✨(front) copy button preserves formatting when pasting into Word

Signed-off-by: Laurent Paoletti <lp@providenz.fr>
🐛(back) add missing color option for project colors
2026-03-24 18:48:39 +01:00 · 2026-03-24 15:12:56 +01:00 · 2026-03-23 18:04:22 +01:00 · 2026-03-17 10:49:56 +01:00 · 2026-03-16 16:41:08 +01:00 · 2026-03-16 09:50:10 +01:00
336 changed files with 38568 additions and 13852 deletions
@@ -1,6 +1,7 @@
 [codespell]
 skip =
    ./git/,
+    **/*.pdf,
    **/*.po,
    **/*.pot,
    **/*.json,
@@ -8,9 +9,12 @@ skip =
    **/node_modules/**,
    **/e2e/report/**,
    *.tsbuildinfo,
+    **/uv.lock,
+    ./docker/files/etc/mime.types,
 check-filenames = true
 ignore-words-list =
    afterAll,
    statics,
 exclude-file =
    ./src/backend/chat/agent_rag/web_search/mocked.py,
+
@@ -85,20 +85,24 @@ jobs:
      - name: Checkout repository
        uses: actions/checkout@v2
      - name: Install Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
        with:
-          python-version: "3.13.3"
-          cache: "pip"
-      - name: Upgrade pip and setuptools
-        run: pip install --upgrade pip setuptools
-      - name: Install development dependencies
-        run: pip install --user .[dev]
+          python-version: "3.13"
+      - name: Install system dependencies for lxml
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y libxml2-dev libxslt-dev
+      - name: Install uv
+        uses: astral-sh/setup-uv@v6
+      - name: Install the project
+        run: uv sync --locked --all-extras
+
      - name: Check code formatting with ruff
-        run: ~/.local/bin/ruff format . --diff
+        run: uv run ruff format . --diff
      - name: Lint code with ruff
-        run: ~/.local/bin/ruff check .
+        run: uv run ruff check .
      - name: Lint code with pylint
-        run: ~/.local/bin/pylint .
+        run: uv run pylint .

  test-back:
    runs-on: ubuntu-latest
@@ -181,22 +185,48 @@ jobs:
            mc version enable conversations/conversations-media-storage"

      - name: Install Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
        with:
-          python-version: "3.13.3"
-          cache: "pip"
-
-      - name: Install development dependencies
-        run: pip install --user .[dev]
+          python-version: "3.13"
+      - name: Install system dependencies for lxml
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y libxml2-dev libxslt-dev
+      - name: Install uv
+        uses: astral-sh/setup-uv@v6
+      - name: Install the dependencies
+        run: uv sync --locked --all-extras

      - name: Install gettext (required to compile messages) and MIME support
        run: |
-          sudo apt-get update
          sudo apt-get install -y gettext pandoc shared-mime-info
-          sudo wget https://svn.apache.org/repos/asf/httpd/httpd/trunk/docs/conf/mime.types -O /etc/mime.types
+          sudo cp $GITHUB_WORKSPACE/docker/files/etc/mime.types /etc/mime.types

      - name: Generate a MO file from strings extracted from the project
-        run: python manage.py compilemessages
+        run: uv run python manage.py compilemessages

      - name: Run tests
-        run: ~/.local/bin/pytest -n 2
+        run: uv run pytest -n 2
+
+  security-trivy-critical:
+    permissions:
+      contents: read
+      security-events: write
+    runs-on: ubuntu-latest
+    steps:
+      - name: Run Trivy analysis for critical vulnerabilities
+        # We use main branch while we might still iterate on the action
+        uses: numerique-gouv/action-trivy-cache/security-trivy-critical@main
+        with:
+          skip-files: src/mail/yarn.lock
+
+  security-trivy:
+    permissions:
+      contents: read
+    runs-on: ubuntu-latest
+    steps:
+      - name: Run Trivy analysis for vulnerabilities
+        # We use main branch while we might still iterate on the action
+        uses: numerique-gouv/action-trivy-cache/security-trivy@main
+        with:
+          skip-files: src/mail/yarn.lock
@@ -22,15 +22,14 @@ jobs:
      - name: Checkout
        uses: actions/checkout@v4
      # Backend i18n
-      - name: Install Python
-        uses: actions/setup-python@v5
+      - name: Set up Python
+        uses: actions/setup-python@v6
        with:
-          python-version: "3.13.3"
-          cache: "pip"
-      - name: Upgrade pip and setuptools
-        run: pip install --upgrade pip setuptools
-      - name: Install development dependencies
-        run: pip install --user .
+          python-version-file: "src/backend/pyproject.toml"
+      - name: Install uv
+        uses: astral-sh/setup-uv@v6
+      - name: Install the project
+        run: uv sync --locked --all-extras
        working-directory: src/backend
      - name: Restore the mail templates
        uses: actions/cache@v4
@@ -46,7 +45,7 @@ jobs:
      - name: generate pot files
        working-directory: src/backend
        run: |
-          DJANGO_CONFIGURATION=Build python manage.py makemessages -a --keep-pot
+          DJANGO_CONFIGURATION=Build uv run python manage.py makemessages -a --keep-pot
      # frontend i18n
      - name: Setup Node.js
        uses: actions/setup-node@v4
@@ -44,6 +44,9 @@ env.d/development/*
 !env.d/development/*.dist
 env.d/terraform

+# Configuration
+**/conversations/configuration/llm/dev.json
+
 # npm
 node_modules

@@ -10,16 +10,117 @@ and this project adheres to

 ### Added

+- ✨(back) add projects with custom LLM instructions
+- ✨(front) projects management UI
+
+### Changed
+
+- ⬆️(dependencies) upgrade Next.js 15 to 16, upgrade python dependencies
+- ✨(front) rich text copy for Word/Docs paste
+ 
+### Fixed
+
+- 🐛(back) add missing color option for project colors
+
+## [0.0.14] - 2026-03-11
+
+### Added
+
+- ✨(user) allow disabling automatic internet search
+- ✨(search) add searchModal and modify leftPanel
+- ✨(waffle) hide the waffle if not fr theme
+- ✨(front) allow pasting an attachment from clipboard
+- ✨(array) temporarily adjust array
+
+### Changed
+
+- ⚡️(front) optimize streaming markdown rendering performance
+- ⬆️(back) update pydantic-ai
+- ♻️(chat) refactor AIAgentService for readability and maintainability
+- 🚸(oidc) ignore case when fallback on email #281
+- ⬆️(back) update pillow, django-pydantic-field, pypdf
+- ♻️(front) migrate from ESLint 8 to ESLint 9 flat config
+- ⬆️(back) update django and pypdf
+
+### Fixed
+
+- 💚(docker) vendor mime.types file instead of fetching from Apache SVN
+- 🚑️(back) fix mime type for pptx
+- 🐛(front) fix math formulas and carousel translations
+- 🐛(helm) reverse liveness and readiness for backend deployment
+- 🐛(front) fix dark mode styling on chat messages
+- 🐛(front) fixed inverted toast for setting changes
+
+## [0.0.13] - 2026-02-09
+
+### Added
+
+- 💄(front) ui fix : update ui-kit
+- ✨(front) add persistent darkmode
+- ✨(front) add ui kit #240
+- 🧱(files) allow to use S3 storage without external access #849
+- ✨(backend) add FindRagBackend #209
+- ⬆️(back) update dependencies
+- ✨(back) use adaptive parsing for pdf documents
+
+### Changed
+
+- 💄(darkmode) change color feedback button
+- 🏗️(back) migrate to uv
+- ♻️(front) optimize syntax highlighting bundle size
+
+### Fixed
+
+- 🐛(back) cast collection Ids to API expected types
+
+## [0.0.12] - 2026-01-27
+
+### Fixed
+
+- ⚡️(front) performance improvements on chat input
+- 💄(front) i18n and standardize pdf parsing display
+
+### Removed
+
+- 🔥(chat) consider PDF documents as other kind of documents #234
+
+## [0.0.11] - 2026-01-16
+
+### Changed
+
+- 📦️(front) update react
+- ✨(chat) generate and edit conversation title
+
+### Fixed
+
+- 🐛(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
+
+### Added
+
 - ✨(front) add retry button

 ### Fixed

+- 🐛(front) fix long user messages
+- 🐛(front) fix "Maximum update depth exceeded" error in Chat component
+- 🐛(front) fix parsing documents display
+- 🐛(front) fix opacity input in error
 - 🐛(front) resolve React hydration errors
 - 🚑️(user) allow longer short names #182

 ## [0.0.9] - 2025-11-17

 ### Added
+
 - ✨(front) add code copy button
 - ✨(RAG) add generic collection RAG tools #159

@@ -27,7 +128,6 @@ and this project adheres to

 - 🔊(langfuse) enable tracing with redacted content #162

-
 ## [0.0.8] - 2025-11-10

 ### Fixed
@@ -42,28 +142,24 @@ 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
@@ -80,14 +176,12 @@ 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
@@ -97,6 +191,7 @@ 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
@@ -104,7 +199,6 @@ 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
@@ -127,7 +221,7 @@ 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
@@ -161,8 +255,12 @@ and this project adheres to
 - ✨(onboarding) add activation code logic for launch #62
 - 💄(chat) add code highlighting for LLM responses #67

-
-[unreleased]: https://github.com/suitenumerique/conversations/compare/v0.0.9...main
+[unreleased]: https://github.com/suitenumerique/conversations/compare/v0.0.14...main
+[0.0.14]: https://github.com/suitenumerique/conversations/releases/v0.0.14
+[0.0.13]: https://github.com/suitenumerique/conversations/releases/v0.0.13
+[0.0.12]: https://github.com/suitenumerique/conversations/releases/v0.0.12
+[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
 [0.0.7]: https://github.com/suitenumerique/conversations/releases/v0.0.7
@@ -3,9 +3,6 @@
 # ---- base image to inherit from ----
 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
-
 # Upgrade system packages to install security updates
 RUN apk update && \
  apk upgrade
@@ -13,21 +10,31 @@ RUN apk update && \
 # ---- Back-end builder image ----
 FROM base AS back-builder

-WORKDIR /builder
+
+ENV UV_COMPILE_BYTECODE=1
+ENV UV_LINK_MODE=copy
+ENV UV_PYTHON_DOWNLOADS=0
+
+COPY --from=ghcr.io/astral-sh/uv:0.9.26 /uv /uvx /bin/

 # Install Rust and Cargo using Alpine's package manager
 RUN apk add --no-cache \
  build-base \
  libffi-dev \
+  libxml2-dev \
+  libxslt-dev \
  rust \
  cargo

-# Copy required python dependencies
-COPY ./src/backend /builder
-
-RUN mkdir /install && \
-  pip install --prefix=/install .
+WORKDIR /app

+RUN --mount=type=cache,target=/root/.cache/uv \
+    --mount=type=bind,source=src/backend/uv.lock,target=uv.lock \
+    --mount=type=bind,source=src/backend/pyproject.toml,target=pyproject.toml \
+    uv sync --locked --no-install-project --no-dev
+COPY src/backend /app
+RUN --mount=type=cache,target=/root/.cache/uv \
+    uv sync --locked --no-dev

 # ---- mails ----
 FROM node:24 AS mail-builder
@@ -49,14 +56,16 @@ RUN apk add \
  pango \
  rdfind

-# Copy installed python dependencies
-COPY --from=back-builder /install /usr/local
+WORKDIR /app
+
+# Copy the application from the builder
+COPY --from=back-builder /app /app
+
+ENV PATH="/app/.venv/bin:$PATH"

 # Copy conversations application (see .dockerignore)
 COPY ./src/backend /app/

-WORKDIR /app
-
 # collectstatic
 RUN DJANGO_CONFIGURATION=Build \
    python manage.py collectstatic --noinput
@@ -79,10 +88,12 @@ RUN apk add \
  gettext \
  gdk-pixbuf \
  libffi-dev \
+  libxml2 \
+  libxslt \
  pango \
  shared-mime-info

-RUN wget https://svn.apache.org/repos/asf/httpd/httpd/trunk/docs/conf/mime.types -O /etc/mime.types
+COPY ./docker/files/etc/mime.types /etc/mime.types

 # Copy entrypoint
 COPY ./docker/files/usr/local/bin/entrypoint /usr/local/bin/entrypoint
@@ -92,17 +103,17 @@ COPY ./docker/files/usr/local/bin/entrypoint /usr/local/bin/entrypoint
 # docker user (see entrypoint).
 RUN chmod g=u /etc/passwd

-# Copy installed python dependencies
-COPY --from=back-builder /install /usr/local

-# Copy conversations application (see .dockerignore)
-COPY ./src/backend /app/
+# Copy the application from the builder
+COPY --from=back-builder /app /app

 WORKDIR /app

+ENV PATH="/app/.venv/bin:$PATH"
+
 # Generate compiled translation messages
 RUN DJANGO_CONFIGURATION=Build \
-    python manage.py compilemessages
+    python manage.py compilemessages --ignore=".venv/**/*"


 # We wrap commands run in this container by the following entrypoint that
@@ -119,10 +130,9 @@ USER root:root
 # Install psql
 RUN apk add postgresql-client

-# Uninstall conversations and re-install it in editable mode along with development
-# dependencies
-RUN pip uninstall -y conversations
-RUN pip install -e .[dev]
+ # Install development dependencies
+RUN --mount=from=ghcr.io/astral-sh/uv:0.9.26,source=/uv,target=/bin/uv \
+    uv sync --all-extras --locked

 # Restore the un-privileged user running the application
 ARG DOCKER_USER
@@ -231,7 +231,7 @@ superuser: ## Create an admin superuser with password "admin"
 .PHONY: superuser

 back-i18n-compile: ## compile the gettext files
-	@$(MANAGE) compilemessages --ignore="venv/**/*"
+	@$(MANAGE) compilemessages --ignore=".venv/**/*"
 .PHONY: back-i18n-compile

 back-i18n-generate: ## create the .pot files used for i18n
@@ -71,9 +71,13 @@ services:
      - "host.docker.internal:host-gateway"
    ports:
      - "8071:8000"
+    networks:
+      - default
+      - lasuite
    volumes:
      - ./src/backend:/app
      - ./data/static:/data/static
+      - /app/.venv
    depends_on:
        postgresql:
            condition: service_healthy
@@ -89,6 +93,9 @@ 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 +184,8 @@ services:
      kc_postgresql:
        condition: service_healthy
        restart: true
+
+networks:
+  lasuite:
+    name: lasuite-network
+    driver: bridge
@@ -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
@@ -0,0 +1,159 @@
+# File Upload Modes
+
+This document describes the different modes for handling file uploads in the Conversations application, and how to configure and use them.
+
+## Overview
+
+The application supports two independent configuration points:
+
+1. **`FILE_UPLOAD_MODE`**: how the frontend uploads files (frontend → storage/backend)
+2. **`FILE_TO_LLM_MODE`**: how the backend provides files to the LLM (backend → LLM)
+
+Each mode has different trade-offs in terms of security, performance, and LLM accessibility. The two settings can be combined based on your network constraints.
+
+## Configuration
+
+### Frontend upload mode (`FILE_UPLOAD_MODE`)
+
+```bash
+# Default: presigned URL upload (backward compatible)
+FILE_UPLOAD_MODE=presigned_url
+
+# Frontend uploads directly to backend
+FILE_UPLOAD_MODE=backend_to_s3
+```
+
+### Backend delivery mode (`FILE_TO_LLM_MODE`)
+
+```bash
+# Default: presigned URL mode (backward compatible)
+FILE_TO_LLM_MODE=presigned_url
+
+# Backend provides base64-encoded data URLs
+FILE_TO_LLM_MODE=backend_base64
+
+# Backend provides temporary URLs through the backend
+FILE_TO_LLM_MODE=backend_temporary_url
+```
+
+Additional settings for backend temporary URL mode:
+
+```bash
+# Base URL to reach backend
+FILE_BACKEND_URL="http://localhost:8071"
+
+# Expiration time for temporary URLs (in seconds, default: 180 = 3 minutes)
+FILE_BACKEND_TEMPORARY_URL_EXPIRATION=180
+```
+
+## Mode Details
+
+### 1. Presigned URL Mode (Default)
+
+**Frontend upload configuration:** `FILE_UPLOAD_MODE=presigned_url`
+
+**Backend delivery configuration:** `FILE_TO_LLM_MODE=presigned_url`
+
+**How it works:**
+- Frontend requests a presigned URL from the backend
+- Frontend uploads the file directly to S3 using the presigned URL
+- Frontend notifies the backend when upload is complete
+- Backend initiates malware detection
+- Backend returns presigned S3 URLs to the LLM
+
+**Advantages:**
+- Files don't pass through the backend server (lower bandwidth usage)
+- Faster uploads for large files (direct to S3)
+- S3 handles the upload, no backend load
+- Backward compatible with existing frontend implementations
+
+**Disadvantages:**
+- S3 bucket must be accessible from the frontend
+- Presigned URLs can be leaked if not handled carefully
+- Frontend needs to handle S3 credentials/configuration
+
+**LLM Access:**
+- Images: Presigned S3 URLs with expiration (default: 3 minutes)
+- Documents: Presigned S3 URLs with expiration (default: 3 minutes)
+
+**When to use:**
+- When frontend has direct access to S3
+- When you want to minimize backend load
+- When S3 is publicly accessible or accessible via VPN
+
+
+### 2. Backend Base64 Mode
+
+**Frontend upload configuration:** `FILE_UPLOAD_MODE=backend_to_s3`
+
+**Backend delivery configuration:** `FILE_TO_LLM_MODE=backend_base64`
+
+**How it works:**
+- Frontend uploads the file directly to the backend
+- Backend stores the file on S3
+- Backend reads the file, encodes it as base64, and creates a data URL
+- LLM receives the file as a base64-encoded data URL
+
+**Advantages:**
+- S3 can be private/internal (not accessible from frontend)
+- Files always go through the backend for validation
+- No presigned URLs to manage
+- Better control over file access
+- Data URLs work with all LLMs that support file content
+
+**Disadvantages:**
+- Backend memory usage increases (entire file loaded for base64 encoding)
+- Slower for very large files (encoding overhead)
+- Increased bandwidth on backend
+- Data URLs can be very large in responses
+
+**LLM Access:**
+- Images: Base64-encoded data URLs (format: `data:image/png;base64,...`)
+- Documents: Base64-encoded data URLs (format: `data:application/pdf;base64,...`)
+
+**When to use:**
+- When S3 is not accessible from the frontend
+- When you want all file uploads to go through the backend
+- When the LLM supports base64-encoded data URLs
+- For smaller files (< 50MB)
+
+
+### 3. Backend Temporary URL Mode
+
+**Frontend upload configuration:** `FILE_UPLOAD_MODE=backend_to_s3`
+
+**Backend delivery configuration:** `FILE_TO_LLM_MODE=backend_temporary_url`
+
+**How it works:**
+- Frontend uploads the file directly to the backend
+- Backend stores the file on S3
+- Backend generates a secure temporary access token stored in cache (TTL: 3 minutes by default)
+- Backend returns a temporary URL pointing to the backend's file-stream endpoint
+- LLM receives the temporary URL and accesses the file through the backend
+- Backend validates the token and streams the file content from S3 to the LLM
+
+**Advantages:**
+- S3 can be private/internal (not accessible from frontend or LLM directly)
+- Files always go through the backend for validation and access control
+- LLM doesn't need direct access to S3
+- Tokens expire quickly (better security than long-lived presigned URLs)
+- No large data URL strings in memory or responses
+- Lower backend memory usage than base64 mode
+- Centralized file access control through the backend
+- Good balance between security and performance
+
+**Disadvantages:**
+- LLM must be able to access the backend server
+- File streaming goes through the backend (adds some latency)
+- Time-limited access (token expires)
+
+**LLM Access:**
+- Images: Temporary backend URLs with format `/api/v1.0/file-stream/{temporary_key}/` (token expiration: configurable, default: 3 minutes)
+- Documents: Temporary backend URLs with format `/api/v1.0/file-stream/{temporary_key}/` (token expiration: configurable, default: 3 minutes)
+
+**When to use:**
+- When S3 is not accessible from the frontend or LLM
+- When you want backend control over uploads and file access
+- When you want time-limited access to files with centralized control
+- When you want the LLM to access files through the backend gateway
+- For large files (backend streams directly from S3 without loading entirely into memory)
@@ -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": {
@@ -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
 )
 ```

@@ -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
@@ -1,6 +0,0 @@
-{
-  "dependencies": {
-    "@ai-sdk/react": "^1.2.12",
-    "@ai-sdk/ui-utils": "^1.2.11"
-  }
-}
@@ -9,11 +9,28 @@ from . import models
 class ChatConversationAdmin(admin.ModelAdmin):
    """Admin class for the ChatConversation model"""

-    autocomplete_fields = ("owner",)
+    autocomplete_fields = ("owner", "project")
+    list_select_related = ("project",)

    list_display = (
        "id",
        "title",
+        "project",
+        "created_at",
+        "updated_at",
+    )
+
+
+@admin.register(models.ChatProject)
+class ChatProjectAdmin(admin.ModelAdmin):
+    """Admin class for the ChatProject model"""
+
+    search_fields = ("title",)
+    list_display = (
+        "id",
+        "title",
+        "icon",
+        "color",
        "created_at",
        "updated_at",
    )
@@ -0,0 +1,280 @@
+"""Document parsers for RAG backends."""
+
+import base64
+import logging
+import time
+from io import BytesIO
+from urllib.parse import urljoin
+
+from django.conf import settings
+
+import requests
+from pypdf import PdfReader, PdfWriter
+
+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: bytes) -> 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 (bytes): The content of the document as a bytes 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
+        )
+
+
+METHOD_TEXT_EXTRACTION = "text_extraction"
+METHOD_OCR = "ocr"
+
+
+def analyze_pdf(pdf_data: bytes) -> dict:
+    """
+    Analyze a PDF to determine if it needs OCR or can use direct text extraction.
+    """
+    reader = PdfReader(BytesIO(pdf_data))
+    total_pages = len(reader.pages)
+    if total_pages == 0:
+        logger.info("No page found in pdf")
+        return {
+            "total_pages": 0,
+            "pages_with_text": 0,
+            "avg_chars_per_page": 0,
+            "text_coverage": 0,
+            "recommended_method": METHOD_TEXT_EXTRACTION,
+        }
+
+    total_chars = 0
+    pages_with_text = 0
+    for page in reader.pages:
+        text = (page.extract_text() or "").strip()
+        char_count = len(text)
+        total_chars += char_count
+
+        if char_count > 50:
+            pages_with_text += 1
+
+    avg_chars = total_chars / total_pages
+    text_coverage = pages_with_text / total_pages
+
+    # Decision logic
+    if (
+        avg_chars > settings.MIN_AVG_CHARS_FOR_TEXT_EXTRACTION
+        and text_coverage > settings.MIN_TEXT_COVERAGE_FOR_TEXT_EXTRACTION
+    ):
+        method = METHOD_TEXT_EXTRACTION
+
+    else:
+        method = METHOD_OCR
+
+    return {
+        "total_pages": total_pages,
+        "pages_with_text": pages_with_text,
+        "avg_chars_per_page": round(avg_chars),
+        "text_coverage": round(text_coverage, 2),
+        "recommended_method": method,
+    }
+
+
+class AdaptiveParserMixin:
+    """
+    Mixin that adds adaptive PDF parsing behavior.
+
+    Analyzes PDF content to choose between direct text extraction (fast) and OCR
+    (for scanned/image PDFs). Subclasses must implement `parse_pdf_document_with_ocr`.
+    """
+
+    def parse_pdf_document(self, name: str, content_type: str, content: bytes) -> str:
+        """Analyze PDF and route to text extraction or OCR based on content."""
+        analysis = analyze_pdf(content)
+
+        logger.info(
+            "Pdf analysis - pages: %s, pages with text: %s, text_coverage: %s, "
+            "recommended method: %s",
+            analysis["total_pages"],
+            analysis["pages_with_text"],
+            analysis["text_coverage"],
+            analysis["recommended_method"],
+        )
+
+        method = analysis["recommended_method"]
+        if method == METHOD_TEXT_EXTRACTION:
+            return self.extract_text_from_pdf(name=name, content_type=content_type, content=content)
+        return self.parse_pdf_document_with_ocr(name=name, content=content)
+
+    def extract_text_from_pdf(self, name: str, content_type: str, content: bytes) -> str:
+        """Extract text directly from PDF without OCR (for text-based PDFs)."""
+        logger.info("Parsing pdf with text extraction")
+        return DocumentConverter().convert_raw(
+            name=name, content_type=content_type, content=content
+        )
+
+    def parse_pdf_document_with_ocr(self, name: str, content: bytes) -> str:
+        """Process PDF through OCR. Must be implemented by subclass."""
+        raise NotImplementedError("Subclass must implement parse_pdf_document_with_ocr")
+
+
+class AdaptivePdfParser(AdaptiveParserMixin, BaseParser):
+    """
+    PDF parser with adaptive text extraction / OCR routing.
+
+    Uses Mistral OCR API for scanned/image PDFs, processed in batches with retry logic.
+    """
+
+    def __init__(self):
+        super().__init__()
+
+        self.endpoint = urljoin(
+            settings.LLM_CONFIGURATIONS[settings.OCR_HRID].provider.base_url, "/v1/ocr"
+        )
+        self.max_retries = settings.OCR_MAX_RETRIES
+        self.retry_delay = settings.OCR_RETRY_DELAY
+        api_key = settings.LLM_CONFIGURATIONS[settings.OCR_HRID].provider.api_key
+
+        self.headers = {
+            "Authorization": f"Bearer {api_key}",
+            "Content-Type": "application/json",
+        }
+
+    def extract_page_batch(self, reader: PdfReader, start_index: int, end_index: int) -> bytes:
+        """Extract a range of pages from PDF as a new PDF bytes object."""
+        writer = PdfWriter()
+        for i in range(start_index, end_index):
+            writer.add_page(reader.pages[i])
+        output = BytesIO()
+        writer.write(output)
+        return output.getvalue()
+
+    def ocr_page_batch(
+        self,
+        name: str,
+        page_content: bytes,
+        start_index: int,
+        end_index: int,
+    ) -> list[str]:
+        """Send page batch to Mistral OCR API with static delay retry."""
+        file_data = base64.standard_b64encode(page_content).decode("utf-8")
+        payload = {
+            "document": {
+                "type": "document_url",
+                "document_name": f"{name}_pages_{start_index + 1}_to_{end_index}",
+                "document_url": f"data:application/pdf;base64,{file_data}",
+            },
+            "model": settings.OCR_MODEL,
+        }
+
+        last_exception = None
+        for attempt in range(self.max_retries):
+            try:
+                response = requests.post(
+                    self.endpoint,
+                    headers=self.headers,
+                    json=payload,
+                    timeout=settings.OCR_TIMEOUT,
+                )
+                response.raise_for_status()
+
+                pages = response.json().get("pages", [])
+                return [page.get("markdown", "") for page in pages]
+
+            except (requests.Timeout, requests.RequestException) as e:
+                last_exception = e
+                if attempt < self.max_retries - 1:
+                    logger.warning(
+                        "OCR attempt %d/%d failed for pages %d-%d: %s. Retrying in %.1fs...",
+                        attempt + 1,
+                        self.max_retries,
+                        start_index + 1,
+                        end_index,
+                        str(e),
+                        self.retry_delay,
+                    )
+                    time.sleep(self.retry_delay)
+
+        logger.error(
+            "OCR failed for pages %d-%d after %d attempts: %s",
+            start_index + 1,
+            end_index,
+            self.max_retries,
+            str(last_exception),
+        )
+        raise last_exception
+
+    def parse_pdf_document_with_ocr(self, name: str, content: bytes) -> str:
+        """Process PDF through OCR in batches, returning concatenated markdown."""
+        reader = PdfReader(BytesIO(content))
+        total_pages = len(reader.pages)
+        batch_size = settings.OCR_BATCH_PAGES
+
+        logger.info("Parsing pdf with OCR (%d pages, batch size %d)", total_pages, batch_size)
+
+        results = []
+        for start_index in range(0, total_pages, batch_size):
+            end_index = min(start_index + batch_size, total_pages)
+            batch_content = self.extract_page_batch(reader, start_index, end_index)
+            try:
+                batch_results = self.ocr_page_batch(name, batch_content, start_index, end_index)
+                results.extend(batch_results)
+                logger.debug(
+                    "Completed OCR for pages %d-%d/%d", start_index + 1, end_index, total_pages
+                )
+            except Exception as e:  # pylint: disable=broad-except #noqa: BLE001
+                logger.error("Failed to OCR pages %d-%d: %s", start_index + 1, end_index, str(e))
+                # Preserve page count with empty placeholders to maintain correct ordering
+                results.extend([""] * (end_index - start_index))
+
+        return "\n\n".join(results)
+
+    def parse_document(self, name: str, content_type: str, content: bytes) -> str:
+        """Route to PDF parser or DocumentConverter 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
+        )
@@ -7,13 +7,13 @@ from typing import List, Optional
 from urllib.parse import urljoin

 from django.conf import settings
+from django.utils.module_loading import import_string

 import httpx
 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_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 +43,15 @@ 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"
+        parser_class = import_string(settings.RAG_DOCUMENT_PARSER)
+        self.parser = parser_class()
+
+    @staticmethod
+    def cast_collection_id(collection_id):
+        """Albert API expects int Ids."""
+        return int(collection_id)

    def create_collection(self, name: str, description: Optional[str] = None) -> str:
        """
@@ -91,7 +93,7 @@ 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 +104,7 @@ 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 +116,7 @@ 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 +124,7 @@ 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 +139,7 @@ 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 +147,7 @@ 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 +165,14 @@ 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 +209,14 @@ 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.
@@ -1,18 +1,19 @@
 """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

 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 +39,12 @@ 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()
+
+    @staticmethod
+    def cast_collection_id(collection_id):
+        """Dummy method to be overridden when needed."""
+        return collection_id

    def get_all_collection_ids(self) -> List[str]:
        """
@@ -53,13 +60,17 @@ class BaseRagBackend:

        collection_ids = []
        if self.collection_id:
-            collection_ids.append(int(self.collection_id))
+            collection_ids.append(self.cast_collection_id(self.collection_id))
        if self.read_only_collection_id:
            collection_ids.extend(
-                [int(collection_id) for collection_id in self.read_only_collection_id]
+                [
+                    self.cast_collection_id(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.
@@ -74,7 +85,7 @@ class BaseRagBackend:
        """
        return await sync_to_async(self.create_collection)(name=name, description=description)

-    def parse_document(self, name: str, content_type: str, content: BytesIO):
+    def parse_document(self, name: str, content_type: str, content: bytes):
        """
        Parse the document and prepare it for the search operation.
        This method should handle the logic to convert the document
@@ -83,14 +94,15 @@ class BaseRagBackend:
        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.
+            content (bytes): The content of the document as a bytes stream.

        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 +110,11 @@ 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.
@@ -109,50 +122,66 @@ 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: bytes, **kwargs
+    ) -> str:
        """
        Parse the document and store it in the Albert collection.

        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.
+            content (bytes): The content of the document as a bytes 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 +197,9 @@ 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 +207,4 @@ class BaseRagBackend:
        try:
            yield backend
        finally:
-            await backend.adelete_collection()
+            await backend.adelete_collection(**kwargs)
@@ -0,0 +1,160 @@
+"""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")
@@ -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]
@@ -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"
+        )
@@ -6,14 +6,103 @@ for the LLM to access them, and then reverting them back to local URLs when
 storing the messages in the database.
 """

+import base64
+import logging
+import mimetypes
+import secrets
 from typing import Dict, Iterable

+from django.conf import settings
+from django.core.cache import cache
+from django.core.files.storage import default_storage
+
 from pydantic_ai import DocumentUrl, ImageUrl, ModelMessage, ModelRequest, UserPromptPart

+from core.file_upload.enums import FileToLLMMode
 from core.file_upload.utils import generate_retrieve_policy

 from chat.models import ChatConversation

+logger = logging.getLogger(__name__)
+
+
+def generate_temporary_url(key: str) -> str:
+    """
+    Generate a temporary URL for accessing a file through the backend.
+
+    Instead of using S3 presigned URLs, this creates a temporary access key
+    that's stored in cache (3 minutes TTL). The LLM accesses the file through
+    a backend endpoint that validates the key and streams the file content.
+
+    This approach:
+    - Works even when S3 is not accessible from the LLM
+    - Provides better security (key is time-limited and single-use)
+    - Allows the backend to control file access centrally
+
+    Args:
+        key (str): The S3 object key where the file is stored.
+
+    Returns:
+        str: A temporary URL with format: /api/v1.0/file-stream/{temporary_key}/
+    """
+    # Generate a secure random key
+    temporary_key = secrets.token_urlsafe(32)
+
+    # Store the S3 key in cache
+    cache_key = f"file_access:{temporary_key}"
+    cache.set(cache_key, key, timeout=settings.FILE_BACKEND_TEMPORARY_URL_EXPIRATION)
+
+    logger.info("Generated temporary file access key for S3 key: %s", key)
+
+    # Return the URL that the LLM will use to access the file
+    return f"{settings.FILE_BACKEND_URL}/api/v1.0/file-stream/{temporary_key}/"
+
+
+def _get_file_url_for_llm(key: str, mode: str | None = None) -> str:
+    """
+    Get the appropriate URL for the LLM to access a file based on the upload mode.
+
+    Args:
+        key (str): The S3 object key where the file is stored.
+        mode (str, optional): The upload mode. Defaults to FILE_TO_LLM_MODE setting.
+
+    Returns:
+        str: The URL or data URL for the LLM to use.
+
+    Supported modes:
+    - presigned_url: Returns a presigned S3 URL (default)
+    - backend_temporary_url: Returns a presigned URL with shorter expiration
+    - backend_base64: Returns a data URL with base64-encoded file content
+    """
+    if mode is None:
+        mode = settings.FILE_TO_LLM_MODE
+
+    if mode == FileToLLMMode.BACKEND_BASE64:
+        # Read file from S3 and encode as base64 data URL
+        try:
+            with default_storage.open(key, "rb") as file:
+                file_content = file.read()
+                # Detect MIME type from file extension or default to octet-stream
+                mime_type, _ = mimetypes.guess_type(key)
+                if not mime_type:
+                    mime_type = "application/octet-stream"
+
+                # Create data URL
+                b64_content = base64.b64encode(file_content).decode("utf-8")
+                return f"data:{mime_type};base64,{b64_content}"
+        except Exception:  # pylint: disable=broad-except
+            # Fall back to presigned URL on error
+            logger.exception(
+                "Failed to read file for base64 encoding, falling back to presigned URL"
+            )
+            return generate_retrieve_policy(key)
+
+    elif mode == FileToLLMMode.BACKEND_TEMPORARY_URL:
+        return generate_temporary_url(key)
+
+    # FileToLLMMode.PRESIGNED_URL or default
+    return generate_retrieve_policy(key)
+

 def update_local_urls(
    conversation: ChatConversation,
@@ -21,7 +110,9 @@ def update_local_urls(
    updated_url: Dict[str, str] | None = None,
 ) -> Iterable[ImageUrl | DocumentUrl]:
    """
-    Replace local image or document URLs in the content list to use presigned S3 URLs.
+    Replace local image or document URLs in the content list to use appropriate S3 URLs
+    based on the configured FILE_TO_LLM_MODE.
+
    ⚠️Be careful, `media_contents` are replaced in place.

    Args:
@@ -31,7 +122,7 @@ def update_local_urls(
            mapping of original URLs to updated URLs.
    Returns:
        Iterable[ImageUrl | DocumentUrl]: Updated iterable of UserContent objects
-            with presigned URLs.
+            with appropriate S3 URLs based on the configured mode.
    """
    # When images are stored locally, there is no host in the URL, so we can
    # just check if the URL starts, frontend adds a prefix `/media-key/` to the key.
@@ -41,7 +132,9 @@ def update_local_urls(
    # Filter only ImageUrl contents
    media_contents = (c for c in contents if isinstance(c, (ImageUrl, DocumentUrl)))

-    # Replace URLs with presigned URLs
+    # Replace URLs with appropriate S3 URLs based on mode
+    upload_mode = settings.FILE_TO_LLM_MODE
+
    for content in media_contents:
        idx = content.url.find(local_media_url_prefix)

@@ -57,7 +150,7 @@ def update_local_urls(
                # except if the user tampers with the conversation.
                continue

-            content.url = generate_retrieve_policy(key)
+            content.url = _get_file_url_for_llm(key, upload_mode)
            if updated_url is not None:
                updated_url[content.url] = _initial_url

@@ -68,7 +161,7 @@ def update_history_local_urls(
    conversation: ChatConversation, messages: list[ModelMessage]
 ) -> list[ModelMessage]:
    """
-    Replace local image/documents URLs in the message list to use presigned S3 URLs.
+    Replace local image/documents URLs in the message list to use appropriate S3 URLs.

    ⚠️Be careful, `messages` are replaced in place.

@@ -79,7 +172,7 @@ def update_history_local_urls(
    Args:
        messages (list[ModelMessage]): List of ModelMessage objects.
    Returns:
-        list[ModelMessage]: Updated list of ModelMessage objects with presigned URLs.
+        list[ModelMessage]: Updated list of ModelMessage objects with appropriate S3 URLs.
    """
    # Filter only ModelRequest messages
    requests = (msg for msg in messages if isinstance(msg, ModelRequest))
@@ -9,6 +9,29 @@ from core.factories import UserFactory
 from . import models


+class ChatProjectFactory(factory.django.DjangoModelFactory):
+    """Factory for creating Project instances."""
+
+    title = factory.Sequence(lambda n: f"title {n}")
+    owner = factory.SubFactory(UserFactory)
+    icon = factory.fuzzy.FuzzyChoice(models.ChatProjectIcon)
+    color = factory.fuzzy.FuzzyChoice(models.ChatProjectColor)
+
+    class Meta:
+        model = models.ChatProject
+        skip_postgeneration_save = True
+
+    @factory.post_generation
+    def number_of_conversations(self, create, extracted, **kwargs):
+        """Create attached conversations for the project."""
+        if not create or not extracted:
+            return
+
+        if not isinstance(extracted, int):
+            raise TypeError("number_of_conversations must be an integer")
+        ChatConversationFactory.create_batch(extracted, project=self, owner=self.owner)
+
+
 class ChatConversationFactory(factory.django.DjangoModelFactory):
    """Factory for creating ChatConversation instances."""

@@ -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()
@@ -0,0 +1,21 @@
+# Generated by Django 5.2.9 on 2025-12-30 09:44
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("chat", "0004_chatconversationattachment_and_more"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="chatconversation",
+            name="title_set_by_user_at",
+            field=models.DateTimeField(
+                blank=True,
+                help_text="Timestamp when the user manually set the title. If set, prevent automatic title generation.",
+                null=True,
+            ),
+        ),
+    ]
@@ -0,0 +1,136 @@
+# Generated by Django 5.2.11 on 2026-02-25 16:20
+
+import uuid
+
+import django.db.models.deletion
+from django.conf import settings
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("chat", "0005_chatconversation_title_set_by_user_at"),
+        migrations.swappable_dependency(settings.AUTH_USER_MODEL),
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name="ChatProject",
+            fields=[
+                (
+                    "id",
+                    models.UUIDField(
+                        default=uuid.uuid4,
+                        editable=False,
+                        help_text="primary key for the record as UUID",
+                        primary_key=True,
+                        serialize=False,
+                        verbose_name="id",
+                    ),
+                ),
+                (
+                    "created_at",
+                    models.DateTimeField(
+                        auto_now_add=True,
+                        help_text="date and time at which a record was created",
+                        verbose_name="created on",
+                    ),
+                ),
+                (
+                    "updated_at",
+                    models.DateTimeField(
+                        auto_now=True,
+                        help_text="date and time at which a record was last updated",
+                        verbose_name="updated on",
+                    ),
+                ),
+                ("title", models.CharField(help_text="Title of the chat project", max_length=100)),
+                (
+                    "icon",
+                    models.CharField(
+                        choices=[
+                            ("folder", "Folder icon"),
+                            ("file", "File icon"),
+                            ("perso", "Perso icon"),
+                            ("gear", "Gear icon"),
+                            ("megaphone", "Megaphone icon"),
+                            ("star", "Star icon"),
+                            ("bookmark", "Bookmark icon"),
+                            ("chart", "Chart icon"),
+                            ("photo", "Photo icon"),
+                            ("euro", "Euro icon"),
+                            ("key", "Key icon"),
+                            ("justice", "Justice icon"),
+                            ("book", "Book icon"),
+                            ("puzzle", "Puzzle icon"),
+                            ("palette", "Palette icon"),
+                            ("terminal", "Terminal icon"),
+                            ("car", "Car icon"),
+                            ("music", "Music icon"),
+                            ("checkmark", "Checkmark icon"),
+                            ("la_suite", "La Suite icon"),
+                        ],
+                        help_text="Project icon",
+                        max_length=20,
+                    ),
+                ),
+                (
+                    "color",
+                    models.CharField(
+                        choices=[
+                            ("color_1", "Color 1"),
+                            ("color_2", "Color 2"),
+                            ("color_3", "Color 3"),
+                            ("color_4", "Color 4"),
+                            ("color_5", "Color 5"),
+                            ("color_6", "Color 6"),
+                            ("color_7", "Color 7"),
+                            ("color_8", "Color 8"),
+                            ("color_9", "Color 9"),
+                            ("color_10", "Color 10"),
+                        ],
+                        help_text="Project icon color",
+                        max_length=20,
+                    ),
+                ),
+                (
+                    "llm_instructions",
+                    models.TextField(
+                        blank=True, help_text="Custom user instructions to be sent to the llm"
+                    ),
+                ),
+                (
+                    "owner",
+                    models.ForeignKey(
+                        on_delete=django.db.models.deletion.CASCADE,
+                        related_name="projects",
+                        to=settings.AUTH_USER_MODEL,
+                    ),
+                ),
+            ],
+            options={
+                "abstract": False,
+            },
+        ),
+        migrations.AddField(
+            model_name="chatconversation",
+            name="project",
+            field=models.ForeignKey(
+                blank=True,
+                null=True,
+                on_delete=django.db.models.deletion.SET_NULL,
+                related_name="conversations",
+                to="chat.chatproject",
+            ),
+        ),
+        migrations.AddIndex(
+            model_name="chatconversation",
+            index=models.Index(
+                fields=["owner", "-created_at"], name="chat_chatco_owner_i_48266a_idx"
+            ),
+        ),
+        migrations.AddIndex(
+            model_name="chatconversation",
+            index=models.Index(fields=["owner", "project"], name="chat_chatco_owner_i_38d719_idx"),
+        ),
+    ]
@@ -15,6 +15,74 @@ from chat.ai_sdk_types import UIMessage
 User = get_user_model()


+class ChatProjectIcon(models.TextChoices):
+    """Project icon text choices."""
+
+    FOLDER = "folder", "Folder icon"
+    FILE = "file", "File icon"
+    PERSO = "perso", "Perso icon"
+    GEAR = "gear", "Gear icon"
+    MEGAPHONE = "megaphone", "Megaphone icon"
+    STAR = "star", "Star icon"
+    BOOKMARK = "bookmark", "Bookmark icon"
+    CHART = "chart", "Chart icon"
+    PHOTO = "photo", "Photo icon"
+    EURO = "euro", "Euro icon"
+    KEY = "key", "Key icon"
+    JUSTICE = "justice", "Justice icon"
+    BOOK = "book", "Book icon"
+    PUZZLE = "puzzle", "Puzzle icon"
+    PALETTE = "palette", "Palette icon"
+    TERMINAL = "terminal", "Terminal icon"
+    CAR = "car", "Car icon"
+    MUSIC = "music", "Music icon"
+    CHECKMARK = "checkmark", "Checkmark icon"
+    LA_SUITE = "la_suite", "La Suite icon"
+
+
+class ChatProjectColor(models.TextChoices):
+    """Project icon color choices. We keep it generic to ease frontend compatibility."""
+
+    COLOR_1 = "color_1", "Color 1"
+    COLOR_2 = "color_2", "Color 2"
+    COLOR_3 = "color_3", "Color 3"
+    COLOR_4 = "color_4", "Color 4"
+    COLOR_5 = "color_5", "Color 5"
+    COLOR_6 = "color_6", "Color 6"
+    COLOR_7 = "color_7", "Color 7"
+    COLOR_8 = "color_8", "Color 8"
+    COLOR_9 = "color_9", "Color 9"
+    COLOR_10 = "color_10", "Color 10"
+
+
+class ChatProject(BaseModel):
+    """Model representing a project that groups conversations together."""
+
+    owner = models.ForeignKey(
+        User,
+        related_name="projects",
+        on_delete=models.CASCADE,
+        null=False,
+        blank=False,
+    )
+    title = models.CharField(
+        max_length=100,
+        help_text="Title of the chat project",
+    )
+    icon = models.CharField(max_length=20, choices=ChatProjectIcon, help_text="Project icon")
+    color = models.CharField(
+        max_length=20, choices=ChatProjectColor, help_text="Project icon color"
+    )
+
+    llm_instructions = models.TextField(
+        blank=True,
+        help_text="Custom user instructions to be sent to the llm",
+    )
+
+    def __str__(self):
+        return self.title
+
+
 class ChatConversation(BaseModel):
    """
    Model representing a chat conversation.
@@ -44,7 +112,12 @@ class ChatConversation(BaseModel):
        null=True,
        help_text="Title of the chat conversation",
    )
-
+    title_set_by_user_at = models.DateTimeField(
+        blank=True,
+        null=True,
+        help_text="Timestamp when the user manually set the title. If set, prevent automatic "
+        "title generation.",
+    )
    ui_messages = models.JSONField(
        default=list,
        blank=True,
@@ -74,6 +147,23 @@ class ChatConversation(BaseModel):
        help_text="Collection ID for the conversation, used for RAG document search",
    )

+    project = models.ForeignKey(
+        ChatProject,
+        related_name="conversations",
+        on_delete=models.SET_NULL,  # explicitly avoid Cascade here
+        null=True,
+        blank=True,
+    )
+
+    class Meta:  # pylint: disable=missing-class-docstring
+        indexes = [
+            models.Index(fields=["owner", "-created_at"]),
+            models.Index(fields=["owner", "project"]),
+        ]
+
+    def __str__(self):
+        return self.title or str(self.pk)
+

 class ChatConversationAttachment(BaseModel):
    """
@@ -4,12 +4,13 @@ from typing import Optional
 from urllib.parse import quote

 from django.conf import settings
+from django.utils import timezone

 from django_pydantic_field.rest_framework import SchemaField  # pylint: disable=no-name-in-module
 from drf_spectacular.utils import extend_schema_field
 from rest_framework import serializers

-from core.file_upload.enums import AttachmentStatus
+from core.file_upload.enums import AttachmentStatus, FileUploadMode
 from core.file_upload.utils import generate_upload_policy

 from chat import models
@@ -24,9 +25,26 @@ class ChatConversationSerializer(serializers.ModelSerializer):

    class Meta:  # pylint: disable=missing-class-docstring
        model = models.ChatConversation
-        fields = ["id", "title", "created_at", "updated_at", "messages", "owner"]
+        fields = ["id", "title", "created_at", "updated_at", "messages", "owner", "project"]
        read_only_fields = ["id", "created_at", "updated_at", "messages"]

+    def validate_project(self, project):
+        """Ensure the project belongs to the current user."""
+        if project and project.owner != self.context["request"].user:
+            raise serializers.ValidationError("The project must belong to the current user.")
+        return project
+
+    def update(self, instance, validated_data):
+        # Project is immutable after creation — no moving or detaching
+        if "project" in validated_data:
+            raise serializers.ValidationError(
+                {"project": "This field can only be set at creation time."}
+            )
+        # If title is being changed, mark it as user-set
+        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)
+

 class ChatConversationInputSerializer(serializers.Serializer):
    """
@@ -173,7 +191,11 @@ class ChatConversationAttachmentSerializer(serializers.ModelSerializer):


 class CreateChatConversationAttachmentSerializer(serializers.ModelSerializer):
-    """Serializer for creating chat conversation attachments."""
+    """Serializer for creating chat conversation attachments.
+
+    For presigned_url mode: returns 'policy' field with presigned URL for direct S3 upload
+    For backend modes: does not return 'policy' field (upload handled via backend endpoint)
+    """

    policy = serializers.SerializerMethodField()
    uploaded_by = serializers.HiddenField(default=serializers.CurrentUserDefault())
@@ -183,9 +205,15 @@ class CreateChatConversationAttachmentSerializer(serializers.ModelSerializer):
        model = models.ChatConversationAttachment
        fields = ["id", "key", "content_type", "file_name", "size", "policy", "uploaded_by"]

-    def get_policy(self, attachment) -> str:
-        """Return the policy to use if the item is a file."""
-        return generate_upload_policy(attachment.key)
+    def get_policy(self, attachment) -> str | None:
+        """Return the policy (presigned URL) only for presigned_url mode."""
+        upload_mode = settings.FILE_UPLOAD_MODE
+
+        # Only return presigned URL in presigned_url mode
+        if upload_mode == FileUploadMode.PRESIGNED_URL:
+            return generate_upload_policy(attachment.key)
+
+        return None

    def validate_size(self, size: Optional[int]) -> Optional[int]:
        """Validate that the size is not greater than the maximum allowed size."""
@@ -199,3 +227,68 @@ class CreateChatConversationAttachmentSerializer(serializers.ModelSerializer):
            )

        return size
+
+
+class ChatProjectNestedSerializer(serializers.ModelSerializer):
+    """Lightweight read-only serializer for nested project info in search results."""
+
+    class Meta:  # pylint: disable=missing-class-docstring
+        model = models.ChatProject
+        fields = ["id", "title", "icon"]
+        read_only_fields = ["id", "title", "icon"]
+
+
+class ChatConversationSearchSerializer(serializers.ModelSerializer):
+    """Serializer for conversation search results with nested project info."""
+
+    project = ChatProjectNestedSerializer(read_only=True)
+
+    class Meta:  # pylint: disable=missing-class-docstring
+        model = models.ChatConversation
+        fields = ["id", "title", "created_at", "updated_at", "project"]
+        read_only_fields = ["id", "title", "created_at", "updated_at", "project"]
+
+
+class ChatConversationNestedSerializer(serializers.ModelSerializer):
+    """Serializer for chat conversations."""
+
+    class Meta:  # pylint: disable=missing-class-docstring
+        model = models.ChatConversation
+        fields = [
+            "id",
+            "title",
+        ]
+        read_only_fields = ["id", "title"]
+
+
+class ChatProjectSerializer(serializers.ModelSerializer):
+    """Serializer for projects."""
+
+    LLM_INSTRUCTIONS_MAX_LENGTH = 4000  # prevent too large prompts, easier to handle here
+
+    owner = serializers.HiddenField(default=serializers.CurrentUserDefault())
+    # Unbounded: the sidebar needs all conversations per project.
+    # Projects are paginated at the view level, keeping payloads reasonable.
+    conversations = ChatConversationNestedSerializer(many=True, read_only=True)
+    llm_instructions = serializers.CharField(
+        max_length=LLM_INSTRUCTIONS_MAX_LENGTH, required=False, allow_blank=True
+    )
+
+    class Meta:  # pylint: disable=missing-class-docstring
+        model = models.ChatProject
+        fields = [
+            "id",
+            "title",
+            "created_at",
+            "updated_at",
+            "icon",
+            "color",
+            "llm_instructions",
+            "owner",
+            "conversations",
+        ]
+        read_only_fields = [
+            "id",
+            "created_at",
+            "updated_at",
+        ]
@@ -0,0 +1,161 @@
+%PDF-1.4
+%âãÏÓ
+1 0 obj
+<<
+/Producer (pypdf)
+>>
+endobj
+2 0 obj
+<<
+/Type /Pages
+/Count 10
+/Kids [ 4 0 R 7 0 R 8 0 R 9 0 R 10 0 R 11 0 R 12 0 R 13 0 R 14 0 R 15 0 R ]
+>>
+endobj
+3 0 obj
+<<
+/Type /Catalog
+/Pages 2 0 R
+>>
+endobj
+4 0 obj
+<<
+/Type /Page
+/MediaBox [ 0 0 612 792 ]
+/Contents 5 0 R
+/Resources <<
+/Font <<
+/F1 6 0 R
+>>
+>>
+/Parent 2 0 R
+>>
+endobj
+5 0 obj
+<<
+/Length 132
+>>
+stream
+BT /F1 12 Tf 100 700 Td (AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA) Tj ET
+endstream
+endobj
+6 0 obj
+<<
+/Type /Font
+/Subtype /Type1
+/BaseFont /Helvetica
+/Encoding /WinAnsiEncoding
+>>
+endobj
+7 0 obj
+<<
+/Type /Page
+/MediaBox [ 0 0 612 792 ]
+/Contents 5 0 R
+/Resources <<
+/Font <<
+/F1 6 0 R
+>>
+>>
+/Parent 2 0 R
+>>
+endobj
+8 0 obj
+<<
+/Type /Page
+/Resources <<
+>>
+/MediaBox [ 0.0 0.0 612 792 ]
+/Parent 2 0 R
+>>
+endobj
+9 0 obj
+<<
+/Type /Page
+/Resources <<
+>>
+/MediaBox [ 0.0 0.0 612 792 ]
+/Parent 2 0 R
+>>
+endobj
+10 0 obj
+<<
+/Type /Page
+/Resources <<
+>>
+/MediaBox [ 0.0 0.0 612 792 ]
+/Parent 2 0 R
+>>
+endobj
+11 0 obj
+<<
+/Type /Page
+/Resources <<
+>>
+/MediaBox [ 0.0 0.0 612 792 ]
+/Parent 2 0 R
+>>
+endobj
+12 0 obj
+<<
+/Type /Page
+/Resources <<
+>>
+/MediaBox [ 0.0 0.0 612 792 ]
+/Parent 2 0 R
+>>
+endobj
+13 0 obj
+<<
+/Type /Page
+/Resources <<
+>>
+/MediaBox [ 0.0 0.0 612 792 ]
+/Parent 2 0 R
+>>
+endobj
+14 0 obj
+<<
+/Type /Page
+/Resources <<
+>>
+/MediaBox [ 0.0 0.0 612 792 ]
+/Parent 2 0 R
+>>
+endobj
+15 0 obj
+<<
+/Type /Page
+/Resources <<
+>>
+/MediaBox [ 0.0 0.0 612 792 ]
+/Parent 2 0 R
+>>
+endobj
+xref
+0 16
+0000000000 65535 f 
+0000000015 00000 n 
+0000000054 00000 n 
+0000000174 00000 n 
+0000000223 00000 n 
+0000000351 00000 n 
+0000000534 00000 n 
+0000000631 00000 n 
+0000000759 00000 n 
+0000000853 00000 n 
+0000000947 00000 n 
+0000001042 00000 n 
+0000001137 00000 n 
+0000001232 00000 n 
+0000001327 00000 n 
+0000001422 00000 n 
+trailer
+<<
+/Size 16
+/Root 3 0 R
+/Info 1 0 R
+>>
+startxref
+1517
+%%EOF
@@ -0,0 +1,355 @@
+%PDF-1.4
+%âãÏÓ
+1 0 obj
+<<
+/Producer (pypdf)
+>>
+endobj
+2 0 obj
+<<
+/Type /Pages
+/Count 10
+/Kids [ 4 0 R 7 0 R 10 0 R 13 0 R 16 0 R 19 0 R 22 0 R 25 0 R 28 0 R 31 0 R ]
+>>
+endobj
+3 0 obj
+<<
+/Type /Catalog
+/Pages 2 0 R
+>>
+endobj
+4 0 obj
+<<
+/Type /Page
+/MediaBox [ 0 0 612 792 ]
+/Contents 5 0 R
+/Resources <<
+/Font <<
+/F1 6 0 R
+>>
+>>
+/Parent 2 0 R
+>>
+endobj
+5 0 obj
+<<
+/Length 332
+>>
+stream
+BT /F1 12 Tf 100 700 Td (AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA) Tj ET
+endstream
+endobj
+6 0 obj
+<<
+/Type /Font
+/Subtype /Type1
+/BaseFont /Helvetica
+/Encoding /WinAnsiEncoding
+>>
+endobj
+7 0 obj
+<<
+/Type /Page
+/MediaBox [ 0 0 612 792 ]
+/Contents 8 0 R
+/Resources <<
+/Font <<
+/F1 9 0 R
+>>
+>>
+/Parent 2 0 R
+>>
+endobj
+8 0 obj
+<<
+/Length 332
+>>
+stream
+BT /F1 12 Tf 100 700 Td (AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA) Tj ET
+endstream
+endobj
+9 0 obj
+<<
+/Type /Font
+/Subtype /Type1
+/BaseFont /Helvetica
+/Encoding /WinAnsiEncoding
+>>
+endobj
+10 0 obj
+<<
+/Type /Page
+/MediaBox [ 0 0 612 792 ]
+/Contents 11 0 R
+/Resources <<
+/Font <<
+/F1 12 0 R
+>>
+>>
+/Parent 2 0 R
+>>
+endobj
+11 0 obj
+<<
+/Length 332
+>>
+stream
+BT /F1 12 Tf 100 700 Td (AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA) Tj ET
+endstream
+endobj
+12 0 obj
+<<
+/Type /Font
+/Subtype /Type1
+/BaseFont /Helvetica
+/Encoding /WinAnsiEncoding
+>>
+endobj
+13 0 obj
+<<
+/Type /Page
+/MediaBox [ 0 0 612 792 ]
+/Contents 14 0 R
+/Resources <<
+/Font <<
+/F1 15 0 R
+>>
+>>
+/Parent 2 0 R
+>>
+endobj
+14 0 obj
+<<
+/Length 332
+>>
+stream
+BT /F1 12 Tf 100 700 Td (AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA) Tj ET
+endstream
+endobj
+15 0 obj
+<<
+/Type /Font
+/Subtype /Type1
+/BaseFont /Helvetica
+/Encoding /WinAnsiEncoding
+>>
+endobj
+16 0 obj
+<<
+/Type /Page
+/MediaBox [ 0 0 612 792 ]
+/Contents 17 0 R
+/Resources <<
+/Font <<
+/F1 18 0 R
+>>
+>>
+/Parent 2 0 R
+>>
+endobj
+17 0 obj
+<<
+/Length 332
+>>
+stream
+BT /F1 12 Tf 100 700 Td (AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA) Tj ET
+endstream
+endobj
+18 0 obj
+<<
+/Type /Font
+/Subtype /Type1
+/BaseFont /Helvetica
+/Encoding /WinAnsiEncoding
+>>
+endobj
+19 0 obj
+<<
+/Type /Page
+/MediaBox [ 0 0 612 792 ]
+/Contents 20 0 R
+/Resources <<
+/Font <<
+/F1 21 0 R
+>>
+>>
+/Parent 2 0 R
+>>
+endobj
+20 0 obj
+<<
+/Length 332
+>>
+stream
+BT /F1 12 Tf 100 700 Td (AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA) Tj ET
+endstream
+endobj
+21 0 obj
+<<
+/Type /Font
+/Subtype /Type1
+/BaseFont /Helvetica
+/Encoding /WinAnsiEncoding
+>>
+endobj
+22 0 obj
+<<
+/Type /Page
+/MediaBox [ 0 0 612 792 ]
+/Contents 23 0 R
+/Resources <<
+/Font <<
+/F1 24 0 R
+>>
+>>
+/Parent 2 0 R
+>>
+endobj
+23 0 obj
+<<
+/Length 332
+>>
+stream
+BT /F1 12 Tf 100 700 Td (AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA) Tj ET
+endstream
+endobj
+24 0 obj
+<<
+/Type /Font
+/Subtype /Type1
+/BaseFont /Helvetica
+/Encoding /WinAnsiEncoding
+>>
+endobj
+25 0 obj
+<<
+/Type /Page
+/MediaBox [ 0 0 612 792 ]
+/Contents 26 0 R
+/Resources <<
+/Font <<
+/F1 27 0 R
+>>
+>>
+/Parent 2 0 R
+>>
+endobj
+26 0 obj
+<<
+/Length 332
+>>
+stream
+BT /F1 12 Tf 100 700 Td (AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA) Tj ET
+endstream
+endobj
+27 0 obj
+<<
+/Type /Font
+/Subtype /Type1
+/BaseFont /Helvetica
+/Encoding /WinAnsiEncoding
+>>
+endobj
+28 0 obj
+<<
+/Type /Page
+/MediaBox [ 0 0 612 792 ]
+/Contents 29 0 R
+/Resources <<
+/Font <<
+/F1 30 0 R
+>>
+>>
+/Parent 2 0 R
+>>
+endobj
+29 0 obj
+<<
+/Length 332
+>>
+stream
+BT /F1 12 Tf 100 700 Td (AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA) Tj ET
+endstream
+endobj
+30 0 obj
+<<
+/Type /Font
+/Subtype /Type1
+/BaseFont /Helvetica
+/Encoding /WinAnsiEncoding
+>>
+endobj
+31 0 obj
+<<
+/Type /Page
+/MediaBox [ 0 0 612 792 ]
+/Contents 32 0 R
+/Resources <<
+/Font <<
+/F1 33 0 R
+>>
+>>
+/Parent 2 0 R
+>>
+endobj
+32 0 obj
+<<
+/Length 332
+>>
+stream
+BT /F1 12 Tf 100 700 Td (AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA) Tj ET
+endstream
+endobj
+33 0 obj
+<<
+/Type /Font
+/Subtype /Type1
+/BaseFont /Helvetica
+/Encoding /WinAnsiEncoding
+>>
+endobj
+xref
+0 34
+0000000000 65535 f 
+0000000015 00000 n 
+0000000054 00000 n 
+0000000176 00000 n 
+0000000225 00000 n 
+0000000353 00000 n 
+0000000736 00000 n 
+0000000833 00000 n 
+0000000961 00000 n 
+0000001344 00000 n 
+0000001441 00000 n 
+0000001572 00000 n 
+0000001956 00000 n 
+0000002054 00000 n 
+0000002185 00000 n 
+0000002569 00000 n 
+0000002667 00000 n 
+0000002798 00000 n 
+0000003182 00000 n 
+0000003280 00000 n 
+0000003411 00000 n 
+0000003795 00000 n 
+0000003893 00000 n 
+0000004024 00000 n 
+0000004408 00000 n 
+0000004506 00000 n 
+0000004637 00000 n 
+0000005021 00000 n 
+0000005119 00000 n 
+0000005250 00000 n 
+0000005634 00000 n 
+0000005732 00000 n 
+0000005863 00000 n 
+0000006247 00000 n 
+trailer
+<<
+/Size 34
+/Root 3 0 R
+/Info 1 0 R
+>>
+startxref
+6345
+%%EOF
@@ -0,0 +1,310 @@
+"""Tests for AdaptivePdfParser and AdaptiveParserMixin."""
+
+from io import BytesIO
+from pathlib import Path
+from unittest.mock import MagicMock, patch
+
+import pytest
+import requests
+from pypdf import PdfReader
+
+from chat.agent_rag.document_converter.parser import (
+    METHOD_OCR,
+    METHOD_TEXT_EXTRACTION,
+    AdaptivePdfParser,
+    analyze_pdf,
+)
+
+FIXTURES_DIR = Path(__file__).parent / "fixtures"
+
+
+@pytest.fixture(name="text_pdf_1_page")
+def provide_text_pdf_1_page():
+    """Load a 1 page PDF with extractable text."""
+    return (FIXTURES_DIR / "text_pdf_1_page.pdf").read_bytes()
+
+
+@pytest.fixture(name="text_pdf_10_pages")
+def provide_text_pdf_10_pages():
+    """Load a 10-page PDF with extractable text (~300 chars per page)."""
+    return (FIXTURES_DIR / "text_10_pages.pdf").read_bytes()
+
+
+@pytest.fixture(name="mixed_pdf_10_pages")
+def provide_mixed_pdf_10_pages():
+    """Load a 10-page PDF with 2 pages of text and 8 blank pages."""
+    return (FIXTURES_DIR / "mixed_10_pages.pdf").read_bytes()
+
+
+MIN_AVG_CHARS_FOR_TEXT_EXTRACTION = 200
+OCR_RETRY_DELAY = 1
+OCR_MAX_RETRIES = 3
+
+
+@pytest.fixture(autouse=True)
+def ai_settings(settings):
+    """Mock Django settings for OCR configuration."""
+    settings.MIN_AVG_CHARS_FOR_TEXT_EXTRACTION = MIN_AVG_CHARS_FOR_TEXT_EXTRACTION
+    settings.MIN_TEXT_COVERAGE_FOR_TEXT_EXTRACTION = 0.7
+    settings.OCR_HRID = "test-ocr-hrid"
+    settings.OCR_MODEL = "test-ocr-model"
+    settings.OCR_TIMEOUT = 60
+    settings.OCR_MAX_RETRIES = OCR_MAX_RETRIES
+    settings.OCR_RETRY_DELAY = OCR_RETRY_DELAY
+    settings.OCR_BATCH_PAGES = 10
+    settings.LLM_CONFIGURATIONS = {
+        "test-ocr-hrid": MagicMock(
+            provider=MagicMock(
+                base_url="https://ocr.example.com",
+                api_key="test-api-key",
+            )
+        )
+    }
+    return settings
+
+
+def test_analyze_pdf_returns_correct_structure(text_pdf_10_pages):
+    """analyze_pdf should return dict with expected keys."""
+    result = analyze_pdf(text_pdf_10_pages)
+
+    assert "total_pages" in result
+    assert "pages_with_text" in result
+    assert "avg_chars_per_page" in result
+    assert "text_coverage" in result
+    assert "recommended_method" in result
+
+
+def test_analyze_pdf_with_text_recommends_extraction(text_pdf_1_page):
+    """PDF with sufficient text should recommend text extraction."""
+    result = analyze_pdf(text_pdf_1_page)
+
+    assert result["total_pages"] == 1
+    assert result["pages_with_text"] == 1
+    assert result["text_coverage"] == pytest.approx(1.0)
+    assert result["avg_chars_per_page"] > MIN_AVG_CHARS_FOR_TEXT_EXTRACTION
+    assert result["recommended_method"] == METHOD_TEXT_EXTRACTION
+
+
+def test_analyze_multi_page_pdf_with_text_recommends_extraction(text_pdf_10_pages):
+    """PDF with sufficient text should recommend text extraction."""
+    result = analyze_pdf(text_pdf_10_pages)
+
+    assert result["total_pages"] == 10
+    assert result["pages_with_text"] == 10
+    assert result["text_coverage"] == pytest.approx(1.0)
+    assert result["avg_chars_per_page"] > MIN_AVG_CHARS_FOR_TEXT_EXTRACTION
+    assert result["recommended_method"] == METHOD_TEXT_EXTRACTION
+
+
+def test_analyze_pdf_mixed_content_recommends_ocr(mixed_pdf_10_pages):
+    """PDF with low text coverage should recommend OCR."""
+    result = analyze_pdf(mixed_pdf_10_pages)
+
+    assert result["total_pages"] == 10
+    assert result["pages_with_text"] == 2
+    assert result["text_coverage"] == pytest.approx(0.2)
+    assert result["recommended_method"] == METHOD_OCR
+
+
+def test_extract_page_batch_single_page(text_pdf_10_pages):
+    """Should extract a single page correctly."""
+    parser = AdaptivePdfParser()
+    reader = PdfReader(BytesIO(text_pdf_10_pages))
+
+    result = parser.extract_page_batch(reader, 0, 1)
+
+    result_reader = PdfReader(BytesIO(result))
+    assert len(result_reader.pages) == 1
+
+
+def test_extract_page_batch_multiple_pages(text_pdf_10_pages):
+    """Should extract multiple pages correctly."""
+    parser = AdaptivePdfParser()
+    reader = PdfReader(BytesIO(text_pdf_10_pages))
+
+    result = parser.extract_page_batch(reader, 2, 7)
+
+    result_reader = PdfReader(BytesIO(result))
+    assert len(result_reader.pages) == 5
+
+
+def test_extract_page_batch_last_batch(text_pdf_10_pages):
+    """Should handle last batch with fewer pages."""
+    parser = AdaptivePdfParser()
+    reader = PdfReader(BytesIO(text_pdf_10_pages))
+
+    result = parser.extract_page_batch(reader, 7, 10)
+
+    result_reader = PdfReader(BytesIO(result))
+    assert len(result_reader.pages) == 3
+
+
+def test_ocr_page_batch_success(text_pdf_1_page):
+    """Should return markdown content on successful OCR."""
+    parser = AdaptivePdfParser()
+
+    with patch("chat.agent_rag.document_converter.parser.requests.post") as mock_post:
+        mock_post.return_value.json.return_value = {
+            "pages": [
+                {"markdown": "# Page 1 content"},
+            ]
+        }
+        mock_post.return_value.raise_for_status = MagicMock()
+
+        result = parser.ocr_page_batch("test.pdf", text_pdf_1_page, 0, 1)
+
+        assert result == ["# Page 1 content"]
+        mock_post.assert_called_once()
+
+
+def test_ocr_page_batch_retry_on_timeout(text_pdf_1_page):
+    """Should retry on timeout with static delay."""
+    parser = AdaptivePdfParser()
+
+    with patch("chat.agent_rag.document_converter.parser.requests.post") as mock_post:
+        with patch("chat.agent_rag.document_converter.parser.time.sleep") as mock_sleep:
+            mock_post.side_effect = [
+                requests.Timeout("Connection timed out"),
+                MagicMock(
+                    json=MagicMock(return_value={"pages": [{"markdown": "# Content"}]}),
+                    raise_for_status=MagicMock(),
+                ),
+            ]
+
+            result = parser.ocr_page_batch("test.pdf", text_pdf_1_page, 0, 1)
+
+            assert result == ["# Content"]
+            assert mock_post.call_count == 2
+            mock_sleep.assert_called_once_with(OCR_RETRY_DELAY)
+
+
+def test_ocr_page_batch_fails_after_max_retries(text_pdf_1_page):
+    """Should raise exception after max retries exceeded."""
+    parser = AdaptivePdfParser()
+
+    with patch("chat.agent_rag.document_converter.parser.requests.post") as mock_post:
+        with patch("chat.agent_rag.document_converter.parser.time.sleep"):
+            mock_post.side_effect = requests.Timeout("Connection timed out")
+
+            with pytest.raises(requests.Timeout):
+                parser.ocr_page_batch("test.pdf", text_pdf_1_page, 0, 1)
+
+            assert mock_post.call_count == OCR_MAX_RETRIES
+
+
+def test_ocr_page_batch_retry_on_request_exception(text_pdf_1_page):
+    """Should retry on general request exceptions."""
+    parser = AdaptivePdfParser()
+
+    with patch("chat.agent_rag.document_converter.parser.requests.post") as mock_post:
+        with patch("chat.agent_rag.document_converter.parser.time.sleep"):
+            mock_post.side_effect = [
+                requests.RequestException("Network error"),
+                requests.RequestException("Network error"),
+                MagicMock(
+                    json=MagicMock(return_value={"pages": [{"markdown": "# Content"}]}),
+                    raise_for_status=MagicMock(),
+                ),
+            ]
+
+            result = parser.ocr_page_batch("test.pdf", text_pdf_1_page, 0, 1)
+
+            assert result == ["# Content"]
+            assert mock_post.call_count == 3
+
+
+def test_parse_pdf_with_ocr_single_batch(text_pdf_10_pages):
+    """Should process PDF in single batch when pages <= batch size."""
+    parser = AdaptivePdfParser()
+
+    with patch("chat.agent_rag.document_converter.parser.requests.post") as mock_post:
+        mock_post.return_value.json.return_value = {
+            "pages": [{"markdown": f"Page {i}"} for i in range(1, 11)]
+        }
+        mock_post.return_value.raise_for_status = MagicMock()
+
+        result = parser.parse_pdf_document_with_ocr("test.pdf", text_pdf_10_pages)
+
+        assert "Page 1" in result
+        assert "Page 10" in result
+        mock_post.assert_called_once()
+
+
+def test_parse_pdf_with_ocr_multiple_batches(text_pdf_10_pages, settings):
+    """Should process PDF in multiple batches when pages > batch size."""
+    settings.OCR_BATCH_PAGES = 4  # Force multiple batches
+    parser = AdaptivePdfParser()
+
+    with patch("chat.agent_rag.document_converter.parser.requests.post") as mock_post:
+        mock_post.return_value.json.side_effect = [
+            {"pages": [{"markdown": f"Page {i}"} for i in range(1, 5)]},
+            {"pages": [{"markdown": f"Page {i}"} for i in range(5, 9)]},
+            {"pages": [{"markdown": f"Page {i}"} for i in range(9, 11)]},
+        ]
+        mock_post.return_value.raise_for_status = MagicMock()
+
+        result = parser.parse_pdf_document_with_ocr("test.pdf", text_pdf_10_pages)
+
+        assert mock_post.call_count == 3
+        assert "Page 1" in result
+        assert "Page 10" in result
+
+
+def test_parse_pdf_with_ocr_partial_failure(text_pdf_10_pages, settings):
+    """Should insert empty placeholders for failed batches."""
+    settings.OCR_BATCH_PAGES = 4  # Force multiple batches
+    parser = AdaptivePdfParser()
+
+    success_response = MagicMock()
+    success_response.json.return_value = {"pages": [{"markdown": f"Page {i}"} for i in range(1, 5)]}
+    success_response.raise_for_status = MagicMock()
+
+    with patch("chat.agent_rag.document_converter.parser.requests.post") as mock_post:
+        with patch("chat.agent_rag.document_converter.parser.time.sleep"):
+            # First batch succeeds, then all retries fail for remaining batches
+            mock_post.side_effect = [
+                success_response,
+                requests.Timeout("OCR failed"),
+                requests.Timeout("OCR failed"),
+                requests.Timeout("OCR failed"),
+                requests.Timeout("OCR failed"),
+                requests.Timeout("OCR failed"),
+                requests.Timeout("OCR failed"),
+            ]
+
+            result = parser.parse_pdf_document_with_ocr("test.pdf", text_pdf_10_pages)
+
+            parts = result.split("\n\n")
+            # First batch succeeded (4 pages), remaining batches failed (6 pages as placeholders)
+            assert len(parts) == 10
+            assert parts[0] == "Page 1"
+            assert parts[3] == "Page 4"
+            assert parts[4] == ""  # Failed batch placeholder
+
+
+def test_parse_document_pdf_routed_correctly(text_pdf_1_page):
+    """Should route PDF content type to PDF parser."""
+    parser = AdaptivePdfParser()
+
+    with patch.object(parser, "parse_pdf_document", return_value="pdf content") as mock_parse:
+        result = parser.parse_document("test.pdf", "application/pdf", text_pdf_1_page)
+
+        assert result == "pdf content"
+        mock_parse.assert_called_once_with(
+            name="test.pdf",
+            content_type="application/pdf",
+            content=text_pdf_1_page,
+        )
+
+
+def test_parse_document_non_pdf_uses_document_converter():
+    """Should route non-PDF content to DocumentConverter."""
+    parser = AdaptivePdfParser()
+
+    with patch("chat.agent_rag.document_converter.parser.DocumentConverter") as mock_converter:
+        mock_converter.return_value.convert_raw.return_value = "docx content"
+
+        result = parser.parse_document("test.docx", "application/vnd.openxmlformats", b"content")
+
+        assert result == "docx content"
+        mock_converter.return_value.convert_raw.assert_called_once()
@@ -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):
@@ -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
@@ -0,0 +1,60 @@
+"""Unit tests for project-level LLM instructions injection."""
+
+import pytest
+
+from chat.clients.pydantic_ai import AIAgentService
+from chat.factories import ChatConversationFactory, ChatProjectFactory
+
+pytestmark = pytest.mark.django_db
+
+
+@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-123"
+    settings.AI_AGENT_INSTRUCTIONS = "You are a helpful assistant"
+    settings.AI_AGENT_TOOLS = []
+
+
+def _get_instruction_names(service):
+    """Return the names of dynamic (callable) instructions registered on the conversation agent."""
+    # pylint: disable=protected-access
+    return [fn.__name__ for fn in service.conversation_agent._instructions if callable(fn)]
+
+
+def test_project_instructions_injected_when_present():
+    """Test that project LLM instructions are injected as a dynamic agent instruction."""
+    project = ChatProjectFactory(llm_instructions="Always answer in bullet points.")
+    conversation = ChatConversationFactory(owner=project.owner, project=project)
+
+    service = AIAgentService(conversation, user=conversation.owner)
+
+    assert "project_instructions" in _get_instruction_names(service)
+    # Verify the instruction returns the correct content
+    instruction_fn = next(
+        fn
+        for fn in service.conversation_agent._instructions  # pylint: disable=protected-access
+        if callable(fn) and fn.__name__ == "project_instructions"
+    )
+    assert instruction_fn() == "Always answer in bullet points."
+
+
+def test_project_instructions_not_injected_when_empty():
+    """Test that empty project instructions are not injected."""
+    project = ChatProjectFactory(llm_instructions="")
+    conversation = ChatConversationFactory(owner=project.owner, project=project)
+
+    service = AIAgentService(conversation, user=conversation.owner)
+
+    assert "project_instructions" not in _get_instruction_names(service)
+
+
+def test_project_instructions_not_injected_when_no_project():
+    """Test that no project instruction is injected for standalone conversations."""
+    conversation = ChatConversationFactory()
+
+    service = AIAgentService(conversation, user=conversation.owner)
+
+    assert "project_instructions" not in _get_instruction_names(service)
@@ -0,0 +1,95 @@
+"""Unit tests for add_document_rag_search_tool_from_setting integration with AIAgentService."""
+
+# pylint: disable=redefined-outer-name, protected-access
+
+import pytest
+from pydantic_ai.models.test import TestModel
+
+from chat.clients.pydantic_ai import AIAgentService
+from chat.factories import ChatConversationFactory, UserFactory
+from chat.llm_configuration import LLModel, LLMProvider
+
+pytestmark = pytest.mark.django_db()
+
+
+@pytest.fixture()
+def _llm_config_with_websearch(settings):
+    """Configure a single active model that includes the web search tool."""
+    settings.LLM_CONFIGURATIONS = {
+        "default-model": LLModel(
+            hrid="default-model",
+            model_name="amazing-llm",
+            human_readable_name="Amazing LLM",
+            is_active=True,
+            icon=None,
+            system_prompt="You are an amazing assistant.",
+            tools=["web_search_brave_with_document_backend"],
+            provider=LLMProvider(
+                hrid="unused",
+                base_url="https://example.com",
+                api_key="key",
+            ),
+        ),
+    }
+
+
+def test_smart_search_disabled_suppresses_tool_at_runtime(_llm_config_with_websearch):
+    """
+    When smart search is off, the tool must be suppressed at runtime.
+    """
+    user = UserFactory(allow_smart_web_search=False)
+    conversation = ChatConversationFactory(owner=user)
+    service = AIAgentService(conversation, user=user)
+
+    assert service._is_smart_search_enabled is False
+    assert service._is_web_search_enabled is True
+
+    # Replicate what _run_agent does before calling the model
+    if not service._is_smart_search_enabled and service._is_web_search_enabled:
+        service._context_deps.web_search_enabled = False
+
+    with service.conversation_agent.override(model=TestModel(), deps=service._context_deps):
+        response = service.conversation_agent.run_sync("Search the web for something.")
+
+    assert response.output == "success (no tool calls)"
+
+
+def test_smart_search_enabled_tool_is_called(_llm_config_with_websearch):
+    """
+    When smart search is on, the tool must be invoked.
+    """
+    user = UserFactory(allow_smart_web_search=True)
+    conversation = ChatConversationFactory(owner=user)
+    service = AIAgentService(conversation, user=user)
+
+    assert service._is_smart_search_enabled is True
+    assert service._context_deps.web_search_enabled is True
+
+    with service.conversation_agent.override(model=TestModel(), deps=service._context_deps):
+        response = service.conversation_agent.run_sync("Search the web for something.")
+
+    assert "web_search_brave_with_document_backend" in response.output
+
+
+def test_force_websearch_overrides_smart_search_disabled(_llm_config_with_websearch):
+    """
+    When smart search is off, the tool must be enabled via force_web_search.
+    """
+    user = UserFactory(allow_smart_web_search=False)
+    conversation = ChatConversationFactory(owner=user)
+    service = AIAgentService(conversation, user=user)
+
+    assert service._is_smart_search_enabled is False
+    assert service._context_deps.web_search_enabled is False
+
+    service._setup_web_search(force_web_search=True)
+
+    web_search_tool_name = service.conversation_agent.get_web_search_tool_name()
+    assert service._context_deps.web_search_enabled is True
+    assert any(
+        callable(instr) and web_search_tool_name in instr()
+        for instr in service.conversation_agent._instructions
+    )
+    with service.conversation_agent.override(model=TestModel(), deps=service._context_deps):
+        response = service.conversation_agent.run_sync("Search the web for something.")
+        assert "web_search_brave_with_document_backend" in response.output
@@ -2,19 +2,25 @@

 import logging
 from contextlib import ExitStack, contextmanager
+from importlib import reload
 from unittest.mock import patch

+from django.urls import clear_url_caches, set_urlconf
 from django.utils import formats, timezone

 import pytest

+import core.urls
+
+import chat.views
+import conversations.urls
 from chat.agents.summarize import SummarizationAgent
 from chat.clients.pydantic_ai import AIAgentService

 logger = logging.getLogger(__name__)


-@pytest.fixture(name="today_promt_date")
+@pytest.fixture(name="today_prompt_date")
 def today_prompt_date_fixture():
    """Fixture to mock date the system prompt when useless to test it."""
    _formatted_date = formats.date_format(timezone.now(), "l d/m/Y", use_l10n=False)
@@ -90,3 +96,35 @@ PIXEL_PNG = (
    b"\x00\x00\x1f\x15\xc4\x89\x00\x00\x00\nIDATx\x9cc\xf8\xff\xff?\x00\x05\xfe\x02\xfe"
    b"\xa7V\xbd\xfa\x00\x00\x00\x00IEND\xaeB`\x82"
 )
+
+
+@pytest.fixture(name="oidc_refresh_token_enabled")
+def fixture_oidc_refresh_token_enabled(settings):
+    """
+    Fixture to enable OIDC refresh token storage during the test.
+
+    This is not a nice fixture, as it forces reloading views and URL configurations.
+    Maybe there is a better way to do this, because even the conditional_refresh_oidc_token
+    function is not nice, but I don't want it to be lazy either.
+    """
+    __initial_value = bool(settings.OIDC_STORE_REFRESH_TOKEN)
+
+    settings.OIDC_STORE_REFRESH_TOKEN = True
+
+    # force view reload
+    reload(chat.views)
+    reload(core.urls)
+    reload(conversations.urls)
+    clear_url_caches()
+    set_urlconf(None)
+
+    yield settings
+
+    settings.OIDC_STORE_REFRESH_TOKEN = __initial_value
+
+    # force view reload
+    reload(chat.views)
+    reload(core.urls)
+    reload(conversations.urls)
+    clear_url_caches()
+    set_urlconf(None)
@@ -0,0 +1 @@
+"""Tests for chat factories."""
@@ -0,0 +1,25 @@
+"""Unit tests for the ChatConversationFactory."""
+
+import pytest
+
+from chat.factories import ChatConversationFactory, ChatProjectFactory
+
+pytestmark = pytest.mark.django_db
+
+
+def test_conversation_factory():
+    """Test that the factory creates a valid conversation with default values."""
+    conversation = ChatConversationFactory()
+
+    assert conversation.owner is not None
+    assert conversation.title is None
+    assert conversation.project is None
+
+
+def test_conversation_factory_with_project():
+    """Test that the factory accepts a project."""
+    project = ChatProjectFactory()
+    conversation = ChatConversationFactory(project=project, owner=project.owner)
+
+    assert conversation.project == project
+    assert conversation.owner == project.owner
@@ -0,0 +1,26 @@
+"""Unit tests for the ChatProjectFactory."""
+
+import pytest
+
+from chat.factories import ChatProjectFactory
+
+pytestmark = pytest.mark.django_db
+
+
+def test_project_factory():
+    """Test that the factory creates a valid project with default values."""
+    project = ChatProjectFactory()
+
+    assert project.title.startswith("title ")
+    assert project.icon
+    assert project.color
+    assert project.owner is not None
+    assert project.conversations.count() == 0
+
+
+def test_project_factory_number_of_conversations():
+    """Test that number_of_conversations creates attached conversations."""
+    project = ChatProjectFactory(number_of_conversations=3)
+
+    assert project.conversations.count() == 3
+    assert all(c.owner == project.owner for c in project.conversations.all())
@@ -0,0 +1,152 @@
+"""Unit tests for the ChatProjectSerializer."""
+
+import pytest
+from rest_framework.test import APIRequestFactory
+
+from core.factories import UserFactory
+
+from chat import serializers
+from chat.factories import ChatConversationFactory, ChatProjectFactory
+from chat.models import ChatProjectColor, ChatProjectIcon
+
+pytestmark = pytest.mark.django_db
+
+
+@pytest.fixture(name="request_context")
+def request_context_fixture():
+    """Return a serializer context with an authenticated request."""
+    user = UserFactory()
+    request = APIRequestFactory().post("/")
+    request.user = user
+    return {"request": request}
+
+
+def test_serialize_project():
+    """Test serializing a project returns expected fields."""
+    project = ChatProjectFactory(
+        title="My project",
+        llm_instructions="My custom instructions",
+        color=ChatProjectColor.COLOR_2,
+        icon=ChatProjectIcon.JUSTICE,
+    )
+    serializer = serializers.ChatProjectSerializer(project)
+    data = serializer.data
+
+    assert data["title"] == "My project"
+    assert data["id"] == str(project.pk)
+    assert data["icon"] == "justice"
+    assert data["color"] == "color_2"
+    assert data["llm_instructions"] == "My custom instructions"
+    assert data["conversations"] == []
+    assert "created_at" in data
+    assert "updated_at" in data
+
+
+def test_serialize_project_with_conversations():
+    """Test serializing a project includes nested conversations."""
+    project = ChatProjectFactory()
+    conversation = ChatConversationFactory(
+        project=project, owner=project.owner, title="My conversation"
+    )
+    serializer = serializers.ChatProjectSerializer(project)
+    data = serializer.data
+
+    assert len(data["conversations"]) == 1
+    assert data["conversations"][0] == {
+        "id": str(conversation.pk),
+        "title": "My conversation",
+    }
+
+
+def test_deserialize_valid_project(request_context):
+    """Test deserializing valid project data."""
+    data = {
+        "title": "My Project",
+        "icon": "star",
+        "color": "color_2",
+    }
+    serializer = serializers.ChatProjectSerializer(data=data, context=request_context)
+
+    assert serializer.is_valid()
+    assert serializer.validated_data["title"] == "My Project"
+    assert serializer.validated_data["icon"] == ChatProjectIcon.STAR
+    assert serializer.validated_data["color"] == ChatProjectColor.COLOR_2
+
+
+def test_deserialize_missing_title(request_context):
+    """Test that title is required."""
+    data = {
+        "icon": ChatProjectIcon.FOLDER,
+        "color": ChatProjectColor.COLOR_1,
+    }
+    serializer = serializers.ChatProjectSerializer(data=data, context=request_context)
+
+    assert not serializer.is_valid()
+    assert "title" in serializer.errors
+
+
+def test_deserialize_invalid_icon(request_context):
+    """Test that an invalid icon value is rejected."""
+    data = {
+        "title": "My Project",
+        "icon": "invalid_icon",
+        "color": ChatProjectColor.COLOR_1,
+    }
+    serializer = serializers.ChatProjectSerializer(data=data, context=request_context)
+
+    assert not serializer.is_valid()
+    assert "icon" in serializer.errors
+
+
+def test_deserialize_invalid_color(request_context):
+    """Test that an invalid color value is rejected."""
+    data = {
+        "title": "My Project",
+        "icon": ChatProjectIcon.FOLDER,
+        "color": "invalid_color",
+    }
+    serializer = serializers.ChatProjectSerializer(data=data, context=request_context)
+
+    assert not serializer.is_valid()
+    assert "color" in serializer.errors
+
+
+def test_deserialize_title_max_length(request_context):
+    """Test that a title exceeding 100 characters is rejected."""
+    data = {
+        "title": "X" * 101,
+        "icon": ChatProjectIcon.FOLDER,
+        "color": ChatProjectColor.COLOR_1,
+    }
+    serializer = serializers.ChatProjectSerializer(data=data, context=request_context)
+
+    assert not serializer.is_valid()
+    assert "title" in serializer.errors
+
+
+def test_conversations_field_is_read_only(request_context):
+    """Test that conversations cannot be set via input data."""
+    data = {
+        "title": "My Project",
+        "icon": ChatProjectIcon.FOLDER,
+        "color": ChatProjectColor.COLOR_1,
+        "conversations": [{"id": "fake", "title": "fake"}],
+    }
+    serializer = serializers.ChatProjectSerializer(data=data, context=request_context)
+
+    assert serializer.is_valid()
+    assert "conversations" not in serializer.validated_data
+
+
+def test_owner_is_set_from_request(request_context):
+    """Test that the owner is automatically set from the request user."""
+    data = {
+        "title": "My Project",
+        "icon": ChatProjectIcon.FOLDER,
+        "color": ChatProjectColor.COLOR_1,
+    }
+    serializer = serializers.ChatProjectSerializer(data=data, context=request_context)
+
+    assert serializer.is_valid()
+    project = serializer.save()
+    assert project.owner == request_context["request"].user
@@ -1,5 +1,6 @@
 """Tests for local_media_url_processors."""

+from io import BytesIO
 from unittest.mock import patch

 import pytest
@@ -12,7 +13,10 @@ from pydantic_ai import (
    UserPromptPart,
 )

+from core.file_upload.enums import FileToLLMMode
+
 from chat.agents.local_media_url_processors import (
+    _get_file_url_for_llm,
    update_history_local_urls,
    update_local_urls,
 )
@@ -121,3 +125,549 @@ def test_update_history_local_urls_no_user_prompt_parts():
        result = update_history_local_urls(conversation, messages)
        assert result == messages
        mock.assert_not_called()
+
+
+@patch("chat.agents.local_media_url_processors._get_file_url_for_llm")
+def test_update_local_urls_uses_get_file_url_for_llm(mock_get_file_url):
+    """Test that update_local_urls uses _get_file_url_for_llm for mode-aware URLs."""
+    conversation = ChatConversationFactory()
+    mock_get_file_url.return_value = "mode-aware-url"
+
+    key = f"{conversation.pk}/test.jpg"
+    contents = [ImageUrl(url=f"/media-key/{key}")]
+
+    result = list(update_local_urls(conversation, contents))
+
+    assert len(result) == 1
+    assert result[0].url == "mode-aware-url"
+    mock_get_file_url.assert_called_once()
+
+
+@patch("chat.agents.local_media_url_processors.generate_retrieve_policy")
+def test_get_file_url_presigned_mode(mock_policy):
+    """Test URL generation in presigned_url mode."""
+
+    mock_policy.return_value = "presigned_s3_url"
+
+    url = _get_file_url_for_llm("test/key.pdf", FileToLLMMode.PRESIGNED_URL)
+
+    assert url == "presigned_s3_url"
+    mock_policy.assert_called_once_with("test/key.pdf")
+
+
+@patch("chat.agents.local_media_url_processors.generate_temporary_url")
+def test_get_file_url_backend_temporary_url_mode(mock_temp_url):
+    """Test URL generation in backend_temporary_url mode."""
+
+    mock_temp_url.return_value = "/api/v1.0/file-stream/token123/"
+
+    url = _get_file_url_for_llm("test/key.pdf", FileToLLMMode.BACKEND_TEMPORARY_URL)
+
+    assert url == "/api/v1.0/file-stream/token123/"
+    mock_temp_url.assert_called_once_with("test/key.pdf")
+
+
+@patch("chat.agents.local_media_url_processors.default_storage.open")
+def test_get_file_url_backend_base64_mode(mock_storage):
+    """Test URL generation in backend_base64 mode."""
+
+    # Mock file content
+    file_content = b"PDF binary content"
+    mock_file = BytesIO(file_content)
+    mock_storage.return_value.__enter__.return_value = mock_file
+
+    url = _get_file_url_for_llm("test/key.pdf", FileToLLMMode.BACKEND_BASE64)
+
+    # URL should be a data URL
+    assert url.startswith("data:")
+    assert "base64" in url
+    mock_storage.assert_called_once()
+
+
+@patch(
+    "chat.agents.local_media_url_processors.default_storage.open", side_effect=Exception("S3 error")
+)
+@patch("chat.agents.local_media_url_processors.generate_retrieve_policy")
+def test_get_file_url_backend_base64_fallback(mock_policy, _mock_storage):
+    """Test fallback to presigned URL when base64 encoding fails."""
+
+    mock_policy.return_value = "fallback_presigned_url"
+
+    url = _get_file_url_for_llm("test/key.pdf", FileToLLMMode.BACKEND_BASE64)
+
+    # Should fall back to presigned URL
+    assert url == "fallback_presigned_url"
+    mock_policy.assert_called_once()
+
+
+@patch("chat.agents.local_media_url_processors._get_file_url_for_llm")
+def test_update_local_urls_multiple_images_with_modes(mock_get_file_url):
+    """Test handling multiple images with mode-aware URL generation."""
+    conversation = ChatConversationFactory()
+
+    # Mock different URLs for different calls
+    urls = ["url1", "url2", "url3"]
+    mock_get_file_url.side_effect = urls
+
+    key1 = f"{conversation.pk}/image1.jpg"
+    key2 = f"{conversation.pk}/image2.png"
+    key3 = f"{conversation.pk}/document.pdf"
+
+    contents = [
+        ImageUrl(url=f"/media-key/{key1}"),
+        ImageUrl(url=f"/media-key/{key2}"),
+        DocumentUrl(url=f"/media-key/{key3}"),
+    ]
+
+    result = list(update_local_urls(conversation, contents))
+
+    assert len(result) == 3
+    assert result[0].url == "url1"
+    assert result[1].url == "url2"
+    assert result[2].url == "url3"
+    assert mock_get_file_url.call_count == 3
+
+
+@patch("chat.agents.local_media_url_processors._get_file_url_for_llm")
+def test_update_local_urls_mixed_external_and_local_urls(mock_get_file_url):
+    """Test handling of mixed external and local URLs."""
+    conversation = ChatConversationFactory()
+    mock_get_file_url.return_value = "mode-aware-url"
+
+    key = f"{conversation.pk}/test.jpg"
+    contents = [
+        ImageUrl(url=f"/media-key/{key}"),  # Local URL - will be processed
+        ImageUrl(url="https://external.com/image.jpg"),  # External URL - kept as is
+        ImageUrl(url="http://another.com/image.png"),  # External URL - kept as is
+    ]
+
+    result = list(update_local_urls(conversation, contents))
+
+    assert len(result) == 3
+    assert result[0].url == "mode-aware-url"
+    assert result[1].url == "https://external.com/image.jpg"
+    assert result[2].url == "http://another.com/image.png"
+    # Only one local URL was processed
+    assert mock_get_file_url.call_count == 1
+
+
+@patch("chat.agents.local_media_url_processors._get_file_url_for_llm")
+def test_update_history_local_urls_with_mode_detection(mock_get_file_url):
+    """Test that update_history_local_urls uses mode detection for URLs."""
+    conversation = ChatConversationFactory()
+    mock_get_file_url.return_value = "mode-aware-url"
+
+    key = f"{conversation.pk}/test.jpg"
+    user_prompt_content = [ImageUrl(url=f"/media-key/{key}")]
+
+    messages = [
+        ModelRequest(parts=[UserPromptPart(content=user_prompt_content)]),
+        ModelResponse(parts=[TextPart(content="I see your image.")]),
+    ]
+
+    with patch("chat.agents.local_media_url_processors.update_local_urls") as mock_update:
+        mock_update.return_value = iter([ImageUrl(url="mode-aware-url")])
+        result = update_history_local_urls(conversation, messages)
+
+        assert len(result) == 2
+        mock_update.assert_called_once()
+
+
+def test_update_local_urls_preserves_other_url_types():
+    """Test that update_local_urls preserves other URL types unchanged."""
+    conversation = ChatConversationFactory()
+
+    contents = [
+        ImageUrl(url="data:image/png;base64,iVBORw0KG..."),  # Already data URL
+        ImageUrl(url="https://example.com/image.jpg"),  # HTTPS
+        ImageUrl(url="http://example.com/image.jpg"),  # HTTP
+    ]
+
+    result = list(update_local_urls(conversation, contents))
+
+    assert len(result) == 3
+    assert result[0].url == "data:image/png;base64,iVBORw0KG..."
+    assert result[1].url == "https://example.com/image.jpg"
+    assert result[2].url == "http://example.com/image.jpg"
+
+
+@patch("chat.agents.local_media_url_processors._get_file_url_for_llm")
+def test_update_local_urls_stores_updated_urls_mapping(mock_get_file_url):
+    """Test that update_local_urls stores the mapping of new to old URLs."""
+    conversation = ChatConversationFactory()
+    mock_get_file_url.return_value = "new-mode-aware-url"
+
+    key = f"{conversation.pk}/test.jpg"
+    old_url = f"/media-key/{key}"
+    contents = [ImageUrl(url=old_url)]
+    updated_urls = {}
+
+    list(update_local_urls(conversation, contents, updated_urls))
+
+    assert "new-mode-aware-url" in updated_urls
+    assert updated_urls["new-mode-aware-url"] == old_url
+
+
+def test_update_local_urls_security_prevents_other_conversation_access():
+    """Test that security check prevents accessing other conversation's files."""
+    conversation = ChatConversationFactory()
+    other_conversation_key = "other-uuid/attachments/file.jpg"
+
+    # Try to access file from different conversation
+    contents = [ImageUrl(url=f"/media-key/{other_conversation_key}")]
+
+    with patch("chat.agents.local_media_url_processors._get_file_url_for_llm") as mock_get:
+        result = list(update_local_urls(conversation, contents))
+
+        # URL should not be processed (security check failed)
+        assert result[0].url == f"/media-key/{other_conversation_key}"
+        # _get_file_url_for_llm should NOT be called
+        mock_get.assert_not_called()
+
+
+@patch("chat.agents.local_media_url_processors._get_file_url_for_llm")
+def test_get_file_url_is_called_with_correct_arguments(mock_get_file_url):
+    """Test that _get_file_url_for_llm is called with correct arguments."""
+    conversation = ChatConversationFactory()
+    mock_get_file_url.return_value = "processed-url"
+
+    key = f"{conversation.pk}/test.jpg"
+    contents = [ImageUrl(url=f"/media-key/{key}")]
+
+    list(update_local_urls(conversation, contents))
+
+    # Verify the function was called with the S3 key (without /media-key/ prefix)
+    mock_get_file_url.assert_called_once()
+    call_args = mock_get_file_url.call_args
+    assert call_args[0][0] == key  # First argument should be the S3 key
+
+
+# ==================== Tests for FILE_TO_LLM_MODE settings ====================
+
+
+@patch("chat.agents.local_media_url_processors.generate_retrieve_policy")
+def test_update_local_urls_with_presigned_url_mode(mock_policy, settings):
+    """Test update_local_urls with PRESIGNED_URL mode."""
+    settings.FILE_TO_LLM_MODE = FileToLLMMode.PRESIGNED_URL
+    conversation = ChatConversationFactory()
+    mock_policy.return_value = "https://s3.example.com/presigned-url"
+
+    key = f"{conversation.pk}/test.jpg"
+    contents = [ImageUrl(url=f"/media-key/{key}")]
+
+    result = list(update_local_urls(conversation, contents))
+
+    assert len(result) == 1
+    assert result[0].url == "https://s3.example.com/presigned-url"
+    mock_policy.assert_called_once_with(key)
+
+
+@patch("chat.agents.local_media_url_processors.generate_temporary_url")
+def test_update_local_urls_with_backend_temporary_url_mode(mock_temp_url, settings):
+    """Test update_local_urls with BACKEND_TEMPORARY_URL mode."""
+    settings.FILE_TO_LLM_MODE = FileToLLMMode.BACKEND_TEMPORARY_URL
+    conversation = ChatConversationFactory()
+    mock_temp_url.return_value = "/api/v1.0/file-stream/temp-token-123/"
+
+    key = f"{conversation.pk}/test.pdf"
+    contents = [DocumentUrl(url=f"/media-key/{key}")]
+
+    result = list(update_local_urls(conversation, contents))
+
+    assert len(result) == 1
+    assert result[0].url == "/api/v1.0/file-stream/temp-token-123/"
+    mock_temp_url.assert_called_once_with(key)
+
+
+@patch("chat.agents.local_media_url_processors.default_storage.open")
+def test_update_local_urls_with_backend_base64_mode(mock_storage, settings):
+    """Test update_local_urls with BACKEND_BASE64 mode."""
+    settings.FILE_TO_LLM_MODE = FileToLLMMode.BACKEND_BASE64
+    conversation = ChatConversationFactory()
+
+    file_content = b"Mock image binary content"
+    mock_file = BytesIO(file_content)
+    mock_storage.return_value.__enter__.return_value = mock_file
+
+    key = f"{conversation.pk}/test.jpg"
+    contents = [ImageUrl(url=f"/media-key/{key}")]
+
+    result = list(update_local_urls(conversation, contents))
+
+    assert len(result) == 1
+    # Should be a data URL
+    assert result[0].url.startswith("data:")
+    assert "base64" in result[0].url
+    mock_storage.assert_called_once()
+
+
+@patch("chat.agents.local_media_url_processors.generate_retrieve_policy")
+@patch("chat.agents.local_media_url_processors.default_storage.open")
+def test_update_local_urls_backend_base64_fallback_on_error(mock_storage, mock_policy, settings):
+    """Test that update_local_urls falls back to presigned URL when base64 fails."""
+    settings.FILE_TO_LLM_MODE = FileToLLMMode.BACKEND_BASE64
+    conversation = ChatConversationFactory()
+    mock_storage.side_effect = Exception("S3 connection error")
+    mock_policy.return_value = "https://s3.example.com/fallback-url"
+
+    key = f"{conversation.pk}/test.jpg"
+    contents = [ImageUrl(url=f"/media-key/{key}")]
+
+    result = list(update_local_urls(conversation, contents))
+
+    assert len(result) == 1
+    # Should fall back to presigned URL
+    assert result[0].url == "https://s3.example.com/fallback-url"
+    mock_policy.assert_called_once_with(key)
+
+
+@patch("chat.agents.local_media_url_processors.generate_retrieve_policy")
+def test_update_local_urls_multiple_files_presigned_mode(mock_policy, settings):
+    """Test update_local_urls with multiple files in PRESIGNED_URL mode."""
+    settings.FILE_TO_LLM_MODE = FileToLLMMode.PRESIGNED_URL
+    conversation = ChatConversationFactory()
+    mock_policy.side_effect = [
+        "https://s3.example.com/image1-presigned",
+        "https://s3.example.com/image2-presigned",
+        "https://s3.example.com/document-presigned",
+    ]
+
+    key1 = f"{conversation.pk}/image1.jpg"
+    key2 = f"{conversation.pk}/image2.png"
+    key3 = f"{conversation.pk}/document.pdf"
+
+    contents = [
+        ImageUrl(url=f"/media-key/{key1}"),
+        ImageUrl(url=f"/media-key/{key2}"),
+        DocumentUrl(url=f"/media-key/{key3}"),
+    ]
+
+    result = list(update_local_urls(conversation, contents))
+
+    assert len(result) == 3
+    assert result[0].url == "https://s3.example.com/image1-presigned"
+    assert result[1].url == "https://s3.example.com/image2-presigned"
+    assert result[2].url == "https://s3.example.com/document-presigned"
+    assert mock_policy.call_count == 3
+
+
+@patch("chat.agents.local_media_url_processors.generate_temporary_url")
+def test_update_local_urls_multiple_files_temporary_url_mode(mock_temp_url, settings):
+    """Test update_local_urls with multiple files in BACKEND_TEMPORARY_URL mode."""
+    settings.FILE_TO_LLM_MODE = FileToLLMMode.BACKEND_TEMPORARY_URL
+    conversation = ChatConversationFactory()
+    mock_temp_url.side_effect = [
+        "/api/v1.0/file-stream/token1/",
+        "/api/v1.0/file-stream/token2/",
+        "/api/v1.0/file-stream/token3/",
+    ]
+
+    key1 = f"{conversation.pk}/image1.jpg"
+    key2 = f"{conversation.pk}/image2.png"
+    key3 = f"{conversation.pk}/document.pdf"
+
+    contents = [
+        ImageUrl(url=f"/media-key/{key1}"),
+        ImageUrl(url=f"/media-key/{key2}"),
+        DocumentUrl(url=f"/media-key/{key3}"),
+    ]
+
+    result = list(update_local_urls(conversation, contents))
+
+    assert len(result) == 3
+    assert result[0].url == "/api/v1.0/file-stream/token1/"
+    assert result[1].url == "/api/v1.0/file-stream/token2/"
+    assert result[2].url == "/api/v1.0/file-stream/token3/"
+    assert mock_temp_url.call_count == 3
+
+
+@patch("chat.agents.local_media_url_processors.generate_retrieve_policy")
+def test_update_local_urls_presigned_mode_preserves_mapping(mock_policy, settings):
+    """Test that PRESIGNED_URL mode correctly stores updated URLs mapping."""
+    settings.FILE_TO_LLM_MODE = FileToLLMMode.PRESIGNED_URL
+    conversation = ChatConversationFactory()
+    presigned_url = "https://s3.example.com/presigned-123"
+    mock_policy.return_value = presigned_url
+
+    key = f"{conversation.pk}/test.jpg"
+    original_url = f"/media-key/{key}"
+    contents = [ImageUrl(url=original_url)]
+    updated_urls = {}
+
+    list(update_local_urls(conversation, contents, updated_urls))
+
+    assert presigned_url in updated_urls
+    assert updated_urls[presigned_url] == original_url
+
+
+@patch("chat.agents.local_media_url_processors.generate_temporary_url")
+def test_update_local_urls_temporary_url_mode_preserves_mapping(mock_temp_url, settings):
+    """Test that BACKEND_TEMPORARY_URL mode correctly stores updated URLs mapping."""
+    settings.FILE_TO_LLM_MODE = FileToLLMMode.BACKEND_TEMPORARY_URL
+    conversation = ChatConversationFactory()
+    temp_url = "/api/v1.0/file-stream/temp-abc-def/"
+    mock_temp_url.return_value = temp_url
+
+    key = f"{conversation.pk}/test.pdf"
+    original_url = f"/media-key/{key}"
+    contents = [DocumentUrl(url=original_url)]
+    updated_urls = {}
+
+    list(update_local_urls(conversation, contents, updated_urls))
+
+    assert temp_url in updated_urls
+    assert updated_urls[temp_url] == original_url
+
+
+@patch("chat.agents.local_media_url_processors.default_storage.open")
+def test_update_local_urls_base64_mode_preserves_mapping(mock_storage, settings):
+    """Test that BACKEND_BASE64 mode correctly stores updated URLs mapping."""
+    settings.FILE_TO_LLM_MODE = FileToLLMMode.BACKEND_BASE64
+    conversation = ChatConversationFactory()
+
+    file_content = b"test image content"
+    mock_file = BytesIO(file_content)
+    mock_storage.return_value.__enter__.return_value = mock_file
+
+    key = f"{conversation.pk}/test.jpg"
+    original_url = f"/media-key/{key}"
+    contents = [ImageUrl(url=original_url)]
+    updated_urls = {}
+
+    result = list(update_local_urls(conversation, contents, updated_urls))
+
+    # Verify mapping was stored
+    assert len(updated_urls) == 1
+    # The data URL should be the key in the mapping
+    data_url = result[0].url
+    assert data_url in updated_urls
+    assert updated_urls[data_url] == original_url
+
+
+@patch("chat.agents.local_media_url_processors.generate_retrieve_policy")
+def test_update_local_urls_presigned_mode_security_check(mock_policy, settings):
+    """Test that PRESIGNED_URL mode respects security checks."""
+    settings.FILE_TO_LLM_MODE = FileToLLMMode.PRESIGNED_URL
+    conversation = ChatConversationFactory()
+    other_key = "other-conversation-id/test.jpg"
+    contents = [ImageUrl(url=f"/media-key/{other_key}")]
+
+    result = list(update_local_urls(conversation, contents))
+
+    # URL should remain unchanged
+    assert result[0].url == f"/media-key/{other_key}"
+    # generate_retrieve_policy should not be called
+    mock_policy.assert_not_called()
+
+
+@patch("chat.agents.local_media_url_processors.generate_temporary_url")
+def test_update_local_urls_temporary_mode_security_check(mock_temp_url, settings):
+    """Test that BACKEND_TEMPORARY_URL mode respects security checks."""
+    settings.FILE_TO_LLM_MODE = FileToLLMMode.BACKEND_TEMPORARY_URL
+    conversation = ChatConversationFactory()
+    other_key = "other-conversation-id/test.pdf"
+    contents = [DocumentUrl(url=f"/media-key/{other_key}")]
+
+    result = list(update_local_urls(conversation, contents))
+
+    # URL should remain unchanged
+    assert result[0].url == f"/media-key/{other_key}"
+    # generate_temporary_url should not be called
+    mock_temp_url.assert_not_called()
+
+
+@patch("chat.agents.local_media_url_processors.default_storage.open")
+def test_update_local_urls_base64_mode_security_check(mock_storage, settings):
+    """Test that BACKEND_BASE64 mode respects security checks."""
+    settings.FILE_TO_LLM_MODE = FileToLLMMode.BACKEND_BASE64
+    conversation = ChatConversationFactory()
+    other_key = "other-conversation-id/test.jpg"
+    contents = [ImageUrl(url=f"/media-key/{other_key}")]
+
+    result = list(update_local_urls(conversation, contents))
+
+    # URL should remain unchanged
+    assert result[0].url == f"/media-key/{other_key}"
+    # Storage should not be opened
+    mock_storage.assert_not_called()
+
+
+@pytest.mark.parametrize(
+    "file_to_llm_mode",
+    [
+        FileToLLMMode.PRESIGNED_URL,
+        FileToLLMMode.BACKEND_TEMPORARY_URL,
+        FileToLLMMode.BACKEND_BASE64,
+    ],
+)
+@patch("chat.agents.local_media_url_processors._get_file_url_for_llm")
+def test_update_local_urls_all_modes_with_external_urls(
+    mock_get_file_url, file_to_llm_mode, settings
+):
+    """Test that all modes preserve external URLs unchanged."""
+    settings.FILE_TO_LLM_MODE = file_to_llm_mode
+    conversation = ChatConversationFactory()
+    mock_get_file_url.return_value = "processed-url"
+
+    key = f"{conversation.pk}/test.jpg"
+    external_urls = [
+        "https://example.com/image.jpg",
+        "http://another.com/image.png",
+        "data:image/png;base64,iVBORw0KG...",
+    ]
+
+    contents = [ImageUrl(url=f"/media-key/{key}")] + [ImageUrl(url=url) for url in external_urls]
+
+    result = list(update_local_urls(conversation, contents))
+
+    assert len(result) == 4
+    assert result[0].url == "processed-url"
+    for i, external_url in enumerate(external_urls, start=1):
+        assert result[i].url == external_url
+
+
+@patch("chat.agents.local_media_url_processors.default_storage.open")
+def test_update_local_urls_base64_mode_with_different_file_types(mock_storage, settings):
+    """Test BACKEND_BASE64 mode with different file MIME types."""
+    settings.FILE_TO_LLM_MODE = FileToLLMMode.BACKEND_BASE64
+    conversation = ChatConversationFactory()
+
+    # Test with different file types
+    test_cases = [
+        ("test.jpg", b"JPEG binary"),
+        ("test.png", b"PNG binary"),
+        ("test.pdf", b"PDF binary"),
+        ("test.txt", b"Text content"),
+    ]
+
+    for filename, content in test_cases:
+        mock_file = BytesIO(content)
+        mock_storage.return_value.__enter__.return_value = mock_file
+
+        key = f"{conversation.pk}/{filename}"
+        contents = [ImageUrl(url=f"/media-key/{key}")]
+
+        result = list(update_local_urls(conversation, contents))
+
+        assert len(result) == 1
+        # Should be a data URL
+        assert result[0].url.startswith("data:")
+        assert "base64" in result[0].url
+
+
+@patch("chat.agents.local_media_url_processors.generate_retrieve_policy")
+def test_update_local_urls_presigned_mode_with_special_characters_in_key(mock_policy, settings):
+    """Test PRESIGNED_URL mode handles keys with special characters."""
+    settings.FILE_TO_LLM_MODE = FileToLLMMode.PRESIGNED_URL
+    conversation = ChatConversationFactory()
+    mock_policy.return_value = "https://s3.example.com/presigned"
+
+    # Key with special characters (should be handled properly by S3)
+    key = f"{conversation.pk}/attachments/file (1).pdf"
+    contents = [DocumentUrl(url=f"/media-key/{key}")]
+
+    result = list(update_local_urls(conversation, contents))
+
+    assert len(result) == 1
+    assert result[0].url == "https://s3.example.com/presigned"
+    mock_policy.assert_called_once_with(key)
@@ -1,14 +1,19 @@
 """Tests for the Brave web search tool."""

-# pylint: disable=too-many-lines
+from typing import Sequence

+# pylint: disable=too-many-lines
 from unittest.mock import AsyncMock, MagicMock, Mock, patch
 from urllib.parse import parse_qs

+from django.contrib.auth.base_user import AbstractBaseUser
+from django.contrib.sessions.backends.cache import SessionStore
+
 import httpx
 import pytest
 import respx
 from pydantic_ai import ModelRetry, RunContext, RunUsage
+from pydantic_ai._run_context import RunContextAgentDepsT

 from chat.tools.exceptions import ModelCannotRetry
 from chat.tools.web_search_brave import (
@@ -38,9 +43,6 @@ 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


@@ -48,6 +50,13 @@ def brave_settings(settings):
 def fixture_mocked_context():
    """Fixture for a mocked RunContext."""
    mock_ctx = Mock(spec=RunContext)
+    mock_ctx.deps = Mock(spec=RunContextAgentDepsT)
+    user = Mock(spec=AbstractBaseUser)
+    user.sub = Mock(spec=Sequence)
+    mock_ctx.deps.user = user
+    session = SessionStore()
+    session["oidc_access_token"] = "mocked-access-token"
+    mock_ctx.deps.session = session
    mock_ctx.usage = RunUsage(input_tokens=0, output_tokens=0)
    mock_ctx.max_retries = 2
    mock_ctx.retries = {}
@@ -1011,7 +1020,12 @@ async def test_web_search_brave_with_document_backend_rag_search_params(mocked_c
            await web_search_brave_with_document_backend(mocked_context, "test query")

    # Verify RAG search was called with correct parameters
-    mock_document_store.asearch.assert_called_once_with("test query", results_count=5)
+    mock_document_store.asearch.assert_called_once_with(
+        query="test query",
+        results_count=5,
+        session=mocked_context.deps.session,
+        user_sub=mocked_context.deps.user.sub,
+    )


@pytest.mark.asyncio
@@ -9,7 +9,7 @@ from django.test import override_settings

 import pytest

-from core.file_upload.enums import AttachmentStatus
+from core.file_upload.enums import AttachmentStatus, FileUploadMode

 from chat import factories, models
 from chat.tests.conftest import PIXEL_PNG
@@ -266,3 +266,40 @@ def test_upload_ended_fix_extension(api_client, name, content, _extension, conte
    assert attachment.content_type == content_type  # updated
    assert attachment.file_name == name  # updated
    assert attachment.size == len(content)  # updated
+
+
+def test_attachment_create_presigned_url_mode_returns_policy(api_client, settings):
+    """Test that presigned_url mode returns policy field."""
+    settings.FILE_UPLOAD_MODE = FileUploadMode.PRESIGNED_URL
+
+    conversation = factories.ChatConversationFactory()
+    api_client.force_login(conversation.owner)
+
+    url = f"/api/v1.0/chats/{conversation.pk!s}/attachments/"
+    response = api_client.post(
+        url,
+        {"file_name": "test.pdf", "size": 1000, "content_type": "application/pdf"},
+        format="json",
+    )
+
+    assert response.status_code == 201
+    data = response.json()
+    assert data["policy"] is not None
+    assert "s3" in data["policy"].lower() or "minio" in data["policy"].lower()
+
+
+def test_attachment_create_backend_to_s3_mode_no_policy(api_client, settings):
+    """Test that backend_to_s3 mode does not return policy."""
+    settings.FILE_UPLOAD_MODE = FileUploadMode.BACKEND_TO_S3
+
+    conversation = factories.ChatConversationFactory()
+    api_client.force_login(conversation.owner)
+
+    url = f"/api/v1.0/chats/{conversation.pk!s}/attachments/"
+    response = api_client.post(
+        url, {"file_name": "test.pdf", "content_type": "application/pdf"}, format="json"
+    )
+
+    assert response.status_code == 201
+    data = response.json()
+    assert data["policy"] is None
@@ -0,0 +1,112 @@
+"""Tests for file upload mode `backend_to_s3`."""
+
+from io import BytesIO
+from unittest import mock
+
+from django.core.files.storage import default_storage
+
+import pytest
+
+from chat import factories, models
+from chat.tests.conftest import PIXEL_PNG
+
+pytestmark = pytest.mark.django_db
+
+
+def test_backend_upload_anonymous_forbidden(api_client):
+    """Anonymous users should not be able to use backend upload."""
+    conversation = factories.ChatConversationFactory()
+    url = f"/api/v1.0/chats/{conversation.pk!s}/attachments/backend-upload/"
+
+    response = api_client.post(url, {}, format="multipart")
+    assert response.status_code == 401
+
+
+def test_backend_upload_not_owner_forbidden(api_client):
+    """Users who don't own the conversation cannot upload via backend."""
+    conversation = factories.ChatConversationFactory()
+    user = factories.UserFactory()
+    api_client.force_login(user)
+
+    url = f"/api/v1.0/chats/{conversation.pk!s}/attachments/backend-upload/"
+    file_obj = BytesIO(PIXEL_PNG)
+    file_obj.name = "test.png"
+
+    response = api_client.post(url, {"file": file_obj, "file_name": "test.png"}, format="multipart")
+    assert response.status_code == 404
+
+
+@mock.patch("chat.views.malware_detection.analyse_file")
+def test_backend_upload_success(mock_malware, api_client):
+    """Test successful backend file upload."""
+    conversation = factories.ChatConversationFactory()
+    api_client.force_login(conversation.owner)
+
+    url = f"/api/v1.0/chats/{conversation.pk!s}/attachments/backend-upload/"
+    file_obj = BytesIO(PIXEL_PNG)
+    file_obj.name = "test.png"
+
+    response = api_client.post(url, {"file": file_obj, "file_name": "test.png"}, format="multipart")
+
+    assert response.status_code == 201
+    data = response.json()
+
+    # Verify response structure
+    assert "id" in data
+    assert "key" in data
+    assert data["file_name"] == "test.png"
+    assert data["size"] == len(PIXEL_PNG)
+    assert data["content_type"] == "image/png"
+
+    # Verify attachment was created
+    attachment = models.ChatConversationAttachment.objects.get(pk=data["id"])
+    assert attachment.conversation == conversation
+    assert attachment.uploaded_by == conversation.owner
+    assert attachment.file_name == "test.png"
+    assert attachment.size == len(PIXEL_PNG)
+
+    # Verify malware detection was called
+    mock_malware.assert_called_once()
+
+
+def test_backend_upload_missing_file(api_client):
+    """Test that backend upload fails without file field."""
+    conversation = factories.ChatConversationFactory()
+    api_client.force_login(conversation.owner)
+
+    url = f"/api/v1.0/chats/{conversation.pk!s}/attachments/backend-upload/"
+
+    response = api_client.post(
+        url,
+        {"file_name": "test.png"},  # No file field
+        format="multipart",
+    )
+
+    assert response.status_code == 400
+    assert "file" in response.json()
+
+
+@mock.patch("chat.views.malware_detection.analyse_file")
+def test_backend_upload_creates_s3_file(_mock_malware, api_client):
+    """Test that backend upload creates file in S3."""
+
+    conversation = factories.ChatConversationFactory()
+    api_client.force_login(conversation.owner)
+
+    url = f"/api/v1.0/chats/{conversation.pk!s}/attachments/backend-upload/"
+    file_obj = BytesIO(PIXEL_PNG)
+    file_obj.name = "test.png"
+
+    response = api_client.post(url, {"file": file_obj, "file_name": "test.png"}, format="multipart")
+
+    assert response.status_code == 201
+    data = response.json()
+    key = data["key"]
+
+    # Verify file exists in S3
+    assert default_storage.exists(key)
+
+    # Verify file content
+    with default_storage.open(key, "rb") as f:
+        content = f.read()
+    assert content == PIXEL_PNG
@@ -1,5 +1,6 @@
 """Common test fixtures for chat conversation endpoint tests."""

+import asyncio
 import json

 from django.utils import timezone
@@ -10,15 +11,9 @@ import respx
 from freezegun import freeze_time


-@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.
-
-    See https://platform.openai.com/docs/api-reference/chat-streaming/streaming
-    """
-    openai_stream = (
+def _create_openai_stream_data():
+    """Helper to create OpenAI stream data."""
+    return (
        "data: "
        + json.dumps(
            {
@@ -59,12 +54,111 @@ def fixture_mock_openai_stream():
        "data: [DONE]\n\n"
    )

+
+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():
-        for line in openai_stream.splitlines(keepends=True):
+        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 (no delays).
+
+    See https://platform.openai.com/docs/api-reference/chat-streaming/streaming
+    """
+    return _create_mock_openai_route(with_delays=False)
+
+
+@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.
+
+    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():
+    """
+    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 a fresh streaming response for each call."""
+        openai_stream = _create_openai_stream_data()
+
+        async def mock_stream():
+            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 response for title generation."""
+        return httpx.Response(
+            200,
+            json={
+                "id": "chatcmpl-title",
+                "object": "chat.completion",
+                "created": int(timezone.make_naive(timezone.now()).timestamp()),
+                "model": "test-model",
+                "choices": [
+                    {
+                        "index": 0,
+                        "message": {
+                            "role": "assistant",
+                            "content": "GENERATED TITLE",
+                        },
+                        "finish_reason": "stop",
+                    }
+                ],
+                "usage": {"prompt_tokens": 50, "completion_tokens": 5, "total_tokens": 55},
+            },
+        )
+
+    def handle_request(request):
+        """Route to streaming or non-streaming response based on request."""
+        body = json.loads(request.content)
+        if body.get("stream", False):
+            return create_stream_response()
+        return create_non_stream_response()

    route = respx.post("https://www.external-ai-service.com/chat/completions").mock(
-        return_value=httpx.Response(200, stream=mock_stream())
+        side_effect=handle_request
    )

    return route
@@ -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():
@@ -216,11 +268,12 @@ 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,
+    today_prompt_date,
    mock_ai_agent_service,
 ):
    """
@@ -353,53 +406,26 @@ 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_prompt_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",
+        "metadata": None,
        "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",
@@ -407,10 +433,12 @@ def test_post_conversation_with_document_upload(  # pylint: disable=too-many-arg
            },
        ],
        "run_id": _run_id,
+        "timestamp": timezone_now,
    }
    assert chat_conversation.pydantic_messages[1] == {
        "finish_reason": None,
        "kind": "response",
+        "metadata": None,
        "model_name": "function::agent_model",
        "parts": [
            {
@@ -419,11 +447,14 @@ def test_post_conversation_with_document_upload(  # pylint: disable=too-many-arg
                "part_kind": "tool-call",
                "tool_call_id": chat_conversation.pydantic_messages[1]["parts"][0]["tool_call_id"],
                "tool_name": "document_search_rag",
+                "provider_details": None,
+                "provider_name": None,
            }
        ],
        "provider_details": None,
        "provider_name": None,
        "provider_response_id": None,
+        "provider_url": None,
        "timestamp": timezone_now,
        "usage": {
            "cache_audio_read_tokens": 0,
@@ -439,16 +470,24 @@ 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_prompt_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",
+        "metadata": None,
        "parts": [
            {
                "content": [
@@ -466,21 +505,26 @@ def test_post_conversation_with_document_upload(  # pylint: disable=too-many-arg
            }
        ],
        "run_id": _run_id,
+        "timestamp": timezone_now,
    }
    assert chat_conversation.pydantic_messages[3] == {
        "finish_reason": None,
        "kind": "response",
+        "metadata": None,
        "model_name": "function::agent_model",
        "parts": [
            {
                "content": "From the document, I can see that it says 'Hello PDF'.",
                "id": None,
                "part_kind": "text",
+                "provider_details": None,
+                "provider_name": None,
            }
        ],
        "provider_details": None,
        "provider_name": None,
        "provider_response_id": None,
+        "provider_url": None,
        "timestamp": timezone_now,
        "usage": {
            "cache_audio_read_tokens": 0,
@@ -499,7 +543,8 @@ 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 +597,12 @@ 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

@@ -569,9 +612,9 @@ 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,
+    today_prompt_date,
    mock_ai_agent_service,
    mock_summarization_agent,  # pylint: disable=unused-argument
 ):
@@ -582,6 +625,7 @@ 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 +687,7 @@ 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 +749,26 @@ 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_prompt_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",
+        "metadata": None,
        "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",
@@ -758,10 +776,12 @@ def test_post_conversation_with_document_upload_summarize(  # pylint: disable=to
            },
        ],
        "run_id": _run_id,
+        "timestamp": timezone_now,
    }
    assert chat_conversation.pydantic_messages[1] == {
        "finish_reason": None,
        "kind": "response",
+        "metadata": None,
        "model_name": "function::agent_model",
        "parts": [
            {
@@ -770,11 +790,14 @@ def test_post_conversation_with_document_upload_summarize(  # pylint: disable=to
                "part_kind": "tool-call",
                "tool_call_id": chat_conversation.pydantic_messages[1]["parts"][0]["tool_call_id"],
                "tool_name": "summarize",
+                "provider_details": None,
+                "provider_name": None,
            }
        ],
        "provider_details": None,
        "provider_name": None,
        "provider_response_id": None,
+        "provider_url": None,
        "timestamp": timezone_now,
        "usage": {
            "cache_audio_read_tokens": 0,
@@ -790,16 +813,24 @@ 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_prompt_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",
+        "metadata": None,
        "parts": [
            {
                "content": "The document discusses various topics.",
@@ -811,17 +842,26 @@ def test_post_conversation_with_document_upload_summarize(  # pylint: disable=to
            }
        ],
        "run_id": _run_id,
+        "timestamp": timezone_now,
    }
    assert chat_conversation.pydantic_messages[3] == {
        "finish_reason": None,
        "kind": "response",
+        "metadata": None,
        "model_name": "function::agent_model",
        "parts": [
-            {"content": "The document discusses various topics.", "id": None, "part_kind": "text"}
+            {
+                "content": "The document discusses various topics.",
+                "id": None,
+                "part_kind": "text",
+                "provider_details": None,
+                "provider_name": None,
+            }
        ],
        "provider_details": None,
        "provider_name": None,
        "provider_response_id": None,
+        "provider_url": None,
        "timestamp": timezone_now,
        "usage": {
            "cache_audio_read_tokens": 0,
@@ -17,7 +17,6 @@ from pydantic_ai.messages import (
    DocumentUrl,
    ModelMessage,
    ModelResponse,
-    SystemPromptPart,
    TextPart,
    UserPromptPart,
 )
@@ -38,11 +37,20 @@ 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_URL = "https://app-find"
+    settings.FIND_API_KEY = "find-api-key"
    settings.AI_MODEL = "test-model"
    settings.AI_AGENT_INSTRUCTIONS = "You are a helpful test assistant :)"
    return settings
@@ -61,15 +69,17 @@ 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,
+    today_prompt_date,
    mock_ai_agent_service,
 ):
    """
    Test POST to /api/v1/chats/{pk}/conversation/ with a document URL.
    """
+
    responses.post(
        "https://albert.api.etalab.gouv.fr/v1/collections",
        json={"id": 123, "object": "collection"},
@@ -85,6 +95,10 @@ 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)
@@ -120,33 +134,30 @@ 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_prompt_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,
+                timestamp=timezone.now(),
            )
        ]
        yield "This is a document about a single pixel."
@@ -189,9 +200,7 @@ 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,
@@ -221,59 +230,58 @@ 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_prompt_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",
+            "metadata": None,
            "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,
                },
            ],
            "run_id": _run_id,
+            "timestamp": timestamp,
        },
        {
            "finish_reason": None,
            "kind": "response",
+            "metadata": None,
            "model_name": "function::agent_model",
            "parts": [
                {
                    "content": "This is a document about a single pixel.",
                    "id": None,
                    "part_kind": "text",
+                    "provider_details": None,
+                    "provider_name": None,
                }
            ],
            "provider_details": None,
            "provider_name": None,
            "provider_response_id": None,
+            "provider_url": None,
            "timestamp": timestamp,
            "usage": {
                "cache_audio_read_tokens": 0,
@@ -429,7 +437,6 @@ 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 +444,8 @@ 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 +481,11 @@ 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?",
@@ -555,27 +548,16 @@ 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
        assert presigned_url.find("X-Amz-Expires=") != -1
+        timestamp_now = timezone.now()

        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?",
@@ -585,16 +567,19 @@ def test_post_conversation_with_local_document_url_in_history(  # pylint: disabl
                                identifier="sample.pdf",
                            ),
                        ],
-                        timestamp=timezone.now(),
+                        timestamp=timestamp_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(
                parts=[TextPart(content="This is a document about a single pixel.")],
                usage=RequestUsage(input_tokens=50, output_tokens=9),
                model_name="function::agent_model",
-                timestamp=timezone.now(),
+                timestamp=timestamp_now,
                run_id=messages[1].run_id,
            ),
            ModelRequest(
@@ -603,9 +588,13 @@ def test_post_conversation_with_local_document_url_in_history(  # pylint: disabl
                        content=[
                            "Give more details about this document.",
                        ],
-                        timestamp=timezone.now(),
+                        timestamp=timestamp_now,
                    )
                ],
+                timestamp=timestamp_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 +694,11 @@ 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 +745,10 @@ 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.",
+            "metadata": None,
            "kind": "request",
            "parts": [
                {
@@ -782,21 +758,26 @@ def test_post_conversation_with_local_document_url_in_history(  # pylint: disabl
                }
            ],
            "run_id": _run_id,
+            "timestamp": "2025-10-18T20:48:20.286204Z",
        },
        {
            "finish_reason": None,
            "kind": "response",
+            "metadata": None,
            "model_name": "function::agent_model",
            "parts": [
                {
                    "content": "This is a document of square, very small and nice.",
                    "id": None,
                    "part_kind": "text",
+                    "provider_details": None,
+                    "provider_name": None,
                }
            ],
            "provider_details": None,
            "provider_name": None,
            "provider_response_id": None,
+            "provider_url": None,
            "timestamp": "2025-10-18T20:48:20.286204Z",
            "usage": {
                "cache_audio_read_tokens": 0,
@@ -823,9 +804,10 @@ 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,
+    today_prompt_date,
    mock_ai_agent_service,
    file_name,
    content_type,
@@ -848,6 +830,10 @@ 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)
@@ -883,47 +869,37 @@ def test_post_conversation_with_local_not_pdf_document_url(  # pylint: disable=t
    )

    async def agent_model(messages: list[ModelMessage], _info: AgentInfo):
+        timestamp_now = timezone.now()
+
        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?",
                            # No presigned URL for non-PDF documents (not supporter by LLM)
                        ],
-                        timestamp=timezone.now(),
+                        timestamp=timestamp_now,
                    ),
                ],
+                timestamp=timestamp_now,
                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_prompt_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 +975,26 @@ 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_prompt_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",
+            "metadata": None,
            "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?",
@@ -1055,21 +1004,26 @@ def test_post_conversation_with_local_not_pdf_document_url(  # pylint: disable=t
                },
            ],
            "run_id": _run_id,
+            "timestamp": timestamp,
        },
        {
            "finish_reason": None,
            "kind": "response",
+            "metadata": None,
            "model_name": "function::agent_model",
            "parts": [
                {
                    "content": "This is a document about you.",
                    "id": None,
                    "part_kind": "text",
+                    "provider_details": None,
+                    "provider_name": None,
                }
            ],
            "provider_details": None,
            "provider_name": None,
            "provider_response_id": None,
+            "provider_url": None,
            "timestamp": timestamp,
            "usage": {
                "cache_audio_read_tokens": 0,
@@ -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,
@@ -27,6 +29,10 @@ from chat.tests.utils import replace_uuids_with_placeholder
 pytestmark = pytest.mark.django_db(transaction=True)


+PYAI_CURRENT = "current"
+PYAI_V1_17 = "v1.17"
+
+
@pytest.fixture(autouse=True)
 def ai_settings(settings):
    """Fixture to set AI service URLs for testing."""
@@ -35,20 +41,13 @@ def ai_settings(settings):
    settings.AI_MODEL = "test-model"
    settings.AI_AGENT_INSTRUCTIONS = "You are a helpful test assistant :)"

+    settings.AUTO_TITLE_AFTER_USER_MESSAGES = None  # disable auto title generation
    return settings


-@pytest.fixture(name="history_conversation")
-def history_conversation_fixture():
-    """Create a conversation with existing message history."""
-    # Create a timestamp for the first message
-    history_timestamp = timezone.now().replace(year=2025, month=6, day=15, hour=10, minute=30)
-
-    # Create a conversation with pre-existing messages
-    conversation = ChatConversationFactory()
-
-    # Add previous user and assistant messages
-    conversation.messages = [
+def build__history_conversation_ui_messages(history_timestamp):
+    """Build ui messages list for fixtures."""
+    return [
        UIMessage(
            id="prev-user-msg-1",
            createdAt=history_timestamp,
@@ -117,94 +116,205 @@ def history_conversation_fixture():
        ),
    ]

+
+@pytest.fixture(name="history_conversation")
+def history_conversation_fixture(request):
+    """Create a conversation with existing message history according to pydantic ai version."""
+
+    # Create a timestamp for the first message
+    history_timestamp = timezone.now().replace(year=2025, month=6, day=15, hour=10, minute=30)
+
+    # Create a conversation with pre-existing messages
+    conversation = ChatConversationFactory()
+    pyai_version = getattr(request, "param", PYAI_CURRENT)
+    # Add previous user and assistant messages
+    if pyai_version == PYAI_V1_17:
+        conversation.pydantic_messages = [
+            {
+                "instructions": None,
+                "kind": "request",
+                "parts": [
+                    {
+                        "content": "You are a helpful test assistant :)",
+                        "dynamic_ref": None,
+                        "part_kind": "system-prompt",
+                        "timestamp": "2025-06-15T10:30:00.000000Z",
+                    },
+                    {
+                        "content": ["How does machine learning work?"],
+                        "part_kind": "user-prompt",
+                        "timestamp": "2025-06-15T10:30:00.000000Z",
+                    },
+                ],
+            },
+            {
+                "kind": "response",
+                "model_name": "test-model",
+                "parts": [
+                    {
+                        "content": (
+                            "Machine learning is a branch of artificial intelligence that "
+                            "focuses on building systems that learn from data."
+                        ),
+                        "part_kind": "text",
+                    }
+                ],
+                "timestamp": "2025-06-15T10:31:00.000000Z",
+                "usage": {
+                    "details": None,
+                    "request_tokens": 10,
+                    "requests": 1,
+                    "response_tokens": 20,
+                    "total_tokens": 30,
+                },
+                "vendor_details": None,
+                "vendor_id": None,
+            },
+            {
+                "instructions": None,
+                "kind": "request",
+                "parts": [
+                    {
+                        "content": ["What are neural networks?"],
+                        "part_kind": "user-prompt",
+                        "timestamp": "2025-06-15T10:32:00.000000Z",
+                    },
+                ],
+            },
+            {
+                "kind": "response",
+                "model_name": "test-model",
+                "parts": [
+                    {
+                        "content": (
+                            "Neural networks are computing systems inspired by the "
+                            "biological neural networks in animal brains."
+                        ),
+                        "part_kind": "text",
+                    }
+                ],
+                "timestamp": "2025-06-15T10:33:00.000000Z",
+                "usage": {
+                    "details": None,
+                    "request_tokens": 5,
+                    "requests": 1,
+                    "response_tokens": 15,
+                    "total_tokens": 20,
+                },
+                "vendor_details": None,
+                "vendor_id": None,
+            },
+        ]
+    else:
+        conversation.pydantic_messages = [
+            {
+                "instructions": None,
+                "kind": "request",
+                "parts": [
+                    {
+                        "content": "You are a helpful test assistant :)",
+                        "dynamic_ref": None,
+                        "part_kind": "system-prompt",
+                        "timestamp": "2025-06-15T10:30:00.000000Z",
+                    },
+                    {
+                        "content": ["How does machine learning work?"],
+                        "part_kind": "user-prompt",
+                        "timestamp": "2025-06-15T10:30:00.000000Z",
+                    },
+                ],
+            },
+            {
+                "kind": "response",
+                "model_name": "test-model",
+                "parts": [
+                    {
+                        "content": (
+                            "Machine learning is a branch of artificial intelligence that "
+                            "focuses on building systems that learn from data."
+                        ),
+                        "part_kind": "text",
+                        "provider_details": {
+                            "finish_reason": "stop",
+                            "timestamp": "2025-07-25T10:36:35.297675Z",
+                        },
+                        "provider_name": "some model",
+                    }
+                ],
+                "timestamp": "2025-06-15T10:31:00.000000Z",
+                "usage": {
+                    "details": None,
+                    "request_tokens": 10,
+                    "requests": 1,
+                    "response_tokens": 20,
+                    "total_tokens": 30,
+                },
+                "provider_details": None,
+                "vendor_id": None,
+            },
+            {
+                "instructions": None,
+                "kind": "request",
+                "parts": [
+                    {
+                        "content": ["What are neural networks?"],
+                        "part_kind": "user-prompt",
+                        "timestamp": "2025-06-15T10:32:00.000000Z",
+                    },
+                ],
+            },
+            {
+                "kind": "response",
+                "metadata": None,
+                "model_name": "test-model",
+                "finish_reason": "stop",
+                "parts": [
+                    {
+                        "content": (
+                            "Neural networks are computing systems inspired by the "
+                            "biological neural networks in animal brains."
+                        ),
+                        "part_kind": "text",
+                        "provider_details": {
+                            "finish_reason": "stop",
+                            "timestamp": "2025-07-25T10:36:35.297675Z",
+                        },
+                        "provider_name": "test-model",
+                        "provider_url": "https://www.external-ai-service.com/",
+                    }
+                ],
+                "timestamp": "2025-06-15T10:33:00.000000Z",
+                "usage": {
+                    "details": None,
+                    "request_tokens": 5,
+                    "requests": 1,
+                    "response_tokens": 15,
+                    "total_tokens": 20,
+                },
+                "provider_details": {
+                    "timestamp": "2025-07-25T10:36:35.297675Z",
+                    "finish_reason": "stop",
+                },
+                "provider_name": "test-model",
+                "provider_response_id": "xyz",
+            },
+        ]
+
    # Set up the OpenAI message format as well
-    conversation.pydantic_messages = [
-        {
-            "instructions": None,
-            "kind": "request",
-            "parts": [
-                {
-                    "content": "You are a helpful test assistant :)",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-06-15T10:30:00.000000Z",
-                },
-                {
-                    "content": ["How does machine learning work?"],
-                    "part_kind": "user-prompt",
-                    "timestamp": "2025-06-15T10:30:00.000000Z",
-                },
-            ],
-        },
-        {
-            "kind": "response",
-            "model_name": "test-model",
-            "parts": [
-                {
-                    "content": (
-                        "Machine learning is a branch of artificial intelligence that "
-                        "focuses on building systems that learn from data."
-                    ),
-                    "part_kind": "text",
-                }
-            ],
-            "timestamp": "2025-06-15T10:31:00.000000Z",
-            "usage": {
-                "details": None,
-                "request_tokens": 10,
-                "requests": 1,
-                "response_tokens": 20,
-                "total_tokens": 30,
-            },
-            "vendor_details": None,
-            "vendor_id": None,
-        },
-        {
-            "instructions": None,
-            "kind": "request",
-            "parts": [
-                {
-                    "content": ["What are neural networks?"],
-                    "part_kind": "user-prompt",
-                    "timestamp": "2025-06-15T10:32:00.000000Z",
-                },
-            ],
-        },
-        {
-            "kind": "response",
-            "model_name": "test-model",
-            "parts": [
-                {
-                    "content": (
-                        "Neural networks are computing systems inspired by the "
-                        "biological neural networks in animal brains."
-                    ),
-                    "part_kind": "text",
-                }
-            ],
-            "timestamp": "2025-06-15T10:33:00.000000Z",
-            "usage": {
-                "details": None,
-                "request_tokens": 5,
-                "requests": 1,
-                "response_tokens": 15,
-                "total_tokens": 20,
-            },
-            "vendor_details": None,
-            "vendor_id": None,
-        },
-    ]
+    conversation.messages = build__history_conversation_ui_messages(history_timestamp)

    conversation.save()
    return conversation


+@pytest.mark.parametrize("history_conversation", [PYAI_CURRENT, PYAI_V1_17], indirect=True)
@freeze_time("2025-07-25T10:36:35.297675Z")
@respx.mock
 def test_post_conversation_data_protocol_with_history(
    api_client, mock_openai_stream, history_conversation
 ):
    """Test posting messages to a conversation with history using the 'data' protocol."""
+
    url = f"/api/v1.0/chats/{history_conversation.pk}/conversation/?protocol=data"
    data = {
        "messages": [
@@ -919,7 +1029,7 @@ 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 = [
@@ -1025,6 +1135,7 @@ def history_conversation_with_tool_fixture():
        },
        {
            "kind": "response",
+            "metadata": None,
            "model_name": "test-model",
            "parts": [
                {
@@ -1066,6 +1177,7 @@ def history_conversation_with_tool_fixture():
        },
        {
            "kind": "response",
+            "metadata": None,
            "model_name": "test-model",
            "parts": [
                {
@@ -1099,6 +1211,7 @@ def history_conversation_with_tool_fixture():
        },
        {
            "kind": "response",
+            "metadata": None,
            "model_name": "test-model",
            "parts": [
                {
@@ -1145,6 +1258,7 @@ def history_conversation_with_tool_fixture():
        },
        {
            "kind": "response",
+            "metadata": None,
            "model_name": "test-model",
            "parts": [
                {
@@ -1377,8 +1491,11 @@ 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",
+        "metadata": None,
        "parts": [
            {
                "content": ["How about Paris weather?"],
@@ -1387,24 +1504,32 @@ def test_post_conversation_with_existing_tool_history(
            }
        ],
        "run_id": _run_id,
+        "timestamp": "2025-07-25T10:36:35.297675Z",
    }

    assert history_conversation_with_tool.pydantic_messages[9] == {
        "finish_reason": "tool_call",
        "kind": "response",
+        "metadata": None,
        "model_name": "test-model",
        "parts": [
            {
                "args": '{"location":"Paris", "unit":"celsius"}',
                "id": None,
                "part_kind": "tool-call",
+                "provider_details": None,
+                "provider_name": None,
                "tool_call_id": "xLDcIljdsDrz0idal7tATWSMm2jhMj47",
                "tool_name": "get_current_weather",
            }
        ],
-        "provider_details": {"finish_reason": "tool_calls"},
+        "provider_details": {
+            "finish_reason": "tool_calls",
+            "timestamp": "2025-07-25T10:36:35.297675Z",
+        },
        "provider_name": "openai",
        "provider_response_id": "chatcmpl-tool-call",
+        "provider_url": "https://www.external-ai-service.com/",
        "timestamp": "2025-07-25T10:36:35.297675Z",
        "usage": {
            "cache_audio_read_tokens": 0,
@@ -1420,8 +1545,11 @@ 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",
+        "metadata": None,
        "parts": [
            {
                "content": {"location": "Paris", "temperature": 22, "unit": "celsius"},
@@ -1433,18 +1561,30 @@ def test_post_conversation_with_existing_tool_history(
            }
        ],
        "run_id": _run_id,
+        "timestamp": "2025-07-25T10:36:35.297675Z",
    }

    assert history_conversation_with_tool.pydantic_messages[11] == {
        "finish_reason": "stop",
        "kind": "response",
+        "metadata": None,
        "model_name": "test-model",
        "parts": [
-            {"content": "The current weather in Paris is nice", "id": None, "part_kind": "text"}
+            {
+                "content": "The current weather in Paris is nice",
+                "id": None,
+                "part_kind": "text",
+                "provider_details": None,
+                "provider_name": None,
+            }
        ],
-        "provider_details": {"finish_reason": "stop"},
+        "provider_details": {
+            "finish_reason": "stop",
+            "timestamp": "2025-07-25T10:36:35.297675Z",
+        },
        "provider_name": "openai",
        "provider_response_id": "chatcmpl-final",
+        "provider_url": "https://www.external-ai-service.com/",
        "timestamp": "2025-07-25T10:36:35.297675Z",
        "usage": {
            "cache_audio_read_tokens": 0,
@@ -1569,3 +1709,307 @@ def test_post_conversation_add_image_to_conversation_with_tool_history(
        toolInvocations=None,
        parts=[TextUIPart(type="text", text="I see a cat in the picture.")],
    )
+
+
+@freeze_time("2025-07-25T10:36:35.297675Z")
+@respx.mock
+@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 TitleGenerationAgent.
+    """
+    # Configure the title generation threshold
+    settings.AUTO_TITLE_AFTER_USER_MESSAGES = 3
+
+    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 in the stream
+
+    assert '"type": "conversation_metadata"' in response_content
+
+    # Refresh and verify title was updated
+    history_conversation.refresh_from_db()
+
+    assert history_conversation.title == "GENERATED 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.called
+    assert mock_openai_stream_with_title_generation.call_count == 2
+
+
+@freeze_time("2025-07-25T10:36:35.297675Z")
+@respx.mock
+def test_post_conversation_does_not_regenerate_title_when_user_set(
+    api_client, mock_openai_stream_with_title_generation, settings, history_conversation
+):
+    """
+    Test that title is NOT regenerated if the user has manually set a title.
+    """
+    settings.AUTO_TITLE_AFTER_USER_MESSAGES = 3
+
+    # Simulate user having set a custom title
+    history_conversation.title = "My Custom Title"
+    history_conversation.title_set_by_user_at = timezone.now()
+    history_conversation.save()
+
+    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)
+
+    response = api_client.post(url, data, format="json")
+
+    assert response.status_code == status.HTTP_200_OK
+
+    # Consume the stream
+    response_content = b"".join(response.streaming_content).decode("utf-8")
+
+    # conversation_metadata should NOT be in the stream since title wasn't generated
+    assert "conversation_metadata" not in response_content
+
+    # Refresh and verify title was NOT changed
+    history_conversation.refresh_from_db()
+
+    assert history_conversation.title == "My Custom Title"
+    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
+
+
+@freeze_time("2025-07-25T10:36:35.297675Z")
+@respx.mock
+def test_post_conversation_does_not_generate_title_before_threshold(
+    api_client, mock_openai_stream_with_title_generation, settings
+):
+    """
+    Test that title is NOT generated before reaching the message threshold.
+    """
+    settings.AUTO_TITLE_AFTER_USER_MESSAGES = 3
+
+    # Create a conversation with only 1 user message
+    history_timestamp = timezone.now().replace(year=2025, month=6, day=15, hour=10, minute=30)
+    conversation = ChatConversationFactory(title="initial title")
+
+    conversation.messages = [
+        UIMessage(
+            id="prev-user-msg-1",
+            createdAt=history_timestamp,
+            content="Hello!",
+            reasoning=None,
+            experimental_attachments=None,
+            role="user",
+            annotations=None,
+            toolInvocations=None,
+            parts=[TextUIPart(type="text", text="Hello!")],
+        ),
+        UIMessage(
+            id="prev-assistant-msg-1",
+            createdAt=history_timestamp.replace(minute=31),
+            content="Hi there! How can I help you?",
+            reasoning=None,
+            experimental_attachments=None,
+            role="assistant",
+            annotations=None,
+            toolInvocations=None,
+            parts=[TextUIPart(type="text", text="Hi there! How can I help you?")],
+        ),
+    ]
+    conversation.save()
+
+    url = f"/api/v1.0/chats/{conversation.pk}/conversation/?protocol=data"
+    data = {
+        "messages": [
+            {
+                "id": "second-user-msg",
+                "role": "user",
+                "parts": [{"text": "What's machine learning?", "type": "text"}],
+                "content": "What's machine learning?",
+                "createdAt": "2025-07-25T10:36:00.000Z",
+            }
+        ]
+    }
+    api_client.force_login(conversation.owner)
+
+    response = api_client.post(url, data, format="json")
+
+    assert response.status_code == status.HTTP_200_OK
+
+    # Consume the stream
+    response_content = b"".join(response.streaming_content).decode("utf-8")
+
+    # conversation_metadata should NOT be in the stream (only 2 user messages)
+    assert "conversation_metadata" not in response_content
+
+    # Refresh and verify title was not updated
+    conversation.refresh_from_db()
+
+    assert conversation.title == "initial title"
+    assert not conversation.title_set_by_user_at
+
+    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
@@ -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 +86,16 @@ 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?",
@@ -115,7 +108,10 @@ 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,
+                timestamp=timezone.now(),
            )
        ]
        yield "This is an image of a single pixel."
@@ -184,27 +180,11 @@ 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",
+            "metadata": None,
            "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?",
@@ -222,17 +202,26 @@ def test_post_conversation_with_local_image_url(
                },
            ],
            "run_id": _run_id,
+            "timestamp": "2025-10-18T20:48:20.286204Z",
        },
        {
            "finish_reason": None,
            "kind": "response",
+            "metadata": None,
            "model_name": "function::agent_model",
            "parts": [
-                {"content": "This is an image of a single pixel.", "id": None, "part_kind": "text"}
+                {
+                    "content": "This is an image of a single pixel.",
+                    "id": None,
+                    "part_kind": "text",
+                    "provider_details": None,
+                    "provider_name": None,
+                }
            ],
            "provider_details": None,
            "provider_name": None,
            "provider_response_id": None,
+            "provider_url": None,
            "timestamp": "2025-10-18T20:48:20.286204Z",
            "usage": {
                "cache_audio_read_tokens": 0,
@@ -252,7 +241,7 @@ def test_post_conversation_with_local_image_url(
@freeze_time()
 def test_post_conversation_with_local_image_wrong_url(
    api_client,
-    today_promt_date,
+    today_prompt_date,
    mock_ai_agent_service,
 ):
    """
@@ -286,11 +275,6 @@ 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 +287,9 @@ def test_post_conversation_with_local_image_wrong_url(
                        timestamp=timezone.now(),
                    ),
                ],
+                timestamp=timezone.now(),
+                instructions=f"You are a helpful test assistant :)\n\n{today_prompt_date}"
+                "\n\nAnswer in english.",
                run_id=messages[0].run_id,
            )
        ]
@@ -340,7 +327,7 @@ def test_post_conversation_with_local_image_wrong_url(
@freeze_time()
 def test_post_conversation_with_remote_image_url(
    api_client,
-    today_promt_date,
+    today_prompt_date,
    mock_ai_agent_service,
 ):
    """
@@ -374,11 +361,6 @@ 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?",
@@ -391,7 +373,10 @@ def test_post_conversation_with_remote_image_url(
                        timestamp=timezone.now(),
                    ),
                ],
+                instructions="You are a helpful test assistant :)\n\n"
+                f"{today_prompt_date}\n\nAnswer in english.",
                run_id=messages[0].run_id,
+                timestamp=timezone.now(),
            )
        ]
        yield "This is an image of a single pixel."
@@ -461,7 +446,7 @@ def test_post_conversation_with_remote_image_url(
@freeze_time("2025-10-18T20:48:20.286204Z")
 def test_post_conversation_with_local_image_url_in_history(
    api_client,
-    today_promt_date,
+    today_prompt_date,
    mock_ai_agent_service,
 ):
    """
@@ -504,27 +489,10 @@ 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_prompt_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?",
@@ -587,27 +555,17 @@ 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
        assert presigned_url.find("X-Amz-Expires=") != -1

+        timestamp_now = timezone.now()
+
        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?",
@@ -617,9 +575,11 @@ def test_post_conversation_with_local_image_url_in_history(
                                identifier="sample.png",
                            ),
                        ],
-                        timestamp=timezone.now(),
+                        timestamp=timestamp_now,
                    ),
-                ]
+                ],
+                instructions="You are a helpful test assistant :)\n\n"
+                f"{today_prompt_date}\n\nAnswer in english.",
            ),
            ModelResponse(
                parts=[TextPart(content="This is an image of a single pixel.")],
@@ -633,10 +593,13 @@ def test_post_conversation_with_local_image_url_in_history(
                        content=[
                            "Give more details about this image.",
                        ],
-                        timestamp=timezone.now(),
+                        timestamp=timestamp_now,
                    )
                ],
                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.",
+                timestamp=timestamp_now,
            ),
        ]
        yield "This is an image of square, very small and nice."
@@ -735,27 +698,10 @@ 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_prompt_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?",
@@ -796,8 +742,10 @@ 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",
+            "metadata": None,
            "parts": [
                {
                    "content": ["Give more details about this image."],
@@ -806,21 +754,26 @@ def test_post_conversation_with_local_image_url_in_history(
                }
            ],
            "run_id": _run_id,
+            "timestamp": "2025-10-18T20:48:20.286204Z",
        },
        {
            "finish_reason": None,
            "kind": "response",
+            "metadata": None,
            "model_name": "function::agent_model",
            "parts": [
                {
                    "content": "This is an image of square, very small and nice.",
                    "id": None,
                    "part_kind": "text",
+                    "provider_details": None,
+                    "provider_name": None,
                }
            ],
            "provider_details": None,
            "provider_name": None,
            "provider_response_id": None,
+            "provider_url": None,
            "timestamp": "2025-10-18T20:48:20.286204Z",
            "usage": {
                "cache_audio_read_tokens": 0,
@@ -0,0 +1,112 @@
+"""Unit tests for conversation with project LLM instructions."""
+
+import json
+
+import pytest
+import respx
+from freezegun import freeze_time
+from rest_framework import status
+
+from chat.factories import ChatConversationFactory, ChatProjectFactory
+from chat.tests.utils import replace_uuids_with_placeholder
+
+pytestmark = pytest.mark.django_db(transaction=True)
+
+
+@pytest.fixture(autouse=True)
+def ai_settings(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 :)"
+
+    return settings
+
+
+@freeze_time("2025-07-25T10:36:35.297675Z")
+@respx.mock
+def test_post_conversation_includes_project_llm_instructions(api_client, mock_openai_stream):
+    """Test that project LLM instructions are sent to the LLM as part of the system prompt."""
+    project = ChatProjectFactory(llm_instructions="Always reply in bullet points.")
+    conversation = ChatConversationFactory(
+        owner=project.owner, project=project, owner__language="en-us"
+    )
+
+    url = f"/api/v1.0/chats/{conversation.pk}/conversation/?protocol=data"
+    data = {
+        "messages": [
+            {
+                "id": "msg-1",
+                "role": "user",
+                "parts": [{"text": "Hello", "type": "text"}],
+                "content": "Hello",
+                "createdAt": "2025-07-03T15:22:17.105Z",
+            }
+        ]
+    }
+    api_client.force_login(conversation.owner)
+    response = api_client.post(url, data, format="json")
+
+    assert response.status_code == status.HTTP_200_OK
+
+    # Wait for the streaming content to be fully received
+    response_content = b"".join(response.streaming_content).decode("utf-8")
+    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'
+    )
+
+    last_request_payload = json.loads(respx.calls.last.request.content)
+    system_message = last_request_payload["messages"][0]
+    assert system_message["role"] == "system"
+    assert "Always reply in bullet points." in system_message["content"]
+    assert mock_openai_stream.called
+
+
+@freeze_time("2025-07-25T10:36:35.297675Z")
+@respx.mock
+def test_post_conversation_without_project_has_no_project_instructions(
+    api_client, mock_openai_stream
+):
+    """Test that conversations without a project do not include project instructions."""
+    conversation = ChatConversationFactory(owner__language="en-us")
+
+    url = f"/api/v1.0/chats/{conversation.pk}/conversation/?protocol=data"
+    data = {
+        "messages": [
+            {
+                "id": "msg-1",
+                "role": "user",
+                "parts": [{"text": "Hello", "type": "text"}],
+                "content": "Hello",
+                "createdAt": "2025-07-03T15:22:17.105Z",
+            }
+        ]
+    }
+    api_client.force_login(conversation.owner)
+    response = api_client.post(url, data, format="json")
+
+    assert response.status_code == status.HTTP_200_OK
+
+    # Wait for the streaming content to be fully received
+    response_content = b"".join(response.streaming_content).decode("utf-8")
+    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'
+    )
+
+    last_request_payload = json.loads(respx.calls.last.request.content)
+    system_message = last_request_payload["messages"][0]
+    assert system_message["role"] == "system"
+    assert system_message["content"] == (
+        "You are a helpful test assistant :)\n\nToday is Friday 25/07/2025.\n\nAnswer in english."
+    )
+    assert mock_openai_stream.called
@@ -1,4 +1,4 @@
-"""Test the post_stop_steaming view."""
+"""Test the post_stop_streaming view."""

 from unittest.mock import patch

@@ -2,9 +2,11 @@

 import pytest
 from rest_framework import status
+from rest_framework.exceptions import ErrorDetail

 from core.factories import UserFactory

+from chat.factories import ChatProjectFactory
 from chat.models import ChatConversation

 pytestmark = pytest.mark.django_db
@@ -28,6 +30,7 @@ def test_create_conversation(api_client):
    conversation = ChatConversation.objects.get(id=response.data["id"])
    assert conversation.owner == user
    assert conversation.title == "New Conversation"
+    assert not conversation.title_set_by_user_at


 def test_create_conversation_other_owner(api_client):
@@ -51,6 +54,60 @@ def test_create_conversation_other_owner(api_client):
    assert conversation.title == "New Conversation"


+def test_create_conversation_with_project(api_client):
+    """Test creating a conversation attached to a project."""
+    project = ChatProjectFactory()
+    url = "/api/v1.0/chats/"
+    data = {
+        "title": "New Conversation",
+        "project": str(project.pk),
+    }
+    api_client.force_login(project.owner)
+    response = api_client.post(url, data, format="json")
+
+    assert response.status_code == status.HTTP_201_CREATED
+    assert str(response.data["project"]) == str(project.pk)
+
+    conversation = ChatConversation.objects.get(id=response.data["id"])
+    assert conversation.project == project
+
+
+def test_create_conversation_with_other_user_project_fails(api_client):
+    """Test that creating a conversation with another user's project is rejected."""
+    user = UserFactory()
+    other_project = ChatProjectFactory()  # owned by another user
+    url = "/api/v1.0/chats/"
+    data = {
+        "title": "New Conversation",
+        "project": str(other_project.pk),
+    }
+    api_client.force_login(user)
+    response = api_client.post(url, data, format="json")
+
+    assert response.status_code == status.HTTP_400_BAD_REQUEST
+
+    assert response.data == {
+        "project": [
+            ErrorDetail(
+                string="The project must belong to the current user.",
+                code="invalid",
+            )
+        ]
+    }
+
+
+def test_create_conversation_without_project(api_client):
+    """Test creating a conversation without a project."""
+    user = UserFactory()
+    url = "/api/v1.0/chats/"
+    data = {"title": "New Conversation"}
+    api_client.force_login(user)
+    response = api_client.post(url, data, format="json")
+
+    assert response.status_code == status.HTTP_201_CREATED
+    assert response.data["project"] is None
+
+
 def test_create_conversation_anonymous(api_client):
    """Test creating a conversation as an anonymous user returns a 401 error."""
    url = "/api/v1.0/chats/"
@@ -5,7 +5,7 @@ from rest_framework import status

 from core.factories import UserFactory

-from chat.factories import ChatConversationFactory
+from chat.factories import ChatConversationFactory, ChatProjectFactory
 from chat.models import ChatConversation

 pytestmark = pytest.mark.django_db
@@ -79,3 +79,145 @@ def test_ordering_conversations(api_client):
    assert response.status_code == status.HTTP_200_OK
    assert response.data["results"][0]["id"] == str(conv1.id)
    assert response.data["results"][1]["id"] == str(conv2.id)
+
+
+def test_list_conversations_no_project_filter_returns_all(api_client):
+    """Test that without project filter, all conversations are returned."""
+    user = UserFactory()
+    project = ChatProjectFactory(owner=user)
+    conv_in_project = ChatConversationFactory(owner=user, project=project, title="In project")
+    conv_no_project = ChatConversationFactory(owner=user, title="No project")
+
+    api_client.force_login(user)
+    response = api_client.get("/api/v1.0/chats/")
+
+    assert response.status_code == status.HTTP_200_OK
+    assert len(response.data["results"]) == 2
+    result_ids = {r["id"] for r in response.data["results"]}
+    assert result_ids == {str(conv_in_project.pk), str(conv_no_project.pk)}
+
+
+def test_filter_conversations_by_project(api_client):
+    """Test filtering conversations by a specific project."""
+    user = UserFactory()
+    project = ChatProjectFactory(owner=user)
+    conv_in_project = ChatConversationFactory(owner=user, project=project, title="In project")
+    ChatConversationFactory(owner=user, title="No project")
+
+    api_client.force_login(user)
+    response = api_client.get(f"/api/v1.0/chats/?project={project.pk}")
+
+    assert response.status_code == status.HTTP_200_OK
+    assert len(response.data["results"]) == 1
+    assert response.data["results"][0]["id"] == str(conv_in_project.pk)
+
+
+def test_filter_conversations_by_project_invalid_uuid(api_client):
+    """Test that an invalid UUID for project filter returns empty results."""
+    user = UserFactory()
+    ChatConversationFactory(owner=user, title="Some chat")
+
+    api_client.force_login(user)
+    response = api_client.get("/api/v1.0/chats/?project=notauuid")
+
+    assert response.status_code == status.HTTP_200_OK
+    assert len(response.data["results"]) == 0
+
+
+def test_filter_conversations_by_project_none(api_client):
+    """Test filtering conversations not linked to any project."""
+    user = UserFactory()
+    project = ChatProjectFactory(owner=user)
+    ChatConversationFactory(owner=user, project=project, title="In project")
+    conv_no_project = ChatConversationFactory(owner=user, title="No project")
+
+    api_client.force_login(user)
+    response = api_client.get("/api/v1.0/chats/?project=none")
+
+    assert response.status_code == status.HTTP_200_OK
+    assert len(response.data["results"]) == 1
+    assert response.data["results"][0]["id"] == str(conv_no_project.pk)
+
+
+def test_filter_conversations_by_project_any(api_client):
+    """Test filtering conversations linked to any project."""
+    user = UserFactory()
+    project = ChatProjectFactory(owner=user)
+    conv_in_project = ChatConversationFactory(owner=user, project=project, title="In project")
+    ChatConversationFactory(owner=user, title="No project")
+
+    api_client.force_login(user)
+    response = api_client.get("/api/v1.0/chats/?project=any")
+
+    assert response.status_code == status.HTTP_200_OK
+    assert len(response.data["results"]) == 1
+    assert response.data["results"][0]["id"] == str(conv_in_project.pk)
+
+
+def test_filter_conversations_by_title_and_project(api_client):
+    """Test filtering conversations by both title and project."""
+    user = UserFactory()
+    project = ChatProjectFactory(owner=user)
+    conv_match = ChatConversationFactory(owner=user, project=project, title="Design review")
+    ChatConversationFactory(owner=user, project=project, title="Budget plan")
+    ChatConversationFactory(owner=user, title="Design ideas")
+
+    api_client.force_login(user)
+    response = api_client.get(f"/api/v1.0/chats/?title=Design&project={project.pk}")
+
+    assert response.status_code == status.HTTP_200_OK
+    assert len(response.data["results"]) == 1
+    assert response.data["results"][0]["id"] == str(conv_match.pk)
+
+
+def test_search_by_title_returns_nested_project_info(api_client):
+    """Test that searching by title returns nested project info (id, title, icon)."""
+    user = UserFactory()
+    project = ChatProjectFactory(owner=user, title="My Project", icon="folder")
+    conv = ChatConversationFactory(owner=user, project=project, title="Hello world")
+
+    api_client.force_login(user)
+    response = api_client.get("/api/v1.0/chats/?title=Hello")
+
+    assert response.status_code == status.HTTP_200_OK
+    assert len(response.data["results"]) == 1
+    result = response.data["results"][0]
+    assert result["id"] == str(conv.pk)
+    assert result["project"] == {
+        "id": str(project.pk),
+        "title": "My Project",
+        "icon": "folder",
+    }
+    assert "messages" not in result
+
+
+def test_search_by_title_returns_null_project_when_none(api_client):
+    """Test that searching by title for a conversation without a project returns null."""
+    user = UserFactory()
+    conv = ChatConversationFactory(owner=user, title="Standalone chat")
+
+    api_client.force_login(user)
+    response = api_client.get("/api/v1.0/chats/?title=Standalone")
+
+    assert response.status_code == status.HTTP_200_OK
+    assert len(response.data["results"]) == 1
+    result = response.data["results"][0]
+    assert result["id"] == str(conv.pk)
+    assert result["project"] is None
+
+
+def test_list_without_title_filter_does_not_nest_project(api_client):
+    """Test that listing without title filter returns project as a UUID, not nested."""
+    user = UserFactory()
+    project = ChatProjectFactory(owner=user)
+    ChatConversationFactory(owner=user, project=project, title="Some chat")
+
+    api_client.force_login(user)
+    response = api_client.get("/api/v1.0/chats/")
+
+    assert response.status_code == status.HTTP_200_OK
+    assert len(response.data["results"]) == 1
+    result = response.data["results"][0]
+    # project should be a flat UUID, not a nested dict
+    assert not isinstance(result["project"], dict)
+    assert str(result["project"]) == str(project.pk)
@@ -0,0 +1,87 @@
+"""Unit tests for partially updating chat conversations in the chat API view."""
+
+import pytest
+from rest_framework import status
+
+from core.factories import UserFactory
+
+from chat.factories import ChatConversationFactory, ChatProjectFactory
+from chat.models import ChatConversation
+
+pytestmark = pytest.mark.django_db
+
+
+def test_partial_update_conversation_title(api_client):
+    """Test partially updating a chat conversation title as the owner."""
+    chat_conversation = ChatConversationFactory(title="Original Title")
+
+    url = f"/api/v1.0/chats/{chat_conversation.pk}/"
+    data = {"title": "Updated Title"}
+    api_client.force_login(chat_conversation.owner)
+    response = api_client.patch(url, data, format="json")
+
+    assert response.status_code == status.HTTP_200_OK
+    assert response.data["title"] == "Updated Title"
+
+    conversation = ChatConversation.objects.get(id=chat_conversation.pk)
+    assert conversation.title == "Updated Title"
+    assert conversation.title_set_by_user_at
+
+
+def test_partial_update_conversation_anonymous(api_client):
+    """Test partially updating a conversation as an anonymous user returns a 401 error."""
+    chat_conversation = ChatConversationFactory()
+
+    url = f"/api/v1.0/chats/{chat_conversation.pk}/"
+    data = {"title": "Updated Title"}
+    response = api_client.patch(url, data, format="json")
+
+    assert response.status_code == status.HTTP_401_UNAUTHORIZED
+
+
+def test_partial_update_conversation_project_fails(api_client):
+    """Test that partially updating a conversation's project is rejected."""
+    conversation = ChatConversationFactory()
+    project = ChatProjectFactory(owner=conversation.owner)
+
+    url = f"/api/v1.0/chats/{conversation.pk}/"
+    data = {"project": str(project.pk)}
+    api_client.force_login(conversation.owner)
+    response = api_client.patch(url, data, format="json")
+
+    assert response.status_code == status.HTTP_400_BAD_REQUEST
+    assert "project" in response.data
+
+    conversation.refresh_from_db()
+    assert conversation.project is None
+
+
+def test_partial_update_conversation_remove_project_fails(api_client):
+    """Test that trying to remove a conversation from a project fails."""
+
+    project = ChatProjectFactory()
+    conversation = ChatConversationFactory(owner=project.owner, project=project)
+
+    url = f"/api/v1.0/chats/{conversation.pk}/"
+    data = {"project": None}
+    api_client.force_login(conversation.owner)
+    response = api_client.patch(url, data, format="json")
+
+    assert response.status_code == status.HTTP_400_BAD_REQUEST
+    assert "project" in response.data
+
+    conversation.refresh_from_db()
+    assert conversation.project == project
+
+
+def test_partial_update_other_user_conversation_fails(api_client):
+    """Test that partially updating another user's conversation returns a 404 error."""
+    chat_conversation = ChatConversationFactory()
+
+    other_user = UserFactory()
+    url = f"/api/v1.0/chats/{chat_conversation.pk}/"
+    data = {"title": "Updated By Other User"}
+    api_client.force_login(other_user)
+    response = api_client.patch(url, data, format="json")
+
+    assert response.status_code == status.HTTP_404_NOT_FOUND
@@ -2,10 +2,11 @@

 import pytest
 from rest_framework import status
+from rest_framework.exceptions import ErrorDetail

 from core.factories import UserFactory

-from chat.factories import ChatConversationFactory
+from chat.factories import ChatConversationFactory, ChatProjectFactory
 from chat.models import ChatConversation

 pytestmark = pytest.mark.django_db
@@ -26,6 +27,34 @@ 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
+
+
+def test_update_conversation_limit_title_length(api_client):
+    """Test that updating a conversation with a title exceeding 100 characters fails validation."""
+    chat_conversation = ChatConversationFactory(title="Initial title")
+
+    url = f"/api/v1.0/chats/{chat_conversation.pk}/"
+    # Create a 101-character title to exceed the 100-character maximum limit
+    new_title = "X" * 101
+    data = {"title": new_title}
+    api_client.force_login(chat_conversation.owner)
+    response = api_client.put(url, data, format="json")
+
+    assert response.status_code == status.HTTP_400_BAD_REQUEST
+
+    assert response.data == {
+        "title": [
+            ErrorDetail(
+                string="Ensure this field has no more than 100 characters.", code="max_length"
+            )
+        ]
+    }
+
+    # Verify in database (title should remain unchanged)
+    conversation = ChatConversation.objects.get(id=chat_conversation.pk)
+    assert conversation.title == "Initial title"
+    assert not conversation.title_set_by_user_at


 def test_update_conversation_anonymous(api_client):
@@ -39,6 +68,42 @@ def test_update_conversation_anonymous(api_client):
    assert response.status_code == status.HTTP_401_UNAUTHORIZED


+def test_update_conversation_project_fails(api_client):
+    """Test that updating a conversation's project is rejected."""
+    conversation = ChatConversationFactory()
+    project = ChatProjectFactory(owner=conversation.owner)
+
+    url = f"/api/v1.0/chats/{conversation.pk}/"
+    data = {"title": "Updated Title", "project": str(project.pk)}
+    api_client.force_login(conversation.owner)
+    response = api_client.put(url, data, format="json")
+
+    assert response.status_code == status.HTTP_400_BAD_REQUEST
+    assert "project" in response.data
+
+    conversation.refresh_from_db()
+    assert conversation.project is None
+
+
+def test_update_conversation_remove_project_fails(api_client):
+    """Test that trying to remove a conversation from a project fails."""
+
+    project = ChatProjectFactory()
+    conversation = ChatConversationFactory(owner=project.owner, project=project)
+
+    url = f"/api/v1.0/chats/{conversation.pk}/"
+
+    data = {"title": "Updated Title", "project": None}
+    api_client.force_login(conversation.owner)
+    response = api_client.put(url, data, format="json")
+
+    assert response.status_code == status.HTTP_400_BAD_REQUEST
+    assert "project" in response.data
+
+    conversation.refresh_from_db()
+    assert conversation.project == project
+
+
 def test_update_other_user_conversation_fails(api_client):
    """Test that updating another user's conversation returns a 404 error."""
    chat_conversation = ChatConversationFactory()
@@ -0,0 +1,109 @@
+"""Unit tests for creating projects."""
+
+import pytest
+from rest_framework import status
+
+from core.factories import UserFactory
+
+from chat.models import ChatProject, ChatProjectColor, ChatProjectIcon
+
+pytestmark = pytest.mark.django_db
+
+
+def test_create_project(api_client):
+    """Test creating a new project as an authenticated user."""
+    user = UserFactory(sub="testuser", email="test@example.com")
+    url = "/api/v1.0/projects/"
+    data = {
+        "title": "New Project",
+        "icon": ChatProjectIcon.FOLDER,
+        "color": ChatProjectColor.COLOR_1,
+    }
+    api_client.force_login(user)
+    response = api_client.post(url, data, format="json")
+
+    assert response.status_code == status.HTTP_201_CREATED
+    assert response.data["title"] == "New Project"
+
+    # Verify in database
+    project = ChatProject.objects.get(id=response.data["id"])
+    assert project.owner == user
+    assert project.title == "New Project"
+    assert project.icon == ChatProjectIcon.FOLDER
+    assert project.color == ChatProjectColor.COLOR_1
+
+
+def test_create_project_other_owner(api_client):
+    """Test that a user cannot assign another user as the owner of a project."""
+    other_user = UserFactory()
+
+    user = UserFactory()
+    url = "/api/v1.0/projects/"
+
+    data = {
+        "title": "New Project",
+        "icon": ChatProjectIcon.FOLDER,
+        "color": ChatProjectColor.COLOR_1,
+        "owner": str(other_user.pk),  # Attempt to set another user as owner
+    }
+
+    api_client.force_login(user)
+    response = api_client.post(url, data, format="json")
+
+    assert response.status_code == status.HTTP_201_CREATED
+
+    # Verify in database
+    project = ChatProject.objects.get(id=response.data["id"])
+    assert project.owner == user
+    assert project.title == "New Project"
+
+
+def test_create_project_with_llm_instructions(api_client):
+    """Test creating a project with custom llm instructions."""
+    user = UserFactory()
+    url = "/api/v1.0/projects/"
+    data = {
+        "title": "New Project",
+        "icon": ChatProjectIcon.FOLDER,
+        "color": ChatProjectColor.COLOR_1,
+        "llm_instructions": "Always answer in French.",
+    }
+    api_client.force_login(user)
+    response = api_client.post(url, data, format="json")
+
+    assert response.status_code == status.HTTP_201_CREATED
+    assert response.data["llm_instructions"] == "Always answer in French."
+
+    project = ChatProject.objects.get(id=response.data["id"])
+    assert project.llm_instructions == "Always answer in French."
+
+
+@pytest.mark.parametrize("color", ChatProjectColor)
+def test_create_project_with_each_color(api_client, color):
+    """Test creating a project with each available color."""
+    user = UserFactory()
+    url = "/api/v1.0/projects/"
+    data = {
+        "title": "Color Project",
+        "icon": ChatProjectIcon.FOLDER,
+        "color": color,
+    }
+    api_client.force_login(user)
+    response = api_client.post(url, data, format="json")
+
+    assert response.status_code == status.HTTP_201_CREATED
+    project = ChatProject.objects.get(id=response.data["id"])
+    assert project.color == color
+
+
+def test_create_project_anonymous(api_client):
+    """Test creating a project as an anonymous user returns a 401 error."""
+    url = "/api/v1.0/projects/"
+    data = {
+        "title": "New Project",
+        "icon": ChatProjectIcon.FOLDER,
+        "color": ChatProjectColor.COLOR_1,
+    }
+    response = api_client.post(url, data, format="json")
+
+    assert response.status_code == status.HTTP_401_UNAUTHORIZED
@@ -0,0 +1,72 @@
+"""Unit tests for project deletion in the chat API view."""
+
+import pytest
+from rest_framework import status
+
+from core.factories import UserFactory
+
+from chat.factories import ChatProjectFactory
+from chat.models import ChatConversation, ChatProject
+
+pytestmark = pytest.mark.django_db
+
+
+def test_delete_project(api_client):
+    """Test deleting a project as the owner."""
+    project = ChatProjectFactory()
+    api_client.force_login(project.owner)
+    response = api_client.delete(f"/api/v1.0/projects/{project.pk}/")
+
+    assert response.status_code == status.HTTP_204_NO_CONTENT
+
+    # Verify deletion in database
+    assert not ChatProject.objects.filter(id=project.pk).exists()
+
+
+def test_delete_project_deletes_related_conversations(api_client):
+    """Test that deleting a project also deletes its conversations."""
+    project = ChatProjectFactory(number_of_conversations=2)
+    conversation_pks = list(project.conversations.values_list("pk", flat=True))
+    api_client.force_login(project.owner)
+    response = api_client.delete(f"/api/v1.0/projects/{project.pk}/")
+
+    assert response.status_code == status.HTTP_204_NO_CONTENT
+    assert not ChatProject.objects.filter(id=project.pk).exists()
+    assert not ChatConversation.objects.filter(pk__in=conversation_pks).exists()
+
+
+def test_delete_project_does_not_affect_other_conversations(api_client):
+    """Test that deleting a project does not delete conversations from other projects."""
+    project = ChatProjectFactory(number_of_conversations=1)
+    other_project = ChatProjectFactory(owner=project.owner, number_of_conversations=1)
+    other_conversation = other_project.conversations.get()
+
+    api_client.force_login(project.owner)
+    response = api_client.delete(f"/api/v1.0/projects/{project.pk}/")
+
+    assert response.status_code == status.HTTP_204_NO_CONTENT
+    assert ChatConversation.objects.filter(pk=other_conversation.pk).exists()
+
+
+def test_delete_other_user_project_fails(api_client):
+    """Test that deleting another user's project returns a 404 error."""
+    project = ChatProjectFactory()
+    other_user = UserFactory()
+    api_client.force_login(other_user)
+    response = api_client.delete(f"/api/v1.0/projects/{project.pk}/")
+
+    assert response.status_code == status.HTTP_404_NOT_FOUND
+
+    # Verify project still exists
+    assert ChatProject.objects.filter(id=project.pk).exists()
+
+
+def test_delete_project_user_anonymous(api_client):
+    """Test deleting a project as an anonymous user returns a 401 error."""
+    project = ChatProjectFactory()
+    response = api_client.delete(f"/api/v1.0/projects/{project.pk}/")
+
+    assert response.status_code == status.HTTP_401_UNAUTHORIZED
+
+    # Verify project still exists
+    assert ChatProject.objects.filter(id=project.pk).exists()
@@ -0,0 +1,177 @@
+"""Unit tests for listing projects in the chat API view."""
+
+import pytest
+from freezegun import freeze_time
+from rest_framework import status
+
+from core.factories import UserFactory
+
+from chat.factories import ChatConversationFactory, ChatProjectFactory
+
+pytestmark = pytest.mark.django_db
+
+
+def test_list_projects(api_client, django_assert_num_queries):
+    """Test retrieving the list of projects for an authenticated user."""
+    project = ChatProjectFactory()
+    url = "/api/v1.0/projects/"
+    api_client.force_login(project.owner)
+
+    with django_assert_num_queries(4):  # user, project count, project list, conversations
+        response = api_client.get(url)
+
+    assert response.status_code == status.HTTP_200_OK
+    results = response.data["results"]
+    assert len(results) == 1
+    assert results[0]["id"] == str(project.pk)
+    assert results[0]["title"] == project.title
+    assert results[0]["conversations"] == []
+
+
+def test_filter_projects_by_title(api_client):
+    """Test filtering projects by title substring."""
+    user = UserFactory(sub="testuser", email="test@example.com")
+
+    ChatProjectFactory(owner=user, title="Test Project")
+
+    ChatProjectFactory(owner=user, title="Other Project")
+
+    url = "/api/v1.0/projects/?title=Test"
+    api_client.force_login(user)
+    response = api_client.get(url)
+
+    assert response.status_code == status.HTTP_200_OK
+    assert len(response.data["results"]) == 1
+    assert response.data["results"][0]["title"] == "Test Project"
+
+
+def test_list_projects_with_conversations(api_client, django_assert_num_queries):
+    """Test retrieving projects with associated conversations ordered by -created_at."""
+    project = ChatProjectFactory()
+
+    with freeze_time("2026-01-01"):
+        conversation_1 = ChatConversationFactory(
+            project=project, owner=project.owner, title="My conversation 1"
+        )
+    with freeze_time("2026-01-02"):
+        conversation_2 = ChatConversationFactory(
+            project=project, owner=project.owner, title="My conversation 2"
+        )
+
+    url = "/api/v1.0/projects/"
+    api_client.force_login(project.owner)
+
+    with django_assert_num_queries(4):  # user, project count, project list, conversations
+        response = api_client.get(url)
+
+    assert response.status_code == status.HTTP_200_OK
+    results = response.data["results"]
+    assert len(results) == 1
+    assert results[0]["id"] == str(project.pk)
+    assert results[0]["title"] == project.title
+    assert results[0]["conversations"] == [
+        {
+            "id": str(conversation_2.id),
+            "title": conversation_2.title,
+        },
+        {
+            "id": str(conversation_1.id),
+            "title": conversation_1.title,
+        },
+    ]
+
+
+def test_list_projects_no_n_plus_one(api_client, django_assert_num_queries):
+    """Test that query count stays constant regardless of project/conversation count."""
+    user = UserFactory()
+    for _ in range(3):
+        ChatProjectFactory(owner=user, number_of_conversations=2)
+
+    url = "/api/v1.0/projects/"
+    api_client.force_login(user)
+
+    with django_assert_num_queries(4):  # user, project count, project list, conversations
+        response = api_client.get(url)
+
+    assert response.status_code == status.HTTP_200_OK
+    assert len(response.data["results"]) == 3
+
+
+def test_list_projects_ordered_by_title(api_client):
+    """Test that projects are returned in alphabetical order by title."""
+    user = UserFactory()
+    ChatProjectFactory(owner=user, title="Zeta")
+    ChatProjectFactory(owner=user, title="Alpha")
+    ChatProjectFactory(owner=user, title="Mu")
+
+    api_client.force_login(user)
+    response = api_client.get("/api/v1.0/projects/")
+
+    assert response.status_code == status.HTTP_200_OK
+    titles = [r["title"] for r in response.data["results"]]
+    assert titles == ["Alpha", "Mu", "Zeta"]
+
+
+@pytest.mark.parametrize(
+    "ordering,expected_titles",
+    [
+        ("created_at", ["First", "Second", "Third"]),
+        ("-created_at", ["Third", "Second", "First"]),
+        ("title", ["First", "Second", "Third"]),
+        ("-title", ["Third", "Second", "First"]),
+    ],
+)
+def test_list_projects_ordering(api_client, ordering, expected_titles):
+    """Test ordering projects by the allowed ordering fields."""
+    user = UserFactory()
+    with freeze_time("2026-01-01"):
+        ChatProjectFactory(owner=user, title="First")
+    with freeze_time("2026-01-02"):
+        ChatProjectFactory(owner=user, title="Second")
+    with freeze_time("2026-01-03"):
+        ChatProjectFactory(owner=user, title="Third")
+
+    api_client.force_login(user)
+    response = api_client.get(f"/api/v1.0/projects/?ordering={ordering}")
+
+    assert response.status_code == status.HTTP_200_OK
+    titles = [r["title"] for r in response.data["results"]]
+    assert titles == expected_titles
+
+
+def test_list_projects_ordering_by_updated_at(api_client):
+    """Test ordering projects by updated_at."""
+    user = UserFactory()
+    with freeze_time("2026-01-01"):
+        project_a = ChatProjectFactory(owner=user, title="A")
+        ChatProjectFactory(owner=user, title="B")
+    with freeze_time("2026-01-02"):
+        project_a.title = "A updated"
+        project_a.save()
+
+    api_client.force_login(user)
+    response = api_client.get("/api/v1.0/projects/?ordering=updated_at")
+
+    assert response.status_code == status.HTTP_200_OK
+    titles = [r["title"] for r in response.data["results"]]
+    assert titles == ["B", "A updated"]
+
+
+def test_list_projects_empty(api_client):
+    """Test retrieving the list of projects for an authenticated user."""
+    user = UserFactory()
+    url = "/api/v1.0/projects/"
+    api_client.force_login(user)
+    response = api_client.get(url)
+
+    assert response.status_code == status.HTTP_200_OK
+    assert len(response.data["results"]) == 0
+
+
+def test_list_projects_anonymous(api_client):
+    """Test listing projects as an anonymous user returns a 401 error."""
+
+    url = "/api/v1.0/projects/"
+    response = api_client.get(url)
+
+    assert response.status_code == status.HTTP_401_UNAUTHORIZED
@@ -0,0 +1,66 @@
+"""Unit tests for partial update of projects in the chat API view."""
+
+import pytest
+from rest_framework import status
+
+from core.factories import UserFactory
+
+from chat.factories import ChatProjectFactory
+from chat.models import ChatProjectColor, ChatProjectIcon
+
+pytestmark = pytest.mark.django_db
+
+
+@pytest.mark.parametrize(
+    "field,value",
+    [
+        ("title", "Updated Title"),
+        ("icon", ChatProjectIcon.STAR),
+        ("color", ChatProjectColor.COLOR_3),
+        ("llm_instructions", "Always answer in French."),
+    ],
+)
+def test_partial_update_project(api_client, field, value):
+    """Test updating a project field as the owner."""
+    project = ChatProjectFactory()
+
+    url = f"/api/v1.0/projects/{project.pk}/"
+    data = {field: value}
+    api_client.force_login(project.owner)
+    response = api_client.patch(url, data, format="json")
+
+    assert response.status_code == status.HTTP_200_OK
+    assert response.data[field] == value
+
+    # Verify in database
+    project.refresh_from_db()
+    assert getattr(project, field) == value
+
+
+def test_partial_update_other_user_project_fails(api_client):
+    """Test that updating another user's project returns a 404 error."""
+    project = ChatProjectFactory()
+
+    other_user = UserFactory()
+    url = f"/api/v1.0/projects/{project.pk}/"
+
+    data = {
+        "title": "Updated By Other User",
+    }
+    api_client.force_login(other_user)
+    response = api_client.patch(url, data, format="json")
+
+    assert response.status_code == status.HTTP_404_NOT_FOUND
+
+
+def test_partial_update_project_anonymous(api_client):
+    """Test updating a project as an anonymous user returns a 401 error."""
+    project = ChatProjectFactory()
+
+    url = f"/api/v1.0/projects/{project.pk}/"
+    data = {
+        "title": "Updated Title",
+    }
+    response = api_client.patch(url, data, format="json")
+
+    assert response.status_code == status.HTTP_401_UNAUTHORIZED
@@ -0,0 +1,45 @@
+"""Unit tests for retrieving projects."""
+
+import pytest
+from rest_framework import status
+
+from core.factories import UserFactory
+
+from chat.factories import ChatProjectFactory
+
+pytestmark = pytest.mark.django_db
+
+
+def test_retrieve_project(api_client):
+    """Test retrieving a project as the owner."""
+    project = ChatProjectFactory()
+
+    url = f"/api/v1.0/projects/{project.pk}/"
+    api_client.force_login(project.owner)
+    response = api_client.get(url)
+
+    assert response.status_code == status.HTTP_200_OK
+    assert response.data["id"] == str(project.pk)
+    assert response.data["title"] == project.title
+
+
+def test_retrieve_other_user_project_fails(api_client):
+    """Test that retrieving another user's project returns a 404 error."""
+    project = ChatProjectFactory()
+
+    other_user = UserFactory()
+    url = f"/api/v1.0/projects/{project.pk}/"
+    api_client.force_login(other_user)
+    response = api_client.get(url)
+
+    assert response.status_code == status.HTTP_404_NOT_FOUND
+
+
+def test_retrieve_project_anonymous(api_client):
+    """Test retrieving a project as an anonymous user returns a 401 error."""
+    project = ChatProjectFactory()
+
+    url = f"/api/v1.0/projects/{project.pk}/"
+    response = api_client.get(url)
+
+    assert response.status_code == status.HTTP_401_UNAUTHORIZED
@@ -0,0 +1,86 @@
+"""Unit tests for updating projects in the chat API view."""
+
+import pytest
+from rest_framework import status
+
+from core.factories import UserFactory
+
+from chat.factories import ChatProjectFactory
+from chat.models import ChatProjectColor, ChatProjectIcon
+
+pytestmark = pytest.mark.django_db
+
+
+def test_update_project(api_client):
+    """Test updating a project as the owner."""
+    project = ChatProjectFactory()
+
+    url = f"/api/v1.0/projects/{project.pk}/"
+    data = {
+        "title": "Updated Title",
+        "icon": ChatProjectIcon.FOLDER,
+        "color": ChatProjectColor.COLOR_1,
+    }
+    api_client.force_login(project.owner)
+    response = api_client.put(url, data, format="json")
+
+    assert response.status_code == status.HTTP_200_OK
+    assert response.data["title"] == "Updated Title"
+
+    # Verify in database
+    project.refresh_from_db()
+    assert project.title == "Updated Title"
+
+
+def test_update_project_llm_instructions(api_client):
+    """Test updating a project's LLM instructions via PUT."""
+    project = ChatProjectFactory(llm_instructions="Old instructions")
+
+    url = f"/api/v1.0/projects/{project.pk}/"
+    data = {
+        "title": project.title,
+        "icon": project.icon,
+        "color": project.color,
+        "llm_instructions": "New instructions",
+    }
+    api_client.force_login(project.owner)
+    response = api_client.put(url, data, format="json")
+
+    assert response.status_code == status.HTTP_200_OK
+    assert response.data["llm_instructions"] == "New instructions"
+
+    project.refresh_from_db()
+    assert project.llm_instructions == "New instructions"
+
+
+def test_update_other_user_project_fails(api_client):
+    """Test that updating another user's project returns a 404 error."""
+    project = ChatProjectFactory()
+
+    other_user = UserFactory()
+    url = f"/api/v1.0/projects/{project.pk}/"
+
+    data = {
+        "title": "Updated By Other User",
+        "icon": ChatProjectIcon.FOLDER,
+        "color": ChatProjectColor.COLOR_1,
+    }
+    api_client.force_login(other_user)
+    response = api_client.put(url, data, format="json")
+
+    assert response.status_code == status.HTTP_404_NOT_FOUND
+
+
+def test_update_project_anonymous(api_client):
+    """Test updating a project as an anonymous user returns a 401 error."""
+    project = ChatProjectFactory()
+
+    url = f"/api/v1.0/projects/{project.pk}/"
+    data = {
+        "title": "Updated Title",
+        "icon": ChatProjectIcon.FOLDER,
+        "color": ChatProjectColor.COLOR_1,
+    }
+    response = api_client.put(url, data, format="json")
+
+    assert response.status_code == status.HTTP_401_UNAUTHORIZED
@@ -0,0 +1,55 @@
+"""Tests for the file stream endpoint."""
+
+from io import BytesIO
+from unittest import mock
+
+from django.core.cache import cache
+
+
+def test_file_stream_invalid_key(api_client):
+    """Test that invalid temporary keys return 404."""
+    cache.clear()
+    url = "/api/v1.0/file-stream/invalid-key/"
+    response = api_client.get(url)
+
+    assert response.status_code == 404
+    error = response.json()["detail"].lower()
+    assert "expired" in error or "invalid" in error
+
+
+def test_file_stream_expired_key(api_client):
+    """Test that expired keys return 404."""
+    cache.clear()
+    # Create a key that's already expired
+    cache.set("file_access:expired-key", "path/to/file.pdf", timeout=0)
+
+    url = "/api/v1.0/file-stream/expired-key/"
+    response = api_client.get(url)
+
+    assert response.status_code == 404
+
+
+@mock.patch("chat.views.magic.Magic")
+@mock.patch("chat.views.default_storage.open")
+def test_file_stream_valid_key_streams_file(mock_storage_open, mock_magic, api_client):
+    """Test that valid temporary keys stream file content."""
+    cache.clear()
+
+    # Create a valid temporary key
+    temporary_key = "test-valid-key"
+    s3_key = "test/path/file.pdf"
+    cache.set(f"file_access:{temporary_key}", s3_key, timeout=300)
+
+    # Mock storage.open to return file content
+    file_mock = BytesIO(b"PDF content here")
+    mock_storage_open.return_value = file_mock
+
+    # Mock magic detector
+    mock_magic_instance = mock.MagicMock()
+    mock_magic_instance.from_buffer.return_value = "application/pdf"
+    mock_magic.return_value = mock_magic_instance
+
+    url = f"/api/v1.0/file-stream/{temporary_key}/"
+    response = api_client.get(url)
+
+    assert response.status_code == 200
@@ -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 (
@@ -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.
@@ -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)

@@ -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"]
@@ -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.
        """
@@ -2,37 +2,58 @@

 import logging
 import os
-from uuid import uuid4
+from uuid import UUID, uuid4

 from django.conf import settings
+from django.core.cache import cache
 from django.core.files.storage import default_storage
+from django.db.models import Prefetch
 from django.http import Http404, StreamingHttpResponse
+from django.utils.decorators import method_decorator

 import langfuse
 import magic
 import posthog
+from drf_spectacular.utils import extend_schema
 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
+from rest_framework.throttling import ScopedRateThrottle
 from rest_framework.views import APIView

 from core.api.viewsets import Pagination, SerializerPerActionMixin
 from core.file_upload import enums
 from core.file_upload.enums import AttachmentStatus
 from core.file_upload.mixins import AttachmentMixin
+from core.file_upload.serializers import FileUploadSerializer
 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__)


-class ChatConversationFilter(filters.BaseFilterBackend):
-    """Filter conversation."""
+def conditional_refresh_oidc_token(func):
+    """
+    Conditionally apply refresh_oidc_access_token decorator.
+
+    The decorator is only applied if OIDC_STORE_REFRESH_TOKEN is True, meaning
+    we can actually refresh something. Broader settings checks are done in settings.py.
+    """
+    if settings.OIDC_STORE_REFRESH_TOKEN:
+        return method_decorator(refresh_oidc_access_token)(func)
+
+    return func
+
+
+class TitleSearchFilter(filters.BaseFilterBackend):
+    """Filter conversation by title (accent-insensitive)."""

    def filter_queryset(self, request, queryset, view):
        """Filter conversation by title."""
@@ -40,6 +61,58 @@ class ChatConversationFilter(filters.BaseFilterBackend):
            queryset = queryset.filter(title__unaccent__icontains=remove_accents(title))
        return queryset

+    def get_schema_operation_parameters(self, view):
+        """Return the schema for the ``title`` query parameter (drf-spectacular)."""
+        return [
+            {
+                "name": "title",
+                "required": False,
+                "in": "query",
+                "description": "Search conversations by title (accent-insensitive). "
+                "When provided, the response uses a search-specific serializer "
+                "with nested project info.",
+                "schema": {"type": "string"},
+            },
+        ]
+
+
+class ProjectFilter(filters.BaseFilterBackend):
+    """Filter conversations by project.
+
+    Accepts a `project` query parameter:
+    - a UUID: conversations belonging to that specific project
+    - "none": conversations not linked to any project
+    - "any": conversations linked to any project
+    """
+
+    def filter_queryset(self, request, queryset, view):
+        """Filter conversations by project."""
+        project_id = request.GET.get("project")
+        if project_id is None:
+            return queryset
+        if project_id == "none":
+            return queryset.filter(project__isnull=True)
+        if project_id == "any":
+            return queryset.filter(project__isnull=False)
+        try:
+            UUID(project_id)
+        except ValueError:
+            return queryset.none()
+        return queryset.filter(project_id=project_id)
+
+    def get_schema_operation_parameters(self, view):
+        """Return the schema for the ``project`` query parameter (drf-spectacular)."""
+        return [
+            {
+                "name": "project",
+                "required": False,
+                "in": "query",
+                "description": "Filter by project. Pass a UUID for a specific project, "
+                '"none" for standalone conversations, or "any" for all project conversations.',
+                "schema": {"type": "string"},
+            },
+        ]
+

 class ChatAttachmentMixin(AttachmentMixin):  # pylint: disable=abstract-method
    """Mixin to handle attachment authorization for chat conversations."""
@@ -102,18 +175,42 @@ class ChatViewSet(  # pylint: disable=too-many-ancestors, abstract-method
    ]
    serializer_class = serializers.ChatConversationSerializer
    post_conversation_serializer_class = serializers.ChatConversationInputSerializer
-    filter_backends = [filters.OrderingFilter, ChatConversationFilter]
+    filter_backends = [filters.OrderingFilter, TitleSearchFilter, ProjectFilter]
    ordering = ["-created_at"]
    ordering_fields = ["created_at", "updated_at"]
    queryset = models.ChatConversation.objects  # defined to be used in AttachmentMixin

+    @extend_schema(
+        responses=serializers.ChatConversationSearchSerializer(many=True),
+        description=(
+            "When the `title` query parameter is provided, returns search results "
+            "with nested project info (id, title, icon) and no messages. "
+            "Without `title`, returns the default conversation list."
+        ),
+    )
+    def list(self, request, *args, **kwargs):
+        return super().list(request, *args, **kwargs)
+
+    def get_serializer_class(self):
+        """Return search serializer when filtering by title on list action."""
+
+        # Search results only include nested project info
+        if self.action == "list" and self.request.query_params.get("title"):
+            return serializers.ChatConversationSearchSerializer
+        return super().get_serializer_class()
+
    def get_queryset(self):
        """Return the queryset for the chat conversations."""
-        return (
-            self.queryset.filter(owner=self.request.user)
-            if self.request.user.is_authenticated
-            else self.queryset.none()
-        )
+        if not self.request.user.is_authenticated:
+            return self.queryset.none()
+
+        qs = self.queryset.filter(owner=self.request.user)
+
+        # Search results use nested project info; post_conversation needs
+        # project.llm_instructions — prefetch to avoid extra queries
+        if self.request.query_params.get("title") or self.action == "post_conversation":
+            qs = qs.select_related("project")
+        return qs

    def get_permissions(self):
        """Return the permissions for the viewset."""
@@ -122,6 +219,7 @@ class ChatViewSet(  # pylint: disable=too-many-ancestors, abstract-method
            self.permission_classes = []
        return super().get_permissions()

+    @conditional_refresh_oidc_token
    @decorators.action(
        methods=["post"],
        detail=True,
@@ -173,6 +271,7 @@ 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 +287,28 @@ 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 +319,7 @@ 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 +469,6 @@ 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

@@ -435,3 +532,212 @@ class ChatConversationAttachmentViewSet(
            )

        return Response(serializer.data, status=status.HTTP_200_OK)
+
+    @decorators.action(
+        detail=False,
+        methods=["post"],
+        url_path="backend-upload",
+        url_name="backend-upload",
+    )
+    def backend_upload_attachment(self, request, *args, **kwargs):
+        """
+        Handle backend file upload for backend_to_s3 mode.
+
+        This endpoint is used when FILE_UPLOAD_MODE is set to backend_to_s3.
+        The frontend sends the file directly to this endpoint,
+        and the backend stores it on S3 and initiates malware detection.
+
+        The attachment lifecycle:
+        1. Frontend sends file via this endpoint
+        2. Backend stores file on S3
+        3. Backend detects MIME type and file size
+        4. Backend initiates malware detection
+        5. After detection, attachment status becomes READY or SUSPICIOUS
+        """
+        # pylint: disable=too-many-locals
+        # Verify the user owns the conversation
+        conversation_id = self.kwargs["conversation_pk"]
+        if not models.ChatConversation.objects.filter(
+            pk=conversation_id,
+            owner=request.user,
+        ).exists():
+            raise Http404
+
+        serializer = FileUploadSerializer(data=request.data)
+        serializer.is_valid(raise_exception=True)
+
+        file_obj = serializer.validated_data["file"]
+        file_name = serializer.validated_data["file_name"]
+
+        # Generate unique file ID and storage key
+        file_id = uuid4()
+        extension = file_name.rpartition(".")[-1] if "." in file_name else None
+        ext_suffix = f".{extension}" if extension else ""
+        key = f"{conversation_id}/{AttachmentMixin.ATTACHMENTS_FOLDER}/{file_id}{ext_suffix}"
+
+        # Store file on S3
+        try:
+            stored_path = default_storage.save(key, file_obj)
+            logger.info("File uploaded to S3: %s", stored_path)
+        except Exception:  # pylint: disable=broad-except
+            logger.exception("Failed to upload file to S3 for conversation %s", conversation_id)
+            return Response(
+                {"detail": "Failed to upload file to storage"},
+                status=status.HTTP_500_INTERNAL_SERVER_ERROR,
+            )
+
+        # Detect MIME type
+        mime_detector = magic.Magic(mime=True)
+        with default_storage.open(key, "rb") as file:
+            mimetype = mime_detector.from_buffer(file.read(2048))
+            file_size = file.size
+
+        # Create attachment record with ANALYZING status
+        attachment = models.ChatConversationAttachment.objects.create(
+            conversation_id=conversation_id,
+            uploaded_by=request.user,
+            upload_state=AttachmentStatus.ANALYZING,
+            key=key,
+            file_name=file_name,
+            content_type=mimetype,
+            size=file_size,
+        )
+
+        logger.info(
+            "Created attachment %s for conversation %s, starting malware detection",
+            attachment.pk,
+            conversation_id,
+        )
+
+        # Start malware detection (will update status to READY or SUSPICIOUS via callbacks)
+        malware_detection.analyse_file(
+            key,
+            safe_callback="chat.malware_detection.conversation_safe_attachment_callback",
+            unknown_callback="chat.malware_detection.unknown_attachment_callback",
+            unsafe_callback="chat.malware_detection.conversation_unsafe_attachment_callback",
+            conversation_id=conversation_id,
+        )
+
+        # Track upload event
+        if settings.POSTHOG_KEY:
+            posthog.capture(
+                "item_uploaded_backend",
+                distinct_id=str(request.user.pk),
+                properties={
+                    "id": attachment.pk,
+                    "file_name": attachment.file_name,
+                    "size": attachment.size,
+                    "mimetype": attachment.content_type,
+                    "mode": settings.FILE_UPLOAD_MODE,
+                },
+            )
+
+        serializer = self.get_serializer(attachment)
+        return Response(serializer.data, status=status.HTTP_201_CREATED)
+
+
+class FileStreamView(APIView):
+    """
+    Stream file content for temporary access URLs.
+
+    This view is used by LLMs to access file content when they cannot directly
+    access S3. A temporary key is stored in cache and validated before serving
+    the file.
+
+    Security:
+    - Temporary key expires after FILE_BACKEND_TEMPORARY_URL_EXPIRATION seconds
+      (default: 180 seconds / 3 minutes)
+    - No authentication required (key is single-use temporary token)
+    - Key is generated using secure random tokens
+    """
+
+    permission_classes = []  # No authentication needed for temporary keys
+    throttle_classes = [ScopedRateThrottle]
+    throttle_scope = "file-stream"
+
+    def get(self, request, temporary_key):
+        """
+        Stream file content using a temporary access key.
+
+        Args:
+            temporary_key: The temporary key generated by generate_temporary_url()
+
+        Returns:
+            StreamingHttpResponse with file content
+        """
+        # Retrieve the S3 key from cache using the temporary key
+        cache_key = f"file_access:{temporary_key}"
+        s3_key = cache.get(cache_key)
+
+        if not s3_key:
+            logger.warning("Temporary file access key not found or expired: %s", temporary_key)
+            raise Http404("File access key expired or invalid")
+
+        # Delete the key from cache to prevent reuse
+        cache.delete(cache_key)
+
+        logger.info("Serving file via temporary key: %s", s3_key)
+
+        try:
+            # Open the file from S3
+            file_obj = default_storage.open(s3_key, "rb")
+
+            # Detect MIME type for proper content-type header
+            mime_detector = magic.Magic(mime=True)
+            file_content = file_obj.read(2048)
+            file_obj.seek(0)
+            content_type = mime_detector.from_buffer(file_content)
+
+            # Extract filename from S3 key (last part after /)
+            filename = s3_key.split("/")[-1]
+
+            # Stream the file content
+            response = StreamingHttpResponse(
+                file_obj,
+                content_type=content_type,
+            )
+            response["Content-Disposition"] = f'inline; filename="{filename}"'
+            return response
+
+        except Exception as exc:
+            logger.exception("Failed to serve file via temporary key: %s", temporary_key)
+            raise Http404("Failed to retrieve file") from exc
+
+
+class ChatProjectViewSet(viewsets.ModelViewSet):  # pylint: disable=too-many-ancestors
+    """ViewSet for managing projects."""
+
+    pagination_class = Pagination
+    permission_classes = [
+        IsActivatedUser,  # see activation_codes application
+        permissions.IsAuthenticated,
+    ]
+    ordering = ["title"]
+    ordering_fields = ["title", "created_at", "updated_at"]
+    queryset = models.ChatProject.objects
+    serializer_class = serializers.ChatProjectSerializer
+    filter_backends = [filters.OrderingFilter, TitleSearchFilter]
+
+    def get_queryset(self):
+        """Return the queryset for the projects."""
+
+        # Prefetch conversations ordered by most recent first
+        conversations_prefetch = Prefetch(
+            "conversations",
+            queryset=models.ChatConversation.objects.order_by("-created_at"),
+        )
+
+        return (
+            self.queryset.filter(owner=self.request.user).prefetch_related(conversations_prefetch)
+            if self.request.user.is_authenticated
+            else self.queryset.none()
+        )
+
+    def perform_destroy(self, instance):
+        """Delete a project and its related conversations.
+
+        ChatConversation.project uses on_delete=SET_NULL (to avoid accidental
+        cascade), so we explicitly delete conversations here.
+        """
+        instance.conversations.all().delete()
+        instance.delete()
@@ -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):
@@ -230,6 +230,27 @@ class Base(BraveSettings, Configuration):
        environ_name="ATTACHMENT_MAX_SIZE",
        environ_prefix=None,
    )
+    FILE_UPLOAD_MODE = values.Value(
+        "presigned_url",
+        environ_name="FILE_UPLOAD_MODE",
+        environ_prefix=None,
+    )
+    FILE_TO_LLM_MODE = values.Value(
+        "presigned_url",
+        environ_name="FILE_TO_LLM_MODE",
+        environ_prefix=None,
+    )
+    FILE_BACKEND_URL = values.Value(
+        "",
+        environ_name="FILE_BACKEND_URL",
+        environ_prefix=None,
+    )
+    FILE_BACKEND_TEMPORARY_URL_EXPIRATION = values.IntegerValue(
+        180,
+        environ_name="FILE_BACKEND_TEMPORARY_URL_EXPIRATION",
+        environ_prefix=None,
+    )
+
    MALWARE_DETECTION = {
        "BACKEND": values.Value(
            "lasuite.malware_detection.backends.dummy.DummyBackend",
@@ -347,6 +368,7 @@ class Base(BraveSettings, Configuration):
        "django.contrib.staticfiles",
        # OIDC third party
        "mozilla_django_oidc",
+        "lasuite.malware_detection",
    ]

    # Cache
@@ -395,6 +417,11 @@ class Base(BraveSettings, Configuration):
                environ_name="API_USERS_LIST_THROTTLE_RATE_BURST",
                environ_prefix=None,
            ),
+            "file-stream": values.Value(
+                default="60/minute",
+                environ_name="API_FILE_STREAM_THROTTLE_RATE",
+                environ_prefix=None,
+            ),
        },
    }

@@ -646,6 +673,11 @@ class Base(BraveSettings, Configuration):
        environ_name="DEFAULT_ALLOW_CONVERSATION_ANALYTICS",
        environ_prefix=None,
    )
+    DEFAULT_ALLOW_SMART_WEB_SEARCH = values.BooleanValue(
+        default=True,
+        environ_name="DEFAULT_ALLOW_SMART_WEB_SEARCH",
+        environ_prefix=None,
+    )

    # These settings are default values used in the default LLM_CONFIGURATIONS
    # They allow a deployment with only one model without a specific configuration file
@@ -676,7 +708,7 @@ class Base(BraveSettings, Configuration):
            # docx files
            "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
            # pptx files
-            "application/vnd.openxmlformats-officedocument.presentationml",
+            "application/vnd.openxmlformats-officedocument.presentationml.presentation",
            # xlsx and xls files
            "application/vnd.ms-excel",
            "application/excel",
@@ -717,6 +749,11 @@ class Base(BraveSettings, Configuration):
        environ_name="RAG_DOCUMENT_SEARCH_BACKEND",
        environ_prefix=None,
    )
+    RAG_DOCUMENT_PARSER = values.Value(
+        "chat.agent_rag.document_converter.parser.AlbertParser",
+        environ_name="RAG_DOCUMENT_PARSER",
+        environ_prefix=None,
+    )
    SPECIFIC_RAG_DOCUMENT_SEARCH_TOOLS = values.DictValue(
        default={},
        environ_name="SPECIFIC_RAG_DOCUMENT_SEARCH_TOOLS",
@@ -782,6 +819,51 @@ USER QUESTION:
        environ_prefix=None,
    )

+    # OCR settings for AdaptivePdfParser
+    OCR_HRID = values.Value(
+        default="etalab-plateform-mistral-medium-2508",
+        environ_name="OCR_HRID",
+        environ_prefix=None,
+    )
+    # Specific Mistral OCR model - Designates which Mistral vision model to use for OCR
+    OCR_MODEL = values.Value(
+        default="mistral-ocr-2512",
+        environ_name="OCR_MODEL",
+        environ_prefix=None,
+    )
+    OCR_TIMEOUT = values.PositiveIntegerValue(
+        default=240,
+        environ_name="OCR_TIMEOUT",
+        environ_prefix=None,
+    )
+    OCR_MAX_RETRIES = values.PositiveIntegerValue(
+        default=3,
+        environ_name="OCR_MAX_RETRIES",
+        environ_prefix=None,
+    )
+
+    OCR_RETRY_DELAY = values.PositiveIntegerValue(
+        default=5,
+        environ_name="OCR_RETRY_DELAY",
+        environ_prefix=None,
+    )
+
+    OCR_BATCH_PAGES = values.PositiveIntegerValue(
+        default=10,
+        environ_name="OCR_BATCH_PAGES",
+        environ_prefix=None,
+    )
+    MIN_AVG_CHARS_FOR_TEXT_EXTRACTION = values.PositiveIntegerValue(
+        default=200,
+        environ_name="MIN_AVG_CHARS_FOR_TEXT_EXTRACTION",
+        environ_prefix=None,
+    )
+    MIN_TEXT_COVERAGE_FOR_TEXT_EXTRACTION = values.FloatValue(
+        default=0.7,
+        environ_name="MIN_TEXT_COVERAGE_FOR_TEXT_EXTRACTION",
+        environ_prefix=None,
+    )
+
    # Summarization
    SUMMARIZATION_SYSTEM_PROMPT = values.Value(
        (
@@ -841,6 +923,23 @@ 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.
@@ -911,7 +1010,9 @@ USER QUESTION:
    LANGFUSE_MEDIA_UPLOAD_ENABLED = values.BooleanValue(
        default=False, environ_name="LANGFUSE_MEDIA_UPLOAD_ENABLED", environ_prefix=None
    )
-
+    AUTO_TITLE_AFTER_USER_MESSAGES = values.PositiveIntegerValue(
+        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(
        default=False,
@@ -919,6 +1020,12 @@ 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):
@@ -1038,6 +1145,42 @@ USER QUESTION:
                "OIDC_ALLOW_DUPLICATE_EMAILS cannot be set to True simultaneously. "
            )

+        # File access configuration validation
+        if cls.FILE_TO_LLM_MODE == "backend_temporary_url" and not cls.FILE_BACKEND_URL:
+            raise ValueError(
+                "FILE_TO_LLM_MODE is set to 'backend_temporary_url' but FILE_BACKEND_URL is empty. "
+                "Please set FILE_BACKEND_URL to a valid URL for backend temporary file access."
+            )
+
+        # Find configuration
+        if (
+            cls.RAG_DOCUMENT_SEARCH_BACKEND
+            == "chat.agent_rag.document_rag_backends.find_rag_backend.FindRagBackend"
+            and not all(
+                (
+                    cls.FIND_API_KEY,
+                    cls.FIND_API_URL,
+                    cls.OIDC_STORE_ACCESS_TOKEN,
+                    cls.OIDC_STORE_REFRESH_TOKEN,
+                )
+            )
+        ):
+            raise ValueError(
+                f"{cls.RAG_DOCUMENT_SEARCH_BACKEND} requires FIND_API_KEY, FIND_API_URL, "
+                "OIDC_STORE_ACCESS_TOKEN and OIDC_STORE_REFRESH_TOKEN to be set."
+            )
+
+        # OCR configuration validation
+        # Note: we call load_llm_configuration directly because LLM_CONFIGURATIONS is a
+        # @property returning a lazy object, which cannot be accessed via cls in a classmethod.
+        if cls.RAG_DOCUMENT_PARSER == "chat.agent_rag.document_converter.parser.AdaptivePdfParser":
+            llm_configs = load_llm_configuration(cls._llm_configuration_file_path)
+            if cls.OCR_HRID not in llm_configs:
+                raise ValueError(
+                    f"OCR_HRID '{cls.OCR_HRID}' not found in LLM_CONFIGURATIONS. "
+                    "Please add a matching provider entry or set OCR_HRID to an existing key."
+                )
+
        # Langfuse initialization
        if cls.LANGFUSE_ENABLED:
            if not cls.LANGFUSE_MEDIA_UPLOAD_ENABLED:
@@ -1131,6 +1274,8 @@ 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"]
@@ -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)
@@ -13,6 +13,7 @@ class UserSerializer(serializers.ModelSerializer):
        fields = [
            "id",
            "allow_conversation_analytics",
+            "allow_smart_web_search",
            "email",
            "full_name",
            "short_name",
@@ -20,23 +21,3 @@ 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"]
@@ -211,6 +211,7 @@ class ConfigView(drf.views.APIView):
            "LANGUAGE_CODE",
            "SENTRY_DSN",
            "FEATURE_FLAGS",
+            "FILE_UPLOAD_MODE",
        ]
        dict_settings = {}
        for setting in array_settings:
@@ -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'"
@@ -55,7 +55,11 @@ class OIDCAuthenticationBackend(LaSuiteOIDCAuthenticationBackend):
        more information about the usage of the application.
        """
        return super().create_user(
-            claims | {"allow_conversation_analytics": settings.DEFAULT_ALLOW_CONVERSATION_ANALYTICS}
+            claims
+            | {
+                "allow_conversation_analytics": settings.DEFAULT_ALLOW_CONVERSATION_ANALYTICS,
+                "allow_smart_web_search": settings.DEFAULT_ALLOW_SMART_WEB_SEARCH,
+            }
        )

    def authenticate(self, request, **kwargs):
@@ -22,6 +22,7 @@ class UserFactory(factory.django.DjangoModelFactory):
        skip_postgeneration_save = True

    allow_conversation_analytics = factory.Faker("boolean", chance_of_getting_true=50)
+    allow_smart_web_search = factory.Faker("boolean", chance_of_getting_true=50)
    sub = factory.Sequence(lambda n: f"user{n!s}")
    email = factory.Faker("email")
    full_name = factory.Faker("name")
@@ -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)
@@ -20,3 +20,28 @@ class AttachmentStatus(StrEnum):
    def choices(cls):
        """Return a list of tuples for each enum member."""
        return [(member.value, member.name) for member in cls]
+
+
+class FileUploadMode(StrEnum):
+    """Defines the possible modes for file upload (from frontend) handling."""
+
+    PRESIGNED_URL = "presigned_url"
+    BACKEND_TO_S3 = "backend_to_s3"
+
+    @classmethod
+    def choices(cls):
+        """Return a list of tuples for each enum member."""
+        return [(member.value, member.name) for member in cls]
+
+
+class FileToLLMMode(StrEnum):
+    """Defines the possible modes to send file to the LLM."""
+
+    PRESIGNED_URL = "presigned_url"
+    BACKEND_BASE64 = "backend_base64"
+    BACKEND_TEMPORARY_URL = "backend_temporary_url"
+
+    @classmethod
+    def choices(cls):
+        """Return a list of tuples for each enum member."""
+        return [(member.value, member.name) for member in cls]
@@ -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)
@@ -0,0 +1,21 @@
+# Generated by Django 5.2.9 on 2025-12-10 15:19
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("core", "0003_alter_user_short_name"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="user",
+            name="allow_smart_web_search",
+            field=models.BooleanField(
+                default=True,
+                help_text="Whether the user allows to use smart web search features.",
+                verbose_name="allow smart web search",
+            ),
+        ),
+    ]
@@ -77,10 +77,13 @@ class UserManager(auth_models.UserManager):

            if settings.OIDC_FALLBACK_TO_EMAIL_FOR_IDENTIFICATION:
                try:
-                    return self.get(email=email)
+                    return self.get(email__iexact=email)
                except self.model.DoesNotExist:
                    pass
-            elif self.filter(email=email).exists() and not settings.OIDC_ALLOW_DUPLICATE_EMAILS:
+            elif (
+                self.filter(email__iexact=email).exists()
+                and not settings.OIDC_ALLOW_DUPLICATE_EMAILS
+            ):
                raise DuplicateEmailError(
                    _(
                        "We couldn't find a user with this sub but the email is already "
@@ -163,6 +166,12 @@ class User(AbstractBaseUser, BaseModel, auth_models.PermissionsMixin):
        help_text=_("Whether the user allows to use their conversations for analytics."),
    )

+    allow_smart_web_search = models.BooleanField(
+        _("allow smart web search"),
+        default=True,
+        help_text=_("Whether the user allows to use smart web search features."),
+    )
+
    objects = UserManager()

    USERNAME_FIELD = "admin_email"
@@ -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>
@@ -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 ""
@@ -64,6 +64,28 @@ def test_authentication_getter_existing_user_via_email(django_assert_num_queries
    assert user == db_user


+def test_authentication_getter_existing_user_via_email_case_insensitive(
+    django_assert_num_queries, monkeypatch
+):
+    """
+    If an existing user doesn't match the sub but matches the email with different case,
+    the user should be returned (case-insensitive email matching).
+    """
+
+    klass = OIDCAuthenticationBackend()
+    db_user = UserFactory(email="john.doe@example.com")
+
+    def get_userinfo_mocked(*args):
+        return {"sub": "123", "email": "JOHN.DOE@EXAMPLE.COM"}
+
+    monkeypatch.setattr(OIDCAuthenticationBackend, "get_userinfo", get_userinfo_mocked)
+
+    with django_assert_num_queries(4):  # user by sub, user by mail, update sub
+        user = klass.get_or_create_user(access_token="test-token", id_token=None, payload=None)
+
+    assert user == db_user
+
+
 def test_authentication_getter_email_none(monkeypatch):
    """
    If no user is found with the sub and no email is provided, a new user should be created.
@@ -149,6 +171,39 @@ def test_authentication_getter_existing_user_no_fallback_to_email_no_duplicate(
    assert models.User.objects.count() == 1


+def test_authentication_getter_existing_user_no_fallback_to_email_no_duplicate_case_insensitive(
+    settings, monkeypatch
+):
+    """
+    When the "OIDC_FALLBACK_TO_EMAIL_FOR_IDENTIFICATION" setting is set to False,
+    the system should detect duplicate emails even with different case.
+    """
+
+    klass = OIDCAuthenticationBackend()
+    _db_user = UserFactory(email="john.doe@example.com")
+
+    # Set the setting to False
+    settings.OIDC_FALLBACK_TO_EMAIL_FOR_IDENTIFICATION = False
+    settings.OIDC_ALLOW_DUPLICATE_EMAILS = False
+
+    def get_userinfo_mocked(*args):
+        return {"sub": "123", "email": "JOHN.DOE@EXAMPLE.COM"}
+
+    monkeypatch.setattr(OIDCAuthenticationBackend, "get_userinfo", get_userinfo_mocked)
+
+    with pytest.raises(
+        SuspiciousOperation,
+        match=(
+            "We couldn't find a user with this sub but the email is already associated "
+            "with a registered user."
+        ),
+    ):
+        klass.get_or_create_user(access_token="test-token", id_token=None, payload=None)
+
+    # Since the sub doesn't match, it should not create a new user
+    assert models.User.objects.count() == 1
+
+
 def test_authentication_getter_existing_user_with_email(django_assert_num_queries, monkeypatch):
    """
    When the user's info contains an email and targets an existing user,
@@ -0,0 +1,110 @@
+"""Tests for generate_temporary_url utility function."""
+
+from django.conf import settings
+from django.core.cache import cache
+
+import pytest
+
+from chat.agents.local_media_url_processors import generate_temporary_url
+
+pytestmark = pytest.mark.django_db
+
+
+def test_generate_temporary_url_returns_string():
+    """Test that generate_temporary_url returns a valid backend streaming URL."""
+    cache.clear()
+    url = generate_temporary_url("test/file.pdf")
+
+    assert isinstance(url, str)
+    assert url.startswith(settings.FILE_BACKEND_URL + "/api/v1.0/file-stream/")
+    assert url.endswith("/")
+
+
+def test_generate_temporary_url_creates_cache_entry():
+    """Test that a cache entry is created with correct mapping."""
+    cache.clear()
+    s3_key = "conversation-id/attachments/file-uuid.pdf"
+    url = generate_temporary_url(s3_key)
+
+    # Extract temporary key from URL
+    temporary_key = url.split("/file-stream/")[1].rstrip("/")
+
+    # Verify cache entry
+    cache_key = f"file_access:{temporary_key}"
+    cached_value = cache.get(cache_key)
+    assert cached_value == s3_key
+
+
+def test_generate_temporary_url_unique_tokens():
+    """Test that different S3 keys produce different temporary tokens."""
+    cache.clear()
+    url1 = generate_temporary_url("file1.pdf")
+    url2 = generate_temporary_url("file2.pdf")
+
+    assert url1 != url2
+
+    key1 = url1.split("/file-stream/")[1].rstrip("/")
+    key2 = url2.split("/file-stream/")[1].rstrip("/")
+
+    assert cache.get(f"file_access:{key1}") == "file1.pdf"
+    assert cache.get(f"file_access:{key2}") == "file2.pdf"
+
+
+def test_generate_temporary_url_token_is_url_safe():
+    """Test that generated tokens contain only URL-safe characters."""
+    cache.clear()
+    url = generate_temporary_url("test.pdf")
+
+    temporary_key = url.split("/file-stream/")[1].rstrip("/")
+
+    # Token should only contain alphanumeric, dash, and underscore
+    assert all(c.isalnum() or c in "-_" for c in temporary_key)
+
+
+def test_generate_temporary_url_token_sufficient_entropy():
+    """Test that generated tokens have sufficient entropy."""
+    cache.clear()
+    url = generate_temporary_url("test.pdf")
+
+    temporary_key = url.split("/file-stream/")[1].rstrip("/")
+
+    # Token should be reasonably long
+    assert len(temporary_key) >= 32
+
+
+def test_generate_temporary_url_no_sensitive_data_in_url():
+    """Test that temporary URLs don't contain S3 key information."""
+    cache.clear()
+
+    s3_key = "secret/conversation-123/attachments/file.pdf"
+    url = generate_temporary_url(s3_key)
+
+    # URL should not contain the actual S3 key
+    assert "secret" not in url
+    assert "conversation-123" not in url
+    assert "file.pdf" not in url
+    # Only the endpoint and random token
+    assert "/api/v1.0/file-stream/" in url
+
+
+def test_generate_temporary_url_various_key_formats():
+    """Test generate_temporary_url with various S3 key formats."""
+    cache.clear()
+
+    test_keys = [
+        "simple/key.pdf",
+        "conversation-123/attachments/file-uuid.pdf",
+        "nested/folder/structure/file.jpg",
+        "file_with_special-chars_123.png",
+    ]
+
+    urls = []
+    for key in test_keys:
+        url = generate_temporary_url(key)
+        urls.append(url)
+
+        temporary_key = url.split("/file-stream/")[1].rstrip("/")
+        assert cache.get(f"file_access:{temporary_key}") == key
+
+    # All URLs should be different
+    assert len(set(urls)) == len(urls)
@@ -47,6 +47,7 @@ def test_api_config(is_authenticated):
        "CRISP_WEBSITE_ID": "123",
        "ENVIRONMENT": "test",
        "FEATURE_FLAGS": {"document-upload": "enabled", "web-search": "enabled"},
+        "FILE_UPLOAD_MODE": "presigned_url",
        "FRONTEND_CSS_URL": "http://testcss/",
        "FRONTEND_HOMEPAGE_FEATURE_ENABLED": True,
        "FRONTEND_THEME": "test-theme",
@@ -189,6 +190,7 @@ async def test_api_config_async(is_authenticated):
        "CRISP_WEBSITE_ID": "123",
        "ENVIRONMENT": "test",
        "FEATURE_FLAGS": {"document-upload": "enabled", "web-search": "enabled"},
+        "FILE_UPLOAD_MODE": "presigned_url",
        "FRONTEND_CSS_URL": "http://testcss/",
        "FRONTEND_HOMEPAGE_FEATURE_ENABLED": True,
        "FRONTEND_THEME": "test-theme",
@@ -225,6 +225,7 @@ def test_api_users_retrieve_me_authenticated():
    assert response.json() == {
        "id": str(user.id),
        "allow_conversation_analytics": user.allow_conversation_analytics,
+        "allow_smart_web_search": user.allow_smart_web_search,
        "email": user.email,
        "full_name": user.full_name,
        "language": user.language,
@@ -338,7 +339,7 @@ def test_api_users_update_anonymous():
 def test_api_users_update_authenticated_self():
    """
    Authenticated users should be able to update their own user but only "language",
-    "allow_conversation_analytics" and "timezone" fields.
+    "allow_conversation_analytics", "allow_smart_web_search" and "timezone" fields.
    """
    user = factories.UserFactory()

@@ -350,6 +351,7 @@ def test_api_users_update_authenticated_self():
        serializers.UserSerializer(
            instance=factories.UserFactory(
                allow_conversation_analytics=not user.allow_conversation_analytics,
+                allow_smart_web_search=not user.allow_smart_web_search,
            )
        ).data
    )
@@ -364,7 +366,12 @@ def test_api_users_update_authenticated_self():
    user.refresh_from_db()
    user_values = dict(serializers.UserSerializer(instance=user).data)
    for key, value in user_values.items():
-        if key in ["allow_conversation_analytics", "language", "timezone"]:
+        if key in [
+            "allow_conversation_analytics",
+            "allow_smart_web_search",
+            "language",
+            "timezone",
+        ]:
            assert value == new_user_values[key]
        else:
            assert value == old_user_values[key]
@@ -419,7 +426,7 @@ def test_api_users_patch_anonymous():
 def test_api_users_patch_authenticated_self():
    """
    Authenticated users should be able to patch their own user but only "language",
-    "allow_conversation_analytics" and "timezone" fields.
+    "allow_conversation_analytics", "allow_smart_web_search" and "timezone" fields.
    """
    user = factories.UserFactory()

@@ -431,6 +438,7 @@ def test_api_users_patch_authenticated_self():
        serializers.UserSerializer(
            instance=factories.UserFactory(
                allow_conversation_analytics=not user.allow_conversation_analytics,
+                allow_smart_web_search=not user.allow_smart_web_search,
            )
        ).data
    )
@@ -446,7 +454,12 @@ def test_api_users_patch_authenticated_self():
    user.refresh_from_db()
    user_values = dict(serializers.UserSerializer(instance=user).data)
    for key, value in user_values.items():
-        if key in ["allow_conversation_analytics", "language", "timezone"]:
+        if key in [
+            "allow_conversation_analytics",
+            "allow_smart_web_search",
+            "language",
+            "timezone",
+        ]:
            assert value == new_user_values[key]
        else:
            assert value == old_user_values[key]
@@ -1,20 +1,28 @@
 """URL configuration for the core app."""

 from django.conf import settings
-from django.urls import include, path
+from django.urls import include, path, re_path

 from lasuite.oidc_login.urls import urlpatterns as oidc_urls
 from rest_framework.routers import DefaultRouter

 from core.api import viewsets
+from core.file_upload.enums import FileToLLMMode

 from activation_codes import viewsets as activation_viewsets
-from chat.views import ChatConversationAttachmentViewSet, ChatViewSet, LLMConfigurationView
+from chat.views import (
+    ChatConversationAttachmentViewSet,
+    ChatProjectViewSet,
+    ChatViewSet,
+    FileStreamView,
+    LLMConfigurationView,
+)

 # - Main endpoints
 router = DefaultRouter()
 router.register("users", viewsets.UserViewSet, basename="users")
 router.register("chats", ChatViewSet, basename="chats")
+router.register("projects", ChatProjectViewSet, basename="projects")
 router.register("activation", activation_viewsets.ActivationViewSet, basename="activation")

 conversation_router = DefaultRouter()
@@ -37,6 +45,21 @@ urlpatterns = [
                    include(conversation_router.urls),
                ),
            ]
+            + (
+                # Only allow file stream URL when configured for backend temporary URL mode
+                [
+                    re_path(
+                        r"^file-stream/(?P<temporary_key>[a-zA-Z0-9_-]+)/$",
+                        FileStreamView.as_view(),
+                        name="file-stream",
+                    ),
+                ]
+                if (
+                    settings.FILE_TO_LLM_MODE == FileToLLMMode.BACKEND_TEMPORARY_URL
+                    or settings.ENVIRONMENT == "test"
+                )
+                else []
+            )
        ),
    ),
    path(f"api/{settings.API_VERSION}/config/", viewsets.ConfigView.as_view()),
@@ -2,8 +2,8 @@ msgid ""
 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: 2025-11-17 16:37\n"
+"POT-Creation-Date: 2026-02-26 21:42+0000\n"
+"PO-Revision-Date: 2026-03-11 15:23\n"
 "Last-Translator: \n"
 "Language-Team: German\n"
 "Language: de_DE\n"
@@ -17,328 +17,320 @@ msgstr ""
 "X-Crowdin-File: backend-conversations.pot\n"
 "X-Crowdin-File-ID: 26\n"

-#: activation_codes/admin.py:55 build/lib/activation_codes/admin.py:55
+#: activation_codes/admin.py:55
 msgid "Configuration"
 msgstr ""

-#: activation_codes/admin.py:66 build/lib/activation_codes/admin.py:66
+#: activation_codes/admin.py:66
 msgid "Usage details"
 msgstr ""

 #: activation_codes/admin.py:70 activation_codes/admin.py:226
-#: build/lib/activation_codes/admin.py:70
-#: build/lib/activation_codes/admin.py:226
 msgid "Timestamps"
 msgstr ""

-#: activation_codes/admin.py:109 build/lib/activation_codes/admin.py:109
+#: activation_codes/admin.py:109
 msgid "Usage"
 msgstr ""

-#: activation_codes/admin.py:117 build/lib/activation_codes/admin.py:117
+#: activation_codes/admin.py:117
 msgid "Description"
 msgstr ""

-#: activation_codes/admin.py:124 build/lib/activation_codes/admin.py:124
+#: activation_codes/admin.py:124
 msgid "No users have used this code yet"
 msgstr ""

-#: activation_codes/admin.py:135 build/lib/activation_codes/admin.py:135
+#: activation_codes/admin.py:135
 msgid "Name"
 msgstr ""

 #: activation_codes/admin.py:136 activation_codes/admin.py:246
-#: build/lib/activation_codes/admin.py:136
-#: build/lib/activation_codes/admin.py:246
 msgid "Email"
 msgstr ""

-#: activation_codes/admin.py:137 build/lib/activation_codes/admin.py:137
+#: activation_codes/admin.py:137
 msgid "Date"
 msgstr ""

-#: activation_codes/admin.py:161 build/lib/activation_codes/admin.py:161
+#: activation_codes/admin.py:161
 msgid "Users who used this code"
 msgstr ""

-#: activation_codes/admin.py:163 build/lib/activation_codes/admin.py:163
+#: activation_codes/admin.py:163
 msgid "Recompute current uses from related activations"
 msgstr ""

-#: activation_codes/admin.py:177 build/lib/activation_codes/admin.py:177
+#: activation_codes/admin.py:177
 msgid "All selected activation codes already have correct usage counts."
 msgstr ""

-#: activation_codes/admin.py:182 build/lib/activation_codes/admin.py:182
+#: activation_codes/admin.py:182
 #, python-format
 msgid "Successfully recomputed usage counts for %(count)d activation code(s)."
 msgstr ""

 #: activation_codes/admin.py:240 activation_codes/admin.py:284
-#: build/lib/activation_codes/admin.py:240
-#: build/lib/activation_codes/admin.py:284
 msgid "User"
 msgstr ""

-#: activation_codes/admin.py:291 build/lib/activation_codes/admin.py:291
+#: activation_codes/admin.py:291
 msgid "Has used activation code"
 msgstr ""

-#: activation_codes/admin.py:293 build/lib/activation_codes/admin.py:293
+#: activation_codes/admin.py:293
 msgid "Add selected users to Brevo waiting list"
 msgstr ""

-#: activation_codes/admin.py:314 build/lib/activation_codes/admin.py:314
+#: activation_codes/admin.py:314
 #, python-format
 msgid "Added %(count)d user(s) to Brevo waiting list."
 msgstr ""

 #: activation_codes/admin.py:319 activation_codes/admin.py:347
-#: build/lib/activation_codes/admin.py:319
-#: build/lib/activation_codes/admin.py:347
 msgid "No valid email address found in selected registrations."
 msgstr ""

-#: activation_codes/admin.py:323 build/lib/activation_codes/admin.py:323
+#: activation_codes/admin.py:323
 msgid "Remove selected users from Brevo waiting list"
 msgstr ""

-#: activation_codes/admin.py:342 build/lib/activation_codes/admin.py:342
+#: activation_codes/admin.py:342
 #, python-format
 msgid "Removed %(count)d user(s) from Brevo waiting list."
 msgstr ""

 #: activation_codes/models.py:38 activation_codes/models.py:85
-#: activation_codes/models.py:178 build/lib/activation_codes/models.py:38
-#: build/lib/activation_codes/models.py:85
-#: build/lib/activation_codes/models.py:178
+#: activation_codes/models.py:178
 msgid "activation code"
 msgstr ""

-#: activation_codes/models.py:39 build/lib/activation_codes/models.py:39
+#: activation_codes/models.py:39
 msgid "The activation code that users will enter"
 msgstr ""

-#: activation_codes/models.py:46 build/lib/activation_codes/models.py:46
+#: activation_codes/models.py:46
 msgid "Code must be alphanumeric and contain no spaces or special characters"
 msgstr ""

-#: activation_codes/models.py:52 build/lib/activation_codes/models.py:52
+#: activation_codes/models.py:52
 msgid "maximum uses"
 msgstr ""

-#: activation_codes/models.py:53 build/lib/activation_codes/models.py:53
+#: activation_codes/models.py:53
 msgid "Maximum number of times this code can be used. 0 means unlimited."
 msgstr ""

-#: activation_codes/models.py:58 build/lib/activation_codes/models.py:58
+#: activation_codes/models.py:58
 msgid "current uses"
 msgstr ""

-#: activation_codes/models.py:59 build/lib/activation_codes/models.py:59
+#: activation_codes/models.py:59
 msgid "Number of times this code has been used"
 msgstr ""

-#: activation_codes/models.py:65 build/lib/activation_codes/models.py:65
-#: build/lib/core/models.py:151 core/models.py:151
+#: activation_codes/models.py:65 core/models.py:154
 msgid "active"
 msgstr ""

-#: activation_codes/models.py:66 build/lib/activation_codes/models.py:66
+#: activation_codes/models.py:66
 msgid "Whether this code can still be used"
 msgstr ""

-#: activation_codes/models.py:71 build/lib/activation_codes/models.py:71
+#: activation_codes/models.py:71
 msgid "expires at"
 msgstr ""

-#: activation_codes/models.py:72 build/lib/activation_codes/models.py:72
+#: activation_codes/models.py:72
 msgid "Date and time when this code expires"
 msgstr ""

-#: activation_codes/models.py:78 build/lib/activation_codes/models.py:78
+#: activation_codes/models.py:78
 msgid "description"
 msgstr ""

-#: activation_codes/models.py:79 build/lib/activation_codes/models.py:79
+#: activation_codes/models.py:79
 msgid "Internal description or notes about this code"
 msgstr ""

-#: activation_codes/models.py:86 build/lib/activation_codes/models.py:86
+#: activation_codes/models.py:86
 msgid "activation codes"
 msgstr ""

-#: activation_codes/models.py:128 build/lib/activation_codes/models.py:128
+#: activation_codes/models.py:128
 msgid "This activation code is no longer valid"
 msgstr ""

-#: activation_codes/models.py:136 build/lib/activation_codes/models.py:136
+#: activation_codes/models.py:136
 msgid "You have already activated your account"
 msgstr ""

 #: activation_codes/models.py:170 activation_codes/models.py:202
-#: build/lib/activation_codes/models.py:170
-#: build/lib/activation_codes/models.py:202 build/lib/core/models.py:173
-#: core/models.py:173
+#: core/models.py:182
 msgid "user"
 msgstr ""

-#: activation_codes/models.py:171 build/lib/activation_codes/models.py:171
+#: activation_codes/models.py:171
 msgid "The user who used the activation code"
 msgstr ""

-#: activation_codes/models.py:179 build/lib/activation_codes/models.py:179
+#: activation_codes/models.py:179
 msgid "The activation code that was used"
 msgstr ""

 #: activation_codes/models.py:186 activation_codes/models.py:210
-#: build/lib/activation_codes/models.py:186
-#: build/lib/activation_codes/models.py:210
 msgid "user activation"
 msgstr ""

-#: activation_codes/models.py:187 build/lib/activation_codes/models.py:187
+#: activation_codes/models.py:187
 msgid "user activations"
 msgstr ""

-#: activation_codes/models.py:203 build/lib/activation_codes/models.py:203
+#: activation_codes/models.py:203
 msgid "The user who made the registration request"
 msgstr ""

-#: activation_codes/models.py:211 build/lib/activation_codes/models.py:211
+#: activation_codes/models.py:211
 msgid "Store if the user received an activation code and used it"
 msgstr ""

-#: activation_codes/models.py:220 build/lib/activation_codes/models.py:220
+#: activation_codes/models.py:220
 msgid "user registration request"
 msgstr ""

-#: activation_codes/models.py:221 build/lib/activation_codes/models.py:221
+#: activation_codes/models.py:221
 msgid "user registration requests"
 msgstr ""

 #: activation_codes/serializers.py:14
-#: build/lib/activation_codes/serializers.py:14
 msgid "The activation code to validate"
 msgstr ""

-#: activation_codes/viewsets.py:107 build/lib/activation_codes/viewsets.py:107
+#: activation_codes/viewsets.py:107
 msgid "Your account has been successfully activated"
 msgstr ""

-#: build/lib/chat/apps.py:12 chat/apps.py:12
+#: chat/apps.py:12
 msgid "chat application"
 msgstr ""

-#: build/lib/core/admin.py:26 core/admin.py:26
+#: core/admin.py:26
 msgid "Personal info"
 msgstr ""

-#: build/lib/core/admin.py:40 core/admin.py:40
+#: core/admin.py:40
 msgid "Permissions"
 msgstr ""

-#: build/lib/core/admin.py:52 core/admin.py:52
+#: core/admin.py:52
 msgid "Important dates"
 msgstr ""

-#: build/lib/core/models.py:39 core/models.py:39
+#: core/models.py:39
 msgid "id"
 msgstr "id"

-#: build/lib/core/models.py:40 core/models.py:40
+#: core/models.py:40
 msgid "primary key for the record as UUID"
 msgstr ""

-#: build/lib/core/models.py:46 core/models.py:46
+#: core/models.py:46
 msgid "created on"
 msgstr ""

-#: build/lib/core/models.py:47 core/models.py:47
+#: core/models.py:47
 msgid "date and time at which a record was created"
 msgstr ""

-#: build/lib/core/models.py:52 core/models.py:52
+#: core/models.py:52
 msgid "updated on"
 msgstr ""

-#: build/lib/core/models.py:53 core/models.py:53
+#: core/models.py:53
 msgid "date and time at which a record was last updated"
 msgstr ""

-#: build/lib/core/models.py:86 core/models.py:86
+#: core/models.py:89
 msgid "We couldn't find a user with this sub but the email is already associated with a registered user."
 msgstr ""

-#: build/lib/core/models.py:99 core/models.py:99
+#: core/models.py:102
 msgid "Enter a valid sub. This value may contain only letters, numbers, and @/./+/-/_/: characters."
 msgstr ""

-#: build/lib/core/models.py:105 core/models.py:105
+#: core/models.py:108
 msgid "sub"
 msgstr ""

-#: build/lib/core/models.py:107 core/models.py:107
+#: core/models.py:110
 msgid "Required. 255 characters or fewer. Letters, numbers, and @/./+/-/_/: characters only."
 msgstr ""

-#: build/lib/core/models.py:116 core/models.py:116
+#: core/models.py:119
 msgid "full name"
 msgstr ""

-#: build/lib/core/models.py:117 core/models.py:117
+#: core/models.py:120
 msgid "short name"
 msgstr ""

-#: build/lib/core/models.py:119 core/models.py:119
+#: core/models.py:122
 msgid "identity email address"
 msgstr ""

-#: build/lib/core/models.py:123 core/models.py:123
+#: core/models.py:126
 msgid "admin email address"
 msgstr ""

-#: build/lib/core/models.py:129 core/models.py:129
+#: core/models.py:132
 msgid "language"
 msgstr ""

-#: build/lib/core/models.py:130 core/models.py:130
+#: core/models.py:133
 msgid "The language in which the user wants to see the interface."
 msgstr ""

-#: build/lib/core/models.py:138 core/models.py:138
+#: core/models.py:141
 msgid "The timezone in which the user wants to see times."
 msgstr ""

-#: build/lib/core/models.py:141 core/models.py:141
+#: core/models.py:144
 msgid "device"
 msgstr ""

-#: build/lib/core/models.py:143 core/models.py:143
+#: core/models.py:146
 msgid "Whether the user is a device or a real user."
 msgstr ""

-#: build/lib/core/models.py:146 core/models.py:146
+#: core/models.py:149
 msgid "staff status"
 msgstr ""

-#: build/lib/core/models.py:148 core/models.py:148
+#: core/models.py:151
 msgid "Whether the user can log into this admin site."
 msgstr ""

-#: build/lib/core/models.py:154 core/models.py:154
+#: core/models.py:157
 msgid "Whether this user should be treated as active. Unselect this instead of deleting accounts."
 msgstr ""

-#: build/lib/core/models.py:161 core/models.py:161
+#: core/models.py:164
 msgid "allow conversation analytics"
 msgstr ""

-#: build/lib/core/models.py:163 core/models.py:163
+#: core/models.py:166
 msgid "Whether the user allows to use their conversations for analytics."
 msgstr ""

-#: build/lib/core/models.py:174 core/models.py:174
+#: core/models.py:170
+msgid "allow smart web search"
+msgstr ""
+
+#: core/models.py:172
+msgid "Whether the user allows to use smart web search features."
+msgstr ""
+
+#: core/models.py:183
 msgid "users"
 msgstr ""

@@ -2,8 +2,8 @@ msgid ""
 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: 2025-11-17 16:37\n"
+"POT-Creation-Date: 2026-02-26 21:42+0000\n"
+"PO-Revision-Date: 2026-03-11 15:23\n"
 "Last-Translator: \n"
 "Language-Team: English\n"
 "Language: en_US\n"
@@ -17,328 +17,320 @@ msgstr ""
 "X-Crowdin-File: backend-conversations.pot\n"
 "X-Crowdin-File-ID: 26\n"

-#: activation_codes/admin.py:55 build/lib/activation_codes/admin.py:55
+#: activation_codes/admin.py:55
 msgid "Configuration"
 msgstr ""

-#: activation_codes/admin.py:66 build/lib/activation_codes/admin.py:66
+#: activation_codes/admin.py:66
 msgid "Usage details"
 msgstr ""

 #: activation_codes/admin.py:70 activation_codes/admin.py:226
-#: build/lib/activation_codes/admin.py:70
-#: build/lib/activation_codes/admin.py:226
 msgid "Timestamps"
 msgstr ""

-#: activation_codes/admin.py:109 build/lib/activation_codes/admin.py:109
+#: activation_codes/admin.py:109
 msgid "Usage"
 msgstr ""

-#: activation_codes/admin.py:117 build/lib/activation_codes/admin.py:117
+#: activation_codes/admin.py:117
 msgid "Description"
 msgstr ""

-#: activation_codes/admin.py:124 build/lib/activation_codes/admin.py:124
+#: activation_codes/admin.py:124
 msgid "No users have used this code yet"
 msgstr ""

-#: activation_codes/admin.py:135 build/lib/activation_codes/admin.py:135
+#: activation_codes/admin.py:135
 msgid "Name"
 msgstr ""

 #: activation_codes/admin.py:136 activation_codes/admin.py:246
-#: build/lib/activation_codes/admin.py:136
-#: build/lib/activation_codes/admin.py:246
 msgid "Email"
 msgstr ""

-#: activation_codes/admin.py:137 build/lib/activation_codes/admin.py:137
+#: activation_codes/admin.py:137
 msgid "Date"
 msgstr ""

-#: activation_codes/admin.py:161 build/lib/activation_codes/admin.py:161
+#: activation_codes/admin.py:161
 msgid "Users who used this code"
 msgstr ""

-#: activation_codes/admin.py:163 build/lib/activation_codes/admin.py:163
+#: activation_codes/admin.py:163
 msgid "Recompute current uses from related activations"
 msgstr ""

-#: activation_codes/admin.py:177 build/lib/activation_codes/admin.py:177
+#: activation_codes/admin.py:177
 msgid "All selected activation codes already have correct usage counts."
 msgstr ""

-#: activation_codes/admin.py:182 build/lib/activation_codes/admin.py:182
+#: activation_codes/admin.py:182
 #, python-format
 msgid "Successfully recomputed usage counts for %(count)d activation code(s)."
 msgstr ""

 #: activation_codes/admin.py:240 activation_codes/admin.py:284
-#: build/lib/activation_codes/admin.py:240
-#: build/lib/activation_codes/admin.py:284
 msgid "User"
 msgstr ""

-#: activation_codes/admin.py:291 build/lib/activation_codes/admin.py:291
+#: activation_codes/admin.py:291
 msgid "Has used activation code"
 msgstr ""

-#: activation_codes/admin.py:293 build/lib/activation_codes/admin.py:293
+#: activation_codes/admin.py:293
 msgid "Add selected users to Brevo waiting list"
 msgstr ""

-#: activation_codes/admin.py:314 build/lib/activation_codes/admin.py:314
+#: activation_codes/admin.py:314
 #, python-format
 msgid "Added %(count)d user(s) to Brevo waiting list."
 msgstr ""

 #: activation_codes/admin.py:319 activation_codes/admin.py:347
-#: build/lib/activation_codes/admin.py:319
-#: build/lib/activation_codes/admin.py:347
 msgid "No valid email address found in selected registrations."
 msgstr ""

-#: activation_codes/admin.py:323 build/lib/activation_codes/admin.py:323
+#: activation_codes/admin.py:323
 msgid "Remove selected users from Brevo waiting list"
 msgstr ""

-#: activation_codes/admin.py:342 build/lib/activation_codes/admin.py:342
+#: activation_codes/admin.py:342
 #, python-format
 msgid "Removed %(count)d user(s) from Brevo waiting list."
 msgstr ""

 #: activation_codes/models.py:38 activation_codes/models.py:85
-#: activation_codes/models.py:178 build/lib/activation_codes/models.py:38
-#: build/lib/activation_codes/models.py:85
-#: build/lib/activation_codes/models.py:178
+#: activation_codes/models.py:178
 msgid "activation code"
 msgstr ""

-#: activation_codes/models.py:39 build/lib/activation_codes/models.py:39
+#: activation_codes/models.py:39
 msgid "The activation code that users will enter"
 msgstr ""

-#: activation_codes/models.py:46 build/lib/activation_codes/models.py:46
+#: activation_codes/models.py:46
 msgid "Code must be alphanumeric and contain no spaces or special characters"
 msgstr ""

-#: activation_codes/models.py:52 build/lib/activation_codes/models.py:52
+#: activation_codes/models.py:52
 msgid "maximum uses"
 msgstr ""

-#: activation_codes/models.py:53 build/lib/activation_codes/models.py:53
+#: activation_codes/models.py:53
 msgid "Maximum number of times this code can be used. 0 means unlimited."
 msgstr ""

-#: activation_codes/models.py:58 build/lib/activation_codes/models.py:58
+#: activation_codes/models.py:58
 msgid "current uses"
 msgstr ""

-#: activation_codes/models.py:59 build/lib/activation_codes/models.py:59
+#: activation_codes/models.py:59
 msgid "Number of times this code has been used"
 msgstr ""

-#: activation_codes/models.py:65 build/lib/activation_codes/models.py:65
-#: build/lib/core/models.py:151 core/models.py:151
+#: activation_codes/models.py:65 core/models.py:154
 msgid "active"
 msgstr ""

-#: activation_codes/models.py:66 build/lib/activation_codes/models.py:66
+#: activation_codes/models.py:66
 msgid "Whether this code can still be used"
 msgstr ""

-#: activation_codes/models.py:71 build/lib/activation_codes/models.py:71
+#: activation_codes/models.py:71
 msgid "expires at"
 msgstr ""

-#: activation_codes/models.py:72 build/lib/activation_codes/models.py:72
+#: activation_codes/models.py:72
 msgid "Date and time when this code expires"
 msgstr ""

-#: activation_codes/models.py:78 build/lib/activation_codes/models.py:78
+#: activation_codes/models.py:78
 msgid "description"
 msgstr ""

-#: activation_codes/models.py:79 build/lib/activation_codes/models.py:79
+#: activation_codes/models.py:79
 msgid "Internal description or notes about this code"
 msgstr ""

-#: activation_codes/models.py:86 build/lib/activation_codes/models.py:86
+#: activation_codes/models.py:86
 msgid "activation codes"
 msgstr ""

-#: activation_codes/models.py:128 build/lib/activation_codes/models.py:128
+#: activation_codes/models.py:128
 msgid "This activation code is no longer valid"
 msgstr ""

-#: activation_codes/models.py:136 build/lib/activation_codes/models.py:136
+#: activation_codes/models.py:136
 msgid "You have already activated your account"
 msgstr ""

 #: activation_codes/models.py:170 activation_codes/models.py:202
-#: build/lib/activation_codes/models.py:170
-#: build/lib/activation_codes/models.py:202 build/lib/core/models.py:173
-#: core/models.py:173
+#: core/models.py:182
 msgid "user"
 msgstr ""

-#: activation_codes/models.py:171 build/lib/activation_codes/models.py:171
+#: activation_codes/models.py:171
 msgid "The user who used the activation code"
 msgstr ""

-#: activation_codes/models.py:179 build/lib/activation_codes/models.py:179
+#: activation_codes/models.py:179
 msgid "The activation code that was used"
 msgstr ""

 #: activation_codes/models.py:186 activation_codes/models.py:210
-#: build/lib/activation_codes/models.py:186
-#: build/lib/activation_codes/models.py:210
 msgid "user activation"
 msgstr ""

-#: activation_codes/models.py:187 build/lib/activation_codes/models.py:187
+#: activation_codes/models.py:187
 msgid "user activations"
 msgstr ""

-#: activation_codes/models.py:203 build/lib/activation_codes/models.py:203
+#: activation_codes/models.py:203
 msgid "The user who made the registration request"
 msgstr ""

-#: activation_codes/models.py:211 build/lib/activation_codes/models.py:211
+#: activation_codes/models.py:211
 msgid "Store if the user received an activation code and used it"
 msgstr ""

-#: activation_codes/models.py:220 build/lib/activation_codes/models.py:220
+#: activation_codes/models.py:220
 msgid "user registration request"
 msgstr ""

-#: activation_codes/models.py:221 build/lib/activation_codes/models.py:221
+#: activation_codes/models.py:221
 msgid "user registration requests"
 msgstr ""

 #: activation_codes/serializers.py:14
-#: build/lib/activation_codes/serializers.py:14
 msgid "The activation code to validate"
 msgstr ""

-#: activation_codes/viewsets.py:107 build/lib/activation_codes/viewsets.py:107
+#: activation_codes/viewsets.py:107
 msgid "Your account has been successfully activated"
 msgstr ""

-#: build/lib/chat/apps.py:12 chat/apps.py:12
+#: chat/apps.py:12
 msgid "chat application"
 msgstr ""

-#: build/lib/core/admin.py:26 core/admin.py:26
+#: core/admin.py:26
 msgid "Personal info"
 msgstr ""

-#: build/lib/core/admin.py:40 core/admin.py:40
+#: core/admin.py:40
 msgid "Permissions"
 msgstr ""

-#: build/lib/core/admin.py:52 core/admin.py:52
+#: core/admin.py:52
 msgid "Important dates"
 msgstr ""

-#: build/lib/core/models.py:39 core/models.py:39
+#: core/models.py:39
 msgid "id"
 msgstr ""

-#: build/lib/core/models.py:40 core/models.py:40
+#: core/models.py:40
 msgid "primary key for the record as UUID"
 msgstr ""

-#: build/lib/core/models.py:46 core/models.py:46
+#: core/models.py:46
 msgid "created on"
 msgstr ""

-#: build/lib/core/models.py:47 core/models.py:47
+#: core/models.py:47
 msgid "date and time at which a record was created"
 msgstr ""

-#: build/lib/core/models.py:52 core/models.py:52
+#: core/models.py:52
 msgid "updated on"
 msgstr ""

-#: build/lib/core/models.py:53 core/models.py:53
+#: core/models.py:53
 msgid "date and time at which a record was last updated"
 msgstr ""

-#: build/lib/core/models.py:86 core/models.py:86
+#: core/models.py:89
 msgid "We couldn't find a user with this sub but the email is already associated with a registered user."
 msgstr ""

-#: build/lib/core/models.py:99 core/models.py:99
+#: core/models.py:102
 msgid "Enter a valid sub. This value may contain only letters, numbers, and @/./+/-/_/: characters."
 msgstr ""

-#: build/lib/core/models.py:105 core/models.py:105
+#: core/models.py:108
 msgid "sub"
 msgstr ""

-#: build/lib/core/models.py:107 core/models.py:107
+#: core/models.py:110
 msgid "Required. 255 characters or fewer. Letters, numbers, and @/./+/-/_/: characters only."
 msgstr ""

-#: build/lib/core/models.py:116 core/models.py:116
+#: core/models.py:119
 msgid "full name"
 msgstr ""

-#: build/lib/core/models.py:117 core/models.py:117
+#: core/models.py:120
 msgid "short name"
 msgstr ""

-#: build/lib/core/models.py:119 core/models.py:119
+#: core/models.py:122
 msgid "identity email address"
 msgstr ""

-#: build/lib/core/models.py:123 core/models.py:123
+#: core/models.py:126
 msgid "admin email address"
 msgstr ""

-#: build/lib/core/models.py:129 core/models.py:129
+#: core/models.py:132
 msgid "language"
 msgstr ""

-#: build/lib/core/models.py:130 core/models.py:130
+#: core/models.py:133
 msgid "The language in which the user wants to see the interface."
 msgstr ""

-#: build/lib/core/models.py:138 core/models.py:138
+#: core/models.py:141
 msgid "The timezone in which the user wants to see times."
 msgstr ""

-#: build/lib/core/models.py:141 core/models.py:141
+#: core/models.py:144
 msgid "device"
 msgstr ""

-#: build/lib/core/models.py:143 core/models.py:143
+#: core/models.py:146
 msgid "Whether the user is a device or a real user."
 msgstr ""

-#: build/lib/core/models.py:146 core/models.py:146
+#: core/models.py:149
 msgid "staff status"
 msgstr ""

-#: build/lib/core/models.py:148 core/models.py:148
+#: core/models.py:151
 msgid "Whether the user can log into this admin site."
 msgstr ""

-#: build/lib/core/models.py:154 core/models.py:154
+#: core/models.py:157
 msgid "Whether this user should be treated as active. Unselect this instead of deleting accounts."
 msgstr ""

-#: build/lib/core/models.py:161 core/models.py:161
+#: core/models.py:164
 msgid "allow conversation analytics"
 msgstr ""

-#: build/lib/core/models.py:163 core/models.py:163
+#: core/models.py:166
 msgid "Whether the user allows to use their conversations for analytics."
 msgstr ""

-#: build/lib/core/models.py:174 core/models.py:174
+#: core/models.py:170
+msgid "allow smart web search"
+msgstr ""
+
+#: core/models.py:172
+msgid "Whether the user allows to use smart web search features."
+msgstr ""
+
+#: core/models.py:183
 msgid "users"
 msgstr ""

@@ -2,8 +2,8 @@ msgid ""
 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: 2025-11-17 16:37\n"
+"POT-Creation-Date: 2026-02-26 21:42+0000\n"
+"PO-Revision-Date: 2026-03-11 15:23\n"
 "Last-Translator: \n"
 "Language-Team: French\n"
 "Language: fr_FR\n"
@@ -17,328 +17,320 @@ msgstr ""
 "X-Crowdin-File: backend-conversations.pot\n"
 "X-Crowdin-File-ID: 26\n"

-#: activation_codes/admin.py:55 build/lib/activation_codes/admin.py:55
+#: activation_codes/admin.py:55
 msgid "Configuration"
 msgstr "Configuration"

-#: activation_codes/admin.py:66 build/lib/activation_codes/admin.py:66
+#: activation_codes/admin.py:66
 msgid "Usage details"
 msgstr "Détails d'utilisation"

 #: activation_codes/admin.py:70 activation_codes/admin.py:226
-#: build/lib/activation_codes/admin.py:70
-#: build/lib/activation_codes/admin.py:226
 msgid "Timestamps"
 msgstr "Horodatages"

-#: activation_codes/admin.py:109 build/lib/activation_codes/admin.py:109
+#: activation_codes/admin.py:109
 msgid "Usage"
 msgstr "Utilisation"

-#: activation_codes/admin.py:117 build/lib/activation_codes/admin.py:117
+#: activation_codes/admin.py:117
 msgid "Description"
 msgstr "Description"

-#: activation_codes/admin.py:124 build/lib/activation_codes/admin.py:124
+#: activation_codes/admin.py:124
 msgid "No users have used this code yet"
 msgstr "Aucun utilisateur n'a encore utilisé ce code"

-#: activation_codes/admin.py:135 build/lib/activation_codes/admin.py:135
+#: activation_codes/admin.py:135
 msgid "Name"
 msgstr "Nom"

 #: activation_codes/admin.py:136 activation_codes/admin.py:246
-#: build/lib/activation_codes/admin.py:136
-#: build/lib/activation_codes/admin.py:246
 msgid "Email"
 msgstr "E-mail"

-#: activation_codes/admin.py:137 build/lib/activation_codes/admin.py:137
+#: activation_codes/admin.py:137
 msgid "Date"
 msgstr "Date"

-#: activation_codes/admin.py:161 build/lib/activation_codes/admin.py:161
+#: activation_codes/admin.py:161
 msgid "Users who used this code"
 msgstr "Utilisateurs qui ont utilisé ce code"

-#: activation_codes/admin.py:163 build/lib/activation_codes/admin.py:163
+#: activation_codes/admin.py:163
 msgid "Recompute current uses from related activations"
 msgstr "Recalculer les utilisations actuelles à partir des activations liées"

-#: activation_codes/admin.py:177 build/lib/activation_codes/admin.py:177
+#: activation_codes/admin.py:177
 msgid "All selected activation codes already have correct usage counts."
 msgstr "Tous les codes d'activation sélectionnés ont déjà un nombre correct d'utilisations."

-#: activation_codes/admin.py:182 build/lib/activation_codes/admin.py:182
+#: activation_codes/admin.py:182
 #, python-format
 msgid "Successfully recomputed usage counts for %(count)d activation code(s)."
 msgstr "Utilisation recalculée avec succès pour %(count)d code(s) d'activation."

 #: activation_codes/admin.py:240 activation_codes/admin.py:284
-#: build/lib/activation_codes/admin.py:240
-#: build/lib/activation_codes/admin.py:284
 msgid "User"
 msgstr "Utilisateur"

-#: activation_codes/admin.py:291 build/lib/activation_codes/admin.py:291
+#: activation_codes/admin.py:291
 msgid "Has used activation code"
 msgstr "A utilisé le code d'activation"

-#: activation_codes/admin.py:293 build/lib/activation_codes/admin.py:293
+#: activation_codes/admin.py:293
 msgid "Add selected users to Brevo waiting list"
 msgstr "Ajouter les utilisateurs sélectionnés à la liste d'attente Brevo"

-#: activation_codes/admin.py:314 build/lib/activation_codes/admin.py:314
+#: activation_codes/admin.py:314
 #, python-format
 msgid "Added %(count)d user(s) to Brevo waiting list."
 msgstr "%(count)d utilisateur(s) ajoutés à la liste d'attente Brevo."

 #: activation_codes/admin.py:319 activation_codes/admin.py:347
-#: build/lib/activation_codes/admin.py:319
-#: build/lib/activation_codes/admin.py:347
 msgid "No valid email address found in selected registrations."
 msgstr "Aucune adresse e-mail valide trouvée dans les inscriptions sélectionnées."

-#: activation_codes/admin.py:323 build/lib/activation_codes/admin.py:323
+#: activation_codes/admin.py:323
 msgid "Remove selected users from Brevo waiting list"
 msgstr "Supprimer les utilisateurs sélectionnés de la liste d'attente Brevo"

-#: activation_codes/admin.py:342 build/lib/activation_codes/admin.py:342
+#: activation_codes/admin.py:342
 #, python-format
 msgid "Removed %(count)d user(s) from Brevo waiting list."
 msgstr "Suppression de %(count)d utilisateur(s) de la liste d'attente Brevo."

 #: activation_codes/models.py:38 activation_codes/models.py:85
-#: activation_codes/models.py:178 build/lib/activation_codes/models.py:38
-#: build/lib/activation_codes/models.py:85
-#: build/lib/activation_codes/models.py:178
+#: activation_codes/models.py:178
 msgid "activation code"
 msgstr "code d'activation"

-#: activation_codes/models.py:39 build/lib/activation_codes/models.py:39
+#: activation_codes/models.py:39
 msgid "The activation code that users will enter"
 msgstr "Le code d'activation que les utilisateurs entreront"

-#: activation_codes/models.py:46 build/lib/activation_codes/models.py:46
+#: activation_codes/models.py:46
 msgid "Code must be alphanumeric and contain no spaces or special characters"
 msgstr "Le code doit être alphanumérique et ne contenir ni espaces ni caractères spéciaux"

-#: activation_codes/models.py:52 build/lib/activation_codes/models.py:52
+#: activation_codes/models.py:52
 msgid "maximum uses"
 msgstr "utilisations maximales"

-#: activation_codes/models.py:53 build/lib/activation_codes/models.py:53
+#: activation_codes/models.py:53
 msgid "Maximum number of times this code can be used. 0 means unlimited."
 msgstr "Nombre maximum d'utilisation de ce code. 0 signifie illimité."

-#: activation_codes/models.py:58 build/lib/activation_codes/models.py:58
+#: activation_codes/models.py:58
 msgid "current uses"
 msgstr "utilisations actuelles"

-#: activation_codes/models.py:59 build/lib/activation_codes/models.py:59
+#: activation_codes/models.py:59
 msgid "Number of times this code has been used"
 msgstr "Nombre de fois où ce code a été utilisé"

-#: activation_codes/models.py:65 build/lib/activation_codes/models.py:65
-#: build/lib/core/models.py:151 core/models.py:151
+#: activation_codes/models.py:65 core/models.py:154
 msgid "active"
 msgstr "actif"

-#: activation_codes/models.py:66 build/lib/activation_codes/models.py:66
+#: activation_codes/models.py:66
 msgid "Whether this code can still be used"
 msgstr "Si ce code peut encore être utilisé"

-#: activation_codes/models.py:71 build/lib/activation_codes/models.py:71
+#: activation_codes/models.py:71
 msgid "expires at"
 msgstr "expiration"

-#: activation_codes/models.py:72 build/lib/activation_codes/models.py:72
+#: activation_codes/models.py:72
 msgid "Date and time when this code expires"
 msgstr "Date et heure d'expiration de ce code"

-#: activation_codes/models.py:78 build/lib/activation_codes/models.py:78
+#: activation_codes/models.py:78
 msgid "description"
 msgstr "description"

-#: activation_codes/models.py:79 build/lib/activation_codes/models.py:79
+#: activation_codes/models.py:79
 msgid "Internal description or notes about this code"
 msgstr "Description interne ou notes à propos de ce code"

-#: activation_codes/models.py:86 build/lib/activation_codes/models.py:86
+#: activation_codes/models.py:86
 msgid "activation codes"
 msgstr "codes d'activation"

-#: activation_codes/models.py:128 build/lib/activation_codes/models.py:128
+#: activation_codes/models.py:128
 msgid "This activation code is no longer valid"
 msgstr "Ce code d'activation n'est plus valide"

-#: activation_codes/models.py:136 build/lib/activation_codes/models.py:136
+#: activation_codes/models.py:136
 msgid "You have already activated your account"
 msgstr "Vous avez déjà activé votre compte"

 #: activation_codes/models.py:170 activation_codes/models.py:202
-#: build/lib/activation_codes/models.py:170
-#: build/lib/activation_codes/models.py:202 build/lib/core/models.py:173
-#: core/models.py:173
+#: core/models.py:182
 msgid "user"
 msgstr "utilisateur"

-#: activation_codes/models.py:171 build/lib/activation_codes/models.py:171
+#: activation_codes/models.py:171
 msgid "The user who used the activation code"
 msgstr "L'utilisateur qui a utilisé le code d'activation"

-#: activation_codes/models.py:179 build/lib/activation_codes/models.py:179
+#: activation_codes/models.py:179
 msgid "The activation code that was used"
 msgstr "Le code d'activation qui a été utilisé"

 #: activation_codes/models.py:186 activation_codes/models.py:210
-#: build/lib/activation_codes/models.py:186
-#: build/lib/activation_codes/models.py:210
 msgid "user activation"
 msgstr "activation d'utilisateur"

-#: activation_codes/models.py:187 build/lib/activation_codes/models.py:187
+#: activation_codes/models.py:187
 msgid "user activations"
 msgstr "activations d'utilisateurs"

-#: activation_codes/models.py:203 build/lib/activation_codes/models.py:203
+#: activation_codes/models.py:203
 msgid "The user who made the registration request"
 msgstr "L'utilisateur qui a fait la demande d'enregistrement"

-#: activation_codes/models.py:211 build/lib/activation_codes/models.py:211
+#: activation_codes/models.py:211
 msgid "Store if the user received an activation code and used it"
 msgstr "Enregistrer si l'utilisateur a reçu un code d'activation et l'a utilisé"

-#: activation_codes/models.py:220 build/lib/activation_codes/models.py:220
+#: activation_codes/models.py:220
 msgid "user registration request"
 msgstr "demande d'inscription d'utilisateur"

-#: activation_codes/models.py:221 build/lib/activation_codes/models.py:221
+#: activation_codes/models.py:221
 msgid "user registration requests"
 msgstr "demandes d'inscription d'utilisateur"

 #: activation_codes/serializers.py:14
-#: build/lib/activation_codes/serializers.py:14
 msgid "The activation code to validate"
 msgstr "Le code d'activation à valider"

-#: activation_codes/viewsets.py:107 build/lib/activation_codes/viewsets.py:107
+#: activation_codes/viewsets.py:107
 msgid "Your account has been successfully activated"
 msgstr "Votre compte a été activé avec succès"

-#: build/lib/chat/apps.py:12 chat/apps.py:12
+#: chat/apps.py:12
 msgid "chat application"
 msgstr "application de chat"

-#: build/lib/core/admin.py:26 core/admin.py:26
+#: core/admin.py:26
 msgid "Personal info"
 msgstr "Informations personnelles"

-#: build/lib/core/admin.py:40 core/admin.py:40
+#: core/admin.py:40
 msgid "Permissions"
 msgstr "Permissions"

-#: build/lib/core/admin.py:52 core/admin.py:52
+#: core/admin.py:52
 msgid "Important dates"
 msgstr "Dates importantes"

-#: build/lib/core/models.py:39 core/models.py:39
+#: core/models.py:39
 msgid "id"
 msgstr "id"

-#: build/lib/core/models.py:40 core/models.py:40
+#: core/models.py:40
 msgid "primary key for the record as UUID"
 msgstr "clé primaire pour l'enregistrement en tant que UUID"

-#: build/lib/core/models.py:46 core/models.py:46
+#: core/models.py:46
 msgid "created on"
 msgstr "créé le"

-#: build/lib/core/models.py:47 core/models.py:47
+#: core/models.py:47
 msgid "date and time at which a record was created"
 msgstr "date et heure de création de l'enregistrement"

-#: build/lib/core/models.py:52 core/models.py:52
+#: core/models.py:52
 msgid "updated on"
 msgstr "mis à jour le"

-#: build/lib/core/models.py:53 core/models.py:53
+#: core/models.py:53
 msgid "date and time at which a record was last updated"
 msgstr "date et heure de la dernière mise à jour de l'enregistrement"

-#: build/lib/core/models.py:86 core/models.py:86
+#: core/models.py:89
 msgid "We couldn't find a user with this sub but the email is already associated with a registered user."
 msgstr "Nous n'avons pas pu trouver un utilisateur avec ce sous-groupe mais l'e-mail est déjà associé à un utilisateur enregistré."

-#: build/lib/core/models.py:99 core/models.py:99
+#: core/models.py:102
 msgid "Enter a valid sub. This value may contain only letters, numbers, and @/./+/-/_/: characters."
 msgstr "Saisissez un 'sub' valide. Cette valeur ne peut contenir que des lettres, des chiffres et les caractères @/./+/-/_/: uniquement."

-#: build/lib/core/models.py:105 core/models.py:105
+#: core/models.py:108
 msgid "sub"
 msgstr "sub"

-#: build/lib/core/models.py:107 core/models.py:107
+#: core/models.py:110
 msgid "Required. 255 characters or fewer. Letters, numbers, and @/./+/-/_/: characters only."
 msgstr "Obligatoire. 255 caractères ou moins. Lettres, chiffres et caractères @/./+/-/_/: uniquement."

-#: build/lib/core/models.py:116 core/models.py:116
+#: core/models.py:119
 msgid "full name"
 msgstr "nom complet"

-#: build/lib/core/models.py:117 core/models.py:117
+#: core/models.py:120
 msgid "short name"
 msgstr "nom court"

-#: build/lib/core/models.py:119 core/models.py:119
+#: core/models.py:122
 msgid "identity email address"
 msgstr "adresse e-mail d'identité"

-#: build/lib/core/models.py:123 core/models.py:123
+#: core/models.py:126
 msgid "admin email address"
 msgstr "adresse e-mail de l'administrateur"

-#: build/lib/core/models.py:129 core/models.py:129
+#: core/models.py:132
 msgid "language"
 msgstr "langue"

-#: build/lib/core/models.py:130 core/models.py:130
+#: core/models.py:133
 msgid "The language in which the user wants to see the interface."
 msgstr "La langue dans laquelle l'utilisateur veut voir l'interface."

-#: build/lib/core/models.py:138 core/models.py:138
+#: core/models.py:141
 msgid "The timezone in which the user wants to see times."
 msgstr "Le fuseau horaire dans lequel l'utilisateur souhaite voir les heures."

-#: build/lib/core/models.py:141 core/models.py:141
+#: core/models.py:144
 msgid "device"
 msgstr "appareil"

-#: build/lib/core/models.py:143 core/models.py:143
+#: core/models.py:146
 msgid "Whether the user is a device or a real user."
 msgstr "Si l'utilisateur est un appareil ou un utilisateur réel."

-#: build/lib/core/models.py:146 core/models.py:146
+#: core/models.py:149
 msgid "staff status"
 msgstr "statut d'équipe"

-#: build/lib/core/models.py:148 core/models.py:148
+#: core/models.py:151
 msgid "Whether the user can log into this admin site."
 msgstr "Si l'utilisateur peut se connecter à ce site d'administration."

-#: build/lib/core/models.py:154 core/models.py:154
+#: core/models.py:157
 msgid "Whether this user should be treated as active. Unselect this instead of deleting accounts."
 msgstr "Si cet utilisateur doit être traité comme actif. Désélectionnez ceci au lieu de supprimer des comptes."

-#: build/lib/core/models.py:161 core/models.py:161
+#: core/models.py:164
 msgid "allow conversation analytics"
 msgstr "autoriser les analyses de conversation"

-#: build/lib/core/models.py:163 core/models.py:163
+#: core/models.py:166
 msgid "Whether the user allows to use their conversations for analytics."
 msgstr "Si l'utilisateur autorise l'utilisation de ses conversations pour des analyses."

-#: build/lib/core/models.py:174 core/models.py:174
+#: core/models.py:170
+msgid "allow smart web search"
+msgstr "autoriser la recherche intelligente sur le web"
+
+#: core/models.py:172
+msgid "Whether the user allows to use smart web search features."
+msgstr "Si l'utilisateur autorise l'utilisation de fonctions de recherche intelligente sur le Web."
+
+#: core/models.py:183
 msgid "users"
 msgstr "utilisateurs"

@@ -2,8 +2,8 @@ msgid ""
 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: 2025-11-17 16:37\n"
+"POT-Creation-Date: 2026-02-26 21:42+0000\n"
+"PO-Revision-Date: 2026-03-11 15:23\n"
 "Last-Translator: \n"
 "Language-Team: Dutch\n"
 "Language: nl_NL\n"
@@ -17,328 +17,320 @@ msgstr ""
 "X-Crowdin-File: backend-conversations.pot\n"
 "X-Crowdin-File-ID: 26\n"

-#: activation_codes/admin.py:55 build/lib/activation_codes/admin.py:55
+#: activation_codes/admin.py:55
 msgid "Configuration"
 msgstr "Configuratie"

-#: activation_codes/admin.py:66 build/lib/activation_codes/admin.py:66
+#: activation_codes/admin.py:66
 msgid "Usage details"
 msgstr "Gebruiksdetails"

 #: activation_codes/admin.py:70 activation_codes/admin.py:226
-#: build/lib/activation_codes/admin.py:70
-#: build/lib/activation_codes/admin.py:226
 msgid "Timestamps"
 msgstr "Tijdstempels"

-#: activation_codes/admin.py:109 build/lib/activation_codes/admin.py:109
+#: activation_codes/admin.py:109
 msgid "Usage"
 msgstr "Gebruik"

-#: activation_codes/admin.py:117 build/lib/activation_codes/admin.py:117
+#: activation_codes/admin.py:117
 msgid "Description"
 msgstr "Beschrijving"

-#: activation_codes/admin.py:124 build/lib/activation_codes/admin.py:124
+#: activation_codes/admin.py:124
 msgid "No users have used this code yet"
 msgstr "Er zijn nog geen gebruikers die deze code hebben gebruikt"

-#: activation_codes/admin.py:135 build/lib/activation_codes/admin.py:135
+#: activation_codes/admin.py:135
 msgid "Name"
 msgstr "Naam"

 #: activation_codes/admin.py:136 activation_codes/admin.py:246
-#: build/lib/activation_codes/admin.py:136
-#: build/lib/activation_codes/admin.py:246
 msgid "Email"
 msgstr "E-mail"

-#: activation_codes/admin.py:137 build/lib/activation_codes/admin.py:137
+#: activation_codes/admin.py:137
 msgid "Date"
 msgstr "Datum"

-#: activation_codes/admin.py:161 build/lib/activation_codes/admin.py:161
+#: activation_codes/admin.py:161
 msgid "Users who used this code"
 msgstr "Gebruikers die deze code hebben gebruikt"

-#: activation_codes/admin.py:163 build/lib/activation_codes/admin.py:163
+#: activation_codes/admin.py:163
 msgid "Recompute current uses from related activations"
 msgstr "Herbereken het huidige gebruik van gerelateerde activeringen"

-#: activation_codes/admin.py:177 build/lib/activation_codes/admin.py:177
+#: activation_codes/admin.py:177
 msgid "All selected activation codes already have correct usage counts."
 msgstr "Alle geselecteerde activeringscodes hebben al het juiste gebruiksaantal."

-#: activation_codes/admin.py:182 build/lib/activation_codes/admin.py:182
+#: activation_codes/admin.py:182
 #, python-format
 msgid "Successfully recomputed usage counts for %(count)d activation code(s)."
 msgstr "Het gebruik van %(count)d activeringscode(s) is opnieuw berekend."

 #: activation_codes/admin.py:240 activation_codes/admin.py:284
-#: build/lib/activation_codes/admin.py:240
-#: build/lib/activation_codes/admin.py:284
 msgid "User"
 msgstr "Gebruiker"

-#: activation_codes/admin.py:291 build/lib/activation_codes/admin.py:291
+#: activation_codes/admin.py:291
 msgid "Has used activation code"
 msgstr "Heeft activeringscode gebruikt"

-#: activation_codes/admin.py:293 build/lib/activation_codes/admin.py:293
+#: activation_codes/admin.py:293
 msgid "Add selected users to Brevo waiting list"
 msgstr "Voeg geselecteerde gebruikers toe aan de Brevo-wachtlijst"

-#: activation_codes/admin.py:314 build/lib/activation_codes/admin.py:314
+#: activation_codes/admin.py:314
 #, python-format
 msgid "Added %(count)d user(s) to Brevo waiting list."
 msgstr "%(count)d gebruiker(s) toegevoegd aan de Brevo-wachtlijst."

 #: activation_codes/admin.py:319 activation_codes/admin.py:347
-#: build/lib/activation_codes/admin.py:319
-#: build/lib/activation_codes/admin.py:347
 msgid "No valid email address found in selected registrations."
 msgstr "Er is geen geldig e-mailadres gevonden in de geselecteerde registraties."

-#: activation_codes/admin.py:323 build/lib/activation_codes/admin.py:323
+#: activation_codes/admin.py:323
 msgid "Remove selected users from Brevo waiting list"
 msgstr "Geselecteerde gebruikers van de Brevo-wachtlijst verwijderen"

-#: activation_codes/admin.py:342 build/lib/activation_codes/admin.py:342
+#: activation_codes/admin.py:342
 #, python-format
 msgid "Removed %(count)d user(s) from Brevo waiting list."
 msgstr "%(count)d gebruiker(s) verwijderd van de Brevo-wachtlijst."

 #: activation_codes/models.py:38 activation_codes/models.py:85
-#: activation_codes/models.py:178 build/lib/activation_codes/models.py:38
-#: build/lib/activation_codes/models.py:85
-#: build/lib/activation_codes/models.py:178
+#: activation_codes/models.py:178
 msgid "activation code"
 msgstr "activeringscode"

-#: activation_codes/models.py:39 build/lib/activation_codes/models.py:39
+#: activation_codes/models.py:39
 msgid "The activation code that users will enter"
 msgstr "De activeringscode die gebruikers invoeren"

-#: activation_codes/models.py:46 build/lib/activation_codes/models.py:46
+#: activation_codes/models.py:46
 msgid "Code must be alphanumeric and contain no spaces or special characters"
 msgstr "De code moet alfanumeriek zijn en mag geen spaties of speciale tekens bevatten"

-#: activation_codes/models.py:52 build/lib/activation_codes/models.py:52
+#: activation_codes/models.py:52
 msgid "maximum uses"
 msgstr "maximaal gebruik"

-#: activation_codes/models.py:53 build/lib/activation_codes/models.py:53
+#: activation_codes/models.py:53
 msgid "Maximum number of times this code can be used. 0 means unlimited."
 msgstr "Maximaal aantal keren dat deze code kan worden gebruikt. 0 betekent onbeperkt."

-#: activation_codes/models.py:58 build/lib/activation_codes/models.py:58
+#: activation_codes/models.py:58
 msgid "current uses"
 msgstr "huidig gebruik"

-#: activation_codes/models.py:59 build/lib/activation_codes/models.py:59
+#: activation_codes/models.py:59
 msgid "Number of times this code has been used"
 msgstr "Aantal keren dat deze code is gebruikt"

-#: activation_codes/models.py:65 build/lib/activation_codes/models.py:65
-#: build/lib/core/models.py:151 core/models.py:151
+#: activation_codes/models.py:65 core/models.py:154
 msgid "active"
 msgstr "actief"

-#: activation_codes/models.py:66 build/lib/activation_codes/models.py:66
+#: activation_codes/models.py:66
 msgid "Whether this code can still be used"
 msgstr "Of deze code nog gebruikt kan worden"

-#: activation_codes/models.py:71 build/lib/activation_codes/models.py:71
+#: activation_codes/models.py:71
 msgid "expires at"
 msgstr "vervalt op"

-#: activation_codes/models.py:72 build/lib/activation_codes/models.py:72
+#: activation_codes/models.py:72
 msgid "Date and time when this code expires"
 msgstr "Datum en tijd waarop deze code verloopt"

-#: activation_codes/models.py:78 build/lib/activation_codes/models.py:78
+#: activation_codes/models.py:78
 msgid "description"
 msgstr "beschrijving"

-#: activation_codes/models.py:79 build/lib/activation_codes/models.py:79
+#: activation_codes/models.py:79
 msgid "Internal description or notes about this code"
 msgstr "Interne beschrijving of notities over deze code"

-#: activation_codes/models.py:86 build/lib/activation_codes/models.py:86
+#: activation_codes/models.py:86
 msgid "activation codes"
 msgstr "activeringscodes"

-#: activation_codes/models.py:128 build/lib/activation_codes/models.py:128
+#: activation_codes/models.py:128
 msgid "This activation code is no longer valid"
 msgstr "Deze activeringscode is niet meer geldig"

-#: activation_codes/models.py:136 build/lib/activation_codes/models.py:136
+#: activation_codes/models.py:136
 msgid "You have already activated your account"
 msgstr "Je hebt je account al geactiveerd"

 #: activation_codes/models.py:170 activation_codes/models.py:202
-#: build/lib/activation_codes/models.py:170
-#: build/lib/activation_codes/models.py:202 build/lib/core/models.py:173
-#: core/models.py:173
+#: core/models.py:182
 msgid "user"
 msgstr "gebruiker"

-#: activation_codes/models.py:171 build/lib/activation_codes/models.py:171
+#: activation_codes/models.py:171
 msgid "The user who used the activation code"
 msgstr "De gebruiker die de activeringscode heeft gebruikt"

-#: activation_codes/models.py:179 build/lib/activation_codes/models.py:179
+#: activation_codes/models.py:179
 msgid "The activation code that was used"
 msgstr "De activeringscode die is gebruikt"

 #: activation_codes/models.py:186 activation_codes/models.py:210
-#: build/lib/activation_codes/models.py:186
-#: build/lib/activation_codes/models.py:210
 msgid "user activation"
 msgstr "gebruikers activering"

-#: activation_codes/models.py:187 build/lib/activation_codes/models.py:187
+#: activation_codes/models.py:187
 msgid "user activations"
 msgstr "gebruikersactivaties"

-#: activation_codes/models.py:203 build/lib/activation_codes/models.py:203
+#: activation_codes/models.py:203
 msgid "The user who made the registration request"
 msgstr "De gebruiker die het registratieverzoek heeft gedaan"

-#: activation_codes/models.py:211 build/lib/activation_codes/models.py:211
+#: activation_codes/models.py:211
 msgid "Store if the user received an activation code and used it"
 msgstr "Opslaan of de gebruiker een activeringscode heeft ontvangen en deze heeft gebruikt"

-#: activation_codes/models.py:220 build/lib/activation_codes/models.py:220
+#: activation_codes/models.py:220
 msgid "user registration request"
 msgstr "gebruikersregistratieverzoek"

-#: activation_codes/models.py:221 build/lib/activation_codes/models.py:221
+#: activation_codes/models.py:221
 msgid "user registration requests"
 msgstr "gebruikersregistratieverzoeken"

 #: activation_codes/serializers.py:14
-#: build/lib/activation_codes/serializers.py:14
 msgid "The activation code to validate"
 msgstr "De activeringscode om te valideren"

-#: activation_codes/viewsets.py:107 build/lib/activation_codes/viewsets.py:107
+#: activation_codes/viewsets.py:107
 msgid "Your account has been successfully activated"
 msgstr "Uw account is succesvol geactiveerd"

-#: build/lib/chat/apps.py:12 chat/apps.py:12
+#: chat/apps.py:12
 msgid "chat application"
 msgstr "chatapplicatie"

-#: build/lib/core/admin.py:26 core/admin.py:26
+#: core/admin.py:26
 msgid "Personal info"
 msgstr "Persoonlijke gegevens"

-#: build/lib/core/admin.py:40 core/admin.py:40
+#: core/admin.py:40
 msgid "Permissions"
 msgstr "Machtigingen"

-#: build/lib/core/admin.py:52 core/admin.py:52
+#: core/admin.py:52
 msgid "Important dates"
 msgstr "Belangrijke data"

-#: build/lib/core/models.py:39 core/models.py:39
+#: core/models.py:39
 msgid "id"
 msgstr "id"

-#: build/lib/core/models.py:40 core/models.py:40
+#: core/models.py:40
 msgid "primary key for the record as UUID"
 msgstr "primaire sleutel voor het record als UUID"

-#: build/lib/core/models.py:46 core/models.py:46
+#: core/models.py:46
 msgid "created on"
 msgstr "gemaakt op"

-#: build/lib/core/models.py:47 core/models.py:47
+#: core/models.py:47
 msgid "date and time at which a record was created"
 msgstr "datum en tijd waarop een record is aangemaakt"

-#: build/lib/core/models.py:52 core/models.py:52
+#: core/models.py:52
 msgid "updated on"
 msgstr "bijgewerkt op"

-#: build/lib/core/models.py:53 core/models.py:53
+#: core/models.py:53
 msgid "date and time at which a record was last updated"
 msgstr "datum en tijd waarop een record voor het laatst is bijgewerkt"

-#: build/lib/core/models.py:86 core/models.py:86
+#: core/models.py:89
 msgid "We couldn't find a user with this sub but the email is already associated with a registered user."
 msgstr "We konden geen gebruiker met dit e-mailadres vinden, maar het e-mailadres is al gekoppeld aan een geregistreerde gebruiker."

-#: build/lib/core/models.py:99 core/models.py:99
+#: core/models.py:102
 msgid "Enter a valid sub. This value may contain only letters, numbers, and @/./+/-/_/: characters."
 msgstr "Voer een geldig subsubtype in. Deze waarde mag alleen letters, cijfers en @/./+/-/_/:-tekens bevatten."

-#: build/lib/core/models.py:105 core/models.py:105
+#: core/models.py:108
 msgid "sub"
 msgstr "id"

-#: build/lib/core/models.py:107 core/models.py:107
+#: core/models.py:110
 msgid "Required. 255 characters or fewer. Letters, numbers, and @/./+/-/_/: characters only."
 msgstr "Verplicht. Maximaal 255 tekens. Alleen letters, cijfers en @/./+/-/_/: tekens."

-#: build/lib/core/models.py:116 core/models.py:116
+#: core/models.py:119
 msgid "full name"
 msgstr "volledige naam"

-#: build/lib/core/models.py:117 core/models.py:117
+#: core/models.py:120
 msgid "short name"
 msgstr "korte naam"

-#: build/lib/core/models.py:119 core/models.py:119
+#: core/models.py:122
 msgid "identity email address"
 msgstr "identiteits e-mailadres"

-#: build/lib/core/models.py:123 core/models.py:123
+#: core/models.py:126
 msgid "admin email address"
 msgstr "beheerders e-mailadres"

-#: build/lib/core/models.py:129 core/models.py:129
+#: core/models.py:132
 msgid "language"
 msgstr "taal"

-#: build/lib/core/models.py:130 core/models.py:130
+#: core/models.py:133
 msgid "The language in which the user wants to see the interface."
 msgstr "De taal waarin de gebruiker de interface wil zien."

-#: build/lib/core/models.py:138 core/models.py:138
+#: core/models.py:141
 msgid "The timezone in which the user wants to see times."
 msgstr "De tijdzone waarin de gebruiker de tijden wil zien."

-#: build/lib/core/models.py:141 core/models.py:141
+#: core/models.py:144
 msgid "device"
 msgstr "apparaat"

-#: build/lib/core/models.py:143 core/models.py:143
+#: core/models.py:146
 msgid "Whether the user is a device or a real user."
 msgstr "Of de gebruiker een apparaat of een echte gebruiker is."

-#: build/lib/core/models.py:146 core/models.py:146
+#: core/models.py:149
 msgid "staff status"
 msgstr "personeelsstatus"

-#: build/lib/core/models.py:148 core/models.py:148
+#: core/models.py:151
 msgid "Whether the user can log into this admin site."
 msgstr "Of de gebruiker kan inloggen op deze beheersite."

-#: build/lib/core/models.py:154 core/models.py:154
+#: core/models.py:157
 msgid "Whether this user should be treated as active. Unselect this instead of deleting accounts."
 msgstr "Of deze gebruiker als actief moet worden beschouwd. Deselecteer dit in plaats van accounts te verwijderen."

-#: build/lib/core/models.py:161 core/models.py:161
+#: core/models.py:164
 msgid "allow conversation analytics"
 msgstr "conversatieanalyse toestaan"

-#: build/lib/core/models.py:163 core/models.py:163
+#: core/models.py:166
 msgid "Whether the user allows to use their conversations for analytics."
 msgstr "Of de gebruiker toestaat dat zijn/haar gesprekken voor analyses worden gebruikt."

-#: build/lib/core/models.py:174 core/models.py:174
+#: core/models.py:170
+msgid "allow smart web search"
+msgstr "smart web zoeken toestaan"
+
+#: core/models.py:172
+msgid "Whether the user allows to use smart web search features."
+msgstr "Of de gebruiker toestemming geeft om smart web zoekfuncties te gebruiken."
+
+#: core/models.py:183
 msgid "users"
 msgstr "gebruikers"

@@ -2,8 +2,8 @@ msgid ""
 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: 2025-11-17 16:37\n"
+"POT-Creation-Date: 2026-02-26 21:42+0000\n"
+"PO-Revision-Date: 2026-03-11 15:23\n"
 "Last-Translator: \n"
 "Language-Team: Russian\n"
 "Language: ru_RU\n"
@@ -17,328 +17,320 @@ msgstr ""
 "X-Crowdin-File: backend-conversations.pot\n"
 "X-Crowdin-File-ID: 26\n"

-#: activation_codes/admin.py:55 build/lib/activation_codes/admin.py:55
+#: activation_codes/admin.py:55
 msgid "Configuration"
 msgstr "Настройки"

-#: activation_codes/admin.py:66 build/lib/activation_codes/admin.py:66
+#: activation_codes/admin.py:66
 msgid "Usage details"
 msgstr "Сведения об использовании"

 #: activation_codes/admin.py:70 activation_codes/admin.py:226
-#: build/lib/activation_codes/admin.py:70
-#: build/lib/activation_codes/admin.py:226
 msgid "Timestamps"
 msgstr "Временные метки"

-#: activation_codes/admin.py:109 build/lib/activation_codes/admin.py:109
+#: activation_codes/admin.py:109
 msgid "Usage"
 msgstr "Использование"

-#: activation_codes/admin.py:117 build/lib/activation_codes/admin.py:117
+#: activation_codes/admin.py:117
 msgid "Description"
 msgstr "Описание"

-#: activation_codes/admin.py:124 build/lib/activation_codes/admin.py:124
+#: activation_codes/admin.py:124
 msgid "No users have used this code yet"
 msgstr "Пока нет пользователей, использовавших этот код"

-#: activation_codes/admin.py:135 build/lib/activation_codes/admin.py:135
+#: activation_codes/admin.py:135
 msgid "Name"
 msgstr "Имя"

 #: activation_codes/admin.py:136 activation_codes/admin.py:246
-#: build/lib/activation_codes/admin.py:136
-#: build/lib/activation_codes/admin.py:246
 msgid "Email"
 msgstr "Эл. почта"

-#: activation_codes/admin.py:137 build/lib/activation_codes/admin.py:137
+#: activation_codes/admin.py:137
 msgid "Date"
 msgstr "Дата"

-#: activation_codes/admin.py:161 build/lib/activation_codes/admin.py:161
+#: activation_codes/admin.py:161
 msgid "Users who used this code"
 msgstr "Пользователи, использующие этот код"

-#: activation_codes/admin.py:163 build/lib/activation_codes/admin.py:163
+#: activation_codes/admin.py:163
 msgid "Recompute current uses from related activations"
 msgstr "Обновить данные использования связанных активаций"

-#: activation_codes/admin.py:177 build/lib/activation_codes/admin.py:177
+#: activation_codes/admin.py:177
 msgid "All selected activation codes already have correct usage counts."
 msgstr "Все выбранные коды активации уже имеют правильное количество использований."

-#: activation_codes/admin.py:182 build/lib/activation_codes/admin.py:182
+#: activation_codes/admin.py:182
 #, python-format
 msgid "Successfully recomputed usage counts for %(count)d activation code(s)."
 msgstr "Количество использованных кодов активации (%(count)d) успешно пересчитано."

 #: activation_codes/admin.py:240 activation_codes/admin.py:284
-#: build/lib/activation_codes/admin.py:240
-#: build/lib/activation_codes/admin.py:284
 msgid "User"
 msgstr "Пользователь"

-#: activation_codes/admin.py:291 build/lib/activation_codes/admin.py:291
+#: activation_codes/admin.py:291
 msgid "Has used activation code"
 msgstr "Использует код активации"

-#: activation_codes/admin.py:293 build/lib/activation_codes/admin.py:293
+#: activation_codes/admin.py:293
 msgid "Add selected users to Brevo waiting list"
 msgstr "Добавить выбранных пользователей в список ожидания Brevo"

-#: activation_codes/admin.py:314 build/lib/activation_codes/admin.py:314
+#: activation_codes/admin.py:314
 #, python-format
 msgid "Added %(count)d user(s) to Brevo waiting list."
 msgstr "В список ожидания Brevo добавлено пользователей: %(count)d."

 #: activation_codes/admin.py:319 activation_codes/admin.py:347
-#: build/lib/activation_codes/admin.py:319
-#: build/lib/activation_codes/admin.py:347
 msgid "No valid email address found in selected registrations."
 msgstr "В выбранных регистрациях не найден действительный адрес электронной почты."

-#: activation_codes/admin.py:323 build/lib/activation_codes/admin.py:323
+#: activation_codes/admin.py:323
 msgid "Remove selected users from Brevo waiting list"
 msgstr "Удалить выбранных пользователей из списка ожидания Brevo"

-#: activation_codes/admin.py:342 build/lib/activation_codes/admin.py:342
+#: activation_codes/admin.py:342
 #, python-format
 msgid "Removed %(count)d user(s) from Brevo waiting list."
 msgstr "Из списка ожидания Brevo удалено пользователей: %(count)d."

 #: activation_codes/models.py:38 activation_codes/models.py:85
-#: activation_codes/models.py:178 build/lib/activation_codes/models.py:38
-#: build/lib/activation_codes/models.py:85
-#: build/lib/activation_codes/models.py:178
+#: activation_codes/models.py:178
 msgid "activation code"
 msgstr "код активации"

-#: activation_codes/models.py:39 build/lib/activation_codes/models.py:39
+#: activation_codes/models.py:39
 msgid "The activation code that users will enter"
 msgstr "Код активации, который будут вводить пользователи"

-#: activation_codes/models.py:46 build/lib/activation_codes/models.py:46
+#: activation_codes/models.py:46
 msgid "Code must be alphanumeric and contain no spaces or special characters"
 msgstr "Код должен быть буквенно-цифровым и не содержать пробелов или специальных символов"

-#: activation_codes/models.py:52 build/lib/activation_codes/models.py:52
+#: activation_codes/models.py:52
 msgid "maximum uses"
 msgstr "максимум использований"

-#: activation_codes/models.py:53 build/lib/activation_codes/models.py:53
+#: activation_codes/models.py:53
 msgid "Maximum number of times this code can be used. 0 means unlimited."
 msgstr "Сколько раз можно использовать этот код. 0 означает неограниченно."

-#: activation_codes/models.py:58 build/lib/activation_codes/models.py:58
+#: activation_codes/models.py:58
 msgid "current uses"
 msgstr "использовано"

-#: activation_codes/models.py:59 build/lib/activation_codes/models.py:59
+#: activation_codes/models.py:59
 msgid "Number of times this code has been used"
 msgstr "Сколько раз этот код был использован"

-#: activation_codes/models.py:65 build/lib/activation_codes/models.py:65
-#: build/lib/core/models.py:151 core/models.py:151
+#: activation_codes/models.py:65 core/models.py:154
 msgid "active"
 msgstr "активный"

-#: activation_codes/models.py:66 build/lib/activation_codes/models.py:66
+#: activation_codes/models.py:66
 msgid "Whether this code can still be used"
 msgstr "Можно ли ещё использовать этот код"

-#: activation_codes/models.py:71 build/lib/activation_codes/models.py:71
+#: activation_codes/models.py:71
 msgid "expires at"
 msgstr "действителен до"

-#: activation_codes/models.py:72 build/lib/activation_codes/models.py:72
+#: activation_codes/models.py:72
 msgid "Date and time when this code expires"
 msgstr "Дата и время окончания действия этого кода"

-#: activation_codes/models.py:78 build/lib/activation_codes/models.py:78
+#: activation_codes/models.py:78
 msgid "description"
 msgstr "описание"

-#: activation_codes/models.py:79 build/lib/activation_codes/models.py:79
+#: activation_codes/models.py:79
 msgid "Internal description or notes about this code"
 msgstr "Внутреннее описание или примечания об этом коде"

-#: activation_codes/models.py:86 build/lib/activation_codes/models.py:86
+#: activation_codes/models.py:86
 msgid "activation codes"
 msgstr "коды активации"

-#: activation_codes/models.py:128 build/lib/activation_codes/models.py:128
+#: activation_codes/models.py:128
 msgid "This activation code is no longer valid"
 msgstr "Этот код активации больше не действителен"

-#: activation_codes/models.py:136 build/lib/activation_codes/models.py:136
+#: activation_codes/models.py:136
 msgid "You have already activated your account"
 msgstr "Вы уже активировали свою учётную запись"

 #: activation_codes/models.py:170 activation_codes/models.py:202
-#: build/lib/activation_codes/models.py:170
-#: build/lib/activation_codes/models.py:202 build/lib/core/models.py:173
-#: core/models.py:173
+#: core/models.py:182
 msgid "user"
 msgstr "пользователь"

-#: activation_codes/models.py:171 build/lib/activation_codes/models.py:171
+#: activation_codes/models.py:171
 msgid "The user who used the activation code"
 msgstr "Пользователь, использовавший код активации"

-#: activation_codes/models.py:179 build/lib/activation_codes/models.py:179
+#: activation_codes/models.py:179
 msgid "The activation code that was used"
 msgstr "Использованный код активации"

 #: activation_codes/models.py:186 activation_codes/models.py:210
-#: build/lib/activation_codes/models.py:186
-#: build/lib/activation_codes/models.py:210
 msgid "user activation"
 msgstr "активация пользователя"

-#: activation_codes/models.py:187 build/lib/activation_codes/models.py:187
+#: activation_codes/models.py:187
 msgid "user activations"
 msgstr "активации пользователя"

-#: activation_codes/models.py:203 build/lib/activation_codes/models.py:203
+#: activation_codes/models.py:203
 msgid "The user who made the registration request"
 msgstr "Пользователь, который сделал запрос на регистрацию"

-#: activation_codes/models.py:211 build/lib/activation_codes/models.py:211
+#: activation_codes/models.py:211
 msgid "Store if the user received an activation code and used it"
 msgstr "Сохранить, если пользователь получил код активации и использовал его"

-#: activation_codes/models.py:220 build/lib/activation_codes/models.py:220
+#: activation_codes/models.py:220
 msgid "user registration request"
 msgstr "запрос на регистрацию пользователя"

-#: activation_codes/models.py:221 build/lib/activation_codes/models.py:221
+#: activation_codes/models.py:221
 msgid "user registration requests"
 msgstr "запросы на регистрацию пользователя"

 #: activation_codes/serializers.py:14
-#: build/lib/activation_codes/serializers.py:14
 msgid "The activation code to validate"
 msgstr "Код активации для проверки"

-#: activation_codes/viewsets.py:107 build/lib/activation_codes/viewsets.py:107
+#: activation_codes/viewsets.py:107
 msgid "Your account has been successfully activated"
 msgstr "Ваша учётная запись успешно активирована"

-#: build/lib/chat/apps.py:12 chat/apps.py:12
+#: chat/apps.py:12
 msgid "chat application"
 msgstr "приложение чата"

-#: build/lib/core/admin.py:26 core/admin.py:26
+#: core/admin.py:26
 msgid "Personal info"
 msgstr "Личные данные"

-#: build/lib/core/admin.py:40 core/admin.py:40
+#: core/admin.py:40
 msgid "Permissions"
 msgstr "Разрешения"

-#: build/lib/core/admin.py:52 core/admin.py:52
+#: core/admin.py:52
 msgid "Important dates"
 msgstr "Важные даты"

-#: build/lib/core/models.py:39 core/models.py:39
+#: core/models.py:39
 msgid "id"
 msgstr "id"

-#: build/lib/core/models.py:40 core/models.py:40
+#: core/models.py:40
 msgid "primary key for the record as UUID"
 msgstr "первичный ключ для записи как UUID"

-#: build/lib/core/models.py:46 core/models.py:46
+#: core/models.py:46
 msgid "created on"
 msgstr "создано"

-#: build/lib/core/models.py:47 core/models.py:47
+#: core/models.py:47
 msgid "date and time at which a record was created"
 msgstr "дата и время создания записи"

-#: build/lib/core/models.py:52 core/models.py:52
+#: core/models.py:52
 msgid "updated on"
 msgstr "обновлено"

-#: build/lib/core/models.py:53 core/models.py:53
+#: core/models.py:53
 msgid "date and time at which a record was last updated"
 msgstr "дата и время последнего обновления записи"

-#: build/lib/core/models.py:86 core/models.py:86
+#: core/models.py:89
 msgid "We couldn't find a user with this sub but the email is already associated with a registered user."
 msgstr "Мы не смогли найти пользователя с этими данными, но этот адрес уже связан с зарегистрированным пользователем."

-#: build/lib/core/models.py:99 core/models.py:99
+#: core/models.py:102
 msgid "Enter a valid sub. This value may contain only letters, numbers, and @/./+/-/_/: characters."
 msgstr "Введите правильный префикс. Он может содержать только буквы, цифры и символы @/./+/-/_/."

-#: build/lib/core/models.py:105 core/models.py:105
+#: core/models.py:108
 msgid "sub"
 msgstr "префикс"

-#: build/lib/core/models.py:107 core/models.py:107
+#: core/models.py:110
 msgid "Required. 255 characters or fewer. Letters, numbers, and @/./+/-/_/: characters only."
 msgstr "Обязательно. 255 символов или меньше. Только буквы, цифры и @/./+/-/_/: /."

-#: build/lib/core/models.py:116 core/models.py:116
+#: core/models.py:119
 msgid "full name"
 msgstr "полное имя"

-#: build/lib/core/models.py:117 core/models.py:117
+#: core/models.py:120
 msgid "short name"
 msgstr "короткое имя"

-#: build/lib/core/models.py:119 core/models.py:119
+#: core/models.py:122
 msgid "identity email address"
 msgstr "личный адрес электронной почты"

-#: build/lib/core/models.py:123 core/models.py:123
+#: core/models.py:126
 msgid "admin email address"
 msgstr "e-mail администратора"

-#: build/lib/core/models.py:129 core/models.py:129
+#: core/models.py:132
 msgid "language"
 msgstr "язык"

-#: build/lib/core/models.py:130 core/models.py:130
+#: core/models.py:133
 msgid "The language in which the user wants to see the interface."
 msgstr "Язык, на котором пользователь хочет видеть интерфейс."

-#: build/lib/core/models.py:138 core/models.py:138
+#: core/models.py:141
 msgid "The timezone in which the user wants to see times."
 msgstr "Часовой пояс, в котором пользователь хочет видеть время."

-#: build/lib/core/models.py:141 core/models.py:141
+#: core/models.py:144
 msgid "device"
 msgstr "устройство"

-#: build/lib/core/models.py:143 core/models.py:143
+#: core/models.py:146
 msgid "Whether the user is a device or a real user."
 msgstr "Пользователь является устройством или человеком."

-#: build/lib/core/models.py:146 core/models.py:146
+#: core/models.py:149
 msgid "staff status"
 msgstr "статус сотрудника"

-#: build/lib/core/models.py:148 core/models.py:148
+#: core/models.py:151
 msgid "Whether the user can log into this admin site."
 msgstr "Может ли пользователь войти на этот административный сайт."

-#: build/lib/core/models.py:154 core/models.py:154
+#: core/models.py:157
 msgid "Whether this user should be treated as active. Unselect this instead of deleting accounts."
 msgstr "Должен ли пользователь рассматриваться как активный. Альтернатива удалению учётных записей."

-#: build/lib/core/models.py:161 core/models.py:161
+#: core/models.py:164
 msgid "allow conversation analytics"
 msgstr "разрешить аналитику для беседы"

-#: build/lib/core/models.py:163 core/models.py:163
+#: core/models.py:166
 msgid "Whether the user allows to use their conversations for analytics."
 msgstr "Разрешает ли пользователь использовать свои беседы для аналитики."

-#: build/lib/core/models.py:174 core/models.py:174
+#: core/models.py:170
+msgid "allow smart web search"
+msgstr "разрешить умный поиск в Интернете"
+
+#: core/models.py:172
+msgid "Whether the user allows to use smart web search features."
+msgstr "Разрешает ли пользователь использовать умный поиск в Интернете."
+
+#: core/models.py:183
 msgid "users"
 msgstr "пользователи"

@@ -2,8 +2,8 @@ msgid ""
 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: 2025-11-17 16:37\n"
+"POT-Creation-Date: 2026-02-26 21:42+0000\n"
+"PO-Revision-Date: 2026-03-11 15:23\n"
 "Last-Translator: \n"
 "Language-Team: Ukrainian\n"
 "Language: uk_UA\n"
@@ -17,328 +17,320 @@ msgstr ""
 "X-Crowdin-File: backend-conversations.pot\n"
 "X-Crowdin-File-ID: 26\n"

-#: activation_codes/admin.py:55 build/lib/activation_codes/admin.py:55
+#: activation_codes/admin.py:55
 msgid "Configuration"
 msgstr "Налаштування"

-#: activation_codes/admin.py:66 build/lib/activation_codes/admin.py:66
+#: activation_codes/admin.py:66
 msgid "Usage details"
 msgstr "Відомості про використання"

 #: activation_codes/admin.py:70 activation_codes/admin.py:226
-#: build/lib/activation_codes/admin.py:70
-#: build/lib/activation_codes/admin.py:226
 msgid "Timestamps"
 msgstr "Відмітки часу"

-#: activation_codes/admin.py:109 build/lib/activation_codes/admin.py:109
+#: activation_codes/admin.py:109
 msgid "Usage"
 msgstr "Використання"

-#: activation_codes/admin.py:117 build/lib/activation_codes/admin.py:117
+#: activation_codes/admin.py:117
 msgid "Description"
 msgstr "Опис"

-#: activation_codes/admin.py:124 build/lib/activation_codes/admin.py:124
+#: activation_codes/admin.py:124
 msgid "No users have used this code yet"
 msgstr "Користувачі ще не використовували цей код"

-#: activation_codes/admin.py:135 build/lib/activation_codes/admin.py:135
+#: activation_codes/admin.py:135
 msgid "Name"
 msgstr "Ім’я"

 #: activation_codes/admin.py:136 activation_codes/admin.py:246
-#: build/lib/activation_codes/admin.py:136
-#: build/lib/activation_codes/admin.py:246
 msgid "Email"
 msgstr "Ел. пошта"

-#: activation_codes/admin.py:137 build/lib/activation_codes/admin.py:137
+#: activation_codes/admin.py:137
 msgid "Date"
 msgstr "Дата"

-#: activation_codes/admin.py:161 build/lib/activation_codes/admin.py:161
+#: activation_codes/admin.py:161
 msgid "Users who used this code"
 msgstr "Користувачі, що використовували цей код"

-#: activation_codes/admin.py:163 build/lib/activation_codes/admin.py:163
+#: activation_codes/admin.py:163
 msgid "Recompute current uses from related activations"
 msgstr "Перерахувати поточні використання пов'язаних ресурсів"

-#: activation_codes/admin.py:177 build/lib/activation_codes/admin.py:177
+#: activation_codes/admin.py:177
 msgid "All selected activation codes already have correct usage counts."
 msgstr "Усі обрані коди активації вже мають коректні лічильники використання."

-#: activation_codes/admin.py:182 build/lib/activation_codes/admin.py:182
+#: activation_codes/admin.py:182
 #, python-format
 msgid "Successfully recomputed usage counts for %(count)d activation code(s)."
 msgstr "Успішно переобчислено використання коду активації %(count)d."

 #: activation_codes/admin.py:240 activation_codes/admin.py:284
-#: build/lib/activation_codes/admin.py:240
-#: build/lib/activation_codes/admin.py:284
 msgid "User"
 msgstr "Користувач"

-#: activation_codes/admin.py:291 build/lib/activation_codes/admin.py:291
+#: activation_codes/admin.py:291
 msgid "Has used activation code"
 msgstr "Використано код активації"

-#: activation_codes/admin.py:293 build/lib/activation_codes/admin.py:293
+#: activation_codes/admin.py:293
 msgid "Add selected users to Brevo waiting list"
 msgstr "Додати обраних користувачів до списку очікування Brevo"

-#: activation_codes/admin.py:314 build/lib/activation_codes/admin.py:314
+#: activation_codes/admin.py:314
 #, python-format
 msgid "Added %(count)d user(s) to Brevo waiting list."
 msgstr "До списку очікування Brevo додано користувачів: %(count)d."

 #: activation_codes/admin.py:319 activation_codes/admin.py:347
-#: build/lib/activation_codes/admin.py:319
-#: build/lib/activation_codes/admin.py:347
 msgid "No valid email address found in selected registrations."
 msgstr "Серед обраних реєстрацій не знайдено дійсної адреси електронної пошти."

-#: activation_codes/admin.py:323 build/lib/activation_codes/admin.py:323
+#: activation_codes/admin.py:323
 msgid "Remove selected users from Brevo waiting list"
 msgstr "Видалити обраних користувачів зі списку очікування Brevo"

-#: activation_codes/admin.py:342 build/lib/activation_codes/admin.py:342
+#: activation_codes/admin.py:342
 #, python-format
 msgid "Removed %(count)d user(s) from Brevo waiting list."
 msgstr "Зі списку очікування Brevo видалено користувачів: %(count)d"

 #: activation_codes/models.py:38 activation_codes/models.py:85
-#: activation_codes/models.py:178 build/lib/activation_codes/models.py:38
-#: build/lib/activation_codes/models.py:85
-#: build/lib/activation_codes/models.py:178
+#: activation_codes/models.py:178
 msgid "activation code"
 msgstr "код активації"

-#: activation_codes/models.py:39 build/lib/activation_codes/models.py:39
+#: activation_codes/models.py:39
 msgid "The activation code that users will enter"
 msgstr "Код активації, що буде введений користувачами"

-#: activation_codes/models.py:46 build/lib/activation_codes/models.py:46
+#: activation_codes/models.py:46
 msgid "Code must be alphanumeric and contain no spaces or special characters"
 msgstr "Код має бути буквено-цифровим, без пробілів або спеціальних символів"

-#: activation_codes/models.py:52 build/lib/activation_codes/models.py:52
+#: activation_codes/models.py:52
 msgid "maximum uses"
 msgstr "максимум використань"

-#: activation_codes/models.py:53 build/lib/activation_codes/models.py:53
+#: activation_codes/models.py:53
 msgid "Maximum number of times this code can be used. 0 means unlimited."
 msgstr "Максимальна кількість разів використання для цього коду. 0 - необмежена."

-#: activation_codes/models.py:58 build/lib/activation_codes/models.py:58
+#: activation_codes/models.py:58
 msgid "current uses"
 msgstr "використано"

-#: activation_codes/models.py:59 build/lib/activation_codes/models.py:59
+#: activation_codes/models.py:59
 msgid "Number of times this code has been used"
 msgstr "Кількість разів використання цього коду"

-#: activation_codes/models.py:65 build/lib/activation_codes/models.py:65
-#: build/lib/core/models.py:151 core/models.py:151
+#: activation_codes/models.py:65 core/models.py:154
 msgid "active"
 msgstr "активний"

-#: activation_codes/models.py:66 build/lib/activation_codes/models.py:66
+#: activation_codes/models.py:66
 msgid "Whether this code can still be used"
 msgstr "Чи цей код все ще може бути використаний"

-#: activation_codes/models.py:71 build/lib/activation_codes/models.py:71
+#: activation_codes/models.py:71
 msgid "expires at"
 msgstr "дійсний до"

-#: activation_codes/models.py:72 build/lib/activation_codes/models.py:72
+#: activation_codes/models.py:72
 msgid "Date and time when this code expires"
 msgstr "Дата та час, коли закінчується дія цього коду"

-#: activation_codes/models.py:78 build/lib/activation_codes/models.py:78
+#: activation_codes/models.py:78
 msgid "description"
 msgstr "опис"

-#: activation_codes/models.py:79 build/lib/activation_codes/models.py:79
+#: activation_codes/models.py:79
 msgid "Internal description or notes about this code"
 msgstr "Внутрішній опис або нотатки про цей код"

-#: activation_codes/models.py:86 build/lib/activation_codes/models.py:86
+#: activation_codes/models.py:86
 msgid "activation codes"
 msgstr "коди активації"

-#: activation_codes/models.py:128 build/lib/activation_codes/models.py:128
+#: activation_codes/models.py:128
 msgid "This activation code is no longer valid"
 msgstr "Цей код активації вже не дійсний"

-#: activation_codes/models.py:136 build/lib/activation_codes/models.py:136
+#: activation_codes/models.py:136
 msgid "You have already activated your account"
 msgstr "Ви вже активували свій обліковий запис"

 #: activation_codes/models.py:170 activation_codes/models.py:202
-#: build/lib/activation_codes/models.py:170
-#: build/lib/activation_codes/models.py:202 build/lib/core/models.py:173
-#: core/models.py:173
+#: core/models.py:182
 msgid "user"
 msgstr "користувач"

-#: activation_codes/models.py:171 build/lib/activation_codes/models.py:171
+#: activation_codes/models.py:171
 msgid "The user who used the activation code"
 msgstr "Користувач, який користувався кодом активації"

-#: activation_codes/models.py:179 build/lib/activation_codes/models.py:179
+#: activation_codes/models.py:179
 msgid "The activation code that was used"
 msgstr "Використаний код активації"

 #: activation_codes/models.py:186 activation_codes/models.py:210
-#: build/lib/activation_codes/models.py:186
-#: build/lib/activation_codes/models.py:210
 msgid "user activation"
 msgstr "активація користувача"

-#: activation_codes/models.py:187 build/lib/activation_codes/models.py:187
+#: activation_codes/models.py:187
 msgid "user activations"
 msgstr "активації користувача"

-#: activation_codes/models.py:203 build/lib/activation_codes/models.py:203
+#: activation_codes/models.py:203
 msgid "The user who made the registration request"
 msgstr "Користувач, що зробив запит на реєстрацію"

-#: activation_codes/models.py:211 build/lib/activation_codes/models.py:211
+#: activation_codes/models.py:211
 msgid "Store if the user received an activation code and used it"
 msgstr "Зберегти, якщо користувач отримав код активації та використав його"

-#: activation_codes/models.py:220 build/lib/activation_codes/models.py:220
+#: activation_codes/models.py:220
 msgid "user registration request"
 msgstr "запит на реєстрацію користувача"

-#: activation_codes/models.py:221 build/lib/activation_codes/models.py:221
+#: activation_codes/models.py:221
 msgid "user registration requests"
 msgstr "запити на реєстрацію користувачів"

 #: activation_codes/serializers.py:14
-#: build/lib/activation_codes/serializers.py:14
 msgid "The activation code to validate"
 msgstr "Код активації для перевірки"

-#: activation_codes/viewsets.py:107 build/lib/activation_codes/viewsets.py:107
+#: activation_codes/viewsets.py:107
 msgid "Your account has been successfully activated"
 msgstr "Ваш обліковий запис успішно активовано"

-#: build/lib/chat/apps.py:12 chat/apps.py:12
+#: chat/apps.py:12
 msgid "chat application"
 msgstr "чат-застосунок"

-#: build/lib/core/admin.py:26 core/admin.py:26
+#: core/admin.py:26
 msgid "Personal info"
 msgstr "Особисті дані"

-#: build/lib/core/admin.py:40 core/admin.py:40
+#: core/admin.py:40
 msgid "Permissions"
 msgstr "Дозволи"

-#: build/lib/core/admin.py:52 core/admin.py:52
+#: core/admin.py:52
 msgid "Important dates"
 msgstr "Важливі дати"

-#: build/lib/core/models.py:39 core/models.py:39
+#: core/models.py:39
 msgid "id"
 msgstr "id"

-#: build/lib/core/models.py:40 core/models.py:40
+#: core/models.py:40
 msgid "primary key for the record as UUID"
 msgstr "первинний ключ для запису як UUID"

-#: build/lib/core/models.py:46 core/models.py:46
+#: core/models.py:46
 msgid "created on"
 msgstr "створено"

-#: build/lib/core/models.py:47 core/models.py:47
+#: core/models.py:47
 msgid "date and time at which a record was created"
 msgstr "дата і час, коли запис було створено"

-#: build/lib/core/models.py:52 core/models.py:52
+#: core/models.py:52
 msgid "updated on"
 msgstr "оновлено"

-#: build/lib/core/models.py:53 core/models.py:53
+#: core/models.py:53
 msgid "date and time at which a record was last updated"
 msgstr "дата і час, коли запис був востаннє оновлений"

-#: build/lib/core/models.py:86 core/models.py:86
+#: core/models.py:89
 msgid "We couldn't find a user with this sub but the email is already associated with a registered user."
 msgstr "Ми не змогли знайти користувача з цими даними, але адреса вже пов'язана з зареєстрованим користувачем."

-#: build/lib/core/models.py:99 core/models.py:99
+#: core/models.py:102
 msgid "Enter a valid sub. This value may contain only letters, numbers, and @/./+/-/_/: characters."
 msgstr "Введіть правильний префікс. Це значення може містити лише літери, цифри та символи @/./+/-/_/."

-#: build/lib/core/models.py:105 core/models.py:105
+#: core/models.py:108
 msgid "sub"
 msgstr "префікс"

-#: build/lib/core/models.py:107 core/models.py:107
+#: core/models.py:110
 msgid "Required. 255 characters or fewer. Letters, numbers, and @/./+/-/_/: characters only."
 msgstr "Обов'язково. 255 символів або менше. Лише літери, цифри та символи @/./+/-/_/."

-#: build/lib/core/models.py:116 core/models.py:116
+#: core/models.py:119
 msgid "full name"
 msgstr "повне ім'я"

-#: build/lib/core/models.py:117 core/models.py:117
+#: core/models.py:120
 msgid "short name"
 msgstr "коротке ім'я"

-#: build/lib/core/models.py:119 core/models.py:119
+#: core/models.py:122
 msgid "identity email address"
 msgstr "адреса електронної пошти особи"

-#: build/lib/core/models.py:123 core/models.py:123
+#: core/models.py:126
 msgid "admin email address"
 msgstr "електронна адреса адміністратора"

-#: build/lib/core/models.py:129 core/models.py:129
+#: core/models.py:132
 msgid "language"
 msgstr "мова"

-#: build/lib/core/models.py:130 core/models.py:130
+#: core/models.py:133
 msgid "The language in which the user wants to see the interface."
 msgstr "Мова, якою користувач хоче бачити інтерфейс."

-#: build/lib/core/models.py:138 core/models.py:138
+#: core/models.py:141
 msgid "The timezone in which the user wants to see times."
 msgstr "Часовий пояс, в якому користувач хоче бачити час."

-#: build/lib/core/models.py:141 core/models.py:141
+#: core/models.py:144
 msgid "device"
 msgstr "пристрій"

-#: build/lib/core/models.py:143 core/models.py:143
+#: core/models.py:146
 msgid "Whether the user is a device or a real user."
 msgstr "Чи є користувач пристроєм чи реальним користувачем."

-#: build/lib/core/models.py:146 core/models.py:146
+#: core/models.py:149
 msgid "staff status"
 msgstr "статус співробітника"

-#: build/lib/core/models.py:148 core/models.py:148
+#: core/models.py:151
 msgid "Whether the user can log into this admin site."
 msgstr "Чи може користувач увійти на цей сайт адміністратора."

-#: build/lib/core/models.py:154 core/models.py:154
+#: core/models.py:157
 msgid "Whether this user should be treated as active. Unselect this instead of deleting accounts."
 msgstr "Чи слід ставитися до цього користувача як до активного. Зніміть вибір замість видалення облікового запису."

-#: build/lib/core/models.py:161 core/models.py:161
+#: core/models.py:164
 msgid "allow conversation analytics"
 msgstr "дозволити аналітику бесіди"

-#: build/lib/core/models.py:163 core/models.py:163
+#: core/models.py:166
 msgid "Whether the user allows to use their conversations for analytics."
 msgstr "Чи дозволяє користувач використовувати свої розмови для аналітики."

-#: build/lib/core/models.py:174 core/models.py:174
+#: core/models.py:170
+msgid "allow smart web search"
+msgstr "дозволити розумний пошук в Інтернеті"
+
+#: core/models.py:172
+msgid "Whether the user allows to use smart web search features."
+msgstr "Чи дозволяє користувач використовувати розумні пошукові функції, пов'язані з Інтернетом."
+
+#: core/models.py:183
 msgid "users"
 msgstr "користувачі"

@@ -7,7 +7,7 @@ build-backend = "setuptools.build_meta"

 [project]
 name = "conversations"
-version = "0.0.9"
+version = "0.0.14"
 authors = [{ "name" = "DINUM", "email" = "dev@mail.numerique.gouv.fr" }]
 classifiers = [
    "Development Status :: 5 - Production/Stable",
@@ -23,7 +23,7 @@ description = "An application to chat with your own AI."
 keywords = ["Django", "AI", "Chatbot", "OpenAI", "Pydantic AI", "Conversations"]
 license = { file = "LICENSE" }
 readme = "README.md"
-requires-python = ">=3.12"
+requires-python = "~=3.13.0"
 dependencies = [
    "deprecated",
    "beautifulsoup4==4.14.2",
@@ -33,19 +33,20 @@ dependencies = [
    "django-cors-headers==4.9.0",
    "django-countries==8.1.0",
    "django-filter==25.2",
-    "django-lasuite[all]==0.0.18",
+    "django-lasuite[all]==0.0.25",
    "django-parler==2.3",
-    "django-pydantic-field==0.4.0",
+    "django-pydantic-field==0.5.4",
    "django-redis==6.0.0",
    "django-storages[s3]==1.14.6",
    "django-timezone-field>=5.1",
-    "django==5.2.8",
+    "django==5.2.12",
    "djangorestframework==3.16.1",
    "drf_spectacular==0.29.0",
    "dockerflow==2024.4.2",
    "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",
@@ -55,9 +56,9 @@ dependencies = [
    "nested-multipart-parser==1.6.0",
    "posthog==7.0.0",
    "pydantic==2.12.4",
-    "pydantic-ai-slim[openai,mistral,mcp,evals,logfire]==1.17.0",
+    "pydantic-ai-slim[openai,mistral,mcp,evals,logfire]==1.62.0",
    "psycopg[binary]==3.2.12",
-    "PyJWT==2.10.1",
+    "PyJWT==2.12.0",
    "python-magic==0.4.27",
    "redis<6.0.0",
    "requests==2.32.5",
@@ -66,6 +67,7 @@ dependencies = [
    "trafilatura==2.0.0",
    "uvicorn==0.38.0",
    "whitenoise==6.11.0",
+    "pypdf==6.9.1",
 ]

 [project.urls]
@@ -106,6 +108,25 @@ zip-safe = true
 [tool.distutils.bdist_wheel]
 universal = true

+[tool.uv]
+required-environments = [
+    "sys_platform == 'linux' and platform_machine == 'x86_64'",
+    "sys_platform == 'darwin'",
+]
+override-dependencies = [
+    "cryptography>=46.0.5", # CVE-2026-26007
+    "joserfc>=1.6.3", # CVE-2026-27932
+    "pillow>=12.1.1", #CVE-2026-25990
+]
+
+[tool.uv.build-backend]
+module-root = ""
+source-exclude = [
+    "**/tests/**",
+    "**/test_*.py",
+    "**/tests.py",
+]
+
 [tool.ruff]
 exclude = [
    ".git",
@@ -137,8 +158,8 @@ select = [
 ]

 [tool.ruff.lint.isort]
-section-order = ["future","standard-library","django","third-party","conversations","first-party","local-folder"]
-sections = { conversations=["core"], django=["django"] }
+section-order = ["future", "standard-library", "django", "third-party", "conversations", "first-party", "local-folder"]
+sections = { conversations = ["core"], django = ["django"] }
 extra-standard-library = ["tomllib"]

 [tool.ruff.lint.per-file-ignores]
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
Laurent Paoletti	402f7a7487	✨(front) copy button preserves formatting when pasting into Word Signed-off-by: Laurent Paoletti <lp@providenz.fr>	2026-03-24 18:48:39 +01:00
Laurent Paoletti	f5a1b72913	🐛(back) add missing color option for project colors Signed-off-by: Laurent Paoletti <lp@providenz.fr>	2026-03-24 15:12:56 +01:00
Laurent Paoletti	9e37f71818	⬆️(dependencies) upgrade Next.js 15 to 16, upgrade python dependencies Signed-off-by: Laurent Paoletti <lp@providenz.fr>	2026-03-23 18:04:22 +01:00
Laurent Paoletti	6dd41e827e	✨(front) projects management UI Signed-off-by: Laurent Paoletti <lp@providenz.fr>	2026-03-17 10:49:56 +01:00
Laurent Paoletti	f6edb14e1f	♻️(front) clean up zustand stores Signed-off-by: Laurent Paoletti <lp@providenz.fr>	2026-03-16 16:41:08 +01:00
Laurent Paoletti	bcf55c6c0c	✨(back) add projects with custom LLM instructions Introduce the project concept for conversations: - Add nested project serializer for search results (`?title=` returns project id, title, icon) - Inject project-level custom LLM instructions into the AI agent systemprompt - Document `title` and `project` query parameters in OpenAPI schema - Fix ChatProjectFactory deprecation warning - Add db compound indexes on ChatConversation for and ChatProject to speed up sidebar queries Signed-off-by: Laurent Paoletti <lp@providenz.fr>	2026-03-16 09:50:10 +01:00
Eléonore Voisin	2f74543d41	✨(search) add searchModal fix ui, fix settings button	2026-03-12 17:53:19 +01:00
Laurent Paoletti	995ad407a6	✨(search) add search modal with improved UX - Add search modal and modify left panel layout - Fix result list flashing by keeping previous data during refetch - Defer loader display to avoid search icon flickering on fast responses - Add Cmd+K / Ctrl+K shortcut to toggle search modal - Auto-focus search input on modal open - Require minimum 3 characters before triggering search - Only mount modal when authenticated and open - Extract shared getRelativeTime utility - Remove unused controlled selection state in QuickSearch Co-Authored-By: Eléonore Voisin <elevoisin@gmail.com Signed-off-by: Laurent Paoletti <lp@providenz.fr>	2026-03-12 16:31:03 +01:00
providenz	0746d23a1e	🌐(i18n) update translated strings Update translated files with new translations Signed-off-by: Laurent Paoletti <lp@providenz.fr>	2026-03-12 09:17:35 +01:00
Laurent Paoletti	c699d7503d	🔖(patch) bump release to 0.0.14 Signed-off-by: Laurent Paoletti <lp@providenz.fr>	2026-03-11 16:20:40 +01:00
Laurent Paoletti	bc7568ccf1	⬆️(back) update django and pypdf Signed-off-by: Laurent Paoletti <lp@providenz.fr>	2026-03-11 15:12:22 +01:00
eliott07	c17a8ae9b9	🐛(frontend) fix inverted toast message for settings toggles fixes inverted toast introduced in smart search PR Remove fixed inverted toast entry from changelog	2026-03-05 13:58:38 +01:00
eliott07	4545083210	✨(user) allow disabling automatic internet search Added user preference to disable automatic tool calls to internet. Preference is stored in user model, can be changed via frontend setting and prevents the tool from showing up unless 'Search on the web' is explicitly enabled Signed-off-by: eliott07 <eliott07@gmail.com> 🐛(settings) fix smart web search default and improve settings layout Updated default value of smart search, adjusted settings modal layout & spacing	2026-02-26 16:27:56 +01:00
natoromano	1088d88aba	🚑️(back) fix mime type for pptx Fix wrong mime type in config (for pptx)	2026-02-25 17:33:16 +01:00
Laurent Paoletti	99353357ff	♻️(front) migrate from ESLint 8 to ESLint 9 flat config - Replace .eslintrc.js files with eslint.config.mjs (flat config) - Upgrade eslint from 8.57.0 to ^9.0.0 - Replace eslint-plugin-import with eslint-plugin-import-x - Replace eslint-config-next with eslint-plugin-react + eslint-plugin-react-hooks - Convert shared config modules from .js (CJS) to .mjs (ESM) - Update lint scripts to use `eslint src/` instead of `next lint` Signed-off-by: Laurent Paoletti <lp@providenz.fr>	2026-02-25 10:32:49 +01:00
Laurent Paoletti	8feed1e3ac	⬆️(back) update django-pydantic-field and pypdf Signed-off-by: Laurent Paoletti <lp@providenz.fr>	2026-02-24 21:27:08 +01:00
Laurent Paoletti	61f86e18df	⬆️(back) update pillow Signed-off-by: Laurent Paoletti <lp@providenz.fr>	2026-02-24 20:15:55 +01:00
Laurent Paoletti	2b8123462a	🐛(front) fix dark mode styling on chat messages Signed-off-by: Laurent Paoletti <lp@providenz.fr>	2026-02-24 17:58:48 +01:00
Quentin BEY	3c3eaf3eeb	🚸(oidc) ignore case when fallback on email Some identity providers might change the case, but in our products we don't consider case variation to be consider as different email addresses. Next step would be to normalize the DB value of email to be lower-case.	2026-02-24 16:07:21 +01:00
Quentin BEY	e925bff1a2	👷(crowdin) use `uv` instead of pip This garanties consistency across actions	2026-02-24 16:05:01 +01:00
Laurent Paoletti	ba712af899	♻️(back) refactor AIAgentService for readability and maintainability Extract large _run_agent method into smaller focused methods Add comprehensive module and method documentation Minor fixes Signed-off-by: Laurent Paoletti <lp@providenz.fr>	2026-02-19 23:31:28 +01:00
Manuel Raynaud	e60c938d44	🐛(helm) reverse liveness and readiness for backend deployment The liveness and readiness are reversed. The liveness was using the heartbeat process that is cheking all django checks and the database connection. Signed-off-by: Laurent Paoletti <lp@providenz.fr>	2026-02-19 19:46:45 +01:00
Eléonore Voisin	5d895d15f9	✨(table) temporarily adjust array temporarily adjust css table	2026-02-18 09:56:27 +01:00
Eléonore Voisin	96a2963adf	✨(waffle) hide the waffle if not fr theme show waffe only on fr theme	2026-02-16 18:20:49 +01:00
Laurent Paoletti	224e6f83fd	⬆️(back) update pydantic-ai Signed-off-by: Laurent Paoletti <lp@providenz.fr>	2026-02-16 11:11:27 +01:00
Laurent Paoletti	af6facf4a3	⚡️(front) optimize streaming markdown rendering with block splitting Split streaming content into independent memoized blocks to avoid re-rendering all markdown/katex/syntax-highlighting on each update. Add some tests for split functions and components. Signed-off-by: Laurent Paoletti <lp@providenz.fr>	2026-02-16 09:46:23 +01:00
natoromano	9d16460777	⬆️ (fix): redo after rebase ✨(front) add e2e pasting an attachment from clipboard add test e2e paste attachment	2026-02-13 11:53:17 +01:00
Laurent Paoletti	09dceb508d	🐛(front) fix math formulas and carousel translations Signed-off-by: Laurent Paoletti <lp@providenz.fr>	2026-02-10 10:23:11 +01:00
Laurent Paoletti	63e0e6c383	💚(docker) vendor mime.types file i/o fetching from Apache Signed-off-by: Laurent Paoletti <lp@providenz.fr>	2026-02-10 09:45:25 +01:00
providenz	a919d9a63b	🌐(i18n) update translated strings Update translated files with new translations Signed-off-by: Laurent Paoletti <lp@providenz.fr>	2026-02-09 15:14:24 +01:00
Laurent Paoletti	9506df341a	🔖(patch) bump release to 0.0.13 - 💄(front) ui fix : update ui-kit - ✨(front) add persistent darkmode - ✨(front) add ui kit #240 - 🧱(files) allow to use S3 storage without external access #849 - ✨(backend) add FindRagBackend #209 - ⬆️(back) update dependencies - ✨(back) Use adaptive parsing for pdf documents - 💄(darkmode) change color feedback butto - 🏗️(back) migrate to uv - ♻️(front) optimize syntax highlighting bundle size - 🐛(back) Cast collection Ids to API expected types Signed-off-by: Laurent Paoletti <lp@providenz.fr>	2026-02-09 15:10:10 +01:00
Laurent Paoletti	c87c734e98	🐛(back) cast collection Ids to API expected types Signed-off-by: Laurent Paoletti <lp@providenz.fr>	2026-02-05 14:56:38 +01:00
Eléonore Voisin	41ade65a49	💄(darkmode) change color feedback button change the color of the feedback button & add a dark mode illustration	2026-02-05 10:41:58 +01:00
Quentin BEY	fd372e1c56	🧱(helm) mount the LLM json config file in jobs The backend might do some consistency checks for settings, some of them are the proper LLM configuration...	2026-02-04 21:41:39 +01:00
Laurent Paoletti	3bbe7fb125	✨(back) Add adaptive pdf parser (text extraction /ocr) Signed-off-by: Laurent Paoletti <lp@providenz.fr>	2026-02-04 16:01:06 +01:00
Eléonore Voisin	082937e107	💄(front) ui fix : update ui-kit - fix Marianne font upgrade package ui-kit add darkmode logo gouv	2026-02-04 11:57:59 +01:00
Laurent Paoletti	54d2d3e807	⬆️(back) update django Signed-off-by: Laurent Paoletti <lp@providenz.fr>	2026-02-03 23:19:13 +01:00
Quentin BEY	23964cbf12	♻️(front) optimize syntax highlighting bundle size Replace rehype-pretty-code with direct Shiki integration Migrate syntax highlighting from rehype-pretty-code to @shikijs/rehype for better bundle optimization. Create a centralized Shiki highlighter that pre-loads only required languages. Also remove unused dependencies: @ag-media/react-pdf-table, @react-pdf/renderer, react-select. Signed-off-by: Laurent Paoletti <lp@providenz.fr>	2026-02-03 21:30:42 +01:00
Eléonore Voisin	ff9e8335f2	✨(front) add persistent darkmode add persistent darkmode and change settings modal	2026-02-03 17:37:27 +01:00
Quentin BEY	8c62f5d933	🐛(find) allow the chat completion view w/o access token Find requires access and refresh tokens, but the current beahavior using Albert API does not. We need to be able to still use the completion endpoint without any stored token.	2026-02-03 10:20:56 +01:00
charles	88bdcc2e60	✨(backend) handle deleting temporary collections I handle deleting document in temporary collection for web_search_brave_with_document_backend	2026-02-02 22:27:26 +01:00
charles	1c573ad3a7	♻️(backend) refactor document parsers I refactor document parsing by introducing AlbertParser and BaseParser	2026-02-02 22:27:26 +01:00
Quentin BEY	3106d5f25f	✨(backend) enhance Find API integration with user sub and tag I enhance Find API integration with user access control and configuration options	2026-02-02 22:27:26 +01:00
charles	23fa1d6b9e	✨(backend) implement FindRagBackend We want to be able to use Find api in rag tools. I add a new rag backend class to do so.	2026-02-02 22:27:26 +01:00
Eléonore Voisin	8ed72fb305	✨(front) fix hover button darkmode fix buttons colors missing -> source item, feedback buttons	2026-02-02 14:18:58 +01:00
Eléonore Voisin	c231e69871	✨(front) add ui kit with dark mode Add UI kit and dark mode Fix missing color variables	2026-02-02 11:00:31 +01:00
Quentin BEY	fb297b97e6	🔇(ci) don't run trivy on mail generation yarn.lock We don't use email generation for now, and we don't expose anything from this yarn file.	2026-01-30 14:58:51 +01:00
Quentin BEY	7858476b84	⬆️(next) bump version to 5.3.9 Fixes GHSA-h25m-26qc-wcjf	2026-01-30 14:47:47 +01:00
Quentin BEY	c02254ec93	⬆️(protobuf) bump version to 6.33.5 Bump with `uv lock --upgrade-package protobuf` This fixes CVE-2026-0994	2026-01-30 14:11:27 +01:00
Quentin BEY	853305ae74	🧱(files) allow to use S3 storage without external access Some architectures do not expose their S3, in such cases it is only available through the backend. This commit proposes two implementations to manage this: - frontend can now upload files to the backend (no direct access to S3) - two new modes to send file to the LLM: a temporary URL on the backend, or directly the file in b64.	2026-01-29 22:30:15 +01:00
Laurent Paoletti	ab2ad0348b	🏗️(back) migrate to uv Signed-off-by: Laurent Paoletti <lp@providenz.fr>	2026-01-29 15:27:49 +01:00
qbey	d752334b5e	🌐(i18n) update translated strings Update translated files with new translations	2026-01-27 16:41:55 +01:00
Quentin BEY	30f825c337	🔖(patch) bump release to 0.0.12 Fixed - ⚡️(front) performance improvements on chat input - 💄(front) i18n and standardize pdf parsing display Removed - 🔥(chat) consider PDF documents as other kind of documents #234	2026-01-27 16:37:54 +01:00
natoromano	f52a27f218	✨(front) i18n and standardize pdf parsing display fix: align i18n key 🌐fix: keep filename Signed-off-by: Laurent Paoletti <lp@providenz.fr>	2026-01-27 12:13:36 +01:00
Laurent Paoletti	3e467cacf2	🐛(back) fix keepalives not sent during document parsing Wrap document_store.parse_and_store_document() calls with asyncio.to_thread() to prevent blocking the event loop. Previously, synchronous document parsing (e.g., PDF) blocked the event loop, preventing keepalive messages from being sent and causing nginx timeouts in production Signed-off-by: Laurent Paoletti <lp@providenz.fr>	2026-01-26 16:20:25 +01:00
Laurent Paoletti	120b204729	⚡️(front) chat input performance improvements Signed-off-by: Laurent Paoletti <lp@providenz.fr>	2026-01-22 12:19:27 +01:00
charles	d9078e75e5	🚨(backend) fix tests I am removing hard coded datetime.	2026-01-22 11:39:47 +01:00
Quentin BEY	09b003856b	🔒️(node-packages) update fixed CVE packages Trivy complains about some packages with fixed CVE, we update them.	2026-01-19 16:09:07 +01:00
Quentin BEY	0b5317a773	🔒️(jaraco) enforce version to fix CVE Vulnerability in jaraco.context caused security issue in setuptools and python3. change python version to fix see GHSA-58pv-8j8x-9vj2 The CVE is not actionable, anyway, we want to please trivy.	2026-01-19 14:38:59 +01:00
Quentin BEY	abf61a9556	🔥(chat) consider PDF documents as other kind of documents We remove the specific management for PDF because it introduces: - limitation regarding the LLM we can use - bad behavior when uploading huge PDFs - more code complexity while not providing really actionnable improvements. This commit removes this, to keep a better control over this.	2026-01-19 14:04:32 +01:00
Laurent Paoletti	3e8c5c77d5	✨(chat) generate and edit conversation title - Auto-generate title via LLM after reaching user message threshold - Add title_set_by_user_at field to track user-customized titles - Skip auto-generation when user has set a custom title - Stream conversation_metadata event to frontend on title update - Invalidate React Query cache to refresh conversation list Signed-off-by: Laurent Paoletti <lp@providenz.fr>	2026-01-18 23:04:43 +01:00
Laurent Paoletti	ddfc86a88f	🐛(back) stream tool responses to prevent too call timeouts Implement sync/sync utilities that inject keepalive messages at regular intervals during stream pauses, preventing proxy timeouts on long-running operations like document(s) summarization. Keepalive messages maintain active connections while tools execute, eliminating forced conversation restarts. Signed-off-by: Laurent Paoletti <lp@providenz.fr>	2026-01-17 13:50:35 +01:00
qbey	e7d76e4477	🌐(i18n) update translated strings Update translated files with new translations	2026-01-16 12:13:55 +01:00
Quentin BEY	fd3399dd66	🔖(patch) bump release to 0.0.11 Changed - 📦️(front) update react Fixed - 🐛(e2e) fix test-e2e-chromium - 🐛(back) fix system prompt compatibility with self-hosted models #200 - ⚰️(back) remove dead code and unused files Removed - 🔥(chat) remove thinking part from frontend #227	2026-01-16 12:03:05 +01:00
Quentin BEY	13c6499c66	🔥(chat) remove thinking part from frontend We want to enable the OSS model but seems like it returns thinking values twice and we don't manage it well... So we disable the frontend while we still don't know how to display the thinking stuff. We could have also cleaned the backend while unused.	2026-01-16 11:43:05 +01:00
Berry den Hartog	a0b31e1e61	🐛(front) fix link color in LeftPanelConversationItem component fix link color component for default theme	2026-01-16 11:43:05 +01:00
Laurent Paoletti	daf90cf110	⚰️(back) remove dead code and unused files Signed-off-by: Laurent Paoletti <lp@providenz.fr>	2026-01-16 11:43:05 +01:00
Laurent Paoletti	29f76fe040	🐛(back) fix system prompt compatibility with self-hosted models Pydantic AI allows setting multiple static and dynamic system prompts to define conversation context and rules. Previously, these were sent to the model API as separate messages, which caused compatibility issues with some self-hosted models (e.g., Gemma3/vLLM). This commit switches from using `system_prompt` to `instruction` as recommended in the Pydantic AI documentation, thus merging several instructions into a single message. Reference: https://ai.pydantic.dev/agents/#system-prompts Signed-off-by: Laurent Paoletti <lp@providenz.fr>	2026-01-16 11:43:05 +01:00
Eléonore Voisin	dc61fdce00	🐛(e2e) fix test-e2e-chronium don't need to wait for the See more button to appear	2025-12-19 08:27:02 +01:00
Eléonore Voisin	aa42a9b4d3	📦️(front) update react update react to 19.2.1	2025-12-16 16:48:06 +01:00
qbey	5475bcd04e	🌐(i18n) update translated strings Update translated files with new translations	2025-12-16 13:15:08 +01:00
Quentin BEY	b1533c016a	🔖(minor) bump release to 0.0.10 Added - ✨(front) add retry button Fixed - 🐛(front) fix long user messages - 🐛(front) fix "Maximum update depth exceeded" error in Chat component - 🐛(front) fix parsing documents display - 🐛(front) fix opacity input in error - 🐛(front) resolve React hydration errors - 🚑️(user) allow longer short names #182	2025-12-15 14:19:30 +01:00
renovate[bot]	9329ee8c90	⬆️(dependencies) update django to v5.2.9 [SECURITY]	2025-12-05 17:18:44 +01:00
Quentin BEY	39bf8f0c2d	🔒️(trivy) run trivy scan on sources (not in docker) Inside the docker images, trivy does not detect frontend issues, we run trivy here to have the lock files. This does not work well for python packages.	2025-12-05 16:52:57 +01:00
Eléonore Voisin	a1ed561204	🐛(front) fix long user messages delete MarkDown for user message	2025-12-04 20:56:54 +01:00
Eléonore Voisin	6dfb9b7328	🐛(front) fix Maximum update depth exceeded - error in Chat component Fix infinite render loop	2025-12-04 14:55:04 +01:00
Eléonore Voisin	38ae97aa31	🐛(front) fix parsing documents display fix width display parsing + fix width doc title'	2025-12-02 17:22:39 +01:00
Eléonore Voisin	19cf3b2663	🐛(front) fix opacity input in error fix opacity input in error	2025-12-02 14:40:27 +01:00