fix: load real tree_data for offline diagnosis (video_split_cli)

app/harness/video_split_cli.py

@@ -18,7 +18,8 @@
       诊断配置的信号；换 prompt / 模型 / 代码实现即换指纹，旧信号不被覆盖。
     - 真实依赖组装参考 app/harness/runner.py::_run_diagnosis：GovernedLLMClient
       (search llm, thinking=True) + RunLogImpl(harness.db) + VersionedSkillStore +
-      DiagnosePrompts(项目根 prompts/) + tree_data={}（由诊断管线内部按需加载）。
+      DiagnosePrompts(项目根 prompts/) + tree_data 按 wrong_ids 涉及 video 预加载
+      （store/videos/<vid>/tree.json 展平）。
     - 缺 .env / config 关键项一律 fail loud（P5），绝不静默兜底。
     - `--dry-run` 用假 deps 跑通两阶段 wiring 不真调 LLM，打印将执行的步骤 + 指纹，
       用于校验装配正确性（对齐 CLAUDE.md §2.5 smoke test）。
@@ -65,6 +66,7 @@ _INFRA_STOP_REASONS: frozenset[str] = frozenset({"error", "parse_error"})
 _DEFAULT_HARNESS_DB = Path("workspaces/default/harness.db")
 _DEFAULT_QUESTIONS_DIR = Path("store/questions/benchmarks/Video-MME")
 _DEFAULT_OUT_DIR = Path("workspaces/video-split")
+_DEFAULT_STORE_DIR = Path("store")  # tree.json 在 store/videos/<vid>/
 
 
 # ---------------------------------------------------------------------------
@@ -260,16 +262,24 @@ def _build_redis_cache(settings: Any) -> Any | None:
 
 
 def build_diagnosis_deps(
-    *, harness_db: Path, concurrency: int, expected_model: str
+    *,
+    harness_db: Path,
+    store_dir: Path,
+    video_ids: list[str],
+    concurrency: int,
+    expected_model: str,
 ) -> DiagnosisDeps:
     """组装 Phase 1 诊断的真实依赖束（GovernedLLMClient + RunLogImpl + prompts）。
 
     与 runner.py::_run_diagnosis 对齐：search LLM（thinking=True）作诊断 judge，
     RunLogImpl 只读读取 harness.db 的 predictions/traces，VersionedSkillStore 读技能，
-    DiagnosePrompts 从项目根 prompts/ 加载，tree_data={} 由诊断管线内部按需加载。
+    DiagnosePrompts 从项目根 prompts/ 加载，tree_data 按 video_ids 从
+    store/videos/<vid>/tree.json 展平预加载（诊断需真实树，缺失即 fail-loud）。
 
     参数:
         harness_db: harness.db 路径（诊断读预测 + 信号落库同库）。
+        store_dir: store 根目录（含 videos/<vid>/tree.json）。
+        video_ids: wrong_ids 涉及的 video 标识列表（可含重复，内部去重加载树）。
         concurrency: 诊断并发上限。
         expected_model: config.diag.model（诊断口径指纹的模型分量）。必须与 .env
             SEARCH_LLM_MODEL 一致——指纹里的 model 与实际诊断所用 model 不一致会让
@@ -281,6 +291,8 @@ def build_diagnosis_deps(
     异常:
         SystemExit: .env 缺 search LLM 凭证（model / base_url / api_key 任一为空），
             或 config.diag.model 与 .env SEARCH_LLM_MODEL 不一致（指纹漂移防护）。
+        FileNotFoundError / ValueError: video_ids 中任一 video 的 tree.json 缺失或
+            无效（load_tree_data_for_videos fail-loud，诊断需真实树）。
     """
     from adapters.breaker import CircuitBreaker
     from adapters.llm import GovernedLLMClient
@@ -327,12 +339,14 @@ def build_diagnosis_deps(
         retry_base_delay_s=settings.llm_retry_base_delay,
         retry_max_delay_s=settings.llm_retry_max_delay,
     )
+    from app.harness.tree_nodes import load_tree_data_for_videos
+
     return DiagnosisDeps(
         run_log=RunLogImpl(str(harness_db)),
         llm=llm,
         skill_store=VersionedSkillStore(_diagnosis_skills_dir()),
         prompts=_load_diagnose_prompts(),
-        tree_data={},
+        tree_data=load_tree_data_for_videos(store_dir, video_ids),
         concurrency=concurrency,
     )
 
@@ -579,24 +593,30 @@ async def run_pipeline(
 # ---------------------------------------------------------------------------
 
 
-def _resolve_paths(args: argparse.Namespace) -> tuple[Path, Path, Path]:
-    """解析 harness_db / questions_dir / out_dir（CLI 覆盖默认工程路径）。"""
+def _resolve_paths(args: argparse.Namespace) -> tuple[Path, Path, Path, Path]:
+    """解析 harness_db / questions_dir / out_dir / store_dir（CLI 覆盖默认工程路径）。"""
     harness_db = args.harness_db or _DEFAULT_HARNESS_DB
     questions_dir = args.questions_dir or _DEFAULT_QUESTIONS_DIR
     out_dir = args.out_dir or _DEFAULT_OUT_DIR
-    return harness_db, questions_dir, out_dir
+    store_dir = args.store_dir or _DEFAULT_STORE_DIR
+    return harness_db, questions_dir, out_dir, store_dir
 
 
 def _execute_real(config: VideoSplitConfig, fingerprint: str, args: argparse.Namespace) -> None:
     """真实执行两阶段管线：组装真实 deps、读错题、跑诊断 + 冻结切分。"""
-    harness_db, questions_dir, out_dir = _resolve_paths(args)
+    harness_db, questions_dir, out_dir, store_dir = _resolve_paths(args)
     if not harness_db.exists():
         raise SystemExit(f"harness.db 不存在: {harness_db}（P5 fail loud）")
     canonical_preds = load_canonical_predictions(harness_db, config.baseline_run_id)
     wrong_ids = select_diagnosable_wrong_ids(canonical_preds)
     questions = load_questions_by_id(questions_dir)
+    video_ids = [questions[qid].video_id for qid in wrong_ids]
     deps = build_diagnosis_deps(
-        harness_db=harness_db, concurrency=args.concurrency, expected_model=config.model
+        harness_db=harness_db,
+        store_dir=store_dir,
+        video_ids=video_ids,
+        concurrency=args.concurrency,
+        expected_model=config.model,
     )
 
     # generated_at：默认盖真实 UTC now（溯源用），--generated-at 可显式固定以复现（C-2）。
@@ -648,7 +668,7 @@ def _execute_dry_run(config: VideoSplitConfig, fingerprint: str, args: argparse.
     Phase 2 build_split 需真实诊断信号方能冻结，dry-run 不真实冻结，仅打印其计划；
     Phase 1 用空 wrong_ids 走 run_baseline_diagnosis 早返回路径，验证装配可调用而不触 LLM。
     """
-    harness_db, questions_dir, out_dir = _resolve_paths(args)
+    harness_db, questions_dir, out_dir, _store_dir = _resolve_paths(args)
     logger.info("=== dry-run：校验两阶段装配（不真调 LLM / 不冻结产物）===")
     logger.info(
         "诊断口径指纹 diag_fingerprint={} (prompt={} model={})",
@@ -730,6 +750,7 @@ def build_arg_parser() -> argparse.ArgumentParser:
     parser.add_argument("--harness-db", type=Path, default=None, dest="harness_db")
     parser.add_argument("--questions-dir", type=Path, default=None, dest="questions_dir")
     parser.add_argument("--out-dir", type=Path, default=None, dest="out_dir")
+    parser.add_argument("--store-dir", type=Path, default=None, dest="store_dir")
     parser.add_argument(
         "--generated-at",
         type=str,

tests/unit/test_video_split_cli.py

@@ -268,6 +268,8 @@ def test_build_diagnosis_deps_model_mismatch_fails_loud(monkeypatch, tmp_path):
     with pytest.raises(SystemExit) as exc:
         cli.build_diagnosis_deps(
             harness_db=tmp_path / "h.db",
+            store_dir=tmp_path,
+            video_ids=[],
             concurrency=2,
             expected_model="deepseek-v4-pro",  # 与 env 不一致
         )
@@ -288,7 +290,11 @@ def test_build_diagnosis_deps_missing_credentials_fails_loud(monkeypatch, tmp_pa
     monkeypatch.setattr(cli, "_DiagLLMSettings", lambda: _EmptySettings())
     with pytest.raises(SystemExit):
         cli.build_diagnosis_deps(
-            harness_db=tmp_path / "h.db", concurrency=2, expected_model="deepseek-v4-pro"
+            harness_db=tmp_path / "h.db",
+            store_dir=tmp_path,
+            video_ids=[],
+            concurrency=2,
+            expected_model="deepseek-v4-pro",
         )
 
 

tests/unit/test_video_split_cli_tree_inject.py

@@ -0,0 +1,33 @@
+"""离线诊断注入：build_diagnosis_deps 按 video_ids 填充非空 tree_data。"""
+
+from pathlib import Path
+from unittest.mock import patch
+
+from app.harness.video_split_cli import build_diagnosis_deps
+
+
+def test_build_diagnosis_deps_loads_tree_for_videos():
+    with (
+        patch("app.harness.video_split_cli._DiagLLMSettings") as settings_cls,
+        patch("adapters.llm.GovernedLLMClient"),
+        patch("adapters.telemetry.SQLiteTelemetryRecorder"),
+        patch("app.harness.video_split_cli._build_redis_cache", return_value=None),
+    ):
+        s = settings_cls.return_value
+        s.search_llm_model = "deepseek-v4-pro"
+        s.search_llm_base_url = "http://x"
+        s.search_llm_api_key = "k"
+        s.llm_circuit_breaker_threshold = 32
+        s.llm_circuit_breaker_cooldown = 60
+        s.llm_timeout = s.llm_ttft_timeout = s.llm_inter_token_timeout = 60
+        s.llm_max_retries = 1
+        s.llm_retry_base_delay = s.llm_retry_max_delay = 1
+        deps = build_diagnosis_deps(
+            harness_db=Path("workspaces/default/harness.db"),
+            store_dir=Path("store"),
+            video_ids=["0RxMZBLeqRI"],
+            concurrency=1,
+            expected_model="deepseek-v4-pro",
+        )
+    assert "0RxMZBLeqRI" in deps.tree_data
+    assert deps.tree_data["0RxMZBLeqRI"]["nodes"]