Compare commits

..

27 Commits

Author SHA1 Message Date
camilleAND 0bdee3025b add way to split xlsx for storage 2026-01-14 16:37:53 +01:00
camilleAND b6449addb4 data analysis tool 2026-01-14 16:37:15 +01:00
Laurent Paoletti f3680b6905 ⚰️(back) remove dead code and unused files
Signed-off-by: Laurent Paoletti <lp@providenz.fr>
2026-01-06 10:42:08 +01:00
Laurent Paoletti 5676ce68c0 🐛(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>
2026-01-05 18:43:38 +01:00
Eléonore Voisin 50a395c546 Revert "🐛(front) optimize chat"
This reverts commit 69bf2cab5d.
2025-12-30 13:46:04 +01:00
Eléonore Voisin 69bf2cab5d 🐛(front) optimize chat
Simplified chat rendering
2025-12-19 17:12:53 +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
Eléonore Voisin 83904d8878 🐛(front) resolve React hydration errors
resolve React hydration errors and infinite update loop

🐛(front) resolve React hydration errors

resolve React hydration errors and infinite update loop
2025-12-02 10:35:48 +01:00
Eléonore Voisin d3922b7448 (front) add retry button
on chat error add retry button
2025-12-01 19:21:34 +01:00
Quentin BEY cdac7cad3b 🚑️(user) allow longer short names
I don't know why it was so short, but a legit user is blocked.
2025-12-01 09:43:36 +01:00
qbey 93ee3cd10d 🌐(i18n) update translated strings
Update translated files with new translations
2025-11-17 17:39:03 +01:00
Quentin BEY 91e1c73ccf 🔖(patch) bump release to 0.0.9
Added
- (front) add code copy button
- (RAG) add generic collection RAG tools #159

Fixed

- 🔊(langfuse) enable tracing with redacted content #162
2025-11-17 17:36:24 +01:00
Quentin BEY 0493badb12 (pydantic-ai) update tests after version bump
The new version adds the `run_id` to messages, we don't need to
test this, so we simply get it from the tested objects.
2025-11-14 19:22:22 +01:00
renovate[bot] c6283bd8c8 ⬆️(dependencies) update python dependencies 2025-11-14 19:22:22 +01:00
Eléonore Voisin e823d21418 (front) add code copy button
add code copy button in code block
2025-11-14 17:20:19 +01:00
Quentin BEY 22ce90488c (e2e) add first chat end-to-end test
This is a very simple test, but it paves the way for more of them.
2025-11-14 15:09:54 +01:00
Quentin BEY 8f5419e6ca 🔊(langfuse) enable tracing with redacted content
We use langfuse to know the model use for product analysis
and token consumption. Before this commit if the user does
not want to share their conversations, we would not know
their token use. Now we send a trace with redacted content:
the input/output is redacted and the tool call arguments
are removed from the trace.
2025-11-14 15:05:03 +01:00
Quentin BEY dcec57719f (RAG) add generic collection RAG tools
This allows to deploy generic RAG tools with predefined
collections to allow specific document database for some
users.
2025-11-13 10:42:02 +01:00
71 changed files with 3351 additions and 1175 deletions
+19
View File
@@ -200,3 +200,22 @@ jobs:
- name: Run tests
run: ~/.local/bin/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
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
+41 -9
View File
@@ -8,6 +8,42 @@ and this project adheres to
## [Unreleased]
### 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
## [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
### Fixed
- 🔊(langfuse) enable tracing with redacted content #162
## [0.0.8] - 2025-11-10
### Fixed
@@ -22,28 +58,24 @@ 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
@@ -60,14 +92,12 @@ 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
@@ -77,6 +107,7 @@ 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
@@ -84,7 +115,6 @@ 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
@@ -107,7 +137,7 @@ 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
@@ -142,7 +172,9 @@ and this project adheres to
- 💄(chat) add code highlighting for LLM responses #67
[unreleased]: https://github.com/suitenumerique/conversations/compare/v0.0.8...main
[unreleased]: https://github.com/suitenumerique/conversations/compare/v0.0.10...main
[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
[0.0.6]: https://github.com/suitenumerique/conversations/releases/v0.0.6
+2 -2
View File
@@ -126,7 +126,7 @@ build-frontend: ## build the frontend container
build-e2e: cache ?=
build-e2e: ## build the e2e container
@$(MAKE) build-backend cache=$(cache)
@$(COMPOSE_E2E) build frontend $(cache)
@$(COMPOSE_E2E) build frontend openmockllm-mistral $(cache)
.PHONY: build-e2e
down: ## stop and remove containers, networks, images, and volumes
@@ -158,7 +158,7 @@ create-compose-with-models: ## override the docker-compose file with models
run-e2e: ## start the e2e server
run-e2e:
@$(MAKE) run-backend
@$(COMPOSE_E2E) up --force-recreate -d frontend
@$(COMPOSE_E2E) up --force-recreate -d frontend openmockllm-mistral
.PHONY: run-e2e
status: ## an alias for "docker compose ps"
+19
View File
@@ -11,3 +11,22 @@ services:
image: conversations:frontend-production
ports:
- "3000:3000"
openmockllm-mistral:
user: "${DOCKER_USER:-1000}"
build:
context: .
dockerfile: ./src/OpenMockLLM/Dockerfile
image: conversations:openmockllm-mistral
command:
- openmockllm
- --host
- "0.0.0.0"
- --port
- "8000"
- --backend
- mistral
- --model-name
- mistral-mock
ports:
- "8900:8000"
+3
View File
@@ -2,6 +2,9 @@
BURST_THROTTLE_RATES="200/minute"
SUSTAINED_THROTTLE_RATES="200/hour"
# LLM
LLM_CONFIGURATION_FILE_PATH = /app/conversations/configuration/llm/default.e2e.json
# Features
FEATURE_FLAG_WEB_SEARCH=ENABLED
FEATURE_FLAG_DOCUMENT_UPLOAD=ENABLED
-6
View File
@@ -1,6 +0,0 @@
{
"dependencies": {
"@ai-sdk/react": "^1.2.12",
"@ai-sdk/ui-utils": "^1.2.11"
}
}
+19
View File
@@ -0,0 +1,19 @@
FROM python:3.13.3-alpine
# Upgrade pip to its latest release to speed up dependencies installation
RUN python -m pip install --upgrade pip setuptools lorem-text
# Upgrade system packages to install security updates
RUN apk update && \
apk upgrade
RUN apk add --no-cache git
# Install the package
RUN pip install git+https://github.com/etalab-ia/openmockllm.git
# Expose the default port
EXPOSE 8000
# Set default command
CMD ["openmockllm", "--host", "0.0.0.0", "--port", "8000"]
+19
View File
@@ -0,0 +1,19 @@
[OpenMockLLM](https://github.com/etalab-ia/OpenMockLLM) is a FastAPI-based mock LLM API server that simulates
several Large Language Model API providers.
This is a simple docker image to run the server for testing and development purposes (E2E tests mainly).
It's a bit overkill to have a dedicated image for that, but it allows simple E2E stack with docker-compose since
our code is also run in Docker containers.
## Build and Run manually
```bash
docker build -t openmockllm .
docker run -p 8000:8000 openmockllm
```
## Next steps
- Add more chat completion behaviors (specific text streaming, function calling, etc.)
- Pin a specific OpenMockLLM version in the Dockerfile
@@ -3,7 +3,7 @@
import json
import logging
from io import BytesIO
from typing import Optional
from typing import List, Optional
from urllib.parse import urljoin
from django.conf import settings
@@ -18,6 +18,169 @@ from chat.agent_rag.document_rag_backends.base_rag_backend import BaseRagBackend
logger = logging.getLogger(__name__)
# Albert API token limit for document vectorization
# We use a conservative chunk size to stay well under the limit
ALBERT_MAX_TOKENS = 8192
ALBERT_CHUNK_SIZE_TOKENS = 5000 # More conservative chunk size with larger safety margin
# Approximate tokens: ~3 characters per token (more conservative estimate for Markdown/Excel)
# Markdown and Excel content often have more tokens per character due to formatting
ALBERT_CHUNK_SIZE_CHARS = ALBERT_CHUNK_SIZE_TOKENS * 3
def _estimate_tokens(content: str) -> int:
"""
Estimate the number of tokens in a text string.
Uses a conservative approximation: ~3 characters per token.
This is more conservative than 4 chars/token to account for:
- Markdown formatting (headers, lists, tables)
- Excel content with special characters
- Whitespace and punctuation
Args:
content (str): The text content to estimate.
Returns:
int: Estimated number of tokens.
"""
return len(content) // 3
def _chunk_content(content: str, max_chars: int = ALBERT_CHUNK_SIZE_CHARS) -> List[str]:
"""
Split content into chunks that fit within Albert's token limit.
Attempts to split at paragraph boundaries (double newlines) when possible,
otherwise splits at line boundaries, and finally at character boundaries.
Validates that each chunk is under the token limit after splitting.
Args:
content (str): The content to chunk.
max_chars (int): Maximum characters per chunk (default: ALBERT_CHUNK_SIZE_CHARS).
Returns:
list[str]: List of content chunks, each under the token limit.
"""
# First check if content fits in one chunk
estimated_tokens = _estimate_tokens(content)
if estimated_tokens <= ALBERT_CHUNK_SIZE_TOKENS:
return [content]
chunks = []
remaining = content
while len(remaining) > 0:
# Check if remaining content fits in one chunk
remaining_tokens = _estimate_tokens(remaining)
if remaining_tokens <= ALBERT_CHUNK_SIZE_TOKENS:
if remaining.strip():
chunks.append(remaining.strip())
break
# Need to split - find the best split point
# Start with max_chars but may need to reduce if token estimate is too high
search_limit = max_chars
# Try to find a split point that keeps us under token limit
# Reduce search limit if needed to ensure token limit is respected
while search_limit > 100: # Minimum chunk size
# Try to split at paragraph boundary (double newline)
split_pos = remaining.rfind("\n\n", 0, search_limit)
if split_pos == -1:
# Try to split at single newline
split_pos = remaining.rfind("\n", 0, search_limit)
if split_pos == -1:
# Force split at character boundary
split_pos = search_limit
# Validate that this chunk is under token limit
chunk_candidate = remaining[:split_pos].strip()
if chunk_candidate:
chunk_tokens = _estimate_tokens(chunk_candidate)
if chunk_tokens <= ALBERT_CHUNK_SIZE_TOKENS:
chunks.append(chunk_candidate)
remaining = remaining[split_pos:].lstrip()
break
# Chunk too large, reduce search limit and try again
search_limit = int(search_limit * 0.8) # Reduce by 20%
else:
# Fallback: force split at a safe size
# This should rarely happen, but ensures we don't get stuck
safe_size = min(max_chars, len(remaining))
chunk = remaining[:safe_size].strip()
if chunk:
chunks.append(chunk)
remaining = remaining[safe_size:].lstrip()
# Validate all chunks are under limit and split further if needed
validated_chunks = []
for chunk_item in chunks:
chunk_tokens = _estimate_tokens(chunk_item)
if chunk_tokens > ALBERT_MAX_TOKENS:
logger.warning(
"Chunk still exceeds token limit (%d tokens, max: %d), forcing split further",
chunk_tokens,
ALBERT_MAX_TOKENS,
)
# Force split this chunk further using a more conservative size
# Use a size that ensures we stay well under the token limit
# Target: ~5000 tokens max per chunk (conservative)
max_safe_chars = ALBERT_CHUNK_SIZE_TOKENS * 3 # 6000 * 3 = 18000 chars for ~5000 tokens
remaining_chunk = chunk_item
while len(remaining_chunk) > 0:
remaining_tokens = _estimate_tokens(remaining_chunk)
if remaining_tokens <= ALBERT_CHUNK_SIZE_TOKENS:
if remaining_chunk.strip():
validated_chunks.append(remaining_chunk.strip())
break
# Find a safe split point
split_pos = min(max_safe_chars, len(remaining_chunk))
# Try to split at a line boundary if possible
line_split = remaining_chunk.rfind("\n", 0, split_pos)
if line_split > max_safe_chars * 0.5: # Only use if it's not too small
split_pos = line_split
sub_chunk = remaining_chunk[:split_pos].strip()
if sub_chunk:
sub_tokens = _estimate_tokens(sub_chunk)
# Double-check this sub-chunk is safe
if sub_tokens > ALBERT_MAX_TOKENS:
# Still too large, use even smaller size
logger.warning(
"Sub-chunk still too large (%d tokens), using smaller split",
sub_tokens,
)
split_pos = ALBERT_CHUNK_SIZE_TOKENS * 2 # 12000 chars for ~3000 tokens
sub_chunk = remaining_chunk[:split_pos].strip()
validated_chunks.append(sub_chunk)
remaining_chunk = remaining_chunk[split_pos:].lstrip()
else:
validated_chunks.append(chunk_item)
# Final validation - ensure NO chunk exceeds the limit
final_chunks = []
for chunk in validated_chunks:
chunk_tokens = _estimate_tokens(chunk)
if chunk_tokens > ALBERT_MAX_TOKENS:
logger.error(
"CRITICAL: Chunk still exceeds limit after all splitting attempts: %d tokens",
chunk_tokens,
)
# Emergency split: use very conservative size
emergency_size = ALBERT_CHUNK_SIZE_TOKENS * 2 # 12000 chars
remaining = chunk
while len(remaining) > 0:
emergency_chunk = remaining[:emergency_size].strip()
if emergency_chunk:
final_chunks.append(emergency_chunk)
remaining = remaining[emergency_size:].lstrip()
else:
final_chunks.append(chunk)
return final_chunks
class AlbertRagBackend(BaseRagBackend): # pylint: disable=too-many-instance-attributes
"""
@@ -33,9 +196,13 @@ class AlbertRagBackend(BaseRagBackend): # pylint: disable=too-many-instance-att
- Perform a search operation using the Albert API.
"""
def __init__(self, collection_id: Optional[str] = None):
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)
super().__init__(collection_id, read_only_collection_id)
self._base_url = settings.ALBERT_API_URL
self._headers = {
"Authorization": f"Bearer {settings.ALBERT_API_KEY}",
@@ -166,7 +333,42 @@ class AlbertRagBackend(BaseRagBackend): # pylint: disable=too-many-instance-att
"""
Store the document content in the Albert collection.
This method should handle the logic to send the document content to the Albert API.
If the document is too large (exceeds Albert's token limit), it will be automatically
split into multiple chunks and stored as separate documents.
Args:
name (str): The name of the document.
content (str): The content of the document in Markdown format.
"""
# Check if content needs to be chunked
estimated_tokens = _estimate_tokens(content)
if estimated_tokens > ALBERT_MAX_TOKENS:
logger.info(
"Document '%s' is too large (%d estimated tokens, limit: %d). "
"Splitting into chunks.",
name,
estimated_tokens,
ALBERT_MAX_TOKENS,
)
chunks = _chunk_content(content)
logger.info("Split document '%s' into %d chunks", name, len(chunks))
# Store each chunk as a separate document
for i, chunk in enumerate(chunks, start=1):
chunk_name = f"{name}_part_{i}" if len(chunks) > 1 else name
self._store_single_document(chunk_name, chunk)
else:
# Document fits within limit, store as-is
self._store_single_document(name, content)
def _store_single_document(self, name: str, content: str) -> None:
"""
Store a single document chunk in the Albert collection.
Internal method that performs the actual API call to store one document.
Args:
name (str): The name of the document.
content (str): The content of the document in Markdown format.
@@ -181,14 +383,68 @@ class AlbertRagBackend(BaseRagBackend): # pylint: disable=too-many-instance-att
},
timeout=settings.ALBERT_API_TIMEOUT,
)
logger.debug(response.json())
logger.debug("Stored document '%s': %s", name, response.json())
response.raise_for_status()
async def astore_document(self, name: str, content: str) -> None:
"""
Store the document content in the Albert collection.
This method should handle the logic to send the document content to the Albert API.
If the document is too large (exceeds Albert's token limit), it will be automatically
split into multiple chunks and stored as separate documents.
Args:
name (str): The name of the document.
content (str): The content of the document in Markdown format.
"""
# Check if content needs to be chunked
estimated_tokens = _estimate_tokens(content)
if estimated_tokens > ALBERT_MAX_TOKENS:
logger.info(
"Document '%s' is too large (%d estimated tokens, limit: %d). "
"Splitting into chunks.",
name,
estimated_tokens,
ALBERT_MAX_TOKENS,
)
chunks = _chunk_content(content)
logger.info("Split document '%s' into %d chunks", name, len(chunks))
# Validate chunks before storing
for i, chunk in enumerate(chunks, start=1):
chunk_tokens = _estimate_tokens(chunk)
logger.debug(
"Chunk %d/%d: %d chars, ~%d tokens",
i,
len(chunks),
len(chunk),
chunk_tokens,
)
if chunk_tokens > ALBERT_MAX_TOKENS:
logger.error(
"Chunk %d/%d still exceeds token limit: %d tokens (max: %d)",
i,
len(chunks),
chunk_tokens,
ALBERT_MAX_TOKENS,
)
# Store each chunk as a separate document
for i, chunk in enumerate(chunks, start=1):
chunk_name = f"{name}_part_{i}" if len(chunks) > 1 else name
await self._astore_single_document(chunk_name, chunk)
else:
# Document fits within limit, store as-is
await self._astore_single_document(name, content)
async def _astore_single_document(self, name: str, content: str) -> None:
"""
Store a single document chunk in the Albert collection.
Internal method that performs the actual API call to store one document.
Args:
name (str): The name of the document.
content (str): The content of the document in Markdown format.
@@ -206,7 +462,7 @@ class AlbertRagBackend(BaseRagBackend): # pylint: disable=too-many-instance-att
},
timeout=settings.ALBERT_API_TIMEOUT,
)
logger.debug(response.json())
logger.debug("Stored document '%s': %s", name, response.json())
response.raise_for_status()
def search(self, query, results_count: int = 4) -> RAGWebResults:
@@ -220,11 +476,13 @@ class AlbertRagBackend(BaseRagBackend): # pylint: disable=too-many-instance-att
Returns:
RAGWebResults: The search results.
"""
collection_ids = self.get_all_collection_ids() # might raise RuntimeError
response = requests.post(
urljoin(self._base_url, self._search_endpoint),
headers=self._headers,
json={
"collections": [int(self.collection_id)],
"collections": collection_ids,
"prompt": query,
"score_threshold": 0.6,
"k": results_count, # Number of chunks to return from the search
@@ -261,12 +519,14 @@ class AlbertRagBackend(BaseRagBackend): # pylint: disable=too-many-instance-att
Returns:
RAGWebResults: The search results.
"""
collection_ids = self.get_all_collection_ids() # might raise RuntimeError
async with httpx.AsyncClient(timeout=settings.ALBERT_API_TIMEOUT) as client:
response = await client.post(
urljoin(self._base_url, self._search_endpoint),
headers=self._headers,
json={
"collections": [int(self.collection_id)],
"collections": collection_ids,
"prompt": query,
"score_threshold": 0.6,
"k": results_count, # Number of chunks to return from the search
@@ -3,7 +3,7 @@
import logging
from contextlib import asynccontextmanager, contextmanager
from io import BytesIO
from typing import Optional
from typing import List, Optional
from asgiref.sync import sync_to_async
@@ -15,11 +15,51 @@ logger = logging.getLogger(__name__)
class BaseRagBackend:
"""Base class for RAG backends."""
def __init__(self, collection_id: Optional[str] = None):
"""Backend settings."""
def __init__(
self,
collection_id: Optional[str] = None,
read_only_collection_id: Optional[List[str]] = None,
):
"""
Backend settings.
Collection ID is required for RAG operations, where you want to manage the collection
lifecycle (create/delete).
Read-only collection IDs can be used to access existing collections
without managing their lifecycle.
Collection ID and read-only collection IDs are separated in the implementation to prevent
unwanted actions.
Args:
collection_id (Optional[str]): The collection ID for managing the collection lifecycle.
read_only_collection_id (Optional[List[str]]): List of read-only collection IDs.
"""
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"
def get_all_collection_ids(self) -> List[str]:
"""
Get all collection IDs, including the main collection ID and read-only collection IDs.
Returns:
List[str]: List of all collection IDs.
Raises:
RuntimeError: If neither collection_id nor read_only_collection_id is provided.
"""
if not self.collection_id and not self.read_only_collection_id:
raise RuntimeError("The RAG backend requires collection_id or read_only_collection_id")
collection_ids = []
if self.collection_id:
collection_ids.append(int(self.collection_id))
if self.read_only_collection_id:
collection_ids.extend(
[int(collection_id) for collection_id in self.read_only_collection_id]
)
return collection_ids
def create_collection(self, name: str, description: Optional[str] = None) -> str:
"""
Create a temporary collection for the search operation.
+1 -3
View File
@@ -190,6 +190,4 @@ class BaseAgent(Agent):
_tools = [get_pydantic_tools_by_name(tool_name) for tool_name in self.configuration.tools]
super().__init__(
model=_model_instance, system_prompt=_system_prompt, tools=_tools, **kwargs
)
super().__init__(model=_model_instance, instructions=_system_prompt, tools=_tools, **kwargs)
+4 -5
View File
@@ -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:
+58 -17
View File
@@ -26,7 +26,7 @@ from django.utils.module_loading import import_string
from asgiref.sync import sync_to_async
from langfuse import get_client
from pydantic_ai import Agent, RunContext
from pydantic_ai import Agent, InstrumentationSettings, RunContext
from pydantic_ai.messages import (
BinaryContent,
DocumentUrl,
@@ -72,11 +72,16 @@ from chat.clients.pydantic_ui_message_converter import (
ui_message_to_user_content,
)
from chat.mcp_servers import get_mcp_servers
from chat.tools.data_analysis import add_data_analysis_tool
from chat.tools.document_generic_search_rag import add_document_rag_search_tool_from_setting
from chat.tools.document_search_rag import add_document_rag_search_tool
from chat.tools.document_summarize import document_summarize
from chat.vercel_ai_sdk.core import events_v4, events_v5
from chat.vercel_ai_sdk.encoder import EventEncoder
# Keep at the top of the file to avoid mocking issues
document_store_backend = import_string(settings.RAG_DOCUMENT_SEARCH_BACKEND)
logger = logging.getLogger(__name__)
User = get_user_model()
@@ -116,7 +121,8 @@ class AIAgentService: # pylint: disable=too-many-instance-attributes
self.language = language # might be None
self._last_stop_check = 0
self._store_analytics = settings.LANGFUSE_ENABLED and user.allow_conversation_analytics
self._langfuse_available = settings.LANGFUSE_ENABLED
self._store_analytics = self._langfuse_available and user.allow_conversation_analytics
self.event_encoder = EventEncoder("v4") # Always use v4 for now
self._support_streaming = True
@@ -137,9 +143,16 @@ class AIAgentService: # pylint: disable=too-many-instance-attributes
self.conversation_agent = ConversationAgent(
model_hrid=self.model_hrid,
language=self.language,
instrument=self._store_analytics,
instrument=InstrumentationSettings(
include_binary_content=self._store_analytics,
include_content=self._store_analytics,
)
if self._langfuse_available
else False,
deps_type=ContextDeps,
)
add_document_rag_search_tool_from_setting(self.conversation_agent, self.user)
add_data_analysis_tool(self.conversation_agent)
@property
def _stop_cache_key(self):
@@ -174,7 +187,7 @@ class AIAgentService: # pylint: disable=too-many-instance-attributes
"""Return only the assistant text deltas (legacy text mode)."""
await self._clean()
with ExitStack() as stack:
if self._store_analytics:
if self._langfuse_available:
span = stack.enter_context(get_client().start_as_current_span(name="conversation"))
span.update_trace(user_id=str(self.user.sub), session_id=str(self.conversation.pk))
@@ -186,7 +199,7 @@ class AIAgentService: # pylint: disable=too-many-instance-attributes
"""Return Vercel-AI-SDK formatted events."""
await self._clean()
with ExitStack() as stack:
if self._store_analytics:
if self._langfuse_available:
span = stack.enter_context(get_client().start_as_current_span(name="conversation"))
span.update_trace(user_id=str(self.user.sub), session_id=str(self.conversation.pk))
async for event in self._run_agent(messages, force_web_search):
@@ -228,6 +241,7 @@ class AIAgentService: # pylint: disable=too-many-instance-attributes
Parse and store input documents in the conversation's document store.
"""
# Early external document URL rejection
if any(
not document.url.startswith("/media-key/")
for document in documents
@@ -241,8 +255,6 @@ class AIAgentService: # pylint: disable=too-many-instance-attributes
):
raise ValueError("Document URL does not belong to the conversation.")
document_store_backend = import_string(settings.RAG_DOCUMENT_SEARCH_BACKEND)
document_store = document_store_backend(self.conversation.collection_id)
if not document_store.collection_id:
# Create a new collection for the conversation
@@ -279,7 +291,24 @@ class AIAgentService: # pylint: disable=too-many-instance-attributes
content=document.data,
)
if not document.media_type.startswith("text/"):
# Don't convert tabular files (CSV, Excel) to Markdown - keep originals for data_analysis tool
# Tabular files are already text-based or can be used directly
is_tabular_file = (
document.media_type in [
"text/csv",
"application/csv",
"application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
"application/vnd.ms-excel",
"application/excel",
]
or any(
document.identifier.lower().endswith(ext)
for ext in [".csv", ".xlsx", ".xls", ".xlsm", ".xlsb"]
)
)
# Only convert non-text files that are not tabular files
if not document.media_type.startswith("text/") and not is_tabular_file:
md_attachment = await models.ChatConversationAttachment.objects.acreate(
conversation=self.conversation,
uploaded_by=self.user,
@@ -353,7 +382,7 @@ class AIAgentService: # pylint: disable=too-many-instance-attributes
return
# Langfuse settings
if self._store_analytics:
if self._langfuse_available:
langfuse = get_client()
langfuse.update_current_trace(
session_id=str(self.conversation.pk),
@@ -377,8 +406,10 @@ class AIAgentService: # pylint: disable=too-many-instance-attributes
self.conversation, input_images, updated_url=image_key_mapping
)
if self._store_analytics:
langfuse.update_current_trace(input=user_prompt)
if self._langfuse_available:
langfuse.update_current_trace(
input=user_prompt if self._store_analytics else "REDACTED"
)
usage = {"promptTokens": 0, "completionTokens": 0}
@@ -410,6 +441,7 @@ class AIAgentService: # pylint: disable=too-many-instance-attributes
],
},
)
try:
await self.parse_input_documents(input_documents)
except Exception as exc: # pylint: disable=broad-except
@@ -447,7 +479,7 @@ class AIAgentService: # pylint: disable=too-many-instance-attributes
if force_web_search:
@self.conversation_agent.system_prompt
@self.conversation_agent.instructions
def force_web_search_prompt() -> str:
"""Dynamic system prompt function to force web search."""
return (
@@ -474,6 +506,7 @@ class AIAgentService: # pylint: disable=too-many-instance-attributes
.aexists()
)
document_urls = []
if not conversation_has_documents and not has_not_pdf_docs:
# No documents to process
@@ -495,7 +528,7 @@ class AIAgentService: # pylint: disable=too-many-instance-attributes
)
# Inform the model (system-level) that documents are attached and available
@self.conversation_agent.system_prompt
@self.conversation_agent.instructions
def attached_documents_note() -> str:
return (
"[Internal context] User documents are attached to this conversation. "
@@ -508,6 +541,13 @@ class AIAgentService: # pylint: disable=too-many-instance-attributes
async def summarize(ctx: RunContext, *args, **kwargs) -> ToolReturn:
"""Wrap the document_summarize tool to provide context and add the tool."""
return await document_summarize(ctx, *args, **kwargs)
if not conversation_has_documents and not has_not_pdf_docs:
# No documents to process
pass
elif has_not_pdf_docs:
# Already handled above with RAG tool
pass
else:
conversation_documents = [
cd
@@ -693,7 +733,7 @@ class AIAgentService: # pylint: disable=too-many-instance-attributes
logger.error("_model_response_message_id already set")
_model_response_message_id = (
str(uuid.uuid4())
if not self._store_analytics
if not self._langfuse_available
else f"trace-{langfuse.get_current_trace_id()}"
)
yield events_v4.StartStepPart(
@@ -717,9 +757,10 @@ class AIAgentService: # pylint: disable=too-many-instance-attributes
image_key_mapping=image_key_mapping or None,
)
if self._store_analytics:
langfuse.update_current_trace(output=run.result.output)
if self._langfuse_available:
langfuse.update_current_trace(
output=run.result.output if self._store_analytics else "REDACTED"
)
# Vercel finish message
yield events_v4.FinishMessagePart(
finish_reason=events_v4.FinishReason.STOP,
@@ -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 @@
"""Unit tests for add_document_rag_search_tool_from_setting integration with AIAgentService."""
import pytest
from core.factories import UserFactory
from chat.clients.pydantic_ai import AIAgentService
from chat.factories import ChatConversationFactory
from chat.llm_configuration import LLModel, LLMProvider
pytestmark = pytest.mark.django_db()
def test_ai_agent_service_adds_rag_tools_from_settings(settings):
"""Test that AIAgentService adds RAG tools from SPECIFIC_RAG_DOCUMENT_SEARCH_TOOLS."""
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=[],
provider=LLMProvider(hrid="unused", base_url="https://example.com", api_key="key"),
),
}
settings.SPECIFIC_RAG_DOCUMENT_SEARCH_TOOLS = {
"legal_documents": {
"collection_ids": [100, 101, 102],
"feature_flag_value": "enabled",
"tool_description": "Use this tool to search legal documents and laws.",
},
"french_public_services": {
"collection_ids": [784, 785],
"feature_flag_value": "enabled",
"tool_description": (
"Use this tool when the user asks for information about French public services."
),
},
}
user = UserFactory()
conversation = ChatConversationFactory(owner=user)
# Create the service
service = AIAgentService(conversation, user=user)
# Check that tools were added to the conversation_agent
agent_tools = service.conversation_agent._function_toolset.tools # pylint: disable=protected-access
assert "legal_documents" in agent_tools
assert "french_public_services" in agent_tools
# Verify tool names and descriptions
assert agent_tools["legal_documents"].name == "legal_documents"
assert (
agent_tools["legal_documents"].description
== "Use this tool to search legal documents and laws."
)
assert agent_tools["french_public_services"].name == "french_public_services"
assert (
agent_tools["french_public_services"].description
== "Use this tool when the user asks for information about French public services."
)
@@ -0,0 +1,270 @@
"""Unit tests for Langfuse tracing in AIAgentService."""
import pytest
import responses
from asgiref.sync import sync_to_async
from langfuse import Langfuse
from pydantic_ai.messages import ModelMessage
from pydantic_ai.models.function import AgentInfo, FunctionModel
from core.factories import UserFactory
from chat.ai_sdk_types import TextUIPart, UIMessage
from chat.clients.pydantic_ai import AIAgentService
from chat.factories import ChatConversationFactory
pytestmark = pytest.mark.django_db()
@pytest.fixture(name="langfuse_client", scope="function")
def langfuse_client_fixture():
"""Fixture to init langfuse for tests."""
langfuse_client = Langfuse(
public_key="pk-test-key",
secret_key="sk-test-key",
host="https://langfuse.example.com",
environment="test",
debug=True,
)
yield langfuse_client
langfuse_client._resources.prompt_cache._task_manager.shutdown() # pylint: disable=protected-access
langfuse_client.shutdown()
@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 = []
@pytest.fixture(name="ui_messages")
def ui_messages_fixture():
"""Fixture for test UI messages."""
return [
UIMessage(
id="msg-1",
role="user",
content="Hello, how are you?",
parts=[TextUIPart(type="text", text="Hello, how are you?")],
)
]
@pytest.fixture(name="agent_model")
def agent_model_fixture():
"""Fixture for agent model function."""
async def _agent_model(_messages: list[ModelMessage], _info: AgentInfo):
"""Simple agent model that returns a fixed response."""
yield "Hello! I'm doing well, thank you for asking."
return FunctionModel(stream_function=_agent_model)
@pytest.mark.asyncio
@responses.activate
async def test_langfuse_span_created_when_enabled_and_analytics_allowed(
agent_model, ui_messages, settings, langfuse_client
):
"""Test Langfuse span is created when enabled and user allows analytics."""
settings.LANGFUSE_ENABLED = True
# Mock Langfuse HTTP endpoints
responses.add(
responses.POST,
"https://langfuse.example.com/api/public/otel/v1/traces",
json={"success": True},
status=200,
)
# Create user with analytics enabled
user = await sync_to_async(UserFactory)(allow_conversation_analytics=True)
conversation = await sync_to_async(ChatConversationFactory)(owner=user)
service = AIAgentService(conversation, user=user)
results = []
with service.conversation_agent.override(model=agent_model):
async for result in service.stream_text_async(ui_messages):
results.append(result)
# Verify that results were generated
assert results == ["Hello! I'm doing well, thank you for asking."]
langfuse_client.flush()
# Verify Langfuse HTTP calls were made
assert len(responses.calls) == 1
assert (
responses.calls[0].request.url == "https://langfuse.example.com/api/public/otel/v1/traces"
)
# quite complex to parse the full body, so just check that expected output is in there
assert b"Hello! I'm doing well, thank you for asking." in responses.calls[0].request.body
@pytest.mark.asyncio
@responses.activate
async def test_langfuse_span_created_when_enabled_and_analytics_disabled(
agent_model, ui_messages, settings, langfuse_client
):
"""Test Langfuse span is created even when user disallows analytics."""
settings.LANGFUSE_ENABLED = True
# Mock Langfuse HTTP endpoints
responses.add(
responses.POST,
"https://langfuse.example.com/api/public/otel/v1/traces",
json={"success": True},
status=200,
)
# Create user with analytics disabled
user = await sync_to_async(UserFactory)(allow_conversation_analytics=False)
conversation = await sync_to_async(ChatConversationFactory)(owner=user)
service = AIAgentService(conversation, user=user)
results = []
with service.conversation_agent.override(model=agent_model):
async for result in service.stream_text_async(ui_messages):
results.append(result)
# Verify that results were generated
assert results == ["Hello! I'm doing well, thank you for asking."]
langfuse_client.flush()
# Verify Langfuse HTTP calls were made
assert len(responses.calls) == 1
assert (
responses.calls[0].request.url == "https://langfuse.example.com/api/public/otel/v1/traces"
)
# quite complex to parse the full body, so just check that expected output is in there
assert b"Hello! I'm doing well, thank you for asking." not in responses.calls[0].request.body
assert b"REDACTED" in responses.calls[0].request.body
@pytest.mark.asyncio
@responses.activate
async def test_no_langfuse_span_when_disabled(agent_model, ui_messages, settings, langfuse_client):
"""Test Langfuse span is not created when Langfuse is disabled."""
settings.LANGFUSE_ENABLED = False
# Mock Langfuse HTTP endpoints (should not be called)
responses.add(
responses.POST,
"https://langfuse.example.com/api/public/ingestion",
json={"success": True},
status=200,
)
user = await sync_to_async(UserFactory)(allow_conversation_analytics=True)
conversation = await sync_to_async(ChatConversationFactory)(owner=user)
service = AIAgentService(conversation, user=user)
results = []
with service.conversation_agent.override(model=agent_model):
async for result in service.stream_text_async(ui_messages):
results.append(result)
# Verify that results were generated
assert results == ["Hello! I'm doing well, thank you for asking."]
langfuse_client.flush()
# Verify NO Langfuse HTTP calls were made
assert len(responses.calls) == 0
@pytest.mark.asyncio
async def test_instrumentation_settings_with_analytics_enabled(settings):
"""Test service correctly sets flags when Langfuse and analytics are enabled."""
# pylint: disable=protected-access
settings.LANGFUSE_ENABLED = True
user = await sync_to_async(UserFactory)(allow_conversation_analytics=True)
conversation = await sync_to_async(ChatConversationFactory)(owner=user)
service = AIAgentService(conversation, user=user)
# Verify that flags are set correctly
assert service._langfuse_available is True
assert service._store_analytics is True
# ConversationAgent should be created successfully
assert service.conversation_agent is not None
@pytest.mark.asyncio
async def test_instrumentation_settings_with_analytics_disabled(settings):
"""Test service correctly sets flags when Langfuse enabled but analytics disabled."""
# pylint: disable=protected-access
settings.LANGFUSE_ENABLED = True
user = await sync_to_async(UserFactory)(allow_conversation_analytics=False)
conversation = await sync_to_async(ChatConversationFactory)(owner=user)
service = AIAgentService(conversation, user=user)
# Verify that flags are set correctly
assert service._langfuse_available is True
assert service._store_analytics is False
# ConversationAgent should be created successfully
assert service.conversation_agent is not None
@pytest.mark.asyncio
async def test_instrumentation_disabled_when_langfuse_disabled(settings):
"""Test service correctly sets flags when Langfuse is disabled."""
# pylint: disable=protected-access
settings.LANGFUSE_ENABLED = False
user = await sync_to_async(UserFactory)(allow_conversation_analytics=True)
conversation = await sync_to_async(ChatConversationFactory)(owner=user)
service = AIAgentService(conversation, user=user)
# Verify that flags are set correctly
assert service._langfuse_available is False
assert service._store_analytics is False
# ConversationAgent should be created successfully
assert service.conversation_agent is not None
def test_store_analytics_flag_when_langfuse_enabled_and_user_allows(settings):
"""Test _store_analytics is True when Langfuse enabled and user allows analytics."""
# pylint: disable=protected-access
settings.LANGFUSE_ENABLED = True
user = UserFactory(allow_conversation_analytics=True)
conversation = ChatConversationFactory(owner=user)
service = AIAgentService(conversation, user=user)
assert service._langfuse_available is True
assert service._store_analytics is True
def test_store_analytics_flag_when_langfuse_enabled_and_user_disallows(settings):
"""Test _store_analytics is False when Langfuse enabled but user disallows analytics."""
# pylint: disable=protected-access
settings.LANGFUSE_ENABLED = True
user = UserFactory(allow_conversation_analytics=False)
conversation = ChatConversationFactory(owner=user)
service = AIAgentService(conversation, user=user)
assert service._langfuse_available is True
assert service._store_analytics is False
def test_store_analytics_flag_when_langfuse_disabled(settings):
"""Test _store_analytics is False when Langfuse is disabled."""
# pylint: disable=protected-access
settings.LANGFUSE_ENABLED = False
user = UserFactory(allow_conversation_analytics=True)
conversation = ChatConversationFactory(owner=user)
service = AIAgentService(conversation, user=user)
assert service._langfuse_available is False
assert service._store_analytics is False
@@ -0,0 +1,403 @@
"""
Unit tests for document generic search RAG tool functionality.
"""
import json
import logging
import httpx
import pytest
import responses
import respx
from asgiref.sync import sync_to_async
from pydantic_ai import Agent, RunContext, RunUsage
from core.factories import UserFactory
from chat.tools.document_generic_search_rag import (
add_document_rag_search_tool_from_setting,
get_specific_rag_search_tool_config,
)
pytestmark = pytest.mark.django_db()
def test_get_specific_rag_search_tool_config_with_disabled_features(settings):
"""Test get_specific_rag_search_tool_config returns tools for enabled features."""
user = UserFactory()
settings.SPECIFIC_RAG_DOCUMENT_SEARCH_TOOLS = {
"french_public_services": {
"collection_ids": [784, 785],
"feature_flag_value": "disabled",
"tool_description": (
"Use this tool when the user asks for information about French public services, "
"the French labor market, employment laws, social benefits, or "
"assistance with administrative procedures."
),
},
"legal_documents": {
"collection_ids": [100, 101, 102],
"feature_flag_value": "disabled",
"tool_description": "Use this tool to search French legal documents and laws.",
"rag_backend_name": "chat.tests.tools.test_document_generic_search_rag.MockRagBackend",
},
}
# The fixture tools are disabled by default
assert get_specific_rag_search_tool_config(user) == {}
def test_get_specific_rag_search_tool_config_with_enabled_features(settings):
"""Test get_specific_rag_search_tool_config returns tools for enabled features."""
user = UserFactory()
settings.SPECIFIC_RAG_DOCUMENT_SEARCH_TOOLS = {
"french_public_services": {
"collection_ids": [784, 785],
"feature_flag_value": "enabled",
"tool_description": (
"Use this tool when the user asks for information about French public services, "
"the French labor market, employment laws, social benefits, or "
"assistance with administrative procedures."
),
},
"legal_documents": {
"collection_ids": [100, 101, 102],
"feature_flag_value": "enabled",
"tool_description": "Use this tool to search French legal documents and laws.",
},
}
assert get_specific_rag_search_tool_config(user) == {
"french_public_services": {
"collection_ids": [784, 785],
"feature_flag_value": "enabled",
"tool_description": "Use this tool when the user "
"asks for information about "
"French public services, the "
"French labor market, "
"employment laws, social "
"benefits, or assistance with "
"administrative procedures.",
},
"legal_documents": {
"collection_ids": [100, 101, 102],
"feature_flag_value": "enabled",
"tool_description": "Use this tool to search French legal documents and laws.",
},
}
@responses.activate
def test_get_specific_rag_search_tool_config_with_dynamic_features(settings, posthog):
"""Test get_specific_rag_search_tool_config with dynamic features."""
user = UserFactory()
responses.post(
f"{posthog.host}/flags/?v=2",
json={"flags": {"legal-documents": {"enabled": True}}},
status=200,
)
settings.SPECIFIC_RAG_DOCUMENT_SEARCH_TOOLS = {
"french_public_services": {
"collection_ids": [784, 785],
"feature_flag_value": "dynamic",
"tool_description": (
"Use this tool when the user asks for information about French public services, "
"the French labor market, employment laws, social benefits, or "
"assistance with administrative procedures."
),
},
"legal_documents": {
"collection_ids": [100, 101, 102],
"feature_flag_value": "dynamic",
"tool_description": "Use this tool to search French legal documents and laws.",
},
}
assert get_specific_rag_search_tool_config(user) == {
"legal_documents": {
"collection_ids": [100, 101, 102],
"feature_flag_value": "dynamic",
"tool_description": "Use this tool to search French legal documents and laws.",
}
}
def test_add_document_rag_search_tool_from_setting_adds_tools(settings):
"""Test that add_document_rag_search_tool_from_setting adds tools to the agent."""
settings.SPECIFIC_RAG_DOCUMENT_SEARCH_TOOLS = {
"legal_documents": {
"collection_ids": [100, 101, 102],
"feature_flag_value": "enabled",
"tool_description": "Use this tool to search legal documents and laws.",
},
}
user = UserFactory()
agent = Agent("test")
assert len(agent._function_toolset.tools) == 0 # pylint: disable=protected-access
add_document_rag_search_tool_from_setting(agent, user)
# Check that tools were added
assert len(agent._function_toolset.tools) == 1 # pylint: disable=protected-access
assert agent._function_toolset.tools["legal_documents"].name == "legal_documents" # pylint: disable=protected-access
assert (
agent._function_toolset.tools["legal_documents"].description # pylint: disable=protected-access
== "Use this tool to search legal documents and laws."
)
assert agent._function_toolset.tools["legal_documents"].function_schema.json_schema == { # pylint: disable=protected-access
"additionalProperties": False,
"properties": {
"query": {"description": "The query to search information about.", "type": "string"}
},
"required": ["query"],
"type": "object",
}
def test_add_document_rag_search_tool_with_invalid_backend(settings, caplog):
"""Test that invalid backend import is handled gracefully."""
caplog.set_level(logging.WARNING, logger="chat.tools.document_generic_search_rag")
settings.SPECIFIC_RAG_DOCUMENT_SEARCH_TOOLS = {
"legal_documents": {
"collection_ids": [100, 101, 102],
"rag_backend_name": "non.existent.Backend",
"feature_flag_value": "enabled",
"tool_description": "Use this tool to search legal documents and laws.",
},
}
user = UserFactory()
agent = Agent("test")
add_document_rag_search_tool_from_setting(agent, user)
# Tool should not be added due to import error
assert len(agent._function_toolset.tools) == 0 # pylint: disable=protected-access
# Check that warning was logged
assert len(caplog.records) == 1
assert "Could not import RAG backend non.existent.Backend" in caplog.records[0].message
def test_add_document_rag_search_tool_with_missing_collection_ids(settings, caplog):
"""Test that missing collection_ids is handled gracefully."""
caplog.set_level(logging.WARNING, logger="chat.tools.document_generic_search_rag")
settings.SPECIFIC_RAG_DOCUMENT_SEARCH_TOOLS = {
"legal_documents": {
"feature_flag_value": "enabled",
"tool_description": "Use this tool to search legal documents and laws.",
},
}
user = UserFactory()
agent = Agent("test")
add_document_rag_search_tool_from_setting(agent, user)
# Tool should not be added due to import error
assert len(agent._function_toolset.tools) == 0 # pylint: disable=protected-access
# Check that warning was logged
assert len(caplog.records) == 1
assert "No collection IDs provided for tool legal_documents" in caplog.records[0].message
def test_add_document_rag_search_tool_with_missing_tool_description(settings, caplog):
"""Test that missing tool_description is handled gracefully."""
caplog.set_level(logging.WARNING, logger="chat.tools.document_generic_search_rag")
settings.SPECIFIC_RAG_DOCUMENT_SEARCH_TOOLS = {
"legal_documents": {
"collection_ids": [100, 101, 102],
"feature_flag_value": "enabled",
},
}
user = UserFactory()
agent = Agent("test")
add_document_rag_search_tool_from_setting(agent, user)
# Tool should not be added due to import error
assert len(agent._function_toolset.tools) == 0 # pylint: disable=protected-access
# Check that warning was logged
assert len(caplog.records) == 1
assert "No tool description provided for tool legal_documents" in caplog.records[0].message
@respx.mock
def test_document_search_rag_tool_execution(settings):
"""Test that the generated RAG tool executes correctly."""
search_mock = respx.post("https://albert.api.etalab.gouv.fr/v1/search").mock(
return_value=httpx.Response(
status_code=200,
json={
"data": [
{
"method": "semantic",
"chunk": {
"id": 1,
"content": "Relevant content snippet.",
"metadata": {"document_name": "doc1.txt"},
},
"score": 0.9,
}
],
"usage": {"prompt_tokens": 10, "completion_tokens": 20},
},
)
)
settings.SPECIFIC_RAG_DOCUMENT_SEARCH_TOOLS = {
"legal_documents": {
"collection_ids": [100, 101, 102],
"feature_flag_value": "enabled",
"tool_description": "Use this tool to search legal documents and laws.",
},
"legal_documents_2": {
"collection_ids": [200],
"feature_flag_value": "enabled",
"tool_description": "Use this tool to search legal documents and laws.",
},
}
user = UserFactory()
agent = Agent(model="test")
add_document_rag_search_tool_from_setting(agent, user)
result = agent.run_sync("What information can you find about French services?")
# Verify the result
assert json.loads(result.output) == {
"legal_documents": {"0": {"snippets": "Relevant content snippet.", "url": "doc1.txt"}},
"legal_documents_2": {"0": {"snippets": "Relevant content snippet.", "url": "doc1.txt"}},
}
assert len(search_mock.calls) == 2
assert json.loads(search_mock.calls[0].request.content) == {
"collections": [100, 101, 102],
"k": 4,
"prompt": "a",
"score_threshold": 0.6,
}
assert json.loads(search_mock.calls[1].request.content) == {
"collections": [200],
"k": 4,
"prompt": "a",
"score_threshold": 0.6,
}
def test_get_specific_rag_search_tool_config_with_empty_settings(settings):
"""Test get_specific_rag_search_tool_config with empty SPECIFIC_RAG_DOCUMENT_SEARCH_TOOLS."""
settings.SPECIFIC_RAG_DOCUMENT_SEARCH_TOOLS = {}
user = UserFactory()
config = get_specific_rag_search_tool_config(user)
assert config == {}
@pytest.mark.asyncio
@respx.mock
async def test_add_document_rag_search_tool_function_call(settings):
"""Test the function behavior."""
search_mock = respx.post("https://albert.api.etalab.gouv.fr/v1/search").mock(
return_value=httpx.Response(
status_code=200,
json={
"data": [
{
"method": "semantic",
"chunk": {
"id": 1,
"content": "Relevant content snippet.",
"metadata": {"document_name": "doc1.txt"},
},
"score": 0.9,
}
],
"usage": {"prompt_tokens": 10, "completion_tokens": 20},
},
)
)
settings.SPECIFIC_RAG_DOCUMENT_SEARCH_TOOLS = {
"legal_documents": {
"collection_ids": [100, 101, 102],
"feature_flag_value": "enabled",
"tool_description": "Use this tool to search legal documents and laws.",
},
}
user = await sync_to_async(UserFactory)()
agent = Agent("test")
add_document_rag_search_tool_from_setting(agent, user)
result = await agent._function_toolset.tools["legal_documents"].function( # pylint: disable=protected-access
RunContext(model="test", usage=RunUsage(), deps={}),
query="Find information about French laws.",
)
assert result.return_value == {
"0": {"snippets": "Relevant content snippet.", "url": "doc1.txt"}
}
assert result.metadata == {"sources": {"doc1.txt"}}
assert len(search_mock.calls) == 1
assert json.loads(search_mock.calls[0].request.content) == {
"collections": [100, 101, 102],
"k": 4,
"prompt": "Find information about French laws.",
"score_threshold": 0.6,
}
@pytest.mark.asyncio
@respx.mock
async def test_document_search_rag_http_status_error(settings, caplog):
"""Test that HTTPStatusError is properly handled and logged."""
caplog.set_level(logging.ERROR, logger="chat.tools.document_generic_search_rag")
# Mock the API to return a 500 error
respx.post("https://albert.api.etalab.gouv.fr/v1/search").mock(
return_value=httpx.Response(
status_code=500,
json={"error": "Internal server error"},
)
)
settings.SPECIFIC_RAG_DOCUMENT_SEARCH_TOOLS = {
"legal_documents": {
"collection_ids": [100, 101, 102],
"feature_flag_value": "enabled",
"tool_description": "Use this tool to search legal documents and laws.",
},
}
user = await sync_to_async(UserFactory)()
agent = Agent("test")
add_document_rag_search_tool_from_setting(agent, user)
# Call the tool function and expect a ModelRetry to be raised and caught
tool_result = await agent._function_toolset.tools["legal_documents"].function( # pylint: disable=protected-access
RunContext(model="test", usage=RunUsage(), deps={}),
query="Find information about French laws.",
)
# Verify the exception message
assert tool_result == (
"Document search service is currently unavailable: Server error '500 Internal "
"Server Error' for url 'https://albert.api.etalab.gouv.fr/v1/search'\n"
"For more information check: "
"https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/500 You must "
"explain this to the user and not try to answer based on your knowledge."
)
# Verify that error was logged
assert "RAG document search failed for tool legal_documents" in caplog.records[0].message
assert "Document search service is currently unavailable" in caplog.records[1].message
@@ -130,6 +130,16 @@ def test_post_conversation_data_protocol(api_client, mock_openai_stream):
assert mock_openai_stream.called
# ensure instructions are merged as a system prompt
last_request_payload = json.loads(respx.calls.last.request.content)
assert last_request_payload["messages"][0] == {
"content": (
"You are a helpful test assistant :)\n\nToday is Friday 25/07/2025.\n\n"
"Answer in english."
),
"role": "system",
}
chat_conversation.refresh_from_db()
assert chat_conversation.ui_messages == [
{
@@ -169,35 +179,23 @@ def test_post_conversation_data_protocol(api_client, mock_openai_stream):
parts=[TextUIPart(type="text", text="Hello there")],
)
_run_id = chat_conversation.pydantic_messages[0]["run_id"]
assert chat_conversation.pydantic_messages == [
{
"instructions": None,
"instructions": (
"You are a helpful test assistant :)\n\n"
"Today is Friday 25/07/2025.\n\nAnswer in english."
),
"kind": "request",
"parts": [
{
"content": "You are a helpful test assistant :)",
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": "2025-07-25T10:36:35.297675Z",
},
{
"content": "Today is Friday 25/07/2025.",
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": "2025-07-25T10:36:35.297675Z",
},
{
"content": "Answer in english.",
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": "2025-07-25T10:36:35.297675Z",
},
{
"content": ["Hello"],
"part_kind": "user-prompt",
"timestamp": "2025-07-25T10:36:35.297675Z",
},
],
"run_id": _run_id,
},
{
"finish_reason": "stop",
@@ -218,6 +216,7 @@ def test_post_conversation_data_protocol(api_client, mock_openai_stream):
"output_audio_tokens": 0,
"output_tokens": 0,
},
"run_id": _run_id,
},
]
@@ -252,6 +251,15 @@ def test_post_conversation_text_protocol(api_client, mock_openai_stream):
assert response_content == "Hello there"
assert mock_openai_stream.called
# ensure instructions are merged as a system prompt
last_request_payload = json.loads(respx.calls.last.request.content)
assert last_request_payload["messages"][0] == {
"content": (
"You are a helpful test assistant :)\n\nToday is Friday 25/07/2025.\n\n"
"Answer in english."
),
"role": "system",
}
chat_conversation.refresh_from_db()
assert chat_conversation.ui_messages == [
@@ -292,35 +300,23 @@ def test_post_conversation_text_protocol(api_client, mock_openai_stream):
parts=[TextUIPart(type="text", text="Hello there")],
)
_run_id = chat_conversation.pydantic_messages[0]["run_id"]
assert chat_conversation.pydantic_messages == [
{
"instructions": None,
"instructions": (
"You are a helpful test assistant :)\n\n"
"Today is Friday 25/07/2025.\n\nAnswer in english."
),
"kind": "request",
"parts": [
{
"content": "You are a helpful test assistant :)",
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": "2025-07-25T10:36:35.297675Z",
},
{
"content": "Today is Friday 25/07/2025.",
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": "2025-07-25T10:36:35.297675Z",
},
{
"content": "Answer in english.",
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": "2025-07-25T10:36:35.297675Z",
},
{
"content": ["Hello"],
"part_kind": "user-prompt",
"timestamp": "2025-07-25T10:36:35.297675Z",
},
],
"run_id": _run_id,
},
{
"finish_reason": "stop",
@@ -341,6 +337,7 @@ def test_post_conversation_text_protocol(api_client, mock_openai_stream):
"output_audio_tokens": 0,
"output_tokens": 0,
},
"run_id": _run_id,
},
]
@@ -403,11 +400,12 @@ def test_post_conversation_with_image(api_client, mock_openai_stream_image):
# Check the exact structure expected by the AI service
assert body["messages"] == [
{
"content": "You are a helpful test assistant :)",
"content": (
"You are a helpful test assistant :)\n\nToday is Friday 25/07/2025."
"\n\nAnswer in english."
),
"role": "system",
},
{"content": "Today is Friday 25/07/2025.", "role": "system"},
{"content": "Answer in english.", "role": "system"},
{
"content": [
{"text": "Hello, what do you see on this picture?", "type": "text"},
@@ -489,29 +487,15 @@ def test_post_conversation_with_image(api_client, mock_openai_stream_image):
parts=[TextUIPart(type="text", text="I see a cat in the picture.")],
)
_run_id = chat_conversation.pydantic_messages[0]["run_id"]
assert chat_conversation.pydantic_messages == [
{
"instructions": None,
"instructions": (
"You are a helpful test assistant :)\n\n"
"Today is Friday 25/07/2025.\n\nAnswer in english."
),
"kind": "request",
"parts": [
{
"content": "You are a helpful test assistant :)",
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": "2025-07-25T10:36:35.297675Z",
},
{
"content": "Today is Friday 25/07/2025.",
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": "2025-07-25T10:36:35.297675Z",
},
{
"content": "Answer in english.",
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": "2025-07-25T10:36:35.297675Z",
},
{
"content": [
"Hello, what do you see on this picture?",
@@ -530,6 +514,7 @@ def test_post_conversation_with_image(api_client, mock_openai_stream_image):
"timestamp": "2025-07-25T10:36:35.297675Z",
},
],
"run_id": _run_id,
},
{
"finish_reason": "stop",
@@ -550,6 +535,7 @@ def test_post_conversation_with_image(api_client, mock_openai_stream_image):
"output_audio_tokens": 0,
"output_tokens": 0,
},
"run_id": _run_id,
},
]
@@ -607,11 +593,12 @@ def test_post_conversation_tool_call(api_client, mock_openai_stream_tool, settin
assert body["messages"] == [
{
"content": "You are a helpful test assistant :)",
"content": (
"You are a helpful test assistant :)\n\n"
"Today is Friday 25/07/2025.\n\nAnswer in english."
),
"role": "system",
},
{"content": "Today is Friday 25/07/2025.", "role": "system"},
{"content": "Answer in english.", "role": "system"},
{"content": [{"text": "Weather in Paris?", "type": "text"}], "role": "user"},
]
@@ -666,35 +653,22 @@ def test_post_conversation_tool_call(api_client, mock_openai_stream_tool, settin
],
)
_run_id = chat_conversation.pydantic_messages[0]["run_id"]
assert chat_conversation.pydantic_messages == [
{
"instructions": None,
"instructions": (
"You are a helpful test assistant :)\n\n"
"Today is Friday 25/07/2025.\n\nAnswer in english."
),
"kind": "request",
"parts": [
{
"content": "You are a helpful test assistant :)",
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": "2025-07-25T10:36:35.297675Z",
},
{
"content": "Today is Friday 25/07/2025.",
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": "2025-07-25T10:36:35.297675Z",
},
{
"content": "Answer in english.",
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": "2025-07-25T10:36:35.297675Z",
},
{
"content": ["Weather in Paris?"],
"part_kind": "user-prompt",
"timestamp": "2025-07-25T10:36:35.297675Z",
},
],
"run_id": _run_id,
},
{
"finish_reason": "tool_call",
@@ -723,9 +697,13 @@ def test_post_conversation_tool_call(api_client, mock_openai_stream_tool, settin
"output_audio_tokens": 0,
"output_tokens": 0,
},
"run_id": _run_id,
},
{
"instructions": None,
"instructions": (
"You are a helpful test assistant :)\n\n"
"Today is Friday 25/07/2025.\n\nAnswer in english."
),
"kind": "request",
"parts": [
{
@@ -737,6 +715,7 @@ def test_post_conversation_tool_call(api_client, mock_openai_stream_tool, settin
"tool_name": "get_current_weather",
}
],
"run_id": _run_id,
},
{
"finish_reason": "stop",
@@ -759,6 +738,7 @@ def test_post_conversation_tool_call(api_client, mock_openai_stream_tool, settin
"output_audio_tokens": 0,
"output_tokens": 0,
},
"run_id": _run_id,
},
]
@@ -815,11 +795,12 @@ def test_post_conversation_tool_call_fails(api_client, mock_openai_stream_tool,
assert body["messages"] == [
{
"content": "You are a helpful test assistant :)",
"content": (
"You are a helpful test assistant :)\n\n"
"Today is Friday 25/07/2025.\n\nAnswer in french."
),
"role": "system",
},
{"content": "Today is Friday 25/07/2025.", "role": "system"},
{"content": "Answer in french.", "role": "system"},
{"content": [{"text": "Weather in Paris?", "type": "text"}], "role": "user"},
]
@@ -874,35 +855,22 @@ def test_post_conversation_tool_call_fails(api_client, mock_openai_stream_tool,
],
)
_run_id = chat_conversation.pydantic_messages[0]["run_id"]
assert chat_conversation.pydantic_messages == [
{
"instructions": None,
"instructions": (
"You are a helpful test assistant :)\n\n"
"Today is Friday 25/07/2025.\n\nAnswer in french."
),
"kind": "request",
"parts": [
{
"content": "You are a helpful test assistant :)",
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": "2025-07-25T10:36:35.297675Z",
},
{
"content": "Today is Friday 25/07/2025.",
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": "2025-07-25T10:36:35.297675Z",
},
{
"content": "Answer in french.",
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": "2025-07-25T10:36:35.297675Z",
},
{
"content": ["Weather in Paris?"],
"part_kind": "user-prompt",
"timestamp": "2025-07-25T10:36:35.297675Z",
},
],
"run_id": _run_id,
},
{
"finish_reason": "tool_call",
@@ -931,9 +899,13 @@ def test_post_conversation_tool_call_fails(api_client, mock_openai_stream_tool,
"output_audio_tokens": 0,
"output_tokens": 0,
},
"run_id": _run_id,
},
{
"instructions": None,
"instructions": (
"You are a helpful test assistant :)\n\n"
"Today is Friday 25/07/2025.\n\nAnswer in french."
),
"kind": "request",
"parts": [
{
@@ -944,6 +916,7 @@ def test_post_conversation_tool_call_fails(api_client, mock_openai_stream_tool,
"tool_name": "get_current_weather",
}
],
"run_id": _run_id,
},
{
"finish_reason": "stop",
@@ -966,6 +939,7 @@ def test_post_conversation_tool_call_fails(api_client, mock_openai_stream_tool,
"output_audio_tokens": 0,
"output_tokens": 0,
},
"run_id": _run_id,
},
]
@@ -1192,35 +1166,21 @@ def test_post_conversation_data_protocol_no_stream(
],
)
_run_id = chat_conversation.pydantic_messages[0]["run_id"]
assert chat_conversation.pydantic_messages == [
{
"instructions": None,
"instructions": (
"You are an amazing assistant.\n\nToday is Friday 25/07/2025.\n\nAnswer in english."
),
"kind": "request",
"parts": [
{
"content": "You are an amazing assistant.",
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": "2025-07-25T10:36:35.297675Z",
},
{
"content": "Today is Friday 25/07/2025.",
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": "2025-07-25T10:36:35.297675Z",
},
{
"content": "Answer in english.",
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": "2025-07-25T10:36:35.297675Z",
},
{
"content": ["Why the sky is blue?"],
"part_kind": "user-prompt",
"timestamp": "2025-07-25T10:36:35.297675Z",
},
],
"run_id": _run_id,
},
{
"finish_reason": "stop",
@@ -1248,6 +1208,7 @@ def test_post_conversation_data_protocol_no_stream(
"output_audio_tokens": 0,
"output_tokens": 135,
},
"run_id": _run_id,
},
]
@@ -1344,35 +1305,22 @@ async def test_post_conversation_async(api_client, mock_openai_stream, monkeypat
parts=[TextUIPart(type="text", text="Hello there")],
)
_run_id = chat_conversation.pydantic_messages[0]["run_id"]
assert chat_conversation.pydantic_messages == [
{
"instructions": None,
"instructions": (
"You are a helpful test assistant :)\n\n"
"Today is Friday 25/07/2025.\n\nAnswer in english."
),
"kind": "request",
"parts": [
{
"content": "You are a helpful test assistant :)",
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": "2025-07-25T10:36:35.297675Z",
},
{
"content": "Today is Friday 25/07/2025.",
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": "2025-07-25T10:36:35.297675Z",
},
{
"content": "Answer in english.",
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": "2025-07-25T10:36:35.297675Z",
},
{
"content": ["Hello"],
"part_kind": "user-prompt",
"timestamp": "2025-07-25T10:36:35.297675Z",
},
],
"run_id": _run_id,
},
{
"finish_reason": "stop",
@@ -1393,5 +1341,6 @@ async def test_post_conversation_async(api_client, mock_openai_stream, monkeypat
"output_audio_tokens": 0,
"output_tokens": 0,
},
"run_id": _run_id,
},
]
@@ -216,7 +216,8 @@ 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
sample_pdf_content,
@@ -351,59 +352,34 @@ def test_post_conversation_with_document_upload( # pylint: disable=too-many-arg
_formatted_date = formats.date_format(timezone.now(), "l d/m/Y", use_l10n=False)
assert len(chat_conversation.pydantic_messages) == 4
_run_id = chat_conversation.pydantic_messages[0]["run_id"]
assert chat_conversation.pydantic_messages[0] == {
"instructions": "When you receive a result from the summarization tool, you "
"MUST return it directly to the user without any "
"modification, paraphrasing, or additional summarization.The "
"tool already produces optimized summaries that should be "
"presented verbatim.You may translate the summary if "
"required, but you MUST preserve all the information from the "
"original summary.You may add a follow-up question after the "
"summary if needed.",
"instructions": "You are a helpful test assistant :)\n\n"
f"{today_promt_date}\n\n"
"Answer in english.\n\n"
"Use document_search_rag ONLY to retrieve specific passages from "
"attached documents. Do NOT use it to summarize; for summaries, "
"call the summarize tool instead.\n\nWhen you receive a result from the "
"summarization tool, you MUST return it directly to the user without "
"any modification, paraphrasing, or additional summarization."
"The tool already produces optimized summaries that should be "
"presented verbatim.You may translate the summary if required, "
"but you MUST preserve all the information from the original summary."
"You may add a follow-up question after the summary if needed.\n\n"
"[Internal context] User documents are attached to this conversation. "
"Do not request re-upload of documents; consider them already "
"available via the internal store.",
"kind": "request",
"parts": [
{
"content": "You are a helpful test assistant :)",
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": timezone_now,
},
{
"content": today_promt_date,
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": timezone_now,
},
{
"content": "Answer in english.",
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": timezone_now,
},
{
"content": "Use document_search_rag ONLY to retrieve specific "
"passages from attached documents. Do NOT use it to "
"summarize; for summaries, call the summarize tool "
"instead.",
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": timezone_now,
},
{
"content": "[Internal context] User documents are attached to this "
"conversation. Do not request re-upload of documents; "
"consider them already available via the internal "
"store.",
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": timezone_now,
},
{
"content": ["What does the document say?"],
"part_kind": "user-prompt",
"timestamp": timezone_now,
},
],
"run_id": _run_id,
}
assert chat_conversation.pydantic_messages[1] == {
"finish_reason": None,
@@ -432,17 +408,25 @@ def test_post_conversation_with_document_upload( # pylint: disable=too-many-arg
"output_audio_tokens": 0,
"output_tokens": 8,
},
"run_id": _run_id,
}
assert chat_conversation.pydantic_messages[2] == {
"instructions": (
"When you receive a result from the summarization tool, you MUST "
"return it directly to the user without any modification, "
"paraphrasing, or additional summarization."
"The tool already produces optimized summaries that should "
"be presented verbatim."
"You may translate the summary if required, but you MUST preserve "
"all the information from the original summary."
"You may add a follow-up question after the summary if needed."
"You are a helpful test assistant :)\n\n"
f"{today_promt_date}\n\n"
"Answer in english.\n\n"
"Use document_search_rag ONLY to retrieve specific passages from "
"attached documents. Do NOT use it to summarize; for summaries, "
"call the summarize tool instead.\n\nWhen you receive a result from the "
"summarization tool, you MUST return it directly to the user without "
"any modification, paraphrasing, or additional summarization."
"The tool already produces optimized summaries that should be "
"presented verbatim.You may translate the summary if required, "
"but you MUST preserve all the information from the original summary."
"You may add a follow-up question after the summary if needed.\n\n"
"[Internal context] User documents are attached to this conversation. "
"Do not request re-upload of documents; consider them already "
"available via the internal store."
),
"kind": "request",
"parts": [
@@ -461,6 +445,7 @@ def test_post_conversation_with_document_upload( # pylint: disable=too-many-arg
"tool_name": "document_search_rag",
}
],
"run_id": _run_id,
}
assert chat_conversation.pydantic_messages[3] == {
"finish_reason": None,
@@ -487,13 +472,15 @@ def test_post_conversation_with_document_upload( # pylint: disable=too-many-arg
"output_audio_tokens": 0,
"output_tokens": 12,
},
"run_id": _run_id,
}
@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
@@ -546,14 +533,12 @@ 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
@@ -576,6 +561,7 @@ 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",
@@ -637,7 +623,7 @@ 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
@@ -696,59 +682,35 @@ def test_post_conversation_with_document_upload_summarize( # pylint: disable=to
_formatted_date = formats.date_format(timezone.now(), "l d/m/Y", use_l10n=False)
assert len(chat_conversation.pydantic_messages) == 4
_run_id = chat_conversation.pydantic_messages[0]["run_id"]
assert chat_conversation.pydantic_messages[0] == {
"instructions": "When you receive a result from the summarization tool, you "
"MUST return it directly to the user without any "
"modification, paraphrasing, or additional summarization.The "
"tool already produces optimized summaries that should be "
"presented verbatim.You may translate the summary if "
"required, but you MUST preserve all the information from the "
"original summary.You may add a follow-up question after the "
"summary if needed.",
"instructions": (
"You are a helpful test assistant :)\n\n"
f"{today_promt_date}\n\n"
"Answer in english.\n\n"
"Use document_search_rag ONLY to retrieve specific passages from "
"attached documents. Do NOT use it to summarize; for summaries, "
"call the summarize tool instead.\n\nWhen you receive a result from the "
"summarization tool, you MUST return it directly to the user without "
"any modification, paraphrasing, or additional summarization."
"The tool already produces optimized summaries that should be "
"presented verbatim.You may translate the summary if required, "
"but you MUST preserve all the information from the original summary."
"You may add a follow-up question after the summary if needed.\n\n"
"[Internal context] User documents are attached to this conversation. "
"Do not request re-upload of documents; consider them already "
"available via the internal store."
),
"kind": "request",
"parts": [
{
"content": "You are a helpful test assistant :)",
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": timezone_now,
},
{
"content": today_promt_date,
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": timezone_now,
},
{
"content": "Answer in english.",
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": timezone_now,
},
{
"content": "Use document_search_rag ONLY to retrieve specific "
"passages from attached documents. Do NOT use it to "
"summarize; for summaries, call the summarize tool "
"instead.",
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": timezone_now,
},
{
"content": "[Internal context] User documents are attached to this "
"conversation. Do not request re-upload of documents; "
"consider them already available via the internal "
"store.",
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": timezone_now,
},
{
"content": ["Make a summary of this document."],
"part_kind": "user-prompt",
"timestamp": timezone_now,
},
],
"run_id": _run_id,
}
assert chat_conversation.pydantic_messages[1] == {
"finish_reason": None,
@@ -777,17 +739,25 @@ def test_post_conversation_with_document_upload_summarize( # pylint: disable=to
"output_audio_tokens": 0,
"output_tokens": 1,
},
"run_id": _run_id,
}
assert chat_conversation.pydantic_messages[2] == {
"instructions": (
"When you receive a result from the summarization tool, you MUST "
"return it directly to the user without any modification, "
"paraphrasing, or additional summarization."
"The tool already produces optimized summaries that should "
"be presented verbatim."
"You may translate the summary if required, but you MUST preserve "
"all the information from the original summary."
"You may add a follow-up question after the summary if needed."
"You are a helpful test assistant :)\n\n"
f"{today_promt_date}\n\n"
"Answer in english.\n\n"
"Use document_search_rag ONLY to retrieve specific passages from "
"attached documents. Do NOT use it to summarize; for summaries, "
"call the summarize tool instead.\n\nWhen you receive a result from the "
"summarization tool, you MUST return it directly to the user without "
"any modification, paraphrasing, or additional summarization."
"The tool already produces optimized summaries that should be "
"presented verbatim.You may translate the summary if required, "
"but you MUST preserve all the information from the original summary."
"You may add a follow-up question after the summary if needed.\n\n"
"[Internal context] User documents are attached to this conversation. "
"Do not request re-upload of documents; consider them already "
"available via the internal store."
),
"kind": "request",
"parts": [
@@ -800,6 +770,7 @@ def test_post_conversation_with_document_upload_summarize( # pylint: disable=to
"tool_name": "summarize",
}
],
"run_id": _run_id,
}
assert chat_conversation.pydantic_messages[3] == {
"finish_reason": None,
@@ -822,4 +793,5 @@ def test_post_conversation_with_document_upload_summarize( # pylint: disable=to
"output_audio_tokens": 0,
"output_tokens": 6,
},
"run_id": _run_id,
}
@@ -17,7 +17,6 @@ from pydantic_ai.messages import (
DocumentUrl,
ModelMessage,
ModelResponse,
SystemPromptPart,
TextPart,
UserPromptPart,
)
@@ -61,7 +60,8 @@ def fixture_sample_document_content():
@responses.activate
@freeze_time()
def test_post_conversation_with_local_pdf_document_url( # pylint: disable=too-many-arguments,too-many-positional-arguments
def test_post_conversation_with_local_pdf_document_url(
# pylint: disable=too-many-arguments,too-many-positional-arguments
api_client,
sample_document_content,
today_promt_date,
@@ -120,7 +120,7 @@ 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
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
@@ -129,11 +129,6 @@ def test_post_conversation_with_local_pdf_document_url( # pylint: disable=too-m
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?",
@@ -145,7 +140,10 @@ def test_post_conversation_with_local_pdf_document_url( # pylint: disable=too-m
],
timestamp=timezone.now(),
),
]
],
instructions=f"You are a helpful test assistant :)\n\n{today_promt_date}"
"\n\nAnswer in english.",
run_id=messages[0].run_id,
)
]
yield "This is a document about a single pixel."
@@ -217,29 +215,14 @@ def test_post_conversation_with_local_pdf_document_url( # pylint: disable=too-m
timestamp = timezone.now().strftime("%Y-%m-%dT%H:%M:%S.%fZ")
_formatted_date = formats.date_format(timezone.now(), "l d/m/Y", use_l10n=False)
_run_id = chat_conversation.pydantic_messages[0]["run_id"]
assert chat_conversation.pydantic_messages == [
{
"instructions": None,
"instructions": "You are a helpful test assistant :)\n\n"
f"{today_promt_date}\n\n"
"Answer in english.",
"kind": "request",
"parts": [
{
"content": "You are a helpful test assistant :)",
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": timestamp,
},
{
"content": today_promt_date,
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": timestamp,
},
{
"content": "Answer in english.",
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": timestamp,
},
{
"content": [
"What is in this document?",
@@ -256,6 +239,7 @@ def test_post_conversation_with_local_pdf_document_url( # pylint: disable=too-m
"timestamp": timestamp,
},
],
"run_id": _run_id,
},
{
"finish_reason": None,
@@ -282,6 +266,7 @@ def test_post_conversation_with_local_pdf_document_url( # pylint: disable=too-m
"output_audio_tokens": 0,
"output_tokens": 9,
},
"run_id": _run_id,
},
]
@@ -425,7 +410,6 @@ 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,
):
"""
@@ -433,6 +417,8 @@ 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",
@@ -468,27 +454,11 @@ 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?",
@@ -551,7 +521,7 @@ def test_post_conversation_with_local_document_url_in_history( # pylint: disabl
)
async def agent_model(messages: list[ModelMessage], _info: AgentInfo):
presigned_url = messages[0].parts[3].content[1].url
presigned_url = messages[0].parts[0].content[1].url
assert presigned_url.startswith("http://localhost:9000/conversations-media-storage/")
assert presigned_url.find("X-Amz-Signature=") != -1
assert presigned_url.find("X-Amz-Date=") != -1
@@ -560,18 +530,6 @@ def test_post_conversation_with_local_document_url_in_history( # pylint: disabl
assert messages == [
ModelRequest(
parts=[
SystemPromptPart(
content="You are a helpful test assistant :)",
timestamp=timezone.now(),
),
SystemPromptPart(
content=today_promt_date,
timestamp=timezone.now(),
),
SystemPromptPart(
content="Answer in english.",
timestamp=timezone.now(),
),
UserPromptPart(
content=[
"What is in this document?",
@@ -583,13 +541,18 @@ def test_post_conversation_with_local_document_url_in_history( # pylint: disabl
],
timestamp=timezone.now(),
),
]
],
instructions="You are a helpful test assistant :)\n\n"
"Today is Saturday 18/10/2025.\n\n"
"Answer in english.",
run_id=messages[0].run_id,
),
ModelResponse(
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(),
run_id=messages[1].run_id,
),
ModelRequest(
parts=[
@@ -599,7 +562,11 @@ def test_post_conversation_with_local_document_url_in_history( # pylint: disabl
],
timestamp=timezone.now(),
)
]
],
instructions="You are a helpful test assistant :)\n\n"
"Today is Saturday 18/10/2025.\n\n"
"Answer in english.",
run_id=messages[2].run_id,
),
]
yield "This is a document of square, very small and nice."
@@ -695,29 +662,14 @@ 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?",
@@ -734,6 +686,7 @@ def test_post_conversation_with_local_document_url_in_history( # pylint: disabl
"timestamp": "2025-10-18T20:48:20.286204Z",
},
],
# no run_id here
},
{
"finish_reason": None,
@@ -760,9 +713,12 @@ def test_post_conversation_with_local_document_url_in_history( # pylint: disabl
"output_audio_tokens": 0,
"output_tokens": 9,
},
# no run_id here
},
{
"instructions": None,
"instructions": "You are a helpful test assistant :)\n\n"
"Today is Saturday 18/10/2025.\n\n"
"Answer in english.",
"kind": "request",
"parts": [
{
@@ -771,6 +727,7 @@ def test_post_conversation_with_local_document_url_in_history( # pylint: disabl
"timestamp": "2025-10-18T20:48:20.286204Z",
}
],
"run_id": _run_id,
},
{
"finish_reason": None,
@@ -797,6 +754,7 @@ def test_post_conversation_with_local_document_url_in_history( # pylint: disabl
"output_audio_tokens": 0,
"output_tokens": 11,
},
"run_id": _run_id,
},
]
@@ -811,7 +769,8 @@ def test_post_conversation_with_local_document_url_in_history( # pylint: disabl
("data.csv", "text/csv"),
],
)
def test_post_conversation_with_local_not_pdf_document_url( # pylint: disable=too-many-arguments,too-many-positional-arguments
def test_post_conversation_with_local_not_pdf_document_url(
# pylint: disable=too-many-arguments,too-many-positional-arguments
api_client,
today_promt_date,
mock_ai_agent_service,
@@ -874,27 +833,6 @@ def test_post_conversation_with_local_not_pdf_document_url( # pylint: disable=t
assert messages == [
ModelRequest(
parts=[
SystemPromptPart(
content="You are a helpful test assistant :)", timestamp=timezone.now()
),
SystemPromptPart(content=today_promt_date, timestamp=timezone.now()),
SystemPromptPart(content="Answer in english.", timestamp=timezone.now()),
SystemPromptPart(
content=(
"Use document_search_rag ONLY to retrieve specific passages from "
"attached documents. Do NOT use it to summarize; for summaries, "
"call the summarize tool instead."
),
timestamp=timezone.now(),
),
SystemPromptPart(
content=(
"[Internal context] User documents are attached to this conversation. "
"Do not request re-upload of documents; consider them already "
"available via the internal store."
),
timestamp=timezone.now(),
),
UserPromptPart(
content=[
"What is in this document?",
@@ -904,15 +842,24 @@ def test_post_conversation_with_local_not_pdf_document_url( # pylint: disable=t
),
],
instructions=(
"When you receive a result from the summarization tool, you MUST "
"return it directly to the user without any modification, "
"paraphrasing, or additional summarization."
"The tool already produces optimized summaries that should "
"be presented verbatim."
"You may translate the summary if required, but you MUST preserve "
"all the information from the original summary."
"You may add a follow-up question after the summary if needed."
"You are a helpful test assistant :)\n\n"
f"{today_promt_date}\n\n"
"Answer in english.\n\n"
"Use document_search_rag ONLY to retrieve specific passages from "
"attached documents. Do NOT use it to summarize; for summaries, "
"call the summarize tool instead.\n\nWhen you receive a result "
"from the summarization tool, you MUST return it directly to "
"the user without any modification, paraphrasing, or additional "
"summarization.The tool already produces optimized summaries "
"that should be presented verbatim.You may translate the summary "
"if required, but you MUST preserve all the information from the "
"original summary.You may add a follow-up question after the "
"summary if needed.\n\n"
"[Internal context] User documents are attached to this conversation. "
"Do not request re-upload of documents; "
"consider them already available via the internal store."
),
run_id=messages[0].run_id,
)
]
yield "This is a document about you."
@@ -982,56 +929,29 @@ def test_post_conversation_with_local_not_pdf_document_url( # pylint: disable=t
timestamp = timezone.now().strftime("%Y-%m-%dT%H:%M:%S.%fZ")
_formatted_date = formats.date_format(timezone.now(), "l d/m/Y", use_l10n=False)
_run_id = chat_conversation.pydantic_messages[0]["run_id"]
assert chat_conversation.pydantic_messages == [
{
"instructions": (
"When you receive a result from the summarization tool, you MUST "
"return it directly to the user without any modification, "
"paraphrasing, or additional summarization."
"The tool already produces optimized summaries that should "
"be presented verbatim."
"You may translate the summary if required, but you MUST preserve "
"all the information from the original summary."
"You may add a follow-up question after the summary if needed."
"You are a helpful test assistant :)\n\n"
f"{today_promt_date}\n\n"
"Answer in english.\n\n"
"Use document_search_rag ONLY to retrieve specific passages from "
"attached documents. Do NOT use it to summarize; for summaries, "
"call the summarize tool instead.\n\nWhen you receive a result "
"from the summarization tool, you MUST return it directly to "
"the user without any modification, paraphrasing, or additional "
"summarization.The tool already produces optimized summaries "
"that should be presented verbatim.You may translate the summary "
"if required, but you MUST preserve all the information from the "
"original summary.You may add a follow-up question after the "
"summary if needed.\n\n"
"[Internal context] User documents are attached to this conversation. "
"Do not request re-upload of documents; "
"consider them already available via the internal store."
),
"kind": "request",
"parts": [
{
"content": "You are a helpful test assistant :)",
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": timestamp,
},
{
"content": today_promt_date,
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": timestamp,
},
{
"content": "Answer in english.",
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": timestamp,
},
{
"content": "Use document_search_rag ONLY to retrieve specific "
"passages from attached documents. Do NOT use it to "
"summarize; for summaries, call the summarize tool "
"instead.",
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": timestamp,
},
{
"content": "[Internal context] User documents are attached to "
"this conversation. Do not request re-upload of "
"documents; consider them already available via the "
"internal store.",
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": timestamp,
},
{
"content": [
"What is in this document?",
@@ -1040,6 +960,7 @@ def test_post_conversation_with_local_not_pdf_document_url( # pylint: disable=t
"timestamp": timestamp,
},
],
"run_id": _run_id,
},
{
"finish_reason": None,
@@ -1066,5 +987,6 @@ def test_post_conversation_with_local_not_pdf_document_url( # pylint: disable=t
"output_audio_tokens": 0,
"output_tokens": 7,
},
"run_id": _run_id,
},
]
@@ -919,7 +919,7 @@ 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 = [
@@ -1373,9 +1373,13 @@ def test_post_conversation_with_existing_tool_history(
# The pydantic_messages should include both the original tool calls and the new ones
assert len(history_conversation_with_tool.pydantic_messages) == 12 # Original 8 + 4 new ones
_run_id = history_conversation_with_tool.pydantic_messages[8]["run_id"]
# Verify the new tool call request is included
assert history_conversation_with_tool.pydantic_messages[8] == {
"instructions": None,
"instructions": "You are a helpful test assistant :)\n\n"
"Today is Friday 25/07/2025.\n\n"
"Answer in dutch.",
"kind": "request",
"parts": [
{
@@ -1384,6 +1388,7 @@ def test_post_conversation_with_existing_tool_history(
"timestamp": "2025-07-25T10:36:35.297675Z",
}
],
"run_id": _run_id,
}
assert history_conversation_with_tool.pydantic_messages[9] == {
@@ -1413,10 +1418,13 @@ def test_post_conversation_with_existing_tool_history(
"output_audio_tokens": 0,
"output_tokens": 0,
},
"run_id": _run_id,
}
assert history_conversation_with_tool.pydantic_messages[10] == {
"instructions": None,
"instructions": "You are a helpful test assistant :)\n\n"
"Today is Friday 25/07/2025.\n\n"
"Answer in dutch.",
"kind": "request",
"parts": [
{
@@ -1428,6 +1436,7 @@ def test_post_conversation_with_existing_tool_history(
"tool_name": "get_current_weather",
}
],
"run_id": _run_id,
}
assert history_conversation_with_tool.pydantic_messages[11] == {
@@ -1451,6 +1460,7 @@ def test_post_conversation_with_existing_tool_history(
"output_audio_tokens": 0,
"output_tokens": 0,
},
"run_id": _run_id,
}
@@ -2,7 +2,7 @@
import uuid
from django.utils import timezone
from django.utils import formats, timezone
import pytest
from dirty_equals import IsUUID
@@ -12,7 +12,6 @@ from pydantic_ai.messages import (
ImageUrl,
ModelMessage,
ModelResponse,
SystemPromptPart,
TextPart,
UserPromptPart,
)
@@ -87,22 +86,15 @@ def test_post_conversation_with_local_image_url(
)
async def agent_model(messages: list[ModelMessage], _info: AgentInfo):
presigned_url = messages[0].parts[3].content[1].url
assert presigned_url.startswith("http://localhost:9000/conversations-media-storage/")
presigned_url = messages[0].parts[0].content[1].url
# assert presigned_url.startswith("http://localhost:9000/conversations-media-storage/")
assert presigned_url.find("X-Amz-Signature=") != -1
assert presigned_url.find("X-Amz-Date=") != -1
assert presigned_url.find("X-Amz-Expires=") != -1
formatted_date = formats.date_format(timezone.now(), "l d/m/Y", use_l10n=False)
assert messages == [
ModelRequest(
parts=[
SystemPromptPart(
content="You are a helpful test assistant :)", timestamp=timezone.now()
),
SystemPromptPart(
content="Today is Saturday 18/10/2025.", timestamp=timezone.now()
),
SystemPromptPart(content="Answer in english.", timestamp=timezone.now()),
UserPromptPart(
content=[
"What is in this image?",
@@ -114,7 +106,10 @@ 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,
)
]
yield "This is an image of a single pixel."
@@ -180,29 +175,13 @@ def test_post_conversation_with_local_image_url(
],
)
_run_id = chat_conversation.pydantic_messages[0]["run_id"]
assert chat_conversation.pydantic_messages == [
{
"instructions": None,
"instructions": "You are a helpful test assistant :)\n\n"
"Today is Saturday 18/10/2025.\n\nAnswer in english.",
"kind": "request",
"parts": [
{
"content": "You are a helpful test assistant :)",
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": "2025-10-18T20:48:20.286204Z",
},
{
"content": "Today is Saturday 18/10/2025.",
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": "2025-10-18T20:48:20.286204Z",
},
{
"content": "Answer in english.",
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": "2025-10-18T20:48:20.286204Z",
},
{
"content": [
"What is in this image?",
@@ -219,6 +198,7 @@ def test_post_conversation_with_local_image_url(
"timestamp": "2025-10-18T20:48:20.286204Z",
},
],
"run_id": _run_id,
},
{
"finish_reason": None,
@@ -241,6 +221,7 @@ def test_post_conversation_with_local_image_url(
"output_audio_tokens": 0,
"output_tokens": 9,
},
"run_id": _run_id,
},
]
@@ -282,11 +263,6 @@ def test_post_conversation_with_local_image_wrong_url(
assert messages == [
ModelRequest(
parts=[
SystemPromptPart(
content="You are a helpful test assistant :)", timestamp=timezone.now()
),
SystemPromptPart(content=today_promt_date, timestamp=timezone.now()),
SystemPromptPart(content="Answer in english.", timestamp=timezone.now()),
UserPromptPart(
content=[
"What is in this image?",
@@ -298,7 +274,10 @@ def test_post_conversation_with_local_image_wrong_url(
],
timestamp=timezone.now(),
),
]
],
instructions=f"You are a helpful test assistant :)\n\n{today_promt_date}"
"\n\nAnswer in english.",
run_id=messages[0].run_id,
)
]
yield "cannot read image." # IRL a 400 error would be raised by the LLM
@@ -369,11 +348,6 @@ def test_post_conversation_with_remote_image_url(
assert messages == [
ModelRequest(
parts=[
SystemPromptPart(
content="You are a helpful test assistant :)", timestamp=timezone.now()
),
SystemPromptPart(content=today_promt_date, timestamp=timezone.now()),
SystemPromptPart(content="Answer in english.", timestamp=timezone.now()),
UserPromptPart(
content=[
"What is in this image?",
@@ -385,7 +359,10 @@ def test_post_conversation_with_remote_image_url(
],
timestamp=timezone.now(),
),
]
],
instructions="You are a helpful test assistant :)\n\n"
f"{today_promt_date}\n\nAnswer in english.",
run_id=messages[0].run_id,
)
]
yield "This is an image of a single pixel."
@@ -498,27 +475,10 @@ def test_post_conversation_with_local_image_url_in_history(
],
pydantic_messages=[
{
"instructions": None,
"instructions": f"You are a helpful test assistant :)\n\n{today_promt_date}"
"\n\nAnswer in english.",
"kind": "request",
"parts": [
{
"content": "You are a helpful test assistant :)",
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": "2025-10-18T20:48:20.286204Z",
},
{
"content": today_promt_date,
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": "2025-10-18T20:48:20.286204Z",
},
{
"content": "Answer in english.",
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": "2025-10-18T20:48:20.286204Z",
},
{
"content": [
"What is in this image?",
@@ -581,7 +541,7 @@ def test_post_conversation_with_local_image_url_in_history(
)
async def agent_model(messages: list[ModelMessage], _info: AgentInfo):
presigned_url = messages[0].parts[3].content[1].url
presigned_url = messages[0].parts[0].content[1].url
assert presigned_url.startswith("http://localhost:9000/conversations-media-storage/")
assert presigned_url.find("X-Amz-Signature=") != -1
assert presigned_url.find("X-Amz-Date=") != -1
@@ -590,18 +550,6 @@ def test_post_conversation_with_local_image_url_in_history(
assert messages == [
ModelRequest(
parts=[
SystemPromptPart(
content="You are a helpful test assistant :)",
timestamp=timezone.now(),
),
SystemPromptPart(
content=today_promt_date,
timestamp=timezone.now(),
),
SystemPromptPart(
content="Answer in english.",
timestamp=timezone.now(),
),
UserPromptPart(
content=[
"What is in this image?",
@@ -613,7 +561,9 @@ def test_post_conversation_with_local_image_url_in_history(
],
timestamp=timezone.now(),
),
]
],
instructions="You are a helpful test assistant :)\n\n"
f"{today_promt_date}\n\nAnswer in english.",
),
ModelResponse(
parts=[TextPart(content="This is an image of a single pixel.")],
@@ -629,7 +579,10 @@ def test_post_conversation_with_local_image_url_in_history(
],
timestamp=timezone.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.",
),
]
yield "This is an image of square, very small and nice."
@@ -725,29 +678,13 @@ def test_post_conversation_with_local_image_url_in_history(
],
)
_run_id = chat_conversation.pydantic_messages[2]["run_id"]
assert chat_conversation.pydantic_messages == [
{
"instructions": None,
"instructions": f"You are a helpful test assistant :)\n\n{today_promt_date}"
"\n\nAnswer in english.",
"kind": "request",
"parts": [
{
"content": "You are a helpful test assistant :)",
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": "2025-10-18T20:48:20.286204Z",
},
{
"content": today_promt_date,
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": "2025-10-18T20:48:20.286204Z",
},
{
"content": "Answer in english.",
"dynamic_ref": None,
"part_kind": "system-prompt",
"timestamp": "2025-10-18T20:48:20.286204Z",
},
{
"content": [
"What is in this image?",
@@ -788,7 +725,8 @@ def test_post_conversation_with_local_image_url_in_history(
},
},
{
"instructions": None,
"instructions": "You are a helpful test assistant :)\n\nToday is Saturday 18/10/2025."
"\n\nAnswer in english.",
"kind": "request",
"parts": [
{
@@ -797,6 +735,7 @@ def test_post_conversation_with_local_image_url_in_history(
"timestamp": "2025-10-18T20:48:20.286204Z",
}
],
"run_id": _run_id,
},
{
"finish_reason": None,
@@ -823,5 +762,6 @@ def test_post_conversation_with_local_image_url_in_history(
"output_audio_tokens": 0,
"output_tokens": 11,
},
"run_id": _run_id,
},
]
@@ -1,4 +1,4 @@
"""Test the post_stop_steaming view."""
"""Test the post_stop_streaming view."""
from unittest.mock import patch
+873
View File
@@ -0,0 +1,873 @@
"""Data analysis tool for tabular files (CSV, Excel)."""
import base64
import functools
import json
import logging
import uuid
from io import BytesIO
from typing import Any, Dict
import matplotlib
import numpy as np
matplotlib.use("Agg") # Use non-interactive backend
import matplotlib.pyplot as plt
import pandas as pd
from django.conf import settings
from django.core.files.storage import default_storage
from django.db.models import Q
from asgiref.sync import sync_to_async
from pydantic_ai import Agent, RunContext
from pydantic_ai.exceptions import ModelRetry
from pydantic_ai.messages import ToolReturn
from core.file_upload.enums import AttachmentStatus
from core.file_upload.utils import generate_retrieve_policy
from chat.agents.base import BaseAgent, prepare_custom_model
from chat.models import ChatConversationAttachment
from chat.tools.exceptions import ModelCannotRetry
from chat.tools.utils import last_model_retry_soft_fail
logger = logging.getLogger(__name__)
# MIME types for tabular files
TABULAR_MIME_TYPES = [
"text/csv",
"application/csv",
"application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
"application/vnd.ms-excel",
"application/excel",
]
@sync_to_async
def read_tabular_file(attachment) -> bytes:
"""Read tabular file content asynchronously."""
with default_storage.open(attachment.key, "rb") as f:
return f.read()
def detect_csv_separator(file_data: bytes) -> str:
"""
Detect the CSV separator by analyzing the first few lines.
Returns the most likely separator: ',', ';', or '\t'
"""
# Read first 10KB to analyze
sample = file_data[:10240].decode("utf-8", errors="ignore")
lines = sample.split("\n")[:10] # First 10 lines
if not lines:
return "," # Default to comma
# Count occurrences of each separator in the first few lines
comma_count = sum(line.count(",") for line in lines)
semicolon_count = sum(line.count(";") for line in lines)
tab_count = sum(line.count("\t") for line in lines)
# Return the separator with the highest count
if tab_count > comma_count and tab_count > semicolon_count:
return "\t"
elif semicolon_count > comma_count:
return ";"
else:
return "," # Default to comma
def _convert_to_serializable(obj: Any) -> Any:
"""
Convert pandas/numpy types to Python native types for JSON serialization.
Handles:
- pandas DataFrame/Series
- numpy scalars (int64, float64, etc.)
- numpy arrays
- pandas Timestamp
- Other non-serializable types
Args:
obj: The object to convert.
Returns:
A JSON-serializable version of the object.
"""
# Handle pandas DataFrame
if isinstance(obj, pd.DataFrame):
# Limit number of rows to avoid huge responses
if len(obj) > 1000:
obj = obj.head(1000)
logger.warning("Result truncated to 1000 rows")
return obj.to_dict(orient="records")
# Handle pandas Series
if isinstance(obj, pd.Series):
# Convert Series to dict, handling index
result_dict = obj.to_dict()
# Convert any numpy/pandas types in the values
return {str(k): _convert_to_serializable(v) for k, v in result_dict.items()}
# Handle numpy scalars
if isinstance(obj, (np.integer, np.floating)):
return obj.item() # Convert to Python native int/float
# Handle numpy arrays
if isinstance(obj, np.ndarray):
return obj.tolist()
# Handle pandas Timestamp
if isinstance(obj, pd.Timestamp):
return obj.isoformat()
# Handle lists and tuples - recursively convert elements
if isinstance(obj, (list, tuple)):
return [_convert_to_serializable(item) for item in obj]
# Handle dicts - recursively convert values
if isinstance(obj, dict):
return {str(k): _convert_to_serializable(v) for k, v in obj.items()}
# Handle None, bool, int, float, str - these are already serializable
if obj is None or isinstance(obj, (bool, int, float, str)):
return obj
# Fallback: try to convert to string
try:
return str(obj)
except Exception:
logger.warning("Could not serialize object of type %s, returning None", type(obj))
return None
def _is_valid_excel_file(file_data: bytes, file_name: str) -> bool:
"""
Check if the file data appears to be a valid Excel file.
XLSX files are ZIP archives, so they should start with ZIP signature (PK\x03\x04).
XLS files have a different signature.
"""
if not file_data:
return False
file_lower = file_name.lower()
# Check for XLSX (ZIP-based) signature
if file_lower.endswith((".xlsx", ".xlsm", ".xlsb")):
# XLSX files are ZIP archives, should start with PK\x03\x04
return file_data[:4] == b"PK\x03\x04"
# Check for XLS (OLE2) signature
if file_lower.endswith(".xls"):
# XLS files are OLE2 compound documents, should start with specific signature
# Common signatures: 0xD0CF11E0 (OLE2) or 0x504B0304 (sometimes saved as ZIP)
return (
file_data[:4] == b"\xd0\xcf\x11\xe0" # OLE2 signature
or file_data[:4] == b"PK\x03\x04" # Sometimes XLS are actually ZIP
)
return False
@sync_to_async
def load_dataframe(file_data: bytes, content_type: str, file_name: str) -> Dict[str, pd.DataFrame]:
"""
Load tabular file into pandas DataFrames.
Returns a dictionary mapping sheet/table names to DataFrames.
For CSV files, uses 'default' as the key.
For Excel files, uses sheet names as keys.
"""
try:
# Handle CSV files - also accept text/plain if file extension is .csv
if content_type in ["text/csv", "application/csv"] or (
content_type == "text/plain" and file_name.lower().endswith(".csv")
):
# Detect the separator
separator = detect_csv_separator(file_data)
logger.debug("Detected CSV separator: %r", separator)
# Read CSV with detected separator
df = pd.read_csv(
BytesIO(file_data),
sep=separator,
on_bad_lines="skip", # Skip problematic lines
engine="python", # More flexible parser
encoding="utf-8",
)
if df.empty:
raise ValueError("CSV file appears to be empty or could not be parsed")
return {"default": df}
elif content_type in [
"application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
"application/vnd.ms-excel",
"application/excel",
] or file_name.lower().endswith((".xlsx", ".xls", ".xlsm", ".xlsb")):
# Validate Excel file format before attempting to read
if not _is_valid_excel_file(file_data, file_name):
logger.warning(
"File '%s' does not appear to be a valid Excel file. "
"File size: %d bytes, First bytes: %r",
file_name,
len(file_data),
file_data[:20] if len(file_data) >= 20 else file_data,
)
raise ValueError(
f"File '{file_name}' does not appear to be a valid Excel file. "
"It may be corrupted or in an unsupported format."
)
file_lower = file_name.lower()
dataframes = {}
# Try different engines based on file extension
if file_lower.endswith(".xls"):
# Old Excel format - try xlrd engine
try:
logger.debug("Attempting to read .xls file with xlrd engine")
excel_file = pd.ExcelFile(BytesIO(file_data), engine="xlrd")
dataframes = {
sheet_name: excel_file.parse(sheet_name)
for sheet_name in excel_file.sheet_names
}
except Exception as xlrd_error:
logger.warning("Failed to read .xls with xlrd: %s", xlrd_error)
# Fallback: try openpyxl (sometimes .xls files are actually .xlsx)
try:
logger.debug("Trying openpyxl as fallback for .xls file")
excel_file = pd.ExcelFile(BytesIO(file_data), engine="openpyxl")
dataframes = {
sheet_name: excel_file.parse(sheet_name)
for sheet_name in excel_file.sheet_names
}
except Exception as openpyxl_error:
logger.error("Failed to read .xls with both engines: %s", openpyxl_error)
raise ValueError(
f"Failed to read Excel file '{file_name}': "
f"xlrd error: {xlrd_error}, openpyxl error: {openpyxl_error}"
) from openpyxl_error
else:
# XLSX format - try openpyxl first
try:
logger.debug("Attempting to read Excel file with openpyxl engine")
excel_file = pd.ExcelFile(BytesIO(file_data), engine="openpyxl")
dataframes = {
sheet_name: excel_file.parse(sheet_name)
for sheet_name in excel_file.sheet_names
}
except Exception as openpyxl_error:
logger.warning("Failed to read with openpyxl: %s", openpyxl_error)
# Try calamine engine if available (faster and more robust)
try:
logger.debug("Trying calamine engine as fallback")
excel_file = pd.ExcelFile(BytesIO(file_data), engine="calamine")
dataframes = {
sheet_name: excel_file.parse(sheet_name)
for sheet_name in excel_file.sheet_names
}
except ImportError:
logger.debug("calamine engine not available")
raise ValueError(
f"Failed to read Excel file '{file_name}' with openpyxl: {openpyxl_error}. "
"The file may be corrupted or in an unsupported format."
) from openpyxl_error
except Exception as calamine_error:
logger.error("Failed to read with calamine: %s", calamine_error)
raise ValueError(
f"Failed to read Excel file '{file_name}': "
f"openpyxl error: {openpyxl_error}, calamine error: {calamine_error}"
) from calamine_error
if not dataframes:
raise ValueError(f"Excel file '{file_name}' contains no readable sheets")
logger.info(
"Successfully loaded Excel file '%s' with %d sheet(s): %s",
file_name,
len(dataframes),
list(dataframes.keys()),
)
return dataframes
else:
raise ValueError(f"Unsupported content type: {content_type}")
except Exception as e:
logger.error("Error loading tabular file: %s", e, exc_info=True)
raise ModelCannotRetry(f"Failed to load file: {str(e)}") from e
def generate_metadata(dataframes: Dict[str, pd.DataFrame], file_name: str) -> Dict[str, Any]:
"""
Generate metadata about the tabular file.
Returns:
Dictionary containing:
- sheets: List of sheet/table names
- schemas: Dictionary mapping sheet names to their schemas
- row_counts: Dictionary mapping sheet names to row counts
- column_info: Dictionary mapping sheet names to column information
"""
metadata = {
"file_name": file_name,
"sheets": list(dataframes.keys()),
"schemas": {},
"row_counts": {},
"column_info": {},
}
for sheet_name, df in dataframes.items():
# Schema: column names and types
metadata["schemas"][sheet_name] = {
col: str(dtype) for col, dtype in df.dtypes.items()
}
# Row count
metadata["row_counts"][sheet_name] = len(df)
# Column info: name, type, sample values, null counts
metadata["column_info"][sheet_name] = {}
for col in df.columns:
col_info = {
"type": str(df[col].dtype),
"null_count": int(df[col].isna().sum()),
"unique_count": int(df[col].nunique()),
}
# Add sample values (non-null)
sample_values = df[col].dropna().head(5).tolist()
if sample_values:
col_info["sample_values"] = [str(v) for v in sample_values]
metadata["column_info"][sheet_name][col] = col_info
return metadata
async def generate_query(
user_query: str, metadata: Dict[str, Any], query_agent: BaseAgent, ctx: RunContext
) -> str:
"""
Use an LLM agent to generate a pandas query from user query and file metadata.
"""
metadata_str = json.dumps(metadata, indent=2)
prompt = f"""You are a data analysis assistant. Given a user query and file metadata, generate a Python pandas query to answer the question.
File metadata:
{metadata_str}
User query: {user_query}
Generate a Python code snippet that:
1. Uses pandas operations (filter, groupby, aggregate, etc.)
2. Works with the dataframes loaded in memory (available as 'dataframes' dict)
3. Assigns the final result to a variable named 'result'
4. Handles the specific sheet/table if multiple sheets exist
5. ALWAYS handles NaN/NA values in boolean conditions using .notna() or .fillna() before filtering
6. If the user asks for a plot/graph/chart, create it using matplotlib and save to 'plot_image' variable as base64
IMPORTANT RULES:
- The code MUST assign the final result to a variable named 'result'
- When filtering with conditions, ALWAYS check for NaN first: df[df['col'].notna() & (df['col'] > value)]
- Use .dropna() if you need to remove rows with missing values
- Use .fillna() if you need to replace missing values
- If plotting: use plt (already imported), create the plot, convert to base64:
```python
plt.figure(figsize=(10, 6))
# ... your plot code ...
buf = BytesIO()
plt.savefig(buf, format='png')
buf.seek(0)
plot_image = base64.b64encode(buf.getvalue()).decode('utf-8')
plt.close()
```
NOTE: Do NOT use import statements - plt, base64, BytesIO are already available.
Return ONLY the Python code, without markdown formatting or explanations. The code should be executable and use variables:
- 'dataframes': dict mapping sheet names to DataFrames
- Sheet names available: {', '.join(metadata['sheets'])}
Example format (without plot):
df = dataframes['default']
df = df[df['column'].notna()] # Remove NaN values first
result = df[df['column'] > 100].groupby('category').sum()
Example format (with plot):
df = dataframes['default']
plt.figure(figsize=(10, 6))
plt.plot(df.index, df['close'])
plt.xlabel('Index')
plt.ylabel('Close')
plt.title('Close vs Index')
buf = BytesIO()
plt.savefig(buf, format='png')
buf.seek(0)
plot_image = base64.b64encode(buf.getvalue()).decode('utf-8')
plt.close()
result = "Plot generated successfully. The plot image has been saved and is available in the tool response."
IMPORTANT:
- Do NOT use import statements in the code. All necessary modules (pd, plt, np, base64, BytesIO) are already available. Do NOT use anything else than these modules.
- When returning the result text, mention that a plot was generated and will be available in the response, but do NOT include the URL in the text - the system will handle displaying it.
Generate the query code:"""
try:
response = await query_agent.run(prompt, usage=ctx.usage)
query_code = response.output.strip()
# Extract code from markdown code blocks if present
if "```python" in query_code:
query_code = query_code.split("```python")[1].split("```")[0].strip()
elif "```" in query_code:
query_code = query_code.split("```")[1].split("```")[0].strip()
return query_code
except Exception as e:
logger.error("Error generating query: %s", e, exc_info=True)
raise ModelRetry("Failed to generate query. Please try rephrasing your question.") from e
@sync_to_async
def execute_query(query_code: str, dataframes: Dict[str, pd.DataFrame]) -> Any:
"""
Execute the generated pandas query safely.
Note: Uses exec() in a restricted environment. The query code is generated
by an LLM based on file metadata, so it should be relatively safe, but
we restrict the available builtins and globals.
"""
try:
# Pre-process dataframes to handle common issues
processed_dataframes = {}
for name, df in dataframes.items():
# Make a copy to avoid modifying original
df_processed = df.copy()
# Replace common NaN representations
df_processed = df_processed.replace(["", " ", "nan", "NaN", "None", "null"], pd.NA)
processed_dataframes[name] = df_processed
# Create a safe execution environment
safe_globals = {
"pd": pd,
"plt": plt,
"np": np,
"base64": base64,
"BytesIO": BytesIO,
"dataframes": processed_dataframes,
"__builtins__": {
"len": len,
"str": str,
"int": int,
"float": float,
"bool": bool,
"list": list,
"dict": dict,
"set": set,
"tuple": tuple,
"range": range,
"sum": sum,
"max": max,
"min": min,
"abs": abs,
"round": round,
},
}
# Clean up query code - remove any import statements that might cause issues
# Split by lines and filter out import statements
lines = query_code.split("\n")
cleaned_lines = [
line
for line in lines
if not line.strip().startswith("import ") and not line.strip().startswith("from ")
]
query_code = "\n".join(cleaned_lines)
# Execute the query in a restricted namespace
local_vars = {}
exec(query_code, safe_globals, local_vars) # noqa: S102
# Get the result - check if 'result' variable exists, otherwise try 'df'
if "result" in local_vars:
result = local_vars["result"]
elif "df" in local_vars:
result = local_vars["df"]
else:
# If no explicit result variable, get the last expression
# This is a fallback - ideally the LLM should assign to 'result'
raise ValueError("Query must assign result to 'result' variable")
# Check if a plot was generated
plot_image = None
if "plot_image" in local_vars:
plot_image = local_vars["plot_image"]
logger.info("Plot image generated")
# Convert result to a serializable format
result = _convert_to_serializable(result)
return {"result": result, "plot_image": plot_image}
except Exception as e:
logger.error("Error executing query: %s", e, exc_info=True)
# Provide more helpful error message
error_msg = str(e)
if "NaN" in error_msg or "NA" in error_msg:
error_msg = (
f"{error_msg}. "
"The query may need to handle missing values (NaN/NA) using .notna() or .dropna() before filtering."
)
raise ModelCannotRetry(f"Failed to execute query: {error_msg}") from e
@last_model_retry_soft_fail
async def data_analysis(ctx: RunContext, query: str) -> ToolReturn:
"""
Analyze tabular data files (CSV, Excel) based on user query.
Can also generate plots/graphs/charts.
This tool:
1. Loads the tabular file(s) from attachments
2. Generates metadata about the file structure
3. Uses an LLM to generate a pandas query based on user query
4. Executes the query and returns results
Args:
ctx (RunContext): The run context containing the conversation.
query (str): The user's data analysis question.
Returns:
ToolReturn: Contains the analysis results and metadata.
"""
try:
# Find tabular files in attachments
# First, get all attachments for debugging
all_attachments = await sync_to_async(list)(
ctx.deps.conversation.attachments.all()
)
logger.info(
"All attachments in conversation: %s",
[
{
"file_name": a.file_name,
"content_type": a.content_type,
"upload_state": a.upload_state,
"conversion_from": a.conversion_from,
}
for a in all_attachments
],
)
# Find tabular files - exclude converted files (they have conversion_from set)
# First try by content_type
tabular_attachments_by_type = await sync_to_async(list)(
ctx.deps.conversation.attachments.filter(
content_type__in=TABULAR_MIME_TYPES,
upload_state=AttachmentStatus.READY,
)
.filter(
Q(conversion_from__isnull=True) | Q(conversion_from="")
)
)
# If no files found by content_type, try by file extension as fallback
# (some systems detect CSV as text/plain instead of text/csv)
if not tabular_attachments_by_type:
csv_extensions = [".csv", ".xlsx", ".xls"]
all_ready_attachments = await sync_to_async(list)(
ctx.deps.conversation.attachments.filter(
upload_state=AttachmentStatus.READY,
)
.filter(
Q(conversion_from__isnull=True) | Q(conversion_from="")
)
)
tabular_attachments = [
att
for att in all_ready_attachments
if any(att.file_name.lower().endswith(ext) for ext in csv_extensions)
# Exclude Markdown files (converted files have .md extension or content_type text/markdown)
and not att.file_name.lower().endswith(".md")
and att.content_type != "text/markdown"
]
if tabular_attachments:
logger.info(
"Found %d tabular file(s) by extension fallback (content_type was not recognized): %s",
len(tabular_attachments),
[f"{a.file_name} ({a.content_type})" for a in tabular_attachments],
)
else:
tabular_attachments = tabular_attachments_by_type
# If still no files found, check if there are converted files that might have originals
# This handles the case where an Excel file was converted to Markdown for RAG
if not tabular_attachments:
# Look for converted files with tabular extensions
csv_extensions = [".csv", ".xlsx", ".xls"]
converted_attachments = await sync_to_async(list)(
ctx.deps.conversation.attachments.filter(
upload_state=AttachmentStatus.READY,
)
.exclude(
Q(conversion_from__isnull=True) | Q(conversion_from="")
)
)
# For each converted file, try to find the original
for converted_att in converted_attachments:
if any(converted_att.file_name.lower().endswith(ext) for ext in csv_extensions):
# Try to find the original file using conversion_from key
original_key = converted_att.conversion_from
if original_key:
original_attachment = await sync_to_async(
ctx.deps.conversation.attachments.filter(
key=original_key,
upload_state=AttachmentStatus.READY,
).first
)()
if original_attachment:
logger.info(
"Found original file '%s' for converted file '%s'",
original_attachment.file_name,
converted_att.file_name,
)
tabular_attachments.append(original_attachment)
break
logger.info(
"Found %d tabular attachment(s): %s",
len(tabular_attachments),
[f"{a.file_name} ({a.content_type})" for a in tabular_attachments],
)
if not tabular_attachments:
raise ModelCannotRetry(
"No tabular files (CSV or Excel) found in the conversation. "
"Please upload a CSV or Excel file first. "
"Note: If you uploaded an Excel file that was converted to Markdown for RAG, "
"the original file must still be available."
)
# Use the first tabular file
attachment = tabular_attachments[0]
logger.info("Analyzing file: %s (type: %s)", attachment.file_name, attachment.content_type)
# Load file data
file_data = await read_tabular_file(attachment)
# Validate that this is actually a valid Excel/CSV file (not a converted Markdown file)
# Check if it's an Excel file that should have ZIP signature
if attachment.file_name.lower().endswith((".xlsx", ".xls", ".xlsm", ".xlsb")):
if not _is_valid_excel_file(file_data, attachment.file_name):
logger.warning(
"File '%s' does not appear to be a valid Excel file. "
"It may be a converted Markdown file. Searching for original...",
attachment.file_name,
)
# Try to find the original file
# Look for an attachment with the same name but without conversion_from
original_attachment = await sync_to_async(
ctx.deps.conversation.attachments.filter(
file_name=attachment.file_name,
upload_state=AttachmentStatus.READY,
)
.filter(
Q(conversion_from__isnull=True) | Q(conversion_from="")
)
.exclude(pk=attachment.pk)
.first
)()
if original_attachment:
logger.info(
"Found original file '%s' (key: %s), using it instead",
original_attachment.file_name,
original_attachment.key,
)
attachment = original_attachment
file_data = await read_tabular_file(attachment)
elif hasattr(attachment, 'conversion_from') and attachment.conversion_from:
# Try to find by key if this file has a conversion_from
original_attachment = await sync_to_async(
ctx.deps.conversation.attachments.filter(
key=attachment.conversion_from,
upload_state=AttachmentStatus.READY,
).first
)()
if original_attachment:
logger.info(
"Found original file via conversion_from: '%s'",
original_attachment.file_name,
)
attachment = original_attachment
file_data = await read_tabular_file(attachment)
else:
raise ModelCannotRetry(
f"File '{attachment.file_name}' appears to be a converted Markdown file, "
"not the original Excel file. The original file is not available. "
"Please re-upload the original Excel file."
)
else:
raise ModelCannotRetry(
f"File '{attachment.file_name}' does not appear to be a valid Excel file. "
"It may be corrupted or in an unsupported format."
)
# Load into pandas DataFrames
dataframes = await load_dataframe(file_data, attachment.content_type, attachment.file_name)
# Generate metadata
metadata = generate_metadata(dataframes, attachment.file_name)
logger.debug("File metadata: %s", json.dumps(metadata, indent=2))
# Generate query using LLM
# NOTE:
# We intentionally create a "bare" Agent instance here instead of using BaseAgent
# with tools enabled. Using BaseAgent would attach all configured tools (including
# this data_analysis tool itself), which can cause the model to try to call tools
# while we're already inside a tool execution, leading to nested tool calls and
# failures like "Failed to generate query. Please try rephrasing your question.".
#
# Here we reuse the same model configuration as BaseAgent but WITHOUT any tools,
# so this internal call is purely text-to-text.
llm_config = settings.LLM_CONFIGURATIONS[settings.LLM_DEFAULT_MODEL_HRID]
if llm_config.is_custom:
model_instance = prepare_custom_model(llm_config)
else:
# Rely on pydantic-ai's built-in model registry / name inference
model_instance = llm_config.model_name
# Use the same keyword as when using BaseAgent, which forwards to Agent.
# On the current pydantic_ai version, the correct kwarg is `output_type`,
# not `result_type` (passing `result_type` raises a UserError).
query_agent = Agent(model=model_instance, output_type=str)
query_code = await generate_query(query, metadata, query_agent, ctx)
logger.debug("Generated query: %s", query_code)
# Execute query
try:
execution_result = await execute_query(query_code, dataframes)
result = execution_result.get("result")
plot_image_base64 = execution_result.get("plot_image")
except Exception as e:
logger.error("Query execution failed: %s", e, exc_info=True)
raise ModelRetry(
f"Failed to execute the generated query: {str(e)}. "
"Please try rephrasing your question."
) from e
# Format result for return
return_value = {
"query": query,
"query_code": query_code,
"result": result,
"metadata": metadata,
}
# Save plot image to storage if generated
plot_url = None
plot_attachment = None
if plot_image_base64:
try:
# Decode base64 image
plot_image_data = base64.b64decode(plot_image_base64)
# Generate a unique filename for the plot
plot_filename = f"plot_{uuid.uuid4().hex[:8]}.png"
plot_key = f"{ctx.deps.conversation.pk}/plots/{plot_filename}"
# Save to storage
await sync_to_async(default_storage.save)(
plot_key, BytesIO(plot_image_data)
)
# Create a permanent attachment record in the database
plot_attachment = await sync_to_async(ChatConversationAttachment.objects.create)(
conversation=ctx.deps.conversation,
uploaded_by=ctx.deps.user,
key=plot_key,
file_name=plot_filename,
content_type="image/png",
upload_state=AttachmentStatus.READY,
size=len(plot_image_data),
)
# Generate presigned URL for immediate access (valid for 1 hour)
plot_url = await sync_to_async(generate_retrieve_policy)(plot_key)
logger.info(
"Plot image saved to storage and database: %s (presigned URL: %s)",
plot_key,
plot_url[:50] + "..."
)
except Exception as e:
logger.error("Failed to save plot image: %s", e, exc_info=True)
# Continue without plot URL if save fails
if plot_url:
# Include both local and presigned URLs
return_value["plot_url"] = plot_url # Presigned URL for direct access
return_value["plot_local_url"] = f"/media-key/{plot_key}" # Local URL for reference
# Include attachment ID for reference
if plot_attachment:
return_value["plot_attachment_id"] = str(plot_attachment.pk)
return ToolReturn(
return_value=return_value,
metadata={"file_name": attachment.file_name, "content_type": attachment.content_type},
)
except (ModelCannotRetry, ModelRetry):
# Re-raise these as-is
raise
except Exception as exc:
# Unexpected error - stop and inform user
logger.exception("Unexpected error in data_analysis: %s", exc)
raise ModelCannotRetry(
f"An unexpected error occurred during data analysis: {type(exc).__name__}. "
"You must explain this to the user and not try to answer based on your knowledge."
) from exc
def add_data_analysis_tool(agent: Agent) -> None:
"""Add the data analysis tool to an existing agent."""
@agent.tool(retries=2)
@functools.wraps(data_analysis)
async def data_analysis_tool(ctx: RunContext, query: str) -> ToolReturn:
"""
Analyze tabular data files (CSV, Excel) based on user query.
This tool loads tabular files, generates metadata about their structure,
uses an LLM to generate a pandas query based on the user's question,
executes the query, and returns the results.
Use this tool when the user asks questions about data in CSV or Excel files,
such as:
- "What is the average sales by region?"
- "Show me the top 10 products by revenue"
- "How many records are in this file?"
- "Filter data where column X is greater than Y"
Args:
ctx (RunContext): The run context containing the conversation.
query (str): The user's data analysis question.
"""
# Import here to avoid circular import
from chat.tools.data_analysis import data_analysis as _data_analysis
return await _data_analysis(ctx, query)
@agent.instructions
def data_analysis_instructions() -> str:
"""Dynamic system prompt function to add data analysis instructions."""
return (
"When the user asks questions about data in CSV or Excel files, "
"use the data_analysis tool to analyze the data and answer their question. "
"The tool will handle loading the file, generating queries, and executing them. "
"When a plot is generated, the tool returns a 'plot_url' in the result. "
"Use this presigned URL directly in markdown image syntax: ![Description](plot_url). "
"Do NOT use local URLs like /media-key/... - always use the presigned URL from plot_url. "
"Present the results clearly to the user."
)
@@ -0,0 +1,137 @@
"""
Helpers to add RAG document search tools to an agent based on settings.
The purpose is to provide a generic way to add multiple RAG document search tools
to an agent based on configuration in settings. Each tool can target specific
document collections and have its own description.
Our use case implies that different users might have access to different document collections,
so the tools added to the agent are also user-specific.
"""
import logging
from django.conf import settings
from django.contrib.auth import get_user_model
from django.utils.module_loading import import_string
from httpx import HTTPStatusError
from pydantic_ai import Agent, ModelRetry, RunContext, RunUsage
from pydantic_ai.messages import ToolReturn
from core.feature_flags.helpers import is_feature_enabled
from chat.tools.utils import last_model_retry_soft_fail
logger = logging.getLogger(__name__)
User = get_user_model()
def get_specific_rag_search_tool_config(user: User) -> dict:
"""
Get the specific RAG search tool configuration from settings.
Settings example:
SPECIFIC_RAG_DOCUMENT_SEARCH_TOOLS = {
"french_public_services": {
"collection_ids": [784, 785],
"feature_flag_value": "disabled",
"tool_description": (
"Use this tool when the user asks for information about French public services, "
"the French labor market, employment laws, social benefits, or "
"assistance with administrative procedures."
),
},
}
"""
return {
tool_name: tool_config
for tool_name, tool_config in settings.SPECIFIC_RAG_DOCUMENT_SEARCH_TOOLS.items()
if is_feature_enabled(user, tool_name)
}
def _create_document_search_rag(agent, name, description, backend, ids):
"""Factory function to create a document search RAG tool."""
@agent.tool(
name=name,
retries=1,
require_parameter_descriptions=True,
description=description,
)
@last_model_retry_soft_fail
async def document_search_rag(ctx: RunContext, query: str) -> ToolReturn:
"""
Args:
ctx (RunContext): The run context containing the conversation.
query (str): The query to search information about.
"""
document_store = backend(read_only_collection_id=ids)
try:
rag_results = await document_store.asearch(query)
except HTTPStatusError as exc:
logger.error(
"RAG document search failed for tool %s with error: %s", name, exc, exc_info=True
)
raise ModelRetry(f"Document search service is currently unavailable: {exc}") from exc
ctx.usage += RunUsage(
input_tokens=rag_results.usage.prompt_tokens,
output_tokens=rag_results.usage.completion_tokens,
)
return ToolReturn(
return_value={
str(idx): {
"url": result.url,
"snippets": result.content,
}
for idx, result in enumerate(rag_results.data)
},
metadata={"sources": {result.url for result in rag_results.data}},
)
return document_search_rag
def add_document_rag_search_tool_from_setting(agent: Agent, user: User) -> None:
"""
This function takes a configuration setting and generates specific search RAG tools and add
it to the agent.
Args:
agent (Agent): The agent to which the tool will be added.
user (User): The user for whom the tool is being added.
"""
for tool_name, tool_config in get_specific_rag_search_tool_config(user).items():
document_store_backend_name = tool_config.get(
"rag_backend_name", settings.RAG_DOCUMENT_SEARCH_BACKEND
)
try:
document_store_backend = import_string(document_store_backend_name)
except ImportError as exc:
logger.warning(
"Could not import RAG backend %s: %s",
document_store_backend_name,
exc,
exc_info=True,
)
continue # Skip if the backend is not available
collection_ids = tool_config.get("collection_ids", [])
if not collection_ids:
logger.warning("No collection IDs provided for tool %s, skipping.", tool_name)
continue # Skip if no collection IDs are provided
tool_description = tool_config.get("tool_description")
if not tool_description:
logger.warning("No tool description provided for tool %s, skipping.", tool_name)
continue # Skip if no tool description is provided
_create_document_search_rag(
agent, tool_name, tool_description, document_store_backend, collection_ids
)
@@ -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 (
-11
View File
@@ -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.
+1 -1
View File
@@ -221,7 +221,7 @@ 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.
+15
View File
@@ -1,5 +1,6 @@
"""Global fixtures for the backend tests."""
import posthog
import pytest
from rest_framework.test import APIClient
from urllib3.connectionpool import HTTPConnectionPool
@@ -41,3 +42,17 @@ def feature_flags_fixture(settings):
"""
settings.FEATURE_FLAGS = settings.FEATURE_FLAGS.model_copy(deep=True)
yield settings.FEATURE_FLAGS
@pytest.fixture(name="posthog", scope="function")
def posthog_fixture(settings):
"""Mock PostHog in tests to avoid real network calls."""
settings.POSTHOG_KEY = {"id": "132456", "host": "https://eu.i.posthog-test.com"}
posthog.api_key = settings.POSTHOG_KEY["id"]
posthog.host = settings.POSTHOG_KEY["host"]
yield posthog
posthog.api_key = None
posthog.host = None
@@ -0,0 +1,43 @@
{
"models": [
{
"hrid": "default-model",
"model_name": "mistral-mock",
"human_readable_name": "Default Model",
"provider_name": "default-provider",
"profile": null,
"settings": {},
"is_active": true,
"icon": [
"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAABwAAAAcCAMAAABF0y+mAAAAn1BMVEUALosAKoovTZjw8vb////+9/jlPUniAAz",
"iABUAGIWbpsTwq7HhAAAAI4dle7DrdX4AJohRaaboXWj7+/zn6On5//9NZaT29vfoWmVHYKDoUl/k5OUAIYddc6vpbHYCM47Y3+v53+LiFCUA",
"HIWnsckYPJHi6PL77O7jJjW3wdf1w8jre4QgQ5TZ2txwg7Pr3+I8WZ6OnsTuoamClL7tlZ5xz5y8AAAAzUlEQVR4AZ3RRQKDQBBEUSTu7h5c4",
"vc/W6Yp3KG2Dz4ynDdeEBvOmq12xx2E1u0B+4NOEocj4DgNJ1PgLAvni8WyBq5Yc71ubFJx23C2q4P7dRYejg1xzvCUgvz5guz11k7gXYKF/1",
"8oyiYuvHAYeVkhXCzolVStHcGDjiQzNmMQxsMI5rEJRdQSPZvbpE2E8aY6gC6Z+2Hg4dFA0Yb4YedNL/v4Fk8WJuwiGhrChJNXI210rnib9Fs",
"JlXRUC/HwTscPIXf/iklq/tjb/gHAdxkCUjAg2QAAAABJRU5ErkJggg=="
],
"system_prompt": "You are a helpful AI assistant.",
"tools": []
},
{
"hrid": "default-summarization-model",
"model_name": "mistral-mock",
"human_readable_name": "Default Summarization Model",
"provider_name": "default-provider",
"profile": null,
"settings": {},
"is_active": true,
"icon": null,
"system_prompt": "You are a helpful AI assistant specialized in summarization.",
"tools": []
}
],
"providers": [
{
"hrid": "default-provider",
"base_url": "http://host.docker.internal:8900",
"api_key": "openmockllm-api-key",
"kind": "mistral"
}
]
}
+5
View File
@@ -717,6 +717,11 @@ class Base(BraveSettings, Configuration):
environ_name="RAG_DOCUMENT_SEARCH_BACKEND",
environ_prefix=None,
)
SPECIFIC_RAG_DOCUMENT_SEARCH_TOOLS = values.DictValue(
default={},
environ_name="SPECIFIC_RAG_DOCUMENT_SEARCH_TOOLS",
environ_prefix=None,
)
# Web search
RAG_WEB_SEARCH_PROMPT_UPDATE = values.Value(
-14
View File
@@ -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)
-20
View File
@@ -20,23 +20,3 @@ class UserSerializer(serializers.ModelSerializer):
"sub",
]
read_only_fields = ["id", "email", "full_name", "short_name", "sub"]
class UserLightSerializer(UserSerializer):
"""Serialize users with limited fields."""
id = serializers.SerializerMethodField(read_only=True)
email = serializers.SerializerMethodField(read_only=True)
def get_id(self, _user):
"""Return always None. Here to have the same fields than in UserSerializer."""
return None
def get_email(self, _user):
"""Return always None. Here to have the same fields than in UserSerializer."""
return None
class Meta:
model = models.User
fields = ["id", "email", "full_name", "short_name"]
read_only_fields = ["id", "email", "full_name", "short_name"]
@@ -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'"
+7
View File
@@ -2,6 +2,7 @@
from enum import StrEnum
from django.conf import settings
from django.utils.text import slugify
from pydantic import BaseModel, ConfigDict
@@ -43,3 +44,9 @@ class FeatureFlags(BaseModel):
# features
web_search: FeatureToggle = FeatureToggle.DISABLED
document_upload: FeatureToggle = FeatureToggle.DISABLED
def __getattr__(self, name: str):
"""Dynamically get specific RAG document search tool feature flags from settings."""
if config := settings.SPECIFIC_RAG_DOCUMENT_SEARCH_TOOLS.get(name):
return FeatureToggle[config.get("feature_flag_value", "DISABLED").upper()]
return super().__getattr__(name)
-25
View File
@@ -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)
-22
View File
@@ -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 +1,17 @@
# Generated by Django 5.2.8 on 2025-12-01 08:40
from django.db import migrations, models
class Migration(migrations.Migration):
dependencies = [
("core", "0002_user_allow_conversation_analytics"),
]
operations = [
migrations.AlterField(
model_name="user",
name="short_name",
field=models.CharField(blank=True, max_length=50, null=True, verbose_name="short name"),
),
]
+1 -1
View File
@@ -114,7 +114,7 @@ class User(AbstractBaseUser, BaseModel, auth_models.PermissionsMixin):
)
full_name = models.CharField(_("full name"), max_length=100, null=True, blank=True)
short_name = models.CharField(_("short name"), max_length=20, null=True, blank=True)
short_name = models.CharField(_("short name"), max_length=50, null=True, blank=True)
email = models.EmailField(_("identity email address"), blank=True, null=True)
@@ -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 ""
@@ -3,7 +3,7 @@ msgstr ""
"Project-Id-Version: la-suite-conversations\n"
"Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: 2025-10-20 21:48+0000\n"
"PO-Revision-Date: 2025-11-10 12:20\n"
"PO-Revision-Date: 2025-12-15 13:49\n"
"Last-Translator: \n"
"Language-Team: German\n"
"Language: de_DE\n"
@@ -3,7 +3,7 @@ msgstr ""
"Project-Id-Version: la-suite-conversations\n"
"Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: 2025-10-20 21:48+0000\n"
"PO-Revision-Date: 2025-11-10 12:20\n"
"PO-Revision-Date: 2025-12-15 13:49\n"
"Last-Translator: \n"
"Language-Team: English\n"
"Language: en_US\n"
@@ -3,7 +3,7 @@ msgstr ""
"Project-Id-Version: la-suite-conversations\n"
"Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: 2025-10-20 21:48+0000\n"
"PO-Revision-Date: 2025-11-10 12:20\n"
"PO-Revision-Date: 2025-12-15 13:49\n"
"Last-Translator: \n"
"Language-Team: French\n"
"Language: fr_FR\n"
@@ -3,7 +3,7 @@ msgstr ""
"Project-Id-Version: la-suite-conversations\n"
"Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: 2025-10-20 21:48+0000\n"
"PO-Revision-Date: 2025-11-10 12:20\n"
"PO-Revision-Date: 2025-12-15 13:49\n"
"Last-Translator: \n"
"Language-Team: Dutch\n"
"Language: nl_NL\n"
@@ -3,7 +3,7 @@ msgstr ""
"Project-Id-Version: la-suite-conversations\n"
"Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: 2025-10-20 21:48+0000\n"
"PO-Revision-Date: 2025-11-10 12:20\n"
"PO-Revision-Date: 2025-12-15 13:49\n"
"Last-Translator: \n"
"Language-Team: Russian\n"
"Language: ru_RU\n"
@@ -3,7 +3,7 @@ msgstr ""
"Project-Id-Version: la-suite-conversations\n"
"Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: 2025-10-20 21:48+0000\n"
"PO-Revision-Date: 2025-11-10 12:20\n"
"PO-Revision-Date: 2025-12-15 13:49\n"
"Last-Translator: \n"
"Language-Team: Ukrainian\n"
"Language: uk_UA\n"
+17 -13
View File
@@ -7,7 +7,7 @@ build-backend = "setuptools.build_meta"
[project]
name = "conversations"
version = "0.0.8"
version = "0.0.10"
authors = [{ "name" = "DINUM", "email" = "dev@mail.numerique.gouv.fr" }]
classifiers = [
"Development Status :: 5 - Production/Stable",
@@ -27,19 +27,19 @@ requires-python = ">=3.12"
dependencies = [
"deprecated",
"beautifulsoup4==4.14.2",
"boto3==1.40.67",
"boto3==1.40.73",
"Brotli==1.2.0",
"django-configurations==2.5.1",
"django-cors-headers==4.9.0",
"django-countries==8.0.0",
"django-countries==8.1.0",
"django-filter==25.2",
"django-lasuite[all]==0.0.17",
"django-lasuite[all]==0.0.18",
"django-parler==2.3",
"django-pydantic-field==0.3.13",
"django-pydantic-field==0.4.0",
"django-redis==6.0.0",
"django-storages[s3]==1.14.6",
"django-timezone-field>=5.1",
"django==5.2.8",
"django==5.2.9",
"djangorestframework==3.16.1",
"drf_spectacular==0.29.0",
"dockerflow==2024.4.2",
@@ -47,22 +47,26 @@ dependencies = [
"factory_boy==3.3.3",
"gunicorn==23.0.0",
"jsonschema==4.25.1",
"langfuse==3.9.0",
"langfuse==3.10.0",
"lxml==5.4.0",
"markdown==3.10",
"markitdown==0.0.2",
"mozilla-django-oidc==4.0.1",
"nested-multipart-parser==1.6.0",
"posthog==6.8.0",
"matplotlib==3.9.2",
"numpy==2.1.3",
"openpyxl==3.1.5",
"pandas==2.2.3",
"posthog==7.0.0",
"pydantic==2.12.4",
"pydantic-ai-slim[openai,mistral,mcp,evals,logfire]==1.11.0",
"pydantic-ai-slim[openai,mistral,mcp,evals,logfire]==1.17.0",
"psycopg[binary]==3.2.12",
"PyJWT==2.10.1",
"python-magic==0.4.27",
"redis<6.0.0",
"requests==2.32.5",
"semchunk==3.2.5",
"sentry-sdk==2.43.0",
"sentry-sdk==2.44.0",
"trafilatura==2.0.0",
"uvicorn==0.38.0",
"whitenoise==6.11.0",
@@ -87,15 +91,15 @@ dev = [
"pylint-django==2.6.1",
"pylint==3.3.9",
"pylint-pydantic==0.4.1",
"pytest-asyncio==1.2.0",
"pytest-asyncio==1.3.0",
"pytest-cov==7.0.0",
"pytest-django==4.11.1",
"pytest==8.4.2",
"pytest==9.0.1",
"pytest-icdiff==0.9",
"pytest-xdist==3.8.0",
"responses==0.25.8",
"respx==0.22.0",
"ruff==0.14.3",
"ruff==0.14.5",
"types-requests==2.32.4.20250913",
]
+5 -5
View File
@@ -1,6 +1,6 @@
{
"name": "app-conversations",
"version": "0.0.8",
"version": "0.0.10",
"private": true,
"scripts": {
"dev": "next dev",
@@ -36,16 +36,16 @@
"i18next-browser-languagedetector": "8.1.0",
"idb": "8.0.3",
"lodash": "4.17.21",
"lottie-react": "^2.4.1",
"luxon": "3.6.1",
"micromark-extension-llm-math": "3.1.1-20250610",
"next": "15.3.3",
"next": "15.3.8",
"posthog-js": "1.249.3",
"react": "*",
"react": "19.2.1",
"react-aria-components": "1.9.0",
"react-dom": "18.3.1",
"react-dom": "19.2.1",
"react-i18next": "15.5.2",
"react-intersection-observer": "9.16.0",
"react-lottie": "^1.2.10",
"react-markdown": "10.1.0",
"react-select": "5.10.1",
"rehype-katex": "7.0.1",
@@ -1,4 +1,4 @@
import { PropsWithChildren, useRef, useState } from 'react';
import { PropsWithChildren, useEffect, useRef, useState } from 'react';
import { css } from 'styled-components';
import { Box, BoxButton, BoxProps, DropButton, Icon, Text } from '@/components';
@@ -35,8 +35,16 @@ export const DropdownMenu = ({
}: PropsWithChildren<DropdownMenuProps>) => {
const { spacingsTokens, colorsTokens } = useCunninghamTheme();
const [isOpen, setIsOpen] = useState(false);
const [buttonWidth, setButtonWidth] = useState<number | undefined>(undefined);
const blockButtonRef = useRef<HTMLDivElement>(null);
useEffect(() => {
// Mettre à jour la largeur uniquement côté client
if (blockButtonRef.current) {
setButtonWidth(blockButtonRef.current.clientWidth);
}
}, [isOpen]);
const onOpenChange = (isOpen: boolean) => {
setIsOpen(isOpen);
};
@@ -76,7 +84,7 @@ export const DropdownMenu = ({
>
<Box
$maxWidth="320px"
$minWidth={`${blockButtonRef.current?.clientWidth}px`}
$minWidth={buttonWidth ? `${buttonWidth}px` : undefined}
role="menu"
>
{topMessage && (
@@ -1,20 +1,17 @@
import Lottie from 'react-lottie';
import dynamic from 'next/dynamic';
const Lottie = dynamic(() => import('lottie-react'), { ssr: false });
import searchingAnimation from '@/assets/lotties/searching';
export const Loader = () => {
const LoaderOptions = {
loop: true,
autoplay: true,
animationData: searchingAnimation,
rendererSettings: {
preserveAspectRatio: 'xMidYMid slice',
},
} as const;
export function Loader() {
return (
<div>
<Lottie options={LoaderOptions} height={24} width={24} />
<div role="status">
<Lottie
animationData={searchingAnimation}
loop
autoplay
style={{ width: 24, height: 24 }}
/>
</div>
);
};
}
@@ -3,6 +3,7 @@ import {
createContext,
useCallback,
useContext,
useEffect,
useState,
} from 'react';
import { createPortal } from 'react-dom';
@@ -47,6 +48,11 @@ interface ToastProviderProps {
export const ToastProvider = ({ children }: ToastProviderProps) => {
const [toasts, setToasts] = useState<ToastItem[]>([]);
const [isMounted, setIsMounted] = useState(false);
useEffect(() => {
setIsMounted(true);
}, []);
const showToast = useCallback(
(
@@ -83,7 +89,9 @@ export const ToastProvider = ({ children }: ToastProviderProps) => {
return (
<ToastContext.Provider value={value}>
{children}
{typeof window !== 'undefined' &&
{isMounted &&
typeof document !== 'undefined' &&
document.body &&
createPortal(
<Box
aria-live="polite"
@@ -1,74 +1,64 @@
import { CunninghamProvider } from '@openfun/cunningham-react';
import { QueryClient, QueryClientProvider } from '@tanstack/react-query';
import { useRouter } from 'next/router';
import dynamic from 'next/dynamic';
import { useEffect } from 'react';
import { ToastProvider } from '@/components';
import { useCunninghamTheme } from '@/cunningham';
import { Auth, KEY_AUTH, setAuthUrl } from '@/features/auth';
import { useResponsiveStore } from '@/stores/';
import { useResponsiveStore } from '@/stores';
import { ConfigProvider } from './config/';
import { ConfigProvider } from './config';
// Client-only providers
const ToastProviderNoSSR = dynamic(
() => import('@/components').then((mod) => ({ default: mod.ToastProvider })),
{ ssr: false, loading: () => null },
);
const CunninghamProviderNoSSR = dynamic(
() =>
import('@openfun/cunningham-react').then((mod) => ({
default: mod.CunninghamProvider,
})),
{ ssr: false },
);
/**
* QueryClient:
* - defaultOptions:
* - staleTime:
* - global cache duration - we decided 3 minutes
* - It can be overridden to each query
*/
const defaultOptions = {
queries: {
staleTime: 1000 * 60 * 3,
retry: 1,
},
};
const queryClient = new QueryClient({
defaultOptions,
defaultOptions: {
queries: { staleTime: 1000 * 60 * 3, retry: 1 },
mutations: {
onError: (error) => {
if (
error instanceof Error &&
'status' in error &&
error.status === 401
) {
void queryClient.resetQueries({ queryKey: [KEY_AUTH] });
setAuthUrl();
if (typeof window !== 'undefined') {
window.location.href = '/401';
}
}
},
},
},
});
export function AppProvider({ children }: { children: React.ReactNode }) {
const { theme } = useCunninghamTheme();
const { replace } = useRouter();
const initializeResizeListener = useResponsiveStore(
(state) => state.initializeResizeListener,
);
const theme = useCunninghamTheme((state) => state.theme);
useEffect(() => {
return initializeResizeListener();
}, [initializeResizeListener]);
useEffect(() => {
queryClient.setDefaultOptions({
...defaultOptions,
mutations: {
onError: (error) => {
if (
error instanceof Error &&
'status' in error &&
error.status === 401
) {
void queryClient.resetQueries({
queryKey: [KEY_AUTH],
});
setAuthUrl();
void replace(`/401`);
}
},
},
});
}, [replace]);
return useResponsiveStore.getState().initializeResizeListener();
}, []);
return (
<QueryClientProvider client={queryClient}>
<CunninghamProvider theme={theme}>
<CunninghamProviderNoSSR theme={theme}>
<ConfigProvider>
<ToastProvider>
<ToastProviderNoSSR>
<Auth>{children}</Auth>
</ToastProvider>
</ToastProviderNoSSR>
</ConfigProvider>
</CunninghamProvider>
</CunninghamProviderNoSSR>
</QueryClientProvider>
);
}
@@ -55,7 +55,7 @@ export const AttachmentList = ({
>
<Box
$background="var(--c--theme--colors--greyscale-050)"
$minWidth="200px"
$width="200px"
$direction="row"
$gap="8px"
$align="center"
@@ -8,6 +8,7 @@ import { Modal, ModalSize } from '@openfun/cunningham-react';
import 'katex/dist/katex.min.css'; // `rehype-katex` does not import the CSS for you
import { useRouter } from 'next/router';
import { useCallback, useEffect, useRef, useState } from 'react';
import type { ChangeEvent, FormEvent } from 'react';
import { useTranslation } from 'react-i18next';
import { MarkdownHooks } from 'react-markdown';
import rehypeKatex from 'rehype-katex';
@@ -16,7 +17,7 @@ import remarkGfm from 'remark-gfm';
import remarkMath from 'remark-math';
import { APIError, errorCauses, fetchAPI } from '@/api';
import { Box, Icon, Loader, StyledLink, Text } from '@/components';
import { Box, Icon, Loader, Text } from '@/components';
import { useUploadFile } from '@/features/attachments/hooks/useUploadFile';
import { useChat } from '@/features/chat/api/useChat';
import { getConversation } from '@/features/chat/api/useConversation';
@@ -26,6 +27,8 @@ import {
useLLMConfiguration,
} from '@/features/chat/api/useLLMConfiguration';
import { AttachmentList } from '@/features/chat/components/AttachmentList';
import { ChatError } from '@/features/chat/components/ChatError';
import { CodeBlock } from '@/features/chat/components/CodeBlock';
import { FeedbackButtons } from '@/features/chat/components/FeedbackButtons';
import { InputChat } from '@/features/chat/components/InputChat';
import { SourceItemList } from '@/features/chat/components/SourceItemList';
@@ -101,19 +104,14 @@ export const Chat = ({
if (modelToSelect) {
setSelectedModel(modelToSelect);
setSelectedModelHrid(modelToSelect.hrid);
}
}
}, [llmConfig, selectedModel, selectedModelHrid]);
// Update store when model selection changes
useEffect(() => {
if (selectedModel?.hrid !== selectedModelHrid) {
setSelectedModelHrid(selectedModel?.hrid || null);
}
}, [selectedModel, selectedModelHrid, setSelectedModelHrid]);
}, [llmConfig, selectedModel, selectedModelHrid, setSelectedModelHrid]);
const handleModelSelect = (model: LLMModel) => {
setSelectedModel(model);
setSelectedModelHrid(model.hrid);
};
const router = useRouter();
@@ -153,17 +151,26 @@ export const Chat = ({
const [initialConversationMessages, setInitialConversationMessages] =
useState<Message[] | undefined>(undefined);
const [pendingFirstMessage, setPendingFirstMessage] = useState<{
event: React.FormEvent<HTMLFormElement>;
event: FormEvent<HTMLFormElement>;
attachments?: Attachment[];
forceWebSearch?: boolean;
} | null>(null);
const [shouldAutoSubmit, setShouldAutoSubmit] = useState(false);
const [shouldRetry, setShouldRetry] = useState(false);
const retryOriginalInputRef = useRef<string>('');
const retryOriginalFilesRef = useRef<FileList | null>(null);
const [hasInitialized, setHasInitialized] = useState(false);
const [streamingMessageHeight, setStreamingMessageHeight] = useState<
number | null
>(null);
const lastUserMessageIdRef = useRef<string | null>(null);
const hasScrolledToBottomOnLoadRef = useRef(false);
const lastSubmissionRef = useRef<{
input: string;
files: FileList | null;
event: FormEvent<HTMLFormElement>;
options?: Record<string, unknown>;
} | null>(null);
const { mutate: createChatConversation } = useCreateChatConversation();
@@ -212,6 +219,7 @@ export const Chat = ({
handleInputChange,
status,
stop: stopChat,
setMessages,
} = useChat({
id: conversationId,
initialMessages: initialConversationMessages,
@@ -244,10 +252,33 @@ export const Chat = ({
void stopGeneration();
};
const handleSubmitWrapper = (event: React.FormEvent<HTMLFormElement>) => {
const handleSubmitWrapper = (event: FormEvent<HTMLFormElement>) => {
void handleSubmit(event);
};
const handleRetry = () => {
if (!lastSubmissionRef.current || !setMessages) {
return;
}
const { input: lastInput, files: lastFiles } = lastSubmissionRef.current;
const lastAssistantIndex = messages.findLastIndex(
(msg) => msg.role === 'assistant',
);
if (lastAssistantIndex !== -1) {
setMessages(messages.filter((_, index) => index !== lastAssistantIndex));
}
retryOriginalInputRef.current = input;
retryOriginalFilesRef.current = files;
handleInputChange({
target: { value: lastInput },
} as ChangeEvent<HTMLTextAreaElement>);
setFiles(lastFiles);
setShouldRetry(true);
};
// Précharger les métadonnées des sources dès que les messages arrivent
useEffect(() => {
messages.forEach((message) => {
@@ -260,7 +291,8 @@ export const Chat = ({
});
}
});
}, [messages, prefetchMetadata]);
// eslint-disable-next-line react-hooks/exhaustive-deps
}, [messages]);
const openSources = (messageId: string) => {
if (isSourceOpen === messageId) {
@@ -303,16 +335,23 @@ export const Chat = ({
const availableHeight = containerHeight - userMessageHeight - 38;
if (streamingMessageHeight !== availableHeight) {
setStreamingMessageHeight(availableHeight);
}
setStreamingMessageHeight((prev) => {
if (prev === null || Math.abs(prev - availableHeight) > 10) {
return availableHeight;
}
return prev;
});
}
}
}
}, [messages, streamingMessageHeight]);
}, [messages]);
// Détecter l'arrivée d'un nouveau message user et retirer la hauteur de l'ancien
useEffect(() => {
if (status === 'streaming') {
return;
}
const userMessages = messages.filter((msg) => msg.role === 'user');
const lastUserMessage = userMessages[userMessages.length - 1];
@@ -325,14 +364,14 @@ export const Chat = ({
}
lastUserMessageIdRef.current = lastUserMessage.id;
}
}, [messages]);
}, [messages, status]);
// Calculer la hauteur pendant submitted/streaming
useEffect(() => {
if (status === 'submitted' || status === 'streaming') {
calculateStreamingHeight();
}
}, [status, calculateStreamingHeight]);
// eslint-disable-next-line react-hooks/exhaustive-deps
}, [status]);
// Scroller vers la question au moment du submit
useEffect(() => {
@@ -352,7 +391,8 @@ export const Chat = ({
messageElement?.scrollIntoView({ block: 'start', behavior: 'smooth' });
});
}, [status, messages]);
// eslint-disable-next-line react-hooks/exhaustive-deps
}, [status]);
// Synchronize conversationId state with prop when it changes (e.g., after navigation)
useEffect(() => {
@@ -361,10 +401,11 @@ export const Chat = ({
if (initialConversationId !== conversationId) {
handleInputChange({
target: { value: '' },
} as React.ChangeEvent<HTMLTextAreaElement>);
} as ChangeEvent<HTMLTextAreaElement>);
setHasInitialized(false); // Réinitialiser pour permettre le scroll au prochain chargement
}
}, [initialConversationId, conversationId, handleInputChange]);
// eslint-disable-next-line react-hooks/exhaustive-deps
}, [initialConversationId, conversationId]);
// On mount, if there is pending input/files, initialize state and set flag
useEffect(() => {
@@ -375,7 +416,7 @@ export const Chat = ({
if (pendingInput) {
const syntheticEvent = {
target: { value: pendingInput },
} as React.ChangeEvent<HTMLInputElement>;
} as ChangeEvent<HTMLInputElement>;
handleInputChange(syntheticEvent);
}
if (pendingFiles) {
@@ -397,13 +438,32 @@ export const Chat = ({
const syntheticFormEvent = {
preventDefault: () => {},
target: form,
} as unknown as React.FormEvent<HTMLFormElement>;
} as unknown as FormEvent<HTMLFormElement>;
void handleSubmit(syntheticFormEvent);
setShouldAutoSubmit(false);
}
// eslint-disable-next-line react-hooks/exhaustive-deps
}, [shouldAutoSubmit, input, files]);
useEffect(() => {
if (
shouldRetry &&
lastSubmissionRef.current &&
input === lastSubmissionRef.current.input
) {
const { event } = lastSubmissionRef.current;
void handleSubmit(event);
handleInputChange({
target: { value: retryOriginalInputRef.current },
} as ChangeEvent<HTMLTextAreaElement>);
setFiles(retryOriginalFilesRef.current);
setShouldRetry(false);
}
// eslint-disable-next-line react-hooks/exhaustive-deps
}, [shouldRetry, input, files]);
// Fetch initial conversation messages if initialConversationId is provided and no pending input
useEffect(() => {
hasScrolledToBottomOnLoadRef.current = false; // Réinitialiser au début du chargement
@@ -457,7 +517,7 @@ export const Chat = ({
}, [hasInitialized, messages.length]);
// Custom handleSubmit to include attachments and handle chat creation
const handleSubmit = async (event: React.FormEvent<HTMLFormElement>) => {
const handleSubmit = async (event: FormEvent<HTMLFormElement>) => {
event.preventDefault();
// Upload files to server and get URLs
@@ -536,6 +596,13 @@ export const Chat = ({
options.experimental_attachments = attachments;
}
lastSubmissionRef.current = {
input,
files,
event,
options: Object.keys(options).length > 0 ? options : undefined,
};
if (Object.keys(options).length > 0) {
baseHandleSubmit(event, options);
} else {
@@ -642,6 +709,11 @@ export const Chat = ({
{message.content && (
<Box
className="mainContent-chat"
data-testid={
message.role === 'assistant'
? 'assistant-message-content'
: undefined
}
$padding={{ all: 'xxs' }}
>
<p className="sr-only">
@@ -649,38 +721,53 @@ export const Chat = ({
? t('You said: ')
: t('Assistant IA replied: ')}
</p>
<MarkdownHooks
remarkPlugins={[remarkGfm, remarkMath]}
rehypePlugins={[
[
rehypePrettyCode,
{
theme: 'github-dark-dimmed',
},
],
rehypeKatex,
]}
components={{
// Custom components for Markdown rendering
// eslint-disable-next-line @typescript-eslint/no-unused-vars
p: ({ node, ...props }) => (
<Text
as="p"
$css="display: block"
$theme="greyscale"
$variation="850"
{...props}
/>
),
a: ({ children, ...props }) => (
<a target="_blank" {...props}>
{children}
</a>
),
}}
>
{message.content}
</MarkdownHooks>
{message.role === 'user' ? (
<Text
as="p"
$css="white-space: pre-wrap; display: block;"
$theme="greyscale"
$variation="850"
>
{message.content}
</Text>
) : (
<MarkdownHooks
remarkPlugins={[remarkGfm, remarkMath]}
rehypePlugins={[
[
rehypePrettyCode,
{
theme: 'github-dark-dimmed',
},
],
rehypeKatex,
]}
components={{
// Custom components for Markdown rendering
// eslint-disable-next-line @typescript-eslint/no-unused-vars
p: ({ node, ...props }) => (
<Text
as="p"
$css="display: block"
$theme="greyscale"
$variation="850"
{...props}
/>
),
a: ({ children, ...props }) => (
<a target="_blank" {...props}>
{children}
</a>
),
// eslint-disable-next-line @typescript-eslint/no-unused-vars
pre: ({ node, children, ...props }) => (
<CodeBlock {...props}>{children}</CodeBlock>
),
}}
>
{message.content}
</MarkdownHooks>
)}
</Box>
)}
@@ -913,27 +1000,11 @@ export const Chat = ({
</Text>
</Box>
) : null}
{status === 'error' && (
<Box
$direction={isMobile ? 'column' : 'row'}
$gap="6px"
$width="100%"
$maxWidth="750px"
$margin={{ all: 'auto', top: 'base', bottom: 'md' }}
$padding={{ left: '13px' }}
>
<Text>{t('Sorry, an error occurred. Please try again.')}</Text>
<StyledLink
href="/"
rel="noopener noreferrer"
$css={`
color: var(--c--theme--colors--greyscale-900);
text-decoration: underline;
`}
>
{t('Start a new conversation.')}
</StyledLink>
</Box>
{status === 'error' && !isUploadingFiles && (
<ChatError
hasLastSubmission={!!lastSubmissionRef.current}
onRetry={handleRetry}
/>
)}
</Box>
<Box
@@ -941,6 +1012,7 @@ export const Chat = ({
position: relative;
bottom: ${isMobile ? '8px' : '20px'};
margin: auto;
background-color: white;
z-index: 1000;
`}
$gap="6px"
@@ -0,0 +1,80 @@
import { Button } from '@openfun/cunningham-react';
import { useRouter } from 'next/router';
import { useTranslation } from 'react-i18next';
import { Box, Icon, Text } from '@/components';
interface ChatErrorProps {
hasLastSubmission: boolean;
onRetry: () => void;
}
export const ChatError = ({ hasLastSubmission, onRetry }: ChatErrorProps) => {
const { t } = useTranslation();
const router = useRouter();
return (
<Box
$direction="column"
$gap="6px"
$width="100%"
$maxWidth="750px"
$margin={{ all: 'auto', top: 'base', bottom: 'md' }}
$padding={{ left: '13px' }}
>
<Text $variation="550" $theme="greyscale">
{t('Sorry, an error occurred. Please try again.')}
</Text>
<Box
$direction="row"
$gap="6px"
$align="center"
$margin={{ top: '10px' }}
>
{hasLastSubmission ? (
<Button
size="small"
color="tertiary"
onClick={onRetry}
className="retry-button"
style={{
color: 'var(--c--theme--colors--greyscale-550)',
borderColor: 'var(--c--theme--colors--greyscale-300)',
}}
icon={
<svg
xmlns="http://www.w3.org/2000/svg"
width="11"
height="15"
viewBox="0 0 11 15"
fill="none"
>
<path
d="M0.733333 10.0333C0.488889 9.61111 0.305556 9.17778 0.183333 8.73333C0.0611111 8.28889 0 7.83333 0 7.36667C0 5.87778 0.516667 4.61111 1.55 3.56667C2.58333 2.52222 3.84444 2 5.33333 2H5.45L4.38333 0.933333L5.31667 0L7.98333 2.66667L5.31667 5.33333L4.38333 4.4L5.45 3.33333H5.33333C4.22222 3.33333 3.27778 3.725 2.5 4.50833C1.72222 5.29167 1.33333 6.24444 1.33333 7.36667C1.33333 7.65556 1.36667 7.93889 1.43333 8.21667C1.5 8.49444 1.6 8.76667 1.73333 9.03333L0.733333 10.0333ZM5.35 14.6667L2.68333 12L5.35 9.33333L6.28333 10.2667L5.21667 11.3333H5.33333C6.44444 11.3333 7.38889 10.9417 8.16667 10.1583C8.94444 9.375 9.33333 8.42222 9.33333 7.3C9.33333 7.01111 9.3 6.72778 9.23333 6.45C9.16667 6.17222 9.06667 5.9 8.93333 5.63333L9.93333 4.63333C10.1778 5.05556 10.3611 5.48889 10.4833 5.93333C10.6056 6.37778 10.6667 6.83333 10.6667 7.3C10.6667 8.78889 10.15 10.0556 9.11667 11.1C8.08333 12.1444 6.82222 12.6667 5.33333 12.6667H5.21667L6.28333 13.7333L5.35 14.6667Z"
fill="currentColor"
/>
</svg>
}
>
{t('Retry')}
</Button>
) : (
<Button
size="small"
color="tertiary"
style={{
color: 'var(--c--theme--colors--greyscale-550)',
borderColor: 'var(--c--theme--colors--greyscale-300)',
}}
onClick={() => {
void router.push('/');
}}
icon={<Icon iconName="add" $color="greyscale" />}
>
{t('Start a new conversation')}
</Button>
)}
</Box>
</Box>
);
};
@@ -0,0 +1,80 @@
import { useRef } from 'react';
import type { ReactNode } from 'react';
import { useTranslation } from 'react-i18next';
import { Box, Icon, Text } from '@/components';
import { useClipboard } from '@/hook';
interface CopyCodeButtonProps {
onCopy: () => void;
}
const CopyCodeButton = ({ onCopy }: CopyCodeButtonProps) => {
const { t } = useTranslation();
return (
<Box
as="button"
onClick={onCopy}
$css={`
position: absolute;
top: 8px;
right: 8px;
padding: 6px 10px;
background: rgba(0, 0, 0, 0.03);
border: 1px solid rgba(255, 255, 255, 0.15);
border-radius: 4px;
cursor: pointer;
font-size: 12px;
font-weight: 500;
color: #fff;
display: flex;
flex-direction: row;
align-items: center;
gap: 4px;
z-index: 10;
transition: all 0.2s;
box-shadow: 0 1px 2px rgba(0, 0, 0, 0.1);
width: fit-content;
&:hover {
background:rgba(255, 255, 255, 0.1);
border: 1px solid rgba(255, 255, 255, 0.20);
}
`}
>
<Icon
iconName="content_copy"
$size="14px"
$theme="greyscale"
$variation="200"
/>
<Text $size="xs" $theme="greyscale" $variation="200">
{t('Copy code')}
</Text>
</Box>
);
};
interface CodeBlockProps {
children: ReactNode;
[key: string]: unknown;
}
export const CodeBlock = ({ children, ...props }: CodeBlockProps) => {
const preRef = useRef<HTMLPreElement>(null);
const copyToClipboard = useClipboard();
const handleCopy = () => {
const code = preRef.current?.querySelector('code');
copyToClipboard(code?.textContent || '');
};
return (
<>
<CopyCodeButton onCopy={handleCopy} />
<Box ref={preRef} $position="relative" as="pre" {...props}>
{children}
</Box>
</>
);
};
@@ -300,7 +300,6 @@ export const InputChat = ({
$css={`
display: block;
position: relative;
opacity: ${status === 'error' ? '0.5' : '1'};
margin: auto;
width: 100%;
padding: ${isDesktop ? '0' : '0 10px'};
@@ -308,26 +307,22 @@ export const InputChat = ({
`}
>
{/* Bouton de scroll vers le bas */}
{messagesLength > 1 &&
status !== 'streaming' &&
status !== 'submitted' &&
containerRef &&
onScrollToBottom && (
<Box
$css={`
{messagesLength > 1 && containerRef && onScrollToBottom && (
<Box
$css={`
position: relative;
height: 0;
width: 100%;
margin: auto;
max-width: 750px;
`}
>
<ScrollDown
onClick={onScrollToBottom}
containerRef={containerRef}
/>
</Box>
)}
>
<ScrollDown
onClick={onScrollToBottom}
containerRef={containerRef}
/>
</Box>
)}
{/* Message de bienvenue */}
{messagesLength === 0 && (
<Box
@@ -423,6 +418,7 @@ export const InputChat = ({
fontSize: '1rem',
border: 'none',
resize: 'none',
opacity: status === 'error' ? '0.5' : '1',
fontFamily: 'inherit',
minHeight: '64px',
maxHeight: '200px',
@@ -573,6 +569,9 @@ export const InputChat = ({
$gap="sm"
$padding={{ bottom: 'base' }}
$align="space-between"
$css={`
opacity: ${status === 'error' ? '0.5' : '1'};
`}
>
<Box
$flex="1"
@@ -40,7 +40,7 @@ export const ToolInvocationItem: React.FC<ToolInvocationItemProps> = ({
$color="var(--c--theme--colors--greyscale-500)"
$padding={{ all: 'sm' }}
$radius="8px"
$css="font-size: 0.9em;"
$css="font-size: 0.9em; width: 100%; white-space: pre-wrap; word-wrap: break-word;"
>
{toolInvocation.state === 'result' ? (
<Text>{`Parsing done: ${documentIdentifiers.join(', ')}`}</Text>
@@ -1,4 +1,4 @@
import { useState } from 'react';
import { useCallback, useRef, useState } from 'react';
interface SourceMetadata {
title: string | null;
@@ -9,109 +9,124 @@ interface SourceMetadata {
// Cache global pour éviter de refetch les mêmes URLs
const metadataCache = new Map<string, SourceMetadata>();
const fetchingUrls = new Set<string>();
export const useSourceMetadataCache = () => {
const [cache, setCache] =
useState<Map<string, SourceMetadata>>(metadataCache);
const [, forceUpdate] = useState({});
const updateCountRef = useRef(0);
const prefetchMetadata = async (url: string) => {
// Si déjà en cache, ne rien faire
if (metadataCache.has(url)) {
return;
const triggerUpdate = useCallback(() => {
updateCountRef.current++;
if (updateCountRef.current % 5 === 0) {
forceUpdate({});
}
}, []);
// Marquer comme en cours de chargement
metadataCache.set(url, {
title: null,
favicon: null,
loading: true,
error: false,
});
setCache(new Map(metadataCache));
try {
if (!url.startsWith('http')) {
metadataCache.set(url, {
title: url,
favicon: '📄',
loading: false,
error: false,
});
setCache(new Map(metadataCache));
const prefetchMetadata = useCallback(
async (url: string) => {
if (metadataCache.has(url) || fetchingUrls.has(url)) {
return;
}
const parser = new DOMParser();
fetchingUrls.add(url);
metadataCache.set(url, {
title: null,
favicon: null,
loading: true,
error: false,
});
triggerUpdate();
let response;
try {
response = await fetch(url, {
mode: 'cors',
headers: {
'User-Agent': 'Mozilla/5.0 (compatible; ChatBot/1.0)',
},
if (!url.startsWith('http')) {
metadataCache.set(url, {
title: url,
favicon: '📄',
loading: false,
error: false,
});
fetchingUrls.delete(url);
triggerUpdate();
return;
}
const parser = new DOMParser();
let response;
try {
response = await fetch(url, {
mode: 'cors',
headers: {
'User-Agent': 'Mozilla/5.0 (compatible; ChatBot/1.0)',
},
});
} catch {
// Si CORS échoue, utiliser juste le hostname
metadataCache.set(url, {
title: new URL(url).hostname,
favicon: null,
loading: false,
error: false,
});
fetchingUrls.delete(url);
triggerUpdate();
return;
}
if (!response.ok) {
throw new Error(`HTTP ${response.status}`);
}
const html = await response.text();
const doc = parser.parseFromString(html, 'text/html');
// Récupérer le titre
const pageTitle =
doc.querySelector('title')?.textContent || new URL(url).hostname;
// Récupérer le favicon
let faviconUrl =
doc.querySelector('link[rel="icon"]')?.getAttribute('href') ||
doc.querySelector('link[rel="shortcut icon"]')?.getAttribute('href');
if (!faviconUrl) {
const urlObj = new URL(url);
faviconUrl = `${urlObj.origin}/favicon.ico`;
}
// Convertir les URLs relatives en absolues
if (faviconUrl && !faviconUrl.startsWith('http')) {
const urlObj = new URL(url);
faviconUrl = new URL(faviconUrl, urlObj.origin).href;
}
metadataCache.set(url, {
title: pageTitle,
favicon: faviconUrl || null,
loading: false,
error: false,
});
} catch {
// Si CORS échoue, utiliser juste le hostname
fetchingUrls.delete(url);
triggerUpdate();
} catch (err) {
console.log('Error fetching metadata for:', url, err);
metadataCache.set(url, {
title: new URL(url).hostname,
favicon: null,
loading: false,
error: false,
error: true,
});
setCache(new Map(metadataCache));
return;
fetchingUrls.delete(url);
triggerUpdate();
}
},
[triggerUpdate],
);
if (!response.ok) {
throw new Error(`HTTP ${response.status}`);
}
const getMetadata = useCallback((url: string): SourceMetadata | undefined => {
return metadataCache.get(url);
}, []);
const html = await response.text();
const doc = parser.parseFromString(html, 'text/html');
// Récupérer le titre
const pageTitle =
doc.querySelector('title')?.textContent || new URL(url).hostname;
// Récupérer le favicon
let faviconUrl =
doc.querySelector('link[rel="icon"]')?.getAttribute('href') ||
doc.querySelector('link[rel="shortcut icon"]')?.getAttribute('href');
if (!faviconUrl) {
const urlObj = new URL(url);
faviconUrl = `${urlObj.origin}/favicon.ico`;
}
// Convertir les URLs relatives en absolues
if (faviconUrl && !faviconUrl.startsWith('http')) {
const urlObj = new URL(url);
faviconUrl = new URL(faviconUrl, urlObj.origin).href;
}
metadataCache.set(url, {
title: pageTitle,
favicon: faviconUrl || null,
loading: false,
error: false,
});
setCache(new Map(metadataCache));
} catch (err) {
console.log('Error fetching metadata for:', url, err);
metadataCache.set(url, {
title: new URL(url).hostname,
favicon: null,
loading: false,
error: true,
});
setCache(new Map(metadataCache));
}
};
const getMetadata = (url: string): SourceMetadata | undefined => {
return cache.get(url);
};
return { prefetchMetadata, getMetadata, cache };
return { prefetchMetadata, getMetadata };
};
@@ -35,6 +35,7 @@
"Conversation analysis enabled": "Analyse de la conversation activée",
"Copied": "Copié",
"Copy": "Copier",
"Copy code": "Copier le code",
"Default": "Par défaut",
"Delete": "Supprimer",
"Delete a conversation": "Supprimer une conversation",
@@ -59,7 +60,7 @@
"Give feedback": "Faire un retour",
"History": "Historique",
"Home": "Accueil",
"If enabled, this allows us to analyse your exchanges to improve the Assistant. If disabled, all conversations remain confidential and are not used in any way. ": "Si cette option est activée, cela nous permet d'analyser vos conversations afin d'améliorer l'Assistant. Si elle est désactivée, toutes les conversations restent confidentielles et ne sont utilisées d'aucune manière ",
"If enabled, this allows us to analyse your exchanges to improve the Assistant. If disabled, all conversations remain confidential and are not used in any way. ": "Si cette option est activée, cela nous permet d'analyser vos conversations afin d'améliorer l'Assistant. Si elle est désactivée, toutes les conversations restent confidentielles et ne sont utilisées d'aucune manière. ",
"Illustration": "Image",
"Image 401": "Image 401",
"Image 403": "Image 403",
@@ -166,6 +167,7 @@
"Conversation analysis enabled": "Gespreksanalyse ingeschakeld",
"Copied": "Gekopieerd",
"Copy": "Kopiëren",
"Copy code": "Kopieer code",
"Default": "Standaard",
"Delete": "Verwijderen",
"Delete a conversation": "Een gesprek verwijderen",
@@ -297,6 +299,7 @@
"Conversation analysis enabled": "Анализ бесед включён",
"Copied": "Скопировано",
"Copy": "Копировать",
"Copy code": "Скопировать код",
"Default": "По-умолчанию",
"Delete": "Удалить",
"Delete a conversation": "Удалить беседу",
@@ -428,6 +431,7 @@
"Conversation analysis enabled": "Аналіз розмов увімкнено",
"Copied": "Скопійовано",
"Copy": "Копіювати",
"Copy code": "Скопіювати код",
"Default": "За замовчуванням",
"Delete": "Видалити",
"Delete a conversation": "Видалити розмову",
@@ -235,6 +235,7 @@ ul a:hover {
figure[data-rehype-pretty-code-figure] {
margin-left: 0;
margin-right: 0;
position: relative;
}
figure[data-rehype-pretty-code-figure] > pre {
@@ -0,0 +1,72 @@
import { expect, test } from '@playwright/test';
test.beforeEach(async ({ page }) => {
await page.goto('/home/');
});
test.describe('Chat page', () => {
test('it checks the page is displayed properly', async ({ page }) => {
await page.goto('/');
const newChatButton = page.getByRole('button', { name: 'New chat' });
await expect(newChatButton).toBeVisible();
const chatInput = page.getByRole('textbox', {
name: 'Enter your message or a',
});
await expect(chatInput).toBeVisible();
const attachmentButton = page.getByRole('button', {
name: 'Add attach file',
});
await expect(attachmentButton).toBeVisible();
const websearchButton = page.getByRole('button', {
name: 'Research on the web',
});
await expect(websearchButton).toBeVisible();
const sendMessageButton = page.getByRole('button', { name: 'Send' });
await expect(sendMessageButton).toBeVisible();
});
test('the user can chat with LLM (simple)', async ({ page }) => {
await page.goto('/');
const newChatButton = page.getByRole('button', { name: 'New chat' });
await expect(newChatButton).toBeVisible();
const chatInput = page.getByRole('textbox', {
name: 'Enter your message or a',
});
await chatInput.click();
await chatInput.fill('Hello, how are you?');
const sendMessageButton = page.getByRole('button', { name: 'Send' });
await expect(sendMessageButton).toBeEnabled();
await page.keyboard.press('Enter');
const copyButton = page.getByRole('button', { name: 'Copy' });
await expect(copyButton).toBeVisible();
const messageContent = page.getByTestId('assistant-message-content');
await expect(messageContent).toBeVisible();
await expect(messageContent).not.toBeEmpty();
// Check history
const chatHistoryLink = page
.getByRole('link', { name: 'Simple chat icon Hello, how' })
.first();
await expect(chatHistoryLink).toBeVisible();
await newChatButton.click();
await page
.getByRole('heading', { name: 'What is on your mind?' })
.isVisible();
await chatHistoryLink.click();
await expect(messageContent).toBeVisible();
});
});
@@ -24,9 +24,7 @@ test.describe('Home page', () => {
// Check the titles
const h2 = page.locator('h2');
await expect(
h2.getByText('Your sovereign AI assistant'),
).toBeVisible();
await expect(h2.getByText('Your sovereign AI assistant')).toBeVisible();
await expect(footer).toBeVisible();
});
@@ -74,9 +72,7 @@ test.describe('Home page', () => {
// Check the titles
const h2 = page.locator('h2');
await expect(
h2.getByText('Your sovereign AI assistant'),
).toBeVisible();
await expect(h2.getByText('Your sovereign AI assistant')).toBeVisible();
await expect(footer).toBeVisible();
});
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "app-e2e",
"version": "0.0.8",
"version": "0.0.10",
"private": true,
"scripts": {
"lint": "eslint . --ext .ts",
+3 -3
View File
@@ -1,6 +1,6 @@
{
"name": "conversations",
"version": "0.0.8",
"version": "0.0.10",
"private": true,
"workspaces": {
"packages": [
@@ -32,8 +32,8 @@
"@typescript-eslint/eslint-plugin": "8.33.1",
"@typescript-eslint/parser": "8.33.1",
"eslint": "8.57.0",
"react": "19.1.0",
"react-dom": "19.1.0",
"react": "19.2.1",
"react-dom": "19.2.1",
"typescript": "5.8.3"
}
}
@@ -1,6 +1,6 @@
{
"name": "eslint-config-conversations",
"version": "0.0.8",
"version": "0.0.10",
"license": "MIT",
"scripts": {
"lint": "eslint --ext .js ."
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "packages-i18n",
"version": "0.0.8",
"version": "0.0.10",
"private": true,
"scripts": {
"extract-translation": "yarn extract-translation:conversations",
+71 -91
View File
@@ -1971,10 +1971,10 @@
"@emnapi/runtime" "^1.4.3"
"@tybys/wasm-util" "^0.9.0"
"@next/env@15.3.3":
version "15.3.3"
resolved "https://registry.npmjs.org/@next/env/-/env-15.3.3.tgz"
integrity sha512-OdiMrzCl2Xi0VTjiQQUK0Xh7bJHnOuET2s+3V+Y40WJBAXrJeGA3f+I8MZJ/YQ3mVGi5XGR1L66oFlgqXhQ4Vw==
"@next/env@15.3.8":
version "15.3.8"
resolved "https://registry.yarnpkg.com/@next/env/-/env-15.3.8.tgz#02326c38d315d72f2ab8b2bcc9a5c81ec5482873"
integrity sha512-SAfHg0g91MQVMPioeFeDjE+8UPF3j3BvHjs8ZKJAUz1BG7eMPvfCKOAgNWJ6s1MLNeP6O2InKQRTNblxPWuq+Q==
"@next/eslint-plugin-next@15.3.3":
version "15.3.3"
@@ -1983,45 +1983,45 @@
dependencies:
fast-glob "3.3.1"
"@next/swc-darwin-arm64@15.3.3":
version "15.3.3"
resolved "https://registry.npmjs.org/@next/swc-darwin-arm64/-/swc-darwin-arm64-15.3.3.tgz"
integrity sha512-WRJERLuH+O3oYB4yZNVahSVFmtxRNjNF1I1c34tYMoJb0Pve+7/RaLAJJizyYiFhjYNGHRAE1Ri2Fd23zgDqhg==
"@next/swc-darwin-arm64@15.3.5":
version "15.3.5"
resolved "https://registry.yarnpkg.com/@next/swc-darwin-arm64/-/swc-darwin-arm64-15.3.5.tgz#75606cb72e1659a23f15195dba760dc01b186c5d"
integrity sha512-lM/8tilIsqBq+2nq9kbTW19vfwFve0NR7MxfkuSUbRSgXlMQoJYg+31+++XwKVSXk4uT23G2eF/7BRIKdn8t8w==
"@next/swc-darwin-x64@15.3.3":
version "15.3.3"
resolved "https://registry.yarnpkg.com/@next/swc-darwin-x64/-/swc-darwin-x64-15.3.3.tgz#71588bad245180ffd1af1e1f894477287e739eb0"
integrity sha512-XHdzH/yBc55lu78k/XwtuFR/ZXUTcflpRXcsu0nKmF45U96jt1tsOZhVrn5YH+paw66zOANpOnFQ9i6/j+UYvw==
"@next/swc-darwin-x64@15.3.5":
version "15.3.5"
resolved "https://registry.yarnpkg.com/@next/swc-darwin-x64/-/swc-darwin-x64-15.3.5.tgz#78ffad7ef26685e5b8150891b467a4ecef94e179"
integrity sha512-WhwegPQJ5IfoUNZUVsI9TRAlKpjGVK0tpJTL6KeiC4cux9774NYE9Wu/iCfIkL/5J8rPAkqZpG7n+EfiAfidXA==
"@next/swc-linux-arm64-gnu@15.3.3":
version "15.3.3"
resolved "https://registry.yarnpkg.com/@next/swc-linux-arm64-gnu/-/swc-linux-arm64-gnu-15.3.3.tgz#66a15f749c14f04a89f8c7e21c7a8d343fc34e6e"
integrity sha512-VZ3sYL2LXB8znNGcjhocikEkag/8xiLgnvQts41tq6i+wql63SMS1Q6N8RVXHw5pEUjiof+II3HkDd7GFcgkzw==
"@next/swc-linux-arm64-gnu@15.3.5":
version "15.3.5"
resolved "https://registry.yarnpkg.com/@next/swc-linux-arm64-gnu/-/swc-linux-arm64-gnu-15.3.5.tgz#d9a405ceec729d62033dbdc48f8c331c544f09fd"
integrity sha512-LVD6uMOZ7XePg3KWYdGuzuvVboxujGjbcuP2jsPAN3MnLdLoZUXKRc6ixxfs03RH7qBdEHCZjyLP/jBdCJVRJQ==
"@next/swc-linux-arm64-musl@15.3.3":
version "15.3.3"
resolved "https://registry.yarnpkg.com/@next/swc-linux-arm64-musl/-/swc-linux-arm64-musl-15.3.3.tgz#14bd66213f7f33d6909574750bcb05037221a2ac"
integrity sha512-h6Y1fLU4RWAp1HPNJWDYBQ+e3G7sLckyBXhmH9ajn8l/RSMnhbuPBV/fXmy3muMcVwoJdHL+UtzRzs0nXOf9SA==
"@next/swc-linux-arm64-musl@15.3.5":
version "15.3.5"
resolved "https://registry.yarnpkg.com/@next/swc-linux-arm64-musl/-/swc-linux-arm64-musl-15.3.5.tgz#65f19ad3ecd2881381ec2a149afba261ba180dde"
integrity sha512-k8aVScYZ++BnS2P69ClK7v4nOu702jcF9AIHKu6llhHEtBSmM2zkPGl9yoqbSU/657IIIb0QHpdxEr0iW9z53A==
"@next/swc-linux-x64-gnu@15.3.3":
version "15.3.3"
resolved "https://registry.yarnpkg.com/@next/swc-linux-x64-gnu/-/swc-linux-x64-gnu-15.3.3.tgz#4a19434545e5e752d9a3ed71f9b34982725f6293"
integrity sha512-jJ8HRiF3N8Zw6hGlytCj5BiHyG/K+fnTKVDEKvUCyiQ/0r5tgwO7OgaRiOjjRoIx2vwLR+Rz8hQoPrnmFbJdfw==
"@next/swc-linux-x64-gnu@15.3.5":
version "15.3.5"
resolved "https://registry.yarnpkg.com/@next/swc-linux-x64-gnu/-/swc-linux-x64-gnu-15.3.5.tgz#cd7f7e002212360b99f7e791a2d2fedb352f2374"
integrity sha512-2xYU0DI9DGN/bAHzVwADid22ba5d/xrbrQlr2U+/Q5WkFUzeL0TDR963BdrtLS/4bMmKZGptLeg6282H/S2i8A==
"@next/swc-linux-x64-musl@15.3.3":
version "15.3.3"
resolved "https://registry.yarnpkg.com/@next/swc-linux-x64-musl/-/swc-linux-x64-musl-15.3.3.tgz#41ab140dd0a04ab7291adbec5836c1ce251a588c"
integrity sha512-HrUcTr4N+RgiiGn3jjeT6Oo208UT/7BuTr7K0mdKRBtTbT4v9zJqCDKO97DUqqoBK1qyzP1RwvrWTvU6EPh/Cw==
"@next/swc-linux-x64-musl@15.3.5":
version "15.3.5"
resolved "https://registry.yarnpkg.com/@next/swc-linux-x64-musl/-/swc-linux-x64-musl-15.3.5.tgz#302c9e4ace935c963d45fce9584754a19295c452"
integrity sha512-TRYIqAGf1KCbuAB0gjhdn5Ytd8fV+wJSM2Nh2is/xEqR8PZHxfQuaiNhoF50XfY90sNpaRMaGhF6E+qjV1b9Tg==
"@next/swc-win32-arm64-msvc@15.3.3":
version "15.3.3"
resolved "https://registry.yarnpkg.com/@next/swc-win32-arm64-msvc/-/swc-win32-arm64-msvc-15.3.3.tgz#fcd1d7e0007b7b73d1acdbf0ad6d91f7aa2deb15"
integrity sha512-SxorONgi6K7ZUysMtRF3mIeHC5aA3IQLmKFQzU0OuhuUYwpOBc1ypaLJLP5Bf3M9k53KUUUj4vTPwzGvl/NwlQ==
"@next/swc-win32-arm64-msvc@15.3.5":
version "15.3.5"
resolved "https://registry.yarnpkg.com/@next/swc-win32-arm64-msvc/-/swc-win32-arm64-msvc-15.3.5.tgz#5bbe1434afa2360634d45fc7860a038d11e4e296"
integrity sha512-h04/7iMEUSMY6fDGCvdanKqlO1qYvzNxntZlCzfE8i5P0uqzVQWQquU1TIhlz0VqGQGXLrFDuTJVONpqGqjGKQ==
"@next/swc-win32-x64-msvc@15.3.3":
version "15.3.3"
resolved "https://registry.yarnpkg.com/@next/swc-win32-x64-msvc/-/swc-win32-x64-msvc-15.3.3.tgz#c0e33e069d7922dd0546cac77a0247ad81d4a1aa"
integrity sha512-4QZG6F8enl9/S2+yIiOiju0iCTFd93d8VC1q9LZS4p/Xuk81W2QDjCFeoogmrWWkAD59z8ZxepBQap2dKS5ruw==
"@next/swc-win32-x64-msvc@15.3.5":
version "15.3.5"
resolved "https://registry.yarnpkg.com/@next/swc-win32-x64-msvc/-/swc-win32-x64-msvc-15.3.5.tgz#9629b2eac3159c70f3449cecc2a29bfd4bcb2d5a"
integrity sha512-5fhH6fccXxnX2KhllnGhkYMndhOiLOLEiVGYjP2nizqeGWkN10sA9taATlXwake2E2XMvYZjjz0Uj7T0y+z1yw==
"@nodelib/fs.scandir@2.1.5":
version "2.1.5"
@@ -6451,14 +6451,6 @@ babel-preset-jest@^29.6.3:
babel-plugin-jest-hoist "^29.6.3"
babel-preset-current-node-syntax "^1.0.0"
babel-runtime@^6.26.0:
version "6.26.0"
resolved "https://registry.yarnpkg.com/babel-runtime/-/babel-runtime-6.26.0.tgz#965c7058668e82b55d7bfe04ff2337bc8b5647fe"
integrity sha512-ITKNuq2wKlW1fJg9sSW52eepoYgZBggvOAHC0u/CYu/qxQ9EVzThCgR69BnSXLHjy2f7SY5zaQ4yt7H9ZVxY2g==
dependencies:
core-js "^2.4.0"
regenerator-runtime "^0.11.0"
bail@^2.0.0:
version "2.0.2"
resolved "https://registry.npmjs.org/bail/-/bail-2.0.2.tgz"
@@ -7004,11 +6996,6 @@ core-js-compat@^3.40.0:
dependencies:
browserslist "^4.24.4"
core-js@^2.4.0:
version "2.6.12"
resolved "https://registry.yarnpkg.com/core-js/-/core-js-2.6.12.tgz#d9333dfa7b065e347cc5682219d6f690859cc2ec"
integrity sha512-Kb2wC0fvsWfQrgk8HU5lW6U/Lcs8+9aaYcy4ZFc6DDlo4nZ7n70dEgE5rtR0oG6ufKDUnrwfWL1mXR5ljDatrQ==
core-js@^3.0.0, core-js@^3.38.1:
version "3.42.0"
resolved "https://registry.npmjs.org/core-js/-/core-js-3.42.0.tgz"
@@ -10097,7 +10084,14 @@ loose-envify@^1.0.0, loose-envify@^1.4.0:
dependencies:
js-tokens "^3.0.0 || ^4.0.0"
lottie-web@^5.12.2:
lottie-react@^2.4.1:
version "2.4.1"
resolved "https://registry.yarnpkg.com/lottie-react/-/lottie-react-2.4.1.tgz#4bd3f2a8a5e48edbd43c05ca5080fdd50f049d31"
integrity sha512-LQrH7jlkigIIv++wIyrOYFLHSKQpEY4zehPicL9bQsrt1rnoKRYCYgpCUe5maqylNtacy58/sQDZTkwMcTRxZw==
dependencies:
lottie-web "^5.10.2"
lottie-web@^5.10.2:
version "5.13.0"
resolved "https://registry.yarnpkg.com/lottie-web/-/lottie-web-5.13.0.tgz#441d3df217cc8ba302338c3f168e1a3af0f221d3"
integrity sha512-+gfBXl6sxXMPe8tKQm7qzLnUy5DUPJPKIyRHwtpCpyUEYjHYRJC/5gjUvdkuO2c3JllrPtHXH5UJJK8LRYl5yQ==
@@ -10844,12 +10838,12 @@ neo-async@^2.6.2:
resolved "https://registry.npmjs.org/neo-async/-/neo-async-2.6.2.tgz"
integrity sha512-Yd3UES5mWCSqR+qNT93S3UoYUkqAZ9lLg8a7g9rimsWmYGK8cVToA4/sF3RrshdyV3sAGMXVUmpMYOw+dLpOuw==
next@15.3.3:
version "15.3.3"
resolved "https://registry.npmjs.org/next/-/next-15.3.3.tgz"
integrity sha512-JqNj29hHNmCLtNvd090SyRbXJiivQ+58XjCcrC50Crb5g5u2zi7Y2YivbsEfzk6AtVI80akdOQbaMZwWB1Hthw==
next@15.3.8:
version "15.3.8"
resolved "https://registry.yarnpkg.com/next/-/next-15.3.8.tgz#c7df2fa890c66fa3042e85437e3c1e8e6bd38b26"
integrity sha512-L+4c5Hlr84fuaNADZbB9+ceRX9/CzwxJ+obXIGHupboB/Q1OLbSUapFs4bO8hnS/E6zV/JDX7sG1QpKVR2bguA==
dependencies:
"@next/env" "15.3.3"
"@next/env" "15.3.8"
"@swc/counter" "0.1.3"
"@swc/helpers" "0.5.15"
busboy "1.6.0"
@@ -10857,14 +10851,14 @@ next@15.3.3:
postcss "8.4.31"
styled-jsx "5.1.6"
optionalDependencies:
"@next/swc-darwin-arm64" "15.3.3"
"@next/swc-darwin-x64" "15.3.3"
"@next/swc-linux-arm64-gnu" "15.3.3"
"@next/swc-linux-arm64-musl" "15.3.3"
"@next/swc-linux-x64-gnu" "15.3.3"
"@next/swc-linux-x64-musl" "15.3.3"
"@next/swc-win32-arm64-msvc" "15.3.3"
"@next/swc-win32-x64-msvc" "15.3.3"
"@next/swc-darwin-arm64" "15.3.5"
"@next/swc-darwin-x64" "15.3.5"
"@next/swc-linux-arm64-gnu" "15.3.5"
"@next/swc-linux-arm64-musl" "15.3.5"
"@next/swc-linux-x64-gnu" "15.3.5"
"@next/swc-linux-x64-musl" "15.3.5"
"@next/swc-win32-arm64-msvc" "15.3.5"
"@next/swc-win32-x64-msvc" "15.3.5"
sharp "^0.34.1"
no-case@^3.0.4:
@@ -11428,7 +11422,7 @@ prompts@^2.0.1:
kleur "^3.0.3"
sisteransi "^1.0.5"
prop-types@^15.6.0, prop-types@^15.6.1, prop-types@^15.6.2, prop-types@^15.7.2, prop-types@^15.8.1:
prop-types@^15.6.0, prop-types@^15.6.2, prop-types@^15.7.2, prop-types@^15.8.1:
version "15.8.1"
resolved "https://registry.npmjs.org/prop-types/-/prop-types-15.8.1.tgz"
integrity sha512-oj87CgZICdulUohogVAR7AjlC0327U4el4L6eAvOqCeudMDVU0NThNaV+b9Df4dXgSP1gXMTnPdhfe/2qDH5cg==
@@ -11785,12 +11779,12 @@ react-dnd@^14.0.3:
fast-deep-equal "^3.1.3"
hoist-non-react-statics "^3.3.2"
react-dom@18.3.1, react-dom@19.0.0, react-dom@19.1.0:
version "19.1.0"
resolved "https://registry.yarnpkg.com/react-dom/-/react-dom-19.1.0.tgz#133558deca37fa1d682708df8904b25186793623"
integrity sha512-Xs1hdnE+DyKgeHJeJznQmYMIBG3TKIHJJT95Q58nHLSrElKlGQqDTR2HQ9fx5CN/Gk6Vh/kupBTDLU11/nDk/g==
react-dom@19.0.0, react-dom@19.2.1:
version "19.2.1"
resolved "https://registry.yarnpkg.com/react-dom/-/react-dom-19.2.1.tgz#ce3527560bda4f997e47d10dab754825b3061f59"
integrity sha512-ibrK8llX2a4eOskq1mXKu/TGZj9qzomO+sNfO98M6d9zIPOEhlBkMkBUBLd1vgS0gQsLDBzA+8jJBVXDnfHmJg==
dependencies:
scheduler "^0.26.0"
scheduler "^0.27.0"
react-i18next@15.5.2:
version "15.5.2"
@@ -11825,15 +11819,6 @@ react-lifecycles-compat@^3.0.0:
resolved "https://registry.npmjs.org/react-lifecycles-compat/-/react-lifecycles-compat-3.0.4.tgz"
integrity sha512-fBASbA6LnOU9dOU2eW7aQ8xmYBSXUIWr+UmF9b1efZBazGNO+rcXT/icdKnYm2pTwcRylVUYwW7H1PHfLekVzA==
react-lottie@^1.2.10:
version "1.2.10"
resolved "https://registry.yarnpkg.com/react-lottie/-/react-lottie-1.2.10.tgz#399f78a448a7833b2380d74fc489ecf15f8d18c7"
integrity sha512-x0eWX3Z6zSx1XM5QSjnLupc6D22LlMCB0PH06O/N/epR2hsLaj1Vxd9RtMnbbEHjJ/qlsgHJ6bpN3vnZI92hjw==
dependencies:
babel-runtime "^6.26.0"
lottie-web "^5.12.2"
prop-types "^15.6.1"
react-markdown@10.1.0:
version "10.1.0"
resolved "https://registry.npmjs.org/react-markdown/-/react-markdown-10.1.0.tgz"
@@ -12021,10 +12006,10 @@ react-window@^1.8.11:
"@babel/runtime" "^7.0.0"
memoize-one ">=3.1.1 <6"
react@*, react@19.0.0, react@19.1.0:
version "19.1.0"
resolved "https://registry.yarnpkg.com/react/-/react-19.1.0.tgz#926864b6c48da7627f004795d6cce50e90793b75"
integrity sha512-FS+XFBNvn3GTAWq26joslQgWNoFu08F4kl0J4CgdNKADkdSGXQyTCnKteIAJy96Br6YbpEU1LSzV5dYtjMkMDg==
react@19.0.0, react@19.2.1:
version "19.2.1"
resolved "https://registry.yarnpkg.com/react/-/react-19.2.1.tgz#8600fa205e58e2e807f6ef431c9f6492591a2700"
integrity sha512-DGrYcCWK7tvYMnWh79yrPHt+vdx9tY+1gPZa7nJQtO/p8bLTDaHp4dzwEhQB7pZ4Xe3ok4XKuEPrVuc+wlpkmw==
readable-stream@^3.4.0:
version "3.6.2"
@@ -12101,11 +12086,6 @@ regenerate@^1.4.2:
resolved "https://registry.npmjs.org/regenerate/-/regenerate-1.4.2.tgz"
integrity sha512-zrceR/XhGYU/d/opr2EKO7aRHUeiBI8qjtfHqADTwZd6Szfy16la6kqD0MIUs5z5hx6AaKa+PixpPrR289+I0A==
regenerator-runtime@^0.11.0:
version "0.11.1"
resolved "https://registry.yarnpkg.com/regenerator-runtime/-/regenerator-runtime-0.11.1.tgz#be05ad7f9bf7d22e056f9726cee5017fbf19e2e9"
integrity sha512-MguG95oij0fC3QV3URf4V2SDYGJhJnJGqvIIgdECeODCT98wSWDAJ94SSuVpYQUoTcGUIL6L4yNB7j1DFFHSBg==
regex-recursion@^6.0.2:
version "6.0.2"
resolved "https://registry.yarnpkg.com/regex-recursion/-/regex-recursion-6.0.2.tgz#a0b1977a74c87f073377b938dbedfab2ea582b33"
@@ -12464,10 +12444,10 @@ scheduler@0.25.0-rc-603e6108-20241029:
resolved "https://registry.npmjs.org/scheduler/-/scheduler-0.25.0-rc-603e6108-20241029.tgz"
integrity sha512-pFwF6H1XrSdYYNLfOcGlM28/j8CGLu8IvdrxqhjWULe2bPcKiKW4CV+OWqR/9fT52mywx65l7ysNkjLKBda7eA==
scheduler@^0.26.0:
version "0.26.0"
resolved "https://registry.yarnpkg.com/scheduler/-/scheduler-0.26.0.tgz#4ce8a8c2a2095f13ea11bf9a445be50c555d6337"
integrity sha512-NlHwttCI/l5gCPR3D1nNXtWABUmBwvZpEQiD4IXSbIDq8BzLIK/7Ir5gTFSGZDUu37K5cMNp0hFtzO38sC7gWA==
scheduler@^0.27.0:
version "0.27.0"
resolved "https://registry.yarnpkg.com/scheduler/-/scheduler-0.27.0.tgz#0c4ef82d67d1e5c1e359e8fc76d3a87f045fe5bd"
integrity sha512-eNv+WrVbKu1f3vbYJT/xtiF5syA5HPIMtf9IgY/nKg0sWqzAUEvqY/xm7OcZc/qafLx/iO9FgOmeSAp4v5ti/Q==
schema-utils@^4.3.0, schema-utils@^4.3.2:
version "4.3.2"
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "mail_mjml",
"version": "0.0.8",
"version": "0.0.10",
"description": "An util to generate html and text django's templates from mjml templates",
"type": "module",
"dependencies": {