Skip to content

♻️ refactor(task-brief): auto-synthesize topic briefs#14324

Merged
arvinxx merged 4 commits into
canaryfrom
feat/lobe-8333-auto-brief-synthesis
Apr 29, 2026
Merged

♻️ refactor(task-brief): auto-synthesize topic briefs#14324
arvinxx merged 4 commits into
canaryfrom
feat/lobe-8333-auto-brief-synthesis

Conversation

@arvinxx

@arvinxx arvinxx commented Apr 29, 2026

Copy link
Copy Markdown
Member

💻 Change Type

  • ✨ feat

🔗 Related Issue

LOBE-8333 — Brief 生成是非常不稳定
close LOBE-8255
close LOBE-8353

🔀 Description of Change

Replaces the agent-driven createBrief tool path on the non-review "done" branch with a programmatic synthesis in TaskLifecycleService.onTopicComplete. Three-layer split:

Layer Source
Whether to emit, type, priority Pure rules (shouldEmitTopicBrief)
artifacts (linked documents) DB query against task_documents (time-window from topic start)
title / summary (user-facing) Dedicated LLM call (chainGenerateBrief) — separate from handoff

Why a new LLM call instead of reusing handoff? Handoff is the agent's internal cheat sheet (terse, tool-aware, action-oriented). Brief is the user's delivery report (user-facing language, focuses on what was delivered). Same content in two voices — reusing the handoff schema would have produced briefs that read like internal traces. The brief schema is intentionally minimal ({ title, summary } only); type/priority/artifacts are determined programmatically and assembled at the briefModel.create call site.

Rollout is gated behind task.config.brief.mode === 'auto'. Default stays 'agent' (existing tool-driven path) — when the flag flips, BriefIdentifier is also unmounted in taskRunner so we don't double-emit. GrowthBook flag wiring is intentionally a follow-up.

Type tightening: briefs.artifacts was unknown end-to-end. Now BriefArtifacts = { documents?: { id, kind, title }[] } flows through the schema, model, store, and TaskDetailActivity. The legacy TRPC brief.create endpoint adapts string[]BriefArtifacts at the boundary so external clients are unaffected.

Files of interest:

  • packages/prompts/src/chains/generateBrief.ts — new chain
  • src/server/services/taskLifecycle/synthesize.ts — rules + artifacts collection
  • src/server/services/taskLifecycle/index.tssynthesizeTopicBrief private method, wired between review and post-tick transition

🧪 How to Test

  • Tested locally (33 unit tests passing across taskLifecycle/ + brief model)
  • Added/updated tests:
    • synthesize.test.ts — 13 tests covering decision rules + trivial-content heuristic
    • onTopicComplete.test.ts — 3 tests verifying auto triggers / agent doesn't / judge-terminated skips
  • Manual smoke test for the auto path requires a real task with config.brief.mode = 'auto' — leaving that for a follow-up grayscale run on internal accounts before flipping the default.

📝 Additional Information

Out of scope (follow-up PRs):

  • GrowthBook flag wiring (cloud repo)
  • createBrief tool manifest downgrade to type: 'insight' only
  • Frontend BriefItem document-link rendering (artifacts now arrive typed, but the UI render is a separate task)

Risks called out in the issue:

  • Extra LLM call per "delivery" topic adds latency; shouldEmitTopicBrief ensures non-delivery ticks don't pay
  • task_documents.createdAt time window is the artifact-attribution signal — needs validation under real workloads
  • Lost agent expressivity for custom decision actions on result briefs (mitigation: extend requestCheckpoint if it surfaces as a real need)

🤖 Generated with Claude Code

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>
@vercel

vercel Bot commented Apr 29, 2026

Copy link
Copy Markdown

The latest updates on your projects. Learn more about Vercel for GitHub.

Project Deployment Actions Updated (UTC)
lobehub Ready Ready Preview, Comment Apr 29, 2026 5:03pm

Request Review

@sourcery-ai sourcery-ai Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Sorry @arvinxx, you have reached your weekly rate limit of 500000 diff characters.

Please try again later or upgrade to continue using Sourcery

@dosubot dosubot Bot added size:L This PR changes 100-499 lines, ignoring generated files. feature:agent Assistant/Agent configuration and behavior labels Apr 29, 2026

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 2af8b5d55d

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

Comment thread src/server/services/taskRunner/index.ts Outdated
arvinxx and others added 2 commits April 30, 2026 00:31
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>
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>
@codecov

codecov Bot commented Apr 29, 2026

Copy link
Copy Markdown

Codecov Report

❌ Patch coverage is 40.72165% with 115 lines in your changes missing coverage. Please review.
✅ Project coverage is 68.84%. Comparing base (105321b) to head (094a147).
⚠️ Report is 1 commits behind head on canary.

Additional details and impacted files
@@            Coverage Diff             @@
##           canary   #14324      +/-   ##
==========================================
- Coverage   68.85%   68.84%   -0.01%     
==========================================
  Files        2366     2368       +2     
  Lines      207418   207609     +191     
  Branches    25081    21643    -3438     
==========================================
+ Hits       142819   142934     +115     
- Misses      64462    64538      +76     
  Partials      137      137              
Flag Coverage Δ
app 62.31% <31.74%> (-0.01%) ⬇️
database 92.29% <100.00%> (+0.01%) ⬆️
packages/agent-runtime 79.93% <ø> (ø)
packages/context-engine 83.87% <ø> (ø)
packages/conversation-flow 92.40% <ø> (ø)
packages/file-loaders 87.60% <ø> (ø)
packages/memory-user-memory 74.74% <ø> (ø)
packages/model-bank 99.94% <ø> (ø)
packages/model-runtime 83.70% <ø> (ø)
packages/prompts 67.98% <29.26%> (-0.65%) ⬇️
packages/python-interpreter 92.90% <ø> (ø)
packages/ssrf-safe-fetch 0.00% <ø> (ø)
packages/utils 87.84% <ø> (ø)
packages/web-crawler 88.41% <ø> (ø)

Flags with carried forward coverage won't be shown. Click here to find out more.

Components Coverage Δ
Store 66.44% <ø> (ø)
Services 53.73% <ø> (ø)
Server 69.12% <31.74%> (-0.02%) ⬇️
Libs 53.30% <ø> (ø)
Utils 79.95% <ø> (ø)
🚀 New features to boost your workflow:
  • ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
  • 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

@arvinxx arvinxx changed the title ✨ feat(task-lifecycle): auto-synthesize topic briefs ♻️ refactor(task-lifecycle): auto-synthesize topic briefs Apr 29, 2026
@arvinxx arvinxx changed the title ♻️ refactor(task-lifecycle): auto-synthesize topic briefs ♻️ refactor(task-brief): auto-synthesize topic briefs Apr 29, 2026
Flip the default from 'agent' to 'auto' so new tasks use the
programmatic synthesis path out of the box. 'agent' becomes an
explicit escape hatch for re-enabling the legacy createBrief tool
flow when something regresses.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
@arvinxx arvinxx merged commit 84df8a9 into canary Apr 29, 2026
31 of 32 checks passed
@arvinxx arvinxx deleted the feat/lobe-8333-auto-brief-synthesis branch April 29, 2026 16:58
@Innei Innei mentioned this pull request May 9, 2026
Innei added a commit that referenced this pull request May 9, 2026
# 🚀 LobeHub Release (20260509)

**Release Date:** May 9, 2026  
**Since v2.1.56:** 236 merged PRs · 19 contributors

> Agent Task System reaches general availability, the Agent Signal
pipeline runs nightly self-review with skill-aware policies, the
heterogeneous-agent runtime crosses replica boundaries, inline documents
become a first-class context source, and bot platforms expand across
Messager, Line, and Telegram.

---

## ✨ Highlights

- **Agent Task System (GA)** — End-to-end task execution platform:
templates, tracking, comment tools, parent reassignment, scheduled cron,
and dependency-ordered batch runs. (#14540, #14515, #14517, #14272,
#14246, #14418, #14403, #14488)
- **Agent Signal nightly self-review** — Wired self-review loop with
prompt + DB support, exponential-backoff retry on receipt listing,
skill-aware policy, and improved skill-intent detection. (#14543,
#14542, #14281, #14409, #14526, #14437)
- **Inline documents in KB tool** — BM25 search and `docs_*` read for
inline document grounding; agent documents usable as VFS. (#14494,
#14222)
- **Inline agent cards in chat** — `lobeAgents` markdown tag renders
agent profile cards inline; clickable card after `createAgent`. (#14495,
#14493)
- **Heterogeneous agent runtime** — Cloud hetero exec pipeline steps 3+4
land, persistence recovers across Vercel replicas, server-side
ingest/finish handler, and `lh hetero exec` CLI. (#14486, #14539,
#14444, #14431)
- **Bot platforms expand** — Messager, Line, DM pair policy, and
messenger DB tables; Telegram API path restored. (#14442, #14207,
#14211, #14496, #14519)
- **Visual analysis tool** — New visual understanding tool, with trigger
tracking and flattened schema. (#14378, #14399, #14550)
- **DeepSeek V4 Pro as OSS default** — OSS deployments ship with
DeepSeek V4 Pro by default; DeepSeek Anthropic runtime supported.
(#14555, #14312)

---

## 🏗️ Core Agent & Architecture

### Agent Task System

- **Task System GA** — End-to-end execution platform now available.
(#14540)
- **Templates, comments, reparenting** — Template tracking, comment
tools, and parent reassignment. (#14515, #14517, #14488)
- **Cron + dependency-ordered runs** — Scheduled status with cron editor
and dependency-ordered subtask batches. (#14246, #14418, #14272)
- **Inspector + chip UI + batch tasks** — Task Inspector/Render
registry, batch `createTasks`/`runTasks`, and chip-based agent-documents
inspector. (#14403, #14404)
- **Recommend templates regardless of brief count** — Recommendations no
longer suppressed when briefs are sparse. (#14508)
- **Scheduling resilience** — Manual run no longer eats next scheduled
tick; recurring tasks survive brief resolution. (#14304, #14348)
- **Brief synthesis** — Auto-synthesize topic briefs; brief actions
revamp; mute resolved-brief icon on home. (#14324, #14228, #14452)
- **Task list & detail polish** — Topic operation ID exposed; task
drawer Gateway reconnect. (#14282)

### Agent Signal pipeline

- **Nightly self-review wired** — Prompt + DB support for the
self-review loop. (#14543)
- **Self-review activities push to briefs** — Activities during nightly
self-reflection now create briefs. (#14437)
- **Skill management policy** — New policy for Skill management running
inside Agent Signal. (#14281)
- **Skill intent detection & routing** — Improved detection plus direct
intent handling when `hintIsSkill`. (#14409, #14526)
- **Document tool outcome rendering** — Decision view restores missing
document tool outcomes. (#14534)
- **Exponential backoff retry** — Listing signal receipts retries with
jittered backoff. (#14542)
- **Easier-to-use signals** — Structural simplification +
recent-activities surface for receipts. (#14290, #14326, #14407)

### Heterogeneous agent runtime

- **Cloud hetero exec pipeline (steps 3 + 4)** — Refactor lands the next
two stages of the cloud hetero agent execution pipeline. (#14486)
- **Persistence recovery on Vercel** — Hetero state recovered across
replica boundaries. (#14539)
- **Server-side ingest/finish + persistence** — `aiAgent.heteroIngest` /
`heteroFinish` handlers. (#14444)
- **`lh hetero exec` CLI** — Standalone heterogeneous agent runs from
CLI. (#14431)
- **Gateway round-trip loading** — `execAgentTask` keeps the input box
in loading state through the full round-trip. (#14503)
- **Provider SDK type routing** — Provider routing now respects SDK
type. (#14520)
- **DeepSeek reasoning preserved** — `reasoning_content` preserved in
OpenAI-compatible runtime for DeepSeek models. (#14546)

### Knowledge & inline docs

- **KB tool BM25 + docs read** — BM25 search and `docs_*` read
integrated for inline documents. (#14494)
- **Agent documents as VFS** — FS-compatible output for agent documents.
(#14222)
- **`lobeAgents` markdown tag** — Inline agent cards rendered from a
markdown tag. (#14495)
- **Clickable agent card after `createAgent`** — Mentions and
recommendations become clickable. (#14493)
- **ExplorerTree** — Generic tree component built on `@pierre/trees` for
reusable explorer surfaces. (#14094)
- **Local file mention snapshots** — Mentions can now snapshot local
files. (#14278)

### Architecture

- **Agent Hono routes** — New agent routes added on Hono. (#14535)
- **`/api/agent` migrated to Hono** — Remaining `/api/agent` routes
finish their migration. (#14478)
- **Agent marketplace merged into web-onboarding** — Reduces package
fragmentation. (#14514)
- **Producer pipeline extracted** — Shared package for the producer
pipeline. (#14425)
- **`agentDispatcher.selectRuntimeType`** — New runtime selection
abstraction. (#14428)
- **pnpm v11 migration** — Workspace consolidated. (#14316)
- **Browser-compatible frontmatter parser** — Replaces `gray-matter`.
(#14435)

---

## 📱 Platforms & Integrations

- **Messager support** — New messager package wired into the chat
surface. (#14442)
- **Messenger DB tables** — IM bot integration gains its persistence
layer. (#14496)
- **Line bot** — Initial Line support and downstream optimization.
(#14207, #14448)
- **DM pair policy** — Group/DM pair-based delivery. (#14211)
- **Telegram API restored** — Missing Telegram API path reconnected.
(#14519)
- **xAI Responses tools stabilized** — Plus unsupported parameter
handling. (#14462, #14445)
- **Volcengine websearch via ResponseAPI** — Built-in websearch for
Volcengine. (#14216)

---

## 🤖 Models & Providers

- **DeepSeek V4 Pro default for OSS** — OSS distribution defaults to
DeepSeek V4 Pro. (#14555)
- **DeepSeek Anthropic runtime** — Anthropic-shape runtime support for
DeepSeek. (#14312)
- **GPT-5.5 / GPT-5.5 Pro** — New OpenAI tier. (#14142)
- **Grok 4.20 / Grok 4.3 / LobeHub-hosted Grok 4.3** — (#14253, #14382,
#14446)
- **Gemma 4 + provider settings normalization** — (#13313)
- **gpt-image-2 + step-image-edit-2** — (#14253, #14329)
- **Model bank refresh + original-pricing display** — Batch model
updates and pricing surfaces. (#14070, #14391)
- **Hunyuan migrated to TokenHub for Hy3 Preview** — (#14108)
- **Reject lobehub model ids no longer in the bank** — (#14261)
- **Hide runtime-only aliases** — Runtime-only model aliases no longer
leak into the model picker. (#14552)

---

## 🖥️ User Experience

### Onboarding

- **Shared prefix steps** — Language and privacy extracted as shared
prefix steps. (#14538)
- **Identity intervention card simplified** — Plus tool result renders
cleanup. (#14505, #14506)
- **Welcome polish + web-onboarding tool UI** — (#14475)
- **Templates fetched from market API** — (#14286)
- **Virtual model id for default onboarding model** — (#14311)
- **Skip / mode-switch footer behind feature flag** — Footer guarded for
desktop and web initialization. (#14560)

### Home & navigation

- **Home recents performance** — Recents refresh periodically and inline
task status; brief and task-template fetch overhead trimmed. (#14518,
#14516)
- **Home refactor + skill-connect recommendations** — Restructured home
with skill-connect recommendation system. (#14266, #14214)
- **Tasks in agent sidebar** — Tasks moved from welcome card into the
sidebar list. (#14500)
- **Sidebar collapse persists** — Home sidebar collapse state stored.
(#14473)
- **Agent-specific topic grouping** — Plus improved empty state and
agent identity in topic search. (#14225)
- **MentionMenu scroll fix** — Mention menu no longer clips inside chat
input. (#14533)

### Conversation & chat

- **Follow-up chips fill input** — Clicking a follow-up chip now fills
the input instead of sending immediately. (#14536)
- **Quick-reply chips below assistant messages** — (#14350)
- **Inline single-tool assistant group + leading sentence promotion** —
(#14244)
- **Assistant-group rendering** — Per-segment content overrides flow
into MessageContent. (#14504)
- **Tool call timer fix** — Timer no longer resets when tool calls
collapse or expand. (#14513)
- **Streaming re-render reduction** — Reference stabilization and
self-subscribing components. (#14470)
- **Topic chat drawer feedback input** — (#14392)

### Skills, agents, devtools

- **Managed skill folders** — Agent view displays managed skill folders
and aligns delete confirmations. (#14553)
- **Review tab + bulk git diffs** — New Review tab with bulk diffs;
gating uses effective working directory. (#14334, #14512)
- **Devtools gallery rebuild** — Plus Review polish, queue-tray images.
(#14423)
- **Agent mock devtools** — Playback & fixture viewer. (#14436)

### Desktop & CLI

- **App tray visibility setting** — (#14463)
- **Notification settings in desktop** — (#14491)
- **Multimodal input across CLI / shared spawn / desktop** — (#14433)
- **CLI bot + userId guide** — (#14258)

---

## 🔧 Tooling

- **Visual analysis tool** — New visual understanding tool with
flattened schema. (#14378, #14550)
- **GitHub marketplace tool UI** — (#14420)
- **Drop "Local" prefix and `____builtin` suffix from tool names** —
(#14364, #14289)
- **Sanitize provider tool names** — Avoids invalid characters from
external providers. (#14510)
- **Generation moderation context** — Moderation context passed through
the generation pipeline. (#14541)
- **Visual analysis trigger tracking** — (#14399)
- **Claude thinking signature sanitization** — History signatures
sanitized when replaying Claude conversations. (#14499)
- **Responses input media sanitization** — Assistant media sanitized in
Responses input. (#14497)

---

## 🔒 Security & Reliability

- **Security:** Removed the `/webapi/proxy` route and dead URL-manifest
plugin code to shrink the SSRF surface. (#14549)
- **Security:** Sessions revoked after password reset. (#14424)
- **Reliability:** Added `prompt_cache_key` to OpenAI chat requests for
stable cache hits. (#14349)
- **Reliability:** `onFinish` now fires even when the browser tab is
backgrounded mid-SSE stream. (#14461)
- **Reliability:** Better-auth session refetch preserves user fields
rather than overwriting them. (#14531)
- **Reliability:** User-memory queries sanitize backticks; user-memory
errors now explicitly injected so failures stay visible. (#14524,
#14525)
- **Reliability:** Auth captcha retries handled; input loading unsticks
on `auth_failed` and recoverable `auth_expired`. (#14346, #14419)
- **Reliability:** Trace snapshot finalized on error path. (#14440)
- **Reliability:** Drop `switchTopic` race under rapid sidebar clicks.
(#14115)
- **Reliability:** PDF chunking logic fixed to prevent vectorization
failure. (#14327)
- **Performance:** Marketplace fork uses a batched API for parallel
installs. (#14537)
- **Performance:** Review tab open latency cut ~9× on large dirty trees.
(#14338)

---

## 👥 Contributors

Huge thanks to **18 contributors** who shipped **236 merged PRs** this
cycle.

@hezhijie0327 · @sxjeru · @yueyinqiu · @octo-patch · @hardy-one ·
@Coooolfan · @CanYuanA · @BillionClaw · @arvinxx · @tjx666 · @Innei ·
@neko · @AmAzing129 · @rdmclin2 · @lijian · @sudongyuer · @rivertwilight
· @cy948

Plus @lobehubbot for i18n and translation maintenance.

---

**Full Changelog**:
v2.1.56...release/weekly-20260509
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

feature:agent Assistant/Agent configuration and behavior size:L This PR changes 100-499 lines, ignoring generated files.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant