fix: pass chat_id to internal task calls for consistent function context (#20585)

Ensure chat_id is reliably passed to function pipelines/manifolds during internal task invocations (web search query generation, RAG query generation, image prompt generation).

This allows stateful functions to maintain per-chat state without fragmentation, as they will now receive a consistent chat_id for all chat-scoped invocations including internal tasks.

Backend changes:
- Pass chat_id in generate_queries call for web search
- Pass chat_id in generate_queries call for RAG/retrieval
- Pass chat_id in generate_image_prompt call

Frontend changes:
- Add optional chat_id parameter to generateQueries API function
- Add optional chat_id parameter to generateAutoCompletion API function

Fixes #20563

backend/open_webui/utils/middleware.py

@@ -1255,6 +1255,7 @@ async def chat_web_search_handler(
                 "messages": messages,
                 "prompt": user_message,
                 "type": "web_search",
+                "chat_id": extra_params.get("__chat_id__"),
             },
             user,
         )
@@ -1585,6 +1586,7 @@ async def chat_image_generation_handler(
                     {
                         "model": form_data["model"],
                         "messages": form_data["messages"],
+                        "chat_id": metadata.get("chat_id"),
                     },
                     user,
                 )
@@ -1691,6 +1693,7 @@ async def chat_completion_files_handler(
                         "model": body["model"],
                         "messages": body["messages"],
                         "type": "retrieval",
+                        "chat_id": body.get("metadata", {}).get("chat_id"),
                     },
                     user,
                 )

src/lib/apis/index.ts

@@ -864,7 +864,8 @@ export const generateQueries = async (
 	model: string,
 	messages: object[],
 	prompt: string,
-	type: string = 'web_search'
+	type: string = 'web_search',
+	chat_id?: string
 ) => {
 	let error = null;
 
@@ -879,7 +880,8 @@ export const generateQueries = async (
 			model: model,
 			messages: messages,
 			prompt: prompt,
-			type: type
+			type: type,
+			...(chat_id && { chat_id: chat_id })
 		})
 	})
 		.then(async (res) => {
@@ -933,7 +935,8 @@ export const generateAutoCompletion = async (
 	model: string,
 	prompt: string,
 	messages?: object[],
-	type: string = 'search query'
+	type: string = 'search query',
+	chat_id?: string
 ) => {
 	const controller = new AbortController();
 	let error = null;
@@ -951,7 +954,8 @@ export const generateAutoCompletion = async (
 			prompt: prompt,
 			...(messages && { messages: messages }),
 			type: type,
-			stream: false
+			stream: false,
+			...(chat_id && { chat_id: chat_id })
 		})
 	})
 		.then(async (res) => {
@@ -1675,7 +1679,7 @@ export interface ModelMeta {
 	profile_image_url?: string;
 }
 
-export interface ModelParams {}
+export interface ModelParams { }
 
 export type GlobalModelConfig = ModelConfig[];