Skip to content

🐛 fix(agent-runtime): scope pending-approval check to current assistant turn#14182

Merged
Innei merged 2 commits into
canaryfrom
fix/agent-runtime-stale-pending-hijack
Apr 26, 2026
Merged

🐛 fix(agent-runtime): scope pending-approval check to current assistant turn#14182
Innei merged 2 commits into
canaryfrom
fix/agent-runtime-stale-pending-hijack

Conversation

@Innei

@Innei Innei commented Apr 25, 2026

Copy link
Copy Markdown
Member

Summary

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 in GeneralChatAgent.runner, and parks the loop in waiting_for_human forever — so after a tool call succeeds, the next LLM call is never scheduled and the conversation appears frozen.

  • Add getCurrentTurnPendingToolMessages helper that resolves the current assistant turn (most recent assistant with tool_calls) and only returns pending tool messages whose parentId matches that assistant.
  • Use the helper in case 'tool_result' and case 'tools_batch_result'. Stale pending rows from earlier turns are now ignored, so the loop continues to the next call_llm as intended.
  • extractAbortInfo (abort path) is intentionally left unchanged — it's a different correctness contract and out of scope for this fix.

Test plan

  • bunx vitest run packages/agent-runtime/src/agents/__tests__/GeneralChatAgent.test.ts (64 / 64 passing)
  • Updated existing should return request_human_approve when there are pending tools fixtures (both phases) to mirror the real persisted shape — assistant carries tool_calls, tool message carries parentId. Without these, the new scope guard would treat them as stale.
  • New regression test: should ignore stale pending tool messages from a previous assistant turn — constructs a previous abandoned turn's pending tool plus a current turn's successful tool result, asserts the runner returns call_llm, not request_human_approve.

Repro context

Was hit while developing on feat/agent-marketplace-picker: after lobe-web-onboarding/updateDocument succeeded, the loop never issued the follow-up LLM call. Server logs (added temporary tracing during diagnosis) showed tool_result -> request_human_approve (pending=1) with the pending row's id pointing at a tool message from a prior turn.

@vercel

vercel Bot commented Apr 25, 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 26, 2026 8:08am

Request Review

@dosubot dosubot Bot added the size:M This PR changes 30-99 lines, ignoring generated files. label Apr 25, 2026

@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.

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

@codecov

codecov Bot commented Apr 25, 2026

Copy link
Copy Markdown

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 67.85%. Comparing base (939f20e) to head (f368cf0).
⚠️ Report is 2 commits behind head on canary.

Additional details and impacted files
@@           Coverage Diff            @@
##           canary   #14182    +/-   ##
========================================
  Coverage   67.85%   67.85%            
========================================
  Files        2229     2229            
  Lines      191473   191486    +13     
  Branches    22989    23774   +785     
========================================
+ Hits       129919   129934    +15     
+ Misses      61425    61423     -2     
  Partials      129      129            
Flag Coverage Δ
app 61.10% <ø> (+<0.01%) ⬆️
database 92.22% <ø> (ø)
packages/agent-runtime 79.93% <100.00%> (+0.11%) ⬆️
packages/context-engine 83.25% <ø> (ø)
packages/conversation-flow 92.40% <ø> (ø)
packages/file-loaders 87.02% <ø> (ø)
packages/memory-user-memory 74.74% <ø> (ø)
packages/model-bank 99.89% <ø> (ø)
packages/model-runtime 84.28% <ø> (ø)
packages/prompts 70.14% <ø> (ø)
packages/python-interpreter 92.90% <ø> (ø)
packages/ssrf-safe-fetch 0.00% <ø> (ø)
packages/utils 88.41% <ø> (ø)
packages/web-crawler 88.66% <ø> (ø)

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

Components Coverage Δ
Store 67.21% <ø> (ø)
Services 53.36% <ø> (ø)
Server 67.60% <ø> (+<0.01%) ⬆️
Libs 53.30% <ø> (ø)
Utils 80.04% <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.

@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: 33765fb1a1

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".

let currentAssistantId: string | undefined;
for (let i = state.messages.length - 1; i >= 0; i--) {
const m = state.messages[i] as any;
if (m.role === 'assistant' && m.tool_calls?.length > 0) {

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

P1 Badge Handle tools messages when finding current pending turn

getCurrentTurnPendingToolMessages only treats assistants with m.tool_calls as the current turn, but both runtimes frequently keep assistant calls in tools on state.messages (client updates via src/store/chat/agents/createAgentExecutors.ts:518-523, and server batch refresh replaces messages from parse(...) at src/server/modules/AgentRuntime/RuntimeExecutors.ts:2202-2203, where parser logic keys off processedMessage.tools in packages/conversation-flow/src/parse.ts:98-103). In those paths currentAssistantId stays undefined, pending tool rows from the active turn are dropped, and tool_result/tools_batch_result can incorrectly continue to call_llm while approvals are still pending (especially mixed safe+approval tool flows), effectively bypassing the intended wait-for-human gate.

Useful? React with 👍 / 👎.

Copy link
Copy Markdown
Member Author

Choose a reason for hiding this comment

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

Fixed in f368cf0fcd: getCurrentTurnPendingToolMessages now treats assistant turns with either tool_calls or persisted tools as active tool-calling turns, and I added regression coverage for both tool_result and tools_batch_result so pending approvals in the tools shape still return request_human_approve. Verified with bunx vitest run src/agents/__tests__/GeneralChatAgent.test.ts from packages/agent-runtime.

Innei added 2 commits April 26, 2026 15:54
…nt 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`).
@Innei Innei force-pushed the fix/agent-runtime-stale-pending-hijack branch from 33765fb to f368cf0 Compare April 26, 2026 08:01
@Innei Innei merged commit d12e050 into canary Apr 26, 2026
39 checks passed
@Innei Innei deleted the fix/agent-runtime-stale-pending-hijack branch April 26, 2026 09:05
@arvinxx arvinxx mentioned this pull request Apr 27, 2026
arvinxx added a commit that referenced this pull request Apr 27, 2026
# 🚀 LobeHub v2.1.53 (20260427)

**Release Date:** April 27, 2026
**Since v2.1.52:** 194 merged PRs · 17 contributors

> Introduce Heterogeneous Agent — Claude Code and Codex run as
first-class desktop runtimes, paired with a new Agent Signal package,
sharper desktop UX, and a wave of flagship model additions.

---

## ✨ Highlights

- **Introduce Heterogeneous Agent** — Claude Code and Codex run as
first-class desktop agents: subagent rendering, partial-message
streaming, multi-turn resume, terminal error surfacing, rich tool
inspectors, and runtime polish. (#14162, #13754, #14067, #14001, #13970,
#13942)
- **Screen capture & Quick Chat tray** — New desktop screen capture
overlay (macOS permission-gated) with Quick Chat tray and upload
pipeline improvements; chat input auto-focuses on overlay mount.
(#13818, #14097, #14105)
- **Desktop topic & tab UX** — Dedicated topic popup window with
cross-window sync, Cmd+W/Cmd+T tab shortcuts, TabBar polish, recent
working directories expanded to 20, and human approval notifications.
(#13957, #13983, #13972, #14036, #14092)
- **Git workflow built-in** — One-click pull/push from the branch chip,
ahead/behind badge, and submodule/worktree repo detection. (#14041,
#13980, #13978)
- **Agent Signal package** — New `@lobechat/agent-signal` runtime for
dynamic memory feedback signals, with OTel metrics and self-iteration in
Lab. (#14157, #14170, #14159, #14169, #14187)
- **New models** — Claude Opus 4.7 with `xhigh` effort tier, GPT-5.5,
DeepSeek V4 Flash/Pro with reasoning slider, Kimi K2.6, MiMo-V2.5/Pro,
gpt-image-2, Qwen3.6 Flash/Plus, and Pixverse-c1. (#13903, #14147,
#14114, #14004, #14089, #14039, #13923)
- **New providers** — OpenCode Zen, OpenCode Go, and Azure OpenAI Router
runtime. (#13943, #14064, #13823)
- **Mobile settings overhaul** — Full settings menu and responsive
profile layout for mobile. (#14019)

---

## 🏗️ Heterogeneous Agent

- Claude Code runtime, working-directory awareness, and sidebar polish.
(#13970)
- CC subagent rendering with persistent streamed text; parallel-tool
orphan fix. (#14001, #13968, #14024)
- Per-step usage persisted to each step assistant message. (#13964)
- Per-phase workflow expand defaults; full-expand toggle with
three-level expansion. (#14171, #13906)
- Hetero-mode actions bar; tool inspector polish. (#13963, #14034,
#14030)
- Codex desktop integration with rich tool rendering and devtools
preview. (#14067, #14100)
- Codex terminal error surfacing and CLI output tracing. (#14166)
- Tighten `isCanUseVision` default and add aggregator fallback. (#14172)
- Persist `ccSessionId` in topic metadata for CC multi-turn resume.
(#13902)
- CC account card, topic filter, and integration polish. (#13955,
#13942, #13950)
- Token-level deltas streamed via `--include-partial-messages`. (#13929)

---

## 🧠 Agent Signal & Self-Iteration

- New `@lobechat/agent-signal` package with dynamic feedback signals.
(#14157)
- AgentSignalRuntime wired through agent-tracing and observability-otel
metrics. (#14170, #14159)
- Self-iteration feature flag added to Lab; front-side flag check.
(#14169, #14186)
- Signal policy for receiving memory feedback dynamically. (#14187)

---

## 💬 Conversation

- Queue follow-up sends during running CC turns. (#14179)
- Persist per-topic chat scroll position; pin user message + fold long
messages. (#14191, #14056)
- Inline resend when editing last user message. (#14080)
- Disable first-block markdown streaming to prevent flicker. (#14193,
#13904)
- Prevent Markdown stream replay when vlist remounts streaming items.
(#14086)
- Stop repinning after manual scroll; unify scroll-to-user + spacer
hooks. (#14099, #14132)

---

## 📱 Platforms & Integrations

### Desktop / Electron

- Screen capture overlay, Quick Chat tray, and upload pipeline
improvements. (#13818)
- macOS permission gate for screen capture; auto-focus chat panel input.
(#14097, #14105)
- Dedicated topic popup window with cross-window sync. (#13957)
- TabBar polish: `+` button for new topic, dark theme blend, close icon
by default. (#13972, #14203, #13973)
- Recent working directories expanded from 5 to 20; submodule/worktree
repo detection. (#14036, #13978)
- Cmd+W / Cmd+T tab shortcuts and global shortcut consolidation.
(#13983, #13880)
- Linux icon configuration; human approval desktop notifications.
(#14042, #14092)

### Git Workflow

- One-click pull/push from branch chip; ahead/behind badge with
refactored GitCtr. (#14041, #13980)

### Mobile

- Full settings menu and responsive profile layout. (#14019)
- Agent route added to mobile router; mobile agent topic route
registered. (#14103, #14158)
- Session list skeleton row layout corrected. (#14040)

### Bot / Messaging

- DM strategy support; bot emoji and markdown render optimization.
(#14201, #14091, #14140)
- Slack webhook fix; bot platform setup guide reference. (#14052,
#14121)

---

## 🤖 Models & Providers

### New models

- **Claude Opus 4.7** with `xhigh` effort tier; strip temperature/top_p.
(#13903, #13909)
- **GPT-5.5**. (#14147)
- **DeepSeek V4** Flash/Pro cards with reasoning slider; cache-hit and
Pro discount pricing. (#14114, #14209, #14196, #14131)
- **Kimi K2.6** model with LobeHub-hosted card. (#14004, #14006)
- **MiMo-V2.5 / V2.5-Pro**. (#14089)
- **gpt-image-2**, **Qwen3.6 Flash/Plus**, **Pixverse-c1**. (#14039,
#13923)

### New providers

- **OpenCode Zen** and **OpenCode Go** with env-var support. (#13943,
#14064)
- **Azure OpenAI Router** runtime support. (#13823)
- Model alias mapping for image and video runtimes. (#13896)
- Seedance video models migrated to Dreamina. (#14144)

### Runtime reliability

- Sanitize invalid tool_call arguments to unbreak strict providers.
(#14033)
- Tolerate null `function.name` in streaming tool_call deltas. (#14139)
- Preserve Gemini 3 `thoughtSignature` in `call_tools_batch`
normalization. (#14032)
- Downgrade `image_url` parts when target model lacks vision. (#14029)
- Preserve Cloudflare provider error context. (#14136)
- Use `safety_identifier` for OpenAI Responses API. (#14148)
- Unwrap underlying PG error in `formatErrorEventData`. (#14038)

---

## 🖥️ User Experience

- **Onboarding** — Preset agent naming suggestions, structured hunk ops
for `updateDocument`, persona analytics snapshot, footer promotion
pipeline, wrap-up button. (#13931, #13989, #13930, #13853, #13934)
- **Document workflow** — Agent documents promoted as primary workspace
panel; history management and compare workflow; web-crawl docs
associated with agent documents. (#13924, #13725, #13893)
- **cmdk** — Agent identity surfaced on topic search results;
topic/message search scoped to current agent. (#14204, #13960)
- **Floating chat panel** and workspace improvements. (#13887)
- **Topic completion status** with dropdown action and filter. (#14005)

---

## 🔧 Tooling

- Redis-backed feature flag provider for runtime config. (#14098)
- Vite upgraded to 8.0.0 with Rolldown strict execution order. (#12720,
#14058)
- `@lobechat/model-bank` automated npm release with provenance. (#14015,
#14017, #14018)
- Skill activation fallback when `activateTools` cannot find identifier.
(#14010)
- Cron tool: timezone and existing jobs injected into system prompt;
clarified `lobe-gtd` and `lobe-cron` descriptions. (#14012, #14013)

---

## 🔒 Security & Reliability

- **Security:** uuid bumped to v14 (advisory). (#14083)
- **Security:** validate avatar URL and scope old-avatar deletion to
owner. (#13982)
- **Security:** clear OIDC sessions on better-auth signout; return 401
(not 500) for expired OIDC JWT. (#13916, #14014)
- **Reliability:** scope pending-approval check to current assistant
turn. (#14182)
- **Reliability:** sanitize heterogeneous-agent attachment cache
filenames. (#13937)
- **Reliability:** reduce subagent task status error noise. (#14026)

---

## 👥 Contributors

Huge thanks to **17 contributors** who shipped **194 merged PRs** this
week.

@hardy · @shaun0927 · @hezhijie0327 · @sxjeru · @arvinxx · @Innei ·
@tjx666 · @lijian · @neko · @rdmclin2 · @AmAzing129 · @sudongyuer ·
@CanisMinor · @rivertwilight

Plus @lobehubbot and renovate[bot] for maintenance.

---

**Full Changelog**:
v2.1.52...v2.1.53
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

size:M This PR changes 30-99 lines, ignoring generated files.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant