research(rectification): DeepSeek Flash 抽 33% 对照现行分类器提示词

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。

scripts/research/jev_intent_current.py

@@ -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

scripts/research/jev_intent_probe.py

@@ -20,6 +20,11 @@ ROOT = Path(__file__).resolve().parents[2]
 if str(ROOT) not in sys.path:
     sys.path.insert(0, str(ROOT))
 
+from scripts.research.jev_intent_current import (  # noqa: E402
+    call_current_retry,
+    current_model_id,
+    stratified_sample,
+)
 from scripts.research.jev_intent_questions import (  # noqa: E402
     JEV_MODEL,
     build_state,
@@ -321,7 +326,9 @@ def run_batch(
     workers: int,
     run_id: str,
     cache: dict[str, Any],
+    call_fn=None,
 ) -> None:
+    caller = call_fn or call_jev_retry
     pending = []
     for sample in samples:
         key = f"{run_id}:{sample['id']}"
@@ -333,7 +340,7 @@ def run_batch(
         return
     print(f"{run_id}: {len(pending)} calls, {len(samples) - len(pending)} cached", flush=True)
     with ThreadPoolExecutor(max_workers=workers) as pool:
-        futures = {pool.submit(call_jev_retry, sample): sample for sample in pending}
+        futures = {pool.submit(caller, sample): sample for sample in pending}
         done = 0
         for future in as_completed(futures):
             sample = futures[future]
@@ -416,19 +423,22 @@ def write_markdown(report: Mapping[str, Any]) -> None:
             f"{m['no_vs_unsure']} | {pct(cons)} | {ms(m['median_ms'])} | {ms(m['p95_ms'])} | "
             f"{(m['mean_input_tokens'] or 0):.0f} |"
         )
+    source_a_m = report["metrics"].get("source_a")
+    if source_a_m:
+        acc = source_a_m.get("answer_class_acc")
+        acc_txt = "—" if acc is None else f"{acc:.1%}"
+        lines += [
+            "",
+            f"来源 A（测试夹具，n={source_a_m['n']}）intent {source_a_m['intent_acc']:.1%}，answer_class {acc_txt}，高置信错误 {source_a_m['high_conf_error_rate']:.1%}。",
+        ]
     lines += [
         "",
         "## 现行模型对照",
         "",
     ]
-    source_a_m = report["metrics"].get("source_a")
-    if source_a_m:
-        lines += [
-            "",
-            f"来源 A（测试夹具，n={source_a_m['n']}）intent {source_a_m['intent_acc']:.1%}，answer_class {source_a_m['answer_class_acc'] or 0:.1%}，高置信错误 {source_a_m['high_conf_error_rate']:.1%}。",
-        ]
     if report["meta"].get("current_model"):
-        lines.append(f"模型：`{report['meta']['current_model']}`。")
+        note = report["meta"].get("current_model_note") or ""
+        lines.append(f"模型：`{report['meta']['current_model']}`。{note}")
         lines.append("")
         lines.append("| 层 | n | intent | answer_class | dated | 自洽率 | 中位 ms |")
         lines.append("| --- | ---: | ---: | ---: | ---: | ---: | ---: |")
@@ -437,10 +447,30 @@ def write_markdown(report: Mapping[str, Any]) -> None:
             cons = (report["metrics"].get("current_self_consistency") or {}).get(layer)
             def pct(value: float | None) -> str:
                 return "—" if value is None else f"{value:.1%}"
+            def ms(value: float | None) -> str:
+                return "—" if value is None else f"{value:.0f}"
             lines.append(
                 f"| {layer} | {m.get('n', 0)} | {pct(m.get('intent_acc'))} | {pct(m.get('answer_class_acc'))} | "
-                f"{pct(m.get('dated_acc'))} | {pct(cons)} | {m.get('median_ms') or 0:.0f} |"
+                f"{pct(m.get('dated_acc'))} | {pct(cons)} | {ms(m.get('median_ms'))} |"
             )
+        paired = report["metrics"].get("paired_sample") or {}
+        if paired:
+            lines.append("")
+            lines.append("同一样本上 Jev vs 现行（相对门槛用这一表）：")
+            lines.append("")
+            lines.append("| 层 | n | Jev intent | 现行 intent | 差（Jev−现行） | 门槛现行−3pp |")
+            lines.append("| --- | ---: | ---: | ---: | ---: | ---: |")
+            for layer in ("choice", "collect", "none"):
+                cell = paired.get(layer) or {}
+                def pct(value: float | None) -> str:
+                    return "—" if value is None else f"{value:.1%}"
+                jev = cell.get("jev_intent")
+                cur = cell.get("current_intent")
+                delta = None if jev is None or cur is None else jev - cur
+                gate = None if cur is None else cur - 0.03
+                lines.append(
+                    f"| {layer} | {cell.get('n', 0)} | {pct(jev)} | {pct(cur)} | {pct(delta)} | {pct(gate)} |"
+                )
     else:
         lines.append(report["meta"].get("current_model_note") or "未跑现行模型。")
     lines += [
@@ -513,16 +543,34 @@ def decide_verdict(report: dict[str, Any]) -> dict[str, str]:
     if high_err > 0.03:
         absolute_fail.append(f"高置信错误率 {high_err:.1%} > 3%")
     if not recall_ok:
-        absolute_fail.append(f"低置信召回 {low_recall} < 60%（错了却仍高置信）")
+        recall_txt = " / ".join(f"{v:.1%}" for v in low_recall)
+        absolute_fail.append(f"低置信召回 {recall_txt} < 60%（错了却仍高置信）")
     if choice_class is not None and choice_class < 0.80:
         absolute_fail.append(f"点选题 answer_class 准确率 {choice_class:.1%}（写库字段）")
+    paired = report["metrics"].get("paired_sample") or {}
+    relative_note = ""
+    if paired:
+        bits = []
+        for layer in ("choice", "collect", "none"):
+            cell = paired.get(layer) or {}
+            jev = cell.get("jev_intent")
+            cur = cell.get("current_intent")
+            if jev is None or cur is None:
+                continue
+            ok = round(jev * 100, 1) >= round((cur - 0.03) * 100, 1)
+            bits.append(
+                f"{layer} Jev {jev:.1%} vs 现行 {cur:.1%}（门槛 {cur-0.03:.1%}，{'过' if ok else '未过'}）"
+            )
+        if bits:
+            relative_note = " 相对 −3pp（同一样本）：" + "；".join(bits) + "。"
     if absolute_fail:
         return {
             "verdict": "不可接",
             "reason": (
                 "来源 C 上 Jev 的绝对门槛未过：" + "；".join(absolute_fail) + "。"
                 + represent
-                + (" 现行模型对照未跑，相对 −3pp 门槛无法计算。" if not current else "")
+                + relative_note
+                + (" 现行模型对照未跑，相对 −3pp 门槛无法计算。" if not current and not paired else "")
             ),
             "if_connect": (
                 "不接。现行分类器继续用会话选定的贵模型。"
@@ -530,7 +578,8 @@ def decide_verdict(report: dict[str, Any]) -> dict[str, str]:
                 f"曲线上 θ={theta} 时高置信错误仍未清零。"
             ),
         }
-    if not current:
+    paired = report["metrics"].get("paired_sample") or {}
+    if not current and not paired:
         return {
             "verdict": "缺数据",
             "reason": (
@@ -545,11 +594,16 @@ def decide_verdict(report: dict[str, Any]) -> dict[str, str]:
         }
     gaps = []
     for layer in ("choice", "collect", "none"):
-        jev = layers[layer]["intent_acc"]
-        cur = (current.get(layer) or {}).get("intent_acc")
+        cell = paired.get(layer) or {}
+        jev = cell.get("jev_intent")
+        cur = cell.get("current_intent")
+        if jev is None:
+            jev = layers[layer]["intent_acc"]
+        if cur is None:
+            cur = (current.get(layer) or {}).get("intent_acc")
         if cur is None:
             continue
-        gaps.append((layer, jev, cur, jev - (cur - 0.03)))
+        gaps.append((layer, jev, cur, round(jev * 100, 1) - round((cur - 0.03) * 100, 1)))
     failed = [g for g in gaps if g[3] < 0]
     if failed:
         return {
@@ -564,38 +618,130 @@ def decide_verdict(report: dict[str, Any]) -> dict[str, str]:
     }
 
 
+def _merge_report_preds(samples: list[dict[str, Any]]) -> None:
+    if not REPORT_JSON.is_file():
+        return
+    try:
+        existing = json.loads(REPORT_JSON.read_text(encoding="utf-8"))
+    except json.JSONDecodeError:
+        return
+    by_id = {row.get("id"): row for row in existing.get("rows") or [] if row.get("id")}
+    for sample in samples:
+        prior = by_id.get(sample.get("id")) or {}
+        for key in ("jev_1", "jev_2", "current_1", "current_2"):
+            if key not in sample and prior.get(key):
+                sample[key] = prior[key]
+
+
+def paired_layer_metrics(rows: Sequence[Mapping[str, Any]]) -> dict[str, Any]:
+    out: dict[str, Any] = {}
+    for layer in ("choice", "collect", "none"):
+        subset = [
+            row for row in rows
+            if row.get("source") == "C"
+            and row.get("layer") == layer
+            and row.get("current_1")
+            and not (row.get("current_1") or {}).get("unavailable")
+        ]
+        if not subset:
+            out[layer] = {"n": 0, "jev_intent": None, "current_intent": None}
+            continue
+        jev = layer_metrics(subset, pred_key="jev_1")
+        cur = layer_metrics(subset, pred_key="current_1")
+        out[layer] = {
+            "n": len(subset),
+            "jev_intent": jev["intent_acc"],
+            "current_intent": cur["intent_acc"],
+            "jev_answer_class": jev["answer_class_acc"],
+            "current_answer_class": cur["answer_class_acc"],
+        }
+    return out
+
+
 def main(argv: Sequence[str] | None = None) -> int:
     parser = argparse.ArgumentParser()
     parser.add_argument("--workers", type=int, default=8)
     parser.add_argument("--limit", type=int, default=0)
     parser.add_argument("--skip-second", action="store_true")
     parser.add_argument("--second-fraction", type=float, default=1.0)
+    parser.add_argument("--current-only", action="store_true")
+    parser.add_argument("--sample-fraction", type=float, default=1.0)
+    parser.add_argument("--sample-seed", type=int, default=20260919)
     args = parser.parse_args(argv)
-    if not os.environ.get("TYPESAFE_API_KEY"):
+    if not args.current_only and not os.environ.get("TYPESAFE_API_KEY"):
         print("TYPESAFE_API_KEY missing", file=sys.stderr)
         return 2
+    if args.current_only and not os.environ.get("DEEPSEEK_API_KEY"):
+        print("DEEPSEEK_API_KEY missing", file=sys.stderr)
+        return 2
     synthetic = load_jsonl(SAMPLES_DIR / "synthetic.jsonl")
     simulated = load_jsonl(SAMPLES_DIR / "simulated.jsonl")
     source_b = load_jsonl(CACHE_DIR / "source_b.jsonl")
     samples = [row for row in synthetic + simulated if row.get("source") in {"A", "C"}]
     if args.limit:
         samples = samples[: args.limit]
+    _merge_report_preds(samples)
     cache = load_cache()
+    current_sample: list[dict[str, Any]] = []
     try:
-        run_batch(samples, workers=args.workers, run_id="jev_1", cache=cache)
-        save_cache(cache)
-        second = samples
-        if args.skip_second:
-            second = []
-        elif args.second_fraction < 1:
-            n = max(1, int(len(samples) * args.second_fraction))
-            second = [row for row in samples if row.get("source") == "C"][:n]
-        if second:
-            run_batch(second, workers=args.workers, run_id="jev_2", cache=cache)
+        if not args.current_only:
+            run_batch(samples, workers=args.workers, run_id="jev_1", cache=cache)
             save_cache(cache)
-        if source_b:
-            run_batch(source_b, workers=args.workers, run_id="jev_1", cache=cache)
+            second = samples
+            if args.skip_second:
+                second = []
+            elif args.second_fraction < 1:
+                n = max(1, int(len(samples) * args.second_fraction))
+                second = [row for row in samples if row.get("source") == "C"][:n]
+            if second:
+                run_batch(second, workers=args.workers, run_id="jev_2", cache=cache)
+                save_cache(cache)
+            if source_b:
+                run_batch(source_b, workers=args.workers, run_id="jev_1", cache=cache)
+                save_cache(cache)
+        source_c_rows = [row for row in samples if row.get("source") == "C"]
+        if args.current_only or os.environ.get("DEEPSEEK_API_KEY"):
+            if args.sample_fraction < 1:
+                current_sample = stratified_sample(
+                    source_c_rows, fraction=args.sample_fraction, seed=args.sample_seed,
+                )
+                current_sample.extend(row for row in samples if row.get("source") == "A")
+            else:
+                current_sample = list(samples)
+            run_batch(
+                current_sample, workers=args.workers, run_id="current_1",
+                cache=cache, call_fn=call_current_retry,
+            )
             save_cache(cache)
+            second_current = current_sample
+            if args.skip_second:
+                second_current = []
+            elif args.second_fraction < 1:
+                second_current = stratified_sample(
+                    [row for row in current_sample if row.get("source") == "C"],
+                    fraction=args.second_fraction,
+                    seed=args.sample_seed + 1,
+                )
+            if second_current:
+                run_batch(
+                    second_current, workers=args.workers, run_id="current_2",
+                    cache=cache, call_fn=call_current_retry,
+                )
+                save_cache(cache)
+            by_id = {row["id"]: row for row in current_sample}
+            for row in second_current:
+                dest = by_id.setdefault(row["id"], row)
+                if row.get("current_1"):
+                    dest["current_1"] = row["current_1"]
+                if row.get("current_2"):
+                    dest["current_2"] = row["current_2"]
+            for sample in samples:
+                extra = by_id.get(sample["id"])
+                if extra:
+                    if extra.get("current_1"):
+                        sample["current_1"] = extra["current_1"]
+                    if extra.get("current_2"):
+                        sample["current_2"] = extra["current_2"]
     finally:
         save_cache(cache)
 
@@ -634,16 +780,41 @@ def main(argv: Sequence[str] | None = None) -> int:
             "reviewer": "agent-rule-v1",
             "sha256": sha,
             "source_b_n": len(source_b),
-            "current_model": None,
+            "current_model": current_model_id() if any(row.get("current_1") for row in samples) else None,
             "current_model_note": (
-                "本机无会话模型目录凭据（模型 key 在数据库加密配置里）。"
-                "现行 `classifyRectificationTurnIntent` 对照未跑。"
+                (
+                    f"DeepSeek Flash 顶现行 `classifyRectificationTurnIntent` 提示词；"
+                    f"来源 C 分层随机 {args.sample_fraction:.0%}（seed {args.sample_seed}），"
+                    f"来源 A 全量。不是线上会话模型。"
+                    if any(row.get("current_1") for row in samples)
+                    else (
+                        "本机无会话模型目录凭据（模型 key 在数据库加密配置里）。"
+                        "现行 `classifyRectificationTurnIntent` 对照未跑。"
+                    )
+                )
             ),
         },
         "metrics": {
             "jev_by_layer": jev_metrics,
             "jev_self_consistency": jev_cons,
-            "current_by_layer": None,
+            "current_by_layer": (
+                {layer: layer_metrics(
+                    [row for row in samples if row.get("source") == "C" and row.get("layer") == layer and row.get("current_1")],
+                    pred_key="current_1",
+                )
+                 for layer in ("choice", "collect", "none")}
+                if any(row.get("current_1") for row in samples) else None
+            ),
+            "current_self_consistency": (
+                {layer: self_consistency(
+                    [row for row in samples if row.get("source") == "C" and row.get("layer") == layer and row.get("current_2")],
+                    "current_1",
+                    "current_2",
+                )
+                 for layer in ("choice", "collect", "none")}
+                if any(row.get("current_2") for row in samples) else None
+            ),
+            "paired_sample": paired_layer_metrics(samples) if any(row.get("current_1") for row in samples) else {},
             "source_a": source_a_metrics,
             "source_b": source_b_metrics,
             "representativeness": {"note": represent_note},