## 📋 Pull Request Information **Original PR:** https://github.com/open-webui/open-webui/pull/23515 **Author:** [@PedroFCM](https://github.com/PedroFCM) **Created:** 4/8/2026 **Status:** ❌ Closed **Base:** `dev` ← **Head:** `fix/native-tool-calling-api-loop` --- ### 📝 Commits (1) - [`9f97b21`](https://github.com/open-webui/open-webui/commit/9f97b21e96bd8b61c8d090b21756a0d8ca8c9f9e) fix: native function calling for REST API consumers ### 📊 Changes **1 file changed** (+59 additions, -6 deletions) <details> <summary>View changed files</summary> 📝 `backend/open_webui/main.py` (+59 -6) </details> ### 📄 Description  Two fixes for native function calling, especially for REST API consumers that bypass the frontend WebSocket session: 1. Pass through the `function_calling` value as-is instead of only checking for `'native'` and falling back to `'default'`. This respects values set via `DEFAULT_MODEL_PARAMS` or per-model params. 2. Add server-side tool-calling loop for API calls (no `session_id`). The native tool execution loop is driven by the frontend via WebSocket. REST API calls never enter that loop, so `tool_calls` are returned raw and tools are never executed. This adds a loop that executes tools and re-invokes the LLM until `finish_reason != 'tool_calls'` or `CHAT_RESPONSE_MAX_TOOL_CALL_RETRIES` is reached. Ref: #9435 # Pull Request Checklist - [x] **Target branch:** `dev` - [x] **Description:** See above and changelog below - [x] **Changelog:** See below - [x] **Documentation:** N/A — no new env vars or user-facing config; uses existing `CHAT_RESPONSE_MAX_TOOL_CALL_RETRIES` - [x] **Dependencies:** No new dependencies - [x] **Testing:** Manually tested with AWS Bedrock models (Claude) via REST API with native tool calling. Verified: tool loop completes, LLM produces final response, frontend WebSocket flow unaffected, requests without tools unchanged. - [x] **Agentic AI Code:** Human-written and manually tested in production - [x] **Code review:** Self-reviewed - [x] **Design & Architecture:** No new settings; uses existing `CHAT_RESPONSE_MAX_TOOL_CALL_RETRIES` - [x] **Git Hygiene:** Single atomic commit rebased on `dev` - [x] **Title Prefix:** `fix:` # Changelog Entry ### Description - Fix native function calling for REST API consumers (`/api/chat/completions`) that don't use a WebSocket session ### Fixed - `function_calling` parameter now passes through the configured value instead of only recognizing `'native'` and falling back to `'default'` - REST API calls with native function calling now execute tools server-side and re-invoke the LLM with tool results, matching the behavior of the frontend WebSocket flow ### Breaking Changes - None. Behavioral change is scoped to REST API requests with `function_calling: native` and tools — these previously returned raw `tool_calls` without execution. --- ### Additional Information - Related discussion: #9435 ("The model does nothing with the result of a native tool call") — reported by 30+ users since Feb 2025 - The server-side loop only activates when: no `session_id` (REST API), `function_calling == 'native'`, and tools are present in metadata - Loop is bounded by existing `CHAT_RESPONSE_MAX_TOOL_CALL_RETRIES` setting - Streaming is temporarily disabled during the tool loop, then restored for the final LLM call ### Contributor License Agreement  - [x] By submitting this pull request, I confirm that I have read and fully agree to the [Contributor License Agreement (CLA)](https://github.com/open-webui/open-webui/blob/main/CONTRIBUTOR_LICENSE_AGREEMENT), and I am providing my contributions under its terms. > [!NOTE] > Deleting the CLA section will lead to immediate closure of your PR and it will not be merged in. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

GiteaMirror commented

2026-05-06 12:12:49 -05:00

Owner

📋 Pull Request Information

Original PR: https://github.com/open-webui/open-webui/pull/23515
Author: @PedroFCM
Created: 4/8/2026
Status: ❌ Closed

Base: dev ← Head: fix/native-tool-calling-api-loop

📝 Commits (1)

9f97b21 fix: native function calling for REST API consumers

📊 Changes

1 file changed (+59 additions, -6 deletions)

View changed files

📝 backend/open_webui/main.py (+59 -6)

📄 Description

Two fixes for native function calling, especially for REST API consumers that bypass the frontend WebSocket session:

Pass through the function_calling value as-is instead of only checking for 'native' and falling back to 'default'. This respects values set via DEFAULT_MODEL_PARAMS or per-model params.
Add server-side tool-calling loop for API calls (no session_id). The native tool execution loop is driven by the frontend via WebSocket. REST API calls never enter that loop, so tool_calls are returned raw and tools are never executed. This adds a loop that executes tools and re-invokes the LLM until finish_reason != 'tool_calls' or CHAT_RESPONSE_MAX_TOOL_CALL_RETRIES is reached.

Ref: #9435

Pull Request Checklist

Target branch: dev
Description: See above and changelog below
Changelog: See below
Documentation: N/A — no new env vars or user-facing config; uses existing CHAT_RESPONSE_MAX_TOOL_CALL_RETRIES
Dependencies: No new dependencies
Testing: Manually tested with AWS Bedrock models (Claude) via REST API with native tool calling. Verified: tool loop completes, LLM produces final response, frontend WebSocket flow unaffected, requests without tools unchanged.
Agentic AI Code: Human-written and manually tested in production
Code review: Self-reviewed
Design & Architecture: No new settings; uses existing CHAT_RESPONSE_MAX_TOOL_CALL_RETRIES
Git Hygiene: Single atomic commit rebased on dev
Title Prefix: fix:

Changelog Entry

Description

Fix native function calling for REST API consumers (/api/chat/completions) that don't use a WebSocket session

Fixed

function_calling parameter now passes through the configured value instead of only recognizing 'native' and falling back to 'default'
REST API calls with native function calling now execute tools server-side and re-invoke the LLM with tool results, matching the behavior of the frontend WebSocket flow

Breaking Changes

None. Behavioral change is scoped to REST API requests with function_calling: native and tools — these previously returned raw tool_calls without execution.

Additional Information

Related discussion: #9435 ("The model does nothing with the result of a native tool call") — reported by 30+ users since Feb 2025
The server-side loop only activates when: no session_id (REST API), function_calling == 'native', and tools are present in metadata
Loop is bounded by existing CHAT_RESPONSE_MAX_TOOL_CALL_RETRIES setting
Streaming is temporarily disabled during the tool loop, then restored for the final LLM call

Contributor License Agreement

By submitting this pull request, I confirm that I have read and fully agree to the Contributor License Agreement (CLA), and I am providing my contributions under its terms.

Note

Deleting the CLA section will lead to immediate closure of your PR and it will not be merged in.

_{🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.}

GiteaMirror added the pull-request label 2026-05-06 12:12:49 -05:00

GiteaMirror closed this issue

2026-05-06 12:12:54 -05:00

[PR #23515] [CLOSED] fix: native function calling for REST API consumers #66086