datawhalechina/hello-agents · error · AgentException

不支持的任务类型: {task_type}

Error message

不支持的任务类型: {task_type}

What it means

Dispatch error in CoachAgent.run: task_type is matched against the literal set {'explain','polish','mimic','suggest'}; anything else reaches the else-branch raise. Combined with the required-fields check, valid coach tasks must carry task_type in that exact lowercase set — 'Explain', 'summarize', or 'rewrite' all fail here.

Source

Thrown at Co-creation-projects/Apricity-InnocoreAI/agents/coach.py:52

        
        try:
            user_id = input_data["user_id"]
            task_type = input_data["task_type"]  # explain, polish, mimic, suggest
            content = input_data["content"]
            context = input_data.get("context", {})
            
            result = None
            
            if task_type == "explain":
                result = await self._handle_explain_task(user_id, content, context)
            elif task_type == "polish":
                result = await self._handle_polish_task(user_id, content, context)
            elif task_type == "mimic":
                result = await self._handle_mimic_task(user_id, content, context)
            elif task_type == "suggest":
                result = await self._handle_suggest_task(user_id, content, context)
            else:
                raise AgentException(f"不支持的任务类型: {task_type}")
            
            self.set_state("completed")
            
            return {
                "status": "success",
                "task_type": task_type,
                "user_id": user_id,
                "result": result,
                "timestamp": datetime.now().isoformat()
            }
            
        except Exception as e:
            self.set_state("error")
            raise AgentException(f"Coach Agent执行失败: {str(e)}")
    
    def get_required_fields(self) -> List[str]:
        """获取必需的输入字段"""
        return ["user_id", "task_type", "content"]

View on GitHub (pinned to 606a07d341)

Solutions

1. Use one of: explain, polish, mimic, suggest (exact lowercase) for task_type.
2. Validate/normalize task_type at the API boundary (strip + lower + membership check) before coach.run.
3. Centralize the enum (Literal['explain','polish','mimic','suggest'] or an Enum) and drive both the dispatch and the API schema from it.
4. When adding a new capability, add both the handler method and the dispatch branch in the same commit.

Example fix

# before
if task_type == "explain": ...
elif task_type == "polish": ...
else:
    raise AgentException(f"不支持的任务类型: {task_type}")

# after — enum-driven dispatch, impossible to desync
from enum import Enum
class CoachTask(str, Enum):
    EXPLAIN = "explain"; POLISH = "polish"; MIMIC = "mimic"; SUGGEST = "suggest"

try:
    handler = getattr(self, f"_handle_{CoachTask(task_type).value}_task")
except ValueError:
    raise AgentException(f"不支持的任务类型: {task_type}; 可选: {[t.value for t in CoachTask]}")
result = await handler(user_id, content, context)

SUPPORTED = {"explain", "polish", "mimic", "suggest"}
task_type = (input_data.get("task_type") or "").strip().lower()
if task_type not in SUPPORTED:
    raise ValueError(f"task_type must be one of {sorted(SUPPORTED)}")

from typing import Literal
CoachTaskType = Literal["explain", "polish", "mimic", "suggest"]

def is_coach_task(v: str) -> bool:
    return v in {"explain", "polish", "mimic", "suggest"}

try:
    result = await coach.run(input_data)
except AgentException as e:
    if "不支持的任务类型" in str(e):
        return 422, {"error": str(e), "supported": [...]}  # client fixable
    raise

When it happens

Trigger: Calling coach.run({'task_type':'summarize',...}) (unsupported), passing uppercase 'EXPLAIN', a typo like 'polishing', or an LLM orchestrator choosing task types outside the advertised enum.

Common situations: Frontend dropdown options not synced with backend enum; adding a new coaching capability in the prompt but not in the if/elif chain; free-text task_type from users passed through unvalidated.

Related errors

• 工具 '{tool_name}' 不存在
• 缺少必需字段: {field}
• 不支持的任务类型: {task['type']}
• 论文不存在: {paper_id}
• Unsupported latency_mode: {latency_mode}

AI-assisted analysis of datawhalechina/hello-agents@606a07d341 (2026-08-14). Data as JSON: /api/errors/4eb53d74192efb84. Report an issue: GitHub.