sgl-project/sglang · error · ValueError

unsupported composite_input type: {input_type}

Error message

unsupported composite_input type: {input_type}

What it means

During composite_input parsing, the declared input_type is not one the parser branch handles (camera control types or 'prompt'), so it refuses to interpret the item.

Source

Thrown at python/sglang/multimodal_gen/runtime/entrypoints/openai/realtime/adapters/lingbot_world_realtime_adapter.py:247

                )
            )
        return f"kind=composite_input, inputs={input_logs}"

    def _parse_composite_input_item(
        self,
        state: LingBotWorldRealtimeState,
        input_type: str,
        payload: Any,
        event_id: int | None,
    ) -> Any:
        if input_type == "camera_actions":
            return state.parse_camera_control_event_payload(
                payload,
                event_id=event_id,
            )
        if input_type == "prompt":
            return self._validate_prompt_payload(payload)
        raise ValueError(f"unsupported composite_input type: {input_type}")

    def _ingest_parsed_composite_input_item(
        self,
        state: LingBotWorldRealtimeState,
        input_type: str,
        parsed_payload: Any,
        event_id: int | None,
    ) -> str:
        if input_type == "camera_actions":
            return state.receive_parsed_camera_control_event_payload(
                parsed_payload,
                event_id=event_id,
            )
        if input_type == "prompt":
            state.receive_prompt(parsed_payload, event_id=event_id)
            return f"kind=prompt, prompt_len={len(parsed_payload)}"
        raise ValueError(f"unsupported composite_input type: {input_type}")

View on GitHub (pinned to 0132848349)

Solutions

1. Restrict input_types entries to 'prompt' and the camera control types the state supports
2. Check the adapter's parse branch for the exact accepted names
3. Upgrade or patch the adapter if you need a new modality, don't just send it

Example fix

// before
{input_types: ["text"], text: "hi"}
// after
{input_types: ["prompt"], prompt: "hi"}

SUPPORTED = {'prompt'} | CAMERA_TYPES
payload['input_types'] = [t for t in payload['input_types'] if t in SUPPORTED]

def is_supported_type(t: str) -> bool: return t == 'prompt' or t in CAMERA_TYPES

except ValueError as e: if 'unsupported composite_input type' in str(e): drop the item and resend

When it happens

Trigger: input_types: ["image"] or any undeclared type name — the per-item parser (_parse_composite_input_item) has no branch for it.

Common situations: Client assuming arbitrary modality names are supported; adapter version lacking a newer input type; typos in type names like 'promt'.

Related errors

• composite_input event payload must be a map
• composite_input event payload requires non-empty input_types
• composite_input input_types must contain non-empty strings
• composite_input event payload requires {input_type}
• prompt event payload must be a string

AI-assisted analysis of sgl-project/sglang@0132848349 (2026-08-28). Data as JSON: /api/errors/fd37cbbbcbcb4d07. Report an issue: GitHub.