Compare commits

..

5 Commits

Author SHA1 Message Date
Zamil Majdy
0da7a54952 test(backend): update tests to expect exceptions instead of None/False
- Update generate_embedding tests to expect RuntimeError/Exception instead of None
- Update store_embedding tests to expect Exception instead of False
- Update ensure_embedding tests to use side_effect=Exception instead of return_value=None
- Update hybrid search tests to mock embed_query with side_effect=Exception
- All tests now verify exception-based error handling instead of return value checking
2026-01-23 23:55:22 -06:00
Zamil Majdy
ba0aa83de3 fix(backend): remove unnecessary exception re-raising in store listing approval
- Let embedding exceptions bubble up naturally
- Only catch exceptions when graceful fallback is needed (search functions)
- Store listing approval should fail with actual error, not wrapped ValueError
2026-01-23 23:36:24 -06:00
Zamil Majdy
4c9333fc37 fix(backend): update callers to catch exceptions instead of checking None/False
- Update store listing approval to catch embedding errors with try/except
- Update semantic_search to catch embedding generation failures
- Update hybrid search (2 places) to catch and gracefully degrade to lexical search
- Remove None return type from embed_query (now raises exceptions)
- All error handling moved to caller level for consistency
2026-01-23 23:31:52 -06:00
Zamil Majdy
03c805ac5a refactor(backend): remove error swallowing in embedding functions
- Remove try/except blocks from individual embedding functions (generate_embedding, store_content_embedding, ensure_content_embedding, get_content_embedding, ensure_embedding)
- Let exceptions propagate to batch operation level
- Update batch error aggregation to show all unique error types with counts instead of just first error
- Prevents Sentry spam while providing better error diagnostics
2026-01-23 23:20:49 -06:00
Zamil Majdy
24d91a6e3e fix(backend): log only first error in embedding batch to prevent Sentry spam
Addresses AUTOGPT-SERVER-7D2

When batch operations like embedding backfill fail for multiple items with
the same error (e.g., database unavailable, vector type missing), log only
the first exception instead of spamming Sentry with identical alerts.

The batch already uses asyncio.gather(return_exceptions=True), so we just
check for failures and log the first exception with context about how many
items failed.

Before: 100 items fail → 100 identical Sentry alerts
After: 100 items fail → 1 Sentry alert with context

Impact: Reduces Sentry noise while preserving diagnostic information
2026-01-23 23:14:30 -06:00
19 changed files with 233 additions and 957 deletions

View File

@@ -178,10 +178,5 @@ AYRSHARE_JWT_KEY=
SMARTLEAD_API_KEY=
ZEROBOUNCE_API_KEY=
# PostHog Analytics
# Get API key from https://posthog.com - Project Settings > Project API Key
POSTHOG_API_KEY=
POSTHOG_HOST=https://eu.i.posthog.com
# Other Services
AUTOMOD_API_KEY=

View File

@@ -48,7 +48,6 @@ from .response_model import (
StreamUsage,
)
from .tools import execute_tool, tools
from .tracking import track_user_message
logger = logging.getLogger(__name__)
@@ -104,33 +103,16 @@ async def _build_system_prompt(user_id: str | None) -> tuple[str, Any]:
return compiled, understanding
async def _generate_session_title(
message: str,
user_id: str | None = None,
session_id: str | None = None,
) -> str | None:
async def _generate_session_title(message: str) -> str | None:
"""Generate a concise title for a chat session based on the first message.
Args:
message: The first user message in the session
user_id: User ID for OpenRouter tracing (optional)
session_id: Session ID for OpenRouter tracing (optional)
Returns:
A short title (3-6 words) or None if generation fails
"""
try:
# Build extra_body for OpenRouter tracing and PostHog analytics
extra_body: dict[str, Any] = {}
if user_id:
extra_body["user"] = user_id[:128] # OpenRouter limit
extra_body["posthogDistinctId"] = user_id
if session_id:
extra_body["session_id"] = session_id[:128] # OpenRouter limit
extra_body["posthogProperties"] = {
"environment": settings.config.app_env.value,
}
response = await client.chat.completions.create(
model=config.title_model,
messages=[
@@ -145,7 +127,6 @@ async def _generate_session_title(
{"role": "user", "content": message[:500]}, # Limit input length
],
max_tokens=20,
extra_body=extra_body,
)
title = response.choices[0].message.content
if title:
@@ -256,14 +237,6 @@ async def stream_chat_completion(
f"new message_count={len(session.messages)}"
)
# Track user message in PostHog
if is_user_message:
track_user_message(
user_id=user_id,
session_id=session_id,
message_length=len(message),
)
logger.info(
f"Upserting session: {session.session_id} with user id {session.user_id}, "
f"message_count={len(session.messages)}"
@@ -283,15 +256,10 @@ async def stream_chat_completion(
# stale data issues when the main flow modifies the session
captured_session_id = session_id
captured_message = message
captured_user_id = user_id
async def _update_title():
try:
title = await _generate_session_title(
captured_message,
user_id=captured_user_id,
session_id=captured_session_id,
)
title = await _generate_session_title(captured_message)
if title:
# Use dedicated title update function that doesn't
# touch messages, avoiding race conditions
@@ -730,20 +698,6 @@ async def _stream_chat_chunks(
f"{f' (retry {retry_count}/{MAX_RETRIES})' if retry_count > 0 else ''}"
)
# Build extra_body for OpenRouter tracing and PostHog analytics
extra_body: dict[str, Any] = {
"posthogProperties": {
"environment": settings.config.app_env.value,
},
}
if session.user_id:
extra_body["user"] = session.user_id[:128] # OpenRouter limit
extra_body["posthogDistinctId"] = session.user_id
if session.session_id:
extra_body["session_id"] = session.session_id[
:128
] # OpenRouter limit
# Create the stream with proper types
stream = await client.chat.completions.create(
model=model,
@@ -752,7 +706,6 @@ async def _stream_chat_chunks(
tool_choice="auto",
stream=True,
stream_options={"include_usage": True},
extra_body=extra_body,
)
# Variables to accumulate tool calls

View File

@@ -1,10 +1,8 @@
import logging
from typing import TYPE_CHECKING, Any
from openai.types.chat import ChatCompletionToolParam
from backend.api.features.chat.model import ChatSession
from backend.api.features.chat.tracking import track_tool_called
from .add_understanding import AddUnderstandingTool
from .agent_output import AgentOutputTool
@@ -22,8 +20,6 @@ from .search_docs import SearchDocsTool
if TYPE_CHECKING:
from backend.api.features.chat.response_model import StreamToolOutputAvailable
logger = logging.getLogger(__name__)
# Single source of truth for all tools
TOOL_REGISTRY: dict[str, BaseTool] = {
"add_understanding": AddUnderstandingTool(),
@@ -60,17 +56,4 @@ async def execute_tool(
tool = TOOL_REGISTRY.get(tool_name)
if not tool:
raise ValueError(f"Tool {tool_name} not found")
# Track tool call in PostHog
logger.info(
f"Tracking tool call: tool={tool_name}, user={user_id}, "
f"session={session.session_id}, call_id={tool_call_id}"
)
track_tool_called(
user_id=user_id,
session_id=session.session_id,
tool_name=tool_name,
tool_call_id=tool_call_id,
)
return await tool.execute(user_id, session, tool_call_id, **parameters)

View File

@@ -8,10 +8,6 @@ from pydantic import BaseModel, Field, field_validator
from backend.api.features.chat.config import ChatConfig
from backend.api.features.chat.model import ChatSession
from backend.api.features.chat.tracking import (
track_agent_run_success,
track_agent_scheduled,
)
from backend.api.features.library import db as library_db
from backend.data.graph import GraphModel
from backend.data.model import CredentialsMetaInput
@@ -457,16 +453,6 @@ class RunAgentTool(BaseTool):
session.successful_agent_runs.get(library_agent.graph_id, 0) + 1
)
# Track in PostHog
track_agent_run_success(
user_id=user_id,
session_id=session_id,
graph_id=library_agent.graph_id,
graph_name=library_agent.name,
execution_id=execution.id,
library_agent_id=library_agent.id,
)
library_agent_link = f"/library/agents/{library_agent.id}"
return ExecutionStartedResponse(
message=(
@@ -548,18 +534,6 @@ class RunAgentTool(BaseTool):
session.successful_agent_schedules.get(library_agent.graph_id, 0) + 1
)
# Track in PostHog
track_agent_scheduled(
user_id=user_id,
session_id=session_id,
graph_id=library_agent.graph_id,
graph_name=library_agent.name,
schedule_id=result.id,
schedule_name=schedule_name,
cron=cron,
library_agent_id=library_agent.id,
)
library_agent_link = f"/library/agents/{library_agent.id}"
return ExecutionStartedResponse(
message=(

View File

@@ -1,250 +0,0 @@
"""PostHog analytics tracking for the chat system."""
import atexit
import logging
from typing import Any
from posthog import Posthog
from backend.util.settings import Settings
logger = logging.getLogger(__name__)
settings = Settings()
# PostHog client instance (lazily initialized)
_posthog_client: Posthog | None = None
def _shutdown_posthog() -> None:
"""Flush and shutdown PostHog client on process exit."""
if _posthog_client is not None:
_posthog_client.flush()
_posthog_client.shutdown()
atexit.register(_shutdown_posthog)
def _get_posthog_client() -> Posthog | None:
"""Get or create the PostHog client instance."""
global _posthog_client
if _posthog_client is not None:
return _posthog_client
if not settings.secrets.posthog_api_key:
logger.debug("PostHog API key not configured, analytics disabled")
return None
_posthog_client = Posthog(
settings.secrets.posthog_api_key,
host=settings.secrets.posthog_host,
)
logger.info(
f"PostHog client initialized with host: {settings.secrets.posthog_host}"
)
return _posthog_client
def _get_base_properties() -> dict[str, Any]:
"""Get base properties included in all events."""
return {
"environment": settings.config.app_env.value,
"source": "chat_copilot",
}
def track_user_message(
user_id: str | None,
session_id: str,
message_length: int,
) -> None:
"""Track when a user sends a message in chat.
Args:
user_id: The user's ID (or None for anonymous)
session_id: The chat session ID
message_length: Length of the user's message
"""
client = _get_posthog_client()
if not client:
return
try:
properties = {
**_get_base_properties(),
"session_id": session_id,
"message_length": message_length,
}
client.capture(
distinct_id=user_id or f"anonymous_{session_id}",
event="copilot_message_sent",
properties=properties,
)
except Exception as e:
logger.warning(f"Failed to track user message: {e}")
def track_tool_called(
user_id: str | None,
session_id: str,
tool_name: str,
tool_call_id: str,
) -> None:
"""Track when a tool is called in chat.
Args:
user_id: The user's ID (or None for anonymous)
session_id: The chat session ID
tool_name: Name of the tool being called
tool_call_id: Unique ID of the tool call
"""
client = _get_posthog_client()
if not client:
logger.info("PostHog client not available for tool tracking")
return
try:
properties = {
**_get_base_properties(),
"session_id": session_id,
"tool_name": tool_name,
"tool_call_id": tool_call_id,
}
distinct_id = user_id or f"anonymous_{session_id}"
logger.info(
f"Sending copilot_tool_called event to PostHog: distinct_id={distinct_id}, "
f"tool_name={tool_name}"
)
client.capture(
distinct_id=distinct_id,
event="copilot_tool_called",
properties=properties,
)
except Exception as e:
logger.warning(f"Failed to track tool call: {e}")
def track_agent_run_success(
user_id: str,
session_id: str,
graph_id: str,
graph_name: str,
execution_id: str,
library_agent_id: str,
) -> None:
"""Track when an agent is successfully run.
Args:
user_id: The user's ID
session_id: The chat session ID
graph_id: ID of the agent graph
graph_name: Name of the agent
execution_id: ID of the execution
library_agent_id: ID of the library agent
"""
client = _get_posthog_client()
if not client:
return
try:
properties = {
**_get_base_properties(),
"session_id": session_id,
"graph_id": graph_id,
"graph_name": graph_name,
"execution_id": execution_id,
"library_agent_id": library_agent_id,
}
client.capture(
distinct_id=user_id,
event="copilot_agent_run_success",
properties=properties,
)
except Exception as e:
logger.warning(f"Failed to track agent run: {e}")
def track_agent_scheduled(
user_id: str,
session_id: str,
graph_id: str,
graph_name: str,
schedule_id: str,
schedule_name: str,
cron: str,
library_agent_id: str,
) -> None:
"""Track when an agent is successfully scheduled.
Args:
user_id: The user's ID
session_id: The chat session ID
graph_id: ID of the agent graph
graph_name: Name of the agent
schedule_id: ID of the schedule
schedule_name: Name of the schedule
cron: Cron expression for the schedule
library_agent_id: ID of the library agent
"""
client = _get_posthog_client()
if not client:
return
try:
properties = {
**_get_base_properties(),
"session_id": session_id,
"graph_id": graph_id,
"graph_name": graph_name,
"schedule_id": schedule_id,
"schedule_name": schedule_name,
"cron": cron,
"library_agent_id": library_agent_id,
}
client.capture(
distinct_id=user_id,
event="copilot_agent_scheduled",
properties=properties,
)
except Exception as e:
logger.warning(f"Failed to track agent schedule: {e}")
def track_trigger_setup(
user_id: str,
session_id: str,
graph_id: str,
graph_name: str,
trigger_type: str,
library_agent_id: str,
) -> None:
"""Track when a trigger is set up for an agent.
Args:
user_id: The user's ID
session_id: The chat session ID
graph_id: ID of the agent graph
graph_name: Name of the agent
trigger_type: Type of trigger (e.g., 'webhook')
library_agent_id: ID of the library agent
"""
client = _get_posthog_client()
if not client:
return
try:
properties = {
**_get_base_properties(),
"session_id": session_id,
"graph_id": graph_id,
"graph_name": graph_name,
"trigger_type": trigger_type,
"library_agent_id": library_agent_id,
}
client.capture(
distinct_id=user_id,
event="copilot_trigger_setup",
properties=properties,
)
except Exception as e:
logger.warning(f"Failed to track trigger setup: {e}")

View File

@@ -1552,7 +1552,7 @@ async def review_store_submission(
# Generate embedding for approved listing (blocking - admin operation)
# Inside transaction: if embedding fails, entire transaction rolls back
embedding_success = await ensure_embedding(
await ensure_embedding(
version_id=store_listing_version_id,
name=store_listing_version.name,
description=store_listing_version.description,
@@ -1560,12 +1560,6 @@ async def review_store_submission(
categories=store_listing_version.categories or [],
tx=tx,
)
if not embedding_success:
raise ValueError(
f"Failed to generate embedding for listing {store_listing_version_id}. "
"This is likely due to OpenAI API being unavailable. "
"Please try again later or contact support if the issue persists."
)
await prisma.models.StoreListing.prisma(tx).update(
where={"id": store_listing_version.StoreListing.id},

View File

@@ -63,49 +63,42 @@ def build_searchable_text(
return " ".join(parts)
async def generate_embedding(text: str) -> list[float] | None:
async def generate_embedding(text: str) -> list[float]:
"""
Generate embedding for text using OpenAI API.
Returns None if embedding generation fails.
Fail-fast: no retries to maintain consistency with approval flow.
Raises exceptions on failure - caller should handle.
"""
try:
client = get_openai_client()
if not client:
logger.error("openai_internal_api_key not set, cannot generate embedding")
return None
client = get_openai_client()
if not client:
raise RuntimeError("openai_internal_api_key not set, cannot generate embedding")
# Truncate text to token limit using tiktoken
# Character-based truncation is insufficient because token ratios vary by content type
enc = encoding_for_model(EMBEDDING_MODEL)
tokens = enc.encode(text)
if len(tokens) > EMBEDDING_MAX_TOKENS:
tokens = tokens[:EMBEDDING_MAX_TOKENS]
truncated_text = enc.decode(tokens)
logger.info(
f"Truncated text from {len(enc.encode(text))} to {len(tokens)} tokens"
)
else:
truncated_text = text
start_time = time.time()
response = await client.embeddings.create(
model=EMBEDDING_MODEL,
input=truncated_text,
)
latency_ms = (time.time() - start_time) * 1000
embedding = response.data[0].embedding
# Truncate text to token limit using tiktoken
# Character-based truncation is insufficient because token ratios vary by content type
enc = encoding_for_model(EMBEDDING_MODEL)
tokens = enc.encode(text)
if len(tokens) > EMBEDDING_MAX_TOKENS:
tokens = tokens[:EMBEDDING_MAX_TOKENS]
truncated_text = enc.decode(tokens)
logger.info(
f"Generated embedding: {len(embedding)} dims, "
f"{len(tokens)} tokens, {latency_ms:.0f}ms"
f"Truncated text from {len(enc.encode(text))} to {len(tokens)} tokens"
)
return embedding
else:
truncated_text = text
except Exception as e:
logger.error(f"Failed to generate embedding: {e}")
return None
start_time = time.time()
response = await client.embeddings.create(
model=EMBEDDING_MODEL,
input=truncated_text,
)
latency_ms = (time.time() - start_time) * 1000
embedding = response.data[0].embedding
logger.info(
f"Generated embedding: {len(embedding)} dims, "
f"{len(tokens)} tokens, {latency_ms:.0f}ms"
)
return embedding
async def store_embedding(
@@ -144,48 +137,45 @@ async def store_content_embedding(
New function for unified content embedding storage.
Uses raw SQL since Prisma doesn't natively support pgvector.
Raises exceptions on failure - caller should handle.
"""
try:
client = tx if tx else prisma.get_client()
client = tx if tx else prisma.get_client()
# Convert embedding to PostgreSQL vector format
embedding_str = embedding_to_vector_string(embedding)
metadata_json = dumps(metadata or {})
# Convert embedding to PostgreSQL vector format
embedding_str = embedding_to_vector_string(embedding)
metadata_json = dumps(metadata or {})
# Upsert the embedding
# WHERE clause in DO UPDATE prevents PostgreSQL 15 bug with NULLS NOT DISTINCT
# Use unqualified ::vector - pgvector is in search_path on all environments
await execute_raw_with_schema(
"""
INSERT INTO {schema_prefix}"UnifiedContentEmbedding" (
"id", "contentType", "contentId", "userId", "embedding", "searchableText", "metadata", "createdAt", "updatedAt"
)
VALUES (gen_random_uuid()::text, $1::{schema_prefix}"ContentType", $2, $3, $4::vector, $5, $6::jsonb, NOW(), NOW())
ON CONFLICT ("contentType", "contentId", "userId")
DO UPDATE SET
"embedding" = $4::vector,
"searchableText" = $5,
"metadata" = $6::jsonb,
"updatedAt" = NOW()
WHERE {schema_prefix}"UnifiedContentEmbedding"."contentType" = $1::{schema_prefix}"ContentType"
AND {schema_prefix}"UnifiedContentEmbedding"."contentId" = $2
AND ({schema_prefix}"UnifiedContentEmbedding"."userId" = $3 OR ($3 IS NULL AND {schema_prefix}"UnifiedContentEmbedding"."userId" IS NULL))
""",
content_type,
content_id,
user_id,
embedding_str,
searchable_text,
metadata_json,
client=client,
# Upsert the embedding
# WHERE clause in DO UPDATE prevents PostgreSQL 15 bug with NULLS NOT DISTINCT
# Use unqualified ::vector - pgvector is in search_path on all environments
await execute_raw_with_schema(
"""
INSERT INTO {schema_prefix}"UnifiedContentEmbedding" (
"id", "contentType", "contentId", "userId", "embedding", "searchableText", "metadata", "createdAt", "updatedAt"
)
VALUES (gen_random_uuid()::text, $1::{schema_prefix}"ContentType", $2, $3, $4::vector, $5, $6::jsonb, NOW(), NOW())
ON CONFLICT ("contentType", "contentId", "userId")
DO UPDATE SET
"embedding" = $4::vector,
"searchableText" = $5,
"metadata" = $6::jsonb,
"updatedAt" = NOW()
WHERE {schema_prefix}"UnifiedContentEmbedding"."contentType" = $1::{schema_prefix}"ContentType"
AND {schema_prefix}"UnifiedContentEmbedding"."contentId" = $2
AND ({schema_prefix}"UnifiedContentEmbedding"."userId" = $3 OR ($3 IS NULL AND {schema_prefix}"UnifiedContentEmbedding"."userId" IS NULL))
""",
content_type,
content_id,
user_id,
embedding_str,
searchable_text,
metadata_json,
client=client,
)
logger.info(f"Stored embedding for {content_type}:{content_id}")
return True
except Exception as e:
logger.error(f"Failed to store embedding for {content_type}:{content_id}: {e}")
return False
logger.info(f"Stored embedding for {content_type}:{content_id}")
return True
async def get_embedding(version_id: str) -> dict[str, Any] | None:
@@ -217,34 +207,31 @@ async def get_content_embedding(
New function for unified content embedding retrieval.
Returns dict with contentType, contentId, embedding, timestamps or None if not found.
Raises exceptions on failure - caller should handle.
"""
try:
result = await query_raw_with_schema(
"""
SELECT
"contentType",
"contentId",
"userId",
"embedding"::text as "embedding",
"searchableText",
"metadata",
"createdAt",
"updatedAt"
FROM {schema_prefix}"UnifiedContentEmbedding"
WHERE "contentType" = $1::{schema_prefix}"ContentType" AND "contentId" = $2 AND ("userId" = $3 OR ($3 IS NULL AND "userId" IS NULL))
""",
content_type,
content_id,
user_id,
)
result = await query_raw_with_schema(
"""
SELECT
"contentType",
"contentId",
"userId",
"embedding"::text as "embedding",
"searchableText",
"metadata",
"createdAt",
"updatedAt"
FROM {schema_prefix}"UnifiedContentEmbedding"
WHERE "contentType" = $1::{schema_prefix}"ContentType" AND "contentId" = $2 AND ("userId" = $3 OR ($3 IS NULL AND "userId" IS NULL))
""",
content_type,
content_id,
user_id,
)
if result and len(result) > 0:
return result[0]
return None
except Exception as e:
logger.error(f"Failed to get embedding for {content_type}:{content_id}: {e}")
return None
if result and len(result) > 0:
return result[0]
return None
async def ensure_embedding(
@@ -272,46 +259,38 @@ async def ensure_embedding(
tx: Optional transaction client
Returns:
True if embedding exists/was created, False on failure
True if embedding exists/was created
Raises exceptions on failure - caller should handle.
"""
try:
# Check if embedding already exists
if not force:
existing = await get_embedding(version_id)
if existing and existing.get("embedding"):
logger.debug(f"Embedding for version {version_id} already exists")
return True
# Check if embedding already exists
if not force:
existing = await get_embedding(version_id)
if existing and existing.get("embedding"):
logger.debug(f"Embedding for version {version_id} already exists")
return True
# Build searchable text for embedding
searchable_text = build_searchable_text(
name, description, sub_heading, categories
)
# Build searchable text for embedding
searchable_text = build_searchable_text(name, description, sub_heading, categories)
# Generate new embedding
embedding = await generate_embedding(searchable_text)
if embedding is None:
logger.warning(f"Could not generate embedding for version {version_id}")
return False
# Generate new embedding
embedding = await generate_embedding(searchable_text)
# Store the embedding with metadata using new function
metadata = {
"name": name,
"subHeading": sub_heading,
"categories": categories,
}
return await store_content_embedding(
content_type=ContentType.STORE_AGENT,
content_id=version_id,
embedding=embedding,
searchable_text=searchable_text,
metadata=metadata,
user_id=None, # Store agents are public
tx=tx,
)
except Exception as e:
logger.error(f"Failed to ensure embedding for version {version_id}: {e}")
return False
# Store the embedding with metadata using new function
metadata = {
"name": name,
"subHeading": sub_heading,
"categories": categories,
}
return await store_content_embedding(
content_type=ContentType.STORE_AGENT,
content_id=version_id,
embedding=embedding,
searchable_text=searchable_text,
metadata=metadata,
user_id=None, # Store agents are public
tx=tx,
)
async def delete_embedding(version_id: str) -> bool:
@@ -521,6 +500,24 @@ async def backfill_all_content_types(batch_size: int = 10) -> dict[str, Any]:
success = sum(1 for result in results if result is True)
failed = len(results) - success
# Aggregate unique errors to avoid Sentry spam
if failed > 0:
# Group errors by type and message
error_summary: dict[str, int] = {}
for result in results:
if isinstance(result, Exception):
error_key = f"{type(result).__name__}: {str(result)}"
error_summary[error_key] = error_summary.get(error_key, 0) + 1
# Log aggregated error summary
error_details = ", ".join(
f"{error} ({count}x)" for error, count in error_summary.items()
)
logger.error(
f"{content_type.value}: {failed}/{len(results)} embeddings failed. "
f"Errors: {error_details}"
)
results_by_type[content_type.value] = {
"processed": len(missing_items),
"success": success,
@@ -557,11 +554,12 @@ async def backfill_all_content_types(batch_size: int = 10) -> dict[str, Any]:
}
async def embed_query(query: str) -> list[float] | None:
async def embed_query(query: str) -> list[float]:
"""
Generate embedding for a search query.
Same as generate_embedding but with clearer intent.
Raises exceptions on failure - caller should handle.
"""
return await generate_embedding(query)
@@ -594,40 +592,30 @@ async def ensure_content_embedding(
tx: Optional transaction client
Returns:
True if embedding exists/was created, False on failure
True if embedding exists/was created
Raises exceptions on failure - caller should handle.
"""
try:
# Check if embedding already exists
if not force:
existing = await get_content_embedding(content_type, content_id, user_id)
if existing and existing.get("embedding"):
logger.debug(
f"Embedding for {content_type}:{content_id} already exists"
)
return True
# Check if embedding already exists
if not force:
existing = await get_content_embedding(content_type, content_id, user_id)
if existing and existing.get("embedding"):
logger.debug(f"Embedding for {content_type}:{content_id} already exists")
return True
# Generate new embedding
embedding = await generate_embedding(searchable_text)
if embedding is None:
logger.warning(
f"Could not generate embedding for {content_type}:{content_id}"
)
return False
# Generate new embedding
embedding = await generate_embedding(searchable_text)
# Store the embedding
return await store_content_embedding(
content_type=content_type,
content_id=content_id,
embedding=embedding,
searchable_text=searchable_text,
metadata=metadata or {},
user_id=user_id,
tx=tx,
)
except Exception as e:
logger.error(f"Failed to ensure embedding for {content_type}:{content_id}: {e}")
return False
# Store the embedding
return await store_content_embedding(
content_type=content_type,
content_id=content_id,
embedding=embedding,
searchable_text=searchable_text,
metadata=metadata or {},
user_id=user_id,
tx=tx,
)
async def cleanup_orphaned_embeddings() -> dict[str, Any]:
@@ -854,9 +842,8 @@ async def semantic_search(
limit = 100
# Generate query embedding
query_embedding = await embed_query(query)
if query_embedding is not None:
try:
query_embedding = await embed_query(query)
# Semantic search with embeddings
embedding_str = embedding_to_vector_string(query_embedding)
@@ -907,24 +894,21 @@ async def semantic_search(
"""
)
try:
results = await query_raw_with_schema(sql, *params)
return [
{
"content_id": row["content_id"],
"content_type": row["content_type"],
"searchable_text": row["searchable_text"],
"metadata": row["metadata"],
"similarity": float(row["similarity"]),
}
for row in results
]
except Exception as e:
logger.error(f"Semantic search failed: {e}")
# Fall through to lexical search below
results = await query_raw_with_schema(sql, *params)
return [
{
"content_id": row["content_id"],
"content_type": row["content_type"],
"searchable_text": row["searchable_text"],
"metadata": row["metadata"],
"similarity": float(row["similarity"]),
}
for row in results
]
except Exception as e:
logger.warning(f"Semantic search failed, falling back to lexical search: {e}")
# Fallback to lexical search if embeddings unavailable
logger.warning("Falling back to lexical search (embeddings unavailable)")
params_lexical: list[Any] = [limit]
user_filter = ""

View File

@@ -298,17 +298,16 @@ async def test_schema_handling_error_cases():
mock_client.execute_raw.side_effect = Exception("Database error")
mock_get_client.return_value = mock_client
result = await embeddings.store_content_embedding(
content_type=ContentType.STORE_AGENT,
content_id="test-id",
embedding=[0.1] * EMBEDDING_DIM,
searchable_text="test",
metadata=None,
user_id=None,
)
# Should return False on error, not raise
assert result is False
# Should raise exception on error
with pytest.raises(Exception, match="Database error"):
await embeddings.store_content_embedding(
content_type=ContentType.STORE_AGENT,
content_id="test-id",
embedding=[0.1] * EMBEDDING_DIM,
searchable_text="test",
metadata=None,
user_id=None,
)
if __name__ == "__main__":

View File

@@ -80,9 +80,8 @@ async def test_generate_embedding_no_api_key():
) as mock_get_client:
mock_get_client.return_value = None
result = await embeddings.generate_embedding("test text")
assert result is None
with pytest.raises(RuntimeError, match="openai_internal_api_key not set"):
await embeddings.generate_embedding("test text")
@pytest.mark.asyncio(loop_scope="session")
@@ -97,9 +96,8 @@ async def test_generate_embedding_api_error():
) as mock_get_client:
mock_get_client.return_value = mock_client
result = await embeddings.generate_embedding("test text")
assert result is None
with pytest.raises(Exception, match="API Error"):
await embeddings.generate_embedding("test text")
@pytest.mark.asyncio(loop_scope="session")
@@ -173,11 +171,10 @@ async def test_store_embedding_database_error(mocker):
embedding = [0.1, 0.2, 0.3]
result = await embeddings.store_embedding(
version_id="test-version-id", embedding=embedding, tx=mock_client
)
assert result is False
with pytest.raises(Exception, match="Database error"):
await embeddings.store_embedding(
version_id="test-version-id", embedding=embedding, tx=mock_client
)
@pytest.mark.asyncio(loop_scope="session")
@@ -277,17 +274,16 @@ async def test_ensure_embedding_create_new(mock_get, mock_store, mock_generate):
async def test_ensure_embedding_generation_fails(mock_get, mock_generate):
"""Test ensure_embedding when generation fails."""
mock_get.return_value = None
mock_generate.return_value = None
mock_generate.side_effect = Exception("Generation failed")
result = await embeddings.ensure_embedding(
version_id="test-id",
name="Test",
description="Test description",
sub_heading="Test heading",
categories=["test"],
)
assert result is False
with pytest.raises(Exception, match="Generation failed"):
await embeddings.ensure_embedding(
version_id="test-id",
name="Test",
description="Test description",
sub_heading="Test heading",
categories=["test"],
)
@pytest.mark.asyncio(loop_scope="session")

View File

@@ -186,13 +186,12 @@ async def unified_hybrid_search(
offset = (page - 1) * page_size
# Generate query embedding
query_embedding = await embed_query(query)
# Graceful degradation if embedding unavailable
if query_embedding is None or not query_embedding:
# Generate query embedding with graceful degradation
try:
query_embedding = await embed_query(query)
except Exception as e:
logger.warning(
"Failed to generate query embedding - falling back to lexical-only search. "
f"Failed to generate query embedding - falling back to lexical-only search: {e}. "
"Check that openai_internal_api_key is configured and OpenAI API is accessible."
)
query_embedding = [0.0] * EMBEDDING_DIM
@@ -464,13 +463,12 @@ async def hybrid_search(
offset = (page - 1) * page_size
# Generate query embedding
query_embedding = await embed_query(query)
# Graceful degradation
if query_embedding is None or not query_embedding:
# Generate query embedding with graceful degradation
try:
query_embedding = await embed_query(query)
except Exception as e:
logger.warning(
"Failed to generate query embedding - falling back to lexical-only search."
f"Failed to generate query embedding - falling back to lexical-only search: {e}"
)
query_embedding = [0.0] * EMBEDDING_DIM
total_non_semantic = (

View File

@@ -172,8 +172,8 @@ async def test_hybrid_search_without_embeddings():
with patch(
"backend.api.features.store.hybrid_search.query_raw_with_schema"
) as mock_query:
# Simulate embedding failure
mock_embed.return_value = None
# Simulate embedding failure by raising exception
mock_embed.side_effect = Exception("Embedding generation failed")
mock_query.return_value = mock_results
# Should NOT raise - graceful degradation
@@ -613,7 +613,9 @@ async def test_unified_hybrid_search_graceful_degradation():
"backend.api.features.store.hybrid_search.embed_query"
) as mock_embed:
mock_query.return_value = mock_results
mock_embed.return_value = None # Embedding failure
mock_embed.side_effect = Exception(
"Embedding generation failed"
) # Embedding failure
# Should NOT raise - graceful degradation
results, total = await unified_hybrid_search(

View File

@@ -666,12 +666,6 @@ class Secrets(UpdateTrackingModel["Secrets"], BaseSettings):
default="https://cloud.langfuse.com", description="Langfuse host URL"
)
# PostHog analytics
posthog_api_key: str = Field(default="", description="PostHog API key")
posthog_host: str = Field(
default="https://us.i.posthog.com", description="PostHog host URL"
)
# Add more secret fields as needed
model_config = SettingsConfigDict(
env_file=".env",

View File

@@ -4204,14 +4204,14 @@ strenum = {version = ">=0.4.9,<0.5.0", markers = "python_version < \"3.11\""}
[[package]]
name = "posthog"
version = "7.6.0"
version = "6.1.1"
description = "Integrate PostHog into any python application."
optional = false
python-versions = ">=3.10"
python-versions = ">=3.9"
groups = ["main"]
files = [
{file = "posthog-7.6.0-py3-none-any.whl", hash = "sha256:c4dd78cf77c4fecceb965f86066e5ac37886ef867d68ffe75a1db5d681d7d9ad"},
{file = "posthog-7.6.0.tar.gz", hash = "sha256:941dfd278ee427c9b14640f09b35b5bb52a71bdf028d7dbb7307e1838fd3002e"},
{file = "posthog-6.1.1-py3-none-any.whl", hash = "sha256:329fd3d06b4d54cec925f47235bd8e327c91403c2f9ec38f1deb849535934dba"},
{file = "posthog-6.1.1.tar.gz", hash = "sha256:b453f54c4a2589da859fd575dd3bf86fcb40580727ec399535f268b1b9f318b8"},
]
[package.dependencies]
@@ -4225,7 +4225,7 @@ typing-extensions = ">=4.2.0"
[package.extras]
dev = ["django-stubs", "lxml", "mypy", "mypy-baseline", "packaging", "pre-commit", "pydantic", "ruff", "setuptools", "tomli", "tomli_w", "twine", "types-mock", "types-python-dateutil", "types-requests", "types-setuptools", "types-six", "wheel"]
langchain = ["langchain (>=0.2.0)"]
test = ["anthropic (>=0.72)", "coverage", "django", "freezegun (==1.5.1)", "google-genai", "langchain-anthropic (>=1.0)", "langchain-community (>=0.4)", "langchain-core (>=1.0)", "langchain-openai (>=1.0)", "langgraph (>=1.0)", "mock (>=2.0.0)", "openai (>=2.0)", "parameterized (>=0.8.1)", "pydantic", "pytest", "pytest-asyncio", "pytest-timeout"]
test = ["anthropic", "coverage", "django", "freezegun (==1.5.1)", "google-genai", "langchain-anthropic (>=0.3.15)", "langchain-community (>=0.3.25)", "langchain-core (>=0.3.65)", "langchain-openai (>=0.3.22)", "langgraph (>=0.4.8)", "mock (>=2.0.0)", "openai", "parameterized (>=0.8.1)", "pydantic", "pytest", "pytest-asyncio", "pytest-timeout"]
[[package]]
name = "postmarker"
@@ -7512,4 +7512,4 @@ cffi = ["cffi (>=1.11)"]
[metadata]
lock-version = "2.1"
python-versions = ">=3.10,<3.14"
content-hash = "ee5742dc1a9df50dfc06d4b26a1682cbb2b25cab6b79ce5625ec272f93e4f4bf"
content-hash = "18b92e09596298c82432e4d0a85cb6d80a40b4229bee0a0c15f0529fd6cb21a4"

View File

@@ -85,7 +85,6 @@ exa-py = "^1.14.20"
croniter = "^6.0.0"
stagehand = "^0.5.1"
gravitas-md2gdocs = "^0.1.0"
posthog = "^7.6.0"
[tool.poetry.group.dev.dependencies]
aiohappyeyeballs = "^2.6.1"

View File

@@ -30,7 +30,3 @@ NEXT_PUBLIC_TURNSTILE=disabled
# PR previews
NEXT_PUBLIC_PREVIEW_STEALING_DEV=
# PostHog Analytics
NEXT_PUBLIC_POSTHOG_KEY=
NEXT_PUBLIC_POSTHOG_HOST=https://eu.i.posthog.com

View File

@@ -34,7 +34,6 @@
"@hookform/resolvers": "5.2.2",
"@next/third-parties": "15.4.6",
"@phosphor-icons/react": "2.1.10",
"@posthog/react": "1.7.0",
"@radix-ui/react-accordion": "1.2.12",
"@radix-ui/react-alert-dialog": "1.1.15",
"@radix-ui/react-avatar": "1.1.10",
@@ -92,7 +91,6 @@
"next-themes": "0.4.6",
"nuqs": "2.7.2",
"party-js": "2.2.0",
"posthog-js": "1.334.1",
"react": "18.3.1",
"react-currency-input-field": "4.0.3",
"react-day-picker": "9.11.1",
@@ -122,6 +120,7 @@
},
"devDependencies": {
"@chromatic-com/storybook": "4.1.2",
"happy-dom": "20.3.4",
"@opentelemetry/instrumentation": "0.209.0",
"@playwright/test": "1.56.1",
"@storybook/addon-a11y": "9.1.5",
@@ -149,7 +148,6 @@
"eslint": "8.57.1",
"eslint-config-next": "15.5.7",
"eslint-plugin-storybook": "9.1.5",
"happy-dom": "20.3.4",
"import-in-the-middle": "2.0.2",
"msw": "2.11.6",
"msw-storybook-addon": "2.0.6",

View File

@@ -23,9 +23,6 @@ importers:
'@phosphor-icons/react':
specifier: 2.1.10
version: 2.1.10(react-dom@18.3.1(react@18.3.1))(react@18.3.1)
'@posthog/react':
specifier: 1.7.0
version: 1.7.0(@types/react@18.3.17)(posthog-js@1.334.1)(react@18.3.1)
'@radix-ui/react-accordion':
specifier: 1.2.12
version: 1.2.12(@types/react-dom@18.3.5(@types/react@18.3.17))(@types/react@18.3.17)(react-dom@18.3.1(react@18.3.1))(react@18.3.1)
@@ -197,9 +194,6 @@ importers:
party-js:
specifier: 2.2.0
version: 2.2.0
posthog-js:
specifier: 1.334.1
version: 1.334.1
react:
specifier: 18.3.1
version: 18.3.1
@@ -1800,10 +1794,6 @@ packages:
'@open-draft/until@2.1.0':
resolution: {integrity: sha512-U69T3ItWHvLwGg5eJ0n3I62nWuE6ilHlmz7zM0npLBRvPRd7e6NYmg54vvRtP5mZG7kZqZCFVdsTWo7BPtBujg==}
'@opentelemetry/api-logs@0.208.0':
resolution: {integrity: sha512-CjruKY9V6NMssL/T1kAFgzosF1v9o6oeN+aX5JB/C/xPNtmgIJqcXHG7fA82Ou1zCpWGl4lROQUKwUNE1pMCyg==}
engines: {node: '>=8.0.0'}
'@opentelemetry/api-logs@0.209.0':
resolution: {integrity: sha512-xomnUNi7TiAGtOgs0tb54LyrjRZLu9shJGGwkcN7NgtiPYOpNnKLkRJtzZvTjD/w6knSZH9sFZcUSUovYOPg6A==}
engines: {node: '>=8.0.0'}
@@ -1824,12 +1814,6 @@ packages:
peerDependencies:
'@opentelemetry/api': '>=1.0.0 <1.10.0'
'@opentelemetry/exporter-logs-otlp-http@0.208.0':
resolution: {integrity: sha512-jOv40Bs9jy9bZVLo/i8FwUiuCvbjWDI+ZW13wimJm4LjnlwJxGgB+N/VWOZUTpM+ah/awXeQqKdNlpLf2EjvYg==}
engines: {node: ^18.19.0 || >=20.6.0}
peerDependencies:
'@opentelemetry/api': ^1.3.0
'@opentelemetry/instrumentation-amqplib@0.55.0':
resolution: {integrity: sha512-5ULoU8p+tWcQw5PDYZn8rySptGSLZHNX/7srqo2TioPnAAcvTy6sQFQXsNPrAnyRRtYGMetXVyZUy5OaX1+IfA==}
engines: {node: ^18.19.0 || >=20.6.0}
@@ -1968,18 +1952,6 @@ packages:
peerDependencies:
'@opentelemetry/api': ^1.3.0
'@opentelemetry/otlp-exporter-base@0.208.0':
resolution: {integrity: sha512-gMd39gIfVb2OgxldxUtOwGJYSH8P1kVFFlJLuut32L6KgUC4gl1dMhn+YC2mGn0bDOiQYSk/uHOdSjuKp58vvA==}
engines: {node: ^18.19.0 || >=20.6.0}
peerDependencies:
'@opentelemetry/api': ^1.3.0
'@opentelemetry/otlp-transformer@0.208.0':
resolution: {integrity: sha512-DCFPY8C6lAQHUNkzcNT9R+qYExvsk6C5Bto2pbNxgicpcSWbe2WHShLxkOxIdNcBiYPdVHv/e7vH7K6TI+C+fQ==}
engines: {node: ^18.19.0 || >=20.6.0}
peerDependencies:
'@opentelemetry/api': ^1.3.0
'@opentelemetry/redis-common@0.38.2':
resolution: {integrity: sha512-1BCcU93iwSRZvDAgwUxC/DV4T/406SkMfxGqu5ojc3AvNI+I9GhV7v0J1HljsczuuhcnFLYqD5VmwVXfCGHzxA==}
engines: {node: ^18.19.0 || >=20.6.0}
@@ -1990,18 +1962,6 @@ packages:
peerDependencies:
'@opentelemetry/api': '>=1.3.0 <1.10.0'
'@opentelemetry/sdk-logs@0.208.0':
resolution: {integrity: sha512-QlAyL1jRpOeaqx7/leG1vJMp84g0xKP6gJmfELBpnI4O/9xPX+Hu5m1POk9Kl+veNkyth5t19hRlN6tNY1sjbA==}
engines: {node: ^18.19.0 || >=20.6.0}
peerDependencies:
'@opentelemetry/api': '>=1.4.0 <1.10.0'
'@opentelemetry/sdk-metrics@2.2.0':
resolution: {integrity: sha512-G5KYP6+VJMZzpGipQw7Giif48h6SGQ2PFKEYCybeXJsOCB4fp8azqMAAzE5lnnHK3ZVwYQrgmFbsUJO/zOnwGw==}
engines: {node: ^18.19.0 || >=20.6.0}
peerDependencies:
'@opentelemetry/api': '>=1.9.0 <1.10.0'
'@opentelemetry/sdk-trace-base@2.2.0':
resolution: {integrity: sha512-xWQgL0Bmctsalg6PaXExmzdedSp3gyKV8mQBwK/j9VGdCDu2fmXIb2gAehBKbkXCpJ4HPkgv3QfoJWRT4dHWbw==}
engines: {node: ^18.19.0 || >=20.6.0}
@@ -2090,57 +2050,11 @@ packages:
webpack-plugin-serve:
optional: true
'@posthog/core@1.13.0':
resolution: {integrity: sha512-knjncrk7qRmssFRbGzBl1Tunt21GRpe0Wv+uVelyL0Rh7PdQUsgguulzXFTps8hA6wPwTU4kq85qnbAJ3eH6Wg==}
'@posthog/react@1.7.0':
resolution: {integrity: sha512-pM7GL7z/rKjiIwosbRiQA3buhLI6vUo+wg+T/ZrVZC7O5bVU07TfgNZTcuOj8E9dx7vDbfNrc1kjDN7PKMM8ug==}
peerDependencies:
'@types/react': '>=16.8.0'
posthog-js: '>=1.257.2'
react: '>=16.8.0'
peerDependenciesMeta:
'@types/react':
optional: true
'@posthog/types@1.334.1':
resolution: {integrity: sha512-ypFnwTO7qbV7icylLbujbamPdQXbJq0a61GUUBnJAeTbBw/qYPIss5IRYICcbCj0uunQrwD7/CGxVb5TOYKWgA==}
'@prisma/instrumentation@6.19.0':
resolution: {integrity: sha512-QcuYy25pkXM8BJ37wVFBO7Zh34nyRV1GOb2n3lPkkbRYfl4hWl3PTcImP41P0KrzVXfa/45p6eVCos27x3exIg==}
peerDependencies:
'@opentelemetry/api': ^1.8
'@protobufjs/aspromise@1.1.2':
resolution: {integrity: sha512-j+gKExEuLmKwvz3OgROXtrJ2UG2x8Ch2YZUxahh+s1F2HZ+wAceUNLkvy6zKCPVRkU++ZWQrdxsUeQXmcg4uoQ==}
'@protobufjs/base64@1.1.2':
resolution: {integrity: sha512-AZkcAA5vnN/v4PDqKyMR5lx7hZttPDgClv83E//FMNhR2TMcLUhfRUBHCmSl0oi9zMgDDqRUJkSxO3wm85+XLg==}
'@protobufjs/codegen@2.0.4':
resolution: {integrity: sha512-YyFaikqM5sH0ziFZCN3xDC7zeGaB/d0IUb9CATugHWbd1FRFwWwt4ld4OYMPWu5a3Xe01mGAULCdqhMlPl29Jg==}
'@protobufjs/eventemitter@1.1.0':
resolution: {integrity: sha512-j9ednRT81vYJ9OfVuXG6ERSTdEL1xVsNgqpkxMsbIabzSo3goCjDIveeGv5d03om39ML71RdmrGNjG5SReBP/Q==}
'@protobufjs/fetch@1.1.0':
resolution: {integrity: sha512-lljVXpqXebpsijW71PZaCYeIcE5on1w5DlQy5WH6GLbFryLUrBD4932W/E2BSpfRJWseIL4v/KPgBFxDOIdKpQ==}
'@protobufjs/float@1.0.2':
resolution: {integrity: sha512-Ddb+kVXlXst9d+R9PfTIxh1EdNkgoRe5tOX6t01f1lYWOvJnSPDBlG241QLzcyPdoNTsblLUdujGSE4RzrTZGQ==}
'@protobufjs/inquire@1.1.0':
resolution: {integrity: sha512-kdSefcPdruJiFMVSbn801t4vFK7KB/5gd2fYvrxhuJYg8ILrmn9SKSX2tZdV6V+ksulWqS7aXjBcRXl3wHoD9Q==}
'@protobufjs/path@1.1.2':
resolution: {integrity: sha512-6JOcJ5Tm08dOHAbdR3GrvP+yUUfkjG5ePsHYczMFLq3ZmMkAD98cDgcT2iA1lJ9NVwFd4tH/iSSoe44YWkltEA==}
'@protobufjs/pool@1.1.0':
resolution: {integrity: sha512-0kELaGSIDBKvcgS4zkjz1PeddatrjYcmMWOlAuAPwAeccUrPHdUqo/J6LiymHHEiJT5NrF1UVwxY14f+fy4WQw==}
'@protobufjs/utf8@1.1.0':
resolution: {integrity: sha512-Vvn3zZrhQZkkBE8LSuW3em98c0FwgO4nxzv6OdSxPKJIEKY2bGbHn+mhGIPerzI4twdxaP8/0+06HBpwf345Lw==}
'@radix-ui/number@1.1.1':
resolution: {integrity: sha512-MkKCwxlXTgz6CFoJx3pCwn07GKp36+aZyu/u2Ln2VrA5DcdyCZkASEDBTd8x5whTQQL5CiYf4prXKLcgQdv29g==}
@@ -3487,9 +3401,6 @@ packages:
'@types/tedious@4.0.14':
resolution: {integrity: sha512-KHPsfX/FoVbUGbyYvk1q9MMQHLPeRZhRJZdO45Q4YjvFkv4hMNghCWTvy7rdKessBsmtz4euWCWAB6/tVpI1Iw==}
'@types/trusted-types@2.0.7':
resolution: {integrity: sha512-ScaPdn1dQczgbl0QFTeTOmVHFULt394XJgOQNoyVhZ6r2vLnMLJfBPd53SB52T/3G36VI1/g2MZaX0cwDuXsfw==}
'@types/unist@2.0.11':
resolution: {integrity: sha512-CmBKiL6NNo/OqgmMn95Fk9Whlp2mtvIv+KNpQKN2F4SjvrEesubTRWGYSg+BnWZOnlCaSTU1sMpsBOzgbYhnsA==}
@@ -4367,9 +4278,6 @@ packages:
core-js-pure@3.47.0:
resolution: {integrity: sha512-BcxeDbzUrRnXGYIVAGFtcGQVNpFcUhVjr6W7F8XktvQW2iJP9e66GP6xdKotCRFlrxBvNIBrhwKteRXqMV86Nw==}
core-js@3.48.0:
resolution: {integrity: sha512-zpEHTy1fjTMZCKLHUZoVeylt9XrzaIN2rbPXEt0k+q7JE5CkCZdo6bNq55bn24a69CH7ErAVLKijxJja4fw+UQ==}
core-util-is@1.0.3:
resolution: {integrity: sha512-ZQBvi1DcpJ4GDqanjucZ2Hj3wEO5pZDS89BWbkcrvdxksJorwUDDZamX9ldFkp9aw2lmBDLgkObEA4DWNJ9FYQ==}
@@ -4661,9 +4569,6 @@ packages:
resolution: {integrity: sha512-GrwoxYN+uWlzO8uhUXRl0P+kHE4GtVPfYzVLcUxPL7KNdHKj66vvlhiweIHqYYXWlw+T8iLMp42Lm67ghw4WMQ==}
engines: {node: '>= 4'}
dompurify@3.3.1:
resolution: {integrity: sha512-qkdCKzLNtrgPFP1Vo+98FRzJnBRGe4ffyCea9IwHB1fyxPOeNTHpLKYGd4Uk9xvNoH0ZoOjwZxNptyMwqrId1Q==}
domutils@2.8.0:
resolution: {integrity: sha512-w96Cjofp72M5IIhpjgobBimYEfoPjx1Vx0BSX9P30WBdZW2WIKU0T1Bd0kz2eNZ9ikjKgHbEyKx8BB6H1L3h3A==}
@@ -5034,9 +4939,6 @@ packages:
picomatch:
optional: true
fflate@0.4.8:
resolution: {integrity: sha512-FJqqoDBR00Mdj9ppamLa/Y7vxm+PRmNWA67N846RvsoYVMKB4q3y/de5PA7gUmRMYK/8CMz2GDZQmCRN1wBcWA==}
file-entry-cache@6.0.1:
resolution: {integrity: sha512-7Gps/XWymbLk2QLYK4NzpMOrYjMhdIxXuIvy2QBsLE6ljuodKvdkWs/cpyJJ3CVIVpH0Oi1Hvg1ovbMzLdFBBg==}
engines: {node: ^10.12.0 || >=12.0.0}
@@ -5843,9 +5745,6 @@ packages:
resolution: {integrity: sha512-HgMmCqIJSAKqo68l0rS2AanEWfkxaZ5wNiEFb5ggm08lDs9Xl2KxBlX3PTcaD2chBM1gXAYf491/M2Rv8Jwayg==}
engines: {node: '>= 0.6.0'}
long@5.3.2:
resolution: {integrity: sha512-mNAgZ1GmyNhD7AuqnTG3/VQ26o760+ZYBPKjPvugO8+nLbYfX6TVpJPseBvopbdY+qpZ/lKUnmEc1LeZYS3QAA==}
longest-streak@3.1.0:
resolution: {integrity: sha512-9Ri+o0JYgehTaVBBDoMqIl8GXtbWg711O3srftcHhZ0dqnETqLaoIK0x17fUw9rFSlK/0NlsKe0Ahhyl5pXE2g==}
@@ -6635,12 +6534,6 @@ packages:
resolution: {integrity: sha512-9ZhXKM/rw350N1ovuWHbGxnGh/SNJ4cnxHiM0rxE4VN41wsg8P8zWn9hv/buK00RP4WvlOyr/RBDiptyxVbkZQ==}
engines: {node: '>=0.10.0'}
posthog-js@1.334.1:
resolution: {integrity: sha512-5cDzLICr2afnwX/cR9fwoLC0vN0Nb5gP5HiCigzHkgHdO+E3WsYefla3EFMQz7U4r01CBPZ+nZ9/srkzeACxtQ==}
preact@10.28.2:
resolution: {integrity: sha512-lbteaWGzGHdlIuiJ0l2Jq454m6kcpI1zNje6d8MlGAFlYvP2GO4ibnat7P74Esfz4sPTdM6UxtTwh/d3pwM9JA==}
prelude-ls@1.2.1:
resolution: {integrity: sha512-vkcDPrRZo1QZLbn5RLGPpg/WmIQ65qoWWhcGKf/b5eplkkarX0m9z8ppCat4mlOqUsWpyNuYgO3VRyrYHSzX5g==}
engines: {node: '>= 0.8.0'}
@@ -6729,10 +6622,6 @@ packages:
property-information@7.1.0:
resolution: {integrity: sha512-TwEZ+X+yCJmYfL7TPUOcvBZ4QfoT5YenQiJuX//0th53DE6w0xxLEtfK3iyryQFddXuvkIk51EEgrJQ0WJkOmQ==}
protobufjs@7.5.4:
resolution: {integrity: sha512-CvexbZtbov6jW2eXAvLukXjXUW1TzFaivC46BpWc/3BpcCysb5Vffu+B3XHMm8lVEuy2Mm4XGex8hBSg1yapPg==}
engines: {node: '>=12.0.0'}
proxy-from-env@1.1.0:
resolution: {integrity: sha512-D+zkORCbA9f1tdWRK0RaCR3GPv50cMxcrz4X8k5LTSUD1Dkw47mKJEZQNunItRTkWwgtaUSo1RVFRIG9ZXiFYg==}
@@ -6754,9 +6643,6 @@ packages:
resolution: {integrity: sha512-4EK3+xJl8Ts67nLYNwqw/dsFVnCf+qR7RgXSK9jEEm9unao3njwMDdmsdvoKBKHzxd7tCYz5e5M+SnMjdtXGQQ==}
engines: {node: '>=0.6'}
query-selector-shadow-dom@1.0.1:
resolution: {integrity: sha512-lT5yCqEBgfoMYpf3F2xQRK7zEr1rhIIZuceDK6+xRkJQ4NMbHTwXqk4NkwDwQMNqXgG9r9fyHnzwNVs6zV5KRw==}
querystring-es3@0.2.1:
resolution: {integrity: sha512-773xhDQnZBMFobEiztv8LIl70ch5MSF/jUQVlhwFyBILqq96anmoctVIYz+ZRp0qbCKATTn6ev02M3r7Ga5vqA==}
engines: {node: '>=0.4.x'}
@@ -7935,9 +7821,6 @@ packages:
web-namespaces@2.0.1:
resolution: {integrity: sha512-bKr1DkiNa2krS7qxNtdrtHAmzuYGFQLiQ13TsorsdT6ULTkPLKuu5+GsFpDlg6JFjUTwX2DyhMPG2be8uPrqsQ==}
web-vitals@5.1.0:
resolution: {integrity: sha512-ArI3kx5jI0atlTtmV0fWU3fjpLmq/nD3Zr1iFFlJLaqa5wLBkUSzINwBPySCX/8jRyjlmy1Volw1kz1g9XE4Jg==}
webidl-conversions@3.0.1:
resolution: {integrity: sha512-2JAn3z8AR6rjK8Sm8orRC0h/bcl/DqL7tRPdGZ4I1CjdF+EaMLmYxBHyXuKL849eucPFhvBoxMsflfOb8kxaeQ==}
@@ -9537,10 +9420,6 @@ snapshots:
'@open-draft/until@2.1.0': {}
'@opentelemetry/api-logs@0.208.0':
dependencies:
'@opentelemetry/api': 1.9.0
'@opentelemetry/api-logs@0.209.0':
dependencies:
'@opentelemetry/api': 1.9.0
@@ -9556,15 +9435,6 @@ snapshots:
'@opentelemetry/api': 1.9.0
'@opentelemetry/semantic-conventions': 1.38.0
'@opentelemetry/exporter-logs-otlp-http@0.208.0(@opentelemetry/api@1.9.0)':
dependencies:
'@opentelemetry/api': 1.9.0
'@opentelemetry/api-logs': 0.208.0
'@opentelemetry/core': 2.2.0(@opentelemetry/api@1.9.0)
'@opentelemetry/otlp-exporter-base': 0.208.0(@opentelemetry/api@1.9.0)
'@opentelemetry/otlp-transformer': 0.208.0(@opentelemetry/api@1.9.0)
'@opentelemetry/sdk-logs': 0.208.0(@opentelemetry/api@1.9.0)
'@opentelemetry/instrumentation-amqplib@0.55.0(@opentelemetry/api@1.9.0)':
dependencies:
'@opentelemetry/api': 1.9.0
@@ -9759,23 +9629,6 @@ snapshots:
transitivePeerDependencies:
- supports-color
'@opentelemetry/otlp-exporter-base@0.208.0(@opentelemetry/api@1.9.0)':
dependencies:
'@opentelemetry/api': 1.9.0
'@opentelemetry/core': 2.2.0(@opentelemetry/api@1.9.0)
'@opentelemetry/otlp-transformer': 0.208.0(@opentelemetry/api@1.9.0)
'@opentelemetry/otlp-transformer@0.208.0(@opentelemetry/api@1.9.0)':
dependencies:
'@opentelemetry/api': 1.9.0
'@opentelemetry/api-logs': 0.208.0
'@opentelemetry/core': 2.2.0(@opentelemetry/api@1.9.0)
'@opentelemetry/resources': 2.2.0(@opentelemetry/api@1.9.0)
'@opentelemetry/sdk-logs': 0.208.0(@opentelemetry/api@1.9.0)
'@opentelemetry/sdk-metrics': 2.2.0(@opentelemetry/api@1.9.0)
'@opentelemetry/sdk-trace-base': 2.2.0(@opentelemetry/api@1.9.0)
protobufjs: 7.5.4
'@opentelemetry/redis-common@0.38.2': {}
'@opentelemetry/resources@2.2.0(@opentelemetry/api@1.9.0)':
@@ -9784,19 +9637,6 @@ snapshots:
'@opentelemetry/core': 2.2.0(@opentelemetry/api@1.9.0)
'@opentelemetry/semantic-conventions': 1.38.0
'@opentelemetry/sdk-logs@0.208.0(@opentelemetry/api@1.9.0)':
dependencies:
'@opentelemetry/api': 1.9.0
'@opentelemetry/api-logs': 0.208.0
'@opentelemetry/core': 2.2.0(@opentelemetry/api@1.9.0)
'@opentelemetry/resources': 2.2.0(@opentelemetry/api@1.9.0)
'@opentelemetry/sdk-metrics@2.2.0(@opentelemetry/api@1.9.0)':
dependencies:
'@opentelemetry/api': 1.9.0
'@opentelemetry/core': 2.2.0(@opentelemetry/api@1.9.0)
'@opentelemetry/resources': 2.2.0(@opentelemetry/api@1.9.0)
'@opentelemetry/sdk-trace-base@2.2.0(@opentelemetry/api@1.9.0)':
dependencies:
'@opentelemetry/api': 1.9.0
@@ -9961,19 +9801,6 @@ snapshots:
type-fest: 4.41.0
webpack-hot-middleware: 2.26.1
'@posthog/core@1.13.0':
dependencies:
cross-spawn: 7.0.6
'@posthog/react@1.7.0(@types/react@18.3.17)(posthog-js@1.334.1)(react@18.3.1)':
dependencies:
posthog-js: 1.334.1
react: 18.3.1
optionalDependencies:
'@types/react': 18.3.17
'@posthog/types@1.334.1': {}
'@prisma/instrumentation@6.19.0(@opentelemetry/api@1.9.0)':
dependencies:
'@opentelemetry/api': 1.9.0
@@ -9981,29 +9808,6 @@ snapshots:
transitivePeerDependencies:
- supports-color
'@protobufjs/aspromise@1.1.2': {}
'@protobufjs/base64@1.1.2': {}
'@protobufjs/codegen@2.0.4': {}
'@protobufjs/eventemitter@1.1.0': {}
'@protobufjs/fetch@1.1.0':
dependencies:
'@protobufjs/aspromise': 1.1.2
'@protobufjs/inquire': 1.1.0
'@protobufjs/float@1.0.2': {}
'@protobufjs/inquire@1.1.0': {}
'@protobufjs/path@1.1.2': {}
'@protobufjs/pool@1.1.0': {}
'@protobufjs/utf8@1.1.0': {}
'@radix-ui/number@1.1.1': {}
'@radix-ui/primitive@1.1.3': {}
@@ -11622,9 +11426,6 @@ snapshots:
dependencies:
'@types/node': 24.10.0
'@types/trusted-types@2.0.7':
optional: true
'@types/unist@2.0.11': {}
'@types/unist@3.0.3': {}
@@ -12526,8 +12327,6 @@ snapshots:
core-js-pure@3.47.0: {}
core-js@3.48.0: {}
core-util-is@1.0.3: {}
cosmiconfig@7.1.0:
@@ -12837,10 +12636,6 @@ snapshots:
dependencies:
domelementtype: 2.3.0
dompurify@3.3.1:
optionalDependencies:
'@types/trusted-types': 2.0.7
domutils@2.8.0:
dependencies:
dom-serializer: 1.4.1
@@ -13410,8 +13205,6 @@ snapshots:
optionalDependencies:
picomatch: 4.0.3
fflate@0.4.8: {}
file-entry-cache@6.0.1:
dependencies:
flat-cache: 3.2.0
@@ -14299,8 +14092,6 @@ snapshots:
loglevel@1.9.2: {}
long@5.3.2: {}
longest-streak@3.1.0: {}
loose-envify@1.4.0:
@@ -15363,24 +15154,6 @@ snapshots:
dependencies:
xtend: 4.0.2
posthog-js@1.334.1:
dependencies:
'@opentelemetry/api': 1.9.0
'@opentelemetry/api-logs': 0.208.0
'@opentelemetry/exporter-logs-otlp-http': 0.208.0(@opentelemetry/api@1.9.0)
'@opentelemetry/resources': 2.2.0(@opentelemetry/api@1.9.0)
'@opentelemetry/sdk-logs': 0.208.0(@opentelemetry/api@1.9.0)
'@posthog/core': 1.13.0
'@posthog/types': 1.334.1
core-js: 3.48.0
dompurify: 3.3.1
fflate: 0.4.8
preact: 10.28.2
query-selector-shadow-dom: 1.0.1
web-vitals: 5.1.0
preact@10.28.2: {}
prelude-ls@1.2.1: {}
prettier-plugin-tailwindcss@0.7.1(prettier@3.6.2):
@@ -15414,21 +15187,6 @@ snapshots:
property-information@7.1.0: {}
protobufjs@7.5.4:
dependencies:
'@protobufjs/aspromise': 1.1.2
'@protobufjs/base64': 1.1.2
'@protobufjs/codegen': 2.0.4
'@protobufjs/eventemitter': 1.1.0
'@protobufjs/fetch': 1.1.0
'@protobufjs/float': 1.0.2
'@protobufjs/inquire': 1.1.0
'@protobufjs/path': 1.1.2
'@protobufjs/pool': 1.1.0
'@protobufjs/utf8': 1.1.0
'@types/node': 24.10.0
long: 5.3.2
proxy-from-env@1.1.0: {}
public-encrypt@4.0.3:
@@ -15450,8 +15208,6 @@ snapshots:
dependencies:
side-channel: 1.1.0
query-selector-shadow-dom@1.0.1: {}
querystring-es3@0.2.1: {}
queue-microtask@1.2.3: {}
@@ -16863,8 +16619,6 @@ snapshots:
web-namespaces@2.0.1: {}
web-vitals@5.1.0: {}
webidl-conversions@3.0.1: {}
webidl-conversions@8.0.1:

View File

@@ -1,62 +1,33 @@
"use client";
import { TooltipProvider } from "@/components/atoms/Tooltip/BaseTooltip";
import {
PostHogPageViewTracker,
PostHogUserTracker,
} from "@/components/monitor/PostHogUserTracker";
import { SentryUserTracker } from "@/components/monitor/SentryUserTracker";
import { BackendAPIProvider } from "@/lib/autogpt-server-api/context";
import { getQueryClient } from "@/lib/react-query/queryClient";
import CredentialsProvider from "@/providers/agent-credentials/credentials-provider";
import OnboardingProvider from "@/providers/onboarding/onboarding-provider";
import { LaunchDarklyProvider } from "@/services/feature-flags/feature-flag-provider";
import { PostHogProvider as PHProvider } from "@posthog/react";
import { QueryClientProvider } from "@tanstack/react-query";
import { ThemeProvider, ThemeProviderProps } from "next-themes";
import { NuqsAdapter } from "nuqs/adapters/next/app";
import posthog from "posthog-js";
import { Suspense, useEffect } from "react";
function PostHogProvider({ children }: { children: React.ReactNode }) {
useEffect(() => {
if (process.env.NEXT_PUBLIC_POSTHOG_KEY) {
posthog.init(process.env.NEXT_PUBLIC_POSTHOG_KEY, {
api_host: process.env.NEXT_PUBLIC_POSTHOG_HOST,
defaults: "2025-11-30",
capture_pageview: false,
capture_pageleave: true,
autocapture: true,
});
}
}, []);
return <PHProvider client={posthog}>{children}</PHProvider>;
}
export function Providers({ children, ...props }: ThemeProviderProps) {
const queryClient = getQueryClient();
return (
<QueryClientProvider client={queryClient}>
<NuqsAdapter>
<PostHogProvider>
<BackendAPIProvider>
<SentryUserTracker />
<PostHogUserTracker />
<Suspense fallback={null}>
<PostHogPageViewTracker />
</Suspense>
<CredentialsProvider>
<LaunchDarklyProvider>
<OnboardingProvider>
<ThemeProvider forcedTheme="light" {...props}>
<TooltipProvider>{children}</TooltipProvider>
</ThemeProvider>
</OnboardingProvider>
</LaunchDarklyProvider>
</CredentialsProvider>
</BackendAPIProvider>
</PostHogProvider>
<BackendAPIProvider>
<SentryUserTracker />
<CredentialsProvider>
<LaunchDarklyProvider>
<OnboardingProvider>
<ThemeProvider forcedTheme="light" {...props}>
<TooltipProvider>{children}</TooltipProvider>
</ThemeProvider>
</OnboardingProvider>
</LaunchDarklyProvider>
</CredentialsProvider>
</BackendAPIProvider>
</NuqsAdapter>
</QueryClientProvider>
);

View File

@@ -1,64 +0,0 @@
"use client";
import { useSupabase } from "@/lib/supabase/hooks/useSupabase";
import { usePathname, useSearchParams } from "next/navigation";
import posthog from "posthog-js";
import { useEffect, useRef } from "react";
/**
* PostHogUserTracker component identifies users in PostHog for analytics.
* This component should be placed high in the component tree to ensure user
* identification happens as soon as the user logs in.
*
* It automatically:
* - Identifies the user when they log in (linking anonymous to authenticated)
* - Resets PostHog when a user logs out
* - Updates identification when user data changes
*/
export function PostHogUserTracker() {
const { user, isUserLoading } = useSupabase();
const previousUserIdRef = useRef<string | null>(null);
useEffect(() => {
if (isUserLoading) return;
if (user) {
// Only identify if we haven't already identified this user
if (previousUserIdRef.current !== user.id) {
posthog.identify(user.id, {
email: user.email,
...(user.user_metadata?.name && { name: user.user_metadata.name }),
});
previousUserIdRef.current = user.id;
}
} else if (previousUserIdRef.current !== null) {
// User logged out - reset PostHog to generate new anonymous ID
posthog.reset();
previousUserIdRef.current = null;
}
}, [user, isUserLoading]);
return null;
}
/**
* PostHogPageViewTracker captures page views on route changes in Next.js App Router.
* The default PostHog capture_pageview only works for initial page loads.
* This component ensures soft navigations (client-side route changes) are also tracked.
*/
export function PostHogPageViewTracker() {
const pathname = usePathname();
const searchParams = useSearchParams();
useEffect(() => {
if (pathname) {
let url = window.origin + pathname;
if (searchParams && searchParams.toString()) {
url = url + `?${searchParams.toString()}`;
}
posthog.capture("$pageview", { $current_url: url });
}
}, [pathname, searchParams]);
return null;
}