接口修改
This commit is contained in:
1 parent
a35aeee6a2
commit
96d0f4ae73
5 files changed
+367
-122
No files matched your search
@@ -93,6 +93,109 @@ _INTENT_READY_PATTERN = re.compile(
|
||||
)
|
||||
|
||||
|
||||
def _normalize_question(text: str) -> str:
|
||||
"""归一化澄清问题文本,用于"和过往是否重复"的判断。
|
||||
|
||||
LLM 复述时常见模式:
|
||||
- 完全一样的字符串
|
||||
- 仅前后空白、标点、emoji 不同(如多/少一个问号)
|
||||
- 仅大小写差异(中文场景几乎不见,但兼容英文/拼音)
|
||||
所以归一化时统一:小写 + 去除非字母/数字/中文字符 + 折叠空白。
|
||||
Levenshtein/语义相似度等模糊匹配先不做,等观察到误判再迭代。
|
||||
"""
|
||||
if not isinstance(text, str):
|
||||
return ""
|
||||
lowered = text.strip().lower()
|
||||
# 只保留中英文字符与数字,去掉 ?。!?,。"":/、() 等标点 + emoji + 空白。
|
||||
return re.sub(r"[^0-9a-z一-鿿]+", "", lowered)
|
||||
|
||||
|
||||
def _normalize_options(raw: object) -> tuple[str, ...]:
|
||||
"""把 options 拍平成可比较的归一化元组,用于"选项是否和上一轮一致"的判断。"""
|
||||
if raw is None:
|
||||
return ()
|
||||
if isinstance(raw, str):
|
||||
# 偶有模型把 list 序列化成 JSON 字符串发回来。
|
||||
try:
|
||||
raw = json.loads(raw)
|
||||
except (json.JSONDecodeError, TypeError):
|
||||
return (_normalize_question(raw),)
|
||||
if not isinstance(raw, list):
|
||||
return (_normalize_question(str(raw)),)
|
||||
out: list[str] = []
|
||||
for item in raw:
|
||||
if isinstance(item, dict):
|
||||
label = item.get("label") or item.get("title") or item.get("name") or item.get("value") or item.get("id") or ""
|
||||
out.append(_normalize_question(str(label)))
|
||||
else:
|
||||
out.append(_normalize_question(str(item)))
|
||||
# 顺序无关:LLM 偶尔会调换选项顺序,但语义上还是同一组。
|
||||
return tuple(sorted(o for o in out if o))
|
||||
|
||||
|
||||
def _is_repeated_clarification(
|
||||
messages: list[dict[str, Any]],
|
||||
*,
|
||||
new_question: str,
|
||||
new_options: object,
|
||||
new_tool_call_id: str | None = None,
|
||||
) -> bool:
|
||||
"""检测本轮的 ask_clarification 是否在过往轮次问过。
|
||||
|
||||
判定为重复必须同时满足:
|
||||
1. 历史里至少有一次 ``ask_clarification`` 的问题文本 / 选项 与本次归一化相同;
|
||||
2. 用户在那次之后**已经发过消息**(即"已回答过")。
|
||||
没有这条限制会把"模型在同一 run 内多次输出同一 tool_call_chunks"
|
||||
误判成重复,导致首次澄清都吞掉。
|
||||
3. 不是同一个 tool_call(LangGraph 偶有把同一 call 拆成多块返回的情况)。
|
||||
|
||||
传回 True → 上层应把 status 从 ``clarification`` 降级为 ``asking``,
|
||||
避免前端弹同一张卡片(配合 SOUL §2.5 prompt 双层防御)。
|
||||
"""
|
||||
norm_new_q = _normalize_question(new_question)
|
||||
norm_new_opts = _normalize_options(new_options)
|
||||
if not norm_new_q and not norm_new_opts:
|
||||
return False
|
||||
|
||||
seen_match_index: int | None = None
|
||||
for idx, msg in enumerate(messages):
|
||||
if not isinstance(msg, dict):
|
||||
continue
|
||||
if (msg.get("type") or "").lower() not in ("ai", "aimessage", "aimessagechunk"):
|
||||
continue
|
||||
for tc in msg.get("tool_calls") or []:
|
||||
if (tc.get("name") or "").lower() != "ask_clarification":
|
||||
continue
|
||||
if new_tool_call_id and tc.get("id") == new_tool_call_id:
|
||||
# 同一个 tool_call 的不同 chunk,不算重复。
|
||||
continue
|
||||
args = tc.get("args") or {}
|
||||
past_q = _normalize_question(str(args.get("question") or ""))
|
||||
past_opts = _normalize_options(args.get("options"))
|
||||
# 问题文本和选项任一明确重叠就视为重复:
|
||||
# - question 相同(options 可能空)
|
||||
# - options 相同且非空(question 可能被改写)
|
||||
q_match = bool(past_q) and past_q == norm_new_q
|
||||
opt_match = bool(past_opts) and past_opts == norm_new_opts
|
||||
if q_match or opt_match:
|
||||
seen_match_index = idx
|
||||
break
|
||||
if seen_match_index is not None:
|
||||
break
|
||||
|
||||
if seen_match_index is None:
|
||||
return False
|
||||
|
||||
# 校验用户在该次澄清之后是否已经发过 human 消息(= 回答过)。
|
||||
for msg in messages[seen_match_index + 1:]:
|
||||
if not isinstance(msg, dict):
|
||||
continue
|
||||
msg_type = (msg.get("type") or "").lower()
|
||||
if msg_type in ("human", "humanmessage", "user"):
|
||||
return True
|
||||
return False
|
||||
|
||||
|
||||
@router.post("/init")
|
||||
async def init_intent(request: Request, payload: dict = Body(...)) -> dict[str, Any]:
|
||||
"""创建任务理解会话用的空 thread。
|
||||
@@ -264,6 +367,34 @@ async def stream_intent(request: Request, payload: dict = Body(...)) -> Streamin
|
||||
# 比 tool_call 旁的短 preamble 更适合作为气泡正文。
|
||||
follow_up = _find_trailing_ai_text(messages, exclude_text=content)
|
||||
display_content = follow_up or content or question
|
||||
|
||||
# 兜底:模型偶尔会复述上一轮的同一澄清问题(SOUL §2.5 prompt
|
||||
# 已经强约束,但小模型 / 长上下文仍可能漏跟随)。检测到完全
|
||||
# 重复时,把 status 从 clarification 降级为 asking,前端只渲染
|
||||
# 文本气泡不弹卡片,避免用户看到"同样选项又出现一次"。
|
||||
if _is_repeated_clarification(
|
||||
messages,
|
||||
new_question=question,
|
||||
new_options=cargs.get("options"),
|
||||
new_tool_call_id=clarification_call.get("id"),
|
||||
):
|
||||
logger.warning(
|
||||
"intent stream: dropping duplicate ask_clarification "
|
||||
"(question=%r) — already asked & answered earlier in thread",
|
||||
question[:80],
|
||||
)
|
||||
fallback_msg = (
|
||||
display_content
|
||||
or "(系统识别到智能体重复了上一问题,已自动跳过。请补充其他信息继续推进。)"
|
||||
)
|
||||
final_frame: dict[str, Any] = {
|
||||
"status": "asking",
|
||||
"content": fallback_msg,
|
||||
"summary": None,
|
||||
}
|
||||
yield f"data: {json.dumps(final_frame, ensure_ascii=False)}\n\n"
|
||||
return
|
||||
|
||||
final_frame: dict[str, Any] = {
|
||||
"status": "clarification",
|
||||
"content": display_content,
|
||||
|
||||
Reference in new issue
Block a user