feat: forward client User-Agent to model backends via {{USER_AGENT}} placeholder (#26333)

Adds a {{USER_AGENT}} custom-header placeholder that relays the inbound
client's User-Agent to upstream model backends, so providers see the real
client instead of Open WebUI's internal aiohttp UA. This makes upstream
usage/cost attribution and backend telemetry possible, and is opt-in
per-connection (no global flag): admins add {{USER_AGENT}} to a connection's
custom headers in Admin > Settings > Connections.

The placeholder is sourced from the live inbound request (with a metadata
fallback for detached RAG/tool calls), so it resolves on every prompt-sending
path, not just chat completions:

- OpenAI completions, Responses API, and proxy — all route through
  get_headers_and_cookies, which now passes the request into get_custom_headers.
- Anthropic Messages API (/api/v1/messages) — already covered, it delegates
  to the chat completion handler.
- Ollama (/api/chat, /v1/completions, /v1/chat/completions, /v1/messages,
  /v1/responses) — previously had no custom-header support at all; send_request
  now applies per-connection custom headers (with templating) for every
  Ollama prompt endpoint.

Custom headers are applied after the built-in user-info headers so explicit
admin-configured headers take precedence. The other existing placeholders
({{CHAT_ID}}, {{USER_ID}}, ...) now also work on the newly covered paths.

Frontend: the connection editor's Headers field is now shown for Ollama
connections too (previously gated to non-Ollama), so the placeholder can be
configured there.

Ref: open-webui/open-webui#26159

backend/open_webui/main.py

@@ -1168,6 +1168,7 @@ async def chat_completion(
 
         metadata = {
             'user_id': user.id,
+            'user_agent': request.headers.get('user-agent', '') or '',
             'chat_id': form_data.pop('chat_id', None) or '',
             'user_message': user_message,
             'user_message_id': user_message.get('id') if user_message else None,

backend/open_webui/routers/ollama.py

@@ -38,7 +38,7 @@ from open_webui.models.models import Models
 from open_webui.models.users import UserModel
 from open_webui.utils.access_control import check_model_access
 from open_webui.utils.auth import get_admin_user, get_verified_user
-from open_webui.utils.headers import include_user_info_headers
+from open_webui.utils.headers import get_custom_headers, include_user_info_headers
 from open_webui.utils.misc import calculate_sha256
 from open_webui.utils.payload import (
     apply_model_params_to_body_ollama,
@@ -99,6 +99,8 @@ async def send_request(
     stream: bool = False,
     content_type: str | None = None,
     metadata: dict | None = None,
+    api_config: dict | None = None,
+    request: Request | None = None,
 ):
     r = None
     streaming = False
@@ -115,6 +117,10 @@ async def send_request(
             if metadata and metadata.get('chat_id'):
                 headers[FORWARD_SESSION_INFO_HEADER_CHAT_ID] = metadata.get('chat_id')
 
+        # Custom per-connection headers last so admin-set headers take precedence.
+        if api_config and api_config.get('headers'):
+            headers.update(get_custom_headers(api_config['headers'], user, metadata, request=request))
+
         r = await session.request(
             method,
             url,
@@ -1100,6 +1106,8 @@ async def generate_chat_completion(
         stream=form_data.stream,
         content_type='application/x-ndjson',
         metadata=metadata,
+        api_config=api_config,
+        request=request,
     )
 
 
@@ -1185,6 +1193,8 @@ async def generate_openai_completion(
         user=user,
         stream=payload.get('stream', False),
         metadata=metadata,
+        api_config=api_config,
+        request=request,
     )
 
 
@@ -1242,6 +1252,8 @@ async def generate_openai_chat_completion(
         user=user,
         stream=payload.get('stream', False),
         metadata=metadata,
+        api_config=api_config,
+        request=request,
     )
 
 
@@ -1294,6 +1306,8 @@ async def generate_anthropic_messages(
         user=user,
         stream=payload.get('stream', False),
         content_type='text/event-stream' if payload.get('stream', False) else None,
+        api_config=api_config,
+        request=request,
     )
 
 
@@ -1352,6 +1366,8 @@ async def generate_responses(
         user=user,
         stream=payload.get('stream', False),
         content_type='text/event-stream' if payload.get('stream', False) else None,
+        api_config=api_config,
+        request=request,
     )
 
 

backend/open_webui/routers/openai.py

@@ -209,7 +209,7 @@ async def get_headers_and_cookies(
         headers['Authorization'] = f'Bearer {token}'
 
     if config.get('headers') and isinstance(config.get('headers'), dict):
-        custom_headers = get_custom_headers(config.get('headers'), user, metadata)
+        custom_headers = get_custom_headers(config.get('headers'), user, metadata, request=request)
         headers.update(custom_headers)
 
     return headers, cookies

backend/open_webui/utils/headers.py

@@ -59,12 +59,22 @@ def include_user_info_headers(headers: dict, user: Optional[Any] = None) -> dict
     }
 
 
-def get_custom_headers(custom_headers: dict, user=None, metadata: dict = None) -> dict:
+def get_custom_headers(custom_headers: dict, user=None, metadata: dict = None, request=None) -> dict:
     if not custom_headers or not isinstance(custom_headers, dict):
         return {}
 
     metadata = metadata or {}
 
+    # UA from the live request; fall back to metadata for detached RAG/tool calls.
+    user_agent = ''
+    if request is not None:
+        try:
+            user_agent = request.headers.get('user-agent', '') or ''
+        except Exception:
+            user_agent = ''
+    if not user_agent:
+        user_agent = metadata.get('user_agent', '') or ''
+
     # Extract user_message info for tree mapping
     user_message = metadata.get('user_message') or {}
     user_message_id = metadata.get('user_message_id', '') or (user_message.get('id', '') if user_message else '')
@@ -83,6 +93,7 @@ def get_custom_headers(custom_headers: dict, user=None, metadata: dict = None) -
         '{{USER_NAME}}': (user.name.strip() if user else '') or '',
         '{{USER_EMAIL}}': (user.email.strip() if user else '') or '',
         '{{USER_ROLE}}': (user.role if user else '') or '',
+        '{{USER_AGENT}}': user_agent,
     }
 
     parsed_headers = {}

src/lib/components/AddConnectionModal.svelte

@@ -436,7 +436,7 @@
 							</div>
 						</div>
 
-						{#if !ollama && !direct}
+						{#if !direct}
 							<div class="flex gap-2 mt-2">
 								<div class="flex flex-col w-full">
 									<label