feat(chat): improve agent generator error propagation (#11884)

## Summary
- Add helper functions in `service.py` to create standardized error
responses with `error_type` classification
- Update service functions to return error dicts instead of `None`,
preserving error details from the Agent Generator microservice
- Update `core.py` to pass through error responses properly
- Update `create_agent.py` to handle error responses with user-friendly
messages based on error type

## Error Types Now Propagated
| Error Type | Description | User Message |
|------------|-------------|--------------|
| `llm_parse_error` | LLM returned unparseable response | "The AI had
trouble understanding this request" |
| `llm_timeout` / `timeout` | Request timed out | "The request took too
long" |
| `llm_rate_limit` / `rate_limit` | Rate limited | "The service is
currently busy" |
| `validation_error` | Agent validation failed | "The generated agent
failed validation" |
| `connection_error` | Could not connect to Agent Generator | Generic
error message |
| `http_error` | HTTP error from Agent Generator | Generic error message
|
| `unknown` | Unclassified error | Generic error message |

## Motivation
This enables better debugging for issues like SECRT-1817 where
decomposition failed due to transient LLM errors but the root cause was
unclear in the logs. Now:
1. Error details from the Agent Generator microservice are preserved
2. Users get more helpful error messages based on error type
3. Debugging is easier with `error_type` in response details

## Related PR
- Agent Generator side:
https://github.com/Significant-Gravitas/AutoGPT-Agent-Generator/pull/102

## Test Plan
- [ ] Test decomposition with various error scenarios (timeout, parse
error)
- [ ] Verify user-friendly messages are shown based on error type
- [ ] Check that error details are logged properly

autogpt_platform/backend/backend/api/features/chat/tools/agent_generator/__init__.py

@@ -9,6 +9,7 @@ from .core import (
     json_to_graph,
     save_agent_to_library,
 )
+from .errors import get_user_message_for_error
 from .service import health_check as check_external_service_health
 from .service import is_external_service_configured
 
@@ -25,4 +26,6 @@ __all__ = [
     # Service
     "is_external_service_configured",
     "check_external_service_health",
+    # Error handling
+    "get_user_message_for_error",
 ]

autogpt_platform/backend/backend/api/features/chat/tools/agent_generator/core.py

@@ -64,7 +64,7 @@ async def generate_agent(instructions: dict[str, Any]) -> dict[str, Any] | None:
         instructions: Structured instructions from decompose_goal
 
     Returns:
-        Agent JSON dict or None on error
+        Agent JSON dict, error dict {"type": "error", ...}, or None on error
 
     Raises:
         AgentGeneratorNotConfiguredError: If the external service is not configured.
@@ -73,7 +73,10 @@ async def generate_agent(instructions: dict[str, Any]) -> dict[str, Any] | None:
     logger.info("Calling external Agent Generator service for generate_agent")
     result = await generate_agent_external(instructions)
     if result:
-        # Ensure required fields
+        # Check if it's an error response - pass through as-is
+        if isinstance(result, dict) and result.get("type") == "error":
+            return result
+        # Ensure required fields for successful agent generation
         if "id" not in result:
             result["id"] = str(uuid.uuid4())
         if "version" not in result:
@@ -267,7 +270,8 @@ async def generate_agent_patch(
         current_agent: Current agent JSON
 
     Returns:
-        Updated agent JSON, clarifying questions dict, or None on error
+        Updated agent JSON, clarifying questions dict {"type": "clarifying_questions", ...},
+        error dict {"type": "error", ...}, or None on unexpected error
 
     Raises:
         AgentGeneratorNotConfiguredError: If the external service is not configured.

autogpt_platform/backend/backend/api/features/chat/tools/agent_generator/errors.py

@@ -0,0 +1,43 @@
+"""Error handling utilities for agent generator."""
+
+
+def get_user_message_for_error(
+    error_type: str,
+    operation: str = "process the request",
+    llm_parse_message: str | None = None,
+    validation_message: str | None = None,
+) -> str:
+    """Get a user-friendly error message based on error type.
+
+    This function maps internal error types to user-friendly messages,
+    providing a consistent experience across different agent operations.
+
+    Args:
+        error_type: The error type from the external service
+            (e.g., "llm_parse_error", "timeout", "rate_limit")
+        operation: Description of what operation failed, used in the default
+            message (e.g., "analyze the goal", "generate the agent")
+        llm_parse_message: Custom message for llm_parse_error type
+        validation_message: Custom message for validation_error type
+
+    Returns:
+        User-friendly error message suitable for display to the user
+    """
+    if error_type == "llm_parse_error":
+        return (
+            llm_parse_message
+            or "The AI had trouble processing this request. Please try again."
+        )
+    elif error_type == "validation_error":
+        return (
+            validation_message
+            or "The request failed validation. Please try rephrasing."
+        )
+    elif error_type == "patch_error":
+        return "Failed to apply the changes. Please try a different approach."
+    elif error_type in ("timeout", "llm_timeout"):
+        return "The request took too long. Please try again."
+    elif error_type in ("rate_limit", "llm_rate_limit"):
+        return "The service is currently busy. Please try again in a moment."
+    else:
+        return f"Failed to {operation}. Please try again."

autogpt_platform/backend/backend/api/features/chat/tools/agent_generator/service.py

@@ -14,6 +14,70 @@ from backend.util.settings import Settings
 
 logger = logging.getLogger(__name__)
 
+
+def _create_error_response(
+    error_message: str,
+    error_type: str = "unknown",
+    details: dict[str, Any] | None = None,
+) -> dict[str, Any]:
+    """Create a standardized error response dict.
+
+    Args:
+        error_message: Human-readable error message
+        error_type: Machine-readable error type
+        details: Optional additional error details
+
+    Returns:
+        Error dict with type="error" and error details
+    """
+    response: dict[str, Any] = {
+        "type": "error",
+        "error": error_message,
+        "error_type": error_type,
+    }
+    if details:
+        response["details"] = details
+    return response
+
+
+def _classify_http_error(e: httpx.HTTPStatusError) -> tuple[str, str]:
+    """Classify an HTTP error into error_type and message.
+
+    Args:
+        e: The HTTP status error
+
+    Returns:
+        Tuple of (error_type, error_message)
+    """
+    status = e.response.status_code
+    if status == 429:
+        return "rate_limit", f"Agent Generator rate limited: {e}"
+    elif status == 503:
+        return "service_unavailable", f"Agent Generator unavailable: {e}"
+    elif status == 504 or status == 408:
+        return "timeout", f"Agent Generator timed out: {e}"
+    else:
+        return "http_error", f"HTTP error calling Agent Generator: {e}"
+
+
+def _classify_request_error(e: httpx.RequestError) -> tuple[str, str]:
+    """Classify a request error into error_type and message.
+
+    Args:
+        e: The request error
+
+    Returns:
+        Tuple of (error_type, error_message)
+    """
+    error_str = str(e).lower()
+    if "timeout" in error_str or "timed out" in error_str:
+        return "timeout", f"Agent Generator request timed out: {e}"
+    elif "connect" in error_str:
+        return "connection_error", f"Could not connect to Agent Generator: {e}"
+    else:
+        return "request_error", f"Request error calling Agent Generator: {e}"
+
+
 _client: httpx.AsyncClient | None = None
 _settings: Settings | None = None
 
@@ -67,7 +131,8 @@ async def decompose_goal_external(
         - {"type": "instructions", "steps": [...]}
         - {"type": "unachievable_goal", ...}
         - {"type": "vague_goal", ...}
-        Or None on error
+        - {"type": "error", "error": "...", "error_type": "..."} on error
+        Or None on unexpected error
     """
     client = _get_client()
 
@@ -83,8 +148,13 @@ async def decompose_goal_external(
         data = response.json()
 
         if not data.get("success"):
-            logger.error(f"External service returned error: {data.get('error')}")
-            return None
+            error_msg = data.get("error", "Unknown error from Agent Generator")
+            error_type = data.get("error_type", "unknown")
+            logger.error(
+                f"Agent Generator decomposition failed: {error_msg} "
+                f"(type: {error_type})"
+            )
+            return _create_error_response(error_msg, error_type)
 
         # Map the response to the expected format
         response_type = data.get("type")
@@ -106,25 +176,37 @@ async def decompose_goal_external(
                 "type": "vague_goal",
                 "suggested_goal": data.get("suggested_goal"),
             }
+        elif response_type == "error":
+            # Pass through error from the service
+            return _create_error_response(
+                data.get("error", "Unknown error"),
+                data.get("error_type", "unknown"),
+            )
         else:
             logger.error(
                 f"Unknown response type from external service: {response_type}"
             )
-            return None
+            return _create_error_response(
+                f"Unknown response type from Agent Generator: {response_type}",
+                "invalid_response",
+            )
 
     except httpx.HTTPStatusError as e:
-        logger.error(f"HTTP error calling external agent generator: {e}")
-        return None
+        error_type, error_msg = _classify_http_error(e)
+        logger.error(error_msg)
+        return _create_error_response(error_msg, error_type)
     except httpx.RequestError as e:
-        logger.error(f"Request error calling external agent generator: {e}")
-        return None
+        error_type, error_msg = _classify_request_error(e)
+        logger.error(error_msg)
+        return _create_error_response(error_msg, error_type)
     except Exception as e:
-        logger.error(f"Unexpected error calling external agent generator: {e}")
-        return None
+        error_msg = f"Unexpected error calling Agent Generator: {e}"
+        logger.error(error_msg)
+        return _create_error_response(error_msg, "unexpected_error")
 
 
 async def generate_agent_external(
-    instructions: dict[str, Any]
+    instructions: dict[str, Any],
 ) -> dict[str, Any] | None:
     """Call the external service to generate an agent from instructions.
 
@@ -132,7 +214,7 @@ async def generate_agent_external(
         instructions: Structured instructions from decompose_goal
 
     Returns:
-        Agent JSON dict or None on error
+        Agent JSON dict on success, or error dict {"type": "error", ...} on error
     """
     client = _get_client()
 
@@ -144,20 +226,28 @@ async def generate_agent_external(
         data = response.json()
 
         if not data.get("success"):
-            logger.error(f"External service returned error: {data.get('error')}")
-            return None
+            error_msg = data.get("error", "Unknown error from Agent Generator")
+            error_type = data.get("error_type", "unknown")
+            logger.error(
+                f"Agent Generator generation failed: {error_msg} "
+                f"(type: {error_type})"
+            )
+            return _create_error_response(error_msg, error_type)
 
         return data.get("agent_json")
 
     except httpx.HTTPStatusError as e:
-        logger.error(f"HTTP error calling external agent generator: {e}")
-        return None
+        error_type, error_msg = _classify_http_error(e)
+        logger.error(error_msg)
+        return _create_error_response(error_msg, error_type)
     except httpx.RequestError as e:
-        logger.error(f"Request error calling external agent generator: {e}")
-        return None
+        error_type, error_msg = _classify_request_error(e)
+        logger.error(error_msg)
+        return _create_error_response(error_msg, error_type)
     except Exception as e:
-        logger.error(f"Unexpected error calling external agent generator: {e}")
-        return None
+        error_msg = f"Unexpected error calling Agent Generator: {e}"
+        logger.error(error_msg)
+        return _create_error_response(error_msg, "unexpected_error")
 
 
 async def generate_agent_patch_external(
@@ -170,7 +260,7 @@ async def generate_agent_patch_external(
         current_agent: Current agent JSON
 
     Returns:
-        Updated agent JSON, clarifying questions dict, or None on error
+        Updated agent JSON, clarifying questions dict, or error dict on error
     """
     client = _get_client()
 
@@ -186,8 +276,13 @@ async def generate_agent_patch_external(
         data = response.json()
 
         if not data.get("success"):
-            logger.error(f"External service returned error: {data.get('error')}")
-            return None
+            error_msg = data.get("error", "Unknown error from Agent Generator")
+            error_type = data.get("error_type", "unknown")
+            logger.error(
+                f"Agent Generator patch generation failed: {error_msg} "
+                f"(type: {error_type})"
+            )
+            return _create_error_response(error_msg, error_type)
 
         # Check if it's clarifying questions
         if data.get("type") == "clarifying_questions":
@@ -196,18 +291,28 @@ async def generate_agent_patch_external(
                 "questions": data.get("questions", []),
             }
 
+        # Check if it's an error passed through
+        if data.get("type") == "error":
+            return _create_error_response(
+                data.get("error", "Unknown error"),
+                data.get("error_type", "unknown"),
+            )
+
         # Otherwise return the updated agent JSON
         return data.get("agent_json")
 
     except httpx.HTTPStatusError as e:
-        logger.error(f"HTTP error calling external agent generator: {e}")
-        return None
+        error_type, error_msg = _classify_http_error(e)
+        logger.error(error_msg)
+        return _create_error_response(error_msg, error_type)
     except httpx.RequestError as e:
-        logger.error(f"Request error calling external agent generator: {e}")
-        return None
+        error_type, error_msg = _classify_request_error(e)
+        logger.error(error_msg)
+        return _create_error_response(error_msg, error_type)
     except Exception as e:
-        logger.error(f"Unexpected error calling external agent generator: {e}")
-        return None
+        error_msg = f"Unexpected error calling Agent Generator: {e}"
+        logger.error(error_msg)
+        return _create_error_response(error_msg, "unexpected_error")
 
 
 async def get_blocks_external() -> list[dict[str, Any]] | None:

autogpt_platform/backend/backend/api/features/chat/tools/create_agent.py

@@ -9,6 +9,7 @@ from .agent_generator import (
     AgentGeneratorNotConfiguredError,
     decompose_goal,
     generate_agent,
+    get_user_message_for_error,
     save_agent_to_library,
 )
 from .base import BaseTool
@@ -117,11 +118,29 @@ class CreateAgentTool(BaseTool):
 
         if decomposition_result is None:
             return ErrorResponse(
-                message="Failed to analyze the goal. The agent generation service may be unavailable or timed out. Please try again.",
+                message="Failed to analyze the goal. The agent generation service may be unavailable. Please try again.",
                 error="decomposition_failed",
+                details={"description": description[:100]},
+                session_id=session_id,
+            )
+
+        # Check if the result is an error from the external service
+        if decomposition_result.get("type") == "error":
+            error_msg = decomposition_result.get("error", "Unknown error")
+            error_type = decomposition_result.get("error_type", "unknown")
+            user_message = get_user_message_for_error(
+                error_type,
+                operation="analyze the goal",
+                llm_parse_message="The AI had trouble understanding this request. Please try rephrasing your goal.",
+            )
+            return ErrorResponse(
+                message=user_message,
+                error=f"decomposition_failed:{error_type}",
                 details={
-                    "description": description[:100]
-                },  # Include context for debugging
+                    "description": description[:100],
+                    "service_error": error_msg,
+                    "error_type": error_type,
+                },
                 session_id=session_id,
             )
 
@@ -186,11 +205,30 @@ class CreateAgentTool(BaseTool):
 
         if agent_json is None:
             return ErrorResponse(
-                message="Failed to generate the agent. The agent generation service may be unavailable or timed out. Please try again.",
+                message="Failed to generate the agent. The agent generation service may be unavailable. Please try again.",
                 error="generation_failed",
+                details={"description": description[:100]},
+                session_id=session_id,
+            )
+
+        # Check if the result is an error from the external service
+        if isinstance(agent_json, dict) and agent_json.get("type") == "error":
+            error_msg = agent_json.get("error", "Unknown error")
+            error_type = agent_json.get("error_type", "unknown")
+            user_message = get_user_message_for_error(
+                error_type,
+                operation="generate the agent",
+                llm_parse_message="The AI had trouble generating the agent. Please try again or simplify your goal.",
+                validation_message="The generated agent failed validation. Please try rephrasing your goal.",
+            )
+            return ErrorResponse(
+                message=user_message,
+                error=f"generation_failed:{error_type}",
                 details={
-                    "description": description[:100]
-                },  # Include context for debugging
+                    "description": description[:100],
+                    "service_error": error_msg,
+                    "error_type": error_type,
+                },
                 session_id=session_id,
             )
 

autogpt_platform/backend/backend/api/features/chat/tools/edit_agent.py

@@ -9,6 +9,7 @@ from .agent_generator import (
     AgentGeneratorNotConfiguredError,
     generate_agent_patch,
     get_agent_as_json,
+    get_user_message_for_error,
     save_agent_to_library,
 )
 from .base import BaseTool
@@ -152,6 +153,28 @@ class EditAgentTool(BaseTool):
                 session_id=session_id,
             )
 
+        # Check if the result is an error from the external service
+        if isinstance(result, dict) and result.get("type") == "error":
+            error_msg = result.get("error", "Unknown error")
+            error_type = result.get("error_type", "unknown")
+            user_message = get_user_message_for_error(
+                error_type,
+                operation="generate the changes",
+                llm_parse_message="The AI had trouble generating the changes. Please try again or simplify your request.",
+                validation_message="The generated changes failed validation. Please try rephrasing your request.",
+            )
+            return ErrorResponse(
+                message=user_message,
+                error=f"update_generation_failed:{error_type}",
+                details={
+                    "agent_id": agent_id,
+                    "changes": changes[:100],
+                    "service_error": error_msg,
+                    "error_type": error_type,
+                },
+                session_id=session_id,
+            )
+
         # Check if LLM returned clarifying questions
         if result.get("type") == "clarifying_questions":
             questions = result.get("questions", [])

autogpt_platform/backend/test/agent_generator/test_service.py

@@ -151,15 +151,20 @@ class TestDecomposeGoalExternal:
     @pytest.mark.asyncio
     async def test_decompose_goal_handles_http_error(self):
         """Test decomposition handles HTTP errors gracefully."""
+        mock_response = MagicMock()
+        mock_response.status_code = 500
         mock_client = AsyncMock()
         mock_client.post.side_effect = httpx.HTTPStatusError(
-            "Server error", request=MagicMock(), response=MagicMock()
+            "Server error", request=MagicMock(), response=mock_response
         )
 
         with patch.object(service, "_get_client", return_value=mock_client):
             result = await service.decompose_goal_external("Build a chatbot")
 
-        assert result is None
+        assert result is not None
+        assert result.get("type") == "error"
+        assert result.get("error_type") == "http_error"
+        assert "Server error" in result.get("error", "")
 
     @pytest.mark.asyncio
     async def test_decompose_goal_handles_request_error(self):
@@ -170,7 +175,10 @@ class TestDecomposeGoalExternal:
         with patch.object(service, "_get_client", return_value=mock_client):
             result = await service.decompose_goal_external("Build a chatbot")
 
-        assert result is None
+        assert result is not None
+        assert result.get("type") == "error"
+        assert result.get("error_type") == "connection_error"
+        assert "Connection failed" in result.get("error", "")
 
     @pytest.mark.asyncio
     async def test_decompose_goal_handles_service_error(self):
@@ -179,6 +187,7 @@ class TestDecomposeGoalExternal:
         mock_response.json.return_value = {
             "success": False,
             "error": "Internal error",
+            "error_type": "internal_error",
         }
         mock_response.raise_for_status = MagicMock()
 
@@ -188,7 +197,10 @@ class TestDecomposeGoalExternal:
         with patch.object(service, "_get_client", return_value=mock_client):
             result = await service.decompose_goal_external("Build a chatbot")
 
-        assert result is None
+        assert result is not None
+        assert result.get("type") == "error"
+        assert result.get("error") == "Internal error"
+        assert result.get("error_type") == "internal_error"
 
 
 class TestGenerateAgentExternal:
@@ -236,7 +248,10 @@ class TestGenerateAgentExternal:
         with patch.object(service, "_get_client", return_value=mock_client):
             result = await service.generate_agent_external({"steps": []})
 
-        assert result is None
+        assert result is not None
+        assert result.get("type") == "error"
+        assert result.get("error_type") == "connection_error"
+        assert "Connection failed" in result.get("error", "")
 
 
 class TestGenerateAgentPatchExternal: