mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-07-27 16:37:55 +00:00
47b0f604f4
* feat(frontend): add structured human input cards for ask_clarification Implement a reusable Human Input Card flow for ask_clarification while keeping the existing text fallback for older clients and IM channels. Backend: - Add structured ToolMessage.artifact.human_input payloads for clarification requests. - Preserve ToolMessage.content as the readable Markdown/text fallback. - Normalize clarification options from native lists, JSON strings, plain strings, mixed scalar values, None, and missing options. - Derive input_mode as choice_with_other when options exist, otherwise free_text. - Keep disable_clarification non-interactive behavior as a plain ToolMessage with no human_input artifact. - Cover artifact persistence and Gateway message metadata preservation in tests. Frontend: - Add human input protocol types, runtime guards, extractors, response builders, and thread-state helpers. - Add reusable HumanInputCard with option buttons, free-text input, pending, read-only, disabled, and answered states. - Render structured clarification cards from artifact.human_input, with Markdown fallback for malformed or legacy tool messages. - Preserve line breaks in structured question/context/option text. - Hide submitted clarification bridge messages from the chat UI via additional_kwargs.hide_from_ui. - Send structured human_input_response metadata through the fourth sendMessage options argument, preserving run context in the third argument. - Wire submissions for normal chats, custom agent chats, agent bootstrap chats, and sidecar chats. - Derive answered state from raw thread.messages so hidden replies still update the original card. - Clear pending state when the hidden reply arrives, dispatch is dropped, or a later async stream failure appears on thread.error. * perf(frontend): optimize HumanInputCard UI interactions - Support Enter key to submit text input (Shift+Enter for newline) - Render question and context fields as Markdown instead of plain text - Replace deprecated FormEventHandler type with structural typing * test(frontend): add unit test cover optimize HumanInputCard UI interactions * feat(frontend): disabled chatbox when has new human-input-card * fix(style): lint error fix * fix: sanitize hidden human input replies - Preserve IME composition safety for human input card Enter submits - Treat hidden human input responses as genuine user messages for sanitization - Keep hidden card replies in memory filtering while excluding malformed/internal hidden messages - Add regression coverage for card IME handling and hidden reply sanitization * fix: tighten human input response validation - Reject empty hidden human input response values - Remove invalid list ARIA role from human input card options - Add backend coverage for empty response payloads --------- Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
77 lines
2.2 KiB
Python
77 lines
2.2 KiB
Python
"""Structured human-input message metadata helpers."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from collections.abc import Mapping
|
|
from typing import Literal, TypedDict
|
|
|
|
HUMAN_INPUT_RESPONSE_KEY = "human_input_response"
|
|
|
|
|
|
class HumanInputTextResponse(TypedDict):
|
|
version: Literal[1]
|
|
kind: Literal["human_input_response"]
|
|
source: str
|
|
request_id: str
|
|
response_kind: Literal["text"]
|
|
value: str
|
|
|
|
|
|
class HumanInputOptionResponse(TypedDict):
|
|
version: Literal[1]
|
|
kind: Literal["human_input_response"]
|
|
source: str
|
|
request_id: str
|
|
response_kind: Literal["option"]
|
|
option_id: str
|
|
value: str
|
|
|
|
|
|
HumanInputResponse = HumanInputTextResponse | HumanInputOptionResponse
|
|
|
|
|
|
def _non_empty_string(value: object) -> str | None:
|
|
return value if isinstance(value, str) and value.strip() else None
|
|
|
|
|
|
def read_human_input_response(additional_kwargs: Mapping[str, object] | None) -> HumanInputResponse | None:
|
|
"""Read a valid human-input response payload from message metadata."""
|
|
if not additional_kwargs:
|
|
return None
|
|
raw = additional_kwargs.get(HUMAN_INPUT_RESPONSE_KEY)
|
|
if not isinstance(raw, Mapping):
|
|
return None
|
|
if raw.get("version") != 1 or raw.get("kind") != "human_input_response":
|
|
return None
|
|
|
|
source = _non_empty_string(raw.get("source"))
|
|
request_id = _non_empty_string(raw.get("request_id"))
|
|
value = _non_empty_string(raw.get("value"))
|
|
if source is None or request_id is None or value is None:
|
|
return None
|
|
|
|
response_kind = raw.get("response_kind")
|
|
if response_kind == "text":
|
|
return {
|
|
"version": 1,
|
|
"kind": "human_input_response",
|
|
"source": source,
|
|
"request_id": request_id,
|
|
"response_kind": "text",
|
|
"value": value,
|
|
}
|
|
if response_kind == "option":
|
|
option_id = _non_empty_string(raw.get("option_id"))
|
|
if option_id is None:
|
|
return None
|
|
return {
|
|
"version": 1,
|
|
"kind": "human_input_response",
|
|
"source": source,
|
|
"request_id": request_id,
|
|
"response_kind": "option",
|
|
"option_id": option_id,
|
|
"value": value,
|
|
}
|
|
return None
|