mirror of
https://github.com/leonvanzyl/autocoder.git
synced 2026-03-17 02:43:09 +00:00
fix: handle rate_limit_event crash in chat sessions
The Claude CLI sends `rate_limit_event` messages that the SDK's `parse_message()` doesn't recognize, raising `MessageParseError` and crashing all three chat session types (spec, assistant, expand). Changes: - Bump claude-agent-sdk minimum from 0.1.0 to 0.1.39 - Add `check_rate_limit_error()` helper in chat_constants.py that detects rate limits from both MessageParseError data payloads and error message text patterns - Wrap `receive_response()` loops in all three `_query_claude()` methods with retry-on-rate-limit logic (up to 3 retries with backoff) - Gracefully log and skip non-rate-limit MessageParseError instead of crashing the session - Add `rate_limited` message type to frontend TypeScript types and handle it in useSpecChat, useAssistantChat, useExpandChat hooks to show "Rate limited. Retrying in Xs..." system messages Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -13,5 +13,6 @@
|
|||||||
"runtimeArgs": ["/c", "cd ui && npx vite"],
|
"runtimeArgs": ["/c", "cd ui && npx vite"],
|
||||||
"port": 5173
|
"port": 5173
|
||||||
}
|
}
|
||||||
]
|
],
|
||||||
|
"autoVerify": true
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -1,6 +1,6 @@
|
|||||||
# Production runtime dependencies only
|
# Production runtime dependencies only
|
||||||
# For development, use requirements.txt (includes ruff, mypy, pytest)
|
# For development, use requirements.txt (includes ruff, mypy, pytest)
|
||||||
claude-agent-sdk>=0.1.0,<0.2.0
|
claude-agent-sdk>=0.1.39,<0.2.0
|
||||||
python-dotenv>=1.0.0
|
python-dotenv>=1.0.0
|
||||||
sqlalchemy>=2.0.0
|
sqlalchemy>=2.0.0
|
||||||
fastapi>=0.115.0
|
fastapi>=0.115.0
|
||||||
|
|||||||
@@ -1,4 +1,4 @@
|
|||||||
claude-agent-sdk>=0.1.0,<0.2.0
|
claude-agent-sdk>=0.1.39,<0.2.0
|
||||||
python-dotenv>=1.0.0
|
python-dotenv>=1.0.0
|
||||||
sqlalchemy>=2.0.0
|
sqlalchemy>=2.0.0
|
||||||
fastapi>=0.115.0
|
fastapi>=0.115.0
|
||||||
|
|||||||
@@ -7,6 +7,7 @@ The assistant can answer questions about the codebase and features
|
|||||||
but cannot modify any files.
|
but cannot modify any files.
|
||||||
"""
|
"""
|
||||||
|
|
||||||
|
import asyncio
|
||||||
import json
|
import json
|
||||||
import logging
|
import logging
|
||||||
import os
|
import os
|
||||||
@@ -25,7 +26,12 @@ from .assistant_database import (
|
|||||||
create_conversation,
|
create_conversation,
|
||||||
get_messages,
|
get_messages,
|
||||||
)
|
)
|
||||||
from .chat_constants import ROOT_DIR
|
from .chat_constants import (
|
||||||
|
MAX_CHAT_RATE_LIMIT_RETRIES,
|
||||||
|
ROOT_DIR,
|
||||||
|
calculate_rate_limit_backoff,
|
||||||
|
check_rate_limit_error,
|
||||||
|
)
|
||||||
|
|
||||||
# Load environment variables from .env file if present
|
# Load environment variables from .env file if present
|
||||||
load_dotenv()
|
load_dotenv()
|
||||||
@@ -393,39 +399,66 @@ class AssistantChatSession:
|
|||||||
|
|
||||||
full_response = ""
|
full_response = ""
|
||||||
|
|
||||||
# Stream the response
|
# Stream the response (with rate-limit retry)
|
||||||
async for msg in self.client.receive_response():
|
for _attempt in range(MAX_CHAT_RATE_LIMIT_RETRIES + 1):
|
||||||
msg_type = type(msg).__name__
|
try:
|
||||||
|
async for msg in self.client.receive_response():
|
||||||
|
msg_type = type(msg).__name__
|
||||||
|
|
||||||
if msg_type == "AssistantMessage" and hasattr(msg, "content"):
|
if msg_type == "AssistantMessage" and hasattr(msg, "content"):
|
||||||
for block in msg.content:
|
for block in msg.content:
|
||||||
block_type = type(block).__name__
|
block_type = type(block).__name__
|
||||||
|
|
||||||
if block_type == "TextBlock" and hasattr(block, "text"):
|
if block_type == "TextBlock" and hasattr(block, "text"):
|
||||||
text = block.text
|
text = block.text
|
||||||
if text:
|
if text:
|
||||||
full_response += text
|
full_response += text
|
||||||
yield {"type": "text", "content": text}
|
yield {"type": "text", "content": text}
|
||||||
|
|
||||||
elif block_type == "ToolUseBlock" and hasattr(block, "name"):
|
elif block_type == "ToolUseBlock" and hasattr(block, "name"):
|
||||||
tool_name = block.name
|
tool_name = block.name
|
||||||
tool_input = getattr(block, "input", {})
|
tool_input = getattr(block, "input", {})
|
||||||
|
|
||||||
|
# Intercept ask_user tool calls -> yield as question message
|
||||||
|
if tool_name == "mcp__features__ask_user":
|
||||||
|
questions = tool_input.get("questions", [])
|
||||||
|
if questions:
|
||||||
|
yield {
|
||||||
|
"type": "question",
|
||||||
|
"questions": questions,
|
||||||
|
}
|
||||||
|
continue
|
||||||
|
|
||||||
# Intercept ask_user tool calls -> yield as question message
|
|
||||||
if tool_name == "mcp__features__ask_user":
|
|
||||||
questions = tool_input.get("questions", [])
|
|
||||||
if questions:
|
|
||||||
yield {
|
yield {
|
||||||
"type": "question",
|
"type": "tool_call",
|
||||||
"questions": questions,
|
"tool": tool_name,
|
||||||
|
"input": tool_input,
|
||||||
}
|
}
|
||||||
continue
|
# Completed successfully — break out of retry loop
|
||||||
|
break
|
||||||
yield {
|
except Exception as exc:
|
||||||
"type": "tool_call",
|
is_rate_limit, retry_secs = check_rate_limit_error(exc)
|
||||||
"tool": tool_name,
|
if is_rate_limit and _attempt < MAX_CHAT_RATE_LIMIT_RETRIES:
|
||||||
"input": tool_input,
|
delay = retry_secs if retry_secs else calculate_rate_limit_backoff(_attempt)
|
||||||
}
|
logger.warning(f"Rate limited (attempt {_attempt + 1}/{MAX_CHAT_RATE_LIMIT_RETRIES}), retrying in {delay}s")
|
||||||
|
yield {
|
||||||
|
"type": "rate_limited",
|
||||||
|
"retry_in": delay,
|
||||||
|
"attempt": _attempt + 1,
|
||||||
|
"max_attempts": MAX_CHAT_RATE_LIMIT_RETRIES,
|
||||||
|
}
|
||||||
|
await asyncio.sleep(delay)
|
||||||
|
await self.client.query(message)
|
||||||
|
continue
|
||||||
|
if is_rate_limit:
|
||||||
|
logger.error("Rate limit retries exhausted for assistant chat")
|
||||||
|
yield {"type": "error", "content": "Rate limited. Please try again later."}
|
||||||
|
return
|
||||||
|
# Non-rate-limit MessageParseError: log and break (don't crash)
|
||||||
|
if type(exc).__name__ == "MessageParseError":
|
||||||
|
logger.warning(f"Ignoring unrecognized message from Claude CLI: {exc}")
|
||||||
|
break
|
||||||
|
raise
|
||||||
|
|
||||||
# Store the complete response in the database
|
# Store the complete response in the database
|
||||||
if full_response and self.conversation_id:
|
if full_response and self.conversation_id:
|
||||||
|
|||||||
@@ -9,6 +9,7 @@ project root and is re-exported here for convenience so that existing
|
|||||||
imports (``from .chat_constants import API_ENV_VARS``) continue to work.
|
imports (``from .chat_constants import API_ENV_VARS``) continue to work.
|
||||||
"""
|
"""
|
||||||
|
|
||||||
|
import logging
|
||||||
import sys
|
import sys
|
||||||
from pathlib import Path
|
from pathlib import Path
|
||||||
from typing import AsyncGenerator
|
from typing import AsyncGenerator
|
||||||
@@ -32,6 +33,45 @@ if _root_str not in sys.path:
|
|||||||
# imports continue to work unchanged.
|
# imports continue to work unchanged.
|
||||||
# -------------------------------------------------------------------
|
# -------------------------------------------------------------------
|
||||||
from env_constants import API_ENV_VARS # noqa: E402, F401
|
from env_constants import API_ENV_VARS # noqa: E402, F401
|
||||||
|
from rate_limit_utils import calculate_rate_limit_backoff, is_rate_limit_error, parse_retry_after # noqa: E402, F401
|
||||||
|
|
||||||
|
logger = logging.getLogger(__name__)
|
||||||
|
|
||||||
|
# -------------------------------------------------------------------
|
||||||
|
# Rate-limit handling for chat sessions
|
||||||
|
# -------------------------------------------------------------------
|
||||||
|
MAX_CHAT_RATE_LIMIT_RETRIES = 3
|
||||||
|
|
||||||
|
|
||||||
|
def check_rate_limit_error(exc: Exception) -> tuple[bool, int | None]:
|
||||||
|
"""Inspect an exception and determine if it represents a rate-limit.
|
||||||
|
|
||||||
|
Returns ``(is_rate_limit, retry_seconds)``. ``retry_seconds`` is the
|
||||||
|
parsed Retry-After value when available, otherwise ``None`` (caller
|
||||||
|
should use exponential backoff).
|
||||||
|
|
||||||
|
Handles:
|
||||||
|
- ``MessageParseError`` whose raw *data* dict has
|
||||||
|
``type == "rate_limit_event"`` (Claude CLI sends this).
|
||||||
|
- Any exception whose string representation matches known rate-limit
|
||||||
|
patterns (via ``rate_limit_utils.is_rate_limit_error``).
|
||||||
|
"""
|
||||||
|
exc_str = str(exc)
|
||||||
|
|
||||||
|
# Check for MessageParseError with a rate_limit_event payload
|
||||||
|
cls_name = type(exc).__name__
|
||||||
|
if cls_name == "MessageParseError":
|
||||||
|
raw_data = getattr(exc, "data", None)
|
||||||
|
if isinstance(raw_data, dict) and raw_data.get("type") == "rate_limit_event":
|
||||||
|
retry = parse_retry_after(str(raw_data)) if raw_data else None
|
||||||
|
return True, retry
|
||||||
|
|
||||||
|
# Fallback: match error text against known rate-limit patterns
|
||||||
|
if is_rate_limit_error(exc_str):
|
||||||
|
retry = parse_retry_after(exc_str)
|
||||||
|
return True, retry
|
||||||
|
|
||||||
|
return False, None
|
||||||
|
|
||||||
|
|
||||||
async def make_multimodal_message(content_blocks: list[dict]) -> AsyncGenerator[dict, None]:
|
async def make_multimodal_message(content_blocks: list[dict]) -> AsyncGenerator[dict, None]:
|
||||||
|
|||||||
@@ -22,7 +22,13 @@ from claude_agent_sdk import ClaudeAgentOptions, ClaudeSDKClient
|
|||||||
from dotenv import load_dotenv
|
from dotenv import load_dotenv
|
||||||
|
|
||||||
from ..schemas import ImageAttachment
|
from ..schemas import ImageAttachment
|
||||||
from .chat_constants import ROOT_DIR, make_multimodal_message
|
from .chat_constants import (
|
||||||
|
MAX_CHAT_RATE_LIMIT_RETRIES,
|
||||||
|
ROOT_DIR,
|
||||||
|
calculate_rate_limit_backoff,
|
||||||
|
check_rate_limit_error,
|
||||||
|
make_multimodal_message,
|
||||||
|
)
|
||||||
|
|
||||||
# Load environment variables from .env file if present
|
# Load environment variables from .env file if present
|
||||||
load_dotenv()
|
load_dotenv()
|
||||||
@@ -298,24 +304,67 @@ class ExpandChatSession:
|
|||||||
else:
|
else:
|
||||||
await self.client.query(message)
|
await self.client.query(message)
|
||||||
|
|
||||||
# Stream the response
|
# Stream the response (with rate-limit retry)
|
||||||
async for msg in self.client.receive_response():
|
for _attempt in range(MAX_CHAT_RATE_LIMIT_RETRIES + 1):
|
||||||
msg_type = type(msg).__name__
|
try:
|
||||||
|
async for msg in self.client.receive_response():
|
||||||
|
msg_type = type(msg).__name__
|
||||||
|
|
||||||
if msg_type == "AssistantMessage" and hasattr(msg, "content"):
|
if msg_type == "AssistantMessage" and hasattr(msg, "content"):
|
||||||
for block in msg.content:
|
for block in msg.content:
|
||||||
block_type = type(block).__name__
|
block_type = type(block).__name__
|
||||||
|
|
||||||
if block_type == "TextBlock" and hasattr(block, "text"):
|
if block_type == "TextBlock" and hasattr(block, "text"):
|
||||||
text = block.text
|
text = block.text
|
||||||
if text:
|
if text:
|
||||||
yield {"type": "text", "content": text}
|
yield {"type": "text", "content": text}
|
||||||
|
|
||||||
self.messages.append({
|
self.messages.append({
|
||||||
"role": "assistant",
|
"role": "assistant",
|
||||||
"content": text,
|
"content": text,
|
||||||
"timestamp": datetime.now().isoformat()
|
"timestamp": datetime.now().isoformat()
|
||||||
|
})
|
||||||
|
# Completed successfully — break out of retry loop
|
||||||
|
break
|
||||||
|
except Exception as exc:
|
||||||
|
is_rate_limit, retry_secs = check_rate_limit_error(exc)
|
||||||
|
if is_rate_limit and _attempt < MAX_CHAT_RATE_LIMIT_RETRIES:
|
||||||
|
delay = retry_secs if retry_secs else calculate_rate_limit_backoff(_attempt)
|
||||||
|
logger.warning(f"Rate limited (attempt {_attempt + 1}/{MAX_CHAT_RATE_LIMIT_RETRIES}), retrying in {delay}s")
|
||||||
|
yield {
|
||||||
|
"type": "rate_limited",
|
||||||
|
"retry_in": delay,
|
||||||
|
"attempt": _attempt + 1,
|
||||||
|
"max_attempts": MAX_CHAT_RATE_LIMIT_RETRIES,
|
||||||
|
}
|
||||||
|
await asyncio.sleep(delay)
|
||||||
|
# Re-send the query before retrying receive_response
|
||||||
|
if attachments and len(attachments) > 0:
|
||||||
|
content_blocks_retry: list[dict[str, Any]] = []
|
||||||
|
if message:
|
||||||
|
content_blocks_retry.append({"type": "text", "text": message})
|
||||||
|
for att in attachments:
|
||||||
|
content_blocks_retry.append({
|
||||||
|
"type": "image",
|
||||||
|
"source": {
|
||||||
|
"type": "base64",
|
||||||
|
"media_type": att.mimeType,
|
||||||
|
"data": att.base64Data,
|
||||||
|
}
|
||||||
})
|
})
|
||||||
|
await self.client.query(make_multimodal_message(content_blocks_retry))
|
||||||
|
else:
|
||||||
|
await self.client.query(message)
|
||||||
|
continue
|
||||||
|
if is_rate_limit:
|
||||||
|
logger.error("Rate limit retries exhausted for expand chat")
|
||||||
|
yield {"type": "error", "content": "Rate limited. Please try again later."}
|
||||||
|
return
|
||||||
|
# Non-rate-limit MessageParseError: log and break (don't crash)
|
||||||
|
if type(exc).__name__ == "MessageParseError":
|
||||||
|
logger.warning(f"Ignoring unrecognized message from Claude CLI: {exc}")
|
||||||
|
break
|
||||||
|
raise
|
||||||
|
|
||||||
def get_features_created(self) -> int:
|
def get_features_created(self) -> int:
|
||||||
"""Get the total number of features created in this session."""
|
"""Get the total number of features created in this session."""
|
||||||
|
|||||||
@@ -6,6 +6,7 @@ Manages interactive spec creation conversation with Claude.
|
|||||||
Uses the create-spec.md skill to guide users through app spec creation.
|
Uses the create-spec.md skill to guide users through app spec creation.
|
||||||
"""
|
"""
|
||||||
|
|
||||||
|
import asyncio
|
||||||
import json
|
import json
|
||||||
import logging
|
import logging
|
||||||
import os
|
import os
|
||||||
@@ -19,7 +20,13 @@ from claude_agent_sdk import ClaudeAgentOptions, ClaudeSDKClient
|
|||||||
from dotenv import load_dotenv
|
from dotenv import load_dotenv
|
||||||
|
|
||||||
from ..schemas import ImageAttachment
|
from ..schemas import ImageAttachment
|
||||||
from .chat_constants import ROOT_DIR, make_multimodal_message
|
from .chat_constants import (
|
||||||
|
MAX_CHAT_RATE_LIMIT_RETRIES,
|
||||||
|
ROOT_DIR,
|
||||||
|
calculate_rate_limit_backoff,
|
||||||
|
check_rate_limit_error,
|
||||||
|
make_multimodal_message,
|
||||||
|
)
|
||||||
|
|
||||||
# Load environment variables from .env file if present
|
# Load environment variables from .env file if present
|
||||||
load_dotenv()
|
load_dotenv()
|
||||||
@@ -304,117 +311,145 @@ class SpecChatSession:
|
|||||||
# Store paths for the completion message
|
# Store paths for the completion message
|
||||||
spec_path = None
|
spec_path = None
|
||||||
|
|
||||||
# Stream the response using receive_response
|
# Stream the response using receive_response (with rate-limit retry)
|
||||||
async for msg in self.client.receive_response():
|
for _attempt in range(MAX_CHAT_RATE_LIMIT_RETRIES + 1):
|
||||||
msg_type = type(msg).__name__
|
try:
|
||||||
|
async for msg in self.client.receive_response():
|
||||||
|
msg_type = type(msg).__name__
|
||||||
|
|
||||||
if msg_type == "AssistantMessage" and hasattr(msg, "content"):
|
if msg_type == "AssistantMessage" and hasattr(msg, "content"):
|
||||||
# Process content blocks in the assistant message
|
# Process content blocks in the assistant message
|
||||||
for block in msg.content:
|
for block in msg.content:
|
||||||
block_type = type(block).__name__
|
block_type = type(block).__name__
|
||||||
|
|
||||||
if block_type == "TextBlock" and hasattr(block, "text"):
|
if block_type == "TextBlock" and hasattr(block, "text"):
|
||||||
# Accumulate text and yield it
|
# Accumulate text and yield it
|
||||||
text = block.text
|
text = block.text
|
||||||
if text:
|
if text:
|
||||||
current_text += text
|
current_text += text
|
||||||
yield {"type": "text", "content": text}
|
yield {"type": "text", "content": text}
|
||||||
|
|
||||||
# Store in message history
|
# Store in message history
|
||||||
self.messages.append({
|
self.messages.append({
|
||||||
"role": "assistant",
|
"role": "assistant",
|
||||||
"content": text,
|
"content": text,
|
||||||
"timestamp": datetime.now().isoformat()
|
"timestamp": datetime.now().isoformat()
|
||||||
})
|
})
|
||||||
|
|
||||||
elif block_type == "ToolUseBlock" and hasattr(block, "name"):
|
elif block_type == "ToolUseBlock" and hasattr(block, "name"):
|
||||||
tool_name = block.name
|
tool_name = block.name
|
||||||
tool_input = getattr(block, "input", {})
|
tool_input = getattr(block, "input", {})
|
||||||
tool_id = getattr(block, "id", "")
|
tool_id = getattr(block, "id", "")
|
||||||
|
|
||||||
if tool_name in ("Write", "Edit"):
|
if tool_name in ("Write", "Edit"):
|
||||||
# File being written or edited - track for verification
|
# File being written or edited - track for verification
|
||||||
file_path = tool_input.get("file_path", "")
|
file_path = tool_input.get("file_path", "")
|
||||||
|
|
||||||
# Track app_spec.txt
|
# Track app_spec.txt
|
||||||
if "app_spec.txt" in str(file_path):
|
if "app_spec.txt" in str(file_path):
|
||||||
pending_writes["app_spec"] = {
|
pending_writes["app_spec"] = {
|
||||||
"tool_id": tool_id,
|
"tool_id": tool_id,
|
||||||
"path": file_path
|
"path": file_path
|
||||||
}
|
}
|
||||||
logger.info(f"{tool_name} tool called for app_spec.txt: {file_path}")
|
logger.info(f"{tool_name} tool called for app_spec.txt: {file_path}")
|
||||||
|
|
||||||
# Track initializer_prompt.md
|
# Track initializer_prompt.md
|
||||||
elif "initializer_prompt.md" in str(file_path):
|
elif "initializer_prompt.md" in str(file_path):
|
||||||
pending_writes["initializer"] = {
|
pending_writes["initializer"] = {
|
||||||
"tool_id": tool_id,
|
"tool_id": tool_id,
|
||||||
"path": file_path
|
"path": file_path
|
||||||
}
|
}
|
||||||
logger.info(f"{tool_name} tool called for initializer_prompt.md: {file_path}")
|
logger.info(f"{tool_name} tool called for initializer_prompt.md: {file_path}")
|
||||||
|
|
||||||
elif msg_type == "UserMessage" and hasattr(msg, "content"):
|
elif msg_type == "UserMessage" and hasattr(msg, "content"):
|
||||||
# Tool results - check for write confirmations and errors
|
# Tool results - check for write confirmations and errors
|
||||||
for block in msg.content:
|
for block in msg.content:
|
||||||
block_type = type(block).__name__
|
block_type = type(block).__name__
|
||||||
if block_type == "ToolResultBlock":
|
if block_type == "ToolResultBlock":
|
||||||
is_error = getattr(block, "is_error", False)
|
is_error = getattr(block, "is_error", False)
|
||||||
tool_use_id = getattr(block, "tool_use_id", "")
|
tool_use_id = getattr(block, "tool_use_id", "")
|
||||||
|
|
||||||
if is_error:
|
if is_error:
|
||||||
content = getattr(block, "content", "Unknown error")
|
content = getattr(block, "content", "Unknown error")
|
||||||
logger.warning(f"Tool error: {content}")
|
logger.warning(f"Tool error: {content}")
|
||||||
# Clear any pending writes that failed
|
# Clear any pending writes that failed
|
||||||
for key in pending_writes:
|
for key in pending_writes:
|
||||||
pending_write = pending_writes[key]
|
pending_write = pending_writes[key]
|
||||||
if pending_write is not None and tool_use_id == pending_write.get("tool_id"):
|
if pending_write is not None and tool_use_id == pending_write.get("tool_id"):
|
||||||
logger.error(f"{key} write failed: {content}")
|
logger.error(f"{key} write failed: {content}")
|
||||||
pending_writes[key] = None
|
pending_writes[key] = None
|
||||||
else:
|
|
||||||
# Tool succeeded - check which file was written
|
|
||||||
|
|
||||||
# Check app_spec.txt
|
|
||||||
if pending_writes["app_spec"] and tool_use_id == pending_writes["app_spec"].get("tool_id"):
|
|
||||||
file_path = pending_writes["app_spec"]["path"]
|
|
||||||
full_path = Path(file_path) if Path(file_path).is_absolute() else self.project_dir / file_path
|
|
||||||
if full_path.exists():
|
|
||||||
logger.info(f"app_spec.txt verified at: {full_path}")
|
|
||||||
files_written["app_spec"] = True
|
|
||||||
spec_path = file_path
|
|
||||||
|
|
||||||
# Notify about file write (but NOT completion yet)
|
|
||||||
yield {
|
|
||||||
"type": "file_written",
|
|
||||||
"path": str(file_path)
|
|
||||||
}
|
|
||||||
else:
|
else:
|
||||||
logger.error(f"app_spec.txt not found after write: {full_path}")
|
# Tool succeeded - check which file was written
|
||||||
pending_writes["app_spec"] = None
|
|
||||||
|
|
||||||
# Check initializer_prompt.md
|
# Check app_spec.txt
|
||||||
if pending_writes["initializer"] and tool_use_id == pending_writes["initializer"].get("tool_id"):
|
if pending_writes["app_spec"] and tool_use_id == pending_writes["app_spec"].get("tool_id"):
|
||||||
file_path = pending_writes["initializer"]["path"]
|
file_path = pending_writes["app_spec"]["path"]
|
||||||
full_path = Path(file_path) if Path(file_path).is_absolute() else self.project_dir / file_path
|
full_path = Path(file_path) if Path(file_path).is_absolute() else self.project_dir / file_path
|
||||||
if full_path.exists():
|
if full_path.exists():
|
||||||
logger.info(f"initializer_prompt.md verified at: {full_path}")
|
logger.info(f"app_spec.txt verified at: {full_path}")
|
||||||
files_written["initializer"] = True
|
files_written["app_spec"] = True
|
||||||
|
spec_path = file_path
|
||||||
|
|
||||||
# Notify about file write
|
# Notify about file write (but NOT completion yet)
|
||||||
yield {
|
yield {
|
||||||
"type": "file_written",
|
"type": "file_written",
|
||||||
"path": str(file_path)
|
"path": str(file_path)
|
||||||
}
|
}
|
||||||
else:
|
else:
|
||||||
logger.error(f"initializer_prompt.md not found after write: {full_path}")
|
logger.error(f"app_spec.txt not found after write: {full_path}")
|
||||||
pending_writes["initializer"] = None
|
pending_writes["app_spec"] = None
|
||||||
|
|
||||||
# Check if BOTH files are now written - only then signal completion
|
# Check initializer_prompt.md
|
||||||
if files_written["app_spec"] and files_written["initializer"]:
|
if pending_writes["initializer"] and tool_use_id == pending_writes["initializer"].get("tool_id"):
|
||||||
logger.info("Both app_spec.txt and initializer_prompt.md verified - signaling completion")
|
file_path = pending_writes["initializer"]["path"]
|
||||||
self.complete = True
|
full_path = Path(file_path) if Path(file_path).is_absolute() else self.project_dir / file_path
|
||||||
yield {
|
if full_path.exists():
|
||||||
"type": "spec_complete",
|
logger.info(f"initializer_prompt.md verified at: {full_path}")
|
||||||
"path": str(spec_path)
|
files_written["initializer"] = True
|
||||||
}
|
|
||||||
|
# Notify about file write
|
||||||
|
yield {
|
||||||
|
"type": "file_written",
|
||||||
|
"path": str(file_path)
|
||||||
|
}
|
||||||
|
else:
|
||||||
|
logger.error(f"initializer_prompt.md not found after write: {full_path}")
|
||||||
|
pending_writes["initializer"] = None
|
||||||
|
|
||||||
|
# Check if BOTH files are now written - only then signal completion
|
||||||
|
if files_written["app_spec"] and files_written["initializer"]:
|
||||||
|
logger.info("Both app_spec.txt and initializer_prompt.md verified - signaling completion")
|
||||||
|
self.complete = True
|
||||||
|
yield {
|
||||||
|
"type": "spec_complete",
|
||||||
|
"path": str(spec_path)
|
||||||
|
}
|
||||||
|
# Completed successfully — break out of retry loop
|
||||||
|
break
|
||||||
|
except Exception as exc:
|
||||||
|
is_rate_limit, retry_secs = check_rate_limit_error(exc)
|
||||||
|
if is_rate_limit and _attempt < MAX_CHAT_RATE_LIMIT_RETRIES:
|
||||||
|
delay = retry_secs if retry_secs else calculate_rate_limit_backoff(_attempt)
|
||||||
|
logger.warning(f"Rate limited (attempt {_attempt + 1}/{MAX_CHAT_RATE_LIMIT_RETRIES}), retrying in {delay}s")
|
||||||
|
yield {
|
||||||
|
"type": "rate_limited",
|
||||||
|
"retry_in": delay,
|
||||||
|
"attempt": _attempt + 1,
|
||||||
|
"max_attempts": MAX_CHAT_RATE_LIMIT_RETRIES,
|
||||||
|
}
|
||||||
|
await asyncio.sleep(delay)
|
||||||
|
# Re-send the query before retrying receive_response
|
||||||
|
await self.client.query(message)
|
||||||
|
continue
|
||||||
|
if is_rate_limit:
|
||||||
|
logger.error("Rate limit retries exhausted for spec chat")
|
||||||
|
yield {"type": "error", "content": "Rate limited. Please try again later."}
|
||||||
|
return
|
||||||
|
# Non-rate-limit MessageParseError: log and break (don't crash)
|
||||||
|
if type(exc).__name__ == "MessageParseError":
|
||||||
|
logger.warning(f"Ignoring unrecognized message from Claude CLI: {exc}")
|
||||||
|
break
|
||||||
|
raise
|
||||||
|
|
||||||
def is_complete(self) -> bool:
|
def is_complete(self) -> bool:
|
||||||
"""Check if spec creation is complete."""
|
"""Check if spec creation is complete."""
|
||||||
|
|||||||
@@ -269,6 +269,20 @@ export function useAssistantChat({
|
|||||||
break;
|
break;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
case "rate_limited": {
|
||||||
|
// Show rate limit info as system message
|
||||||
|
setMessages((prev) => [
|
||||||
|
...prev,
|
||||||
|
{
|
||||||
|
id: generateId(),
|
||||||
|
role: "system",
|
||||||
|
content: `Rate limited. Retrying in ${data.retry_in}s... (attempt ${data.attempt}/${data.max_attempts})`,
|
||||||
|
timestamp: new Date(),
|
||||||
|
},
|
||||||
|
]);
|
||||||
|
break;
|
||||||
|
}
|
||||||
|
|
||||||
case "pong": {
|
case "pong": {
|
||||||
// Keep-alive response, nothing to do
|
// Keep-alive response, nothing to do
|
||||||
break;
|
break;
|
||||||
|
|||||||
@@ -226,6 +226,20 @@ export function useExpandChat({
|
|||||||
break
|
break
|
||||||
}
|
}
|
||||||
|
|
||||||
|
case 'rate_limited': {
|
||||||
|
// Show rate limit info as system message
|
||||||
|
setMessages((prev) => [
|
||||||
|
...prev,
|
||||||
|
{
|
||||||
|
id: generateId(),
|
||||||
|
role: 'system',
|
||||||
|
content: `Rate limited. Retrying in ${data.retry_in}s... (attempt ${data.attempt}/${data.max_attempts})`,
|
||||||
|
timestamp: new Date(),
|
||||||
|
},
|
||||||
|
])
|
||||||
|
break
|
||||||
|
}
|
||||||
|
|
||||||
case 'pong': {
|
case 'pong': {
|
||||||
// Keep-alive response, nothing to do
|
// Keep-alive response, nothing to do
|
||||||
break
|
break
|
||||||
|
|||||||
@@ -322,6 +322,20 @@ export function useSpecChat({
|
|||||||
break
|
break
|
||||||
}
|
}
|
||||||
|
|
||||||
|
case 'rate_limited': {
|
||||||
|
// Show rate limit info as system message
|
||||||
|
setMessages((prev) => [
|
||||||
|
...prev,
|
||||||
|
{
|
||||||
|
id: generateId(),
|
||||||
|
role: 'system',
|
||||||
|
content: `Rate limited. Retrying in ${data.retry_in}s... (attempt ${data.attempt}/${data.max_attempts})`,
|
||||||
|
timestamp: new Date(),
|
||||||
|
},
|
||||||
|
])
|
||||||
|
break
|
||||||
|
}
|
||||||
|
|
||||||
case 'pong': {
|
case 'pong': {
|
||||||
// Keep-alive response, nothing to do
|
// Keep-alive response, nothing to do
|
||||||
break
|
break
|
||||||
|
|||||||
@@ -407,6 +407,13 @@ export interface SpecChatResponseDoneMessage {
|
|||||||
type: 'response_done'
|
type: 'response_done'
|
||||||
}
|
}
|
||||||
|
|
||||||
|
export interface SpecChatRateLimitedMessage {
|
||||||
|
type: 'rate_limited'
|
||||||
|
retry_in: number
|
||||||
|
attempt: number
|
||||||
|
max_attempts: number
|
||||||
|
}
|
||||||
|
|
||||||
export type SpecChatServerMessage =
|
export type SpecChatServerMessage =
|
||||||
| SpecChatTextMessage
|
| SpecChatTextMessage
|
||||||
| SpecChatQuestionMessage
|
| SpecChatQuestionMessage
|
||||||
@@ -416,6 +423,7 @@ export type SpecChatServerMessage =
|
|||||||
| SpecChatErrorMessage
|
| SpecChatErrorMessage
|
||||||
| SpecChatPongMessage
|
| SpecChatPongMessage
|
||||||
| SpecChatResponseDoneMessage
|
| SpecChatResponseDoneMessage
|
||||||
|
| SpecChatRateLimitedMessage
|
||||||
|
|
||||||
// Image attachment for chat messages
|
// Image attachment for chat messages
|
||||||
export interface ImageAttachment {
|
export interface ImageAttachment {
|
||||||
@@ -501,6 +509,13 @@ export interface AssistantChatPongMessage {
|
|||||||
type: 'pong'
|
type: 'pong'
|
||||||
}
|
}
|
||||||
|
|
||||||
|
export interface AssistantChatRateLimitedMessage {
|
||||||
|
type: 'rate_limited'
|
||||||
|
retry_in: number
|
||||||
|
attempt: number
|
||||||
|
max_attempts: number
|
||||||
|
}
|
||||||
|
|
||||||
export type AssistantChatServerMessage =
|
export type AssistantChatServerMessage =
|
||||||
| AssistantChatTextMessage
|
| AssistantChatTextMessage
|
||||||
| AssistantChatToolCallMessage
|
| AssistantChatToolCallMessage
|
||||||
@@ -509,6 +524,7 @@ export type AssistantChatServerMessage =
|
|||||||
| AssistantChatErrorMessage
|
| AssistantChatErrorMessage
|
||||||
| AssistantChatConversationCreatedMessage
|
| AssistantChatConversationCreatedMessage
|
||||||
| AssistantChatPongMessage
|
| AssistantChatPongMessage
|
||||||
|
| AssistantChatRateLimitedMessage
|
||||||
|
|
||||||
// ============================================================================
|
// ============================================================================
|
||||||
// Expand Chat Types
|
// Expand Chat Types
|
||||||
@@ -532,6 +548,7 @@ export type ExpandChatServerMessage =
|
|||||||
| SpecChatErrorMessage // Reuse error message type
|
| SpecChatErrorMessage // Reuse error message type
|
||||||
| SpecChatPongMessage // Reuse pong message type
|
| SpecChatPongMessage // Reuse pong message type
|
||||||
| SpecChatResponseDoneMessage // Reuse response_done type
|
| SpecChatResponseDoneMessage // Reuse response_done type
|
||||||
|
| SpecChatRateLimitedMessage // Reuse rate_limited message type
|
||||||
|
|
||||||
// Bulk feature creation
|
// Bulk feature creation
|
||||||
export interface FeatureBulkCreate {
|
export interface FeatureBulkCreate {
|
||||||
|
|||||||
Reference in New Issue
Block a user