🚨(backend) fix tests

I am removing hard coded datetime.

.gitignore

@@ -44,6 +44,9 @@ env.d/development/*
 !env.d/development/*.dist
 env.d/terraform
 
+# Configuration
+**/conversations/configuration/llm/dev.json
+
 # npm
 node_modules
 

CHANGELOG.md

@@ -8,14 +8,31 @@ and this project adheres to
 
 ## [Unreleased]
 
+### Added
+
+- ✨(backend) add FindRagBackend
+
+### Removed
+
+- 🔥(chat) consider PDF documents as other kind of documents #234
+
+## [0.0.11] - 2026-01-16
+
 ### Changed
-- 🐛(front) optimize chat
+
 - 📦️(front) update react
 - ✨(chat) Generate and edit conversation title
 
 ### Fixed
 
-- 🐛(e2e) fix test-e2e-chronium
+- 🐛(e2e) fix test-e2e-chromium
+- 🐛(back) fix system prompt compatibility with self-hosted models #200
+- ⚰️(back) remove dead code and unused files
+- 🐛(back) prevent tool call timeouts
+
+### Removed
+
+- 🔥(chat) remove thinking part from frontend #227
 
 ## [0.0.10] - 2025-12-15
 
@@ -35,6 +52,7 @@ and this project adheres to
 ## [0.0.9] - 2025-11-17
 
 ### Added
+
 - ✨(front) add code copy button
 - ✨(RAG) add generic collection RAG tools #159
 
@@ -42,7 +60,6 @@ and this project adheres to
 
 - 🔊(langfuse) enable tracing with redacted content #162
 
-
 ## [0.0.8] - 2025-11-10
 
 ### Fixed
@@ -57,28 +74,24 @@ and this project adheres to
 
 - 🔥(posthog) remove posthog middleware for async mode fix #146
 
-
 ## [0.0.7] - 2025-10-28
 
 ### Fixed
 
 - 🚑️(posthog) fix the posthog middleware for async mode #133
 
-
 ## [0.0.6] - 2025-10-28
 
 ### Fixed
 
 - 🚑️(stats) fix tracking id in upload event #130
 
-
 ## [0.0.5] - 2025-10-27
 
 ### Fixed
 
 - 🚑️(drag-drop) fix the rejection display on Safari #127
 
-
 ## [0.0.4] - 2025-10-27
 
 ### Added
@@ -95,14 +108,12 @@ and this project adheres to
 - 🐛(front) fix mobile source
 - 🐛(attachments) reject the whole drag&drop if unsupported formats #123
 
-
 ## [0.0.3] - 2025-10-21
 
 ### Fixed
 
 - 🚑️(web-search) fix missing argument in RAG backend #116
 
-
 ## [0.0.2] - 2025-10-21
 
 ### Added
@@ -112,6 +123,7 @@ and this project adheres to
 - 📈(posthog) add `sub` field to tracking #95
 
 ### Changed
+
 - 🔧(front) change links feedback tchap + settings popup
 - 🐛(front) code activation fix session end #93
 - 💬(wording) error page wording #102
@@ -119,7 +131,6 @@ and this project adheres to
 - 🐛(activation-codes) create contact in brevo before add to list #108
 - ⚗️(summarization) add system prompt to handle tool #112
 
-
 ## [0.0.1] - 2025-10-19
 
 ### Changed
@@ -142,7 +153,7 @@ and this project adheres to
 - 🎨(front) change list attachment in chat
 - 🎨(front) move emplacement for attachment
 - 🎨(ui) retour ui sources files
-- ✨(ui) fix retour global ui 
+- ✨(ui) fix retour global ui
 - 🐛(fix) broken staging css
 - 🎨(alpha) adjustment for alpha version
 - ✨(ui) delete flex message
@@ -177,7 +188,8 @@ and this project adheres to
 - 💄(chat) add code highlighting for LLM responses #67
 
 
-[unreleased]: https://github.com/suitenumerique/conversations/compare/v0.0.10...main
+[unreleased]: https://github.com/suitenumerique/conversations/compare/v0.0.11...main
+[0.0.11]: https://github.com/suitenumerique/conversations/releases/v0.0.11
 [0.0.10]: https://github.com/suitenumerique/conversations/releases/v0.0.10
 [0.0.9]: https://github.com/suitenumerique/conversations/releases/v0.0.9
 [0.0.8]: https://github.com/suitenumerique/conversations/releases/v0.0.8

Dockerfile

@@ -4,7 +4,7 @@
 FROM python:3.13.3-alpine AS base
 
 # Upgrade pip to its latest release to speed up dependencies installation
-RUN python -m pip install --upgrade pip setuptools
+RUN python -m pip install --upgrade pip
 
 # Upgrade system packages to install security updates
 RUN apk update && \

compose.yml

@@ -71,6 +71,9 @@ services:
       - "host.docker.internal:host-gateway"
     ports:
       - "8071:8000"
+    networks:
+      - default
+      - lasuite
     volumes:
       - ./src/backend:/app
       - ./data/static:/data/static
@@ -89,6 +92,9 @@ services:
     image: nginx:1.25
     ports:
       - "8083:8083"
+    networks:
+      - default
+      - lasuite
     volumes:
       - ./docker/files/etc/nginx/conf.d:/etc/nginx/conf.d:ro
     depends_on:
@@ -177,3 +183,8 @@ services:
       kc_postgresql:
         condition: service_healthy
         restart: true
+
+networks:
+  lasuite:
+    name: lasuite-network
+    driver: bridge

docs/env.md

@@ -95,6 +95,9 @@ These are the environment variables you can set for the `conversations-backend`
 | CACHES_KEY_PREFIX                               | The prefix used to every cache keys.                                                                                              | conversations                                           |
 | THEME_CUSTOMIZATION_FILE_PATH                   | full path to the file customizing the theme. An example is provided in src/backend/conversations/configuration/theme/default.json | BASE_DIR/conversations/configuration/theme/default.json |
 | THEME_CUSTOMIZATION_CACHE_TIMEOUT               | Cache duration for the customization settings                                                                                     | 86400                                                   |
+| FIND_API_KEY                                    | API key of Find                                                                                                                   |                                                         |
+| FIND_API_URL                                    | URL of Find                                                                                                                       | `https://app-find/api`                                  |
+| FIND_API_TIMEOUT                                | Find API timeout                                                                                                                  | 30                                                      |
 
 
 ## conversations-frontend image

docs/llm-configuration.md

@@ -244,9 +244,9 @@ For Mistral AI models using the Etalab platform:
 {
   "models": [
     {
-      "hrid": "mistral-large",
-      "model_name": "mistral-large-latest",
-      "human_readable_name": "Mistral Large (Etalab)",
+      "hrid": "mistral-medium",
+      "model_name": "mistral-medium-2508",
+      "human_readable_name": "Mistral Medium (Etalab)",
       "provider_name": "mistral-etalab",
       "profile": null,
       "settings": {

docs/tools/web_search_brave.md

@@ -357,6 +357,7 @@ The RAG backend performs semantic search to find the most relevant content:
 rag_results = document_store.search(
     query,
     results_count=settings.BRAVE_RAG_WEB_SEARCH_CHUNK_NUMBER,
+    **kwargs, # Additional search parameters like session with access_token
 )
 ```
 

env.d/development/common.e2e.dist

@@ -8,3 +8,5 @@ LLM_CONFIGURATION_FILE_PATH = /app/conversations/configuration/llm/default.e2e.j
 # Features
 FEATURE_FLAG_WEB_SEARCH=ENABLED
 FEATURE_FLAG_DOCUMENT_UPLOAD=ENABLED
+
+AUTO_TITLE_AFTER_USER_MESSAGES=3

package.json

@@ -1,6 +0,0 @@
-{
-  "dependencies": {
-    "@ai-sdk/react": "^1.2.12",
-    "@ai-sdk/ui-utils": "^1.2.11"
-  }
-}

src/backend/chat/agent_rag/document_converter/parser.py

@@ -0,0 +1,66 @@
+"""Document parsers for RAG backends."""
+
+import logging
+from io import BytesIO
+from urllib.parse import urljoin
+
+from django.conf import settings
+
+import requests
+
+from chat.agent_rag.document_converter.markitdown import DocumentConverter
+
+logger = logging.getLogger(__name__)
+
+
+class BaseParser:
+    """Base class for document parsers."""
+
+    def parse_document(self, name: str, content_type: str, content: BytesIO) -> str:
+        """
+        Parse the document and prepare it for the search operation.
+        This method should handle the logic to convert the document
+        into a format suitable for storage.
+
+        Args:
+            name (str): The name of the document.
+            content_type (str): The MIME type of the document (e.g., "application/pdf").
+            content (BytesIO): The content of the document as a BytesIO stream.
+
+        Returns:
+            str: The document content in Markdown format.
+        """
+        raise NotImplementedError("Must be implemented in subclass.")
+
+
+class AlbertParser(BaseParser):
+    """Document parser using Albert API for PDFs and DocumentConverter for other formats."""
+
+    endpoint = urljoin(settings.ALBERT_API_URL, "/v1/parse-beta")
+
+    def parse_pdf_document(self, name: str, content_type: str, content: bytes) -> str:
+        """Parse PDF document using Albert API."""
+        response = requests.post(
+            self.endpoint,
+            headers={
+                "Authorization": f"Bearer {settings.ALBERT_API_KEY}",
+            },
+            files={
+                "file": (name, content, content_type),
+                "output_format": (None, "markdown"),
+            },
+            timeout=settings.ALBERT_API_PARSE_TIMEOUT,
+        )
+        response.raise_for_status()
+
+        return "\n\n".join(
+            document_page["content"] for document_page in response.json().get("data", [])
+        )
+
+    def parse_document(self, name: str, content_type: str, content: bytes) -> str:
+        """Parse document based on content type."""
+        if content_type == "application/pdf":
+            return self.parse_pdf_document(name=name, content_type=content_type, content=content)
+        return DocumentConverter().convert_raw(
+            name=name, content_type=content_type, content=content
+        )

src/backend/chat/agent_rag/document_rag_backends/albert_rag_backend.py

@@ -13,7 +13,7 @@ import requests
 
 from chat.agent_rag.albert_api_constants import Searches
 from chat.agent_rag.constants import RAGWebResult, RAGWebResults, RAGWebUsage
-from chat.agent_rag.document_converter.markitdown import DocumentConverter
+from chat.agent_rag.document_converter.parser import AlbertParser
 from chat.agent_rag.document_rag_backends.base_rag_backend import BaseRagBackend
 
 logger = logging.getLogger(__name__)
@@ -26,9 +26,6 @@ class AlbertRagBackend(BaseRagBackend):  # pylint: disable=too-many-instance-att
 
     It provides methods to:
     - Create a collection for the search operation.
-    - Parse documents and convert them to Markdown format:
-       + Handle PDF parsing using the Albert API.
-       + Use the DocumentConverter (markitdown) for other formats.
     - Store parsed documents in the Albert collection.
     - Perform a search operation using the Albert API.
     """
@@ -46,10 +43,9 @@ class AlbertRagBackend(BaseRagBackend):  # pylint: disable=too-many-instance-att
         }
         self._collections_endpoint = urljoin(self._base_url, "/v1/collections")
         self._documents_endpoint = urljoin(self._base_url, "/v1/documents")
-        self._pdf_parser_endpoint = urljoin(self._base_url, "/v1/parse-beta")
         self._search_endpoint = urljoin(self._base_url, "/v1/search")
-
         self._default_collection_description = "Temporary collection for RAG document search"
+        self.parser = AlbertParser()
 
     def create_collection(self, name: str, description: Optional[str] = None) -> str:
         """
@@ -91,7 +87,7 @@ class AlbertRagBackend(BaseRagBackend):  # pylint: disable=too-many-instance-att
         self.collection_id = str(response.json()["id"])
         return self.collection_id
 
-    def delete_collection(self) -> None:
+    def delete_collection(self, **kwargs) -> None:
         """
         Delete the current collection
         """
@@ -102,7 +98,7 @@ class AlbertRagBackend(BaseRagBackend):  # pylint: disable=too-many-instance-att
         )
         response.raise_for_status()
 
-    async def adelete_collection(self) -> None:
+    async def adelete_collection(self, **kwargs) -> None:
         """
         Asynchronously delete the current collection
         """
@@ -114,59 +110,7 @@ class AlbertRagBackend(BaseRagBackend):  # pylint: disable=too-many-instance-att
             )
             response.raise_for_status()
 
-    def parse_pdf_document(self, name: str, content_type: str, content: BytesIO) -> str:
-        """
-        Parse the PDF document content and return the text content.
-        This method should handle the logic to convert the PDF into
-        a format suitable for the Albert API.
-        """
-        response = requests.post(
-            self._pdf_parser_endpoint,
-            headers=self._headers,
-            files={
-                "file": (
-                    name,
-                    content,
-                    content_type,
-                ),  # Use the name as the filename in the request
-                "output_format": (None, "markdown"),  # Specify the output format as Markdown,
-            },
-            timeout=settings.ALBERT_API_PARSE_TIMEOUT,
-        )
-        response.raise_for_status()
-
-        return "\n\n".join(
-            document_page["content"] for document_page in response.json().get("data", [])
-        )
-
-    def parse_document(self, name: str, content_type: str, content: BytesIO):
-        """
-        Parse the document and prepare it for the search operation.
-        This method should handle the logic to convert the document
-        into a format suitable for the Albert API.
-
-        Args:
-            name (str): The name of the document.
-            content_type (str): The MIME type of the document (e.g., "application/pdf").
-            content (BytesIO): The content of the document as a BytesIO stream.
-
-        Returns:
-            str: The document content in Markdown format.
-        """
-        # Implement the parsing logic here
-        if content_type == "application/pdf":
-            # Handle PDF parsing
-            markdown_content = self.parse_pdf_document(
-                name=name, content_type=content_type, content=content
-            )
-        else:
-            markdown_content = DocumentConverter().convert_raw(
-                name=name, content_type=content_type, content=content
-            )
-
-        return markdown_content
-
-    def store_document(self, name: str, content: str) -> None:
+    def store_document(self, name: str, content: str, **kwargs) -> None:
         """
         Store the document content in the Albert collection.
         This method should handle the logic to send the document content to the Albert API.
@@ -174,6 +118,7 @@ class AlbertRagBackend(BaseRagBackend):  # pylint: disable=too-many-instance-att
         Args:
             name (str): The name of the document.
             content (str): The content of the document in Markdown format.
+            **kwargs: Additional arguments.
         """
         response = requests.post(
             urljoin(self._base_url, self._documents_endpoint),
@@ -188,7 +133,7 @@ class AlbertRagBackend(BaseRagBackend):  # pylint: disable=too-many-instance-att
         logger.debug(response.json())
         response.raise_for_status()
 
-    async def astore_document(self, name: str, content: str) -> None:
+    async def astore_document(self, name: str, content: str, **kwargs) -> None:
         """
         Store the document content in the Albert collection.
         This method should handle the logic to send the document content to the Albert API.
@@ -196,6 +141,7 @@ class AlbertRagBackend(BaseRagBackend):  # pylint: disable=too-many-instance-att
         Args:
             name (str): The name of the document.
             content (str): The content of the document in Markdown format.
+            **kwargs: Additional arguments.
         """
         async with httpx.AsyncClient(timeout=settings.ALBERT_API_TIMEOUT) as client:
             response = await client.post(
@@ -213,13 +159,14 @@ class AlbertRagBackend(BaseRagBackend):  # pylint: disable=too-many-instance-att
             logger.debug(response.json())
             response.raise_for_status()
 
-    def search(self, query, results_count: int = 4) -> RAGWebResults:
+    def search(self, query: str, results_count: int = 4, **kwargs) -> RAGWebResults:
         """
         Perform a search using the Albert API based on the provided query.
 
         Args:
             query (str): The search query.
             results_count (int): The number of results to return.
+            **kwargs: Additional arguments.
 
         Returns:
             RAGWebResults: The search results.
@@ -256,13 +203,14 @@ class AlbertRagBackend(BaseRagBackend):  # pylint: disable=too-many-instance-att
             ),
         )
 
-    async def asearch(self, query, results_count: int = 4) -> RAGWebResults:
+    async def asearch(self, query, results_count: int = 4, **kwargs) -> RAGWebResults:
         """
         Perform an asynchronous search using the Albert API based on the provided query.
 
         Args:
             query (str): The search query.
             results_count (int): The number of results to return.
+            **kwargs: Additional arguments.
 
         Returns:
             RAGWebResults: The search results.

src/backend/chat/agent_rag/document_rag_backends/base_rag_backend.py

@@ -1,6 +1,7 @@
 """Implementation of the Albert API for RAG document search."""
 
 import logging
+from abc import ABC, abstractmethod
 from contextlib import asynccontextmanager, contextmanager
 from io import BytesIO
 from typing import List, Optional
@@ -8,11 +9,12 @@ from typing import List, Optional
 from asgiref.sync import sync_to_async
 
 from chat.agent_rag.constants import RAGWebResults
+from chat.agent_rag.document_converter.parser import BaseParser
 
 logger = logging.getLogger(__name__)
 
 
-class BaseRagBackend:
+class BaseRagBackend(ABC):
     """Base class for RAG backends."""
 
     def __init__(
@@ -38,6 +40,7 @@ class BaseRagBackend:
         self.collection_id = collection_id
         self.read_only_collection_id = read_only_collection_id or []
         self._default_collection_description = "Temporary collection for RAG document search"
+        self.parser: BaseParser = BaseParser()
 
     def get_all_collection_ids(self) -> List[str]:
         """
@@ -53,13 +56,14 @@ class BaseRagBackend:
 
         collection_ids = []
         if self.collection_id:
-            collection_ids.append(int(self.collection_id))
+            collection_ids.append(self.collection_id)
         if self.read_only_collection_id:
             collection_ids.extend(
                 [int(collection_id) for collection_id in self.read_only_collection_id]
             )
         return collection_ids
 
+    @abstractmethod
     def create_collection(self, name: str, description: Optional[str] = None) -> str:
         """
         Create a temporary collection for the search operation.
@@ -88,9 +92,10 @@ class BaseRagBackend:
         Returns:
             str: The document content in Markdown format.
         """
-        raise NotImplementedError("Must be implemented in subclass.")
+        return self.parser.parse_document(name, content_type, content)
 
-    def store_document(self, name: str, content: str) -> None:
+    @abstractmethod
+    def store_document(self, name: str, content: str, **kwargs) -> None:
         """
         Store the document content in the collection.
         This method should handle the logic to send the document content to the API.
@@ -98,10 +103,11 @@ class BaseRagBackend:
         Args:
             name (str): The name of the document.
             content (str): The content of the document in Markdown format.
+            **kwargs: Additional arguments. ex: "user_sub" for access control.
         """
         raise NotImplementedError("Must be implemented in subclass.")
 
-    async def astore_document(self, name: str, content: str) -> None:
+    async def astore_document(self, name: str, content: str, **kwargs) -> None:
         """
         Store the document content in the collection.
         This method should handle the logic to send the document content to the API.
@@ -109,10 +115,13 @@ class BaseRagBackend:
         Args:
             name (str): The name of the document.
             content (str): The content of the document in Markdown format.
+            **kwargs: Additional arguments. ex: "user_sub" for access control.
         """
-        return await sync_to_async(self.store_document)(name=name, content=content)
+        return await sync_to_async(self.store_document)(name=name, content=content, **kwargs)
 
-    def parse_and_store_document(self, name: str, content_type: str, content: BytesIO) -> str:
+    def parse_and_store_document(
+        self, name: str, content_type: str, content: BytesIO, **kwargs
+    ) -> str:
         """
         Parse the document and store it in the Albert collection.
 
@@ -120,39 +129,52 @@ class BaseRagBackend:
             name (str): The name of the document.
             content_type (str): The MIME type of the document (e.g., "application/pdf").
             content (BytesIO): The content of the document as a BytesIO stream.
+            **kwargs: Additional arguments. ex: "user_sub" for access control.
         """
         if not self.collection_id:
             raise RuntimeError("The RAG backend requires collection_id")
 
         document_content = self.parse_document(name, content_type, content)
-        self.store_document(name, document_content)
+        self.store_document(name, document_content, **kwargs)
         return document_content
 
-    def delete_collection(self) -> None:
+    @abstractmethod
+    def delete_collection(self, **kwargs) -> None:
         """
         Delete the collection.
         This method should handle the logic to delete the collection from the backend.
         """
         raise NotImplementedError("Must be implemented in subclass.")
 
-    async def adelete_collection(self) -> None:
+    async def adelete_collection(self, **kwargs) -> None:
         """
         Delete the collection.
         This method should handle the logic to delete the collection from the backend.
         """
-        return await sync_to_async(self.delete_collection)()
+        return await sync_to_async(self.delete_collection)(**kwargs)
 
-    def search(self, query, results_count: int = 4) -> RAGWebResults:
+    @abstractmethod
+    def search(self, query: str, results_count: int = 4, **kwargs) -> RAGWebResults:
         """
         Search the collection for the given query.
+
+        Args:
+            query: The search query string.
+            results_count: Number of results to return.
+            **kwargs: Additional arguments. ex: 'session' for OIDC authentication.
         """
         raise NotImplementedError("Must be implemented in subclass.")
 
-    async def asearch(self, query, results_count: int = 4) -> RAGWebResults:
+    async def asearch(self, query: str, results_count: int = 4, **kwargs) -> RAGWebResults:
         """
-        Search the collection for the given query.
+        Search the collection for the given query asynchronously.
+
+        Args:
+            query: The search query string.
+            results_count: Number of results to return.
+            **kwargs: Additional arguments. ex: 'session' for OIDC authentication.
         """
-        return await sync_to_async(self.search)(query=query, results_count=results_count)
+        return await sync_to_async(self.search)(query=query, results_count=results_count, **kwargs)
 
     @classmethod
     @contextmanager
@@ -168,7 +190,9 @@ class BaseRagBackend:
 
     @classmethod
     @asynccontextmanager
-    async def temporary_collection_async(cls, name: str, description: Optional[str] = None):
+    async def temporary_collection_async(
+        cls, name: str, description: Optional[str] = None, **kwargs
+    ):
         """Context manager for RAG backend with temporary collections."""
         backend = cls()
 
@@ -176,4 +200,4 @@ class BaseRagBackend:
         try:
             yield backend
         finally:
-            await backend.adelete_collection()
+            await backend.adelete_collection(**kwargs)

src/backend/chat/agent_rag/document_rag_backends/find_rag_backend.py

@@ -0,0 +1,163 @@
+"""Implementation of the Find API for RAG document search."""
+
+import logging
+import uuid
+from typing import List, Optional
+from urllib.parse import urljoin
+from uuid import uuid4
+
+from django.conf import settings
+from django.utils import timezone
+
+import requests
+
+from chat.agent_rag.constants import RAGWebResult, RAGWebResults, RAGWebUsage
+from chat.agent_rag.document_converter.parser import AlbertParser
+from chat.agent_rag.document_rag_backends.base_rag_backend import BaseRagBackend
+from utils.oidc import with_fresh_access_token
+
+logger = logging.getLogger(__name__)
+
+
+SUPPORTED_LANGUAGE_CODES = ["en", "fr", "de", "nl"]
+
+
+class FindRagBackend(BaseRagBackend):
+    """
+    This class is a placeholder for the Find API implementation.
+    It is designed to be used with the RAG (Retrieval-Augmented Generation) document search system.
+
+    It provides methods to:
+    - Store parsed documents in the Find index.
+    - Perform a search operation using the Find API.
+    """
+
+    def __init__(
+        self,
+        collection_id: Optional[str] = None,
+        read_only_collection_id: Optional[List[str]] = None,
+    ):
+        # Initialize any necessary parameters or configurations here
+        super().__init__(collection_id, read_only_collection_id)
+        self.api_key = settings.FIND_API_KEY
+        self.search_endpoint = "api/v1.0/documents/search/"
+        self.indexing_endpoint = "api/v1.0/documents/index/"
+        self.deleting_endpoint = "api/v1.0/documents/delete/"
+        self.parser = AlbertParser()  # Find Rag relies on Albert parser
+
+    def create_collection(self, name: str, description: Optional[str] = None) -> str:
+        """
+        init collection_id
+        """
+        self.collection_id = self.collection_id or str(uuid.uuid4())
+        return self.collection_id
+
+    @with_fresh_access_token
+    def delete_collection(self, **kwargs) -> None:
+        """
+        Delete the current collection
+        """
+        response = requests.post(
+            urljoin(settings.FIND_API_URL, self.deleting_endpoint),
+            headers={"Authorization": f"Bearer {kwargs['session'].get('oidc_access_token')}"},
+            json={
+                "tags": [f"collection-{self.collection_id}"],
+                # "service": "conversations"
+            },
+            timeout=settings.FIND_API_TIMEOUT,
+        )
+        response.raise_for_status()
+
+    def store_document(self, name: str, content: str, **kwargs) -> None:
+        """
+        index document in Find
+
+        Args:
+            name (str): The name of the document.
+            content (str): The content of the document in Markdown format.
+            user_sub (str): The user subject identifier for access control.
+        """
+        logger.debug("index document '%s' in Find", name)
+
+        user_sub = kwargs.get("user_sub")
+        if not user_sub:
+            raise ValueError("user_sub is required to store document in FindRagBackend")
+
+        response = requests.post(
+            urljoin(settings.FIND_API_URL, self.indexing_endpoint),
+            headers={"Authorization": f"Bearer {self.api_key}"},
+            json={
+                "id": str(uuid4()),
+                "title": str(name) or "",
+                "depth": 0,
+                "path": str(name) or "",
+                "numchild": 0,
+                "content": content or "",
+                "created_at": timezone.now().isoformat(),
+                "updated_at": timezone.now().isoformat(),
+                "tags": [f"collection-{self.collection_id}"],
+                "size": len(content.encode("utf-8")),
+                "users": [user_sub],
+                "groups": [],
+                "reach": "authenticated",
+                "is_active": True,
+            },
+            timeout=settings.FIND_API_TIMEOUT,
+        )
+        response.raise_for_status()
+
+    @with_fresh_access_token
+    def search(self, query: str, results_count: int = 4, **kwargs) -> RAGWebResults:
+        """
+        Perform a search using the Find API.
+        Uses the user's OIDC token from the request session.
+
+        Args:
+            query: The search query.
+            results_count: Number of results to return.
+            **kwargs: Additional arguments. Expected: 'session' containing OIDC tokens,
+
+        Returns:
+            RAGWebResults: The search results.
+        """
+        logger.debug("search documents in Find with query '%s'", query)
+        response = requests.post(
+            urljoin(settings.FIND_API_URL, self.search_endpoint),
+            headers={"Authorization": f"Bearer {kwargs['session'].get('oidc_access_token')}"},
+            json={
+                "q": query or "*",
+                "tags": [
+                    f"collection-{collection_id}" for collection_id in self.get_all_collection_ids()
+                ],
+                "k": results_count,
+            },
+            timeout=settings.FIND_API_TIMEOUT,
+        )
+        response.raise_for_status()
+
+        return RAGWebResults(
+            data=[
+                RAGWebResult(
+                    url=get_language_value(result["_source"], "title"),
+                    content=get_language_value(result["_source"], "content"),
+                    score=result["_score"],
+                )
+                for result in response.json()
+            ],
+            usage=RAGWebUsage(
+                prompt_tokens=0,
+                completion_tokens=0,
+            ),
+        )
+
+
+def get_language_value(source, language_field):
+    """
+    extract the value of the language field with the correct language_code extension.
+    "title" and "content" have extensions like "title.en" or "title.fr".
+    get_language_value will return the value regardless of the extension.
+    """
+    for language_code in SUPPORTED_LANGUAGE_CODES:
+        if f"{language_field}.{language_code}" in source:
+            return source[f"{language_field}.{language_code}"]
+    raise ValueError(f"No '{language_field}' field with any supported language code in object")

src/backend/chat/agents/base.py

@@ -10,7 +10,6 @@ import httpx
 from pydantic_ai import Agent
 from pydantic_ai.models import get_user_agent
 from pydantic_ai.profiles import ModelProfile
-from pydantic_ai.toolsets import FunctionToolset
 
 from chat.tools import get_pydantic_tools_by_name
 
@@ -174,22 +173,18 @@ class BaseAgent(Agent):
             # and pydantic_ai.models.infer_model()
             _model_instance = self.configuration.model_name
 
-        _system_prompt = self.configuration.system_prompt
-        _base_toolset = (
-            [
-                FunctionToolset(
-                    tools=[
-                        get_pydantic_tools_by_name(tool_name)
-                        for tool_name in self.configuration.tools
-                    ]
-                )
-            ]
-            if self.configuration.tools
-            else None
-        )
+        _system_prompt = self.get_system_prompt()
 
-        _tools = [get_pydantic_tools_by_name(tool_name) for tool_name in self.configuration.tools]
+        _tools = self.get_tools()
 
-        super().__init__(
-            model=_model_instance, system_prompt=_system_prompt, tools=_tools, **kwargs
-        )
+        super().__init__(model=_model_instance, instructions=_system_prompt, tools=_tools, **kwargs)
+
+    def get_system_prompt(self) -> str | None:
+        """Override this method to customize the system prompt."""
+        return self.configuration.system_prompt
+
+    def get_tools(self) -> list | None:
+        """Override this method to customize tools."""
+        if not self.configuration.tools:
+            return []
+        return [get_pydantic_tools_by_name(tool_name) for tool_name in self.configuration.tools]

src/backend/chat/agents/conversation.py

@@ -16,7 +16,6 @@ from .base import BaseAgent
 
 logger = logging.getLogger(__name__)
 
-
 MOCKED_RESPONSE = """
 # **Ode to the AI Assistant** 🤖✨
 
@@ -102,10 +101,10 @@ class ConversationAgent(BaseAgent):
         if settings.WARNING_MOCK_CONVERSATION_AGENT:
             self._model = FunctionModel(stream_function=mocked_agent_model)
 
-        @self.system_prompt
+        @self.instructions
         def add_the_date() -> str:
             """
-            Dynamic system prompt function to add the current date.
+            Dynamic instruction function to add the current date.
 
             Warning: this will always use the date in the server timezone,
             not the user's timezone...
@@ -113,9 +112,9 @@ class ConversationAgent(BaseAgent):
             _formatted_date = formats.date_format(timezone.now(), "l d/m/Y", use_l10n=False)
             return f"Today is {_formatted_date}."
 
-        @self.system_prompt
+        @self.instructions
         def enforce_response_language() -> str:
-            """Dynamic system prompt function to set the expected language to use."""
+            """Dynamic instruction function to set the expected language to use."""
             return f"Answer in {get_language_name(language).lower()}." if language else ""
 
     def get_web_search_tool_name(self) -> str | None:
@@ -132,3 +131,25 @@ class ConversationAgent(BaseAgent):
                 if tool.name.startswith("web_search_"):
                     return tool.name
         return None
+
+
+@dataclasses.dataclass(init=False)
+class TitleGenerationAgent(BaseAgent):
+    """Agent that generates concise, descriptive titles for conversations."""
+
+    def __init__(self, **kwargs):
+        super().__init__(
+            model_hrid=settings.LLM_DEFAULT_MODEL_HRID,
+            output_type=str,
+            **kwargs,
+        )
+
+    def get_tools(self):
+        return []
+
+    def get_system_prompt(self):
+        return (
+            "You are a title generator. Your task is to create concise, descriptive titles "
+            "that accurately summarize conversation content and help the user quickly identify the "
+            "conversation.\n\n"
+        )

src/backend/chat/clients/pydantic_ai.py

@@ -52,15 +52,13 @@ from pydantic_ai.messages import (
 )
 
 from core.feature_flags.helpers import is_feature_enabled
-from core.file_upload.utils import generate_retrieve_policy
 
 from chat import models
-from chat.agents.conversation import ConversationAgent
+from chat.agents.conversation import ConversationAgent, TitleGenerationAgent
 from chat.agents.local_media_url_processors import (
     update_history_local_urls,
     update_local_urls,
 )
-from chat.agents.summarize import SummarizationAgent
 from chat.ai_sdk_types import (
     LanguageModelV1Source,
     SourceUIPart,
@@ -77,7 +75,10 @@ from chat.tools.document_generic_search_rag import add_document_rag_search_tool_
 from chat.tools.document_search_rag import add_document_rag_search_tool
 from chat.tools.document_summarize import document_summarize
 from chat.vercel_ai_sdk.core import events_v4, events_v5
-from chat.vercel_ai_sdk.encoder import EventEncoder
+from chat.vercel_ai_sdk.encoder import CURRENT_EVENT_ENCODER_VERSION, EventEncoder
+
+# Keep at the top of the file to avoid mocking issues
+document_store_backend = import_string(settings.RAG_DOCUMENT_SEARCH_BACKEND)
 
 logger = logging.getLogger(__name__)
 
@@ -90,6 +91,7 @@ class ContextDeps:
 
     conversation: models.ChatConversation
     user: User
+    session: Optional[Dict] = None
     web_search_enabled: bool = False
 
 
@@ -104,7 +106,14 @@ def get_model_configuration(model_hrid: str):
 class AIAgentService:  # pylint: disable=too-many-instance-attributes
     """Service class for AI-related operations (Pydantic-AI edition)."""
 
-    def __init__(self, conversation: models.ChatConversation, user, model_hrid=None, language=None):
+    def __init__(  # pylint: disable=too-many-arguments,too-many-positional-arguments
+        self,
+        conversation: models.ChatConversation,
+        user,
+        session=None,
+        model_hrid=None,
+        language=None,
+    ):
         """
         Initialize the AI agent service.
 
@@ -120,7 +129,7 @@ class AIAgentService:  # pylint: disable=too-many-instance-attributes
 
         self._langfuse_available = settings.LANGFUSE_ENABLED
         self._store_analytics = self._langfuse_available and user.allow_conversation_analytics
-        self.event_encoder = EventEncoder("v4")  # Always use v4 for now
+        self.event_encoder = EventEncoder(CURRENT_EVENT_ENCODER_VERSION)  # We use v4 for now
 
         self._support_streaming = True
         if (streaming := get_model_configuration(self.model_hrid).supports_streaming) is not None:
@@ -134,6 +143,7 @@ class AIAgentService:  # pylint: disable=too-many-instance-attributes
         self._context_deps = ContextDeps(
             conversation=conversation,
             user=user,
+            session=session,
             web_search_enabled=self._is_web_search_enabled,
         )
 
@@ -237,6 +247,7 @@ class AIAgentService:  # pylint: disable=too-many-instance-attributes
         Parse and store input documents in the conversation's document store.
         """
         # Early external document URL rejection
+
         if any(
             not document.url.startswith("/media-key/")
             for document in documents
@@ -250,8 +261,6 @@ class AIAgentService:  # pylint: disable=too-many-instance-attributes
         ):
             raise ValueError("Document URL does not belong to the conversation.")
 
-        document_store_backend = import_string(settings.RAG_DOCUMENT_SEARCH_BACKEND)
-
         document_store = document_store_backend(self.conversation.collection_id)
         if not document_store.collection_id:
             # Create a new collection for the conversation
@@ -277,6 +286,7 @@ class AIAgentService:  # pylint: disable=too-many-instance-attributes
                         name=document.identifier,
                         content_type=document.media_type,
                         content=document_data,
+                        user_sub=self.user.sub,
                     )
                 else:
                     # Remote URL
@@ -286,6 +296,7 @@ class AIAgentService:  # pylint: disable=too-many-instance-attributes
                     name=document.identifier,
                     content_type=document.media_type,
                     content=document.data,
+                    user_sub=self.user.sub,
                 )
 
             if not document.media_type.startswith("text/"):
@@ -357,16 +368,7 @@ class AIAgentService:  # pylint: disable=too-many-instance-attributes
         messages: List[UIMessage],
         force_web_search: bool = False,
     ) -> events_v4.Event | events_v5.Event:
-        """
-        Drive the agent for the provided user message, stream Vercel-AI-SDK event parts representing model and tool activity, and persist the final conversation state.
-        
-        Parameters:
-            messages (List[UIMessage]): UI messages for the conversation; the last message must be from the user.
-            force_web_search (bool): If true, require the agent to invoke the configured web search tool before answering (ignored if the feature or tool is unavailable).
-        
-        Returns:
-            events_v4.Event | events_v5.Event: Streamed event parts such as `TextPart`, `ToolCallPart`/`ToolCallStreamingStartPart`/`ToolCallDeltaPart`, `ToolResultPart`, `ReasoningPart`, `SourcePart`, `DataPart`, `StartStepPart`, and `FinishMessagePart` that drive frontend updates.
-        """
+        """Run the Pydantic AI agent and stream events."""
         if messages[-1].role != "user":
             return
 
@@ -430,6 +432,7 @@ class AIAgentService:  # pylint: disable=too-many-instance-attributes
                     ],
                 },
             )
+
             try:
                 await self.parse_input_documents(input_documents)
             except Exception as exc:  # pylint: disable=broad-except
@@ -456,28 +459,6 @@ class AIAgentService:  # pylint: disable=too-many-instance-attributes
 
         await self._agent_stop_streaming(force_cache_check=True)
 
-        generated_title = None
-
-        # +1 because we're about to add a new user message
-        current_user_count = sum(1 for msg in self.conversation.messages if msg.role == "user") + 1
-        if (
-            current_user_count == settings.AUTO_TITLE_AFTER_USER_MESSAGES
-            and not self.conversation.title_set_by_user_at
-        ):
-            generated_title = await self._generate_title()
-
-        # Notify frontend about the title update
-        if generated_title:
-            yield events_v4.DataPart(
-                data=[
-                    {
-                        "type": "conversation_metadata",
-                        "conversationId": str(self.conversation.pk),
-                        "title": generated_title,
-                    }
-                ]
-            )
-
         if force_web_search and not self._is_web_search_enabled:
             logger.warning("Web search is forced but the feature is disabled, ignoring.")
             force_web_search = False
@@ -489,7 +470,7 @@ class AIAgentService:  # pylint: disable=too-many-instance-attributes
 
         if force_web_search:
 
-            @self.conversation_agent.system_prompt
+            @self.conversation_agent.instructions
             def force_web_search_prompt() -> str:
                 """Dynamic system prompt function to force web search."""
                 return (
@@ -500,27 +481,19 @@ class AIAgentService:  # pylint: disable=too-many-instance-attributes
         _tool_is_streaming = False
         _model_response_message_id = None
 
-        # Check for existing non-PDF documents in the conversation:
-        # - if no document at all: do nothing
-        # - if only PDFs: prepare document URLs for the agent
-        # - if other document types: add the RAG search tool
-        #   to allow searching in all kinds of documents
-        has_not_pdf_docs = await (
+        # Check for existing documents (any non-image attachment for this conversation)
+        has_documents = await (
             models.ChatConversationAttachment.objects.filter(
                 Q(conversion_from__isnull=True) | Q(conversion_from=""),
                 conversation=self.conversation,
             )
-            .exclude(
-                Q(content_type__startswith="image/") | Q(content_type="application/pdf"),
-            )
+            .exclude(content_type__startswith="image/")
             .aexists()
         )
 
-        document_urls = []
-        if not conversation_has_documents and not has_not_pdf_docs:
-            # No documents to process
-            pass
-        elif has_not_pdf_docs:
+        should_enable_rag = conversation_has_documents or has_documents
+
+        if should_enable_rag:
             add_document_rag_search_tool(self.conversation_agent)
 
             @self.conversation_agent.instructions
@@ -537,7 +510,7 @@ class AIAgentService:  # pylint: disable=too-many-instance-attributes
                 )
 
             # Inform the model (system-level) that documents are attached and available
-            @self.conversation_agent.system_prompt
+            @self.conversation_agent.instructions
             def attached_documents_note() -> str:
                 return (
                     "[Internal context] User documents are attached to this conversation. "
@@ -550,30 +523,6 @@ class AIAgentService:  # pylint: disable=too-many-instance-attributes
             async def summarize(ctx: RunContext, *args, **kwargs) -> ToolReturn:
                 """Wrap the document_summarize tool to provide context and add the tool."""
                 return await document_summarize(ctx, *args, **kwargs)
-        else:
-            conversation_documents = [
-                cd
-                async for cd in models.ChatConversationAttachment.objects.filter(
-                    Q(conversion_from__isnull=True) | Q(conversion_from=""),
-                    conversation=self.conversation,
-                )
-                .exclude(
-                    content_type__startswith="image/",
-                )
-                .values_list("key", "content_type")
-            ]
-
-            for doc_key, doc_content_type in conversation_documents:
-                if doc_content_type == "application/pdf":
-                    _presigned_url = generate_retrieve_policy(doc_key)
-                    document_urls.append(
-                        DocumentUrl(
-                            url=_presigned_url,
-                            identifier=doc_key.split("/")[-1],
-                            media_type="application/pdf",
-                        )
-                    )
-                    image_key_mapping[_presigned_url] = f"/media-key/{doc_key}"
 
         async with AsyncExitStack() as stack:
             # MCP servers (if any) can be initialized here
@@ -588,7 +537,7 @@ class AIAgentService:  # pylint: disable=too-many-instance-attributes
                     history.append(ModelResponse(parts=[TextPart(content="ok")], kind="response"))
 
             async with self.conversation_agent.iter(
-                [user_prompt] + input_images + document_urls,
+                [user_prompt] + input_images,
                 message_history=history,  # history will pass through agent's history_processors
                 deps=self._context_deps,
                 toolsets=mcp_servers,
@@ -749,22 +698,49 @@ class AIAgentService:  # pylint: disable=too-many-instance-attributes
 
         await self._agent_stop_streaming(force_cache_check=True)
 
-        # Persist conversation
-        await sync_to_async(self._update_conversation)(
+        # Prepare conversation update (save deferred until after potential title generation)
+        await sync_to_async(self._prepare_update_conversation)(
             final_output=run.result.new_messages(),
             usage=usage,
             final_output_from_tool=_final_output_from_tool,
             ui_sources=_ui_sources,
             model_response_message_id=_model_response_message_id,
             image_key_mapping=image_key_mapping or None,
-            generated_title=generated_title,
         )
 
+        generated_title = None
+
+        # Auto-generate title after N user messages if not manually set
+        user_messages_count = sum(1 for msg in self.conversation.messages if msg.role == "user")
+
+        should_generate_title = (
+            user_messages_count == settings.AUTO_TITLE_AFTER_USER_MESSAGES
+            and not self.conversation.title_set_by_user_at
+        )
+
+        if should_generate_title:
+            if generated_title := await self._generate_title():
+                self.conversation.title = generated_title
+
+        # Persist conversation (including any generated title)
+        await sync_to_async(self.conversation.save)()
+
+        # Notify frontend about the title update
+        if generated_title:
+            yield events_v4.DataPart(
+                data=[
+                    {
+                        "type": "conversation_metadata",
+                        "conversationId": str(self.conversation.pk),
+                        "title": generated_title,
+                    }
+                ]
+            )
+
         if self._langfuse_available:
             langfuse.update_current_trace(
                 output=run.result.output if self._store_analytics else "REDACTED"
             )
-
         # Vercel finish message
         yield events_v4.FinishMessagePart(
             finish_reason=events_v4.FinishReason.STOP,
@@ -774,7 +750,7 @@ class AIAgentService:  # pylint: disable=too-many-instance-attributes
             ),
         )
 
-    def _update_conversation(  # noqa: PLR0913
+    def _prepare_update_conversation(  # noqa: PLR0913
         self,
         *,
         final_output: List[ModelRequest | ModelMessage],
@@ -783,25 +759,18 @@ class AIAgentService:  # pylint: disable=too-many-instance-attributes
         ui_sources: List[SourceUIPart] = None,
         model_response_message_id: str | None = None,
         image_key_mapping: Dict[str, str] = None,
-        generated_title: str | None = None,
     ):  # pylint: disable=too-many-arguments
         """
-        Merge the agent's final outputs into the conversation and persist updated conversation state.
-        
-        Parameters:
-            final_output (List[ModelRequest | ModelMessage]): Sequence of model requests and responses produced by the agent run; these will be merged into a single request and a single response before saving.
-            usage (Dict[str, int]): Token usage statistics to store on the conversation (e.g., promptTokens, completionTokens).
-            final_output_from_tool (str | None): Optional text produced by a tool that should be appended to the final model response.
-            ui_sources (List[SourceUIPart], optional): Optional UI-visible source parts to attach to the final response message.
-            model_response_message_id (str | None, optional): If provided, assign this id to the saved model response UI message; if omitted, a warning will be logged.
-            image_key_mapping (Dict[str, str], optional): Mapping from original (unsigned) media URLs to presigned/rewritten URLs; applied to image/document references in the merged request parts.
-            generated_title (str | None, optional): Optional auto-generated conversation title to apply to the conversation.
-        
-        Behavior:
-            - Merges multiple model request/response objects into a single ModelRequest and ModelResponse.
-            - Rewrites image/document URLs in user prompt parts when an image_key_mapping is provided.
-            - Converts merged model messages to UI messages, appends ui_sources if present, and sets the response message id when supplied.
-            - Appends the merged request and response messages to the conversation, updates agent usage and pydantic messages, applies a generated title if given, and saves the conversation.
+        Save everything related to the conversation.
+
+        Things to improve here:
+         - The way we need to add the UI sources to the final output message.
+
+        Args:
+            final_output (List[ModelRequest | ModelMessage]): The final output from the agent.
+            usage (Dict[str, int]): The token usage statistics.
+            user_initial_prompt_str (str | None): The initial user prompt string, if any.
+            ui_sources (List[SourceUIPart]): Optional UI sources to include in the conversation.
         """
         _merged_final_output_request = ModelRequest(
             parts=[
@@ -847,43 +816,40 @@ class AIAgentService:  # pylint: disable=too-many-instance-attributes
         self.conversation.pydantic_messages += json.loads(
             ModelMessagesTypeAdapter.dump_json(final_output).decode("utf-8")
         )
-        if generated_title:
-            self.conversation.title = generated_title
-        self.conversation.save()
 
     async def _generate_title(self) -> str | None:
-        """
-        Create a concise conversation title based on the conversation's first messages.
-        
-        Uses the summarization agent to produce a short title in the same language as the user's messages. Returns the generated title text trimmed to at most 100 characters, or `None` if generation fails or produces no text.
-        
-        Returns:
-            str | None: The generated title (trimmed to 100 characters), or `None` when no title is available.
-        """
+        """Generate a title for the conversation using LLM based on first messages."""
 
-        # Build context from the first messages
+        # Build context from messages
+        # Note: We intentionally use only msg.content for title generation.
+        # Parts containing tool invocations or reasoning are excluded as they
+        # don't contribute to a meaningful context here
         context = "\n".join(
-            f"{msg.role}: {msg.content[:300]}"  # Limit content length per message
-            for msg in self.conversation.messages[:6]  # First few messages (3 user + 3 assistant)
+            f"{msg.role}: {(msg.content or '')[:300]}"  # Limit content length per message
+            for msg in self.conversation.messages
+            if msg.content
         )
 
+        language = self.language or settings.LANGUAGE_CODE
         prompt = (
-            "Generate a short, concise title (maximum 60 characters) for this conversation. "
-            "The title should capture the main topic or intent. "
-            "Return ONLY the title text, nothing else. No quotes, no explanations.\n\n"
-            "Return the title text in the same language the user messages are written."
-            f"If in doubt, use {self.language or 'French'}."
+            "Generate a concise title (3-5 words, max 100 characters) for this conversation.\n\n"
+            "Requirements:\n"
+            "- Capture the main topic or user intent\n"
+            "- The title must be a simple string, no markdown\n"
+            "- Help the user quickly identify the conversation\n"
+            f"- Match the language of the user messages (default: {language})\n"
+            "- Avoid the word 'summary' unless explicitly requested\n\n"
+            "Output: Title text only, no quotes, labels, or explanation.\n\n"
             f"Conversation:\n{context}"
         )
-
         try:
-            agent = SummarizationAgent()
+            agent = TitleGenerationAgent()
             result = await agent.run(prompt)
-            title = (result.output or "").strip()[:100]  # Enforce max length
+            title = (result.output or "").strip()[:100]  # Enforce max length (conversation.title)
             logger.info("Generated title for conversation %s: %s", self.conversation.pk, title)
             return title if title else None
         except Exception as exc:  # pylint: disable=broad-except #noqa: BLE001
             logger.warning(
                 "Failed to generate title for conversation %s: %s", self.conversation.pk, exc
             )
-            return None
+            return None

src/backend/chat/keepalive.py

@@ -0,0 +1,171 @@
+"""Helpers to prevent proxy timeouts during long-running stream operations.
+
+This module provides utilities to wrap synchronous and asynchronous iterators
+with keepalive messages. When a stream pauses for longer than the specified
+interval, keepalive messages are injected to prevent proxy/gateway
+timeouts while waiting for the stream data.
+"""
+
+import asyncio
+import logging
+import queue
+import threading
+import time
+from typing import AsyncIterator, Iterator
+
+from django.conf import settings
+
+from .vercel_ai_sdk.core.events_v4 import DataPart as V4DataPart
+from .vercel_ai_sdk.core.events_v5 import DataPart as V5DataPart
+from .vercel_ai_sdk.encoder import (
+    CURRENT_EVENT_ENCODER_VERSION,
+    EventEncoder,
+    EventEncoderVersion,
+)
+
+logger = logging.getLogger(__name__)
+
+
+def get_keepalive_message() -> str:
+    """Generate a keepalive message based on encoder/SDK version."""
+    if CURRENT_EVENT_ENCODER_VERSION == EventEncoderVersion.V4:
+        event = V4DataPart(data=[{"status": "WAITING"}])
+    else:
+        event = V5DataPart(data={"status": "WAITING"})
+    encoder = EventEncoder(CURRENT_EVENT_ENCODER_VERSION)
+    return encoder.encode(event)
+
+
+async def stream_with_keepalive_async(
+    stream: AsyncIterator[str],
+) -> AsyncIterator[str]:
+    """Wrap an async iterator to emit keepalive during long pauses.
+
+    Args:
+        stream: The async iterator to wrap
+    Yields:
+        Items from the original stream, plus keepalive messages during pauses
+    Raises:
+        Any exception raised by the original stream
+    """
+    q: asyncio.Queue = asyncio.Queue()
+    finished = asyncio.Event()
+    keepalive_message = get_keepalive_message()
+
+    async def producer():
+        """Background task that consumes the original stream into a queue."""
+
+        try:
+            async for stream_item in stream:
+                await q.put(stream_item)
+        except Exception as exc:  # pylint: disable=broad-except #noqa: BLE001
+            # Pass exceptions through the queue so the consumer can re-raise them.
+            # This ensures errors aren't silently swallowed.
+            await q.put(exc)
+        finally:
+            finished.set()
+            await q.put(None)  # Sentinel to signal completion
+
+    producer_task = asyncio.create_task(producer())
+
+    try:
+        while True:
+            try:
+                item = await asyncio.wait_for(q.get(), timeout=settings.KEEPALIVE_INTERVAL)
+                if item is None:
+                    break
+                if isinstance(item, Exception):
+                    raise item
+                yield item
+            except asyncio.TimeoutError:
+                # No data received within interval
+                if finished.is_set():
+                    # Producer is done, queue is empty (else we would not have timed out)
+                    break
+
+                logger.debug("Send keepalive")
+                yield keepalive_message
+    finally:
+        # Cleanup
+        producer_task.cancel()
+        try:
+            await producer_task
+        except asyncio.CancelledError:
+            pass
+
+
+def get_current_time() -> float:
+    """Get current monotonic time, avoiding freezegun interferences.
+
+    Returns time.monotonic() which:
+    - Is NOT affected by freezegun's @freeze_time decorator (unlike time.time())
+    - Prevents issues where frozen time in main thread differs from real time in
+      spawned threads, causing incorrect keepalive interval computation
+    - Is the best clock for measuring time intervals
+
+    Wrapped in a function to ease mocking in tests.
+
+    Returns:
+        float: Monotonic time in seconds since an arbitrary reference point
+    """
+    return time.monotonic()
+
+
+def stream_with_keepalive_sync(stream: Iterator[str]) -> Iterator[str]:
+    """Wraps a synchronous stream with keepalive messages."""
+
+    q: queue.Queue = queue.Queue()
+    stream_done = threading.Event()
+    keepalive_message = get_keepalive_message()
+    # Mutable container so threads can read/write shared timestamp
+    last_yield_time = [get_current_time()]
+
+    def consume_stream():
+        """Read from source stream and forward chunks to queue."""
+        try:
+            for chunk in stream:
+                if stream_done.is_set():
+                    return  # early exit
+                q.put(chunk, timeout=1)  # Arbitrary timeout prevents blocking forever
+        # pylint: disable=broad-exception-caught
+        except Exception as e:
+            logger.exception("Error in stream consumption")
+            q.put(e)
+        finally:
+            stream_done.set()
+
+    def send_keepalives():
+        """Inject keepalive messages when idle too long.
+
+        Uses get_current_time() (time.monotonic) instead of time.time()
+        to avoid issues with freezegun in tests.
+        """
+        while not stream_done.is_set():
+            # Sleep before checking to give main loop time to process and update timestamp
+            time.sleep(0.5)  # let main loop process first, empiric value
+            if get_current_time() - last_yield_time[0] >= settings.KEEPALIVE_INTERVAL:
+                try:
+                    q.put(keepalive_message, timeout=0.1)
+                except queue.Full:
+                    pass
+
+    for target in (consume_stream, send_keepalives):
+        threading.Thread(target=target, daemon=True).start()
+
+    try:
+        # Continue while stream is active or queue has still items
+        while not stream_done.is_set() or not q.empty():
+            try:
+                item = q.get(timeout=1)  # short timeout, avoid blocking and stay responsive
+            except queue.Empty:
+                continue
+
+            # Re-raise from consume_stream
+            if isinstance(item, Exception):
+                raise item
+
+            yield item
+            last_yield_time[0] = get_current_time()
+    finally:
+        # Signal threads to stop
+        stream_done.set()

src/backend/chat/serializers.py

@@ -30,14 +30,6 @@ class ChatConversationSerializer(serializers.ModelSerializer):
 
     def update(self, instance, validated_data):
         # If title is being changed, mark it as user-set
-        """
-        Update the ChatConversation instance and record when the title is changed by the user.
-        
-        If `validated_data` contains a `title` different from the instance's current title, sets `title_set_by_user_at` to the current time.
-        
-        Returns:
-            The updated ChatConversation instance.
-        """
         if "title" in validated_data and validated_data["title"] != instance.title:
             instance.title_set_by_user_at = timezone.now()
         return super().update(instance, validated_data)
@@ -213,4 +205,4 @@ class CreateChatConversationAttachmentSerializer(serializers.ModelSerializer):
                 f"File size exceeds the maximum limit of {max_size:d} MB."
             )
 
-        return size
+        return size

src/backend/chat/tests/agents/test_build_conversation_agent.py

@@ -27,9 +27,14 @@ def test_build_pydantic_agent_success_no_tools():
     """Test successful agent creation without tools."""
     agent = ConversationAgent(model_hrid="default-model")
     assert isinstance(agent, Agent)
+    assert agent._system_prompts == ()
+
+    instructions = agent._instructions
+    assert len(instructions) == 3
+    assert instructions[0] == "You are a helpful assistant"
+    assert instructions[1].__name__ == "add_the_date"
+    assert instructions[2].__name__ == "enforce_response_language"
 
-    assert agent._system_prompts == ("You are a helpful assistant",)
-    assert agent._instructions == []
     assert isinstance(agent.model, OpenAIChatModel)
     assert agent.model.model_name == "model-123"
     assert str(agent.model.client.base_url) == "https://api.llm.com/v1/"
@@ -37,6 +42,7 @@ def test_build_pydantic_agent_success_no_tools():
     assert agent._function_toolset.tools == {}
 
 
+@freeze_time("2025-07-25T10:36:35.297675Z")
 def test_build_pydantic_agent_with_tools(settings):
     """Test successful agent creation with tools."""
     settings.AI_AGENT_TOOLS = ["get_current_weather"]
@@ -44,8 +50,14 @@ def test_build_pydantic_agent_with_tools(settings):
     agent = ConversationAgent(model_hrid="default-model")
     assert isinstance(agent, Agent)
 
-    assert agent._system_prompts == ("You are a helpful assistant",)
-    assert agent._instructions == []
+    instructions = agent._instructions
+    assert len(instructions) == 3
+    assert instructions[0] == "You are a helpful assistant"
+    assert instructions[1].__name__ == "add_the_date"
+    assert instructions[1]() == "Today is Friday 25/07/2025."
+    assert instructions[2].__name__ == "enforce_response_language"
+    assert instructions[2]() == ""
+
     assert isinstance(agent.model, OpenAIChatModel)
     assert agent.model.model_name == "model-123"
     assert str(agent.model.client.base_url) == "https://api.llm.com/v1/"
@@ -56,21 +68,23 @@ def test_build_pydantic_agent_with_tools(settings):
 @freeze_time("2025-07-25T10:36:35.297675Z")
 def test_add_dynamic_system_prompt():
     """
-    Ensure add_the_date and enforce_response_language system prompt are registered
+    Ensure add_the_date and enforce_response_language instructions are registered
     and returns proper values.
     """
     agent = ConversationAgent(model_hrid="default-model")
 
-    assert len(agent._system_prompt_functions) == 2
+    assert len(agent._system_prompt_functions) == 0
 
-    assert agent._system_prompt_functions[0].function.__name__ == "add_the_date"
-    assert agent._system_prompt_functions[0].function() == "Today is Friday 25/07/2025."
-
-    assert agent._system_prompt_functions[1].function.__name__ == "enforce_response_language"
-    assert agent._system_prompt_functions[1].function() == ""
+    instructions = agent._instructions
+    assert len(instructions) == 3
+    assert instructions[0] == "You are a helpful assistant"
+    assert instructions[1].__name__ == "add_the_date"
+    assert instructions[1]() == "Today is Friday 25/07/2025."
+    assert instructions[2].__name__ == "enforce_response_language"
+    assert instructions[2]() == ""
 
     agent = ConversationAgent(model_hrid="default-model", language="fr-fr")
-    assert agent._system_prompt_functions[1].function() == "Answer in french."
+    assert agent._instructions[2]() == "Answer in french."
 
 
 def test_agent_get_web_search_tool_name(settings):

src/backend/chat/tests/agents/test_title_generation_agent.py

@@ -0,0 +1,66 @@
+"""Test cases for the TitleGenerationAgent class."""
+
+# pylint: disable=protected-access
+
+import pytest
+from pydantic_ai.models.openai import OpenAIChatModel
+
+from chat.agents.conversation import TitleGenerationAgent
+
+
+@pytest.fixture(autouse=True)
+def base_settings(settings):
+    """Set up base settings for the tests."""
+    settings.AI_BASE_URL = "https://api.llm.com/v1/"
+    settings.AI_API_KEY = "test-key"
+    settings.AI_MODEL = "model-XYZ"
+    settings.AI_AGENT_INSTRUCTIONS = "You are a helpful assistant"
+    settings.AI_AGENT_TOOLS = []
+    settings.LLM_DEFAULT_MODEL_HRID = "default-model"
+
+
+def test_title_generation_agent_uses_default_model_hrid(settings):
+    """Test that TitleGenerationAgent uses LLM_DEFAULT_MODEL_HRID from settings."""
+    settings.AI_MODEL = "custom-llm-model"
+    settings.AI_BASE_URL = "https://custom.api.com/v1/"
+    settings.AI_API_KEY = "custom-key"
+    settings.LLM_DEFAULT_MODEL_HRID = "default-model"
+
+    agent = TitleGenerationAgent()
+
+    assert isinstance(agent._model, OpenAIChatModel)
+    assert settings.LLM_CONFIGURATIONS["default-model"].model_name == "custom-llm-model"
+    assert agent._model.model_name == "custom-llm-model"
+
+
+def test_title_generation_agent_model_configuration():
+    """Test that the agent model is properly configured."""
+    agent = TitleGenerationAgent()
+
+    assert isinstance(agent._model, OpenAIChatModel)
+    assert agent._model.model_name == "model-XYZ"
+    assert str(agent._model.client.base_url) == "https://api.llm.com/v1/"
+    assert agent._model.client.api_key == "test-key"
+
+
+def test_title_generation_agent_has_no_tools():
+    """Test that TitleGenerationAgent has no tools configured."""
+    agent = TitleGenerationAgent()
+
+    assert agent._function_toolset.tools == {}
+    assert not agent.get_tools()
+
+
+def test_title_generation_agent_instructions():
+    """Test that the agent instructions contain the system prompt."""
+    agent = TitleGenerationAgent()
+
+    # The agent should have the title generation system prompt as instructions
+    instructions = agent._instructions
+    assert len(instructions) == 1
+    expected = (
+        "You are a title generator. Your task is to create concise, descriptive titles "
+        "that accurately summarize conversation content and help the user quickly identify the "
+        "conversation.\n\n"
+    )
+    assert instructions[0] == expected

src/backend/chat/tests/tools/test_web_search_brave.py

@@ -38,9 +38,6 @@ def brave_settings(settings):
     settings.BRAVE_SEARCH_EXTRA_SNIPPETS = True
     settings.BRAVE_SUMMARIZATION_ENABLED = False
     settings.BRAVE_CACHE_TTL = 3600
-    settings.RAG_DOCUMENT_SEARCH_BACKEND = (
-        "chat.agent_rag.document_rag_backends.albert_rag_backend.AlbertRagBackend"
-    )
     settings.BRAVE_RAG_WEB_SEARCH_CHUNK_NUMBER = 5
 
 

src/backend/chat/tests/views/chat/conftest.py

@@ -0,0 +1,17 @@
+"""Common test fixtures for chat views tests."""
+
+from unittest import mock
+
+import pytest
+
+
+@pytest.fixture(autouse=True)
+def mock_process_request():
+    """
+    Mock process_request to bypass OIDC authentication in tests.
+    """
+    with mock.patch(
+        "lasuite.oidc_login.decorators.RefreshOIDCAccessToken.process_request"
+    ) as mocked_process_request:
+        mocked_process_request.return_value = None
+        yield mocked_process_request

src/backend/chat/tests/views/chat/conversations/conftest.py

@@ -1,5 +1,6 @@
 """Common test fixtures for chat conversation endpoint tests."""
 
+import asyncio
 import json
 
 from django.utils import timezone
@@ -10,18 +11,8 @@ import respx
 from freezegun import freeze_time
 
 
-def build_openai_stream():
-    """
-    Constructs a string that simulates an OpenAI streaming response payload.
-    
-    The returned string contains three OpenAI-style `data:` blocks: a first chunk with content "Hello",
-    a second chunk with content " there" and a `finish_reason` of "stop" (including a `usage` object),
-    and a final `data: [DONE]` marker. Timestamp fields are generated from timezone.now() converted to
-    naive timestamps.
-    
-    Returns:
-        A string containing concatenated `data:` lines representing streaming chunks and a final `[DONE]` marker.
-    """
+def _create_openai_stream_data():
+    """Helper to create OpenAI stream data."""
     return (
         "data: "
         + json.dumps(
@@ -64,73 +55,80 @@ def build_openai_stream():
     )
 
 
+def _create_mock_openai_route(with_delays: bool = False, delay_seconds: float = 1.0):
+    """Create a mock OpenAI stream route with optional delays."""
+    openai_stream = _create_openai_stream_data()
+
+    async def mock_stream():
+        lines = openai_stream.splitlines(keepends=True)
+        for i, line in enumerate(lines):
+            yield line.encode()
+            if with_delays and i == 1:
+                # Delay after second line to trigger keepalive during streaming
+                await asyncio.sleep(delay_seconds)
+
+    return respx.post("https://www.external-ai-service.com/chat/completions").mock(
+        return_value=httpx.Response(200, stream=mock_stream())
+    )
+
+
 @pytest.fixture(name="mock_openai_stream")
 @freeze_time("2025-07-25T10:36:35.297675Z")
 def fixture_mock_openai_stream():
     """
-    Fixture to mock the OpenAI stream response.
+    Fixture to mock the OpenAI stream response (no delays).
 
     See https://platform.openai.com/docs/api-reference/chat-streaming/streaming
     """
-    openai_stream = build_openai_stream()
+    return _create_mock_openai_route(with_delays=False)
 
-    async def mock_stream():
-        """
-        Yield each line of the prepared OpenAI-style streaming payload as encoded bytes.
-        
-        Yields:
-            AsyncGenerator[bytes, None]: Sequential byte chunks for each line in the constructed stream, preserving original line endings.
-        """
-        for line in openai_stream.splitlines(keepends=True):
-            yield line.encode()
 
-    route = respx.post("https://www.external-ai-service.com/chat/completions").mock(
-        return_value=httpx.Response(200, stream=mock_stream())
-    )
+@pytest.fixture(name="mock_openai_stream_slow")
+def fixture_mock_openai_stream_slow():
+    """
+    Fixture to mock the OpenAI stream response with delays to trigger keepalives.
 
-    return route
+    No @freeze_time decorator because asyncio.sleep() needs real time to work properly.
+    """
+    return _create_mock_openai_route(with_delays=True, delay_seconds=1.0)
 
 
 @pytest.fixture(name="mock_openai_stream_with_title_generation")
 @freeze_time("2025-07-25T10:36:35.297675Z")
 def fixture_mock_openai_stream_with_title_generation():
     """
-    Mock pytest fixture that intercepts POST requests to the external chat completions endpoint and returns either a streaming chat response or a non-streaming title-generation response depending on the incoming request.
-    
-    When the request JSON has "stream" set to True, the fixture returns an HTTP streaming response that imitates OpenAI's chat streaming payload; otherwise it returns a non-streaming JSON response containing a generated title and usage metadata.
-    
-    Returns:
-        respx.Route: A configured respx route that intercepts POST requests to
-        "https://www.external-ai-service.com/chat/completions" and replies based on the request body.
+    Fixture to mock the OpenAI stream response.
+
+
+    This fixture handles two different types of API calls made during a single request:
+
+    1. **Conversation (streaming)**: The main chat uses `stream=True` to get real-time
+       token-by-token responses. The API returns chunked data like:
+       `data: {"choices": [{"delta": {"content": "Hello"}}]}`
+
+    2. **Title generation (non-streaming)**: After the conversation, the backend calls
+       the API again with `stream=False` to generate a title. This returns a standard
+       JSON response with the complete message.
+
+    The `handle_request` function inspects each incoming request's body to determine
+    which type of response to return:
+    - `{"stream": true, ...}`  → SSE streaming response
+    - `{"stream": false, ...}` → JSON response with generated title
+    Each call gets a new generator instance (avoiding generator exhaustion)
     """
 
     def create_stream_response():
-        """
-        Create an HTTP response whose body streams encoded lines of an OpenAI-style streaming payload.
-        
-        Returns:
-            httpx.Response: HTTP 200 response with a streaming body that yields encoded bytes for each line of the streaming payload.
-        """
-        openai_stream = build_openai_stream()
+        """Create a fresh streaming response for each call."""
+        openai_stream = _create_openai_stream_data()
 
         async def mock_stream():
-            """
-            Yield encoded byte chunks for each line of the OpenAI stream.
-            
-            Each yielded value is a bytes object containing one line (including its line ending) from the prebuilt OpenAI streaming payload, suitable for use as an HTTP streaming response body.
-            """
             for line in openai_stream.splitlines(keepends=True):
                 yield line.encode()
 
         return httpx.Response(200, stream=mock_stream())
 
     def create_non_stream_response():
-        """
-        Create a non-streaming OpenAI-like chat completion response containing a generated title.
-        
-        Returns:
-            httpx.Response: HTTP 200 response whose JSON payload represents a chat completion with a single assistant message containing the generated title and accompanying metadata (id, model, timestamps, choices, and usage).
-        """
+        """Create a non-streaming response for title generation."""
         return httpx.Response(
             200,
             json={
@@ -153,15 +151,7 @@ def fixture_mock_openai_stream_with_title_generation():
         )
 
     def handle_request(request):
-        """
-        Selects a streaming or non-streaming HTTP response based on the request JSON `stream` flag.
-        
-        Parameters:
-            request (httpx.Request): Incoming request whose JSON body is inspected for the `stream` boolean flag.
-        
-        Returns:
-            httpx.Response: A response that streams the OpenAI-style event lines if `stream` is True, otherwise a non-streaming JSON response.
-        """
+        """Route to streaming or non-streaming response based on request."""
         body = json.loads(request.content)
         if body.get("stream", False):
             return create_stream_response()
@@ -177,14 +167,7 @@ def fixture_mock_openai_stream_with_title_generation():
 @pytest.fixture(name="mock_openai_no_stream")
 @freeze_time("2025-07-25T10:36:35.297675Z")
 def fixture_mock_openai_no_stream():
-    """
-    Create a respx route that returns a fixed, non-streaming OpenAI chat completion response.
-    
-    The mocked response is an HTTP 200 JSON payload representing a completed assistant message (explaining Rayleigh scattering) with associated metadata and usage details.
-    
-    Returns:
-        respx.Route: The configured respx route intercepting POST requests to https://www.external-ai-service.com/chat/completions.
-    """
+    """Fixture to mock the OpenAI response."""
 
     route = respx.post("https://www.external-ai-service.com/chat/completions").mock(
         return_value=httpx.Response(
@@ -498,4 +481,4 @@ def fixture_mock_openai_stream_tool():
         ]
     )
 
-    return route
+    return route

src/backend/chat/tests/views/chat/conversations/test_conversation.py

@@ -3,6 +3,7 @@
 
 import json
 import logging
+from unittest.mock import ANY, patch
 
 from django.utils import timezone
 
@@ -130,6 +131,143 @@ def test_post_conversation_data_protocol(api_client, mock_openai_stream):
 
     assert mock_openai_stream.called
 
+    # ensure instructions are merged as a system prompt
+    last_request_payload = json.loads(respx.calls.last.request.content)
+    assert last_request_payload["messages"][0] == {
+        "content": (
+            "You are a helpful test assistant :)\n\nToday is Friday 25/07/2025.\n\n"
+            "Answer in english."
+        ),
+        "role": "system",
+    }
+
+    chat_conversation.refresh_from_db()
+    assert chat_conversation.ui_messages == [
+        {
+            "content": "Hello",
+            "createdAt": "2025-07-03T15:22:17.105Z",
+            "id": "yuPoOuBkKA4FnKvk",
+            "parts": [{"text": "Hello", "type": "text"}],
+            "role": "user",
+        }
+    ]
+
+    assert len(chat_conversation.messages) == 2
+
+    assert chat_conversation.messages[0].id == IsUUID(4)
+    assert chat_conversation.messages[0] == UIMessage(
+        id=chat_conversation.messages[0].id,  # don't test the message ID here
+        createdAt=timezone.now(),  # Mocked timestamp
+        content="Hello",
+        reasoning=None,
+        experimental_attachments=None,
+        role="user",
+        annotations=None,
+        toolInvocations=None,
+        parts=[TextUIPart(type="text", text="Hello")],
+    )
+
+    assert chat_conversation.messages[1].id == IsUUID(4)
+    assert chat_conversation.messages[1] == UIMessage(
+        id=chat_conversation.messages[1].id,  # don't test the message ID here
+        createdAt=timezone.now(),  # Mocked timestamp
+        content="Hello there",
+        reasoning=None,
+        experimental_attachments=None,
+        role="assistant",
+        annotations=None,
+        toolInvocations=None,
+        parts=[TextUIPart(type="text", text="Hello there")],
+    )
+
+    _run_id = chat_conversation.pydantic_messages[0]["run_id"]
+
+    assert chat_conversation.pydantic_messages == [
+        {
+            "instructions": (
+                "You are a helpful test assistant :)\n\n"
+                "Today is Friday 25/07/2025.\n\nAnswer in english."
+            ),
+            "kind": "request",
+            "parts": [
+                {
+                    "content": ["Hello"],
+                    "part_kind": "user-prompt",
+                    "timestamp": "2025-07-25T10:36:35.297675Z",
+                },
+            ],
+            "run_id": _run_id,
+        },
+        {
+            "finish_reason": "stop",
+            "kind": "response",
+            "model_name": "test-model",
+            "parts": [{"content": "Hello there", "id": None, "part_kind": "text"}],
+            "provider_details": {"finish_reason": "stop"},
+            "provider_name": "openai",
+            "provider_response_id": "chatcmpl-1234567890",
+            "timestamp": "2025-07-25T10:36:35.297675Z",
+            "usage": {
+                "cache_audio_read_tokens": 0,
+                "cache_read_tokens": 0,
+                "cache_write_tokens": 0,
+                "details": {},
+                "input_audio_tokens": 0,
+                "input_tokens": 0,
+                "output_audio_tokens": 0,
+                "output_tokens": 0,
+            },
+            "run_id": _run_id,
+        },
+    ]
+
+
+@freeze_time("2025-07-25T10:36:35.297675Z")
+@respx.mock
+@patch("chat.keepalive.get_current_time")
+def test_post_conversation_data_protocol_triggers_keepalives(
+    mock_time, api_client, mock_openai_stream
+):
+    """Test streaming response contains keepalive messages"""
+    chat_conversation = ChatConversationFactory(owner__language="en-us")
+    mock_time.side_effect = [float(i * 60) for i in range(10)]
+    url = f"/api/v1.0/chats/{chat_conversation.pk}/conversation/?protocol=data"
+    data = {
+        "messages": [
+            {
+                "id": "yuPoOuBkKA4FnKvk",
+                "role": "user",
+                "parts": [{"text": "Hello", "type": "text"}],
+                "content": "Hello",
+                "createdAt": "2025-07-03T15:22:17.105Z",
+            }
+        ]
+    }
+    api_client.force_login(chat_conversation.owner)
+
+    response = api_client.post(url, data, format="json")
+
+    assert response.status_code == status.HTTP_200_OK
+    assert response.get("Content-Type") == "text/event-stream"
+    assert response.get("x-vercel-ai-data-stream") == "v1"
+    assert response.streaming
+
+    # Wait for the streaming content to be fully received
+    response_content = b"".join(response.streaming_content).decode("utf-8")
+
+    # Replace UUIDs with placeholders for assertion
+    response_content = replace_uuids_with_placeholder(response_content)
+
+    assert response_content == (
+        '0:"Hello"\n'
+        '0:" there"\n'
+        'f:{"messageId":"<mocked_uuid>"}\n'
+        'd:{"finishReason":"stop","usage":{"promptTokens":0,"completionTokens":0}}\n'
+        '2:[{"status": "WAITING"}]\n'
+    )
+
+    assert mock_openai_stream.called
+
     chat_conversation.refresh_from_db()
     assert chat_conversation.ui_messages == [
         {
@@ -172,27 +310,13 @@ def test_post_conversation_data_protocol(api_client, mock_openai_stream):
     _run_id = chat_conversation.pydantic_messages[0]["run_id"]
     assert chat_conversation.pydantic_messages == [
         {
-            "instructions": None,
+            "instructions": (
+                "You are a helpful test assistant :)\n\n"
+                "Today is Friday 25/07/2025.\n\n"
+                "Answer in english."
+            ),
             "kind": "request",
             "parts": [
-                {
-                    "content": "You are a helpful test assistant :)",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-07-25T10:36:35.297675Z",
-                },
-                {
-                    "content": "Today is Friday 25/07/2025.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-07-25T10:36:35.297675Z",
-                },
-                {
-                    "content": "Answer in english.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-07-25T10:36:35.297675Z",
-                },
                 {
                     "content": ["Hello"],
                     "part_kind": "user-prompt",
@@ -255,6 +379,15 @@ def test_post_conversation_text_protocol(api_client, mock_openai_stream):
     assert response_content == "Hello there"
 
     assert mock_openai_stream.called
+    # ensure instructions are merged as a system prompt
+    last_request_payload = json.loads(respx.calls.last.request.content)
+    assert last_request_payload["messages"][0] == {
+        "content": (
+            "You are a helpful test assistant :)\n\nToday is Friday 25/07/2025.\n\n"
+            "Answer in english."
+        ),
+        "role": "system",
+    }
 
     chat_conversation.refresh_from_db()
     assert chat_conversation.ui_messages == [
@@ -296,29 +429,15 @@ def test_post_conversation_text_protocol(api_client, mock_openai_stream):
     )
 
     _run_id = chat_conversation.pydantic_messages[0]["run_id"]
+
     assert chat_conversation.pydantic_messages == [
         {
-            "instructions": None,
+            "instructions": (
+                "You are a helpful test assistant :)\n\n"
+                "Today is Friday 25/07/2025.\n\nAnswer in english."
+            ),
             "kind": "request",
             "parts": [
-                {
-                    "content": "You are a helpful test assistant :)",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-07-25T10:36:35.297675Z",
-                },
-                {
-                    "content": "Today is Friday 25/07/2025.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-07-25T10:36:35.297675Z",
-                },
-                {
-                    "content": "Answer in english.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-07-25T10:36:35.297675Z",
-                },
                 {
                     "content": ["Hello"],
                     "part_kind": "user-prompt",
@@ -409,11 +528,12 @@ def test_post_conversation_with_image(api_client, mock_openai_stream_image):
     # Check the exact structure expected by the AI service
     assert body["messages"] == [
         {
-            "content": "You are a helpful test assistant :)",
+            "content": (
+                "You are a helpful test assistant :)\n\nToday is Friday 25/07/2025."
+                "\n\nAnswer in english."
+            ),
             "role": "system",
         },
-        {"content": "Today is Friday 25/07/2025.", "role": "system"},
-        {"content": "Answer in english.", "role": "system"},
         {
             "content": [
                 {"text": "Hello, what do you see on this picture?", "type": "text"},
@@ -498,27 +618,12 @@ def test_post_conversation_with_image(api_client, mock_openai_stream_image):
     _run_id = chat_conversation.pydantic_messages[0]["run_id"]
     assert chat_conversation.pydantic_messages == [
         {
-            "instructions": None,
+            "instructions": (
+                "You are a helpful test assistant :)\n\n"
+                "Today is Friday 25/07/2025.\n\nAnswer in english."
+            ),
             "kind": "request",
             "parts": [
-                {
-                    "content": "You are a helpful test assistant :)",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-07-25T10:36:35.297675Z",
-                },
-                {
-                    "content": "Today is Friday 25/07/2025.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-07-25T10:36:35.297675Z",
-                },
-                {
-                    "content": "Answer in english.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-07-25T10:36:35.297675Z",
-                },
                 {
                     "content": [
                         "Hello, what do you see on this picture?",
@@ -616,11 +721,12 @@ def test_post_conversation_tool_call(api_client, mock_openai_stream_tool, settin
 
     assert body["messages"] == [
         {
-            "content": "You are a helpful test assistant :)",
+            "content": (
+                "You are a helpful test assistant :)\n\n"
+                "Today is Friday 25/07/2025.\n\nAnswer in english."
+            ),
             "role": "system",
         },
-        {"content": "Today is Friday 25/07/2025.", "role": "system"},
-        {"content": "Answer in english.", "role": "system"},
         {"content": [{"text": "Weather in Paris?", "type": "text"}], "role": "user"},
     ]
 
@@ -678,27 +784,12 @@ def test_post_conversation_tool_call(api_client, mock_openai_stream_tool, settin
     _run_id = chat_conversation.pydantic_messages[0]["run_id"]
     assert chat_conversation.pydantic_messages == [
         {
-            "instructions": None,
+            "instructions": (
+                "You are a helpful test assistant :)\n\n"
+                "Today is Friday 25/07/2025.\n\nAnswer in english."
+            ),
             "kind": "request",
             "parts": [
-                {
-                    "content": "You are a helpful test assistant :)",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-07-25T10:36:35.297675Z",
-                },
-                {
-                    "content": "Today is Friday 25/07/2025.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-07-25T10:36:35.297675Z",
-                },
-                {
-                    "content": "Answer in english.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-07-25T10:36:35.297675Z",
-                },
                 {
                     "content": ["Weather in Paris?"],
                     "part_kind": "user-prompt",
@@ -737,7 +828,10 @@ def test_post_conversation_tool_call(api_client, mock_openai_stream_tool, settin
             "run_id": _run_id,
         },
         {
-            "instructions": None,
+            "instructions": (
+                "You are a helpful test assistant :)\n\n"
+                "Today is Friday 25/07/2025.\n\nAnswer in english."
+            ),
             "kind": "request",
             "parts": [
                 {
@@ -829,11 +923,12 @@ def test_post_conversation_tool_call_fails(api_client, mock_openai_stream_tool,
 
     assert body["messages"] == [
         {
-            "content": "You are a helpful test assistant :)",
+            "content": (
+                "You are a helpful test assistant :)\n\n"
+                "Today is Friday 25/07/2025.\n\nAnswer in french."
+            ),
             "role": "system",
         },
-        {"content": "Today is Friday 25/07/2025.", "role": "system"},
-        {"content": "Answer in french.", "role": "system"},
         {"content": [{"text": "Weather in Paris?", "type": "text"}], "role": "user"},
     ]
 
@@ -891,27 +986,12 @@ def test_post_conversation_tool_call_fails(api_client, mock_openai_stream_tool,
     _run_id = chat_conversation.pydantic_messages[0]["run_id"]
     assert chat_conversation.pydantic_messages == [
         {
-            "instructions": None,
+            "instructions": (
+                "You are a helpful test assistant :)\n\n"
+                "Today is Friday 25/07/2025.\n\nAnswer in french."
+            ),
             "kind": "request",
             "parts": [
-                {
-                    "content": "You are a helpful test assistant :)",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-07-25T10:36:35.297675Z",
-                },
-                {
-                    "content": "Today is Friday 25/07/2025.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-07-25T10:36:35.297675Z",
-                },
-                {
-                    "content": "Answer in french.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-07-25T10:36:35.297675Z",
-                },
                 {
                     "content": ["Weather in Paris?"],
                     "part_kind": "user-prompt",
@@ -950,7 +1030,10 @@ def test_post_conversation_tool_call_fails(api_client, mock_openai_stream_tool,
             "run_id": _run_id,
         },
         {
-            "instructions": None,
+            "instructions": (
+                "You are a helpful test assistant :)\n\n"
+                "Today is Friday 25/07/2025.\n\nAnswer in french."
+            ),
             "kind": "request",
             "parts": [
                 {
@@ -1214,27 +1297,11 @@ def test_post_conversation_data_protocol_no_stream(
     _run_id = chat_conversation.pydantic_messages[0]["run_id"]
     assert chat_conversation.pydantic_messages == [
         {
-            "instructions": None,
+            "instructions": (
+                "You are an amazing assistant.\n\nToday is Friday 25/07/2025.\n\nAnswer in english."
+            ),
             "kind": "request",
             "parts": [
-                {
-                    "content": "You are an amazing assistant.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-07-25T10:36:35.297675Z",
-                },
-                {
-                    "content": "Today is Friday 25/07/2025.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-07-25T10:36:35.297675Z",
-                },
-                {
-                    "content": "Answer in english.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-07-25T10:36:35.297675Z",
-                },
                 {
                     "content": ["Why the sky is blue?"],
                     "part_kind": "user-prompt",
@@ -1369,27 +1436,12 @@ async def test_post_conversation_async(api_client, mock_openai_stream, monkeypat
     _run_id = chat_conversation.pydantic_messages[0]["run_id"]
     assert chat_conversation.pydantic_messages == [
         {
-            "instructions": None,
+            "instructions": (
+                "You are a helpful test assistant :)\n\n"
+                "Today is Friday 25/07/2025.\n\nAnswer in english."
+            ),
             "kind": "request",
             "parts": [
-                {
-                    "content": "You are a helpful test assistant :)",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-07-25T10:36:35.297675Z",
-                },
-                {
-                    "content": "Today is Friday 25/07/2025.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-07-25T10:36:35.297675Z",
-                },
-                {
-                    "content": "Answer in english.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-07-25T10:36:35.297675Z",
-                },
                 {
                     "content": ["Hello"],
                     "part_kind": "user-prompt",
@@ -1420,3 +1472,143 @@ async def test_post_conversation_async(api_client, mock_openai_stream, monkeypat
             "run_id": _run_id,
         },
     ]
+
+
+@freeze_time("2025-07-25T10:36:35.297675Z", tick=True)
+@respx.mock
+@pytest.mark.asyncio
+async def test_post_conversation_async_triggers_keepalive(
+    api_client, mock_openai_stream_slow, monkeypatch, caplog, settings
+):
+    """Test posting messages to a conversation using the 'data' protocol."""
+    monkeypatch.setenv("PYTHON_SERVER_MODE", "async")
+
+    settings.KEEPALIVE_INTERVAL = 1  # s
+
+    chat_conversation = await sync_to_async(ChatConversationFactory)(owner__language="en-us")
+
+    url = f"/api/v1.0/chats/{chat_conversation.pk}/conversation/?protocol=data"
+    data = {
+        "messages": [
+            {
+                "id": "yuPoOuBkKA4FnKvk",
+                "role": "user",
+                "parts": [{"text": "Hello", "type": "text"}],
+                "content": "Hello",
+                "createdAt": "2025-07-03T15:22:17.105Z",
+            }
+        ]
+    }
+    await api_client.aforce_login(chat_conversation.owner)
+
+    caplog.clear()
+    caplog.set_level(level=logging.DEBUG, logger="chat.views")
+
+    response = await sync_to_async(api_client.post)(url, data, format="json")  # client is sync
+
+    assert response.status_code == status.HTTP_200_OK
+    assert response.get("Content-Type") == "text/event-stream"
+    assert response.get("x-vercel-ai-data-stream") == "v1"
+    assert response.streaming
+
+    assert "Using ASYNC streaming for chat conversation" in caplog.text
+
+    # Wait for the streaming content to be fully received => async iterator -> list
+    # This fails it the streaming is not an async generator
+    response_content = b"".join([content async for content in response.streaming_content]).decode(
+        "utf-8"
+    )
+
+    # Replace UUIDs with placeholders for assertion
+    response_content = replace_uuids_with_placeholder(response_content)
+
+    assert response_content == (
+        '0:"Hello"\n'
+        '2:[{"status": "WAITING"}]\n'
+        '0:" there"\n'
+        'f:{"messageId":"<mocked_uuid>"}\n'
+        'd:{"finishReason":"stop","usage":{"promptTokens":0,"completionTokens":0}}\n'
+    )
+
+    assert mock_openai_stream_slow.called
+
+    await chat_conversation.arefresh_from_db()
+    assert chat_conversation.ui_messages == [
+        {
+            "content": "Hello",
+            "createdAt": "2025-07-03T15:22:17.105Z",
+            "id": "yuPoOuBkKA4FnKvk",
+            "parts": [{"text": "Hello", "type": "text"}],
+            "role": "user",
+        }
+    ]
+
+    assert len(chat_conversation.messages) == 2
+
+    assert chat_conversation.messages[0].id == IsUUID(4)
+    assert chat_conversation.messages[0] == UIMessage(
+        id=chat_conversation.messages[0].id,  # don't test the message ID here
+        createdAt=chat_conversation.messages[0].createdAt,  # Mocked timestamp
+        content="Hello",
+        reasoning=None,
+        experimental_attachments=None,
+        role="user",
+        annotations=None,
+        toolInvocations=None,
+        parts=[TextUIPart(type="text", text="Hello")],
+    )
+
+    assert chat_conversation.messages[1].id == IsUUID(4)
+    assert chat_conversation.messages[1] == UIMessage(
+        id=chat_conversation.messages[1].id,  # don't test the message ID here
+        createdAt=chat_conversation.messages[1].createdAt,  # Mocked timestamp
+        content="Hello there",
+        reasoning=None,
+        experimental_attachments=None,
+        role="assistant",
+        annotations=None,
+        toolInvocations=None,
+        parts=[TextUIPart(type="text", text="Hello there")],
+    )
+
+    _run_id = chat_conversation.pydantic_messages[0]["run_id"]
+
+    # using ANY because time is not frozen in this api mock
+    assert chat_conversation.pydantic_messages == [
+        {
+            "instructions": (
+                "You are a helpful test assistant :)\n\n"
+                "Today is Friday 25/07/2025.\n\nAnswer in english."
+            ),
+            "kind": "request",
+            "parts": [
+                {
+                    "content": ["Hello"],
+                    "part_kind": "user-prompt",
+                    "timestamp": ANY,
+                },
+            ],
+            "run_id": _run_id,
+        },
+        {
+            "finish_reason": "stop",
+            "kind": "response",
+            "model_name": "test-model",
+            "parts": [{"content": "Hello there", "id": None, "part_kind": "text"}],
+            "provider_details": {"finish_reason": "stop"},
+            "provider_name": "openai",
+            "provider_response_id": "chatcmpl-1234567890",
+            "timestamp": ANY,
+            "usage": {
+                "cache_audio_read_tokens": 0,
+                "cache_read_tokens": 0,
+                "cache_write_tokens": 0,
+                "details": {},
+                "input_audio_tokens": 0,
+                "input_tokens": 0,
+                "output_audio_tokens": 0,
+                "output_tokens": 0,
+            },
+            "run_id": _run_id,
+        },
+    ]

src/backend/chat/tests/views/chat/conversations/test_conversation_with_document_upload.py

@@ -8,6 +8,7 @@ import logging
 from io import BytesIO
 from unittest import mock
 
+from django.contrib.sessions.backends.cache import SessionStore
 from django.utils import formats, timezone
 
 import httpx
@@ -41,28 +42,49 @@ from chat.tests.utils import replace_uuids_with_placeholder
 pytestmark = pytest.mark.django_db(transaction=True)
 
 
-@pytest.fixture(autouse=True)
-def ai_settings(settings):
+@pytest.fixture(
+    autouse=True,
+    params=[
+        "chat.agent_rag.document_rag_backends.find_rag_backend.FindRagBackend",
+        "chat.agent_rag.document_rag_backends.albert_rag_backend.AlbertRagBackend",
+    ],
+)
+def ai_settings(request, settings):
     """Fixture to set AI service URLs for testing."""
-    settings.AI_BASE_URL = "https://www.external-ai-service.com/"
-    settings.AI_API_KEY = "test-api-key"
-    settings.AI_MODEL = "test-model"
-    settings.AI_AGENT_INSTRUCTIONS = "You are a helpful test assistant :)"
 
-    # Enable Albert API for document search
-    settings.RAG_DOCUMENT_SEARCH_BACKEND = (
-        "chat.agent_rag.document_rag_backends.albert_rag_backend.AlbertRagBackend"
-    )
-    settings.ALBERT_API_URL = "https://albert.api.etalab.gouv.fr"
-    settings.ALBERT_API_KEY = "albert-api-key"
+    # enable on rag document search tool
+    settings.RAG_DOCUMENT_SEARCH_BACKEND = request.param
     settings.RAG_WEB_SEARCH_PROMPT_UPDATE = (
         "Based on the following document contents:\n\n{search_results}\n\n"
         "Please answer the user's question: {user_prompt}"
     )
 
+    settings.AI_BASE_URL = "https://www.external-ai-service.com/"
+    settings.AI_API_KEY = "test-api-key"
+    settings.AI_MODEL = "test-model"
+    settings.AI_AGENT_INSTRUCTIONS = "You are a helpful test assistant :)"
+
+    # Albert API settings
+    settings.ALBERT_API_URL = "https://albert.api.etalab.gouv.fr"
+    settings.ALBERT_API_KEY = "albert-api-key"
+
+    # Find API settings
+    settings.FIND_API_URL = "https://find.api.example.com"
+    settings.FIND_API_KEY = "find-api-key"
+
     return settings
 
 
+@pytest.fixture(autouse=True)
+def mock_refresh_access_token():
+    """Mock refresh_access_token to bypass token refresh in tests."""
+    with mock.patch("utils.oidc.refresh_access_token") as mocked_refresh_access_token:
+        session = SessionStore()
+        session["oidc_access_token"] = "mocked-access-token"
+        mocked_refresh_access_token.return_value = session
+        yield mocked_refresh_access_token
+
+
 @pytest.fixture(name="sample_pdf_content")
 def fixture_sample_pdf_content():
     """Create a dummy PDF content as BytesIO."""
@@ -81,10 +103,18 @@ def fixture_sample_pdf_content():
     return BytesIO(pdf_data)
 
 
-@pytest.fixture(name="mock_albert_api")
-def fixture_mock_albert_api():
+@pytest.fixture(name="mock_document_api")
+def fixture_mock_document_api():
     """Fixture to mock the Albert API endpoints."""
     # Mock collection creation
+
+    document_name = "sample.pdf"
+    document_content = "This is the content of the PDF."
+    prompt_tokens = 10
+    completion_tokens = 20
+    search_method = "semantic"
+    search_score = 0.9
+
     responses.post(
         "https://albert.api.etalab.gouv.fr/v1/collections",
         json={"id": "123", "name": "test-collection"},
@@ -101,7 +131,7 @@ def fixture_mock_albert_api():
                     "metadata": {"document_name": "sample.pdf"},
                 }
             ],
-            "usage": {"prompt_tokens": 10, "completion_tokens": 20},
+            "usage": {"prompt_tokens": prompt_tokens, "completion_tokens": completion_tokens},
         },
         status=status.HTTP_200_OK,
     )
@@ -119,20 +149,42 @@ def fixture_mock_albert_api():
         json={
             "data": [
                 {
-                    "method": "semantic",
+                    "method": search_method,
                     "chunk": {
                         "id": 123,
-                        "content": "This is the content of the PDF.",
-                        "metadata": {"document_name": "sample.pdf"},
+                        "content": document_content,
+                        "metadata": {"document_name": document_name},
                     },
-                    "score": 0.9,
+                    "score": search_score,
                 }
             ],
-            "usage": {"prompt_tokens": 10, "completion_tokens": 20},
+            "usage": {"prompt_tokens": prompt_tokens, "completion_tokens": completion_tokens},
         },
         status=status.HTTP_200_OK,
     )
 
+    # Mock document indexing (Find API)
+    responses.post(
+        "https://find.api.example.com/api/v1.0/documents/index/",
+        json={"id": "456", "status": "indexed"},
+        status=status.HTTP_200_OK,
+    )
+
+    # Mock document search (Find API)
+    responses.post(
+        "https://find.api.example.com/api/v1.0/documents/search/",
+        json=[
+            {
+                "_source": {
+                    "title.fr": document_name,
+                    "content.fr": document_content,
+                },
+                "_score": search_score,
+            }
+        ],
+        status=status.HTTP_200_OK,
+    )
+
 
 @pytest.fixture(name="mock_summarization_agent")
 def fixture_mock_summarization_agent():
@@ -216,9 +268,10 @@ def fixture_mock_openai_stream():
 @responses.activate
 @respx.mock
 @freeze_time()
-def test_post_conversation_with_document_upload(  # pylint: disable=too-many-arguments,too-many-positional-arguments
+def test_post_conversation_with_document_upload(
+    # pylint: disable=too-many-arguments,too-many-positional-arguments
     api_client,
-    mock_albert_api,  # pylint: disable=unused-argument
+    mock_document_api,  # pylint: disable=unused-argument
     sample_pdf_content,
     today_promt_date,
     mock_ai_agent_service,
@@ -353,53 +406,25 @@ def test_post_conversation_with_document_upload(  # pylint: disable=too-many-arg
     assert len(chat_conversation.pydantic_messages) == 4
 
     _run_id = chat_conversation.pydantic_messages[0]["run_id"]
+
     assert chat_conversation.pydantic_messages[0] == {
-        "instructions": "When you receive a result from the summarization tool, you "
-        "MUST return it directly to the user without any "
-        "modification, paraphrasing, or additional summarization.The "
-        "tool already produces optimized summaries that should be "
-        "presented verbatim.You may translate the summary if "
-        "required, but you MUST preserve all the information from the "
-        "original summary.You may add a follow-up question after the "
-        "summary if needed.",
+        "instructions": "You are a helpful test assistant :)\n\n"
+        f"{today_promt_date}\n\n"
+        "Answer in english.\n\n"
+        "Use document_search_rag ONLY to retrieve specific passages from "
+        "attached documents. Do NOT use it to summarize; for summaries, "
+        "call the summarize tool instead.\n\nWhen you receive a result from the "
+        "summarization tool, you MUST return it directly to the user without "
+        "any modification, paraphrasing, or additional summarization."
+        "The tool already produces optimized summaries that should be "
+        "presented verbatim.You may translate the summary if required, "
+        "but you MUST preserve all the information from the original summary."
+        "You may add a follow-up question after the summary if needed.\n\n"
+        "[Internal context] User documents are attached to this conversation. "
+        "Do not request re-upload of documents; consider them already "
+        "available via the internal store.",
         "kind": "request",
         "parts": [
-            {
-                "content": "You are a helpful test assistant :)",
-                "dynamic_ref": None,
-                "part_kind": "system-prompt",
-                "timestamp": timezone_now,
-            },
-            {
-                "content": today_promt_date,
-                "dynamic_ref": None,
-                "part_kind": "system-prompt",
-                "timestamp": timezone_now,
-            },
-            {
-                "content": "Answer in english.",
-                "dynamic_ref": None,
-                "part_kind": "system-prompt",
-                "timestamp": timezone_now,
-            },
-            {
-                "content": "Use document_search_rag ONLY to retrieve specific "
-                "passages from attached documents. Do NOT use it to "
-                "summarize; for summaries, call the summarize tool "
-                "instead.",
-                "dynamic_ref": None,
-                "part_kind": "system-prompt",
-                "timestamp": timezone_now,
-            },
-            {
-                "content": "[Internal context] User documents are attached to this "
-                "conversation. Do not request re-upload of documents; "
-                "consider them already available via the internal "
-                "store.",
-                "dynamic_ref": None,
-                "part_kind": "system-prompt",
-                "timestamp": timezone_now,
-            },
             {
                 "content": ["What does the document say?"],
                 "part_kind": "user-prompt",
@@ -439,14 +464,21 @@ def test_post_conversation_with_document_upload(  # pylint: disable=too-many-arg
     }
     assert chat_conversation.pydantic_messages[2] == {
         "instructions": (
-            "When you receive a result from the summarization tool, you MUST "
-            "return it directly to the user without any modification, "
-            "paraphrasing, or additional summarization."
-            "The tool already produces optimized summaries that should "
-            "be presented verbatim."
-            "You may translate the summary if required, but you MUST preserve "
-            "all the information from the original summary."
-            "You may add a follow-up question after the summary if needed."
+            "You are a helpful test assistant :)\n\n"
+            f"{today_promt_date}\n\n"
+            "Answer in english.\n\n"
+            "Use document_search_rag ONLY to retrieve specific passages from "
+            "attached documents. Do NOT use it to summarize; for summaries, "
+            "call the summarize tool instead.\n\nWhen you receive a result from the "
+            "summarization tool, you MUST return it directly to the user without "
+            "any modification, paraphrasing, or additional summarization."
+            "The tool already produces optimized summaries that should be "
+            "presented verbatim.You may translate the summary if required, "
+            "but you MUST preserve all the information from the original summary."
+            "You may add a follow-up question after the summary if needed.\n\n"
+            "[Internal context] User documents are attached to this conversation. "
+            "Do not request re-upload of documents; consider them already "
+            "available via the internal store."
         ),
         "kind": "request",
         "parts": [
@@ -499,7 +531,8 @@ def test_post_conversation_with_document_upload(  # pylint: disable=too-many-arg
 @responses.activate
 @respx.mock
 @freeze_time("2025-07-25T10:36:35.297675Z")
-def test_post_conversation_with_document_upload_feature_disabled(  # pylint: disable=too-many-arguments,too-many-positional-arguments
+def test_post_conversation_with_document_upload_feature_disabled(
+    # pylint: disable=too-many-arguments,too-many-positional-arguments
     api_client,
     caplog,
     mock_openai_stream,  # pylint: disable=unused-argument
@@ -552,14 +585,12 @@ def test_post_conversation_with_document_upload_feature_disabled(  # pylint: dis
 
     # Replace UUIDs with placeholders for assertion
     response_content = replace_uuids_with_placeholder(response_content)
-
     assert response_content == (
         '0:"From the document, I can see that "\n'
         "0:\"it says 'Hello PDF'.\"\n"
         'f:{"messageId":"<mocked_uuid>"}\n'
         'd:{"finishReason":"stop","usage":{"promptTokens":150,"completionTokens":25}}\n'
     )
-
     # This behavior must be improved in the future to inform the user properly
     assert "Document upload feature is disabled, ignoring input documents." in caplog.text
 
@@ -569,7 +600,7 @@ def test_post_conversation_with_document_upload_feature_disabled(  # pylint: dis
 @freeze_time()
 def test_post_conversation_with_document_upload_summarize(  # pylint: disable=too-many-arguments,too-many-positional-arguments  # noqa: PLR0913
     api_client,
-    mock_albert_api,  # pylint: disable=unused-argument
+    mock_document_api,  # pylint: disable=unused-argument
     sample_pdf_content,
     today_promt_date,
     mock_ai_agent_service,
@@ -582,6 +613,7 @@ def test_post_conversation_with_document_upload_summarize(  # pylint: disable=to
     api_client.force_authenticate(user=chat_conversation.owner)
 
     pdf_base64 = base64.b64encode(sample_pdf_content.read()).decode("utf-8")
+
     message = UIMessage(
         id="1",
         role="user",
@@ -643,7 +675,7 @@ def test_post_conversation_with_document_upload_summarize(  # pylint: disable=to
         'document discusses various topics."}\n'
         '0:"The document discusses various topics."\n'
         'f:{"messageId":"<mocked_uuid>"}\n'
-        'd:{"finishReason":"stop","usage":{"promptTokens":317,"completionTokens":19}}\n'
+        'd:{"finishReason":"stop","usage":{"promptTokens":287,"completionTokens":19}}\n'
     )
 
     # Check that the conversation was updated
@@ -705,52 +737,25 @@ def test_post_conversation_with_document_upload_summarize(  # pylint: disable=to
 
     _run_id = chat_conversation.pydantic_messages[0]["run_id"]
     assert chat_conversation.pydantic_messages[0] == {
-        "instructions": "When you receive a result from the summarization tool, you "
-        "MUST return it directly to the user without any "
-        "modification, paraphrasing, or additional summarization.The "
-        "tool already produces optimized summaries that should be "
-        "presented verbatim.You may translate the summary if "
-        "required, but you MUST preserve all the information from the "
-        "original summary.You may add a follow-up question after the "
-        "summary if needed.",
+        "instructions": (
+            "You are a helpful test assistant :)\n\n"
+            f"{today_promt_date}\n\n"
+            "Answer in english.\n\n"
+            "Use document_search_rag ONLY to retrieve specific passages from "
+            "attached documents. Do NOT use it to summarize; for summaries, "
+            "call the summarize tool instead.\n\nWhen you receive a result from the "
+            "summarization tool, you MUST return it directly to the user without "
+            "any modification, paraphrasing, or additional summarization."
+            "The tool already produces optimized summaries that should be "
+            "presented verbatim.You may translate the summary if required, "
+            "but you MUST preserve all the information from the original summary."
+            "You may add a follow-up question after the summary if needed.\n\n"
+            "[Internal context] User documents are attached to this conversation. "
+            "Do not request re-upload of documents; consider them already "
+            "available via the internal store."
+        ),
         "kind": "request",
         "parts": [
-            {
-                "content": "You are a helpful test assistant :)",
-                "dynamic_ref": None,
-                "part_kind": "system-prompt",
-                "timestamp": timezone_now,
-            },
-            {
-                "content": today_promt_date,
-                "dynamic_ref": None,
-                "part_kind": "system-prompt",
-                "timestamp": timezone_now,
-            },
-            {
-                "content": "Answer in english.",
-                "dynamic_ref": None,
-                "part_kind": "system-prompt",
-                "timestamp": timezone_now,
-            },
-            {
-                "content": "Use document_search_rag ONLY to retrieve specific "
-                "passages from attached documents. Do NOT use it to "
-                "summarize; for summaries, call the summarize tool "
-                "instead.",
-                "dynamic_ref": None,
-                "part_kind": "system-prompt",
-                "timestamp": timezone_now,
-            },
-            {
-                "content": "[Internal context] User documents are attached to this "
-                "conversation. Do not request re-upload of documents; "
-                "consider them already available via the internal "
-                "store.",
-                "dynamic_ref": None,
-                "part_kind": "system-prompt",
-                "timestamp": timezone_now,
-            },
             {
                 "content": ["Make a summary of this document."],
                 "part_kind": "user-prompt",
@@ -790,14 +795,21 @@ def test_post_conversation_with_document_upload_summarize(  # pylint: disable=to
     }
     assert chat_conversation.pydantic_messages[2] == {
         "instructions": (
-            "When you receive a result from the summarization tool, you MUST "
-            "return it directly to the user without any modification, "
-            "paraphrasing, or additional summarization."
-            "The tool already produces optimized summaries that should "
-            "be presented verbatim."
-            "You may translate the summary if required, but you MUST preserve "
-            "all the information from the original summary."
-            "You may add a follow-up question after the summary if needed."
+            "You are a helpful test assistant :)\n\n"
+            f"{today_promt_date}\n\n"
+            "Answer in english.\n\n"
+            "Use document_search_rag ONLY to retrieve specific passages from "
+            "attached documents. Do NOT use it to summarize; for summaries, "
+            "call the summarize tool instead.\n\nWhen you receive a result from the "
+            "summarization tool, you MUST return it directly to the user without "
+            "any modification, paraphrasing, or additional summarization."
+            "The tool already produces optimized summaries that should be "
+            "presented verbatim.You may translate the summary if required, "
+            "but you MUST preserve all the information from the original summary."
+            "You may add a follow-up question after the summary if needed.\n\n"
+            "[Internal context] User documents are attached to this conversation. "
+            "Do not request re-upload of documents; consider them already "
+            "available via the internal store."
         ),
         "kind": "request",
         "parts": [

src/backend/chat/tests/views/chat/conversations/test_conversation_with_document_url.py

@@ -17,7 +17,6 @@ from pydantic_ai.messages import (
     DocumentUrl,
     ModelMessage,
     ModelResponse,
-    SystemPromptPart,
     TextPart,
     UserPromptPart,
 )
@@ -38,11 +37,19 @@ from chat.tests.utils import replace_uuids_with_placeholder
 pytestmark = pytest.mark.django_db(transaction=True)
 
 
-@pytest.fixture(autouse=True)
-def ai_settings(settings):
+@pytest.fixture(
+    autouse=True,
+    params=[
+        "chat.agent_rag.document_rag_backends.find_rag_backend.FindRagBackend",
+        "chat.agent_rag.document_rag_backends.albert_rag_backend.AlbertRagBackend",
+    ],
+)
+def ai_settings(request, settings):
     """Fixture to set AI service URLs for testing."""
+    settings.RAG_DOCUMENT_SEARCH_BACKEND = request.param
     settings.AI_BASE_URL = "https://www.external-ai-service.com/"
     settings.AI_API_KEY = "test-api-key"
+    settings.FIND_API_KEY = "find-api-key"
     settings.AI_MODEL = "test-model"
     settings.AI_AGENT_INSTRUCTIONS = "You are a helpful test assistant :)"
     return settings
@@ -61,7 +68,8 @@ def fixture_sample_document_content():
 
 @responses.activate
 @freeze_time()
-def test_post_conversation_with_local_pdf_document_url(  # pylint: disable=too-many-arguments,too-many-positional-arguments
+def test_post_conversation_with_local_pdf_document_url(
+    # pylint: disable=too-many-arguments,too-many-positional-arguments
     api_client,
     sample_document_content,
     today_promt_date,
@@ -85,6 +93,10 @@ def test_post_conversation_with_local_pdf_document_url(  # pylint: disable=too-m
         json={"id": "document_id", "object": "document"},
         status=200,
     )
+    responses.post(
+        "https://app-find/api/v1.0/documents/index/",
+        status=200,
+    )
 
     chat_conversation = ChatConversationFactory(owner__language="en-us")
     api_client.force_authenticate(user=chat_conversation.owner)
@@ -120,32 +132,28 @@ def test_post_conversation_with_local_pdf_document_url(  # pylint: disable=too-m
     )
 
     async def agent_model(messages: list[ModelMessage], _info: AgentInfo):
-        presigned_url = messages[0].parts[3].content[1].url
-        assert presigned_url.startswith("http://localhost:9000/conversations-media-storage/")
-        assert presigned_url.find("X-Amz-Signature=") != -1
-        assert presigned_url.find("X-Amz-Date=") != -1
-        assert presigned_url.find("X-Amz-Expires=") != -1
-
         assert messages == [
             ModelRequest(
                 parts=[
-                    SystemPromptPart(
-                        content="You are a helpful test assistant :)", timestamp=timezone.now()
-                    ),
-                    SystemPromptPart(content=today_promt_date, timestamp=timezone.now()),
-                    SystemPromptPart(content="Answer in english.", timestamp=timezone.now()),
-                    UserPromptPart(
-                        content=[
-                            "What is in this document?",
-                            DocumentUrl(
-                                url=presigned_url,  # presigned URL for this conversation
-                                media_type="application/pdf",
-                                identifier="sample.pdf",
-                            ),
-                        ],
-                        timestamp=timezone.now(),
-                    ),
+                    UserPromptPart(content=["What is in this document?"], timestamp=timezone.now())
                 ],
+                instructions=(
+                    "You are a helpful test assistant :)\n\n"
+                    f"{today_promt_date}\n\n"
+                    "Answer in english.\n\n"
+                    "Use document_search_rag ONLY to retrieve specific passages from attached "
+                    "documents. Do NOT use it to summarize; for summaries, call the summarize "
+                    "tool instead.\n\nWhen you receive a result from the summarization tool, "
+                    "you MUST return it directly to the user without any modification, "
+                    "paraphrasing, or additional summarization.The tool already produces "
+                    "optimized summaries that should be presented verbatim.You may translate "
+                    "the summary if required, but you MUST preserve all the information from "
+                    "the original summary.You may add a follow-up question after the summary "
+                    "if needed.\n\n"
+                    "[Internal context] User documents are attached to this conversation. "
+                    "Do not request re-upload of documents; consider them already available "
+                    "via the internal store."
+                ),
                 run_id=messages[0].run_id,
             )
         ]
@@ -189,9 +197,7 @@ def test_post_conversation_with_local_pdf_document_url(  # pylint: disable=too-m
         createdAt=timezone.now(),
         content="What is in this document?",
         reasoning=None,
-        experimental_attachments=[
-            Attachment(name="sample.pdf", contentType="application/pdf", url=document_url)
-        ],
+        experimental_attachments=None,  # We should fix this, but for now document appears in source
         role="user",
         annotations=None,
         toolInvocations=None,
@@ -221,38 +227,31 @@ def test_post_conversation_with_local_pdf_document_url(  # pylint: disable=too-m
     _run_id = chat_conversation.pydantic_messages[0]["run_id"]
     assert chat_conversation.pydantic_messages == [
         {
-            "instructions": None,
+            "instructions": "You are a helpful test assistant :)\n\n"
+            f"{today_promt_date}\n\n"
+            "Answer in english.\n"
+            "\n"
+            "Use document_search_rag ONLY to retrieve specific passages "
+            "from attached documents. Do NOT use it to summarize; for "
+            "summaries, call the summarize tool instead.\n"
+            "\n"
+            "When you receive a result from the summarization tool, you "
+            "MUST return it directly to the user without any "
+            "modification, paraphrasing, or additional summarization.The "
+            "tool already produces optimized summaries that should be "
+            "presented verbatim.You may translate the summary if "
+            "required, but you MUST preserve all the information from "
+            "the original summary.You may add a follow-up question after "
+            "the summary if needed.\n"
+            "\n"
+            "[Internal context] User documents are attached to this "
+            "conversation. Do not request re-upload of documents; "
+            "consider them already available via the internal store.",
             "kind": "request",
             "parts": [
-                {
-                    "content": "You are a helpful test assistant :)",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": timestamp,
-                },
-                {
-                    "content": today_promt_date,
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": timestamp,
-                },
-                {
-                    "content": "Answer in english.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": timestamp,
-                },
                 {
                     "content": [
                         "What is in this document?",
-                        {
-                            "force_download": False,
-                            "identifier": "sample.pdf",
-                            "kind": "document-url",
-                            "media_type": "application/pdf",
-                            "url": document_url,
-                            "vendor_metadata": None,
-                        },
                     ],
                     "part_kind": "user-prompt",
                     "timestamp": timestamp,
@@ -429,7 +428,6 @@ def test_post_conversation_with_remote_document_url(
 @freeze_time("2025-10-18T20:48:20.286204Z")
 def test_post_conversation_with_local_document_url_in_history(  # pylint: disable=too-many-arguments,too-many-positional-arguments
     api_client,
-    today_promt_date,
     mock_ai_agent_service,
 ):
     """
@@ -437,6 +435,8 @@ def test_post_conversation_with_local_document_url_in_history(  # pylint: disabl
     """
     chat_conversation_pk = "0be55da5-8eb7-4dad-aa0f-fea454bd5809"
     document_url = f"/media-key/{chat_conversation_pk}/sample.pdf"
+    formatted_date = formats.date_format(timezone.now(), "l d/m/Y", use_l10n=False)
+
     chat_conversation = ChatConversationFactory(
         pk=chat_conversation_pk,
         owner__language="en-us",
@@ -472,27 +472,11 @@ def test_post_conversation_with_local_document_url_in_history(  # pylint: disabl
         ],
         pydantic_messages=[
             {
-                "instructions": None,
+                "instructions": "You are a helpful test assistant :)\n\n"
+                f"Today is {formatted_date}.\n\n"
+                "Answer in english.",
                 "kind": "request",
                 "parts": [
-                    {
-                        "content": "You are a helpful test assistant :)",
-                        "dynamic_ref": None,
-                        "part_kind": "system-prompt",
-                        "timestamp": "2025-10-18T20:48:20.286204Z",
-                    },
-                    {
-                        "content": today_promt_date,
-                        "dynamic_ref": None,
-                        "part_kind": "system-prompt",
-                        "timestamp": "2025-10-18T20:48:20.286204Z",
-                    },
-                    {
-                        "content": "Answer in english.",
-                        "dynamic_ref": None,
-                        "part_kind": "system-prompt",
-                        "timestamp": "2025-10-18T20:48:20.286204Z",
-                    },
                     {
                         "content": [
                             "What is in this document?",
@@ -555,7 +539,7 @@ def test_post_conversation_with_local_document_url_in_history(  # pylint: disabl
     )
 
     async def agent_model(messages: list[ModelMessage], _info: AgentInfo):
-        presigned_url = messages[0].parts[3].content[1].url
+        presigned_url = messages[0].parts[0].content[1].url
         assert presigned_url.startswith("http://localhost:9000/conversations-media-storage/")
         assert presigned_url.find("X-Amz-Signature=") != -1
         assert presigned_url.find("X-Amz-Date=") != -1
@@ -564,18 +548,6 @@ def test_post_conversation_with_local_document_url_in_history(  # pylint: disabl
         assert messages == [
             ModelRequest(
                 parts=[
-                    SystemPromptPart(
-                        content="You are a helpful test assistant :)",
-                        timestamp=timezone.now(),
-                    ),
-                    SystemPromptPart(
-                        content=today_promt_date,
-                        timestamp=timezone.now(),
-                    ),
-                    SystemPromptPart(
-                        content="Answer in english.",
-                        timestamp=timezone.now(),
-                    ),
                     UserPromptPart(
                         content=[
                             "What is in this document?",
@@ -588,6 +560,9 @@ def test_post_conversation_with_local_document_url_in_history(  # pylint: disabl
                         timestamp=timezone.now(),
                     ),
                 ],
+                instructions="You are a helpful test assistant :)\n\n"
+                "Today is Saturday 18/10/2025.\n\n"
+                "Answer in english.",
                 run_id=messages[0].run_id,
             ),
             ModelResponse(
@@ -606,6 +581,9 @@ def test_post_conversation_with_local_document_url_in_history(  # pylint: disabl
                         timestamp=timezone.now(),
                     )
                 ],
+                instructions="You are a helpful test assistant :)\n\n"
+                "Today is Saturday 18/10/2025.\n\n"
+                "Answer in english.",
                 run_id=messages[2].run_id,
             ),
         ]
@@ -705,27 +683,11 @@ def test_post_conversation_with_local_document_url_in_history(  # pylint: disabl
     _run_id = chat_conversation.pydantic_messages[2]["run_id"]
     assert chat_conversation.pydantic_messages == [
         {
-            "instructions": None,
+            "instructions": "You are a helpful test assistant :)\n\n"
+            "Today is Saturday 18/10/2025.\n\n"
+            "Answer in english.",
             "kind": "request",
             "parts": [
-                {
-                    "content": "You are a helpful test assistant :)",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-10-18T20:48:20.286204Z",
-                },
-                {
-                    "content": today_promt_date,
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-10-18T20:48:20.286204Z",
-                },
-                {
-                    "content": "Answer in english.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-10-18T20:48:20.286204Z",
-                },
                 {
                     "content": [
                         "What is in this document?",
@@ -772,7 +734,9 @@ def test_post_conversation_with_local_document_url_in_history(  # pylint: disabl
             # no run_id here
         },
         {
-            "instructions": None,
+            "instructions": "You are a helpful test assistant :)\n\n"
+            "Today is Saturday 18/10/2025.\n\n"
+            "Answer in english.",
             "kind": "request",
             "parts": [
                 {
@@ -823,7 +787,8 @@ def test_post_conversation_with_local_document_url_in_history(  # pylint: disabl
         ("data.csv", "text/csv"),
     ],
 )
-def test_post_conversation_with_local_not_pdf_document_url(  # pylint: disable=too-many-arguments,too-many-positional-arguments
+def test_post_conversation_with_local_not_pdf_document_url(
+    # pylint: disable=too-many-arguments,too-many-positional-arguments
     api_client,
     today_promt_date,
     mock_ai_agent_service,
@@ -848,6 +813,10 @@ def test_post_conversation_with_local_not_pdf_document_url(  # pylint: disable=t
         json={"id": "document_id", "object": "document"},
         status=200,
     )
+    responses.post(
+        "https://app-find/api/v1.0/documents/index/",
+        status=200,
+    )
 
     chat_conversation = ChatConversationFactory(owner__language="en-us")
     api_client.force_authenticate(user=chat_conversation.owner)
@@ -886,27 +855,6 @@ def test_post_conversation_with_local_not_pdf_document_url(  # pylint: disable=t
         assert messages == [
             ModelRequest(
                 parts=[
-                    SystemPromptPart(
-                        content="You are a helpful test assistant :)", timestamp=timezone.now()
-                    ),
-                    SystemPromptPart(content=today_promt_date, timestamp=timezone.now()),
-                    SystemPromptPart(content="Answer in english.", timestamp=timezone.now()),
-                    SystemPromptPart(
-                        content=(
-                            "Use document_search_rag ONLY to retrieve specific passages from "
-                            "attached documents. Do NOT use it to summarize; for summaries, "
-                            "call the summarize tool instead."
-                        ),
-                        timestamp=timezone.now(),
-                    ),
-                    SystemPromptPart(
-                        content=(
-                            "[Internal context] User documents are attached to this conversation. "
-                            "Do not request re-upload of documents; consider them already "
-                            "available via the internal store."
-                        ),
-                        timestamp=timezone.now(),
-                    ),
                     UserPromptPart(
                         content=[
                             "What is in this document?",
@@ -916,14 +864,22 @@ def test_post_conversation_with_local_not_pdf_document_url(  # pylint: disable=t
                     ),
                 ],
                 instructions=(
-                    "When you receive a result from the summarization tool, you MUST "
-                    "return it directly to the user without any modification, "
-                    "paraphrasing, or additional summarization."
-                    "The tool already produces optimized summaries that should "
-                    "be presented verbatim."
-                    "You may translate the summary if required, but you MUST preserve "
-                    "all the information from the original summary."
-                    "You may add a follow-up question after the summary if needed."
+                    "You are a helpful test assistant :)\n\n"
+                    f"{today_promt_date}\n\n"
+                    "Answer in english.\n\n"
+                    "Use document_search_rag ONLY to retrieve specific passages from "
+                    "attached documents. Do NOT use it to summarize; for summaries, "
+                    "call the summarize tool instead.\n\nWhen you receive a result "
+                    "from the summarization tool, you MUST return it directly to "
+                    "the user without any modification, paraphrasing, or additional "
+                    "summarization.The tool already produces optimized summaries "
+                    "that should be presented verbatim.You may translate the summary "
+                    "if required, but you MUST preserve all the information from the "
+                    "original summary.You may add a follow-up question after the "
+                    "summary if needed.\n\n"
+                    "[Internal context] User documents are attached to this conversation. "
+                    "Do not request re-upload of documents; "
+                    "consider them already available via the internal store."
                 ),
                 run_id=messages[0].run_id,
             )
@@ -999,53 +955,25 @@ def test_post_conversation_with_local_not_pdf_document_url(  # pylint: disable=t
     assert chat_conversation.pydantic_messages == [
         {
             "instructions": (
-                "When you receive a result from the summarization tool, you MUST "
-                "return it directly to the user without any modification, "
-                "paraphrasing, or additional summarization."
-                "The tool already produces optimized summaries that should "
-                "be presented verbatim."
-                "You may translate the summary if required, but you MUST preserve "
-                "all the information from the original summary."
-                "You may add a follow-up question after the summary if needed."
+                "You are a helpful test assistant :)\n\n"
+                f"{today_promt_date}\n\n"
+                "Answer in english.\n\n"
+                "Use document_search_rag ONLY to retrieve specific passages from "
+                "attached documents. Do NOT use it to summarize; for summaries, "
+                "call the summarize tool instead.\n\nWhen you receive a result "
+                "from the summarization tool, you MUST return it directly to "
+                "the user without any modification, paraphrasing, or additional "
+                "summarization.The tool already produces optimized summaries "
+                "that should be presented verbatim.You may translate the summary "
+                "if required, but you MUST preserve all the information from the "
+                "original summary.You may add a follow-up question after the "
+                "summary if needed.\n\n"
+                "[Internal context] User documents are attached to this conversation. "
+                "Do not request re-upload of documents; "
+                "consider them already available via the internal store."
             ),
             "kind": "request",
             "parts": [
-                {
-                    "content": "You are a helpful test assistant :)",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": timestamp,
-                },
-                {
-                    "content": today_promt_date,
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": timestamp,
-                },
-                {
-                    "content": "Answer in english.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": timestamp,
-                },
-                {
-                    "content": "Use document_search_rag ONLY to retrieve specific "
-                    "passages from attached documents. Do NOT use it to "
-                    "summarize; for summaries, call the summarize tool "
-                    "instead.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": timestamp,
-                },
-                {
-                    "content": "[Internal context] User documents are attached to "
-                    "this conversation. Do not request re-upload of "
-                    "documents; consider them already available via the "
-                    "internal store.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": timestamp,
-                },
                 {
                     "content": [
                         "What is in this document?",

src/backend/chat/tests/views/chat/conversations/test_conversation_with_history.py

@@ -2,6 +2,7 @@
 # pylint: disable=too-many-lines
 
 import json
+from unittest.mock import patch
 
 from django.utils import timezone
 
@@ -11,6 +12,7 @@ from dirty_equals import IsUUID
 from freezegun import freeze_time
 from rest_framework import status
 
+from chat.agents.conversation import TitleGenerationAgent
 from chat.ai_sdk_types import (
     Attachment,
     TextUIPart,
@@ -29,24 +31,13 @@ pytestmark = pytest.mark.django_db(transaction=True)
 
 @pytest.fixture(autouse=True)
 def ai_settings(settings):
-    """
-    Configure AI-related settings for tests on the provided settings object.
-    
-    Sets test values for AI service base URL, API key, model, agent instructions, and sets
-    AUTO_TITLE_AFTER_USER_MESSAGES to 999 to disable automatic title generation during tests.
-    
-    Parameters:
-        settings (object): Django settings-like object to be mutated for test configuration.
-    
-    Returns:
-        object: The same settings object with AI-related test configuration applied.
-    """
+    """Fixture to set AI service URLs for testing."""
     settings.AI_BASE_URL = "https://www.external-ai-service.com/"
     settings.AI_API_KEY = "test-api-key"
     settings.AI_MODEL = "test-model"
     settings.AI_AGENT_INSTRUCTIONS = "You are a helpful test assistant :)"
 
-    settings.AUTO_TITLE_AFTER_USER_MESSAGES = 999  # disable auto title generation
+    settings.AUTO_TITLE_AFTER_USER_MESSAGES = None  # disable auto title generation
     return settings
 
 
@@ -931,7 +922,7 @@ def history_conversation_with_tool_fixture():
     history_timestamp = timezone.now().replace(year=2025, month=6, day=15, hour=10, minute=30)
 
     # Create a conversation with pre-existing messages including a tool invocation
-    conversation = ChatConversationFactory()
+    conversation = ChatConversationFactory(owner__language="nl-nl")
 
     # Add previous user and assistant messages with tool invocation
     conversation.messages = [
@@ -1389,7 +1380,9 @@ def test_post_conversation_with_existing_tool_history(
 
     # Verify the new tool call request is included
     assert history_conversation_with_tool.pydantic_messages[8] == {
-        "instructions": None,
+        "instructions": "You are a helpful test assistant :)\n\n"
+        "Today is Friday 25/07/2025.\n\n"
+        "Answer in dutch.",
         "kind": "request",
         "parts": [
             {
@@ -1432,7 +1425,9 @@ def test_post_conversation_with_existing_tool_history(
     }
 
     assert history_conversation_with_tool.pydantic_messages[10] == {
-        "instructions": None,
+        "instructions": "You are a helpful test assistant :)\n\n"
+        "Today is Friday 25/07/2025.\n\n"
+        "Answer in dutch.",
         "kind": "request",
         "parts": [
             {
@@ -1585,14 +1580,80 @@ def test_post_conversation_add_image_to_conversation_with_tool_history(
 
 @freeze_time("2025-07-25T10:36:35.297675Z")
 @respx.mock
-def test_post_conversation_triggers_automatic_title_generation(
+@patch("chat.clients.pydantic_ai.TitleGenerationAgent", wraps=TitleGenerationAgent)
+def test_post_conversation_triggers_automatic_title_generation_after_first_message(
+    mock_title_agent, api_client, mock_openai_stream_with_title_generation, settings
+):
+    """
+    Test that posting the first user message triggers automatic title generation.
+
+    AUTO_TITLE_AFTER_USER_MESSAGES = 1
+
+    The conversation is a new one. Posting the first message
+    should trigger title generation via the TitleGenerationAgent.
+    """
+    # Configure the title generation threshold
+    settings.AUTO_TITLE_AFTER_USER_MESSAGES = 1
+    conversation = ChatConversationFactory()
+    url = f"/api/v1.0/chats/{conversation.pk}/conversation/?protocol=data"
+    data = {
+        "messages": [
+            {
+                "id": "third-user-msg",
+                "role": "user",
+                "parts": [{"text": "Can you explain backpropagation?", "type": "text"}],
+                "content": "Can you explain backpropagation?",
+                "createdAt": "2025-07-25T10:36:00.000Z",
+            }
+        ]
+    }
+    api_client.force_login(conversation.owner)
+
+    conversation.title = "initial title"
+    conversation.save()
+
+    assert not conversation.title_set_by_user_at
+
+    response = api_client.post(url, data, format="json")
+
+    assert response.status_code == status.HTTP_200_OK
+    assert response.get("Content-Type") == "text/event-stream"
+    assert response.streaming
+
+    # Wait for the streaming content to be fully received
+    response_content = b"".join(response.streaming_content).decode("utf-8")
+
+    # Verify the conversation_metadata event is in the stream
+
+    assert '"type": "conversation_metadata"' in response_content
+
+    # Refresh and verify title was updated
+    conversation.refresh_from_db()
+
+    assert conversation.title == "GENERATED TITLE"
+    # title_set_by_user_at should remain None since it was auto-generated
+    assert not conversation.title_set_by_user_at
+
+    assert mock_openai_stream_with_title_generation.called
+    assert mock_openai_stream_with_title_generation.call_count == 2
+
+    # Verify TitleGenerationAgent was called
+    mock_title_agent.assert_called_once()
+
+
+@freeze_time("2025-07-25T10:36:35.297675Z")
+@respx.mock
+def test_post_conversation_triggers_automatic_title_generation_at_threshold(
     api_client, mock_openai_stream_with_title_generation, settings, history_conversation
 ):
     """
     Test that posting the 3rd user message triggers automatic title generation.
 
+    AUTO_TITLE_AFTER_USER_MESSAGES = 3
+
+
     The history_conversation fixture has 2 user messages. Posting a 3rd message
-    should trigger title generation via the SummarizationAgent.
+    should trigger title generation via the TitleGenerationAgent.
     """
     # Configure the title generation threshold
     settings.AUTO_TITLE_AFTER_USER_MESSAGES = 3
@@ -1637,7 +1698,6 @@ def test_post_conversation_triggers_automatic_title_generation(
     assert not history_conversation.title_set_by_user_at
 
     assert mock_openai_stream_with_title_generation.called
-
     assert mock_openai_stream_with_title_generation.call_count == 2
 
 
@@ -1684,10 +1744,9 @@ def test_post_conversation_does_not_regenerate_title_when_user_set(
     history_conversation.refresh_from_db()
 
     assert history_conversation.title == "My Custom Title"
-    assert history_conversation.title_set_by_user_at is not None
+    assert history_conversation.title_set_by_user_at
 
     assert mock_openai_stream_with_title_generation.called
-
     assert mock_openai_stream_with_title_generation.call_count == 1
 
 
@@ -1761,4 +1820,63 @@ def test_post_conversation_does_not_generate_title_before_threshold(
     assert conversation.title == "initial title"
     assert not conversation.title_set_by_user_at
 
-    assert mock_openai_stream_with_title_generation.call_count == 1
+    assert mock_openai_stream_with_title_generation.call_count == 1
+
+
+@freeze_time("2025-07-25T10:36:35.297675Z")
+@respx.mock
+def test_post_conversation_does_not_generate_title_after_threshold(
+    api_client, mock_openai_stream_with_title_generation, settings, history_conversation
+):
+    """
+    Test that posting the 3rd user message does not trigger automatic title generation.
+
+    AUTO_TITLE_AFTER_USER_MESSAGES = 2
+
+    The history_conversation fixture has 2 user messages. Posting a 3rd message
+    should not trigger title generation.
+    """
+    # Configure the title generation threshold
+    settings.AUTO_TITLE_AFTER_USER_MESSAGES = 2
+
+    url = f"/api/v1.0/chats/{history_conversation.pk}/conversation/?protocol=data"
+    data = {
+        "messages": [
+            {
+                "id": "third-user-msg",
+                "role": "user",
+                "parts": [{"text": "Can you explain backpropagation?", "type": "text"}],
+                "content": "Can you explain backpropagation?",
+                "createdAt": "2025-07-25T10:36:00.000Z",
+            }
+        ]
+    }
+    api_client.force_login(history_conversation.owner)
+
+    history_conversation.title = "initial title"
+    history_conversation.save()
+
+    assert not history_conversation.title_set_by_user_at
+
+    response = api_client.post(url, data, format="json")
+
+    assert response.status_code == status.HTTP_200_OK
+    assert response.get("Content-Type") == "text/event-stream"
+    assert response.streaming
+
+    # Wait for the streaming content to be fully received
+    response_content = b"".join(response.streaming_content).decode("utf-8")
+
+    # Verify the conversation_metadata event is not in the stream
+
+    assert "conversation_metadata" not in response_content
+
+    # Refresh and verify title was NOT updated (past threshold)
+    history_conversation.refresh_from_db()
+
+    # title not updated
+    assert history_conversation.title == "initial title"
+    # title_set_by_user_at should remain None since it was auto-generated
+    assert not history_conversation.title_set_by_user_at
+
+    assert mock_openai_stream_with_title_generation.call_count == 1

src/backend/chat/tests/views/chat/conversations/test_conversation_with_image_url.py

@@ -2,7 +2,7 @@
 
 import uuid
 
-from django.utils import timezone
+from django.utils import formats, timezone
 
 import pytest
 from dirty_equals import IsUUID
@@ -12,7 +12,6 @@ from pydantic_ai.messages import (
     ImageUrl,
     ModelMessage,
     ModelResponse,
-    SystemPromptPart,
     TextPart,
     UserPromptPart,
 )
@@ -87,22 +86,15 @@ def test_post_conversation_with_local_image_url(
     )
 
     async def agent_model(messages: list[ModelMessage], _info: AgentInfo):
-        presigned_url = messages[0].parts[3].content[1].url
-        assert presigned_url.startswith("http://localhost:9000/conversations-media-storage/")
+        presigned_url = messages[0].parts[0].content[1].url
+        # assert presigned_url.startswith("http://localhost:9000/conversations-media-storage/")
         assert presigned_url.find("X-Amz-Signature=") != -1
         assert presigned_url.find("X-Amz-Date=") != -1
         assert presigned_url.find("X-Amz-Expires=") != -1
-
+        formatted_date = formats.date_format(timezone.now(), "l d/m/Y", use_l10n=False)
         assert messages == [
             ModelRequest(
                 parts=[
-                    SystemPromptPart(
-                        content="You are a helpful test assistant :)", timestamp=timezone.now()
-                    ),
-                    SystemPromptPart(
-                        content="Today is Saturday 18/10/2025.", timestamp=timezone.now()
-                    ),
-                    SystemPromptPart(content="Answer in english.", timestamp=timezone.now()),
                     UserPromptPart(
                         content=[
                             "What is in this image?",
@@ -115,6 +107,8 @@ def test_post_conversation_with_local_image_url(
                         timestamp=timezone.now(),
                     ),
                 ],
+                instructions="You are a helpful test assistant :)\n\nToday is "
+                f"{formatted_date}.\n\nAnswer in english.",
                 run_id=messages[0].run_id,
             )
         ]
@@ -184,27 +178,10 @@ def test_post_conversation_with_local_image_url(
     _run_id = chat_conversation.pydantic_messages[0]["run_id"]
     assert chat_conversation.pydantic_messages == [
         {
-            "instructions": None,
+            "instructions": "You are a helpful test assistant :)\n\n"
+            "Today is Saturday 18/10/2025.\n\nAnswer in english.",
             "kind": "request",
             "parts": [
-                {
-                    "content": "You are a helpful test assistant :)",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-10-18T20:48:20.286204Z",
-                },
-                {
-                    "content": "Today is Saturday 18/10/2025.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-10-18T20:48:20.286204Z",
-                },
-                {
-                    "content": "Answer in english.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-10-18T20:48:20.286204Z",
-                },
                 {
                     "content": [
                         "What is in this image?",
@@ -286,11 +263,6 @@ def test_post_conversation_with_local_image_wrong_url(
         assert messages == [
             ModelRequest(
                 parts=[
-                    SystemPromptPart(
-                        content="You are a helpful test assistant :)", timestamp=timezone.now()
-                    ),
-                    SystemPromptPart(content=today_promt_date, timestamp=timezone.now()),
-                    SystemPromptPart(content="Answer in english.", timestamp=timezone.now()),
                     UserPromptPart(
                         content=[
                             "What is in this image?",
@@ -303,6 +275,8 @@ def test_post_conversation_with_local_image_wrong_url(
                         timestamp=timezone.now(),
                     ),
                 ],
+                instructions=f"You are a helpful test assistant :)\n\n{today_promt_date}"
+                "\n\nAnswer in english.",
                 run_id=messages[0].run_id,
             )
         ]
@@ -374,11 +348,6 @@ def test_post_conversation_with_remote_image_url(
         assert messages == [
             ModelRequest(
                 parts=[
-                    SystemPromptPart(
-                        content="You are a helpful test assistant :)", timestamp=timezone.now()
-                    ),
-                    SystemPromptPart(content=today_promt_date, timestamp=timezone.now()),
-                    SystemPromptPart(content="Answer in english.", timestamp=timezone.now()),
                     UserPromptPart(
                         content=[
                             "What is in this image?",
@@ -391,6 +360,8 @@ def test_post_conversation_with_remote_image_url(
                         timestamp=timezone.now(),
                     ),
                 ],
+                instructions="You are a helpful test assistant :)\n\n"
+                f"{today_promt_date}\n\nAnswer in english.",
                 run_id=messages[0].run_id,
             )
         ]
@@ -504,27 +475,10 @@ def test_post_conversation_with_local_image_url_in_history(
         ],
         pydantic_messages=[
             {
-                "instructions": None,
+                "instructions": f"You are a helpful test assistant :)\n\n{today_promt_date}"
+                "\n\nAnswer in english.",
                 "kind": "request",
                 "parts": [
-                    {
-                        "content": "You are a helpful test assistant :)",
-                        "dynamic_ref": None,
-                        "part_kind": "system-prompt",
-                        "timestamp": "2025-10-18T20:48:20.286204Z",
-                    },
-                    {
-                        "content": today_promt_date,
-                        "dynamic_ref": None,
-                        "part_kind": "system-prompt",
-                        "timestamp": "2025-10-18T20:48:20.286204Z",
-                    },
-                    {
-                        "content": "Answer in english.",
-                        "dynamic_ref": None,
-                        "part_kind": "system-prompt",
-                        "timestamp": "2025-10-18T20:48:20.286204Z",
-                    },
                     {
                         "content": [
                             "What is in this image?",
@@ -587,7 +541,7 @@ def test_post_conversation_with_local_image_url_in_history(
     )
 
     async def agent_model(messages: list[ModelMessage], _info: AgentInfo):
-        presigned_url = messages[0].parts[3].content[1].url
+        presigned_url = messages[0].parts[0].content[1].url
         assert presigned_url.startswith("http://localhost:9000/conversations-media-storage/")
         assert presigned_url.find("X-Amz-Signature=") != -1
         assert presigned_url.find("X-Amz-Date=") != -1
@@ -596,18 +550,6 @@ def test_post_conversation_with_local_image_url_in_history(
         assert messages == [
             ModelRequest(
                 parts=[
-                    SystemPromptPart(
-                        content="You are a helpful test assistant :)",
-                        timestamp=timezone.now(),
-                    ),
-                    SystemPromptPart(
-                        content=today_promt_date,
-                        timestamp=timezone.now(),
-                    ),
-                    SystemPromptPart(
-                        content="Answer in english.",
-                        timestamp=timezone.now(),
-                    ),
                     UserPromptPart(
                         content=[
                             "What is in this image?",
@@ -619,7 +561,9 @@ def test_post_conversation_with_local_image_url_in_history(
                         ],
                         timestamp=timezone.now(),
                     ),
-                ]
+                ],
+                instructions="You are a helpful test assistant :)\n\n"
+                f"{today_promt_date}\n\nAnswer in english.",
             ),
             ModelResponse(
                 parts=[TextPart(content="This is an image of a single pixel.")],
@@ -637,6 +581,8 @@ def test_post_conversation_with_local_image_url_in_history(
                     )
                 ],
                 run_id=messages[2].run_id,
+                instructions="You are a helpful test assistant :)\n\n"
+                "Today is Saturday 18/10/2025.\n\nAnswer in english.",
             ),
         ]
         yield "This is an image of square, very small and nice."
@@ -735,27 +681,10 @@ def test_post_conversation_with_local_image_url_in_history(
     _run_id = chat_conversation.pydantic_messages[2]["run_id"]
     assert chat_conversation.pydantic_messages == [
         {
-            "instructions": None,
+            "instructions": f"You are a helpful test assistant :)\n\n{today_promt_date}"
+            "\n\nAnswer in english.",
             "kind": "request",
             "parts": [
-                {
-                    "content": "You are a helpful test assistant :)",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-10-18T20:48:20.286204Z",
-                },
-                {
-                    "content": today_promt_date,
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-10-18T20:48:20.286204Z",
-                },
-                {
-                    "content": "Answer in english.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-10-18T20:48:20.286204Z",
-                },
                 {
                     "content": [
                         "What is in this image?",
@@ -796,7 +725,8 @@ def test_post_conversation_with_local_image_url_in_history(
             },
         },
         {
-            "instructions": None,
+            "instructions": "You are a helpful test assistant :)\n\nToday is Saturday 18/10/2025."
+            "\n\nAnswer in english.",
             "kind": "request",
             "parts": [
                 {

src/backend/chat/tests/views/chat/conversations/test_stop_streaming.py

@@ -1,4 +1,4 @@
-"""Test the post_stop_steaming view."""
+"""Test the post_stop_streaming view."""
 
 from unittest.mock import patch
 

src/backend/chat/tests/views/chat/test_update.py

@@ -27,7 +27,7 @@ def test_update_conversation(api_client):
     # Verify in database
     conversation = ChatConversation.objects.get(id=chat_conversation.pk)
     assert conversation.title == "Updated Title"
-    assert conversation.title_set_by_user_at is not None
+    assert conversation.title_set_by_user_at
 
 
 def test_update_conversation_limit_title_length(api_client):

src/backend/chat/tools/document_search_rag.py

@@ -26,7 +26,7 @@ def add_document_rag_search_tool(agent: Agent) -> None:
 
         document_store = document_store_backend(ctx.deps.conversation.collection_id)
 
-        rag_results = document_store.search(query)
+        rag_results = document_store.search(query, session=ctx.deps.session)
 
         ctx.usage += RunUsage(
             input_tokens=rag_results.usage.prompt_tokens,
@@ -39,7 +39,7 @@ def add_document_rag_search_tool(agent: Agent) -> None:
             metadata={"sources": {result.url for result in rag_results.data}},
         )
 
-    @agent.system_prompt
+    @agent.instructions
     def document_rag_instructions() -> str:
         """Dynamic system prompt function to add RAG instructions if any."""
         return (

src/backend/chat/tools/exceptions.py

@@ -3,17 +3,6 @@
 from pydantic_ai import ModelRetry
 
 
-class ModelRetryLast(ModelRetry):
-    """
-    Same as ModelRetry but also holds the last retry message to return when all attempts failed.
-    """
-
-    def __init__(self, message: str, last_retry_message: str):
-        """Initialize ModelRetryLast with message and last retry message."""
-        self.last_retry_message = last_retry_message
-        super().__init__(message)
-
-
 class ModelCannotRetry(ModelRetry):
     """
     Exception to raise when a tool function cannot be retried.

src/backend/chat/tools/web_search_brave.py

@@ -127,7 +127,7 @@ async def _extract_and_summarize_snippets_async(query: str, url: str) -> List[st
         return []
 
 
-async def _fetch_and_store_async(url: str, document_store) -> None:
+async def _fetch_and_store_async(url: str, document_store, **kwargs) -> None:
     """Fetch, extract and store text content from the URL in the document store."""
 
     try:
@@ -136,7 +136,7 @@ async def _fetch_and_store_async(url: str, document_store) -> None:
         logger.debug("Fetched document: %s", document)
 
         if document:
-            await document_store.astore_document(url, document)
+            await document_store.astore_document(url, document, **kwargs)
     except DocumentFetchError as e:
         logger.warning("Failed to fetch and store %s: %s", url, e)
         # Continue with other documents
@@ -307,19 +307,26 @@ async def web_search_brave_with_document_backend(ctx: RunContext, query: str) ->
         temp_collection_name = f"tmp-{uuid.uuid4()}"
         try:
             async with document_store_backend.temporary_collection_async(
-                temp_collection_name
+                temp_collection_name, session=ctx.deps.session
             ) as document_store:
                 # Fetch and store all documents concurrently
                 tasks = [
-                    _fetch_and_store_async(result["url"], document_store)
+                    _fetch_and_store_async(
+                        result["url"],
+                        document_store,
+                        user_sub=ctx.deps.user.sub,
+                        session=ctx.deps.session,
+                    )
                     for result in raw_search_results
                 ]
                 await asyncio.gather(*tasks, return_exceptions=True)
 
                 # Perform RAG search
                 rag_results = await document_store.asearch(
-                    query,
+                    query=query,
                     results_count=settings.BRAVE_RAG_WEB_SEARCH_CHUNK_NUMBER,
+                    session=ctx.deps.session,
+                    user_sub=ctx.deps.user.sub,
                 )
                 logger.info("RAG search returned:  %s", rag_results)
 

src/backend/chat/vercel_ai_sdk/encoder/__init__.py

@@ -2,6 +2,6 @@
 This module contains the EventEncoder class.
 """
 
-from .encoder import EventEncoder
+from .encoder import CURRENT_EVENT_ENCODER_VERSION, EventEncoder, EventEncoderVersion
 
-__all__ = ["EventEncoder"]
+__all__ = ["EventEncoder", "CURRENT_EVENT_ENCODER_VERSION", "EventEncoderVersion"]

src/backend/chat/vercel_ai_sdk/encoder/encoder.py

@@ -1,6 +1,7 @@
 """Event Encoder for Vercel AI SDK"""
 
-from typing import Literal, Union
+from enum import Enum
+from typing import Union
 
 from ..core.events_v4 import BaseEvent as V4BaseEvent
 from ..core.events_v4 import TextPart
@@ -8,16 +9,26 @@ from ..core.events_v5 import BaseEvent as V5BaseEvent
 from ..core.events_v5 import TextDeltaEvent
 
 
+class EventEncoderVersion(str, Enum):
+    """Enumeration of supported event encoder versions."""
+
+    V4 = "v4"
+    V5 = "v5"
+
+
+CURRENT_EVENT_ENCODER_VERSION = EventEncoderVersion.V4  # used encoder version
+
+
 class EventEncoder:
     """
     Encodes events for the Vercel AI SDK based on the specified version.
     """
 
-    def __init__(self, version: Literal["v4", "v5"] = None):
+    def __init__(self, version: EventEncoderVersion):
         """
         Initializes the EventEncoder with the specified version.
         """
-        if version not in ["v4", "v5"]:
+        if version not in [EventEncoderVersion.V4, EventEncoderVersion.V5]:
             raise ValueError("Unsupported version. Supported versions are 'v4' and 'v5'.")
 
         self.version = version
@@ -28,7 +39,7 @@ class EventEncoder:
         """
         return "text/event-stream"
 
-    def encode(self, event: Union[V5BaseEvent, V5BaseEvent]) -> str | None:
+    def encode(self, event: Union[V4BaseEvent, V5BaseEvent]) -> str | None:
         """
         Encodes an event based on the version.
 
@@ -38,15 +49,15 @@ class EventEncoder:
             str | None: The encoded event as a string,
             or None if the event type is not adapted to the SDK version.
         """
-        if self.version == "v4" and isinstance(event, V4BaseEvent):
+        if self.version == EventEncoderVersion.V4 and isinstance(event, V4BaseEvent):
             return self._encode_v4_streaming(event)
 
-        if self.version == "v5" and isinstance(event, V5BaseEvent):
+        if self.version == EventEncoderVersion.V5 and isinstance(event, V5BaseEvent):
             return self._encode_sse(event)
 
         return None
 
-    def encode_text(self, event: Union[V5BaseEvent, V5BaseEvent]) -> str | None:
+    def encode_text(self, event: Union[V4BaseEvent, V5BaseEvent]) -> str | None:
         """
         Encodes an event based on the version.
 
@@ -56,10 +67,10 @@ class EventEncoder:
             str | None: The encoded event as a string,
             or None if the event type is not adapted to the SDK version.
         """
-        if self.version == "v4" and isinstance(event, TextPart):
+        if self.version == EventEncoderVersion.V4 and isinstance(event, TextPart):
             return event.text
 
-        if self.version == "v5" and isinstance(event, TextDeltaEvent):
+        if self.version == EventEncoderVersion.V5 and isinstance(event, TextDeltaEvent):
             return event.delta
 
         return None
@@ -70,7 +81,7 @@ class EventEncoder:
         """
         return f"{event.type}:{event.model_dump_json(by_alias=True, exclude={'type'})}\n"
 
-    def _encode_sse(self, event: Union[V5BaseEvent, V5BaseEvent]) -> str:
+    def _encode_sse(self, event: Union[V4BaseEvent, V5BaseEvent]) -> str:
         """
         Encodes an event into an SSE string.
         """

src/backend/chat/views.py

@@ -7,11 +7,13 @@ from uuid import uuid4
 from django.conf import settings
 from django.core.files.storage import default_storage
 from django.http import Http404, StreamingHttpResponse
+from django.utils.decorators import method_decorator
 
 import langfuse
 import magic
 import posthog
 from lasuite.malware_detection import malware_detection
+from lasuite.oidc_login.decorators import refresh_oidc_access_token
 from rest_framework import decorators, filters, mixins, permissions, status, viewsets
 from rest_framework.exceptions import MethodNotAllowed, PermissionDenied, ValidationError
 from rest_framework.response import Response
@@ -26,6 +28,7 @@ from core.filters import remove_accents
 from activation_codes.permissions import IsActivatedUser
 from chat import models, serializers
 from chat.clients.pydantic_ai import AIAgentService
+from chat.keepalive import stream_with_keepalive_async, stream_with_keepalive_sync
 from chat.serializers import ChatConversationRequestSerializer
 
 logger = logging.getLogger(__name__)
@@ -122,6 +125,7 @@ class ChatViewSet(  # pylint: disable=too-many-ancestors, abstract-method
             self.permission_classes = []
         return super().get_permissions()
 
+    @method_decorator(refresh_oidc_access_token)
     @decorators.action(
         methods=["post"],
         detail=True,
@@ -173,6 +177,7 @@ class ChatViewSet(  # pylint: disable=too-many-ancestors, abstract-method
         ai_service = AIAgentService(
             conversation=conversation,
             user=self.request.user,
+            session=request.session,
             model_hrid=model_hrid,
             language=(
                 self.request.user.language
@@ -188,29 +193,28 @@ class ChatViewSet(  # pylint: disable=too-many-ancestors, abstract-method
         if is_async_mode:
             logger.debug("Using ASYNC streaming for chat conversation.")
             if protocol == "data":
-                streaming_content = ai_service.stream_data_async(
+                base_stream = ai_service.stream_data_async(
                     messages, force_web_search=force_web_search
                 )
             else:  # Default to 'text' protocol
-                streaming_content = ai_service.stream_text_async(
+                base_stream = ai_service.stream_text_async(
                     messages, force_web_search=force_web_search
                 )
+            streaming_content = stream_with_keepalive_async(base_stream)
         else:
             logger.debug("Using SYNC streaming for chat conversation.")
             if protocol == "data":
-                streaming_content = ai_service.stream_data(
-                    messages, force_web_search=force_web_search
-                )
+                base_stream = ai_service.stream_data(messages, force_web_search=force_web_search)
             else:  # Default to 'text' protocol
-                streaming_content = ai_service.stream_text(
-                    messages, force_web_search=force_web_search
-                )
+                base_stream = ai_service.stream_text(messages, force_web_search=force_web_search)
 
+            streaming_content = stream_with_keepalive_sync(base_stream)
         response = StreamingHttpResponse(
             streaming_content,
             content_type="text/event-stream",
             headers={
                 "x-vercel-ai-data-stream": "v1",  # This header is used for Vercel AI streaming,
+                "X-Accel-Buffering": "no",  # Prevent nginx buffering
             },
         )
         return response
@@ -221,7 +225,7 @@ class ChatViewSet(  # pylint: disable=too-many-ancestors, abstract-method
         url_path="stop-streaming",
         url_name="stop-streaming",
     )
-    def post_stop_steaming(self, request, pk):  # pylint: disable=unused-argument
+    def post_stop_streaming(self, request, pk):  # pylint: disable=unused-argument
         """Handle POST requests to stop streaming the chat conversation.
 
         This action will put a poison pill in the redis cache to stop any ongoing streaming.
@@ -371,7 +375,6 @@ class ChatConversationAttachmentViewSet(
             owner=self.request.user,
         ).exists():
             raise Http404
-
         file_name = serializer.validated_data["file_name"]
         extension = file_name.rpartition(".")[-1] if "." in file_name else None
 

src/backend/conftest.py

@@ -22,7 +22,7 @@ def no_http_requests(monkeypatch):
     Credits: https://blog.jerrycodes.com/no-http-requests/
     """
 
-    allowed_hosts = {"localhost", "minio", "minio:9000"}
+    allowed_hosts = {"localhost", "127.0.0.1", "minio", "minio:9000"}
     original_urlopen = HTTPConnectionPool.urlopen
 
     def urlopen_mock(self, method, url, *args, **kwargs):

src/backend/conversations/settings.py

@@ -841,6 +841,23 @@ USER QUESTION:
         environ_prefix=None,
     )
 
+    # Find
+    FIND_API_KEY = values.Value(
+        None,
+        environ_name="FIND_API_KEY",
+        environ_prefix=None,
+    )
+    FIND_API_URL = values.Value(
+        "https://app-find/api",
+        environ_name="FIND_API_URL",
+        environ_prefix=None,
+    )
+    FIND_API_TIMEOUT = values.PositiveIntegerValue(
+        default=30,  # seconds
+        environ_name="FIND_API_TIMEOUT",
+        environ_prefix=None,
+    )
+
     # Logging
     # We want to make it easy to log to console but by default we log production
     # to Sentry and don't want to log to console.
@@ -912,7 +929,7 @@ USER QUESTION:
         default=False, environ_name="LANGFUSE_MEDIA_UPLOAD_ENABLED", environ_prefix=None
     )
     AUTO_TITLE_AFTER_USER_MESSAGES = values.PositiveIntegerValue(
-        3, environ_name="AUTO_TITLE_AFTER_USER_MESSAGES", environ_prefix=None
+        default=None, environ_name="AUTO_TITLE_AFTER_USER_MESSAGES", environ_prefix=None
     )
     # WARNING: Testing purpose only. Do not use in production.
     WARNING_MOCK_CONVERSATION_AGENT = values.BooleanValue(
@@ -921,6 +938,12 @@ USER QUESTION:
         environ_prefix=None,
     )
 
+    # Default keepalive interval: 55s (safely below typical 60s proxy timeouts)
+    # Prevents connection drops during long stream pauses while providing 5s safety margin.
+    KEEPALIVE_INTERVAL = values.PositiveIntegerValue(
+        default=55, environ_name="KEEPALIVE_INTERVAL", environ_prefix=None
+    )
+
     # pylint: disable=invalid-name
     @property
     def ENVIRONMENT(self):
@@ -1133,6 +1156,8 @@ class Test(Base):
 
     POSTHOG_KEY = None
 
+    AUTO_TITLE_AFTER_USER_MESSAGES = None
+
     def __init__(self):
         # pylint: disable=invalid-name
         self.INSTALLED_APPS += ["drf_spectacular_sidecar"]

src/backend/core/api/__init__.py

@@ -1,12 +1,9 @@
 """Conversations core API endpoints"""
 
-from django.conf import settings
 from django.core.exceptions import ValidationError
 
 from rest_framework import exceptions as drf_exceptions
 from rest_framework import views as drf_views
-from rest_framework.decorators import api_view
-from rest_framework.response import Response
 
 
 def exception_handler(exc, context):
@@ -28,14 +25,3 @@ def exception_handler(exc, context):
         exc = drf_exceptions.ValidationError(detail=detail)
 
     return drf_views.exception_handler(exc, context)
-
-
-# pylint: disable=unused-argument
-@api_view(["GET"])
-def get_frontend_configuration(request):
-    """Returns the frontend configuration dict as configured in settings."""
-    frontend_configuration = {
-        "LANGUAGE_CODE": settings.LANGUAGE_CODE,
-    }
-    frontend_configuration.update(settings.FRONTEND_CONFIGURATION)
-    return Response(frontend_configuration)

src/backend/core/api/serializers.py

@@ -20,23 +20,3 @@ class UserSerializer(serializers.ModelSerializer):
             "sub",
         ]
         read_only_fields = ["id", "email", "full_name", "short_name", "sub"]
-
-
-class UserLightSerializer(UserSerializer):
-    """Serialize users with limited fields."""
-
-    id = serializers.SerializerMethodField(read_only=True)
-    email = serializers.SerializerMethodField(read_only=True)
-
-    def get_id(self, _user):
-        """Return always None. Here to have the same fields than in UserSerializer."""
-        return None
-
-    def get_email(self, _user):
-        """Return always None. Here to have the same fields than in UserSerializer."""
-        return None
-
-    class Meta:
-        model = models.User
-        fields = ["id", "email", "full_name", "short_name"]
-        read_only_fields = ["id", "email", "full_name", "short_name"]

src/backend/core/authentication/__init__.py

@@ -1,52 +0,0 @@
-"""Custom authentication classes for the Conversations core app"""
-
-from django.conf import settings
-
-from rest_framework.authentication import BaseAuthentication
-from rest_framework.exceptions import AuthenticationFailed
-
-
-class ServerToServerAuthentication(BaseAuthentication):
-    """
-    Custom authentication class for server-to-server requests.
-    Validates the presence and correctness of the Authorization header.
-    """
-
-    AUTH_HEADER = "Authorization"
-    TOKEN_TYPE = "Bearer"  # noqa S105
-
-    def authenticate(self, request):
-        """
-        Authenticate the server-to-server request by validating the Authorization header.
-
-        This method checks if the Authorization header is present in the request, ensures it
-        contains a valid token with the correct format, and verifies the token against the
-        list of allowed server-to-server tokens. If the header is missing, improperly formatted,
-        or contains an invalid token, an AuthenticationFailed exception is raised.
-
-        Returns:
-            None: If authentication is successful
-                  (no user is authenticated for server-to-server requests).
-
-        Raises:
-            AuthenticationFailed: If the Authorization header is missing, malformed,
-            or contains an invalid token.
-        """
-        auth_header = request.headers.get(self.AUTH_HEADER)
-        if not auth_header:
-            raise AuthenticationFailed("Authorization header is missing.")
-
-        # Validate token format and existence
-        auth_parts = auth_header.split(" ")
-        if len(auth_parts) != 2 or auth_parts[0] != self.TOKEN_TYPE:
-            raise AuthenticationFailed("Invalid authorization header.")
-
-        token = auth_parts[1]
-        if token not in settings.SERVER_TO_SERVER_API_TOKENS:
-            raise AuthenticationFailed("Invalid server-to-server token.")
-
-        # Authentication is successful, but no user is authenticated
-
-    def authenticate_header(self, request):
-        """Return the WWW-Authenticate header value."""
-        return f"{self.TOKEN_TYPE} realm='Create document server to server'"

src/backend/core/fields.py

@@ -1,25 +0,0 @@
-"""A JSONField for DRF to handle serialization/deserialization."""
-
-import json
-
-from rest_framework import serializers
-
-
-class JSONField(serializers.Field):
-    """
-    A custom field for handling JSON data.
-    """
-
-    def to_representation(self, value):
-        """
-        Convert the JSON string to a Python dictionary for serialization.
-        """
-        return value
-
-    def to_internal_value(self, data):
-        """
-        Convert the Python dictionary to a JSON string for deserialization.
-        """
-        if data is None:
-            return None
-        return json.dumps(data)

src/backend/core/filters.py

@@ -2,31 +2,9 @@
 
 import unicodedata
 
-import django_filters
-
 
 def remove_accents(value):
     """Remove accents from a string (vélo -> velo)."""
     return "".join(
         c for c in unicodedata.normalize("NFD", value) if unicodedata.category(c) != "Mn"
     )
-
-
-class AccentInsensitiveCharFilter(django_filters.CharFilter):
-    """
-    A custom CharFilter that filters on the accent-insensitive value searched.
-    """
-
-    def filter(self, qs, value):
-        """
-        Apply the filter to the queryset using the unaccented version of the field.
-
-        Args:
-            qs: The queryset to filter.
-            value: The value to search for in the unaccented field.
-        Returns:
-            A filtered queryset.
-        """
-        if value:
-            value = remove_accents(value)
-        return super().filter(qs, value)

src/backend/core/templates/core/generate_document.html

@@ -1,14 +0,0 @@
-<!DOCTYPE html>
-<html>
-<head>
-    <title>Generate Document</title>
-</head>
-<body>
-    <h2>Generate Document</h2>
-    <form method="post" enctype="multipart/form-data">
-        {% csrf_token %}
-        {{ form.as_p }}
-        <button type="submit">Generate PDF</button>
-    </form>
-</body>
-</html>

src/backend/core/templatetags/extra_tags.py

@@ -1,58 +0,0 @@
-"""Custom template tags for the core application of People."""
-
-import base64
-
-from django import template
-from django.contrib.staticfiles import finders
-
-from PIL import ImageFile as PillowImageFile
-
-register = template.Library()
-
-
-def image_to_base64(file_or_path, close=False):
-    """
-    Return the src string of the base64 encoding of an image represented by its path
-    or file opened or not.
-
-    Inspired by Django's "get_image_dimensions"
-    """
-    pil_parser = PillowImageFile.Parser()
-    if hasattr(file_or_path, "read"):
-        file = file_or_path
-        if file.closed and hasattr(file, "open"):
-            file_or_path.open()
-        file_pos = file.tell()
-        file.seek(0)
-    else:
-        try:
-            # pylint: disable=consider-using-with
-            file = open(file_or_path, "rb")
-        except OSError:
-            return ""
-        close = True
-
-    try:
-        image_data = file.read()
-        if not image_data:
-            return ""
-        pil_parser.feed(image_data)
-        if pil_parser.image:
-            mime_type = pil_parser.image.get_format_mimetype()
-            encoded_string = base64.b64encode(image_data)
-            return f"data:{mime_type:s};base64, {encoded_string.decode('utf-8'):s}"
-        return ""
-    finally:
-        if close:
-            file.close()
-        else:
-            file.seek(file_pos)
-
-
-@register.simple_tag
-def base64_static(path):
-    """Return a static file into a base64."""
-    full_path = finders.find(path)
-    if full_path:
-        return image_to_base64(full_path, True)
-    return ""

src/backend/locale/de_DE/LC_MESSAGES/django.po

@@ -3,7 +3,7 @@ msgstr ""
 "Project-Id-Version: la-suite-conversations\n"
 "Report-Msgid-Bugs-To: \n"
 "POT-Creation-Date: 2025-10-20 21:48+0000\n"
-"PO-Revision-Date: 2025-12-15 13:49\n"
+"PO-Revision-Date: 2026-01-16 11:04\n"
 "Last-Translator: \n"
 "Language-Team: German\n"
 "Language: de_DE\n"

src/backend/locale/en_US/LC_MESSAGES/django.po

@@ -3,7 +3,7 @@ msgstr ""
 "Project-Id-Version: la-suite-conversations\n"
 "Report-Msgid-Bugs-To: \n"
 "POT-Creation-Date: 2025-10-20 21:48+0000\n"
-"PO-Revision-Date: 2025-12-15 13:49\n"
+"PO-Revision-Date: 2026-01-16 11:04\n"
 "Last-Translator: \n"
 "Language-Team: English\n"
 "Language: en_US\n"

src/backend/locale/fr_FR/LC_MESSAGES/django.po

@@ -3,7 +3,7 @@ msgstr ""
 "Project-Id-Version: la-suite-conversations\n"
 "Report-Msgid-Bugs-To: \n"
 "POT-Creation-Date: 2025-10-20 21:48+0000\n"
-"PO-Revision-Date: 2025-12-15 13:49\n"
+"PO-Revision-Date: 2026-01-16 11:04\n"
 "Last-Translator: \n"
 "Language-Team: French\n"
 "Language: fr_FR\n"

src/backend/locale/nl_NL/LC_MESSAGES/django.po

@@ -3,7 +3,7 @@ msgstr ""
 "Project-Id-Version: la-suite-conversations\n"
 "Report-Msgid-Bugs-To: \n"
 "POT-Creation-Date: 2025-10-20 21:48+0000\n"
-"PO-Revision-Date: 2025-12-15 13:49\n"
+"PO-Revision-Date: 2026-01-16 11:04\n"
 "Last-Translator: \n"
 "Language-Team: Dutch\n"
 "Language: nl_NL\n"

src/backend/locale/ru_RU/LC_MESSAGES/django.po

@@ -3,7 +3,7 @@ msgstr ""
 "Project-Id-Version: la-suite-conversations\n"
 "Report-Msgid-Bugs-To: \n"
 "POT-Creation-Date: 2025-10-20 21:48+0000\n"
-"PO-Revision-Date: 2025-12-15 13:49\n"
+"PO-Revision-Date: 2026-01-16 11:04\n"
 "Last-Translator: \n"
 "Language-Team: Russian\n"
 "Language: ru_RU\n"

src/backend/locale/uk_UA/LC_MESSAGES/django.po

@@ -3,7 +3,7 @@ msgstr ""
 "Project-Id-Version: la-suite-conversations\n"
 "Report-Msgid-Bugs-To: \n"
 "POT-Creation-Date: 2025-10-20 21:48+0000\n"
-"PO-Revision-Date: 2025-12-15 13:49\n"
+"PO-Revision-Date: 2026-01-16 11:04\n"
 "Last-Translator: \n"
 "Language-Team: Ukrainian\n"
 "Language: uk_UA\n"

src/backend/pyproject.toml

@@ -46,6 +46,7 @@ dependencies = [
     "easy_thumbnails==2.10.1",
     "factory_boy==3.3.3",
     "gunicorn==23.0.0",
+    "jaraco.context>=6.1.0",
     "jsonschema==4.25.1",
     "langfuse==3.10.0",
     "lxml==5.4.0",

src/backend/utils/oidc.py

@@ -0,0 +1,54 @@
+"""Utility functions for OIDC token management."""
+
+from functools import wraps
+
+from django.conf import settings
+
+import requests
+from lasuite.oidc_login.backends import get_oidc_refresh_token, store_tokens
+from rest_framework.exceptions import AuthenticationFailed
+
+
+def refresh_access_token(session):
+    """Refresh the OIDC access token using the refresh token."""
+    refresh_token = get_oidc_refresh_token(session)
+    if not refresh_token:
+        raise AuthenticationFailed({"error": "Refresh token is missing from session"})
+
+    response = requests.post(
+        settings.OIDC_OP_TOKEN_ENDPOINT,
+        data={
+            "grant_type": "refresh_token",
+            "client_id": settings.OIDC_RP_CLIENT_ID,
+            "client_secret": settings.OIDC_RP_CLIENT_SECRET,
+            "refresh_token": refresh_token,
+        },
+        timeout=5,
+    )
+    response.raise_for_status()
+    token_info = response.json()
+
+    store_tokens(
+        session,
+        access_token=token_info.get("access_token"),
+        id_token=None,
+        refresh_token=token_info.get("refresh_token"),
+    )
+    return session
+
+
+def with_fresh_access_token(func):
+    """
+    Decorator to handle OIDC token refresh and extraction.
+    Expects 'session' in kwargs and update it with the fresh token.
+    """
+
+    @wraps(func)
+    def wrapper(*args, **kwargs):
+        session = kwargs.pop("session", None)
+        if session is None:
+            raise AuthenticationFailed({"error": "Session is required but not provided"})
+        refreshed_session = refresh_access_token(session)
+        return func(*args, session=refreshed_session, **kwargs)
+
+    return wrapper

src/frontend/apps/conversations/package.json

@@ -1,6 +1,6 @@
 {
   "name": "app-conversations",
-  "version": "0.0.10",
+  "version": "0.0.11",
   "private": true,
   "scripts": {
     "dev": "next dev",
@@ -9,6 +9,7 @@
     "build-theme": "cunningham -g css,ts -o src/cunningham --utility-classes && yarn prettier && yarn stylelint --fix",
     "start": "npx -y serve@latest out",
     "lint": "tsc --noEmit && next lint",
+    "lint:fix": "tsc --noEmit && next lint --fix",
     "prettier": "prettier --write .",
     "stylelint": "stylelint \"**/*.css\"",
     "test": "jest",

src/frontend/apps/conversations/src/components/Loader.tsx

@@ -1,8 +1,7 @@
 import dynamic from 'next/dynamic';
 
-import searchingAnimation from '@/assets/lotties/searching';
-
 const Lottie = dynamic(() => import('lottie-react'), { ssr: false });
+import searchingAnimation from '@/assets/lotties/searching';
 
 export function Loader() {
   return (

src/frontend/apps/conversations/src/features/chat/api/useChat.tsx

@@ -44,12 +44,7 @@ interface ConversationMetadataEvent {
   conversationId: string;
   title: string;
 }
-/**
- * Type guard that determines whether a value is a ConversationMetadataEvent.
- *
- * @param item - Value to test
- * @returns `true` if `item` is a ConversationMetadataEvent, `false` otherwise.
- */
+// Type guard to check if an item is a ConversationMetadataEvent
 function isConversationMetadataEvent(
   item: unknown,
 ): item is ConversationMetadataEvent {
@@ -57,18 +52,14 @@ function isConversationMetadataEvent(
     typeof item === 'object' &&
     item !== null &&
     'type' in item &&
-    item.type === 'conversation_metadata'
+    item.type === 'conversation_metadata' &&
+    'conversationId' in item &&
+    typeof item.conversationId === 'string' &&
+    'title' in item &&
+    typeof item.title === 'string'
   );
 }
 
-/**
- * Hook that provides chat functionality with a custom fetch adapter and automatic conversation-list cache invalidation.
- *
- * The hook invokes the underlying AI chat implementation with `maxSteps` set to 3 and a fetch wrapper that appends UI-driven query parameters; when the chat stream emits a `conversation_metadata` event the hook invalidates the conversation list cache (KEY_LIST_CONVERSATION).
- *
- * @param options - Chat configuration options (note: `maxSteps` is overridden to 3 and the `fetch` implementation is replaced)
- * @returns The chat hook result object containing `data`, status flags, and control methods for interacting with the chat stream.
- */
 export function useChat(options: Omit<UseChatOptions, 'fetch'>) {
   const queryClient = useQueryClient();
 
@@ -90,4 +81,4 @@ export function useChat(options: Omit<UseChatOptions, 'fetch'>) {
     }
   }, [result.data, queryClient]);
   return result;
-}
+}

src/frontend/apps/conversations/src/features/chat/components/ChatMessage.tsx

@@ -1,386 +0,0 @@
-import {
-  Message,
-  ReasoningUIPart,
-  SourceUIPart,
-  ToolInvocationUIPart,
-} from '@ai-sdk/ui-utils';
-import 'katex/dist/katex.min.css';
-import { memo, useDeferredValue } from 'react';
-import { useTranslation } from 'react-i18next';
-import { MarkdownHooks } from 'react-markdown';
-import rehypeKatex from 'rehype-katex';
-import rehypePrettyCode from 'rehype-pretty-code';
-import remarkGfm from 'remark-gfm';
-import remarkMath from 'remark-math';
-
-import { Box, Icon, Text } from '@/components';
-import { useClipboard } from '@/hook';
-import { useResponsiveStore } from '@/stores';
-
-import { AttachmentList } from './AttachmentList';
-import { CodeBlock } from './CodeBlock';
-import { FeedbackButtons } from './FeedbackButtons';
-import { SourceItemList } from './SourceItemList';
-import { ToolInvocationItem } from './ToolInvocationItem';
-
-// Mémoriser les plugins Markdown en dehors du composant pour éviter les recréations
-const remarkPlugins = [remarkGfm, remarkMath];
-const rehypePlugins = [
-  [
-    rehypePrettyCode,
-    {
-      theme: 'github-dark-dimmed',
-    },
-  ],
-  rehypeKatex,
-];
-
-// Composants Markdown mémorisés
-// eslint-disable-next-line @typescript-eslint/no-explicit-any
-const markdownComponents: any = {
-  // eslint-disable-next-line @typescript-eslint/no-unused-vars, @typescript-eslint/no-explicit-any
-  p: ({ node, ...props }: any) => (
-    <Text
-      as="p"
-      $css="display: block"
-      $theme="greyscale"
-      $variation="850"
-      {...props}
-    />
-  ),
-  // eslint-disable-next-line @typescript-eslint/no-explicit-any
-  a: ({ children, ...props }: any) => (
-    <a target="_blank" rel="noopener noreferrer" {...props}>
-      {children}
-    </a>
-  ),
-  // eslint-disable-next-line @typescript-eslint/no-unused-vars, @typescript-eslint/no-explicit-any
-  pre: ({ node, children, ...props }: any) => (
-    <CodeBlock {...props}>{children}</CodeBlock>
-  ),
-};
-
-// Composant Markdown mémorisé pour éviter les recalculs inutiles
-const MemoizedMarkdown = memo(function MemoizedMarkdown({
-  content,
-}: {
-  content: string;
-}) {
-  return (
-    <MarkdownHooks
-      remarkPlugins={remarkPlugins}
-      // eslint-disable-next-line @typescript-eslint/no-explicit-any, @typescript-eslint/no-unsafe-assignment
-      rehypePlugins={rehypePlugins as any} // Type mismatch with react-markdown types
-      // eslint-disable-next-line @typescript-eslint/no-unsafe-assignment
-      components={markdownComponents}
-    >
-      {content}
-    </MarkdownHooks>
-  );
-});
-
-interface ChatMessageProps {
-  message: Message;
-  isLastAssistantMessageInConversation: boolean;
-  shouldApplyStreamingHeight: boolean;
-  streamingMessageHeight: number | null;
-  isCurrentlyStreaming: boolean;
-  status: 'idle' | 'streaming' | 'submitted' | 'ready' | 'error';
-  isSourceOpen: string | null;
-  conversationId: string | undefined;
-  onOpenSources: (messageId: string) => void;
-  getMetadata: (url: string) =>
-    | {
-        title: string | null;
-        favicon: string | null;
-        loading: boolean;
-        error: boolean;
-      }
-    | undefined;
-}
-
-export const ChatMessage = memo(function ChatMessage({
-  message,
-  isLastAssistantMessageInConversation,
-  shouldApplyStreamingHeight,
-  streamingMessageHeight,
-  isCurrentlyStreaming,
-  status,
-  isSourceOpen,
-  conversationId,
-  onOpenSources,
-  getMetadata,
-}: ChatMessageProps) {
-  const { t } = useTranslation();
-  const copyToClipboard = useClipboard();
-  const { isMobile } = useResponsiveStore();
-
-  const deferredContent = useDeferredValue(message.content);
-
-  const contentToRender =
-    message.role === 'assistant' ? deferredContent : message.content;
-
-  return (
-    <Box
-      key={message.id}
-      data-message-id={message.id}
-      $css={`
-        display: flex;
-        width: 100%;
-        margin: auto;
-        margin-bottom: ${isLastAssistantMessageInConversation ? '30px' : '0px'};
-        color: var(--c--theme--colors--greyscale-850);
-        padding-left: 12px;
-        padding-right: 12px;
-        max-width: 750px;
-        text-align: left;
-        overflow-wrap: anywhere;
-        flex-direction: ${message.role === 'user' ? 'row-reverse' : 'row'};
-      `}
-    >
-      <Box
-        $display="block"
-        $width={`${message.role === 'user' ? 'auto' : '100%'}`}
-      >
-        {message.experimental_attachments &&
-          message.experimental_attachments.length > 0 && (
-            <Box>
-              <AttachmentList
-                attachments={message.experimental_attachments}
-                isReadOnly={true}
-              />
-            </Box>
-          )}
-        <Box
-          $radius="8px"
-          $width={`${message.role === 'user' ? 'auto' : '100%'}`}
-          $maxWidth="100%"
-          $padding={`${message.role === 'user' ? '12px' : '0'}`}
-          $margin={{ vertical: 'base' }}
-          $background={`${message.role === 'user' ? '#EEF1F4' : 'white'}`}
-          $css={`
-            display: inline-block;
-            float: right;
-            ${shouldApplyStreamingHeight ? `min-height: ${streamingMessageHeight}px;` : ''}
-          `}
-        >
-          {message.content && (
-            <Box
-              className="mainContent-chat"
-              data-testid={
-                message.role === 'assistant'
-                  ? 'assistant-message-content'
-                  : undefined
-              }
-              $padding={{ all: 'xxs' }}
-            >
-              <p className="sr-only">
-                {message.role === 'user'
-                  ? t('You said: ')
-                  : t('Assistant IA replied: ')}
-              </p>
-              {message.role === 'user' ? (
-                <Text
-                  as="p"
-                  $css="white-space: pre-wrap; display: block;"
-                  $theme="greyscale"
-                  $variation="850"
-                >
-                  {message.content}
-                </Text>
-              ) : (
-                <MemoizedMarkdown content={contentToRender} />
-              )}
-            </Box>
-          )}
-
-          <Box $direction="column" $gap="2">
-            {isCurrentlyStreaming &&
-              isLastAssistantMessageInConversation &&
-              status === 'streaming' &&
-              message.parts?.some(
-                (part) =>
-                  part.type === 'tool-invocation' &&
-                  part.toolInvocation.toolName !== 'document_parsing',
-              ) && (
-                <Box
-                  $direction="row"
-                  $align="center"
-                  $gap="6px"
-                  $width="100%"
-                  $maxWidth="750px"
-                  $margin={{
-                    all: 'auto',
-                    top: 'base',
-                    bottom: 'md',
-                  }}
-                >
-                  <Text $variation="600" $size="md">
-                    {(() => {
-                      const toolInvocation = message.parts?.find(
-                        (part) =>
-                          part.type === 'tool-invocation' &&
-                          part.toolInvocation.toolName !== 'document_parsing',
-                      );
-                      if (
-                        toolInvocation?.type === 'tool-invocation' &&
-                        toolInvocation.toolInvocation.toolName === 'summarize'
-                      ) {
-                        return t('Summarizing...');
-                      }
-                      return t('Search...');
-                    })()}
-                  </Text>
-                </Box>
-              )}
-            {message.parts
-              ?.filter(
-                (part) =>
-                  part.type === 'reasoning' || part.type === 'tool-invocation',
-              )
-              .map(
-                (
-                  part: ReasoningUIPart | ToolInvocationUIPart,
-                  partIndex: number,
-                ) =>
-                  part.type === 'reasoning' ? (
-                    <Box
-                      key={`reasoning-${partIndex}`}
-                      $background="var(--c--theme--colors--greyscale-100)"
-                      $color="var(--c--theme--colors--greyscale-500)"
-                      $padding={{ all: 'sm' }}
-                      $radius="md"
-                      $css="font-size: 0.9em;"
-                    >
-                      {part.reasoning}
-                    </Box>
-                  ) : part.type === 'tool-invocation' &&
-                    isCurrentlyStreaming &&
-                    isLastAssistantMessageInConversation ? (
-                    <ToolInvocationItem
-                      key={`tool-invocation-${partIndex}`}
-                      toolInvocation={part.toolInvocation}
-                      status={status}
-                      hideSearchLoader={true}
-                    />
-                  ) : null,
-              )}
-          </Box>
-          {message.role === 'assistant' &&
-            !(
-              isLastAssistantMessageInConversation && status === 'streaming'
-            ) && (
-              <Box
-                $css="color: #222631; font-size: 12px;"
-                $direction="row"
-                $align="center"
-                $justify="space-between"
-                $gap="6px"
-                $margin={{ top: 'base' }}
-              >
-                <Box $direction="row" $gap="4px">
-                  <Box
-                    $direction="row"
-                    $align="center"
-                    $gap="4px"
-                    className="c__button--neutral action-chat-button"
-                    onClick={() => copyToClipboard(message.content)}
-                    onKeyDown={(e) => {
-                      if (e.key === 'Enter' || e.key === ' ') {
-                        e.preventDefault();
-                        copyToClipboard(message.content);
-                      }
-                    }}
-                    role="button"
-                    tabIndex={0}
-                  >
-                    <Icon
-                      iconName="content_copy"
-                      $theme="greyscale"
-                      $variation="550"
-                      $size="16px"
-                      className="action-chat-button-icon"
-                    />
-                    {!isMobile && (
-                      <Text $theme="greyscale" $variation="550">
-                        {t('Copy')}
-                      </Text>
-                    )}
-                  </Box>
-                  {message.parts?.some((part) => part.type === 'source') &&
-                    (() => {
-                      const sourceCount =
-                        message.parts?.filter((part) => part.type === 'source')
-                          .length || 0;
-                      return (
-                        <Box
-                          $direction="row"
-                          $align="center"
-                          $gap="4px"
-                          className={`c__button--neutral action-chat-button ${isSourceOpen === message.id ? 'action-chat-button--open' : ''}`}
-                          onClick={() => onOpenSources(message.id)}
-                          onKeyDown={(e) => {
-                            if (e.key === 'Enter' || e.key === ' ') {
-                              e.preventDefault();
-                              onOpenSources(message.id);
-                            }
-                          }}
-                          role="button"
-                          tabIndex={0}
-                        >
-                          <Icon
-                            iconName="book"
-                            $theme="greyscale"
-                            $variation="550"
-                            $size="16px"
-                            className="action-chat-button-icon"
-                          />
-                          <Text
-                            $theme="greyscale"
-                            $variation="550"
-                            $weight="500"
-                            $size="12px"
-                          >
-                            {t('Show')} {sourceCount}{' '}
-                            {sourceCount !== 1 ? t('sources') : t('source')}
-                          </Text>
-                        </Box>
-                      );
-                    })()}
-                </Box>
-                <Box $direction="row" $gap="4px">
-                  {conversationId &&
-                    message.id &&
-                    message.id.startsWith('trace-') && (
-                      <FeedbackButtons
-                        conversationId={conversationId}
-                        messageId={message.id}
-                      />
-                    )}
-                </Box>
-              </Box>
-            )}
-          {message.parts &&
-            isSourceOpen === message.id &&
-            (() => {
-              const sourceParts = message.parts.filter(
-                (part): part is SourceUIPart => part.type === 'source',
-              );
-              return (
-                <Box
-                  $css={`
-                    animation: fade-in 0.2s ease-out;
-                  `}
-                >
-                  <SourceItemList
-                    parts={sourceParts}
-                    getMetadata={getMetadata}
-                  />
-                </Box>
-              );
-            })()}
-        </Box>
-      </Box>
-    </Box>
-  );
-});

src/frontend/apps/conversations/src/features/chat/hooks/index.ts

@@ -1,3 +1,2 @@
 export { useChatScroll } from './useChatScroll';
 export { useSourceMetadataCache } from './useSourceMetadata';
-export { useModelSelection } from './useModelSelection';

src/frontend/apps/conversations/src/features/chat/hooks/useModelSelection.ts

@@ -1,44 +0,0 @@
-import { useEffect, useRef, useState } from 'react';
-
-import { LLMModel, useLLMConfiguration } from '../api/useLLMConfiguration';
-import { useChatPreferencesStore } from '../stores/useChatPreferencesStore';
-
-export const useModelSelection = () => {
-  const { data: llmConfig } = useLLMConfiguration();
-  const { selectedModelHrid, setSelectedModelHrid } = useChatPreferencesStore();
-  const [selectedModel, setSelectedModel] = useState<LLMModel | null>(null);
-  const hasInitializedRef = useRef(false);
-
-  useEffect(() => {
-    // Ne s'exécuter qu'une seule fois quand llmConfig est chargé
-    if (llmConfig?.models && !hasInitializedRef.current) {
-      let modelToSelect: LLMModel | undefined;
-
-      if (selectedModelHrid) {
-        // Try to find the previously selected model
-        modelToSelect = llmConfig.models.find(
-          (model) =>
-            model.hrid === selectedModelHrid && model.is_active !== false,
-        );
-      }
-
-      // If no saved model or saved model not found/inactive, use default
-      if (!modelToSelect) {
-        modelToSelect = llmConfig.models.find((model) => model.is_default);
-      }
-
-      if (modelToSelect) {
-        setSelectedModel(modelToSelect);
-        setSelectedModelHrid(modelToSelect.hrid);
-        hasInitializedRef.current = true;
-      }
-    }
-  }, [llmConfig?.models, selectedModelHrid, setSelectedModelHrid]);
-
-  const handleModelSelect = (model: LLMModel) => {
-    setSelectedModel(model);
-    setSelectedModelHrid(model.hrid);
-  };
-
-  return { selectedModel, handleModelSelect };
-};

src/frontend/apps/conversations/src/features/left-panel/components/ConversationItemActions.tsx

@@ -21,6 +21,13 @@ export const ConversationItemActions = ({
   const renameModal = useModal();
 
   const options: DropdownMenuOption[] = [
+    {
+      label: t('Rename chat'),
+      icon: 'edit',
+      callback: () => renameModal.open(),
+      disabled: false,
+      testId: `conversation-item-actions-rename-${conversation.id}`,
+    },
     {
       label: t('Delete chat'),
       icon: 'delete',
@@ -28,13 +35,6 @@ export const ConversationItemActions = ({
       disabled: false,
       testId: `conversation-item-actions-remove-${conversation.id}`,
     },
-    {
-      label: t('Rename chat'),
-      icon: 'tune',
-      callback: () => renameModal.open(),
-      disabled: false,
-      testId: `conversation-item-actions-rename-${conversation.id}`,
-    },
   ];
 
   return (

src/frontend/apps/conversations/src/features/left-panel/components/LeftPanelConversationItem.tsx

@@ -58,7 +58,7 @@ export const LeftPanelConversationItem = ({
     >
       <StyledLink
         href={`/chat/${conversation.id}/`}
-        $css="overflow: auto; flex-grow: 1;"
+        $css="overflow: auto; flex-grow: 1; color: var(--c--theme--colors--greyscale-900);"
         onClick={handleLinkClick}
       >
         <SimpleConversationItem showAccesses conversation={conversation} />

src/frontend/apps/conversations/src/features/left-panel/components/ModalRemoveConversation.tsx

@@ -46,7 +46,7 @@ export const ModalRemoveConversation = ({
         <>
           <Button
             aria-label={t('Close the modal')}
-            color="secondary"
+            color="tertiary"
             fullWidth
             onClick={() => onClose()}
           >
@@ -79,7 +79,10 @@ export const ModalRemoveConversation = ({
         </Text>
       }
     >
-      <Box className="--conversations--modal-remove-chat">
+      <Box
+        className="--conversations--modal-remove-chat"
+        data-testid="delete-chat-confirm"
+      >
         <Text $size="sm" $variation="600">
           {t('Are you sure you want to delete this conversation ?')}
         </Text>

src/frontend/apps/conversations/src/features/left-panel/components/ModalRenameConversation.tsx

@@ -1,12 +1,12 @@
 import { Button, Input, Modal, ModalSize } from '@openfun/cunningham-react';
-import { t } from 'i18next';
 import { useState } from 'react';
+import { useTranslation } from 'react-i18next';
 
 import { Box, Text, useToast } from '@/components';
 import { useRenameConversation } from '@/features/chat/api/useRenameConversation';
 import { ChatConversation } from '@/features/chat/types';
 
-interface ModalRenameConversation {
+interface ModalRenameConversationProps {
   onClose: () => void;
   conversation: ChatConversation;
 }
@@ -14,9 +14,9 @@ interface ModalRenameConversation {
 export const ModalRenameConversation = ({
   onClose,
   conversation,
-}: ModalRenameConversation) => {
+}: ModalRenameConversationProps) => {
   const { showToast } = useToast();
-
+  const { t } = useTranslation();
   const { mutate: renameConversation } = useRenameConversation({
     onSuccess: () => {
       showToast(
@@ -32,17 +32,18 @@ export const ModalRenameConversation = ({
         error.cause?.[0] ||
         error.message ||
         t('An error occurred while renaming the conversation');
-      showToast('error', t(errorMessage), undefined, 4000);
+      showToast('error', errorMessage, undefined, 4000);
     },
   });
 
   const [newName, setNewName] = useState(conversation.title ?? '');
   const handleSubmit = (e: React.FormEvent) => {
     e.preventDefault();
-    if (newName.trim()) {
+    const trimmedNewName = newName.trim();
+    if (trimmedNewName) {
       renameConversation({
         conversationId: conversation.id,
-        title: newName,
+        title: trimmedNewName,
       });
     }
   };
@@ -56,7 +57,7 @@ export const ModalRenameConversation = ({
         <>
           <Button
             aria-label={t('Close the modal')}
-            color="secondary"
+            color="tertiary"
             onClick={() => onClose()}
           >
             {t('Cancel')}
@@ -85,10 +86,17 @@ export const ModalRenameConversation = ({
       }
     >
       <Box className="--conversations--modal-rename-chat">
-        <form onSubmit={handleSubmit} id="rename-chat-form" className="mt-s">
+        <form
+          onSubmit={handleSubmit}
+          id="rename-chat-form"
+          data-testid="rename-chat-form"
+          className="mt-s"
+        >
           <Input
+            type="text"
             label={t('New name')}
             maxLength={100}
+            value={newName}
             onChange={(e: React.ChangeEvent<HTMLInputElement>) => {
               setNewName(e.target.value);
             }}

src/frontend/apps/conversations/src/features/left-panel/components/__tests__/ConversationItemActions.test.tsx

@@ -0,0 +1,255 @@
+import { CunninghamProvider } from '@openfun/cunningham-react';
+import { render, screen, waitFor } from '@testing-library/react';
+import userEvent from '@testing-library/user-event';
+
+import { ToastProvider } from '@/components';
+import { ChatConversation } from '@/features/chat/types';
+
+import { ConversationItemActions } from '../ConversationItemActions';
+
+const mockPush = jest.fn();
+let mockPathname = '/';
+
+jest.mock('next/router', () => ({
+  useRouter: () => ({
+    push: mockPush,
+    pathname: mockPathname,
+    route: '/',
+    query: {},
+    asPath: '/',
+  }),
+}));
+
+jest.mock('next/navigation', () => ({
+  usePathname: () => mockPathname,
+}));
+
+jest.mock('react-i18next', () => ({
+  useTranslation: () => ({
+    t: (key: string, options?: Record<string, string>) => {
+      if (options) {
+        return Object.entries(options).reduce(
+          (acc, [k, v]) => acc.replace(`{{${k}}}`, v),
+          key,
+        );
+      }
+      return key;
+    },
+  }),
+}));
+
+jest.mock('i18next', () => ({
+  t: (key: string) => key,
+}));
+
+jest.mock('@/features/chat/api/useRenameConversation', () => ({
+  useRenameConversation: () => ({
+    mutate: jest.fn(),
+  }),
+}));
+
+jest.mock('@/features/chat/api/useRemoveConversation', () => ({
+  useRemoveConversation: () => ({
+    mutate: jest.fn(),
+  }),
+}));
+
+const renderWithProviders = (ui: React.ReactNode) => {
+  return render(
+    <CunninghamProvider>
+      <ToastProvider>{ui}</ToastProvider>
+    </CunninghamProvider>,
+  );
+};
+
+describe('ConversationItemActions', () => {
+  const mockConversation: ChatConversation = {
+    id: 'conv-123',
+    title: 'Original Title',
+    messages: [],
+    created_at: new Date().toISOString(),
+    updated_at: new Date().toISOString(),
+  };
+  beforeEach(() => {
+    jest.clearAllMocks();
+    mockPathname = '/';
+  });
+
+  const renderComponent = (conversation = mockConversation) => {
+    return renderWithProviders(
+      <ConversationItemActions conversation={conversation} />,
+    );
+  };
+
+  it('renders the actions button', () => {
+    renderComponent();
+
+    expect(
+      screen.getByTestId(
+        `conversation-item-actions-button-${mockConversation.id}`,
+      ),
+    ).toBeInTheDocument();
+  });
+
+  it('renders dropdown menu with correct aria-label', () => {
+    renderComponent();
+
+    expect(
+      screen.getByLabelText(
+        `Actions list for conversation ${mockConversation.title}`,
+      ),
+    ).toBeInTheDocument();
+  });
+
+  it('renders dropdown menu with fallback title when conversation has no title', () => {
+    const untitledConversation = { ...mockConversation, title: '' };
+    renderComponent(untitledConversation);
+
+    expect(
+      screen.getByLabelText(
+        `Actions list for conversation Untitled conversation`,
+      ),
+    ).toBeInTheDocument();
+  });
+
+  it('opens dropdown menu when clicking the actions button', async () => {
+    const user = userEvent.setup();
+    renderComponent();
+
+    const actionsButton = screen.getByLabelText(
+      `Actions list for conversation ${mockConversation.title}`,
+    );
+    await user.click(actionsButton);
+
+    expect(
+      screen.getByTestId(
+        `conversation-item-actions-rename-${mockConversation.id}`,
+      ),
+    ).toBeInTheDocument();
+    expect(
+      screen.getByTestId(
+        `conversation-item-actions-remove-${mockConversation.id}`,
+      ),
+    ).toBeInTheDocument();
+  });
+
+  it('displays rename and delete options in the dropdown', async () => {
+    const user = userEvent.setup();
+    renderComponent();
+
+    const actionsButton = screen.getByLabelText(
+      `Actions list for conversation ${mockConversation.title}`,
+    );
+    await user.click(actionsButton);
+
+    expect(screen.getByText('Rename chat')).toBeInTheDocument();
+    expect(screen.getByText('Delete chat')).toBeInTheDocument();
+  });
+
+  it('opens rename modal when clicking rename option', async () => {
+    const user = userEvent.setup();
+    renderComponent();
+
+    const actionsButton = screen.getByLabelText(
+      `Actions list for conversation ${mockConversation.title}`,
+    );
+    await user.click(actionsButton);
+
+    const renameOption = screen.getByTestId(
+      `conversation-item-actions-rename-${mockConversation.id}`,
+    );
+    await user.click(renameOption);
+    // Modal should be open
+    await waitFor(() => {
+      expect(screen.getByRole('dialog')).toBeInTheDocument();
+    });
+
+    expect(screen.getByRole('textbox')).toHaveValue(mockConversation.title);
+
+    expect(screen.getByTestId('rename-chat-form')).toBeInTheDocument();
+  });
+
+  it('opens delete modal when clicking delete option', async () => {
+    const user = userEvent.setup();
+    renderComponent();
+
+    const actionsButton = screen.getByLabelText(
+      `Actions list for conversation ${mockConversation.title}`,
+    );
+    await user.click(actionsButton);
+
+    const deleteOption = screen.getByTestId(
+      `conversation-item-actions-remove-${mockConversation.id}`,
+    );
+    await user.click(deleteOption);
+
+    await waitFor(() => {
+      expect(screen.getByRole('dialog')).toBeInTheDocument();
+    });
+    expect(screen.getByTestId('delete-chat-confirm')).toBeInTheDocument();
+  });
+
+  it('does not render modals initially', () => {
+    renderComponent();
+
+    expect(screen.queryByRole('dialog')).not.toBeInTheDocument();
+    expect(screen.queryByTestId('delete-chat-confirm')).not.toBeInTheDocument();
+    expect(screen.queryByTestId('rename-chat-form')).not.toBeInTheDocument();
+  });
+
+  it('closes rename modal when onClose is called', async () => {
+    const user = userEvent.setup();
+    renderComponent();
+
+    // Open dropdown and click rename
+    const actionsButton = screen.getByLabelText(
+      `Actions list for conversation ${mockConversation.title}`,
+    );
+    await user.click(actionsButton);
+    await user.click(
+      screen.getByTestId(
+        `conversation-item-actions-rename-${mockConversation.id}`,
+      ),
+    );
+
+    // Modal should be open
+    await waitFor(() => {
+      expect(screen.getByRole('dialog')).toBeInTheDocument();
+    });
+
+    // Close the modal
+    await user.click(screen.getByText('Cancel'));
+
+    await waitFor(() => {
+      expect(screen.queryByRole('dialog')).not.toBeInTheDocument();
+    });
+  });
+
+  it('closes delete modal when onClose is called', async () => {
+    const user = userEvent.setup();
+    renderComponent();
+
+    // Open dropdown and click delete
+    const actionsButton = screen.getByLabelText(
+      `Actions list for conversation ${mockConversation.title}`,
+    );
+    await user.click(actionsButton);
+    await user.click(
+      screen.getByTestId(
+        `conversation-item-actions-remove-${mockConversation.id}`,
+      ),
+    );
+
+    // Modal should be open
+    await waitFor(() => {
+      expect(screen.getByRole('dialog')).toBeInTheDocument();
+    });
+
+    // Close the modal
+    await user.click(screen.getByText('Cancel'));
+
+    await waitFor(() => {
+      expect(screen.queryByRole('dialog')).not.toBeInTheDocument();
+    });
+  });
+});

src/frontend/apps/conversations/src/features/left-panel/components/__tests__/ModalRenameConversation.test.tsx

@@ -0,0 +1,280 @@
+import { CunninghamProvider } from '@openfun/cunningham-react';
+import { render, screen, waitFor } from '@testing-library/react';
+import userEvent from '@testing-library/user-event';
+
+import { useToast } from '@/components';
+import { useRenameConversation } from '@/features/chat/api/useRenameConversation';
+import { ChatConversation } from '@/features/chat/types';
+
+import { ModalRenameConversation } from '../ModalRenameConversation';
+
+jest.mock('@/components', () => ({
+  ...jest.requireActual('@/components'),
+  useToast: jest.fn(),
+}));
+
+jest.mock('@/features/chat/api/useRenameConversation');
+
+jest.mock('react-i18next', () => ({
+  useTranslation: () => ({
+    t: (key: string, options?: Record<string, string>) => {
+      if (options) {
+        return Object.entries(options).reduce(
+          (acc, [k, v]) => acc.replace(`{{${k}}}`, v),
+          key,
+        );
+      }
+      return key;
+    },
+  }),
+}));
+jest.mock('i18next', () => ({
+  t: (key: string) => key,
+}));
+const renderWithProviders = (component: React.ReactNode) => {
+  return render(<CunninghamProvider>{component}</CunninghamProvider>);
+};
+
+describe('ModalRenameConversation', () => {
+  const mockOnClose = jest.fn();
+  const mockShowToast = jest.fn();
+  const mockRenameConversation = jest.fn();
+
+  const mockConversation: ChatConversation = {
+    id: 'conv-123',
+    title: 'Original Title',
+    messages: [],
+    created_at: new Date().toISOString(),
+    updated_at: new Date().toISOString(),
+  } as ChatConversation;
+
+  beforeEach(() => {
+    jest.clearAllMocks();
+    (useToast as jest.Mock).mockReturnValue({
+      showToast: mockShowToast,
+    });
+    (useRenameConversation as jest.Mock).mockReturnValue({
+      mutate: mockRenameConversation,
+    });
+  });
+
+  it('renders the modal with correct title and initial value', () => {
+    renderWithProviders(
+      <ModalRenameConversation
+        onClose={mockOnClose}
+        conversation={mockConversation}
+      />,
+    );
+
+    expect(screen.getByText('Rename chat')).toBeInTheDocument();
+    expect(screen.getByRole('textbox')).toHaveValue('Original Title');
+    expect(screen.getByText('Cancel')).toBeInTheDocument();
+    expect(screen.getByText('Rename')).toBeInTheDocument();
+  });
+
+  it('updates input value when user types', async () => {
+    const user = userEvent.setup();
+    renderWithProviders(
+      <ModalRenameConversation
+        onClose={mockOnClose}
+        conversation={mockConversation}
+      />,
+    );
+
+    const input = screen.getByRole('textbox');
+
+    await user.clear(input);
+    await user.type(input, 'New Title');
+
+    expect(input).toHaveValue('New Title');
+  });
+
+  it('closes modal when Cancel button is clicked', async () => {
+    const user = userEvent.setup();
+    renderWithProviders(
+      <ModalRenameConversation
+        onClose={mockOnClose}
+        conversation={mockConversation}
+      />,
+    );
+
+    await user.click(screen.getByText('Cancel'));
+
+    expect(mockOnClose).toHaveBeenCalledTimes(1);
+  });
+
+  it('submits form with new name and shows success toast', async () => {
+    const user = userEvent.setup();
+    let onSuccessCallback: (() => void) | undefined;
+
+    (useRenameConversation as jest.Mock).mockImplementation(({ onSuccess }) => {
+      onSuccessCallback = onSuccess;
+      return { mutate: mockRenameConversation };
+    });
+
+    renderWithProviders(
+      <ModalRenameConversation
+        onClose={mockOnClose}
+        conversation={mockConversation}
+      />,
+    );
+
+    const input = screen.getByRole('textbox');
+    await user.clear(input);
+    await user.type(input, 'Updated Title');
+    await user.click(screen.getByText('Rename'));
+
+    expect(mockRenameConversation).toHaveBeenCalledWith({
+      conversationId: 'conv-123',
+      title: 'Updated Title',
+    });
+
+    onSuccessCallback?.();
+
+    await waitFor(() => {
+      expect(mockShowToast).toHaveBeenCalledWith(
+        'success',
+        'The conversation has been renamed.',
+        undefined,
+        4000,
+      );
+    });
+    expect(mockOnClose).toHaveBeenCalled();
+  });
+
+  it('does not submit form when new name is empty or whitespace', async () => {
+    const user = userEvent.setup();
+    renderWithProviders(
+      <ModalRenameConversation
+        onClose={mockOnClose}
+        conversation={mockConversation}
+      />,
+    );
+
+    const input = screen.getByRole('textbox');
+    await user.clear(input);
+    await user.type(input, '   ');
+    await user.click(screen.getByText('Rename'));
+
+    expect(mockRenameConversation).not.toHaveBeenCalled();
+  });
+
+  it('shows error toast when rename fails with cause', async () => {
+    const user = userEvent.setup();
+    let onErrorCallback: ((error: any) => void) | undefined;
+
+    (useRenameConversation as jest.Mock).mockImplementation(({ onError }) => {
+      onErrorCallback = onError;
+      return { mutate: mockRenameConversation };
+    });
+
+    renderWithProviders(
+      <ModalRenameConversation
+        onClose={mockOnClose}
+        conversation={mockConversation}
+      />,
+    );
+
+    const input = screen.getByRole('textbox');
+    await user.clear(input);
+    await user.type(input, 'New Title');
+    await user.click(screen.getByText('Rename'));
+
+    const error = {
+      cause: ['Specific error from API'],
+      message: 'Generic error',
+    };
+    onErrorCallback?.(error);
+
+    await waitFor(() => {
+      expect(mockShowToast).toHaveBeenCalledWith(
+        'error',
+        'Specific error from API',
+        undefined,
+        4000,
+      );
+    });
+  });
+
+  it('shows error toast with message when no cause is provided', async () => {
+    const user = userEvent.setup();
+    let onErrorCallback: ((error: any) => void) | undefined;
+
+    (useRenameConversation as jest.Mock).mockImplementation(({ onError }) => {
+      onErrorCallback = onError;
+      return { mutate: mockRenameConversation };
+    });
+
+    renderWithProviders(
+      <ModalRenameConversation
+        onClose={mockOnClose}
+        conversation={mockConversation}
+      />,
+    );
+
+    const input = screen.getByRole('textbox');
+    await user.clear(input);
+    await user.type(input, 'New Title');
+    await user.click(screen.getByText('Rename'));
+
+    const error = {
+      message: 'Network error',
+    };
+    onErrorCallback?.(error);
+
+    await waitFor(() => {
+      expect(mockShowToast).toHaveBeenCalledWith(
+        'error',
+        'Network error',
+        undefined,
+        4000,
+      );
+    });
+  });
+
+  it('shows default error message when error has no cause or message', async () => {
+    const user = userEvent.setup();
+    let onErrorCallback: ((error: any) => void) | undefined;
+
+    (useRenameConversation as jest.Mock).mockImplementation(({ onError }) => {
+      onErrorCallback = onError;
+      return { mutate: mockRenameConversation };
+    });
+
+    renderWithProviders(
+      <ModalRenameConversation
+        onClose={mockOnClose}
+        conversation={mockConversation}
+      />,
+    );
+
+    const input = screen.getByRole('textbox');
+    await user.clear(input);
+    await user.type(input, 'New Title');
+    await user.click(screen.getByText('Rename'));
+
+    const error = {};
+    onErrorCallback?.(error);
+
+    await waitFor(() => {
+      expect(mockShowToast).toHaveBeenCalledWith(
+        'error',
+        'An error occurred while renaming the conversation',
+        undefined,
+        4000,
+      );
+    });
+  });
+
+  it('enforces maxLength of 100 characters on input', () => {
+    renderWithProviders(
+      <ModalRenameConversation
+        onClose={mockOnClose}
+        conversation={mockConversation}
+      />,
+    );
+
+    const input = screen.getByRole('textbox');
+    expect(input).toHaveAttribute('maxLength', '100');
+  });
+});

src/frontend/apps/conversations/src/i18n/translations.json

@@ -31,7 +31,6 @@
       "Close the modal": "Fermer la modale",
       "Confirm deletion": "Confirmer la suppression",
       "Content modal to delete conversation": "Modale pour supprimer la conversation",
-      "Content modal to rename conversation": "Modale pour renommer la conversation",
       "Conversation analysis disabled": "Analyse de la conversation désactivée",
       "Conversation analysis enabled": "Analyse de la conversation activée",
       "Copied": "Copié",
@@ -77,7 +76,6 @@
       "Logout": "Se déconnecter",
       "New chat": "Nouvelle conversation",
       "New feedback": "Nouveaux commentaires",
-      "New name": "Nouveau nom",
       "No code? ": "Pas de code ? ",
       "No conversation found": "Aucune conversation trouvée",
       "Notify me": "Me notifier",
@@ -89,9 +87,8 @@
       "Proconnect Login": "Connexion Proconnect",
       "Quick search input": "Saisie de recherche rapide",
       "Remove attachment": "Supprimer la pièce jointe",
-      "Rename": "Renommer",
-      "Rename chat": "Renommer la conversation",
       "Research on the web": "Rechercher sur le web",
+      "Retry": "Réessayer",
       "Search": "Rechercher",
       "Search for a chat": "Rechercher un chat",
       "Search results": "Résultats de la recherche",
@@ -104,14 +101,13 @@
       "Simple chat icon": "Icône de chat simple",
       "Something bad happens, please retry.": "Une erreur inattendue s'est produite, veuillez réessayer.",
       "Sorry, an error occurred. Please try again.": "Désolé, une erreur s'est produite. Veuillez réessayer.",
-      "Start a new conversation.": "Commencer une nouvelle conversation.",
+      "Start a new conversation": "Commencer une nouvelle conversation",
       "Start conversation": "Entamer la conversation",
       "Stop": "Stop",
       "Summarizing...": "Résumé en cours...",
       "The Assistant is a sovereign conversational AI designed for public servants. It helps you save time on daily tasks like rephrasing, summarising, translating, or searching information. Your data never leaves France and is stored on secure, state-compliant infrastructures. It is never used for commercial purposes.": "L'Assistant est une IA souveraine conçue pour les fonctionnaires. Il vous permet de gagner du temps sur des tâches quotidiennes telles que la reformulation, le résumé, la traduction ou la recherche d'informations. Vos données ne quittent jamais la France et sont stockées sur des infrastructures sûres et conformes à l'état et ne sont jamais utilisées à des fins commerciales.",
       "The Assistant is in Beta": "L'Assistant est en Bêta",
       "The conversation has been deleted.": "La conversation a été supprimée.",
-      "The conversation has been renamed": "La conversation a été renom.",
       "The summary feature is not supported yet.": "La fonctionnalité de résumé n'est pas encore prise en charge.",
       "Thinking...": "Réflexion...",
       "To add a file to the conversation, drop it here.": "Pour ajouter un fichier à la conversation, déposez-le ici.",
@@ -225,6 +221,7 @@
       "Quick search input": "Snelle zoekinvoer",
       "Remove attachment": "Bijlage verwijderen",
       "Research on the web": "Onderzoek op het internet",
+      "Retry": "Opnieuw proberen",
       "Search": "Zoek",
       "Search for a chat": "Zoek naar een chat",
       "Search results": "Zoekresultaten",
@@ -237,7 +234,7 @@
       "Simple chat icon": "Eenvoudig chatpictogram",
       "Something bad happens, please retry.": "Er is iets misgegaan. Probeer het opnieuw.",
       "Sorry, an error occurred. Please try again.": "Sorry, er is een fout opgetreden. Probeer het opnieuw.",
-      "Start a new conversation.": "Begin een nieuw gesprek.",
+      "Start a new conversation": "Begin een nieuw gesprek",
       "Start conversation": "Begin een gesprek",
       "Stop": "Stop",
       "Summarizing...": "Samenvatten...",
@@ -357,6 +354,7 @@
       "Quick search input": "Быстрый поиск",
       "Remove attachment": "Удалить вложение",
       "Research on the web": "Исследование в Интернете",
+      "Retry": "Повторить",
       "Search": "Поиск",
       "Search for a chat": "Поиск беседы",
       "Search results": "Результаты поиска",
@@ -369,7 +367,7 @@
       "Simple chat icon": "Простой значок чата",
       "Something bad happens, please retry.": "Что-то пошло не так, повторите попытку.",
       "Sorry, an error occurred. Please try again.": "Извините, произошла ошибка. Пожалуйста, попробуйте ещё раз.",
-      "Start a new conversation.": "Начать новую беседу.",
+      "Start a new conversation": "Начать новую беседу",
       "Start conversation": "Начать беседу",
       "Stop": "Остановить",
       "Summarizing...": "Обобщение...",
@@ -489,6 +487,7 @@
       "Quick search input": "Швидкий пошук",
       "Remove attachment": "Видалити вкладення",
       "Research on the web": "Дослідження в Інтернеті",
+      "Retry": "Повторити",
       "Search": "Пошук",
       "Search for a chat": "Пошук розмови",
       "Search results": "Результати пошуку",
@@ -501,7 +500,7 @@
       "Simple chat icon": "Проста піктограма розмови",
       "Something bad happens, please retry.": "Сталася помилка, спробуйте ще раз.",
       "Sorry, an error occurred. Please try again.": "Вибачте, виникла помилка. Спробуйте ще раз.",
-      "Start a new conversation.": "Розпочати нову розмову.",
+      "Start a new conversation": "Розпочати нову розмову",
       "Start conversation": "Почати розмову",
       "Stop": "Зупинити",
       "Summarizing...": "Узагальнення...",

src/frontend/apps/e2e/__tests__/app-conversations/chat.spec.ts

@@ -52,7 +52,7 @@ test.describe('Chat page', () => {
 
     const messageContent = page.getByTestId('assistant-message-content');
     await expect(messageContent).toBeVisible();
-    await expect(messageContent).not.toBeEmpty(); 
+    await expect(messageContent).not.toBeEmpty();
 
     // Check history
     const chatHistoryLink = page

src/frontend/apps/e2e/package.json

@@ -1,6 +1,6 @@
 {
   "name": "app-e2e",
-  "version": "0.0.10",
+  "version": "0.0.11",
   "private": true,
   "scripts": {
     "lint": "eslint . --ext .ts",

src/frontend/package.json

@@ -1,6 +1,6 @@
 {
   "name": "conversations",
-  "version": "0.0.10",
+  "version": "0.0.11",
   "private": true,
   "workspaces": {
     "packages": [

src/frontend/packages/eslint-config-conversations/package.json

@@ -1,6 +1,6 @@
 {
   "name": "eslint-config-conversations",
-  "version": "0.0.10",
+  "version": "0.0.11",
   "license": "MIT",
   "scripts": {
     "lint": "eslint --ext .js ."

src/frontend/packages/i18n/package.json

@@ -1,6 +1,6 @@
 {
   "name": "packages-i18n",
-  "version": "0.0.10",
+  "version": "0.0.11",
   "private": true,
   "scripts": {
     "extract-translation": "yarn extract-translation:conversations",

src/frontend/yarn.lock

@@ -11355,9 +11355,9 @@ posthog-js@1.249.3:
     web-vitals "^4.2.4"
 
 preact@^10.19.3:
-  version "10.26.6"
-  resolved "https://registry.npmjs.org/preact/-/preact-10.26.6.tgz"
-  integrity sha512-5SRRBinwpwkaD+OqlBDeITlRgvd8I8QlxHJw9AxSdMNV6O+LodN9nUyYGpSF7sadHjs6RzeFShMexC6DbtWr9g==
+  version "10.24.0"
+  resolved "https://registry.npmjs.org/preact/-/preact-10.24.0.tgz"
+  integrity sha512-aK8Cf+jkfyuZ0ZZRG9FbYqwmEiGQ4y/PUO4SuTWoyWL244nZZh7bd5h2APd4rSNDYTBNghg1L+5iJN3Skxtbsw==
 
 prelude-ls@^1.2.1:
   version "1.2.1"

src/mail/package.json

@@ -1,6 +1,6 @@
 {
   "name": "mail_mjml",
-  "version": "0.0.10",
+  "version": "0.0.11",
   "description": "An util to generate html and text django's templates from mjml templates",
   "type": "module",
   "dependencies": {

src/mail/yarn.lock

@@ -399,10 +399,10 @@ glob-parent@~5.1.2:
   dependencies:
     is-glob "^4.0.1"
 
-glob@^10.3.10, glob@^10.3.3:
-  version "10.4.5"
-  resolved "https://registry.yarnpkg.com/glob/-/glob-10.4.5.tgz#f4d9f0b90ffdbab09c9d77f5f29b4262517b0956"
-  integrity sha512-7Bv8RF0k6xjo7d4A/PxYLbUCfb6c+Vpd2/mB2yRDlew7Jb5hEXiCD9ibfO7wpk8i4sevK6DFny9h7EYbM3/sHg==
+glob@^10.5.0:
+  version "10.5.0"
+  resolved "https://registry.yarnpkg.com/glob/-/glob-10.5.0.tgz#8ec0355919cd3338c28428a23d4f24ecc5fe738c"
+  integrity sha512-DfXN8DfhJ7NH3Oe7cFmu3NCu1wKbkReJ8TorzSAFbSKrlNaQSKfIzqYqVY8zlbs2NLBbWpRiU52GX2PbaBVNkg==
   dependencies:
     foreground-child "^3.1.0"
     jackspeak "^3.1.2"