langgenius/dify · error · BadRequest

Agent App only supports streaming response mode.

Error message

Agent App only supports streaming response mode.

What it means

Error "Agent App only supports streaming response mode." thrown in langgenius/dify.

Source

Thrown at api/controllers/console/app/completion.py:76

from services.app_task_service import AppTaskService
from services.errors.llm import InvokeRateLimitError

logger = logging.getLogger(__name__)


@runtime_checkable
class _ClosableStream(Protocol):
    def close(self) -> None: ...


def _resolve_debugger_chat_streaming(
    *, app_mode: AppMode, response_mode: str, response_mode_provided: bool = True
) -> bool:
    """Agent App runtime is SSE-only until backend blocking runs are supported."""
    if app_mode != AppMode.AGENT:
        return response_mode != "blocking"
    if response_mode_provided and response_mode == "blocking":
        raise BadRequest("Agent App only supports streaming response mode.")
    return True


class BaseMessagePayload(BaseModel):
    inputs: dict[str, Any]
    # Agent Apps (AppMode.AGENT) derive their model + prompt from the bound Agent
    # Soul, so no override ``model_config`` is sent; chat / agent-chat / completion
    # debugging still pass it. Optional here, required in practice by those modes
    # downstream when their config is built from args.
    model_config_data: dict[str, Any] = Field(
        default_factory=dict,
        alias="model_config",
    )
    files: list[Any] | None = Field(
        default=None,
        description="Uploaded files",
    )
    response_mode: Literal["blocking", "streaming"] = Field(default="blocking", description="Response mode")

View on GitHub (pinned to ef8544b173)

When it happens

Trigger: Thrown at api/controllers/console/app/completion.py:76 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of langgenius/dify@ef8544b173 (2026-08-12). Data as JSON: /api/errors/009dd01724e075da. Report an issue: GitHub.