ros/autocoder
1
0
Fork 0
mirror of https://github.com/leonvanzyl/autocoder.git synced 2026-01-30 14:22:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: address CodeRabbitAI review comments for conversation history

Browse Source 
- Fix duplicate onConversationCreated callbacks by tracking activeConversationId
- Fix history loss when switching conversations with Map-based deduplication
- Disable input while conversation is loading to prevent message routing issues
- Gate WebSocket debug logs behind DEV flag (import.meta.env.DEV)
- Downgrade server logging from info to debug level for reduced noise
- Fix .gitignore prefixes for playwright paths (ui/playwright-report/, ui/test-results/)
- Remove debug console.log from ConversationHistory.tsx
- Add staleTime (30s) to single conversation query for better caching
- Increase history message cap from 20 to 35 for better context
- Replace fixed timeouts with condition-based waits in e2e tests
This commit is contained in:
liri
2026-01-16 22:43:15 +00:00
parent 7d761cb8d0
commit c229e2b39b
8 changed files with 61 additions and 53 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
server/routers/assistant_chat.py
View File

@@ -260,7 +260,7 @@ async def assistant_chat_websocket(websocket: WebSocket, project_name: str):
data = await websocket.receive_text()
message = json.loads(data)
msg_type = message.get("type")
logger.info(f"Assistant received message type: {msg_type}")
logger.debug(f"Assistant received message type: {msg_type}")
if msg_type == "ping":
await websocket.send_json({"type": "pong"})
@@ -269,23 +269,24 @@ async def assistant_chat_websocket(websocket: WebSocket, project_name: str):
elif msg_type == "start":
# Get optional conversation_id to resume
conversation_id = message.get("conversation_id")
logger.info(f"Processing start message with conversation_id={conversation_id}")
logger.debug(f"Processing start message with conversation_id={conversation_id}")
try:
# Create a new session
logger.info(f"Creating session for {project_name}")
logger.debug(f"Creating session for {project_name}")
session = await create_session(
project_name,
project_dir,
conversation_id=conversation_id,
)
logger.info(f"Session created, starting...")
logger.debug("Session created, starting...")
# Stream the initial greeting
async for chunk in session.start():
logger.info(f"Sending chunk: {chunk.get('type')}")
if logger.isEnabledFor(logging.DEBUG):
logger.debug(f"Sending chunk: {chunk.get('type')}")
await websocket.send_json(chunk)
logger.info("Session start complete")
logger.debug("Session start complete")
except Exception as e:
logger.exception(f"Error starting assistant session for {project_name}")
await websocket.send_json({

2
server/services/assistant_chat_session.py
View File

@@ -345,6 +345,8 @@ class AssistantChatSession:
history = get_messages(self.project_dir, self.conversation_id)
# Exclude the message we just added (last one)
history = history[:-1] if history else []
# Cap history to last 35 messages to prevent context overload
history = history[-35:] if len(history) > 35 else history
if history:
# Format history as context for Claude
history_lines = ["[Previous conversation history for context:]"]