agentscope-ai/agentscope · error · RuntimeError

"AgentScope streaming model yielded no chunks."

Error message

"AgentScope streaming model yielded no chunks."

What it means

When the configured ChatModelBase returns an async generator (streaming), the adapter drains it and keeps the last chunk; if the stream yields nothing at all, there is no result to return and a RuntimeError is raised.

Source

Thrown at src/agentscope/middleware/_longterm_memory/_mem0/_agentscope_adapter.py:165

async def _await_chat(
    model: ChatModelBase,
    messages: list[Msg],
    tools: list[dict] | None,
) -> "ChatResponse":
    """Call the AgentScope chat model, handling both streaming and
    non-streaming returns."""
    result = await model(messages, tools=tools)
    # Streaming model — drain the generator and keep the final chunk,
    # which carries the complete content per AgentScope's streaming
    # contract. ``isinstance`` (not ``hasattr``) — Pydantic BaseModel
    # raises KeyError instead of AttributeError on missing dunder
    # attrs, which ``hasattr`` does not catch.
    if isinstance(result, AsyncGenerator):
        last = None
        async for chunk in result:
            last = chunk
        if last is None:
            raise RuntimeError(
                "AgentScope streaming model yielded no chunks.",
            )
        return last
    return result


def _convert_messages_to_agentscope(
    messages: list[dict[str, str]],
) -> list[Msg]:
    """mem0 hands us OpenAI-style ``[{"role", "content"}, ...]`` dicts;
    AgentScope wants ``Msg`` objects."""
    out: list[Msg] = []
    for m in messages:
        role = m.get("role")
        content = m.get("content", "")
        if role == "system":
            out.append(SystemMsg(name="system", content=content))
        elif role == "user":

View on GitHub (pinned to e90f1c7592)

Solutions

1. Test the model directly with a real request to confirm it streams chunks
2. If mocking, make the async generator yield at least one chunk
3. Check provider API key/quota if real streams terminate empty

Example fix

// before
async def fake_stream(*a, **k):
    return
    yield
// after
async def fake_stream(*a, **k):
    yield ChatResponse(text='ok')

try:
    result = llm.generate_response(msgs)
except RuntimeError as e:
    if 'yielded no chunks' in str(e):
        result = llm.generate_response(msgs)  # one retry on empty stream
    else:
        raise

When it happens

Trigger: Attaching a streaming AgentScope model that immediately completes without emitting chunks (e.g. stub model in tests, provider error that closes the stream silently).

Common situations: Unit tests with mocked streaming models that return empty async generators; provider/network edge cases where the stream closes before any chunk arrives.

Related errors

• "AgentScope embedding model returned no embeddings."
• Failed to get the completed response from model {model_name}
• One or more tool calls raised an exception
• Input validation failed for tool '{tool_call.name}': {e.mess
• Invalid permission decision behavior: {decision.behavior}

AI-assisted analysis of agentscope-ai/agentscope@e90f1c7592 (2026-08-28). Data as JSON: /api/errors/45d6c1512bec5f48. Report an issue: GitHub.