🐛 fix(task-runner): fall back to inbox agent when task has no assignee by arvinxx · Pull Request #14671 · lobehub/lobehub

arvinxx · 2026-05-11T10:58:54Z

💻 Change Type

🐛 fix

🔀 Description of Change

TaskRunnerService.run previously threw BAD_REQUEST when a task lacked assigneeAgentId, which broke any task created without --agent. Now it resolves the built-in inbox agent for the user and persists it on the task before executing.

If the inbox agent cannot be resolved (shouldn't happen in practice), we surface an INTERNAL_SERVER_ERROR instead of the previous misleading "use --agent" message.

🧪 How to Test

Tested locally

Run a task that was created without an assignee — it should now execute under the inbox agent instead of failing with BAD_REQUEST.

Previously threw a BAD_REQUEST when a task lacked assigneeAgentId, which broke runs for tasks created without --agent. Now resolves the built-in inbox agent and persists it on the task before executing.

vercel · 2026-05-11T10:58:57Z

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

Project	Deployment	Actions	Updated (UTC)
lobehub	Ready	Preview, Comment	May 11, 2026 11:14am

sourcery-ai

We've reviewed this pull request using the Sourcery rules engine

chatgpt-codex-connector

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 11573d68a7

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".

codecov · 2026-05-11T11:07:38Z

Codecov Report

❌ Patch coverage is 16.66667% with 10 lines in your changes missing coverage. Please review.
✅ Project coverage is 66.18%. Comparing base (831c258) to head (11573d6).
⚠️ Report is 6 commits behind head on canary.

Additional details and impacted files

@@            Coverage Diff             @@
##           canary   #14671      +/-   ##
==========================================
- Coverage   66.18%   66.18%   -0.01%     
==========================================
  Files        2897     2897              
  Lines      253870   253878       +8     
  Branches    24788    25643     +855     
==========================================
  Hits       168019   168019              
- Misses      85699    85707       +8     
  Partials      152      152

Flag	Coverage Δ
app	`60.56% <16.66%> (-0.01%)`	⬇️
database	`91.82% <ø> (ø)`
packages/agent-runtime	`80.48% <ø> (ø)`
packages/builtin-tool-lobe-agent	`83.41% <ø> (ø)`
packages/context-engine	`84.00% <ø> (ø)`
packages/conversation-flow	`92.43% <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	`83.67% <ø> (ø)`
packages/prompts	`70.39% <ø> (ø)`
packages/python-interpreter	`92.90% <ø> (ø)`
packages/ssrf-safe-fetch	`0.00% <ø> (ø)`
packages/types	`5.44% <ø> (ø)`
packages/utils	`88.02% <ø> (ø)`
packages/web-crawler	`88.16% <ø> (ø)`

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

Components	Coverage Δ
Store	`66.84% <ø> (ø)`
Services	`54.16% <ø> (ø)`
Server	`71.60% <16.66%> (-0.01%)`	⬇️
Libs	`55.22% <ø> (ø)`
Utils	`82.51% <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.

`TaskRunnerService.runTask` previously threw `BAD_REQUEST` for any task without `assigneeAgentId`, which broke runs created without `--agent`. Resolve and persist the user's built-in inbox agent instead, surfacing an `INTERNAL_SERVER_ERROR` only if that resolution itself fails. Picked from #14671 (closes once landed). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

…me (#14670) * ✨ feat(task): snapshot agent model into task.config at create time Pin the assignee agent's current model/provider into task.config when a task is created so later changes to the agent's default model don't silently affect already-created tasks. On first run, backfill the snapshot for tasks created before this change. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * 🐛 fix(task-runner): fall back to inbox agent when task has no assignee `TaskRunnerService.runTask` previously threw `BAD_REQUEST` for any task without `assigneeAgentId`, which broke runs created without `--agent`. Resolve and persist the user's built-in inbox agent instead, surfacing an `INTERNAL_SERVER_ERROR` only if that resolution itself fails. Picked from #14671 (closes once landed). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * ♻️ refactor(task): collapse router orchestration into TaskService Move multi-step task verbs out of the TRPC router into `TaskService`: `createTask`, `cancelTopic`, `deleteTopic`, `runReview`, `updateStatus`, `previewSubtaskLayers`, `runReadySubtasks`. The router keeps only input validation + error wrapping; the tool runtime now shares the same `createTask` path (was duplicating the model snapshot + parent resolution). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * 🚨 ci: fix tsgo errors from TaskService extraction `runReadySubtasks` router was rebuilding the `data` payload via a conditional spread, which forced TS to infer a discriminated union that broke `result.data.skipped` access in the integration test. Pass the service result straight through so `skipped` stays a single optional field. Also cast the stubbed `taskService` in the tool runtime unit tests to bypass strict structural typing — same pattern the other dep stubs already use. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

…me (lobehub#14670) * ✨ feat(task): snapshot agent model into task.config at create time Pin the assignee agent's current model/provider into task.config when a task is created so later changes to the agent's default model don't silently affect already-created tasks. On first run, backfill the snapshot for tasks created before this change. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * 🐛 fix(task-runner): fall back to inbox agent when task has no assignee `TaskRunnerService.runTask` previously threw `BAD_REQUEST` for any task without `assigneeAgentId`, which broke runs created without `--agent`. Resolve and persist the user's built-in inbox agent instead, surfacing an `INTERNAL_SERVER_ERROR` only if that resolution itself fails. Picked from lobehub#14671 (closes once landed). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * ♻️ refactor(task): collapse router orchestration into TaskService Move multi-step task verbs out of the TRPC router into `TaskService`: `createTask`, `cancelTopic`, `deleteTopic`, `runReview`, `updateStatus`, `previewSubtaskLayers`, `runReadySubtasks`. The router keeps only input validation + error wrapping; the tool runtime now shares the same `createTask` path (was duplicating the model snapshot + parent resolution). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * 🚨 ci: fix tsgo errors from TaskService extraction `runReadySubtasks` router was rebuilding the `data` payload via a conditional spread, which forced TS to infer a discriminated union that broke `result.data.skipped` access in the integration test. Pass the service result straight through so `skipped` stays a single optional field. Also cast the stubbed `taskService` in the tool runtime unit tests to bypass strict structural typing — same pattern the other dep stubs already use. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

arvinxx · 2026-05-12T15:20:17Z

Superseded by #14670, which already picked this fix into canary (see its commit message: "Picked from #14671"). After rebasing onto canary the diff is empty, so closing.

…me (#14670) * ✨ feat(task): snapshot agent model into task.config at create time Pin the assignee agent's current model/provider into task.config when a task is created so later changes to the agent's default model don't silently affect already-created tasks. On first run, backfill the snapshot for tasks created before this change. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * 🐛 fix(task-runner): fall back to inbox agent when task has no assignee `TaskRunnerService.runTask` previously threw `BAD_REQUEST` for any task without `assigneeAgentId`, which broke runs created without `--agent`. Resolve and persist the user's built-in inbox agent instead, surfacing an `INTERNAL_SERVER_ERROR` only if that resolution itself fails. Picked from #14671 (closes once landed). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * ♻️ refactor(task): collapse router orchestration into TaskService Move multi-step task verbs out of the TRPC router into `TaskService`: `createTask`, `cancelTopic`, `deleteTopic`, `runReview`, `updateStatus`, `previewSubtaskLayers`, `runReadySubtasks`. The router keeps only input validation + error wrapping; the tool runtime now shares the same `createTask` path (was duplicating the model snapshot + parent resolution). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * 🚨 ci: fix tsgo errors from TaskService extraction `runReadySubtasks` router was rebuilding the `data` payload via a conditional spread, which forced TS to infer a discriminated union that broke `result.data.skipped` access in the integration test. Pass the service result straight through so `skipped` stays a single optional field. Also cast the stubbed `taskService` in the tool runtime unit tests to bypass strict structural typing — same pattern the other dep stubs already use. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

…me (lobehub#14670) * ✨ feat(task): snapshot agent model into task.config at create time Pin the assignee agent's current model/provider into task.config when a task is created so later changes to the agent's default model don't silently affect already-created tasks. On first run, backfill the snapshot for tasks created before this change. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * 🐛 fix(task-runner): fall back to inbox agent when task has no assignee `TaskRunnerService.runTask` previously threw `BAD_REQUEST` for any task without `assigneeAgentId`, which broke runs created without `--agent`. Resolve and persist the user's built-in inbox agent instead, surfacing an `INTERNAL_SERVER_ERROR` only if that resolution itself fails. Picked from lobehub#14671 (closes once landed). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * ♻️ refactor(task): collapse router orchestration into TaskService Move multi-step task verbs out of the TRPC router into `TaskService`: `createTask`, `cancelTopic`, `deleteTopic`, `runReview`, `updateStatus`, `previewSubtaskLayers`, `runReadySubtasks`. The router keeps only input validation + error wrapping; the tool runtime now shares the same `createTask` path (was duplicating the model snapshot + parent resolution). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * 🚨 ci: fix tsgo errors from TaskService extraction `runReadySubtasks` router was rebuilding the `data` payload via a conditional spread, which forced TS to infer a discriminated union that broke `result.data.skipped` access in the integration test. Pass the service result straight through so `skipped` stays a single optional field. Also cast the stubbed `taskService` in the tool runtime unit tests to bypass strict structural typing — same pattern the other dep stubs already use. 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(task-runner): fall back to inbox agent when task has no assignee

11573d6

Previously threw a BAD_REQUEST when a task lacked assigneeAgentId, which broke runs for tasks created without --agent. Now resolves the built-in inbox agent and persists it on the task before executing.

dosubot Bot added the size:S This PR changes 10-29 lines, ignoring generated files. label May 11, 2026

sourcery-ai Bot reviewed May 11, 2026

View reviewed changes

chatgpt-codex-connector Bot reviewed May 11, 2026

View reviewed changes

Comment thread src/server/services/taskRunner/index.ts

vercel Bot deployed to Preview May 11, 2026 11:14 View deployment

arvinxx closed this May 12, 2026

arvinxx deleted the fix/task-runner-inbox-fallback branch May 12, 2026 15:21

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

🐛 fix(task-runner): fall back to inbox agent when task has no assignee#14671

🐛 fix(task-runner): fall back to inbox agent when task has no assignee#14671
arvinxx wants to merge 1 commit into
canaryfrom
fix/task-runner-inbox-fallback

arvinxx commented May 11, 2026

Uh oh!

vercel Bot commented May 11, 2026 •

edited

Loading

Uh oh!

sourcery-ai Bot left a comment

Uh oh!

chatgpt-codex-connector Bot left a comment

Uh oh!

Uh oh!

codecov Bot commented May 11, 2026 •

edited

Loading

Uh oh!

arvinxx commented May 12, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

Uh oh!

Conversation

arvinxx commented May 11, 2026

💻 Change Type

🔀 Description of Change

🧪 How to Test

Uh oh!

vercel Bot commented May 11, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

sourcery-ai Bot left a comment

Choose a reason for hiding this comment

Uh oh!

chatgpt-codex-connector Bot left a comment

Choose a reason for hiding this comment

💡 Codex Review

Uh oh!

Uh oh!

codecov Bot commented May 11, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Codecov Report

Uh oh!

arvinxx commented May 12, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

vercel Bot commented May 11, 2026 •

edited

Loading

codecov Bot commented May 11, 2026 •

edited

Loading