research(rectification): DeepSeek Flash 抽 33% 对照现行分类器提示词
Independent Staging Quality Gate / validate (push) Successful in 10m16s
Independent Staging Quality Gate / publish (push) Successful in 3m57s

来源 B 仍为 0。Flash 套生产提示词,采集题相对门槛未过。结论仍不可接。
This commit is contained in:
jesse-ux
2026-09-19 09:45:29 +08:00
parent fde541c2ca
commit d6fc4fb8b3
7 changed files with 8610 additions and 527 deletions
+183
View File
@@ -0,0 +1,183 @@
"""Stand-in for classifyRectificationTurnIntent using an OpenAI-compatible chat API.
Copies the production instruction strings from turn-intent-classifier.ts.
Does not change production. Reads DEEPSEEK_API_KEY from the environment only.
"""
from __future__ import annotations
import json
import os
import time
import urllib.error
import urllib.request
from typing import Any, Mapping, Sequence
from scripts.research.jev_intent_questions import build_state, enforce_combo
# Keep these byte-for-byte with frontend/src/lib/rectification-agentic/v9/turn-intent-classifier.ts
CHOICE_INSTRUCTIONS = """你只做当前生时校正问题的意图分类,不回答用户,也不修改任何状态。
结合当前问题和动态选项判断用户是在回答当前问题、提供新的带时间经历、要求停止整个校正、询问结果,还是语义不清。
若是在回答当前问题,answer_class 必须使用某个选项提供的 answer_class;否则 answer_class 必须为 null。
has_new_dated_event 仅在用户同一句里除了回答当前问题之外,还提供了新的、带大概时间的经历时为 true;单纯的否定或单纯的选项回答必须为 false。
若同一句话既回答了当前问题又补充了新的带时间经历,intent 仍为 answer_current_focus,has_new_dated_event 为 true。
“当前方面没有、那段时间没有变化”通常是回答当前问题,不是停止整个流程;只有用户明确要求停止整个校正时才分类为 stop_rectification。
不要按 A/B/C/D 的位置猜语义,只按选项 label 与 answer_class 判断。"""
COLLECT_INSTRUCTIONS = """你只做当前生时校正采集题的意图分类,不回答用户,也不修改任何状态。
当前问题没有点选选项。判断用户是在回答当前采集题、提供新的带时间经历、要求停止整个校正、询问结果,还是语义不清。
「没有、没发生过、这方面没什么」→ intent 为 answer_current_focus,answer_class 为 no(该方面没有事,本次不再问)。
「记不清、不记得、忘了、想不起来、以后再说」→ intent 为 answer_current_focus,answer_class 为 unsure(先放着,以后可补)。
用户用带大概年月的经历直接回答当前采集题 → intent 为 answer_current_focus,answer_class 为 yes(程度较弱时为 weak_yes),has_new_dated_event 为 false。
不要把「没有」或「记不清」标成 yes。若既没有否定、也没有说记不清、也没有给出带年月经历,intent 为 unclear,answer_class 必须为 null。
若用户只在补充带时间的经历、并没有回答当前采集题,intent 为 provide_new_evidence,answer_class 必须为 null。
has_new_dated_event 仅在用户同一句里除了回答当前采集题之外,还提供了新的、带大概时间的经历时为 true;单纯的否定或记不清必须为 false。
若同一句话既明确否定当前采集题又补充了新的带时间经历,intent 仍为 answer_current_focus 且 answer_class 为 no,不要改成 provide_new_evidence。
“当前方面没有”通常是回答当前采集题,不是停止整个流程;只有用户明确要求停止整个校正时才分类为 stop_rectification。
不要按关键词表或正则猜测,只根据当前问题与用户这句话的语义分类。"""
JSON_SCHEMA_HINT = (
"只输出一个 JSON 对象,不要解释。字段:"
'{"intent":"answer_current_focus|provide_new_evidence|stop_rectification|ask_about_result|unclear",'
'"answer_class":"yes"|"weak_yes"|"no"|"unsure"|null,'
'"has_new_dated_event":true|false}'
)
DEFAULT_MODEL = "deepseek-flash"
DEFAULT_BASE = "https://api.deepseek.com"
def current_model_id() -> str:
return os.environ.get("DEEPSEEK_MODEL") or DEFAULT_MODEL
def _instructions(sample: Mapping[str, Any]) -> str:
focus = sample.get("focus") if isinstance(sample.get("focus"), dict) else {}
options = list(focus.get("options") or [])
return CHOICE_INSTRUCTIONS if options else COLLECT_INSTRUCTIONS
def _parse_content(text: str) -> dict[str, Any]:
raw = (text or "").strip()
if raw.startswith("```"):
raw = raw.strip("`")
if raw.lower().startswith("json"):
raw = raw[4:]
raw = raw.strip()
start = raw.find("{")
end = raw.rfind("}")
if start < 0 or end <= start:
raise ValueError("no_json_object")
payload = json.loads(raw[start : end + 1])
if not isinstance(payload, dict):
raise ValueError("json_not_object")
return payload
def call_current(sample: Mapping[str, Any], *, timeout: float = 60.0) -> dict[str, Any]:
api_key = os.environ.get("DEEPSEEK_API_KEY") or ""
if not api_key:
raise RuntimeError("DEEPSEEK_API_KEY missing")
base = (os.environ.get("DEEPSEEK_BASE_URL") or DEFAULT_BASE).rstrip("/")
model = current_model_id()
body = {
"model": model,
"messages": [
{"role": "system", "content": _instructions(sample) + "\n" + JSON_SCHEMA_HINT},
{"role": "user", "content": json.dumps(build_state(sample), ensure_ascii=False)},
],
"temperature": 0,
"max_tokens": 256,
"thinking": {"type": "disabled"},
"response_format": {"type": "json_object"},
"stream": False,
}
request = urllib.request.Request(
f"{base}/chat/completions",
data=json.dumps(body).encode("utf-8"),
headers={
"Content-Type": "application/json",
"Authorization": f"Bearer {api_key}",
},
method="POST",
)
started = time.perf_counter()
with urllib.request.urlopen(request, timeout=timeout) as response:
payload = json.loads(response.read().decode("utf-8"))
elapsed_ms = int((time.perf_counter() - started) * 1000)
content = (((payload.get("choices") or [{}])[0].get("message") or {}).get("content")) or ""
parsed = _parse_content(content)
combo = enforce_combo(
parsed.get("intent"),
parsed.get("answer_class"),
parsed.get("has_new_dated_event"),
)
usage = payload.get("usage") or {}
return {
"ok": True,
"unavailable": False,
"model": payload.get("model") or model,
"intent": combo["intent"],
"answer_class": combo["answer_class"],
"has_new_dated_event": combo["has_new_dated_event"],
"confidence": None,
"raw": parsed,
"input_tokens": usage.get("prompt_tokens") or usage.get("input_tokens"),
"output_tokens": usage.get("completion_tokens") or usage.get("output_tokens"),
"elapsed_ms": elapsed_ms,
}
def call_current_retry(sample: Mapping[str, Any], *, retries: int = 4) -> dict[str, Any]:
last_error = ""
delay = 1.0
for _attempt in range(retries):
try:
return call_current(sample)
except urllib.error.HTTPError as exc:
last_error = f"HTTP{exc.code}"
if exc.code in {429, 500, 502, 503, 529}:
time.sleep(delay)
delay = min(delay * 2, 16)
continue
break
except Exception as exc: # noqa: BLE001
last_error = type(exc).__name__
time.sleep(delay)
delay = min(delay * 2, 16)
return {
"ok": False,
"unavailable": True,
"model": current_model_id(),
"intent": None,
"answer_class": None,
"has_new_dated_event": None,
"confidence": None,
"raw": None,
"input_tokens": None,
"output_tokens": None,
"elapsed_ms": None,
"error": last_error,
}
def stratified_sample(
rows: Sequence[Mapping[str, Any]],
*,
fraction: float,
seed: int,
) -> list[dict[str, Any]]:
import random
rng = random.Random(seed)
picked: list[dict[str, Any]] = []
by_layer: dict[str, list[Mapping[str, Any]]] = {"choice": [], "collect": [], "none": []}
for row in rows:
layer = str(row.get("layer") or "none")
by_layer.setdefault(layer, []).append(row)
for layer, group in by_layer.items():
items = list(group)
rng.shuffle(items)
n = max(1, int(round(len(items) * fraction))) if items else 0
picked.extend(dict(item) for item in items[:n])
return picked