Skip to content

✨ feat(server,task): batch run subtasks in dependency order#14418

Merged
arvinxx merged 2 commits into
canaryfrom
feat/task-batch-run
May 4, 2026
Merged

✨ feat(server,task): batch run subtasks in dependency order#14418
arvinxx merged 2 commits into
canaryfrom
feat/task-batch-run

Conversation

@arvinxx

@arvinxx arvinxx commented May 4, 2026

Copy link
Copy Markdown
Member

Summary

  • Adds a Run all button next to the subtasks + icon. Clicking it opens a confirm modal that previews subtasks grouped into dependency layers (Layer 1 starts immediately, Layer N waits on N-1, cycles surfaced as warnings) and kicks off the first layer on confirm.
  • Server-side TaskGraphService computes the layered plan via Kahn topo sort + cycle detection. Two new TRPC procedures expose it: task.previewSubtaskLayers (read) and task.runReadySubtasks (kicks off layer 1).
  • Subsequent layers fire automatically as upstream tasks complete β€” no client-side polling, no batch-run state.

The hidden bug this also fixes

task.updateStatus({ status: 'completed' }) already had unlock logic that called getUnlockedTasks and flipped each unlocked dependent to running in the DB β€” but it never invoked the runner, so those tasks ended up as phantom-running rows with no topic in flight.

This PR routes all three completion paths through TaskRunnerService.cascadeOnCompletion, which actually creates a topic and enqueues the agent run for every unlocked dependent:

  1. task.updateStatus TRPC route (user manually completes)
  2. BriefService.resolve (user approves a result brief)
  3. TaskLifecycleService judge auto-pass (review passes automatically)

If a dependent has no assignee or otherwise can't start, the cascade marks it paused with the error message instead of leaving it in a phantom state.

Behavior change to call out: before this PR, completing a task with downstream dependents would silently leave them stuck. After this PR they actually run. Existing dependency relationships in production data will start cascading on the next completion.

Test plan

  • bunx vitest run src/server/services/taskGraph β€” 11 unit tests for layer planning (linear / diamond / cycles / mixed status)
  • bunx vitest run src/server/routers/lambda/__tests__/integration/task.integration.test.ts β€” 5 new integration tests cover preview layering, cycle reporting, layer-1 kickoff, noop case, and cascade-on-complete
  • bunx vitest run src/server/services/brief/index.test.ts β€” asserts brief approval triggers cascade
  • bun run type-check clean
  • Manual: open task detail β†’ click Run all β†’ confirm modal shows layered preview β†’ run β†’ verify layer 1 tasks transition to running, layer 2 stays backlog until predecessors complete

πŸ€– Generated with Claude Code

@vercel

vercel Bot commented May 4, 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 May 4, 2026 11:35am

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:XL This PR changes 500-999 lines, ignoring generated files. feature:api API endpoint and backend issues labels May 4, 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.

πŸ’‘ Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 9581c8e43f

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 πŸ‘.

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

Comment thread src/server/services/taskGraph/index.ts Outdated
Comment thread src/server/services/taskGraph/index.ts Outdated
@codecov

codecov Bot commented May 4, 2026

Copy link
Copy Markdown

Codecov Report

❌ Patch coverage is 85.96491% with 48 lines in your changes missing coverage. Please review.
βœ… Project coverage is 68.72%. Comparing base (317fdce) to head (00813b3).
⚠️ Report is 7 commits behind head on canary.

Additional details and impacted files
@@            Coverage Diff             @@
##           canary   #14418      +/-   ##
==========================================
+ Coverage   68.64%   68.72%   +0.08%     
==========================================
  Files        2494     2496       +2     
  Lines      213260   213951     +691     
  Branches    21505    26077    +4572     
==========================================
+ Hits       146384   147042     +658     
- Misses      66732    66765      +33     
  Partials      144      144              
Flag Coverage Ξ”
app 62.90% <85.96%> (+0.14%) ⬆️
database 92.37% <ΓΈ> (ΓΈ)
packages/agent-runtime 79.94% <ΓΈ> (ΓΈ)
packages/builtin-tool-lobe-agent 83.41% <ΓΈ> (ΓΈ)
packages/context-engine 83.88% <ΓΈ> (ΓΈ)
packages/conversation-flow 92.43% <ΓΈ> (ΓΈ)
packages/file-loaders 87.60% <ΓΈ> (ΓΈ)
packages/memory-user-memory 74.74% <ΓΈ> (ΓΈ)
packages/model-bank 99.94% <ΓΈ> (ΓΈ)
packages/model-runtime 83.82% <ΓΈ> (ΓΈ)
packages/prompts 69.57% <ΓΈ> (ΓΈ)
packages/python-interpreter 92.90% <ΓΈ> (ΓΈ)
packages/ssrf-safe-fetch 0.00% <ΓΈ> (ΓΈ)
packages/types 5.05% <ΓΈ> (-0.01%) ⬇️
packages/utils 88.02% <ΓΈ> (ΓΈ)
packages/web-crawler 88.29% <ΓΈ> (-0.13%) ⬇️

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

Components Coverage Ξ”
Store 66.75% <16.66%> (-0.01%) ⬇️
Services 53.80% <100.00%> (+0.01%) ⬆️
Server 69.93% <89.64%> (+0.27%) ⬆️
Libs 53.36% <ΓΈ> (ΓΈ)
Utils 79.95% <ΓΈ> (ΓΈ)
πŸš€ New features to boost your workflow:
  • ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
  • πŸ“¦ JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

Adds a "Run all" entry on the subtasks panel that kicks off the first
dependency layer; subsequent layers fire automatically as upstream tasks
complete. Layer planning (Kahn topo sort + cycle detection) lives in a
new TaskGraphService and runs server-side via two TRPC procedures.

Also fixes a pre-existing bug where `task.updateStatus(completed)` was
flipping unlocked dependents to `running` without ever invoking the
runner β€” leaving them in a phantom running state with no topic in
flight. Cascade now goes through TaskRunnerService.cascadeOnCompletion
from all three completion paths (TRPC updateStatus, brief approval,
judge auto-pass), so dependency chains advance end-to-end on their own.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
@arvinxx arvinxx force-pushed the feat/task-batch-run branch from 9581c8e to 948ad1c Compare May 4, 2026 11:20
…reams

The graph used to drop any dependency edge whose upstream wasn't in the
runnable set. That silently freed two correctness-breaking cases:

- A backlog subtask that depends on a *running / scheduled* sibling
  landed in layer 1 and got kicked off before its blocker finished.
- A descendant that depends on a task *outside the current subtree*
  (allowed by the schema) lost its blocker entirely and ran prematurely.

Edges are now classified per dependency: terminal-OK upstreams drop the
edge; in-batch runnable upstreams keep their in-degree contribution; any
other status β€” in-flight, runnable but out of scope, or unknown β€” marks
the dependent as `blockedExternally` and excludes it from the layered
plan. External blockage propagates transitively through in-batch edges
so we never run a downstream of a blocked task either. `planForParent`
fetches statuses for cross-scope upstreams so the classifier has real
data to decide on.

The UI surfaces the new bucket via `RunSubtasksPreview` and keeps the
modal open (with the run button disabled) when a plan has nothing to
start but does have blocked tasks worth explaining.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
@arvinxx arvinxx merged commit 11e6619 into canary May 4, 2026
33 of 34 checks passed
@arvinxx arvinxx deleted the feat/task-batch-run branch May 4, 2026 11:44
Innei added a commit that referenced this pull request May 9, 2026
# πŸš€ LobeHub Release (20260509)

**Release Date:** May 9, 2026  
**Since v2.1.56:** 236 merged PRs Β· 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)** β€” 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** β€” 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** β€” BM25 search and `docs_*` read for
inline document grounding; agent documents usable as VFS. (#14494,
#14222)
- **Inline agent cards in chat** β€” `lobeAgents` markdown tag renders
agent profile cards inline; clickable card after `createAgent`. (#14495,
#14493)
- **Heterogeneous agent runtime** β€” 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** β€” Messager, Line, DM pair policy, and
messenger DB tables; Telegram API path restored. (#14442, #14207,
#14211, #14496, #14519)
- **Visual analysis tool** β€” New visual understanding tool, with trigger
tracking and flattened schema. (#14378, #14399, #14550)
- **DeepSeek V4 Pro as OSS default** β€” OSS deployments ship with
DeepSeek V4 Pro by default; DeepSeek Anthropic runtime supported.
(#14555, #14312)

---

## πŸ—οΈ Core Agent & Architecture

### Agent Task System

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

### Agent Signal pipeline

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

### Heterogeneous agent runtime

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

### Knowledge & inline docs

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

### Architecture

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

---

## πŸ“± Platforms & Integrations

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

---

## πŸ€– Models & Providers

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

---

## πŸ–₯️ User Experience

### Onboarding

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

### Home & navigation

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

### Conversation & chat

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

### Skills, agents, devtools

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

### Desktop & CLI

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

---

## πŸ”§ Tooling

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

---

## πŸ”’ 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 ~9Γ— on large dirty trees.
(#14338)

---

## πŸ‘₯ Contributors

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

@hezhijie0327 Β· @sxjeru Β· @yueyinqiu Β· @octo-patch Β· @hardy-one Β·
@Coooolfan Β· @CanYuanA Β· @BillionClaw Β· @arvinxx Β· @tjx666 Β· @Innei Β·
@neko Β· @AmAzing129 Β· @rdmclin2 Β· @lijian Β· @sudongyuer Β· @rivertwilight
Β· @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:api API endpoint and backend issues size:XL This PR changes 500-999 lines, ignoring generated files.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant