Merge pull request #212 from AutoForgeAI/fix/rate-limit-and-version-bump

fix: resolve false-positive rate limit and version bump to 0.1.15

agent.py

@@ -74,7 +74,15 @@ async def run_agent_session(
         await client.query(message)
 
         # Collect response text and show tool use
+        # Retry receive_response() on MessageParseError — the SDK raises this for
+        # unknown CLI message types (e.g. "rate_limit_event") which kills the async
+        # generator.  The subprocess is still alive so we restart to read remaining
+        # messages from the buffered channel.
         response_text = ""
+        max_parse_retries = 50
+        parse_retries = 0
+        while True:
+            try:
                 async for msg in client.receive_response():
                     msg_type = type(msg).__name__
 
@@ -115,6 +123,17 @@ async def run_agent_session(
                                     # Tool succeeded - just show brief confirmation
                                     print("   [Done]", flush=True)
 
+                break  # Normal completion
+            except Exception as inner_exc:
+                if type(inner_exc).__name__ == "MessageParseError":
+                    parse_retries += 1
+                    if parse_retries > max_parse_retries:
+                        print(f"Too many unrecognized CLI messages ({parse_retries}), stopping")
+                        break
+                    print(f"Ignoring unrecognized message from Claude CLI: {inner_exc}")
+                    continue
+                raise  # Re-raise to outer except
+
         print("\n" + "-" * 70 + "\n")
         return "continue", response_text
 

package.json

@@ -1,6 +1,6 @@
 {
   "name": "autoforge-ai",
-  "version": "0.1.14",
+  "version": "0.1.15",
   "description": "Autonomous coding agent with web UI - build complete apps with AI",
   "license": "AGPL-3.0",
   "bin": {

server/services/assistant_chat_session.py

@@ -7,7 +7,6 @@ The assistant can answer questions about the codebase and features
 but cannot modify any files.
 """
 
-import asyncio
 import json
 import logging
 import os
@@ -27,10 +26,9 @@ from .assistant_database import (
     get_messages,
 )
 from .chat_constants import (
-    MAX_CHAT_RATE_LIMIT_RETRIES,
     ROOT_DIR,
-    calculate_rate_limit_backoff,
     check_rate_limit_error,
+    safe_receive_response,
 )
 
 # Load environment variables from .env file if present
@@ -399,10 +397,9 @@ class AssistantChatSession:
 
         full_response = ""
 
-        # Stream the response (with rate-limit retry)
+        # Stream the response
-        for _attempt in range(MAX_CHAT_RATE_LIMIT_RETRIES + 1):
         try:
-                async for msg in self.client.receive_response():
+            async for msg in safe_receive_response(self.client, logger):
                 msg_type = type(msg).__name__
 
                 if msg_type == "AssistantMessage" and hasattr(msg, "content"):
@@ -434,30 +431,12 @@ class AssistantChatSession:
                                 "tool": tool_name,
                                 "input": tool_input,
                             }
-                # Completed successfully — break out of retry loop
-                break
         except Exception as exc:
-                is_rate_limit, retry_secs = check_rate_limit_error(exc)
+            is_rate_limit, _ = 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)
-                    await self.client.query(message)
-                    continue
             if is_rate_limit:
-                    logger.error("Rate limit retries exhausted for assistant chat")
+                logger.warning(f"Rate limited: {exc}")
                 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

server/services/chat_constants.py

@@ -12,7 +12,7 @@ imports (``from .chat_constants import API_ENV_VARS``) continue to work.
 import logging
 import sys
 from pathlib import Path
-from typing import AsyncGenerator
+from typing import Any, AsyncGenerator
 
 # -------------------------------------------------------------------
 # Root directory of the autoforge project (repository root).
@@ -33,15 +33,10 @@ if _root_str not in sys.path:
 # imports continue to work unchanged.
 # -------------------------------------------------------------------
 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
+from rate_limit_utils import 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.
@@ -49,24 +44,15 @@ def check_rate_limit_error(exc: Exception) -> tuple[bool, int | None]:
     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``).
     """
+    # MessageParseError = unknown CLI message type (e.g. "rate_limit_event").
+    # These are informational events, NOT actual rate limit errors.
+    # The word "rate_limit" in the type name would false-positive the regex.
+    if type(exc).__name__ == "MessageParseError":
+        return False, None
+
+    # For all other exceptions: match error text against known rate-limit patterns
     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
@@ -74,6 +60,34 @@ def check_rate_limit_error(exc: Exception) -> tuple[bool, int | None]:
     return False, None
 
 
+async def safe_receive_response(client: Any, log: logging.Logger) -> AsyncGenerator:
+    """Wrap ``client.receive_response()`` to skip ``MessageParseError``.
+
+    The Claude Code CLI may emit message types (e.g. ``rate_limit_event``)
+    that the installed Python SDK does not recognise, causing
+    ``MessageParseError`` which kills the async generator.  The CLI
+    subprocess is still alive and the SDK uses a buffered memory channel,
+    so we restart ``receive_response()`` to continue reading remaining
+    messages without losing data.
+    """
+    max_retries = 50
+    retries = 0
+    while True:
+        try:
+            async for msg in client.receive_response():
+                yield msg
+            return  # Normal completion
+        except Exception as exc:
+            if type(exc).__name__ == "MessageParseError":
+                retries += 1
+                if retries > max_retries:
+                    log.error(f"Too many unrecognized CLI messages ({retries}), stopping")
+                    return
+                log.warning(f"Ignoring unrecognized message from Claude CLI: {exc}")
+                continue
+            raise
+
+
 async def make_multimodal_message(content_blocks: list[dict]) -> AsyncGenerator[dict, None]:
     """Yield a single multimodal user message in Claude Agent SDK format.
 

server/services/expand_chat_session.py

@@ -23,11 +23,10 @@ from dotenv import load_dotenv
 
 from ..schemas import ImageAttachment
 from .chat_constants import (
-    MAX_CHAT_RATE_LIMIT_RETRIES,
     ROOT_DIR,
-    calculate_rate_limit_backoff,
     check_rate_limit_error,
     make_multimodal_message,
+    safe_receive_response,
 )
 
 # Load environment variables from .env file if present
@@ -304,10 +303,9 @@ class ExpandChatSession:
         else:
             await self.client.query(message)
 
-        # Stream the response (with rate-limit retry)
+        # Stream the response
-        for _attempt in range(MAX_CHAT_RATE_LIMIT_RETRIES + 1):
         try:
-                async for msg in self.client.receive_response():
+            async for msg in safe_receive_response(self.client, logger):
                 msg_type = type(msg).__name__
 
                 if msg_type == "AssistantMessage" and hasattr(msg, "content"):
@@ -324,46 +322,12 @@ class ExpandChatSession:
                                     "content": text,
                                     "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)
+            is_rate_limit, _ = 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")
+                logger.warning(f"Rate limited: {exc}")
                 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:

server/services/spec_chat_session.py

@@ -6,7 +6,6 @@ Manages interactive spec creation conversation with Claude.
 Uses the create-spec.md skill to guide users through app spec creation.
 """
 
-import asyncio
 import json
 import logging
 import os
@@ -21,11 +20,10 @@ from dotenv import load_dotenv
 
 from ..schemas import ImageAttachment
 from .chat_constants import (
-    MAX_CHAT_RATE_LIMIT_RETRIES,
     ROOT_DIR,
-    calculate_rate_limit_backoff,
     check_rate_limit_error,
     make_multimodal_message,
+    safe_receive_response,
 )
 
 # Load environment variables from .env file if present
@@ -311,10 +309,9 @@ class SpecChatSession:
         # Store paths for the completion message
         spec_path = None
 
-        # Stream the response using receive_response (with rate-limit retry)
+        # Stream the response
-        for _attempt in range(MAX_CHAT_RATE_LIMIT_RETRIES + 1):
         try:
-                async for msg in self.client.receive_response():
+            async for msg in safe_receive_response(self.client, logger):
                 msg_type = type(msg).__name__
 
                 if msg_type == "AssistantMessage" and hasattr(msg, "content"):
@@ -424,31 +421,12 @@ class SpecChatSession:
                                         "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)
+            is_rate_limit, _ = 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")
+                logger.warning(f"Rate limited: {exc}")
                 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:

ui/package-lock.json

@@ -56,7 +56,7 @@
     },
     "..": {
       "name": "autoforge-ai",
-      "version": "0.1.14",
+      "version": "0.1.15",
       "license": "AGPL-3.0",
       "bin": {
         "autoforge": "bin/autoforge.js"

ui/src/hooks/useAssistantChat.ts

@@ -269,20 +269,6 @@ export function useAssistantChat({
             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": {
             // Keep-alive response, nothing to do
             break;

ui/src/hooks/useExpandChat.ts

@@ -226,20 +226,6 @@ export function useExpandChat({
             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': {
             // Keep-alive response, nothing to do
             break

ui/src/hooks/useSpecChat.ts

@@ -322,20 +322,6 @@ export function useSpecChat({
             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': {
             // Keep-alive response, nothing to do
             break

ui/src/lib/types.ts

@@ -407,13 +407,6 @@ export interface SpecChatResponseDoneMessage {
   type: 'response_done'
 }
 
-export interface SpecChatRateLimitedMessage {
-  type: 'rate_limited'
-  retry_in: number
-  attempt: number
-  max_attempts: number
-}
-
 export type SpecChatServerMessage =
   | SpecChatTextMessage
   | SpecChatQuestionMessage
@@ -423,7 +416,6 @@ export type SpecChatServerMessage =
   | SpecChatErrorMessage
   | SpecChatPongMessage
   | SpecChatResponseDoneMessage
-  | SpecChatRateLimitedMessage
 
 // Image attachment for chat messages
 export interface ImageAttachment {
@@ -509,13 +501,6 @@ export interface AssistantChatPongMessage {
   type: 'pong'
 }
 
-export interface AssistantChatRateLimitedMessage {
-  type: 'rate_limited'
-  retry_in: number
-  attempt: number
-  max_attempts: number
-}
-
 export type AssistantChatServerMessage =
   | AssistantChatTextMessage
   | AssistantChatToolCallMessage
@@ -524,7 +509,6 @@ export type AssistantChatServerMessage =
   | AssistantChatErrorMessage
   | AssistantChatConversationCreatedMessage
   | AssistantChatPongMessage
-  | AssistantChatRateLimitedMessage
 
 // ============================================================================
 // Expand Chat Types
@@ -548,7 +532,6 @@ export type ExpandChatServerMessage =
   | SpecChatErrorMessage       // Reuse error message type
   | SpecChatPongMessage        // Reuse pong message type
   | SpecChatResponseDoneMessage // Reuse response_done type
-  | SpecChatRateLimitedMessage // Reuse rate_limited message type
 
 // Bulk feature creation
 export interface FeatureBulkCreate {