail-out so
unreachable offsets still resolve.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🐛 fix(conversation): converge scroll snapshot to clamped offset on cap-out
When the saved offset is unreachable (e.g. messages were trimmed since
the snapshot was written), the polling loop hits its 30-frame cap and
falls through to scrollTo(targetOffset). Without this fix, the snapshot
keeps the stale unreachable offset, so every future revisit pays the
full polling delay before clamping again.
After the cap-out scrollTo lands, read the actual scrollOffset and
persist it (with a recomputed atBottom). Reachable-target restores still
leave the snapshot untouched so we don't churn writes for no reason.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ✨ feat: auto-dismiss upload dock after completion
UploadDock now auto-removes all completed files and hides itself 3 seconds
after all uploads finish (or error). If new uploads start during the timer,
the timer is cancelled and the dock stays visible.
Closes#9605
* fix(ci): 将 `useRef<ReturnType<typeof setTimeout>>()` 改为 `useRef<ReturnType<typeof setTimeout> | null>(null)`。
Auto-generated by pr-dispatcher (task: 01KQ9ZB50GQXWTYADHAWEGTNQR, attempt: 1).
Co-Authored-By: Claude <noreply@anthropic.com>
* fix(ci): Guarded `clearTimeout(autoDismissTimerRef.current)` calls with `if (autoDismissTimerRef.current)` checks in the UploadDock auto-dismiss effect.
Auto-generated by pr-dispatcher (task: 01KQA0NZB57SFPHP45227ENZAT, attempt: 1).
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
* 💄 style(task): replace page drawer with modal and rebuild artifact card
- Migrate page preview from a right-side drawer to a centered modal
(`PageModal`) with allow-fullscreen support; rename store state
`activePageDrawerPageId` → `activePageModalId` and the corresponding
`openPageDrawer` / `closePageDrawer` actions / selectors.
- Refresh artifact cards: collapse to a single-line layout (smaller
file icon, inline size + identifier tag) and add a remove action
that calls `unpinDocument` against the artifact's `sourceTaskId`
fallback chain (so artifacts pinned from another task unpin from
the right task, not just the active one).
- Surface `sourceTaskId` on `TaskDetailWorkspaceNode` /
`WorkspaceDocNode` and through the task service so the renderer
can resolve the owning task for the unpin call.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ✨ feat(brief): add delete action for brief cards
- `briefService.delete` calls `brief.delete` mutation; `deleteBrief`
store action removes the brief from the in-memory list after the
server roundtrip.
- `TaskBriefCard` exposes a `MoreHorizontal` dropdown with a danger
delete item gated by an `App.confirm` modal; `TaskActivities`
passes `onAfterDelete=refreshActiveTask` so the activity list
re-fetches once the brief is gone.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🐛 fix(task): use local timezone over DB-default UTC on first schedule enable
The `tasks` table seeds `schedule_timezone` to `'UTC'` on row creation, so
even a task that has never been scheduled surfaces `timezone='UTC'`. The
previous "if timezone is missing, use local" check therefore never fired,
and first-time schedule enable always defaulted to UTC.
Treat a missing `pattern` as the reliable signal that the user has never
opened the schedule form, and override the DB-default UTC with the user's
local IANA zone in that case. A user-chosen timezone (with a real
pattern) is still preserved on subsequent re-entries.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 💄 style(task/scheduler): replace TimePicker with half-hour Select
- Cron storage rounds minutes to 0/30 (see `buildCronPattern`), so the
picker only ever needs 48 half-hour slots — flatten antd's
hour×minute grid into a single-column `Select`.
- Anchor every dropdown (`getPopupContainer`) inside the parent Base UI
Popover so option clicks aren't treated as outside-clicks (which
dismissed the popover before the selection committed).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🐛 fix(task/subtasks): wire context menu via Tree.onRightClick
`ContextMenuTrigger` was attached to each subtask title's inner
`Flexbox`, but antd `Tree`'s row-level `.ant-tree-node-content-wrapper`
only `preventDefault`s the contextmenu event when an `onRightClick`
handler is provided. Right-clicks landing in the row gap (anywhere
outside the title element) fell through to the browser's native menu.
- Refactor `useTaskItemContextMenu` into a shared
`useTaskContextMenuActions` factory exposing stable
`buildItems(task)` / `installKeyboardHandlers(task)`. Existing
`useTaskItemContextMenu(task)` API is preserved as a thin wrapper.
- `TaskSubtasks` now calls `Tree.onRightClick`, looks up the subtask
by `node.key` from a recursively-built map (subtasks are returned
as a nested tree, not flat), and calls `showContextMenu` plus the
keyboard-handler installer imperatively.
- The flat-map walk is recursive so right-click works on nested
children, not just top-level subtasks.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 💄 style(task/topic): wrap dropdown to swallow card click + relabel topic ID
- Wrap the topic card's `MoreHorizontal` dropdown in a `Flexbox`
with `onClick={stopPropagation}` so menu interactions don't
bubble through to the card-level click handler.
- Fix the menu label fallback: `Copy run ID` → `Copy topic ID` to
match what the action actually copies.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🐛 fix(task/artifacts): also refresh active task SWR after unpin
`unpinDocument` is called with `node.sourceTaskId` (the task that
owns the pin row, often a descendant DB id), but the open detail
page's SWR cache is keyed by `activeTaskId` (typically the parent
identifier from `/task/{identifier}`). Refreshing only the source
key left the parent's workspace stale until reload.
After the unpin succeeds, also revalidate the active key when it
differs from the source. The server call still uses the source id
because `model.unpinDocument` deletes by exact `(taskId, documentId)`
match — passing the parent identifier would no-op for docs pinned
by a subtask.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ✨ feat(panel): give page and task right panels independent visibility
Page editor and Task layout now read/write `showPageAgentPanel` /
`showTaskAgentPanel` (with matching `togglePageAgentPanel` /
`toggleTaskAgentPanel` actions) instead of sharing the global
`showRightPanel`, so toggling one no longer flips the other. Task panel
defaults to collapsed; page panel stays open.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 💄 style(task/detail): tighten artifact size label and align activity card padding
- artifact size shows raw count with "字" instead of "1.4k 字符"
- swap artifact file icon to FileTextIcon (lucide), 18px
- BriefCard padding 12 → paddingInline 8 to align with CommentInput; BriefIcon 20 → 24
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ♻️ refactor(task/page-modal): give modal its own header via PageEditor slot
PageEditor now accepts an optional `header` slot (undefined keeps the
built-in Header, null hides it). PageModal stops relying on antd's title
chrome and supplies its own header — title + autosave on the left, panel
toggle and close on the right — so the modal no longer stacks two
headers and owns its own composition.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🐛 fix(page): mirror document into pageStore on standalone fetch
Document fetch now upserts the loaded `page`-source document into
pageStore via a new `upsertDocument` action. PageExplorer reads title
and emoji from pageStore selectors, so opening a page from a context
that never hit the page list (e.g. the task workspace modal) used to
show empty title/emoji until the list was visited.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 💄 style(task): polish schedule popover
Refresh the schedule popover after design review:
- Header: avatar with ⚡ icon + summary (e.g. "Runs every 10 min" / "Daily
at 09:00 · China Standard Time"); next-run preview block under the title.
- Segmented tabs gain Calendar / Refresh icons; Recurring tab drops the
Clear button + advanced section (only Schedule mode keeps advanced).
- Advanced settings is now an Accordion (matches lobehub patterns) and
hosts timezone + max executions.
- All inputs switch to variant="filled"; weekday picker uses
colorPrimaryBg + colorPrimary instead of solid primary to fix the
white-on-white "burned" active state.
- Popover surface uses colorBgContainer + colorBorderSecondary border +
12px radius for clearer elevation.
New `scheduler/helpers.ts` formats the cron summary, resolves IANA
timezone display names via Intl, and computes the next firing time for
both heartbeat and cron schedules (uses dayjs/plugin/timezone).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🐛 fix(task): hide standalone "Brief" fallback in task list
When a brief activity has no title/summary AND no briefType, the latest
activity line on the task list rendered just "Brief" / "简要" — useless
text with no actual content. Return undefined in that case so the line
is omitted entirely.
Drops the now-unused `taskDetail.latestActivity.briefOnly` key.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ✨ feat(task): navigate to /page/:id when clicking artifact tree
Drop `selectable={false}` on the workspace tree and wire `onSelect` to
push `/page/<documentId>`, so artifacts are openable from the task
detail page.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 💄 style(task): enforce 10-minute minimum on recurring interval
Drop the Seconds unit from the Recurring tab so users can't schedule
sub-minute intervals (which the runner can't keep up with anyway), and
clamp existing values that are smaller than 10 minutes to 10 minutes
when the popover opens.
Drops the now-unused `taskSchedule.seconds` key.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 💄 style(task): surface needs-review group above backlog in task list
Reorder the default kanban/list groups so `needsInput` (paused + failed)
sits at the top — the list view stacks groups vertically, and putting
actionable items first means users see what needs attention before
scrolling past long backlogs.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🐛 fix(task): catch up next heartbeat firing past stale lastAt
When `lastAt + interval` already lies in the past (e.g. task was paused
for hours), step forward by whole intervals so the returned time is
strictly after now. Otherwise the popover would show a stale
"next run" timestamp until the next tick lands.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ✨ feat(task): open artifact pages in right-side drawer
Replace the `/page/:id` navigation from the artifact tree (a4af053338)
with a right-side drawer that shows the page in-place — the same UX
pattern as the chat document portal, so users keep the task context
while previewing artifacts.
- New `PageDrawer` mirrors `TopicChatDrawer` styling (right-anchored
floating drawer with rounded edges + shadow). Renders `PageExplorer`
inside.
- Task store gains `activePageDrawerPageId` state with
`openPageDrawer` / `closePageDrawer` actions; opening a page also
closes the topic drawer so the two don't stack on the same edge.
- `TaskArtifacts.onSelect` now calls `openPageDrawer(documentId)`
instead of pushing a new route.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🐛 fix(task): seed defaults when entering an automation mode
Switching to a mode without persisting its core fields left the task in
a "mode enabled but unconfigured" state — the popover showed
"自动化未启用" / "Automation is off" because schedulePattern was still
null even though the Schedule tab was active, and the cron runtime had
nothing to fire.
`setAutomationMode` now seeds:
- `heartbeatInterval = 600` (10 min) when entering heartbeat without one
- `schedulePattern = '0 9 * * *'` + `scheduleTimezone = 'UTC'` when
entering schedule mode without them
Existing values are preserved on subsequent mode toggles.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🐛 fix(task): default scheduleTimezone to user's local IANA zone
Hardcoding `UTC` meant a user in Shanghai who picked "Daily 09:00" on a
fresh task would actually fire at 17:00 local. Resolve the user's local
zone via `Intl.DateTimeFormat().resolvedOptions().timeZone` (with a UTC
fallback for environments where Intl is unavailable) so the seeded
default matches what the user expects.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 💄 style(task): polish list, detail, and schedule UI
- Always show top-right + button in kanban view (no inline create input there)
- Unify subtasks/artifacts/activities section indicator on the Accordion arrow
- Refresh schedule popover nextRun every minute and move styling to staticStyles
- Move paused/failed groups ahead of running/backlog in task list ordering
- Color the scheduled status icon with colorWarning to match other active states
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🐛 fix(gateway): gate reconnect on server URL, not user toggle
Resuming a Gateway-running operation should depend on whether the server has
a Gateway URL configured — the user's lab toggle controls *new* requests, not
reattaching to an op that's already running.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ✨ feat(task): surface scheduled state with cancel action and countdown
- Reorder list view group ranks so paused/failed (待审阅) sit above
running and backlog, matching the kanban needsInput-first layout.
- Map `scheduled` task status to the running group so cron/heartbeat
tasks waiting between ticks no longer fall through to backlog.
- Render a muted "Scheduled" pill on task list rows so users can tell
scheduled (waiting) apart from running (executing now) at a glance.
- Add a "Cancel schedule" action and live countdown to the task detail
page when status=scheduled; cancel disables automation AND moves the
task back to backlog so the status badge updates immediately.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 💄 style(task): redesign artifact list as flat cards with file icons
Replace the antd Tree-based artifact view with a flat list of clickable
outlined cards. Each card uses FileIcon (resolves a real file glyph from
the title's extension) and shows the artifact title, size, and source
task tag inline. Removes the unused folder/tree visualization since
workspace nodes today are effectively flat.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 💄 style(task): use warning color for scheduled status icon
Promote the scheduled status icon from `colorTextDescription` to
`colorWarning` so it visually groups with `running` (also warning) — both
states represent "automation in progress" and now share a consistent
warm color, matching how kanban groups them in the same column.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ♻️ refactor(topic): use shared MAIN_SIDEBAR_EXCLUDE_TRIGGERS constant
Replace the local EXCLUDE_TRIGGERS array with the canonical
MAIN_SIDEBAR_EXCLUDE_TRIGGERS exported from `@/const/topic` so the chat
sidebar and any other consumers stay aligned on which trigger types are
hidden from the main topic list.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 💄 style(task): rename artifact label from 作品 to 产物 in zh-CN
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 💄 style(task): align artifact cards with activities content width
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ✨ feat(brief): collapse resolved brief cards by default
Resolved brief cards now show only the header row with a "marked as resolved" badge and an expand chevron; clicking the chevron reveals the summary and actions. Also tightens the collapsed summary max-height from 240 to 180.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 💄 style(task): show human-readable schedule on trigger tag
The list/properties trigger tag rendered the raw cron pattern
("0 9 * * * (Asia/Shanghai)") which is unreadable for non-engineers.
Reuse the popover's `formatScheduleDescription` + `formatTimezoneName`
helpers so the tag now reads as e.g. "每天 09:00 执行 · 中国标准时间".
The raw cron + IANA id moves into the tooltip for users who need it.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 💄 style(task): split timezone onto a smaller secondary line
The schedule summary used to read "每天 09:00 执行 · 中国标准时间" on a
single line, which crowded the popover header and the inline trigger tag
in TaskProperties. Move the timezone onto its own line below the
description with a smaller font and `colorTextDescription`, so the
primary information (when it fires) reads cleanly first.
For the compact pill (`mode='tag'`) used in the task list, drop the
visible timezone entirely — it stays accessible via the tooltip
alongside the raw cron pattern.
Drops the now-unused `taskSchedule.summary.schedule` interpolation key.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 💄 style(task): default to schedule mode + reword automation copy
- Toggle "自动化" on now lands in the Schedule tab (cron) instead of the
Heartbeat tab. A scheduled run is the more common, predictable choice
— users who want fixed intervals can switch tabs from there.
- Rename the heartbeat tab from "循环任务"/"Recurring" to "心跳模式"/
"Heartbeat" so the term matches the underlying mechanism (and the
existing `taskSchedule.tag.heartbeat` copy).
- Replace 执行 with 运行 across the schedule UI strings (持续执行 → 持
续运行, 执行频率 → 运行频率, 下次执行 → 下次运行, etc.) for a more
natural "run" framing.
- Drop dead keys `taskSchedule.interval` and `taskSchedule.schedulerNotReady`.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🐛 fix(brief): resolve brief and re-run task on free-form feedback
The SquarePen feedback editor only called addComment, leaving the
urgent brief unresolved — so the heartbeat re-arm gate kept skipping
the task with reason=human-waiting and the card never moved. Switch
the path to submitFeedback (resolveBrief + task.run) so the agent
picks up resolvedComment on the next turn.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 💄 style(task): make trigger tag hover human-readable too
The pill already shows "每天 09:00 运行", but the tooltip still leaked
the raw cron + IANA id ("0 9 * * * (Asia/Shanghai)") on hover. Replace
it with a single readable line using "·" as separator, e.g.
"每天 09:00 运行 · 中国标准时间".
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* chore: add userId and serverId tooltip guide
* feat: update built in message tool
* ✨ feat(cli): add bot dm-policy / allowlist subcommands (LOBE-8254)
Extend `lh bot update` with --dm-policy / --group-policy / --user-id /
--server-id, and add new `lh bot allowlist` and `lh bot group-allowlist`
subcommand groups (list/add/remove/clear). All write paths read existing
settings first and merge so unrelated keys aren't wiped by the partial
update.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ✨ feat(channel): warn when a saved bot is missing the operator userId
Surface an inline alert and auto-expand the Advanced Settings group when an
existing bot has no settings.userId — without it AI tools can't push
notifications back to the operator and pairing approvals fail silently.
Skip on first-time configs and on platforms that don't expose userId.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* chore: optimize userId alert
* fix: test case
* fix: footer effective userId
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🐛 fix(utils): preserve JPEG format when compressing uploaded images
Images with dimensions > 1920px were always re-encoded as PNG regardless
of original format, inflating small JPEGs (100–200 KB) to 1 MB+ because
PNG is lossless while JPEG is lossy.
Fix: pass file.type to compressImage(), encode JPEG inputs as JPEG at
0.85 quality (not PNG), and derive File MIME type from the data URL
instead of hardcoding 'image/png'.
PNG and WebP inputs still compress to PNG as before.
Fixes#13485
* ✅ test(utils): add tests for JPEG format preservation in compressImage
Per @tjx666's request on #13585. Adds explicit coverage for the JPEG
format-preservation behaviour:
- compressImage with type='image/jpeg' calls toDataURL with quality 0.85
- compressImage with type='image/png' calls toDataURL without a quality arg
- compressImage with no type defaults to PNG
- compressImageFile preserves JPEG inputs as image/jpeg (regression fence
for the previously hardcoded 'image/png' MIME type in dataUrlToFile)
- compressImageFile keeps WebP inputs as PNG (documents the fallback)
The existing PNG tests are preserved to guard against regression in the
lossless path.
---------
Co-authored-by: octo-patch <octo-patch@github.com>
Co-authored-by: YuTengjing <ytj2713151713@gmail.com>
* ♻️ refactor(recent): rewrite queryRecent in Drizzle, exclude web-tool scrapes
- Replace raw SQL UNION with Drizzle's typed unionAll (topicArm/documentArm/taskArm)
- Hoist filter lists into named constants (SYSTEM_TOPIC_TRIGGERS,
TOOL_DOCUMENT_SOURCE_TYPES, TASK_FINAL_STATUSES) for readability
- Recent now excludes documents whose sourceType is in ('file', 'web') so
web-browsing tool scrapes stop leaking in alongside file uploads
- Add RecentModel test coverage
* 🐛 fix(recent): widen TOOL_DOCUMENT_SOURCE_TYPES to const tuple for inArray
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ✨ feat(task): support scheduled status for cron-driven automation
Adds the new `scheduled` task status to the type system, lifecycle, and
UI so cron-driven tasks can park between ticks instead of falling back
to `paused`. Replaces the SchedulerTab placeholder with a real cron
editor (frequency / weekday / time / timezone / max runs) and surfaces
the schedule config through TaskDetailData.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🐛 fix(task): show full execution history in detail
`findWithHandoff` defaulted to a limit of 4, which fits the prompt-build
case but truncated the activity feed in the task detail UI to the latest
4 runs. Make `limit` required and pass 100 from the detail service so
scheduled tasks display their full run history.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 💄 style(QueueTray): use elevated surface tokens
Switch the queue tray's border to colorFillSecondary and its background
to colorBgElevated so it visually sits above the chat input rather than
blending into the page background.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🐛 fix(send-message): forward topic-list filter to server response
Without this, sending a message refreshes `topicDataMap` with an
unfiltered list, so completed/cron topics flash back into the sidebar
until the next SWR revalidation.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🐛 fix(topic): preserve filter fields in internal_updateTopics
internal_updateTopics rewrote topicDataMap[key] from scratch and dropped
excludeStatuses / excludeTriggers, so #getTopicFilter returned undefined
on the second sendMessageInServer call and stopped forwarding the filter
to the server — completed/cron topics could leak in until SWR
revalidated. Carry the filter fields forward from currentData, matching
loadMoreTopics.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🐛 fix(agent): clear stale topic in store when switching agents
Switching agents from `/agent/agt_A/tpc_X` to `/agent/agt_B` left the
previous topic's messages on screen and made *Start new topic* feel
inert. Two fixes:
- ChatHydration: replace the `useEffect`-based `useStoreUpdater` with
`useLayoutEffect` so the URL→store sync of `activeTopicId` /
`activeThreadId` runs before paint. Otherwise Conversation paints
one frame against the prior agent's `activeTopicId` and only catches
up on the next render. Also handles `null` (rather than `undefined`)
so the store actually clears instead of silently retaining the stale
id.
- AgentPage (desktop + web): drive the topic-popup guard from
`useParams().topicId` instead of the store, since URL is the source
of truth for which topic to render.
Drops the now-unnecessary `Portal` import from the desktop variant.
* 🐛 fix(conversation): update context handling and improve thread list visibility logic
Signed-off-by: Innei <tukon479@gmail.com>
* 🐛 fix(topic): update ThreadList to accept topicId prop and improve thread visibility logic
Signed-off-by: Innei <tukon479@gmail.com>
* ✅ test(topic): align topic item thread list mock
* 🐛 fix(agent): show active thread title in conversation header
Header `Tags` always read `topicSelectors.currentActiveTopic(s)?.title`,
so when navigating into a subtopic (`activeThreadId` set via the
`?thread=...` URL sync) the title bar still showed the parent topic's
name. Read the matching thread from `s.threadMaps[s.activeTopicId]`
when `activeThreadId` is set and fall back to `chat:thread.title`
("Subtopic") for unnamed threads.
Signed-off-by: Innei <tukon479@gmail.com>
---------
Signed-off-by: Innei <tukon479@gmail.com>
* 🐛 fix(topic): drop switchTopic race under rapid sidebar clicks
Share the single-click debounce timer at module level so a click on any
topic cancels a pending click from another, and add an epoch guard in
ChatTopicActionImpl.switchTopic so stale refresh continuations cannot
flip activeTopicId back to a superseded topic.
Fixes LOBE-7785
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🐛 fix(topic): yield before refresh so switchTopic epoch can skip stale fetches
The post-await epoch check was dead code: nothing followed the await.
Yield a microtask before the refresh so queued switchTopic sync bodies
can bump #switchTopicEpoch first, then bail the superseded caller before
its SWR mutate ever fires.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🔖 chore(release): release version v2.1.53 [skip ci]
* fix(cli): improve gen status/download error message for wrong asyncTaskId
* docs(cli-skill): clarify asyncTaskId vs generationId in gen status/download
* fix(builtin-skills): clarify asyncTaskId vs generationId in gen status/download
* fix(cli): distinguish asyncTaskId not found vs generationId not found in error message
* Update package.json
---------
Co-authored-by: lobehubbot <i@lobehub.com>
* ✨ feat(tasks/progress): align workspace progress visibility with chat input
Switch the right-side ProgressSection to selectCurrentTurnTodosFromMessages so it appears and disappears in lockstep with the TodoProgress bar above ChatInput, instead of lingering on stale historical todos.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 💄 style(tasks): promote tasks entry into top-level header nav
Place the Tasks entry directly under Home in the sidebar header alongside Search/Home, instead of letting it float inside the customizable body list.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 💄 style(tasks/comment): use filled background for the task detail comment input
Switch the task detail comment input from a bordered card on `colorBgElevated` (which read as outline-only in light mode) to a `colorFillTertiary` filled card so it looks consistently filled in both light and dark themes.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ♿ fix(tasks/progress): restore keyboard toggle & uncap expanded list
Address two regressions introduced when ProgressSection moved off Accordion:
- Re-add keyboard/ARIA semantics on the toggle (role=button, tabIndex, aria-expanded, aria-controls, Enter/Space handler) so keyboard and screen-reader users can collapse/expand the panel. Toggle now lives on the header row only, so clicking todos no longer collapses the panel.
- Replace the `max-height: 600px` cap with the `grid-template-rows: 0fr → 1fr` pattern, letting the list grow to its natural height. Long todo plans are no longer clipped; the parent sidebar (already `overflow-y: auto`) handles scrolling.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ✨ feat(tasks/documents): auto-pin agent-created documents to current task
Why: taskDocuments table and TaskModel.pinDocument exist with pinnedBy='agent',
but the agent-documents runtime never called pinDocument, so documents written
during a task were never linked to that task's workspace.
How: In agentDocumentsRuntime factory, read context.taskId and pin the new
documentId after createDocument / createTopicDocument / copyDocument /
upsertDocumentByFilename. Idempotent via the existing (taskId, documentId)
unique constraint.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ✨ feat(tasks/artifacts): render task-level artifacts on the detail page
Why: The taskDocuments table now auto-populates when an agent writes a doc,
and the backend already serves the workspace tree (own task + descendants)
via getTaskDetail. The detail page just wasn't rendering it yet.
How: New TaskArtifacts component reads activeTaskWorkspace and shows a
collapsible tree (file/folder + size + source-task tag). Selectable is off
for now — click-through interaction will land in a follow-up.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🐛 fix(tasks/lifecycle): deliver onTopicComplete webhook via QStash
The hook was registered without `delivery: 'qstash'`, defaulting to plain
fetch. The target route `/api/workflows/task/on-topic-complete` is mounted
under `qstashAuth()`, which rejects unsigned requests with 401 in
production. `HookDispatcher.fetchDeliver` only logs failures, so the
webhook silently failed — leaving topic.status stuck at 'running' forever
for every heartbeat (and regular) task in production.
Same fix applied to all four agentEvalRun webhook registrations for
consistency, even though those routes are currently unauthenticated.
LOBE-8303
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ✨ feat(desktop/notification): deep-link notification click to source chat
Resolve the SPA path (group / 1:1 topic / agent root) from the conversation
context when posting a desktop notification, and forward it through the
existing main-broadcast `navigate` pipeline so clicking the notification
brings the user back to the originating chat instead of just focusing the
window.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 💄 style(tasks): move tasks tab back into the customizable sidebar
Removes 'tasks' from the fixed header nav and re-adds it as a default,
user-reorderable item under the body sidebar (alongside pages / recents).
Reverts the header-promotion from 287a3ac815 in favor of letting users
place / hide the tab themselves.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 💄 style(tasks/detail): introduce TaskBriefCard, polish topic row layout
- Split a dedicated TaskBriefCard for the detail timeline so brief styling
there can diverge from the daily-brief card without conditionals.
- Promote the agent avatar (with profile popup) to the TopicCard header,
drop the redundant author chip and calendar icon next to the timestamp.
- Move the dashed divider from BriefCardSummary into BriefCard so any
consumer of the summary block doesn't get an unexpected leading rule.
- Tighten card padding (CommentCard / TopicCard) to align with the timeline
rhythm.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 💄 style(agent/header): round segmented control items in ViewSwitcher
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
✨ feat(tasks): drop custom actions on result briefs & show trigger tag in subtasks
- Result briefs render a fixed single-button UI, so reject custom actions at
brief creation time and remove the unused defaults / lifecycle actions.
- Surface automation trigger (heartbeat / schedule) on subtask rows by
threading the fields through TaskService → TaskDetailSubtask → tree.
- Polish: tree title flex/overflow fix, QueueTray send icon swapped to ArrowUp.
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 💄 style(task): right-align subtask assignee avatar and make it clickable
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ✨ feat(brief): standardize result brief actions to mark-as-done + edit
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 💄 style(brief): align decision brief icon with kanban pending-review column
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ✨ feat(brief): rename result brief primary action to "Confirm complete"
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ✨ feat(tasks): wire passive Gateway WS reconnect for the task topic drawer
The task topic drawer rendered messages from the DB but never connected
to the Gateway, so a running task showed only the initial prompt and the
empty assistant placeholder. Server already writes runningOperation into
topic metadata; expose it through TaskDetailActivity and reuse the main
agent reconnect hook so the drawer establishes the WebSocket on open.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 💄 style(brief): mute Check icon on resolved success tag
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🐛 fix(recent): exclude system-trigger topics from the Recent sidebar
The Recent SQL union pulled every topic regardless of trigger, so cron,
eval, task_manager, and task-runner topics leaked into the main "最近"
list alongside ordinary chats. Filter them in the topics SELECT, and
align the long-stale `TopicTrigger.RunTask` constant with the literal
`'task'` that TaskRunnerService actually writes (the const was unused
so no DB migration is needed).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
📝 docs(skills): record contributor roster in version-release skill
- Add Contributor Ordering section with the canonical LobeHub team roster (10 handles) and a flat-list rule (community first, team after, sorted by PR count desc).
- Note the git-author-name vs GitHub-handle pitfall (e.g. YuTengjing -> @tjx666) and how to verify via gh CLI.
- Drop commits count from the changelog template's metadata and contributors lines; reword the contributors intro to a "Huge thanks to N contributors" pattern.
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
When users mention Klavis-managed services (Notion, Slack, Google Drive,
Airtable, Jira, Figma, etc.), the activator now recognizes these as
credential/connection intents and activates lobe-creds automatically.
This enables the full Klavis OAuth flow to be triggered inline without
requiring the user to manually navigate to settings.
Related to #14090
* ✨ feat(cmdk): show agent identity on topic search results
When two topics share the same title (e.g. customer email used as topic
name), the Cmd+K search results were indistinguishable. Surface the
owning agent's avatar + title before the date so users can tell them
apart at a glance.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🔒 fix(cmdk): scope topic→agent join to current user
Prevent cross-tenant agent metadata (avatar / backgroundColor / title)
from leaking into Cmd+K topic search results when a topic row carries
an agentId that resolves to another user's agent — a state reachable
via crafted/migrated rows where topic creation persists input.agentId
even after resolveContext fails.
The agents JOIN now matches on (id AND agents.userId = current user);
mismatched rows fall through as null and the renderer omits the agent
chip rather than surfacing foreign data.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 💄 style(chat-input): drop @-mention hint from follow-up placeholder for heterogeneous agents
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 💄 style(home): hide suggested questions when agent task flag is on
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ✨ feat(task): wire QStash-driven heartbeat self-rescheduling
Implements LOBE-8233: heartbeat tasks now self-arm via QStash delayed
publish (or LocalScheduler setTimeout in dev). After each topic completes,
TaskLifecycleService re-arms the next tick based on current DB state, with
a 3-strike fuse on consecutive errors and a skip-when-urgent-brief guard.
Adds /heartbeat-tick + /watchdog workflow handlers (signed) and extracts
TaskRunnerService from the task.run mutation so both router and tick
handler share one runner.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🐛 fix(task): unblock heartbeat fuse + safe overlap handling + TaskItem typing
- TaskLifecycle re-arm now excludes type='error' urgent briefs from the
human-waiting check; the fresh error brief from onTopicComplete was
always present and stalled retries after the very first failure,
making the 3-strike fuse unreachable.
- TaskRunner only rolls back running→paused when *this* invocation
set the running state; heartbeatTick treats CONFLICT as a graceful
'in-flight' skip so overlapping ticks don't 500 or clobber the
in-flight run's status.
- buildTaskPrompt now types its task arg + getReviewConfig as TaskItem
(the prompts package already depends on @lobechat/types) so server
TaskModel methods are assignable without parameter contravariance
errors.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ♻️ refactor(task): extract qstashAuth Hono middleware for webhook signature verification
Three handlers (on-topic-complete, heartbeat-tick, watchdog) duplicated the
same `c.req.text() → verifyQStashSignature → 401` boilerplate. Extracted to
src/server/workflows-hono/middlewares/qstashAuth.ts and mounted on the
routes; handlers now just `c.req.json()` (Hono cross-converts the cached
body so the middleware reading text() doesn't break json() in the handler).
Note: this is for one-shot QStash webhook receivers. Upstash *Workflow*
endpoints (memory-user-memory) keep using `serve()` from
`@upstash/workflow/hono`, which has its own built-in verification.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ♻️ refactor(task): move buildTaskPrompt back to server (it's a DB orchestrator, not a renderer)
Putting buildTaskPrompt under @lobechat/prompts was a layering mistake:
the function does ~10 DB calls (briefs / topics / subtasks / dep
identifier resolution / parent task assembly) and just maps the rows
through to buildTaskRunPrompt at the end.
The prompts package should stay pure rendering — buildTaskRunPrompt
already lives there as the actual renderer. Moving the orchestrator
back to src/server/services/taskRunner/ also lets it import model
classes directly instead of structurally-typed deps, dropping the
TaskPromptDeps abstraction.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ✨ feat(conversation): persist per-topic chat scroll position to localStorage
Restores scroll position when switching back to a topic, keyed by
messageMapKey(context). Falls back to scroll-to-bottom for new topics or
when the user was already at the bottom. Storage is capped at 500 entries
with 30-day expiry and silent fallback on quota errors.
Fixes LOBE-8251
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🔨 chore(conversation): rename scroll snapshot storage prefix to LOBEHUB
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🔨 chore(conversation): use LOBEHUB_SCROLL as scroll snapshot key prefix
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🐛 fix(conversation): preserve scroll across draft-to-topic key transition
When a draft conversation (`*_new` key) gets promoted to a real topic via
onTopicCreated, the contextKey changes mid-stream for the same logical
conversation. Treating it as a topic switch loaded a missing snapshot and
fell back to scrollToIndex(end), yanking users away from content they
were reading.
Now we detect the draft-promotion shape, migrate the snapshot to the new
key, and skip the restore pass while data is already on screen.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🔥 chore(settings): remove queryRewrite system agent
Removes the unused knowledge-base query rewrite system agent: settings UI in agent/service-model pages, type definition, default config, store selector, server env parser, locale strings across 18 languages, env-variable docs, and the now-orphan chainRewriteQuery prompt chain.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🐛 fix(agent-runtime): scope pending-approval check to current assistant turn
A stale `pluginIntervention.status === 'pending'` row from a prior turn
(e.g. an abandoned approval flow whose user never clicked approve/reject)
gets loaded back into `state.messages` via `historyMessages`, hijacks every
subsequent `tool_result` / `tools_batch_result` phase, and parks the loop
in `waiting_for_human` forever — so after a tool call succeeds, the next
LLM call is never scheduled.
Scope the pending check to tool messages whose `parentId` matches the
current assistant turn (the most recent assistant with `tool_calls`).
* ✅ test(agent-runtime): cover persisted tools pending approvals
* ✨ feat(conversation): queue follow-up sends during running CC turns (Plan A)
Without this, a send fired while a Claude Code turn was running would spawn
a second `claude` process in parallel. Now CC participates in the same
soft-queue path that Client mode already uses: follow-ups are queued and
auto-drained into a fresh sendMessage once the current turn completes.
"Send now" remains a manual stop + send — no new UI, minimum architectural
diff vs. the persistent-stdin Plan B.
Refs LOBE-7346.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ♻️ refactor(conversation): use AI_RUNTIME_OPERATION_TYPES in queue filter
Replace inline `op.type === 'execAgentRuntime' || 'execHeterogeneousAgent'`
with the `AI_RUNTIME_OPERATION_TYPES` constant already used by cancelOperation,
loading-state selectors, and the plugin slice. Picks up `execServerAgentRuntime`
(Gateway) for free — same parallel-run risk as CC, now also queued.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🐛 fix(conversation): drain queue after heteroSessionId is persisted
The drain previously fired from inside onComplete on a fixed setTimeout(100),
racing with the post-sendPrompt updateTopicMetadata write that persists
adapter.sessionId as topic.metadata.heteroSessionId. On the very first queued
follow-up for a topic the metadata write could lose, leaving resolveHeteroResume
to start a fresh CLI session instead of resuming and breaking turn-to-turn
continuity.
Move the drain to run after `await updateTopicMetadata(...)`, so the next
sendMessage observes the just-finished session id. Drain still gated on
"not aborted, no terminal error" — manual stop preserves the queue.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ✨ feat(conversation): add Send-now to QueueTray + keep Stop visible while typing
Two changes for the queue UX:
1. QueueTray: per-row "Send now" icon between Edit and Delete. Clicking it
cancels the current AI runtime op for the context, removes that item from
the queue, and immediately fires sendMessage with its payload. Remaining
queue items stay in place — the new turn's drain picks them up after it
finishes.
2. ChatInput Stop button: previously flipped to Send the moment the composer
had any text during loading (`isInputLoading && isInputEmpty`), which read
as "agent finished" and made queued sends look like fresh sends. Now Stop
stays up for the whole loading window. Enter still enqueues; the QueueTray
Send-now icon is the explicit cancel+send escape hatch.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Object-typed JSON Schemas without `required` could be reserialized as
`required: null` by strict OpenAI-compatible upstreams (bailian / glm /
zhipu), which then reject the request with `at '/required': got null,
want array`. Default missing/non-array `required` to `[]` at the tool
generation boundary so the wire format stays consistent.
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
🐛 fix(agent-runtime): tighten isCanUseVision default to false and add aggregator fallback
The runtime capability probe in RuntimeExecutors used `info?.abilities?.vision ?? true`,
which silently treated any model whose card omits the `vision` ability key as vision-capable.
This neutralised the LOBE-7214 downgrade pass for two real cases:
- Models present in the registry without an explicit `vision: true` (e.g. deepseek-v4-pro)
- Models routed through aggregator providers like `lobehub`, where `(model, providerId)` has
no direct registry hit so the lookup fell through to the default
Switch the default to `false` (matching `isCanUseVideo`) and add a cross-provider fallback
that resolves an aggregator-routed model id against its upstream model card.
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Two follow-ups to the await-review refactor (#14167):
P1: BriefService.resolve previously completed the task on `approve` of any
`decision` brief, but `decision` is also used for non-terminal mid-execution
checkpoints — approving a routine checkpoint shouldn't end the task. Limit
the accept-signal to `result` briefs. The review max-iterations path now
emits a `result` brief (it semantically *is* the final-but-imperfect
deliverable awaiting force-pass), keeping the existing approve→completed
wiring intact for that case.
P2: Judge-accepted result briefs (auto-review pass) were created unresolved,
so the UI rendered active approve/feedback buttons on a task that was
already `completed` — the same lifecycle/UI mismatch the original refactor
set out to remove. Mark the Judge-issued brief as resolved at creation
(`resolvedAction: 'auto-judge-pass'`).
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
✨ feat(conversation): per-phase workflow expand defaults for heterogeneous agents
Extend `defaultWorkflowExpandLevel` to accept either a single level (current
behavior) or an object split by phase (`streaming` / `completion`). Plain
string still applies to both phases.
Wires heterogeneous agents (Codex, Claude Code) to `{ streaming: 'full' }` so
all tool details stay visible while the turn is running, while keeping the
default collapse behavior once the turn finishes.
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🐛 fix(heterogeneous-agent): surface Codex terminal errors and trace CLI output
- Map Codex `error` / `turn.failed` events to terminal error events
- Filter noisy WARN blocks from Codex stderr when reporting exit errors
- Persist CLI stdin/stdout/stderr to .heerogeneous-tracing/ in dev mode
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🐛 fix(heterogeneous-agent): skip trace when cwd is missing
`mkdir(dir, { recursive: true })` would otherwise materialize a stale or
typo'd cwd from scratch, swallowing the configuration error and running
the agent in an unintended empty directory. Probe `cwd` first and bail
out of trace setup so spawn() surfaces the real failure.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Treat agent-emitted `result` briefs as proposals, not completion signals.
Tasks now stay `paused` (await-review) until an explicit accept signal
arrives — user-clicked `approve` action on a `result`/`decision` brief, or
an auto-review (Judge) pass.
Closes LOBE-8223.
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
🐛 fix(builtin-tool-memory): flatten searchUserMemory schema for OpenAI/xAI strict tool validation
Inline `definitions` and `$ref`, bound recursive `anchor` to one level, and
switch `oneOf`/`allOf` to `anyOf` so providers like grok-4 stop rejecting the
tool with "Invalid arguments passed to the model." (LOBE-8224).
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🔥 feat(tasks): drop per-agent /agent/:aid/tasks routes again
PR #13887 reintroduced the per-agent Tasks surface (sidebar entry, route
files, agentId-scoped breadcrumb/list/board, /agent/:aid/tasks/:taskId
navigation) that #14109 had removed in favor of unified /tasks and
/task/:id. Restore the unified-only model: drop the agent sidebar Tasks
nav item, delete the agent-scoped route files, strip agent-tasks blocks
from both desktopRouter configs, and revert the agentId props and
per-agent navigate paths in AgentTasksPage / KanbanBoard / Breadcrumb /
TaskDetailPage. Preserves #14137's canceled kanban column.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🐛 fix(agent): redirect any agent sub-route before opening new topic
handleNewTopic only checked /profile and /channel, so on /agent/:aid/page,
/agent/:aid/cron/:cronId or other sub-routes the redirect was skipped and
mutate() opened a new topic on a non-chat screen — looking ineffective to
the user. Match useTopicNavigation's pattern: derive an agent base path
from params (with topicId when present) and treat anything longer than
that as a sub-route, so adding new sub-routes never re-introduces this gap.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🐛 fix(agent): always push agent chat route before opening new topic
The previous fix conditioned the redirect on isInAgentSubRoute, which
left the URL untouched on /agent/:aid/:topicId — opening a new topic
while the URL still pointed at the previous one. Drop the conditional
and always push /agent/:aid: it covers every sub-route (/profile,
/channel, /page, /cron/:cronId, …) and strips any stale :topicId so
the URL matches the freshly opened topic. Restores Nav.test.tsx.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🧹 chore: remove unused desktop upload IPC
* 🔥 feat(heterogeneous-agent): remove lab flag for GA rollout
External CLI agents (Claude Code, Codex) are now always available on desktop
without the lab toggle. Drops the `enableHeterogeneousAgent` preference,
selector, settings switch, locale strings, and menu-item gating.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ⬆️ chore(deps): bump @lobehub/ui to ^5.9.6 and @lobehub/editor to ^4.9.3
Unpin from exact versions so future patch/minor releases roll in automatically.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🐛 fix(model-runtime): guard tool_use.input against non-object parsed arguments
Anthropic tool_use.input and Gemini functionCall.args both require a plain
object. Models occasionally emit malformed JSON whose top-level shape parses
into an array / null / primitive (e.g. unescaped quotes inside long string
args make the parser re-segment the payload). Previously we assigned the
parsed value directly, causing 400 "Input should be a valid dictionary".
Now guard the parsed value and fall back to {} with a console.warn carrying
tool id / name / parsed type, so we can monitor real-world frequency.
Refs: LOBE-8201
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🐛 fix(model-runtime): recover tool_call input from parsed[0] when arguments parse to an array
Previously fell back to {} when JSON.parse returned a non-object (array /
null / primitive). For the array case, prefer best-effort recovery from
element[0] instead — covers two real model failure modes:
* Single-element wrap: model emitted `[{...real args...}]` instead of
`{...}` → full recovery
* Unescaped quotes re-segmenting a long string arg into multiple objects
→ element[0] still carries the first legit key (e.g. `content` for
writeLocalFile), so partial intent is preserved instead of total loss
Falls back to {} for empty arrays, arrays whose first element isn't a
plain object, and the null/primitive cases (unchanged behavior).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Promote /devtools out of the main layout and break the monolithic gallery
into a layout + sidebar + per-tool detail route (/devtools/:identifier).
Each builtin-tool category (inspectors, interventions, placeholders,
streamings) now exposes a list*Entries registry helper so the sidebar can
enumerate them alongside the existing renders.
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
🐛 fix(model-runtime): use safety_identifier instead of user for OpenAI Responses API
OpenAI Responses API rejects the deprecated `user` parameter ("Unsupported
parameter: user"). Switch the three Responses API call sites
(generateObject, handleResponseAPIMode, generateObjectWithTools) to send
`safety_identifier` instead. Chat Completions paths are left untouched
since this factory backs many openai-compatible providers that still
accept `user`.
Fixes LOBE-8202
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🐛 fix(model-runtime): tolerate null function.name in streaming tool_call deltas
Some providers (NVIDIA NIM with z-ai/glm5 and qwen3.5-MoE, plus some
aihubmix-style proxies) open a streaming tool_call with
\`function.name = null\` as a start marker and supply the real name in a
later delta. The strict MessageToolCallSchema threw ZodError mid-stream
and killed the whole operation before any tokens were even recorded.
- parseToolCalls: coerce null/undefined name to '' before Zod parse;
merge name from subsequent deltas (previously only arguments merged).
- RuntimeExecutors: drop tool_calls whose name never resolved to a
non-empty string before pushing to state.messages, so they can't
poison subsequent history replays on strict providers.
Closes LOBE-8199.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 💬 chore: trim RuntimeExecutors state-persist comment to the phenomenon
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 💄 style(claude-code): polish ToolSearch inspector tag
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🐛 fix(tasks): preserve topic title when handoff is missing
Task activity rows rendered "Untitled" while the topic was still running
because the activity builder read `handoff.title` (populated post-summary)
and fell back straight to a hardcoded constant. Join `topics` in
`findWithHandoff` and fall through `handoff.title → topics.title → Untitled`
so running topics show the task name instead of "Untitled".
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ✨ feat(conversation): add defaultWorkflowExpandLevel to control workflow fold default
Replace WorkflowCollapse.defaultStreamingExpanded (bool) with
defaultWorkflowExpandLevel ('collapsed' | 'semi' | 'full'), threaded
through MessageItem → AssistantGroup → Group → WorkflowCollapse and
exposed on ChatList (applies to the default item renderer only).
When set, pins both the initial state and post-completion reset so
'full' keeps tool-call groups expanded across streaming → complete;
pending intervention still forces expansion.
Apply 'full' in the task detail TopicChatDrawer so viewers see all
tool details by default. Migrate the Onboarding caller from
defaultWorkflowExpanded={false} to defaultWorkflowExpandLevel='collapsed'.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🐛 fix(tasks): restart detail polling after data arrives
SWR's function-form refreshInterval is evaluated on effect mount and after each
timer fires. When the first call runs with cache.data=undefined, our function
returned 0 — so no timer was ever scheduled, and polling never started even
after the fetch populated the cache. Drive polling from a reactive zustand
selector instead, so refreshInterval is a stable number that flips once the
task/topic status is known.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 💄 style(tasks): rename paused label to "Pending review"
"Paused" read like the task was stopped by the user. The actual semantic is
"agent has finished a run and is waiting for user to review and nudge it next" —
so rename the label in STATUS_META and the matching i18n keys (status.paused
and the kanban column needsInput). Also promote paused into USER_SELECTABLE_STATUSES
so users can explicitly park a task back into this state from the context menu.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ✨ feat(tasks): add canceled kanban column
Expose a dedicated "Canceled" column in the kanban board so canceled tasks no
longer blend into the done column. Defaults to hidden (alongside done) to keep
the board compact, and maps the new column key through COLUMN_STATUS_ICON plus
the i18n table that KanbanColumn already referenced but was missing an entry
for.
* 💄 style(tasks): brighten priority icon and add label fallback
- Use colorTextSecondary (brighter than colorTextDescription) for non-urgent
priority icons so they read against the row background.
- Add a static label string to PRIORITY_META so callers can pass it as the
i18n defaultValue instead of an empty string — prevents unlocalised UI when
a translation is missing mid-rollout.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ✨ feat(tasks): route 1–N hotkeys to hovered status/priority submenu
The task context menu already supported number shortcuts to switch status. Extend
that to priority: when the user hovers the Priority submenu, pressing 1–5 picks
the corresponding priority level. A ref tracks which submenu is active (defaults
to Status on open) so the keydown handler knows which list to index into.
Also pick up meta.label as the i18n defaultValue for priority entries, matching
the new PRIORITY_META field so missing translations fall back to readable text
instead of an empty string.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 💄 style(tasks): drop column count from collapsed hidden panel header
The vertical collapsed header was getting noisy with "Hidden · 2" style
duplication — the count is already implied by the expanded tooltip, and the
vertical orientation makes the trailing number crowd the icon.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 💄 style(tasks): show hotkey hint and check in status/priority menu
Surface the 1–N keyboard shortcuts next to each status/priority entry, with a
check icon on the currently selected value. Extract the render into a shared
menuExtra helper so TaskStatusTag and TaskPriorityTag share the same pattern
instead of each inlining its own layout.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ✨ feat(FloatingChatPanel): add single-instance mount guard
* ✨ feat(FloatingChatPanel): add inner ChatBody layout
* ✨ feat(FloatingChatPanel): add reusable floating conversation panel
* ✅ test(FloatingChatPanel): add props wiring smoke tests
* Refactor agent topic and page routes
* Restore topic page routing for floating chat panel
* ✨ feat(FloatingChatPanel): enhance ChatBody and TopicItem for improved routing and styling
- Updated ChatBody to maintain scroll ownership while hiding overflow.
- Refactored TopicItem to correctly highlight active topics based on routing context.
- Added tests for TopicItem to ensure correct active state behavior.
- Introduced static styles for FloatingChatPanel to manage layout overflow.
Signed-off-by: Innei <tukon479@gmail.com>
* chore: help to merge & rebase
* chore: align merge with canary — drop pkg.pr.new ui, adopt canary useMenu, remove NotebookButton
* ✨ feat: add ViewSwitcher component and update localization for chat views
- Introduced a new ViewSwitcher component to toggle between chat, page, and task views in the conversation header.
- Updated English and Chinese localization files to include new labels for the view switcher options.
- Refactored the conversation header to integrate the ViewSwitcher, enhancing the user interface for better navigation.
Signed-off-by: Innei <tukon479@gmail.com>
* fix: update @lobehub/ui to version 5.9.1 and refactor FloatingChatPanel to use FloatingSheet component
- Updated the @lobehub/ui dependency in package.json to version 5.9.1.
- Refactored FloatingChatPanel to utilize the new FloatingSheet component, enhancing its layout and state management.
- Introduced a new ChatLayout component for better organization of chat-related UI elements.
- Adjusted routing configuration to incorporate the new ChatLayout for agent chat pages.
Signed-off-by: Innei <tukon479@gmail.com>
* feat: add TopicCanvas and TitleSection components for topic management
- Introduced TopicCanvas component to serve as a document canvas for topics, integrating an editor and title section.
- Added TitleSection component for managing topic titles and emojis, enhancing user interaction with a dedicated UI.
- Updated FloatingChatPanel to accommodate the new TopicCanvas, ensuring a cohesive layout in the topic page.
- Enhanced tests to verify the integration of TopicCanvas within the topic page route.
Signed-off-by: Innei <tukon479@gmail.com>
* ✨ feat(agent-page): bind documentId to URL and introduce HeaderSlot
- Add nested /agent/:aid/:topicId/page/:docId route with PageRedirect for bare /page
- Introduce useAutoCreateTopicDocument with module-level inflight de-dup
- Lift Portal + WorkingSidebar to (chat) layout; keep ChatHeader in left column
- Sidebar document clicks on page route navigate to /page/:docId instead of opening Portal
- Add HeaderSlot (context + createPortal) as a reusable header injection point
- Mount AutoSaveHint via HeaderSlot; register Files hotkey scope in TopicCanvas so Cmd+S triggers manual save
- Sync desktopRouter.config.tsx and desktopRouter.config.desktop.tsx
- Extend RecentlyViewed plugin to round-trip optional docId segment
* Use topic titles for auto-created page documents
* Add page-agent init gating and runtime diagnostics
* Support current-topic agent documents
* Implement Active Topic Document and Disabled Tool Call Filtering
- Introduced ActiveTopicDocumentContextInjector to inject context for active topic documents into user messages.
- Added DisabledToolCallFilter to remove historical tool calls for disabled tools in the current runtime scope.
- Updated MessagesEngine to utilize the new context injectors and filters.
- Enhanced tests to verify the correct injection of active topic document context and filtering of disabled tool calls.
This update improves the handling of document editing contexts and tool management in the conversation flow.
Signed-off-by: Innei <tukon479@gmail.com>
* feat: enhance agent document management with LiteXML operations
- Updated API names for clarity, changing 'patchDocument' to 'modifyNodes'.
- Introduced LiteXML operation schema for document modifications.
- Implemented new mutation for modifying document nodes via LiteXML.
- Enhanced document retrieval methods to support format options (XML, Markdown, Both).
- Added support for editor data snapshots and normalization of diff nodes.
- Improved document history management to handle editor data with diff nodes.
- Created tests for new features and ensured existing functionality remains intact.
Signed-off-by: Innei <tukon479@gmail.com>
* 🐛 fix: apply agent document xml edits directly
* Refine document cache invalidation and editor hydration
* 🐛 fix: stabilize agent topic hydration
* fix: update @lobehub/editor dependency version and clean up test mocks
Signed-off-by: Innei <tukon479@gmail.com>
* Potential fix for pull request finding 'Useless assignment to local variable'
Co-authored-by: Copilot Autofix powered by AI <223894421+github-code-quality[bot]@users.noreply.github.com>
* 🐛 fix(document): preserve pending diff nodes through save path
Skip normalizeEditorDataDiffNodes on every autosave so diff nodes awaiting
user review survive persistence. Normalization now runs only on explicit
Accept/Reject via DiffAllToolbar. Also flip headless litexml ops to delay:true
to match the new review flow.
* 🐛 fix(agent): detect agent sub-route from URL params not cached topic
isInAgentSubRoute used routeTopicId (with activeTopicId fallback) as its
base path. On /agent/:aid/profile with a cached activeTopicId, the base
became /agent/:aid/:cachedTopicId which pathname cannot startsWith, so
sub-route detection returned false and sidebar topic clicks only called
switchTopic without routing back to chat — users stayed stuck on profile.
Derive the sub-route base from params.topicId directly so stale store
state cannot mask the check. routeTopicId export keeps the fallback for
sidebar highlighting.
* 🐛 fix(page): repair topic page document recovery
* 🐛 fix(page-agent): block tool calls when page editor is not mounted
scope is topic-bound not route-bound, so navigating from /agent/.../Page
to /agent/... keeps scope==='page' and PageAgentIdentifier stayed in the
injected plugin list. The LLM could still call initPage / modifyNodes /
etc. against a stale editor reference, returning misleading success
(e.g. nodeCount=0).
Two layers of guard:
- PageAgentExecutor wraps `invoke` and returns a structured
PAGE_EDITOR_NOT_MOUNTED / kind: 'replan' result when the runtime
editor is not mounted, pointing the LLM at lobe-agent-documents.
- streamingExecutor drops PageAgentIdentifier from the tool set via
the new `composeEnabledTools` pipeline when scope==='page' and
the page-agent runtime is not ready.
Also extract the tool-set composition (inject merge + runtime drops)
out of the ~320-line internal_createAgentState into
`mecha/toolSetComposer`, with unit tests.
* 🐛 fix(chat): unify message stream for /agent/:topicId and /page/:docId
Before this change a page-scoped conversation (FloatingChatPanel with
scope='page' in the /Page route) partitioned the client message store by
scope, so /agent/:topicId and /agent/:topicId/page/:docId each built their
own messagesMap slot and SWR cache — but the TRPC getMessages endpoint
ignores scope and returned the same messages for both, producing duplicate
fetches and a visible message-history split between the two surfaces.
Fixes by keeping scope='page' as a capability/surfacing marker only:
- messageMapKey: collapse 'page' to the default scope early in
toMessageMapContext, so threadId/groupId still win and only the
main/page pair actually unifies.
- useFetchMessages: build the SWR key from identity fields
(agentId, groupId, threadId, topicId) instead of the full
ConversationContext, so scope no longer partitions the cache.
agentConfigResolver/streamingExecutor/composeEnabledTools still read
scope='page' from operation.context for PageAgent injection and
initialContext.pageEditor wiring — the capability layer is unchanged.
Also fix two pre-existing test regressions surfaced by re-running the
impacted suites:
- streamingExecutor page-editor initialContext test now mocks
pageAgentRuntime.isReady() (required since the PageAgent editor-ready
guard landed).
- FloatingChatPanel default shell props test updated to match the
[180,320,520,800] snap points introduced in 62dc91e444.
* ♻️ refactor(FloatingChatPanel): read main slot without changing scope
Revert the global messageMapKey/SWR-key changes from b650cdc9d7 — the
global collapse over-reached and coupled message routing to scope in
ways other surfaces don't want. Instead, specialize only the place that
actually has the dual-role problem.
`scope` should be a capability marker (PageAgent tool + pageEditor
initialContext injection), not a message-list partition. Floating panel
on /agent/:topicId/page is the only caller that sets scope='page', and
its message list should mirror /agent/:topicId — the surfaces share a
topic.
Local collapse in FloatingChatPanel: compute chatKey with
`scope === 'page' ? 'main' : scope`, so messagesMap is read from the
main slot. The downstream ConversationContext keeps scope='page' for
the capability layer; only the slot lookup is specialized.
Kept from b650cdc9d7 (unrelated to the revert):
- streamingExecutor test mocks pageAgentRuntime.isReady() — required
by the PageAgent editor-ready guard in 01ef7bc142.
- FloatingChatPanel snap-points test matches [180,320,520,800] from
62dc91e444.
* 🐛 fix(FloatingChatPanel): simplify chat key computation for message retrieval
Signed-off-by: Innei <tukon479@gmail.com>
* 🐛 fix(index.desktop.test): update LocationProbe to reflect route changes and improve test accuracy
Signed-off-by: Innei <tukon479@gmail.com>
* Constrain agent header title under centered switcher
* 🐛 Fix conversation header view switcher layout
* 🐛 Fix agent topic path links and cmdk context
* 🐛 fix(test): align document history fixtures and layout ui mock
* 🐛 fix(e2e): support dialog-based topic rename
* ♻️ refactor(debug): use scoped debuggers for PR logging
---------
Signed-off-by: Innei <tukon479@gmail.com>
Co-authored-by: Neko Ayaka <neko@ayaka.moe>
Co-authored-by: Copilot Autofix powered by AI <223894421+github-code-quality[bot]@users.noreply.github.com>
* ✨ feat: polish task list id and date display
* ✨ feat: hide completed tasks from agent task card list
Completed tasks crowd the homepage card list and bury the ones that
still need attention; extract sort/limit into a testable helper so the
filter lives in one place.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ✨ feat(claude-code): render Agent tool streaming with instruction and subagent thread toggle
While a subagent is running (args parsed, tool_result not back) the CC
Agent tool fell back to the generic 参数列表 dump. Surface the instruction
markdown and, once the executor has created the subagent Thread, the
open/close subtopic button — so the user can jump into the live
conversation instead of waiting for the summary.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ✨ feat(tasks): add /tasks sidebar entry and Linear-style item context menu
- Wire up /tasks as a top-level home sidebar item (gated on enableAgentTask) and register route metadata for Electron tab title
- Render a dashed UserRound placeholder when a task has no assignee, and add a search input + arrow-key navigation to the agent picker popover
- Wrap task list rows in a ContextMenuTrigger with status/priority submenus, copy id/link, and delete-with-confirm
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ✨ feat(tasks): unify task routes under /tasks and /task/:id, drop agent-scoped pages
Removes the per-agent `/agent/:aid/tasks` list and detail routes in favor of a
single cross-agent surface (`/tasks` list/kanban + `/task/:taskId` detail).
Kanban board now fetches across all agents via `useFetchTaskGroupList({ allAgents })`,
fixing the blank board on the `/tasks` route.
UI polish shipped alongside:
- Hidden kanban columns panel persists to global status, pinned to the right with
a swim-lane background to match other columns.
- Breadcrumb chevron margins tightened; separator, ancestors, and task detail
crumbs share the same compact styling.
- TaskDetailAssignee renders a clickable "Unassigned" placeholder when no agent
is set, so the selector is always reachable.
- Run button stays clickable without an assignee; falls back to the inbox agent
on click so users get a working default.
- Breadcrumb drops the per-agent tasks link; nav inside agents removes the now
dangling Tasks tab since `/tasks` is a top-level sidebar entry.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ✨ feat(tasks): hide completed & canceled tasks by default with Show footer
Hides completed/canceled tasks by default in the list view with a Linear-style "N tasks hidden by display options · Show" footer and a toggle in the display-options popover.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ✨ feat(tasks): add copy id/link actions to task detail header, use app origin
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🔥 refactor(tasks): drop agentId plumbing from unified task detail route
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 💄 style(tasks): float topic chat drawer with read-only messages
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 💄 style(tasks): inline subtasks add button and run button loading state
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ✨ feat(workflows): unify hono scaffold and add task on-topic-complete webhook
Consolidate workflow routes behind a single Hono app mounted at the
catch-all /api/workflows/[[...route]], with per-domain sub-apps. New
workflow segments now only need a folder under src/server/workflows-hono/
plus one app.route(...) line in the root — no new Next.js route files.
Also implements /api/workflows/task/on-topic-complete, which task.run
registers as the onComplete webhook. The handler wires the payload into
TaskLifecycleService.onTopicComplete; task.run now also includes
taskIdentifier in the webhook body so the handler skips a DB lookup.
LOBE-6659
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 💄 style(tasks): align subtasks header pill with add button on same row
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ✨ feat(tasks): add AgentTaskManager side panel and polish task detail
- Mount AgentTaskManager conversation alongside the task detail route and
sync the task's assignee agent into chat store so the right panel talks
to the correct agent
- Reverse activities timeline to newest-first and float the comment input
on top with a card-styled container and guiding placeholder copy
- Redesign TopicCard with a live status icon, meta row, and dropdown
actions (open run / copy id); introduce shared TopicStatusIcon with
animated running state
- Swap task status palette: running uses warning+CircleDot, paused uses
info+Hand; show numeric shortcut extras on context menu status/priority
items alongside the checkmark for the current value
- Refresh hidden-columns panel to panel-open/close icons and inline the
count beside the header
- Drop fixed min height on create-task inline editor; tighten activity
row padding
- Fix Flexbox import in useTaskItemContextMenu (react-layout-kit → @lobehub/ui)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 💄 style(tasks): show topic status icon in chat drawer title
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 🐛 fix(tasks): drop stale AutoSaveHint on task list page
Task list does not save anything, but it reused the global taskSaveStatus from detail page — after editing a task, switching back to the list would still show "latest version loaded".
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 💄 style(tasks): drop redundant status tag in topic chat drawer title
Status is already expressed by the colored TopicStatusIcon next to the title.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 💄 style(tasks): add tooltip hint for unassigned assignee
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 💄 style(tasks): polish topic chat drawer border and spacing
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 💄 style(tasks): show check before shortcut in context menu extra
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ♻️ refactor(conversation): unify spacer + scroll-to-user hooks
Merge `useConversationSpacer` and `useScrollToUserMessage` into a single
`useConversationScroll` hook to eliminate the races that caused occasional
"send message but viewport doesn't pin to the new user message" regressions.
Race fixes:
- Single `prevLengthRef` and a single send-detection effect, replacing two
hooks with independent length tracking that could disagree across renders.
- `virtuaRef` is passed in and dereferenced at call time instead of reading
`virtuaRef.current?.scrollToIndex` during render — removes the window
where the ref hadn't been attached yet when a send fired.
- Pin state is an explicit `{ index, seenActive }` ref with three clear
transitions (send / layout-bump / user-scroll-up) instead of several
cooperating refs + derived flags.
- Retries are layout-driven: each `spacerLayoutVersion` bump re-fires
`scrollToIndex` exactly once. The old 0/32/96ms timer fan-out is gone.
Also bumps `AT_BOTTOM_THRESHOLD` 100 → 300 so `atBottom` stays stable
while the spacer is settling.
* ♻️ refactor(conversation): extract sub-hooks from useConversationScroll
Split the unified conversation scroll hook into four cooperating sub-hooks
in the same file so each layer has one clear concern:
- useSpacerLayoutSignal — ResizeObserver on the spacer node → version bumps
- useSpacerHeight — natural height / mount lifecycle / shrink state
- usePinController — pin state machine + virtua-aware scroll dispatch
- useScrollShrink — scrollOffset delta → cancel pin / shrink spacer
The main hook now owns just the send-detection effect, the pin re-fire on
layout settle, and derived output. Behavior is unchanged — same 15 tests
pass — but each piece is now readable in isolation.
* ⚡️ perf(conversation): narrow VirtualizedList subscription to a boolean
VirtualizedList only needs to know whether the second-to-last message is
the user's — the full displayMessages array was never used. Move the
derivation into `dataSelectors.isSecondLastMessageFromUser` so the
component re-renders on role transitions, not on every assistant token.
* ✅ test(e2e): cover conversation scroll behavior across the auto-scroll setting
Adds three scenarios under `@AGENT-SCROLL-*` that exercise the merged
`useConversationScroll` hook end-to-end through the real chat UI:
- AGENT-SCROLL-001 — with auto-scroll ON, the viewport ends up near the
bottom once a long response has finished streaming.
- AGENT-SCROLL-002 — with auto-scroll OFF, the user's message stays
pinned to the top and the viewport does not chase the assistant.
- AGENT-SCROLL-003 — with auto-scroll ON, scrolling up mid-stream cancels
the pin and the viewport is not yanked back to the bottom afterwards.
Also extends the LLM mock with `setConfig` / `resetConfig` so scenario 3
can slow the response down enough for the mid-stream manual scroll, and
adds `presetResponses.longScrollArticle` (long enough to overflow the
viewport so scroll assertions are meaningful).
* ✅ test(e2e): cover send-time pin-to-top as its own scenario
AGENT-SCROLL-004 exercises the core pin behavior of `useConversationScroll`
independent of the auto-scroll setting: after sending a message, the user's
turn must be anchored to the top of the scrollport. Uses the slow-response
mock so the assertion runs while the spacer is still mounted.
* ✅ test(e2e): tune scroll scenarios after runtime validation
Run outcomes against a cold Next dev server (paradedb + next dev -p 3006):
- AGENT-SCROLL-001 (enabled → viewport stays near bottom) — passing
- AGENT-SCROLL-002 (disabled → user msg pinned to top) — passing
- AGENT-SCROLL-004 (send pins user msg to top) — passing
- AGENT-SCROLL-003 (mid-stream scroll-up cancels pin) — skipped
Scenario 3 is marked `@skip` until the LLM mock supports truly chunked
SSE streaming. The current mock fulfils the whole body at once, which
collapses the "mid-stream" window to a handful of ms and makes the
manual-scroll timing race-prone. The cancel-pin path is already
covered at the unit level in `useConversationScroll.test.ts`, so the
e2e placeholder just keeps the scenario on the radar.
Other tweaks for dev-mode reliability:
- Bumped setting-toggle step timeout to 90 s (turbopack cold compile of
`/settings/chat-appearance` can exceed the default 30 s on first hit)
- Relaxed the inner `networkidle` / `toBeVisible` waits there to match
- Added a matching negative-path Then ("not pinned") that would power
the skipped scenario once the mock is upgraded
* 🐛 fix(conversation): rebind pin tracking on every new turn
The message index refs that drive `latestAssistantSignature` and the
messages `ResizeObserver` were plain `useRef`s updated inside the send-
detection effect. On the render triggered by spacer state updates right
after a send, `[dataSource, displayMessages]` could be unchanged, so the
signature memo returned its cached value and the observer effect never
rebound to the new turn's user/assistant DOM nodes. Under certain commit
orderings this left spacer height tracking the previous turn and let
the pin-to-user anchor drift.
Turn the indices into state, include `assistantMessageIndex` in the
signature memo's deps, and forward the state (not a ref) to
`useSpacerHeight`. The observer now reliably rebinds to the fresh
nodes on the very next render.
Adds a unit regression covering the observer-rebind path and an e2e
scenario (`AGENT-SCROLL-005`) that sends two consecutive turns and
checks that the second user message still pins to the top.
* feat: add the agent runtime tools call hooks
* feat: add more agent runtime hooks
* fix: add the lost hooks
* fix: add the agent runtimes hooks test
* fix: slove some error
* fix: change the as any to hooksEvent
* fix: slove the lint error
* fix: slove the lint error
* fix: slove the lint error
* fix: clean the code
* fix: change the toolCallCounts into all mode & add all hooks into qstash runtime way
* 🐛 fix: harden beforeToolCall mock validation and remove userId fallbacks
- dispatchBeforeToolCall returns { content, isMocked } instead of { content } | null
for explicit mock detection (avoids falsy content edge cases)
- mock() rejects invalid content: empty string, undefined, object, array, number, null
- Remove all `userId: ctx.userId || ''` fallbacks — userId absence should surface, not silently degrade
- beforeToolCall adds separate dispatch() observation path for QStash webhook delivery
- Add BeforeToolCallObservationEvent type for production webhook payload
- Add 3 unit tests for mock content validation edge cases
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* ✨ feat(builtin-skills): add bot platform setup guide reference
Add `references/bot-setup-guide` to the LobeHub skill with step-by-step
credential setup instructions for Discord, Slack, Telegram, Feishu, Lark,
QQ, and WeChat. Enables agents to guide users through platform bot
configuration end-to-end via the `lh bot` CLI workflow.
* ✨ feat(builtin-skills): split bot setup guide into per-platform references
Replace the single `bot-setup-guide` reference with 7 platform-specific
guides (Discord, Telegram, Slack, Feishu, Lark, QQ, WeChat), each with
detailed step-by-step credential setup instructions matched to the actual
schema fields. Also update the LobeHub skill description to trigger
activation when users mention connecting messaging platform bots.
* ♻️ refactor(builtin-skills): nest bot platform guides under references/bot/ directory
Move bot setup guide resource keys from flat `references/bot-*` to
nested `references/bot/*` so they appear as a subfolder in the
skill resource tree instead of a flat list.
* 🐛 fix(builtin-skills): fix Telegram --app-id and WeChat CLI setup guide
- Telegram: add required --app-id (numeric bot ID from token prefix)
to the lh bot add command; explain how to extract it from the token
- WeChat: remove incorrect CLI QR scan flow; lh bot connect only starts
an already-configured provider and does not perform QR auth.
Redirect users to Web UI for initial WeChat setup
* 📝 docs(builtin-skills): clarify WeChat setup steps with exact UI navigation
Guide users to click 消息频道 (Message Channel) in the left sidebar
then select WeChat to get the QR code, matching the actual UI layout.
description: "Agent runtime lifecycle hooks for observing and intercepting agent execution. Use when adding hooks to agent operations, mocking tool calls, logging step events, handling human intervention, sub-agent calls, context compression, or building eval/tracing integrations. Triggers on 'hooks', 'beforeToolCall', 'afterToolCall', 'beforeStep', 'afterStep', 'onComplete', 'onError', 'tool mock', 'agent lifecycle', 'human intervention', 'callAgent', 'compact'."
user-invocable: false
---
# Agent Runtime Hooks
Lifecycle hooks for observing and intercepting agent execution. Hooks are registered per-operation via `execAgent({ hooks })` and dispatched by `HookDispatcher`.
## Hook Types
16 hook types across 5 categories:
```
execAgent({ hooks })
│
├─ beforeStep ──────────── Before each step executes
│ │
│ ├─ [call_llm] LLM inference
│ │
│ ├─ [call_tool]
│ │ ├─ beforeToolCall ── Before tool executes (supports mocking)
│ │ ├─ (tool execution)
│ │ ├─ afterToolCall ─── After tool completes (observation only)
│ │ └─ onToolCallError ─ Tool threw an exception
│ │
│ ├─ [request_human_approve]
│ │ ├─ beforeHumanIntervention ── Before agent pauses
│ │ ├─ afterHumanIntervention ─── After approve/reject + resume
│ │ └─ onStopByHumanIntervention ── User rejected, agent halted
│ │
│ ├─ [compress_context]
│ │ ├─ beforeCompact ──── Before compression starts
│ │ ├─ afterCompact ───── After compression completes
│ │ └─ onCompactError ─── Compression failed
│ │
│ ├─ [callAgent] (via execSubAgentTask)
│ │ ├─ beforeCallAgent ── Before sub-agent starts
│ │ ├─ afterCallAgent ─── After sub-agent completes
│ │ └─ onCallAgentError ── Sub-agent failed
│ │
│ └─ afterStep ──────────── After step completes
│
├─ (next step...)
│
├─ onComplete ───────────── Operation reaches terminal state
└─ onError ──────────────── Error during execution
**`onCallAgentError`** — Sub-agent failed. Dispatched on **parent** operation.
```ts
// event: CallAgentErrorHookEvent
{
(operationId,agentId,error);
}
```
Note: CallAgent hooks require `parentOperationId` in `ExecSubAgentTaskParams`.
## Design Notes
- **Fire-and-forget**: All handlers return `Promise<void>`. Errors are non-fatal.
- **Exception**: `beforeToolCall` supports mock via `event.mock()` — uses `dispatchBeforeToolCall()` which returns the mock result.
- **Sequential**: Same-type hooks run in registration order.
- **Local only**: `beforeToolCall` mock only works in local mode (in-memory hooks). Webhook mode does not support mocking.
- **Scoped per operation**: Auto-cleaned via `hookDispatcher.unregister()` on completion.
- **Sandbox/MCP**: No separate hooks — they go through `executeTool`, so `beforeToolCall`/`afterToolCall` cover them. Use `event.identifier` to filter.
## Real-World Example: agent-evals
See `devtools/agent-evals/helpers/runner.ts` — `createEvalHooks()` uses `afterStep`, `onComplete`, `afterToolCall`, and `beforeToolCall` (for mock).
description: Build or extend LobeHub Agent Signal pipelines for background or quiet agent work driven by event sources, semantic signals, and action handlers. Use when adding a new Agent Signal source, signal or action type, policy, middleware handler, workflow handoff, dedupe or scope behavior, or observability around `src/server/services/agentSignal/**`, `packages/agent-signal`, or `packages/observability-otel/src/modules/agent-signal`.
---
# Agent Signal
Use this skill to implement event-driven background work for agents without coupling the work to the foreground chat request.
1. Read `references/architecture.md` to map the package boundary, runtime queue, scope model, and async workflow handoff.
2. Read `references/handlers.md` before writing any new policy, source handler, signal handler, or action handler.
3. Read `references/observability.md` when you need tracing, metrics, debugging, or workflow snapshot visibility.
## Use The Right Entry Point
- Use `emitAgentSignalSourceEvent(...)` when a server-owned producer should execute the pipeline immediately.
- Use `executeAgentSignalSourceEvent(...)` when a worker or controlled backend path already owns execution timing and may inject a runtime guard backend.
- Use `enqueueAgentSignalSourceEvent(...)` when the caller should return quickly and let Upstash Workflow process the event out-of-band.
- Use `emitAgentSignalSourceEventWithStore(...)` for isolated tests or evals that should avoid ambient Redis state.
Read:
-`src/server/services/agentSignal/index.ts`
-`src/server/workflows/agentSignal/index.ts`
-`src/server/workflows/agentSignal/run.ts`
## Core Model
-`source`: A normalized fact that happened. Sources come from producers such as runtime lifecycle events, user messages, or bot ingress.
-`signal`: A semantic interpretation derived from one source or from another signal. Signals express meaning, routing, or policy state.
-`action`: A concrete side effect planned from one signal. Actions do the work.
-`policy`: An installable middleware bundle that registers source, signal, and action handlers.
-`procedure`: Not a distinct runtime node. Treat "procedure" as the end-to-end flow for one use case: ingress source, matching handlers, planned actions, execution result, and observability.
Keep the boundaries strict:
- Add a new `source` when the outside world produced a new event.
- Add a new `signal` when the system needs a reusable semantic interpretation.
- Add a new `action` when the runtime needs a concrete side effect.
- Add or update a `policy` when you are wiring those pieces together.
## Implementation Workflow
1. Decide whether the use case is synchronous or quiet background work.
2. Define or reuse a source type in `src/server/services/agentSignal/sourceTypes.ts`.
3. Define or reuse signal and action types in `src/server/services/agentSignal/policies/types.ts`.
4. Implement handlers with `defineSourceHandler`, `defineSignalHandler`, or `defineActionHandler`.
5. Bundle handlers with `defineAgentSignalHandlers(...)`.
6. Register the policy in `src/server/services/agentSignal/policies/index.ts` and pass it into the runtime factory if needed.
7. Add or update ingress code that emits or enqueues the source event.
8. Add observability and tests before considering the flow complete.
- Reuse existing source, signal, and action types before adding new ones.
- Keep source handlers focused on interpretation and fan-out, not heavy side effects.
- Keep action handlers responsible for side effects, idempotency, and executor-style result reporting.
- Use stable ids and idempotency keys when the same source can arrive more than once.
- Preserve scope discipline. The runtime uses `scopeKey` to serialize related background work.
- Prefer the dedicated shared package types and builders from `@lobechat/agent-signal` for normalized nodes and result contracts.
- Add focused tests near the touched runtime, policy, or store module. Existing tests under `src/server/services/agentSignal/**/__tests__` are the reference pattern.
## References
- Architecture and boundaries: `references/architecture.md`
- Writing handlers and policies: `references/handlers.md`
- Observability, metrics, and debugging: `references/observability.md`
- a trace envelope with source, signals, actions, results, edges, and handler runs
- a compact telemetry record with dominant path, status breakdown, and chain metadata
This projection is built from:
- source node
- emitted signals
- planned actions
- executor results
## How To Inspect A Chain
Use this order:
1. Inspect the source type and payload.
2. Inspect emitted signals.
3. Inspect planned actions.
4. Inspect executor results.
5. Inspect projected edges and dominant path.
The helper `toAgentSignalTraceEvents(...)` flattens a chain into compact event records suitable for tracing snapshots.
## Workflow Snapshot Bridge
Workflow-triggered runs do not naturally pass through the normal foreground runtime snapshot path, so `runAgentSignalWorkflow` adds a development-only bridge into `.agent-tracing/`.
Read:
-`src/server/workflows/agentSignal/run.ts`
Use that path when:
- the source was enqueued with `enqueueAgentSignalSourceEvent(...)`
- you need local trace visibility for quiet background work
## Common Debug Questions
### The source emits but nothing happens
Check:
- feature gate enabled for the user
- source type matches a registered source handler
- dedupe or scope lock did not short-circuit generation
@@ -166,7 +166,7 @@ Each platform exposes a `PlatformDefinition` registered in `platforms/index.ts`:
}
```
`schema` drives both server validation (`mergeWithDefaults`, `extractDefaults`) **and** the auto-generated UI form. Top-level keys `applicationId` / `credentials` / `settings` map to DB columns. Common settings fields live in `platforms/const.ts` (`displayToolCallsField`, `serverIdField`, `userIdField`).
`schema` drives both server validation (`mergeWithDefaults`, `extractDefaults`) **and** the auto-generated UI form. Top-level keys `applicationId` / `credentials` / `settings` map to DB columns. Common settings fields live in `platforms/const.ts` (`displayToolCallsField`, `makeServerIdField(platform?)`, `makeUserIdField(platform?)`). The `serverId` / `userId` factories take a platform identifier so the field's hint can render platform-specific "how to find this ID" guidance (Discord Developer Mode, Telegram @userinfobot, etc.); pass no argument to fall back to generic copy.
Each platform implements `PlatformClient` (see `platforms/types.ts`):
-`src/server/routers/lambda/video/index.ts` — video creation (uses `authedProcedure` + `serverDatabase`)
-`src/server/routers/lambda/generation.ts` — status checking
-`packages/database/src/models/asyncTask.ts` — `AsyncTaskModel` including `checkTimeoutTasks`
**Note**: Image/video routes do NOT use the `keyVaults` middleware — they read API keys from the database via `initModelRuntimeFromDB` or `createAsyncCaller`.
@@ -30,6 +30,17 @@ This is NON-NEGOTIABLE. Skipping Linear comments is a workflow violation.
When creating issues with `mcp__linear-server__create_issue`, **MUST add the `claude code` label**.
## Language
Issue titles, descriptions, and comments **MUST follow the language of the current conversation**, not default to English.
- Conversation in 中文 → issue body in 中文;technical terms (file paths, identifiers, library names, commands, error messages) stay in English.
- Conversation in English → issue body in English.
- Code blocks, file paths, and quoted strings always stay in their original form regardless of surrounding language.
- This applies equally to **updates** — when editing an existing issue (description **and titles**), preserve the language of the conversation that triggered the edit; do not switch the issue language during a refactor (Chinese → English or vice versa).
Rationale: the issue is a continuation of the conversation. Forcing English when the discussion is in Chinese creates translation friction for the collaborator who came from that thread.
## Creating Sub-issue Trees
When breaking a parent issue into a tree of sub-issues (e.g., task decomposition for LOBE-xxx), follow these rules — they work around real limitations of the Linear MCP tools.
description: 'Code review checklist for LobeHub. Use when reviewing PRs, diffs, or code changes. Covers correctness, security, quality, and project-specific patterns.'
name: review-checklist
description: 'Common recurring mistakes in LobeHub code review — console leftovers, missing return await, hardcoded secrets, hardcoded i18n strings, desktop router pair drift, antd vs @lobehub/ui, non-idempotent migrations, cloud impact red flags. Use as a quick checklist when reviewing PRs, diffs, or branch changes.'
---
# Code Review Guide
# Review Checklist
## Before You Start
1. Read `/typescript` and `/testing` skills for code style and test conventions
2. Get the diff (skip if already in context, e.g., injected by GitHub review app): `git diff` or `git diff origin/canary..HEAD`
## Checklist
### Correctness
## Correctness
- Leftover `console.log` / `console.debug` — should use `debug` package or remove
- Missing `return await` in try/catch — see <https://typescript-eslint.io/rules/return-await/> (not in our ESLint config yet, requires type info)
- Can the fix/implementation be more concise, efficient, or have better compatibility?
### Security
## Security
- No sensitive data (API keys, tokens, credentials) in `console.*` or `debug()` output
- No base64 output to terminal — extremely long, freezes output
- No hardcoded secrets — use environment variables
### Testing
## Testing
- Bug fixes must include tests covering the fixed scenario
- New logic (services, store actions, utilities) should have test coverage
- Existing tests still cover the changed behavior?
- Prefer `vi.spyOn` over `vi.mock` (see `/testing` skill)
### i18n
## i18n
- New user-facing strings use i18n keys, not hardcoded text
- Keys added to `src/locales/default/{namespace}.ts` with `{feature}.{context}.{action|status}` naming
- For PRs: `locales/` translations for all languages updated (`pnpm i18n`)
### SPA / routing
## SPA / routing
- **`desktopRouter` pair:** If the diff touches `src/spa/router/desktopRouter.config.tsx`, does it also update `src/spa/router/desktopRouter.config.desktop.tsx` with the same route paths and nesting? Single-file edits often cause drift and blank screens.
### Reuse
## Reuse
- Newly written code duplicates existing utilities in `packages/utils` or shared modules?
- Copy-pasted blocks with slight variation — extract into shared function
@@ -238,13 +238,34 @@ Use `---` separators between major blocks for long releases.
- Keep concise.
- Must include `Migration overview`, operator impact, and rollback/backup note.
### Contributor Ordering
Render contributors as a **single flat list** (no separate "Community" / "Core Team" subsections). Order: **community contributors first, team members after**. Within each group, sort by PR count desc. Bots (`@lobehubbot`, `renovate[bot]`) go on a separate "maintenance" line.
**LobeHub team roster** — anyone in this list is a team member; anyone not in this list is a community contributor:
-@arvinxx
-@Innei
-@tjx666 (commit author name: YuTengjing)
-@LiJian
-@Neko
-@Rdmclin2
-@AmAzing129
-@sudongyuer
-@rivertwilight
-@CanisMinor
> **Resolving handles** — git author names (e.g. `YuTengjing`) are not always the GitHub handle. Verify via `gh pr view <PR> --json author` or `gh api search/users -f q='<email>'` before listing.
If a new contributor appears who is not on this list, treat them as community by default and ask the user whether to add them to the roster.
**Hotfix Scope:** Agent topic-switching regression — stale chat state on agent change
> Clears residual topic state when navigating between agents and restores blank-canvas behavior on agent switch.
## 🐛 What's Fixed
- **Stale topic on agent switch** — Switching from `/agent/agt_A/tpc_X` to `/agent/agt_B` no longer leaves the previous topic's messages on screen, and _Start new topic_ responds again. (#14231)
- **Header & sidebar consistency** — Conversation header now shows the active subtopic's title, and the sidebar keeps the parent topic's thread list expanded while a thread is open.
## ⚙️ Upgrade
- Self-hosted: pull the new image and restart. No schema or env changes.
- Cloud: applied automatically.
## 👥 Owner
@{pr-author}
> **Note for Claude**: Replace `{pr-author}` with the actual PR author. Retrieve via `gh pr view <number> --json author --jq '.author.login'`. Do not hardcode a username.
2.**Create PR to main** with a gitmoji prefix title (e.g. `🐛 fix: description`)
3.**After merge**: auto-tag-release detects `hotfix/*` branch → auto patch +1.
3.**Write a short hotfix changelog** — See `changelog-example/hotfix.md`. Keep it minimal: scope line, 1-3 fix bullets (symptom + fix in one sentence), upgrade note, owner. No long root-cause section — that lives in the commit message.
- **Hotfix owner**: Use the actual PR author (retrieve via `gh pr view <number> --json author --jq '.author.login'`), never hardcode a username.
4.**After merge**: auto-tag-release detects `hotfix/*` branch → auto patch +1.
- **@ONLY-yours**: Performance, streaming, settings, general bugs, web platform, marketplace, agent builder, schedule task
- **@tjx666**: Model providers and configuration, new model additions, image/video generation, vision, cloud version, documentation, TTS, auth, login/register, database
This document serves as a comprehensive guide for all team members when developing LobeHub.
## Project Description
You are developing an open-source, modern-design AI Agent Workspace: LobeHub (previously LobeChat).
Guidelines for using AI coding agents in this LobeHub repository.
## Tech Stack
- **Frontend**: Next.js 16, React 19, TypeScript
-**UI Components**: Ant Design, @lobehub/ui, antd-style
-**State Management**: Zustand, SWR
-**Database**: PostgreSQL, PGLite, Drizzle ORM
-**Testing**: Vitest, Testing Library
-**Package Manager**: pnpm (monorepo structure)
- Next.js 16 + React 19 + TypeScript
-SPA inside Next.js with `react-router-dom`
-`@lobehub/ui`, antd for components; antd-style for CSS-in-JS — **prefer `createStaticStyles` with `cssVar.*`** (zero-runtime); only fall back to `createStyles` + `token` when styles genuinely need runtime computation. See `.cursor/docs/createStaticStyles_migration_guide.md`.
-react-i18next for i18n; zustand for state management
-SWR for data fetching; TRPC for type-safe backend
SPA-related code is grouped under `src/spa/` (entries + router) and `src/routes/` (page segments). We use a **roots vs features** split: route trees only hold page segments; business logic and UI live in features.
- **`src/spa/`** – SPA entry points (`entry.web.tsx`, `entry.mobile.tsx`, `entry.desktop.tsx`, `entry.popup.tsx`) and React Router config (`router/`, with `desktopRouter.config.*`, `mobileRouter.config.tsx`, `popupRouter.config.tsx`). Keeps router config next to entries to avoid confusion with `src/routes/`.
- **`src/routes/` (roots)**\
Only page-segment files: `_layout/index.tsx`, `index.tsx` (or `page.tsx`), and dynamic segments like `[id]/index.tsx`. Keep these **thin**: they should only import from `@/features/*` and compose layout/page, with no business logic or heavy UI.
- **`src/features/`**\
Business components by **domain** (e.g. `Pages`, `PageEditor`, `Home`). Put layout chunks (sidebar, header, body), hooks, and domain-specific UI here. Each feature exposes an `index.ts` (or `index.tsx`) with clear exports.
When adding or changing SPA routes:
1. In `src/routes/`, add only the route segment files (layout + page) that delegate to features.
2. Implement layout and page content under `src/features/<Domain>/` and export from there.
3. In route files, use `import { X } from '@/features/<Domain>'` (or `import Y from '@/features/<Domain>/...'`). Do not add new `features/` folders inside `src/routes/`.
4.**Register the desktop route tree in both configs:**`src/spa/router/desktopRouter.config.tsx` and `src/spa/router/desktopRouter.config.desktop.tsx` must stay in sync (same paths and nesting). Updating only one can cause **blank screens** if the other build path expects the route. `desktopRouter.sync.test.tsx` guards this invariant — keep it passing.
See the **spa-routes** skill (`.agents/skills/spa-routes/SKILL.md`) for the full convention and file-division rules.
## Development
### Starting the Dev Environment
```bash
# SPA dev mode (frontend only, proxies API to localhost:3010)
bun run dev:spa
# Full-stack dev (Next.js + Vite SPA concurrently)
bun run dev
```
After `dev:spa` starts, the terminal prints a **Debug Proxy** URL:
Open this URL to develop locally against the production backend (app.lobehub.com). The proxy page loads your local Vite dev server's SPA into the online environment, enabling HMR with real server config.
### Git Workflow
- **Branch strategy**: `canary` is the development branch (cloud production); `main` is the release branch (periodically cherry-picks from canary)
- New branches should be created from `canary`; PRs should target `canary`
- Use rebase for git pull
-Git commit messages should prefix with gitmoji
-Git branch name format: `feat/feature-name`
- Use `.github/PULL_REQUEST_TEMPLATE.md` for PR descriptions
- **Protection of local changes**: Never use `git restore`, `git checkout --`, `git reset --hard`, or any other command or workflow that can forcibly overwrite, discard, or silently replace user-owned uncommitted changes. Before any revert or restoration affecting existing files, inspect the working tree carefully and obtain explicit user confirmation.
- Use rebase for `git pull`
-Commit messages: prefix with gitmoji
-Branch format: `<type>/<feature-name>`
### Package Management
- Use`pnpm`as the primary package manager
- Use`bun` to run npm scripts
- Use`bunx`to run executable npm packages
-`pnpm`for dependency management
-`bun` to run npm scripts
-`bunx`for executable npm packages
### Code Style Guidelines
#### TypeScript
- Prefer interfaces over types for object shapes
### Testing Strategy
### Testing
```bash
# Web tests
bunx vitest run --silent='passed-only''[file-path-pattern]'
# Run specific test (NEVER run `bun run test` - takes ~10 minutes)
bunx vitest run --silent='passed-only''[file-path]'
# Package tests (e.g., database)
cd packages/[package-name]&& bunx vitest run --silent='passed-only''[file-path-pattern]'
# Database package
cd packages/database&& bunx vitest run --silent='passed-only''[file]'
```
**Important Notes**:
-Wrap file paths in single quotes to avoid shell expansion
- Never run `bun run test` - this runs all tests and takes \~10 minutes
### Type Checking
- Use `bun run type-check` to check for type errors
- Prefer `vi.spyOn` over `vi.mock`
- Tests must pass type check: `bun run type-check`
-After 2 failed fix attempts, stop and ask for help
### i18n
-**Keys**: Add to `src/locales/default/namespace.ts`
-**Dev**: Translate `locales/zh-CN/namespace.json` locale file only for preview
- DON'T run`pnpm i18n`, let CI auto handle it
-Add keys to a namespace file under `src/locales/default/` (e.g. `agent.ts`, `auth.ts`)
-For dev preview: translate `locales/zh-CN/` and `locales/en-US/`
-`pnpm i18n` is slow; run it manually when locale keys need updating (e.g. before opening a PR).
## SPA Routes and Features
### Code Review
- **`src/routes/`** holds only page segments (`_layout/index.tsx`, `index.tsx`, `[id]/index.tsx`). Keep route files **thin** — import from `@/features/*` and compose, no business logic.
- **`src/features/`** holds business components by **domain** (e.g. `Pages`, `PageEditor`, `Home`). Layout pieces, hooks, and domain UI go here.
- **Desktop router parity:** When changing the main SPA route tree, update **both**`src/spa/router/desktopRouter.config.tsx` (dynamic imports) and `src/spa/router/desktopRouter.config.desktop.tsx` (sync imports) so paths and nesting match. Changing only one can leave routes unregistered and cause **blank screens**.
- See the **spa-routes** skill (`.agents/skills/spa-routes/SKILL.md`) for the full convention and file-division rules.
## Skills (Auto-loaded)
All AI development skills are available in `.agents/skills/` directory and auto-loaded by Claude Code when relevant.
**IMPORTANT**: When reviewing PRs or code diffs, ALWAYS read `.agents/skills/code-review/SKILL.md` first.
Before reviewing a PR / diff / branch change, read the **review-checklist** skill (`.agents/skills/review-checklist/SKILL.md`) — it lists the recurring mistakes specific to this codebase.
- **misc**: clear stale topic when switching agents from a topic route.
<br/>
<details>
<summary><kbd>Improvements and Fixes</kbd></summary>
#### What's fixed
- **misc**: clear stale topic when switching agents from a topic route, closes [#14231](https://github.com/lobehub/lobe-chat/issues/14231) ([deeb97a](https://github.com/lobehub/lobe-chat/commit/deeb97a))
Guidelines for using Claude Code in this LobeHub repository.
## Tech Stack
- Next.js 16 + React 19 + TypeScript
- SPA inside Next.js with `react-router-dom`
-`@lobehub/ui`, antd for components; antd-style for CSS-in-JS — **prefer `createStaticStyles` with `cssVar.*`** (zero-runtime); only fall back to `createStyles` + `token` when styles genuinely need runtime computation. See `.cursor/docs/createStaticStyles_migration_guide.md`.
- react-i18next for i18n; zustand for state management
- SWR for data fetching; TRPC for type-safe backend
SPA-related code is grouped under `src/spa/` (entries + router) and `src/routes/` (page segments). We use a **roots vs features** split: route trees only hold page segments; business logic and UI live in features.
- **`src/spa/`** – SPA entry points (`entry.web.tsx`, `entry.mobile.tsx`, `entry.desktop.tsx`) and React Router config (`router/`). Keeps router config next to entries to avoid confusion with `src/routes/`.
- **`src/routes/` (roots)**\
Only page-segment files: `_layout/index.tsx`, `index.tsx` (or `page.tsx`), and dynamic segments like `[id]/index.tsx`. Keep these **thin**: they should only import from `@/features/*` and compose layout/page, with no business logic or heavy UI.
- **`src/features/`**\
Business components by **domain** (e.g. `Pages`, `PageEditor`, `Home`). Put layout chunks (sidebar, header, body), hooks, and domain-specific UI here. Each feature exposes an `index.ts` (or `index.tsx`) with clear exports.
When adding or changing SPA routes:
1. In `src/routes/`, add only the route segment files (layout + page) that delegate to features.
2. Implement layout and page content under `src/features/<Domain>/` and export from there.
3. In route files, use `import { X } from '@/features/<Domain>'` (or `import Y from '@/features/<Domain>/...'`). Do not add new `features/` folders inside `src/routes/`.
4.**Register the desktop route tree in both configs:**`src/spa/router/desktopRouter.config.tsx` and `src/spa/router/desktopRouter.config.desktop.tsx` must stay in sync (same paths and nesting). Updating only one can cause **blank screens** if the other build path expects the route.
See the **spa-routes** skill (`.agents/skills/spa-routes/SKILL.md`) for the full convention and file-division rules.
## Development
### Starting the Dev Environment
```bash
# SPA dev mode (frontend only, proxies API to localhost:3010)
bun run dev:spa
# Full-stack dev (Next.js + Vite SPA concurrently)
bun run dev
```
After `dev:spa` starts, the terminal prints a **Debug Proxy** URL:
Open this URL to develop locally against the production backend (app.lobehub.com). The proxy page loads your local Vite dev server's SPA into the online environment, enabling HMR with real server config.
### Git Workflow
- **Branch strategy**: `canary` is the development branch (cloud production); `main` is the release branch (periodically cherry-picks from canary)
- New branches should be created from `canary`; PRs should target `canary`
- Use rebase for `git pull`
- Commit messages: prefix with gitmoji
- Branch format: `<type>/<feature-name>`
### Package Management
-`pnpm` for dependency management
-`bun` to run npm scripts
-`bunx` for executable npm packages
### Testing
```bash
# Run specific test (NEVER run `bun run test` - takes ~10 minutes)
bunx vitest run --silent='passed-only''[file-path]'
# Database package
cd packages/database && bunx vitest run --silent='passed-only''[file]'
```
- Prefer `vi.spyOn` over `vi.mock`
- Tests must pass type check: `bun run type-check`
- After 2 failed fix attempts, stop and ask for help
### i18n
- Add keys to `src/locales/default/namespace.ts`
- For dev preview: translate `locales/zh-CN/` and `locales/en-US/`
- Don't run `pnpm i18n` - CI handles it
## Skills (Auto-loaded by Claude)
Claude Code automatically loads relevant skills from `.agents/skills/`.
title: 'Plugin System: Extend Your Agents with Community Skills'
description: LobeHub now supports a plugin ecosystem that lets Agents access real-time information, interact with external services, and handle specialized tasks without leaving the conversation.
description: >-
LobeHub now supports a plugin ecosystem that lets Agents access real-time
information, interact with external services, and handle specialized tasks
title: 'Visual Recognition: Chat With Images, Not Just Text'
description: LobeHub now supports multimodal models including GPT-4 Vision, Google Gemini Pro Vision, and GLM-4 Vision. Upload or drag images into conversations and your Agent will understand and respond to visual content.
description: >-
LobeHub now supports multimodal models including GPT-4 Vision, Google Gemini
Pro Vision, and GLM-4 Vision. Upload or drag images into conversations and
your Agent will understand and respond to visual content.
title: 'Voice Conversations: Talk Naturally With Your Agents'
description: LobeHub now supports Text-to-Speech (TTS) and Speech-to-Text (STT), enabling natural voice interactions. Speak with your Agents and hear responses in clear, personalized voices.
description: >-
LobeHub now supports Text-to-Speech (TTS) and Speech-to-Text (STT), enabling
natural voice interactions. Speak with your Agents and hear responses in
title: 'Text-to-Image: Create Visuals Directly in Chat'
description: LobeHub now supports text-to-image generation. Invoke DALL-E 3, MidJourney, or Pollinations directly during conversations to turn your ideas into images without leaving the chat.
description: >-
LobeHub now supports text-to-image generation. Invoke DALL-E 3, MidJourney, or
Pollinations directly during conversations to turn your ideas into images
title: "50+ New Models and 10+ Providers Added to the Ecosystem"
description: LobeHub expands its AI ecosystem with 50+ new models and 10+ providers, making it easier to access diverse AI capabilities without changing your workflow.
title: 50+ New Models and 10+ Providers Added to the Ecosystem
description: >-
LobeHub expands its AI ecosystem with 50+ new models and 10+ providers, making
it easier to access diverse AI capabilities without changing your workflow.
title: "Customizable Hotkeys, Data Export, and Provider Expansion"
description: LobeHub adds customizable hotkeys, data export functionality, and expands provider support to make daily workflows smoother and more portable.
title: 'Customizable Hotkeys, Data Export, and Provider Expansion'
description: >-
LobeHub adds customizable hotkeys, data export functionality, and expands
provider support to make daily workflows smoother and more portable.
title: "Prompt Variables and Claude 4 Reasoning Model Support"
description: LobeHub introduces prompt variables for reusable templates and adds full support for Claude 4 reasoning models with web search integration.
title: Prompt Variables and Claude 4 Reasoning Model Support
description: >-
LobeHub introduces prompt variables for reusable templates and adds full
support for Claude 4 reasoning models with web search integration.
title: "Gemini Image Generation and Non-Streaming Mode Support \U0001F3A8"
description: >-
Gemini 2.5 Flash Image generation, non-streaming response mode, and expanded model coverage give you more flexibility in how you generate and receive content.
Gemini 2.5 Flash Image generation, non-streaming response mode, and expanded
model coverage give you more flexibility in how you generate and receive
title: "MCP Cloud Endpoints and Model Library Expansion \U0001F50C"
description: >-
Connect to managed MCP tools from the marketplace without self-hosting, while new providers and knowledge base pages improve daily workflows.
Connect to managed MCP tools from the marketplace without self-hosting, while
new providers and knowledge base pages improve daily workflows.
tags:
- MCP
- LobeHub
Some files were not shown because too many files have changed in this diff
Show More
Reference in New Issue
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.