✨ feat: support client-side function tool execution in Response API by arvinxx · Pull Request #13414 · lobehub/lobehub

arvinxx · 2026-03-30T14:54:24Z

Summary

Implement client-side function tool execution for the Response API (LOBE-6543):

Function tool injection: type: 'function' tools are converted to UniformTool and injected into the LLM with source='client' in the toolSourceMap
Pause mechanism: When the LLM calls a client function tool, RuntimeExecutors.call_tool / call_tools_batch detects source='client' and interrupts the agent loop instead of executing
Resume flow: Second request with function_call_output input items writes tool results to the topic and resumes the agent via previous_response_id
Streaming events: Adds response.function_call_arguments.done event; emits response.incomplete when paused for client tool
Tool name format: Client function tools use their original name (e.g., get_weather) instead of internal identifier/apiName format
Response ID simplification: Uses topicId directly as response ID (includes 🔧 refactor: simplify response ID to use topicId directly #13410)

Flow

1st request → LLM calls client function → stream emits function_call events → response.incomplete
2nd request with function_call_output → tool results injected → LLM generates final response → response.completed

Fixes LOBE-6543

Test plan

Verify function tool definitions are passed to LLM and callable
Verify streaming emits correct function_call event sequence (added → delta → done → item.done)
Verify response.incomplete status when agent pauses for client tool
Verify function_call_output resume flow produces final response
Verify mixed hosted + client tools work correctly in batch
Run openresponses compliance tests (tool-calling, tool-calling-streaming)

🤖 Generated with Claude Code

vercel · 2026-03-30T14:54:35Z

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

Project	Deployment	Actions	Updated (UTC)
lobehub	Error		Mar 31, 2026 7:05am

sourcery-ai

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

lobehubbot · 2026-03-30T14:55:50Z

@nekomeowww - This PR implements client-side function tool execution in the Response API, touching backend server services and agent runtime. Please take a look.

codecov · 2026-03-30T14:59:08Z

Codecov Report

❌ Patch coverage is 19.23077% with 105 lines in your changes missing coverage. Please review.
✅ Project coverage is 66.91%. Comparing base (6402656) to head (4f21f9c).
⚠️ Report is 14 commits behind head on canary.

Additional details and impacted files

@@            Coverage Diff             @@
##           canary   #13414      +/-   ##
==========================================
- Coverage   66.95%   66.91%   -0.05%     
==========================================
  Files        1930     1930              
  Lines      156582   156708     +126     
  Branches    15137    18774    +3637     
==========================================
+ Hits       104837   104856      +19     
- Misses      51625    51732     +107     
  Partials      120      120

Flag	Coverage Δ
app	`58.68% <19.23%> (-0.05%)`	⬇️
database	`96.66% <ø> (ø)`
packages/agent-runtime	`89.11% <ø> (ø)`
packages/context-engine	`86.51% <ø> (ø)`
packages/conversation-flow	`92.36% <ø> (ø)`
packages/file-loaders	`87.02% <ø> (ø)`
packages/memory-user-memory	`66.68% <ø> (ø)`
packages/model-bank	`99.85% <ø> (ø)`
packages/model-runtime	`84.48% <ø> (ø)`
packages/prompts	`67.76% <ø> (ø)`
packages/python-interpreter	`92.90% <ø> (ø)`
packages/ssrf-safe-fetch	`0.00% <ø> (ø)`
packages/utils	`90.41% <ø> (ø)`
packages/web-crawler	`88.82% <ø> (ø)`

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

Components	Coverage Δ
Store	`67.08% <ø> (ø)`
Services	`49.21% <ø> (ø)`
Server	`67.27% <19.23%> (-0.17%)`	⬇️
Libs	`51.03% <ø> (ø)`
Utils	`89.08% <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

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: fbbd9715a5

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".

src/server/services/aiAgent/index.ts

packages/openapi/src/services/responses.service.ts

Implement LOBE-6543: when the Response API receives tools with type='function', inject them into the LLM and pause execution when the LLM calls them, allowing the client to provide results via function_call_output input items. Key changes: - Add 'client' to ToolSource type - Inject function tools into LLM via execAgent with source='client' in sourceMap - Pause agent loop (interrupt) when LLM calls a client function tool - Handle function_call_output resume flow via previous_response_id - Add response.function_call_arguments.done streaming event - Emit response.incomplete when interrupted for client tool execution - Use original function name for client tools instead of identifier/apiName - Simplify response ID to use topicId directly (includes LOBE-6536 fix) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

MessageModel is not exported from @lobechat/database package. Replace direct DB writes with prompt-based approach for tool result resume. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

…o ToolSource CLIENT_FN_IDENTIFIER `__fn__` caused ambiguous splits with PLUGIN_SCHEMA_SEPARATOR `____`, breaking tool name resolution. Renamed to `lobe-client-fn` and added `client` to the ToolSource union in @lobechat/types to match context-engine's definition. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

lobehubbot · 2026-03-31T08:24:51Z

❤️ Great PR @arvinxx ❤️

The growth of project is inseparable from user feedback and contribution, thanks for your contribution! If you are interesting with the lobehub developer community, please join our discord and then dm @arvinxx or @canisminor1990. They will invite you to our private developer channel. We are talking about the lobe-chat development or sharing ai newsletter around the world.

@chriszf

# 🚀 release: 20260407 This release includes **148 commits**. Key updates are below. - **Response API tool execution is more capable and reliable** — Added hosted builtin tools + client-side function tools and improved tool-call streaming/completion behavior. [#13406](#13406) [#13414](#13414) [#13506](#13506) [#13555](#13555) - **Input and composition UX upgraded** — Added AI input auto-completion and multiple chat-input stability fixes. [#13458](#13458) [#13551](#13551) [#13481](#13481) - **Model/provider compatibility improved** — Better Gemini/Google tool schema handling and additional model updates. [#13429](#13429) [#13465](#13465) [#13613](#13613) - **Desktop and CLI reliability improved** — Gateway WebSocket support and desktop runtime upgrades. [#13608](#13608) [#13550](#13550) [#13557](#13557) - **Security hardening continued** — Fixed auth and sanitization risks and upgraded vulnerable dependencies. [#13535](#13535) [#13529](#13529) [#13479](#13479) ### Models & Providers - Added/updated support for `glm-5v-turbo`, GLM-5.1 updates, and qwen3.5-omni series. [#13487](#13487) [#13405](#13405) [#13422](#13422) - Added additional ImageGen providers/models (Wanxiang 2.7 and Keling from Qwen). [#13478](#13478) - Improved Gemini/Google tool schema and compatibility handling across runtime paths. [#13429](#13429) [#13465](#13465) [#13613](#13613) ### Response API & Runtime - Added hosted builtin tools in Response API and client-side function tool execution support. [#13406](#13406) [#13414](#13414) - Improved stream tool-call argument handling and `response.completed` output correctness. [#13506](#13506) [#13555](#13555) - Improved runtime error/context handling for intervention and provider edge cases. [#13420](#13420) [#13607](#13607) ### Desktop App - Bumped desktop dependencies and runtime integrations (`agent-browser`, `electron`). [#13550](#13550) [#13557](#13557) - Simplified desktop release channel setup by removing nightly release flow. [#13480](#13480) ### CLI - Added OpenClaw migration command. [#13566](#13566) - Added local device binding support for `lh agent run`. [#13277](#13277) - Added WebSocket gateway support and reconnect reliability improvements. [#13608](#13608) [#13418](#13418) ### Security - Removed risky `apiKey` fallback behavior in webapi auth path to prevent bypass risk. [#13535](#13535) - Sanitized HTML artifact rendering and iframe sandboxing to reduce XSS-to-RCE risk. [#13529](#13529) - Upgraded nodemailer to v8 to address SMTP command injection advisory. [#13479](#13479) ### Bug Fixes - Fixed image generation model default switch issues. [#13587](#13587) - Fixed subtopic re-fork message scope behavior and agent panel reset edge cases. [#13606](#13606) [#13556](#13556) - Fixed chat-input freeze on paste and mention plugin behavior. [#13551](#13551) [#13415](#13415) - Fixed auth/social sign-in and settings UX edge cases. [#13368](#13368) [#13392](#13392) [#13338](#13338) ### Credits Huge thanks to these contributors: @chriszf @hardy-one @Innei @lijian @neko @OctopusNote @rdmclin2 @rivertwilight @RylanCai @suyua9 @sxjeru @Tsuki @wangyk @WindSpiritSR @yizhuo @YuTengjing @hezhijie0327 @arvinxx

sourcery-ai bot reviewed Mar 30, 2026

View reviewed changes

chatgpt-codex-connector bot reviewed Mar 30, 2026

View reviewed changes

src/server/services/aiAgent/index.ts Show resolved Hide resolved

packages/openapi/src/services/responses.service.ts Show resolved Hide resolved

arvinxx force-pushed the feat/client-function-tool-execution branch from fbbd971 to fd22e09 Compare March 30, 2026 15:29

🐛 fix: remove MessageModel import, use prompt-based resume flow

5a006b7

MessageModel is not exported from @lobechat/database package. Replace direct DB writes with prompt-based approach for tool result resume. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

vercel bot had a problem deploying to Preview March 30, 2026 15:57 Failure

vercel bot had a problem deploying to Preview March 31, 2026 07:05 Failure

arvinxx merged commit 674c849 into canary Mar 31, 2026
32 of 34 checks passed

arvinxx deleted the feat/client-function-tool-execution branch March 31, 2026 08:24

nekomeowww mentioned this pull request Apr 7, 2026

🚀 release: 20260407 #13626

Merged

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

✨ feat: support client-side function tool execution in Response API#13414

✨ feat: support client-side function tool execution in Response API#13414
arvinxx merged 3 commits intocanaryfrom
feat/client-function-tool-execution

arvinxx commented Mar 30, 2026

Uh oh!

vercel bot commented Mar 30, 2026 •

edited

Loading

Uh oh!

sourcery-ai bot left a comment

Uh oh!

lobehubbot commented Mar 30, 2026

Uh oh!

codecov bot commented Mar 30, 2026 •

edited

Loading

Uh oh!

chatgpt-codex-connector bot left a comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

lobehubbot commented Mar 31, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Uh oh!

Conversation

arvinxx commented Mar 30, 2026

Summary

Flow

Test plan

Uh oh!

vercel bot commented Mar 30, 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!

lobehubbot commented Mar 30, 2026

Uh oh!

codecov bot commented Mar 30, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Codecov Report

Uh oh!

chatgpt-codex-connector bot left a comment

Choose a reason for hiding this comment

💡 Codex Review

Uh oh!

Uh oh!

Uh oh!

Uh oh!

lobehubbot commented Mar 31, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

vercel bot commented Mar 30, 2026 •

edited

Loading

codecov bot commented Mar 30, 2026 •

edited

Loading