From df46046c86865fcaa3cf66b5b91d81ffaf606f9b Mon Sep 17 00:00:00 2001
From: chihlasm <michael@chihlas.com>
Date: Sun, 8 Mar 2026 15:43:22 -0400
Subject: [PATCH] fix: resolve MissingGreenlet crash and add MCP fallback in AI
 Assistant

Capture user_id/account_id before try block so error handler survives
db.rollback() without triggering lazy loads in async context. Add
retry-without-MCP fallback when Anthropic MCP server returns rate limit
or connection errors.

Fixes PYTHON-FASTAPI-3, PYTHON-FASTAPI-4

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---
 backend/app/api/endpoints/assistant_chat.py   | 18 +++++++----
 .../app/services/assistant_chat_service.py    | 32 +++++++++++++------
 2 files changed, 35 insertions(+), 15 deletions(-)

diff --git a/backend/app/api/endpoints/assistant_chat.py b/backend/app/api/endpoints/assistant_chat.py
index 83422367..3bcc1f5e 100644
--- a/backend/app/api/endpoints/assistant_chat.py
+++ b/backend/app/api/endpoints/assistant_chat.py
@@ -145,11 +145,17 @@ async def post_message(
 
     plan = await get_user_plan(current_user.account_id, db)
 
+    # Capture scalar fields before the try block — after db.rollback()
+    # the ORM objects are expired and accessing attributes triggers a
+    # lazy load, which crashes in async context (MissingGreenlet).
+    user_id = current_user.id
+    account_id = current_user.account_id
+
     try:
         ai_content, suggested_flows, chat = await assistant_chat_service.send_message(
             chat_id=chat_id,
-            user_id=current_user.id,
-            account_id=current_user.account_id,
+            user_id=user_id,
+            account_id=account_id,
             message=data.message,
             db=db,
         )
@@ -159,8 +165,8 @@ async def post_message(
         logger.exception("Assistant chat message failed: %s", e)
         await db.rollback()
         await record_ai_usage(
-            user_id=current_user.id,
-            account_id=current_user.account_id,
+            user_id=user_id,
+            account_id=account_id,
             conversation_id=None,
             generation_type="assistant_message",
             tier=plan,
@@ -180,8 +186,8 @@ async def post_message(
         )
 
     await record_ai_usage(
-        user_id=current_user.id,
-        account_id=current_user.account_id,
+        user_id=user_id,
+        account_id=account_id,
         conversation_id=None,
         generation_type="assistant_message",
         tier=plan,
diff --git a/backend/app/services/assistant_chat_service.py b/backend/app/services/assistant_chat_service.py
index 86390608..9508fe56 100644
--- a/backend/app/services/assistant_chat_service.py
+++ b/backend/app/services/assistant_chat_service.py
@@ -189,15 +189,29 @@ async def _call_anthropic_cached(
             }
         ]
 
-    response = await client.beta.messages.create(
-        model=settings.AI_MODEL_ANTHROPIC,
-        max_tokens=max_tokens,
-        system=system_blocks,
-        messages=messages,
-        mcp_servers=mcp_servers,
-        tools=tools,
-        betas=["mcp-client-2025-11-20"],
-    )
+    try:
+        response = await client.beta.messages.create(
+            model=settings.AI_MODEL_ANTHROPIC,
+            max_tokens=max_tokens,
+            system=system_blocks,
+            messages=messages,
+            mcp_servers=mcp_servers,
+            tools=tools,
+            betas=["mcp-client-2025-11-20"],
+        )
+    except anthropic.BadRequestError as e:
+        # MCP server failures (rate limits, connection errors) should not
+        # block the assistant entirely — retry without MCP tools.
+        if "MCP server" in str(e) and mcp_servers is not anthropic.NOT_GIVEN:
+            logger.warning("MCP server error, retrying without MCP: %s", e)
+            response = await client.beta.messages.create(
+                model=settings.AI_MODEL_ANTHROPIC,
+                max_tokens=max_tokens,
+                system=system_blocks,
+                messages=messages,
+            )
+        else:
+            raise
 
     # Extract text from response — MCP responses can have multiple block
     # types (text, mcp_tool_use, mcp_tool_result). We join all text blocks.