diff --git a/app/harness/video_split_cli.py b/app/harness/video_split_cli.py
index 6e1c6fe..1a66813 100644
--- a/app/harness/video_split_cli.py
+++ b/app/harness/video_split_cli.py
@@ -245,7 +245,9 @@ def _build_redis_cache(settings: Any) -> Any | None:
         return None
 
 
-def build_diagnosis_deps(*, harness_db: Path, concurrency: int) -> DiagnosisDeps:
+def build_diagnosis_deps(
+    *, harness_db: Path, 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，
@@ -255,12 +257,16 @@ def build_diagnosis_deps(*, harness_db: Path, concurrency: int) -> DiagnosisDeps
     参数:
         harness_db: harness.db 路径（诊断读预测 + 信号落库同库）。
         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
+            信号以错误模型指纹落库，破坏可复现 / resume / 口径隔离，故此处 fail loud。
 
     返回:
         DiagnosisDeps 冻结依赖束。
 
     异常:
-        SystemExit: .env 缺 search LLM 凭证（model / base_url / api_key 任一为空）。
+        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）。
     """
     from adapters.breaker import CircuitBreaker
     from adapters.llm import GovernedLLMClient
@@ -276,6 +282,13 @@ def build_diagnosis_deps(*, harness_db: Path, concurrency: int) -> DiagnosisDeps
             "诊断 LLM 凭证缺失：.env 需配置 SEARCH_LLM_MODEL / SEARCH_LLM_BASE_URL / "
             "SEARCH_LLM_API_KEY（P5 fail loud，不静默兜底）"
         )
+    if expected_model != settings.search_llm_model:
+        raise SystemExit(
+            "诊断模型指纹漂移：config.diag.model="
+            f"{expected_model!r} 与 .env SEARCH_LLM_MODEL={settings.search_llm_model!r} "
+            "不一致；指纹里的 model 必须等于实际诊断所用 model（P5 fail loud，"
+            "请对齐 config/video_split.yaml diag.model 与 .env SEARCH_LLM_MODEL）"
+        )
 
     telemetry_db = Path("logs/telemetry.db")
     telemetry_db.parent.mkdir(parents=True, exist_ok=True)
@@ -537,7 +550,9 @@ def _execute_real(config: VideoSplitConfig, fingerprint: str, args: argparse.Nam
         raise SystemExit(f"harness.db 不存在: {harness_db}（P5 fail loud）")
     wrong_ids = load_diagnosable_wrong_ids(harness_db, config.baseline_run_id)
     questions = load_questions_by_id(questions_dir)
-    deps = build_diagnosis_deps(harness_db=harness_db, concurrency=args.concurrency)
+    deps = build_diagnosis_deps(
+        harness_db=harness_db, concurrency=args.concurrency, expected_model=config.model
+    )
 
     from adapters.baseline_diagnosis_store import SqliteDiagnosisSignalStore
 
diff --git a/config/video_split.yaml b/config/video_split.yaml
index 127788b..b6f143c 100644
--- a/config/video_split.yaml
+++ b/config/video_split.yaml
@@ -21,5 +21,5 @@ video_split:
 
 diag:                          # 诊断口径指纹三分量（隔离不同诊断配置的信号，参与主键）
   prompt_version: diagnose_v1  # 诊断 prompt 版本标识（换 prompt 即换指纹，旧记录不被覆盖）
-  model: deepseek-v4-pro       # 执行诊断的模型名（与 .env JUDGE_LLM_MODEL 对齐）
+  model: deepseek-v4-pro       # 执行诊断的模型名（必须与 .env SEARCH_LLM_MODEL 一致，CLI 会 fail loud 校验）
   # code_version 由 build_video_split.sh 注入 git 短 SHA，不写死在此（随代码变动）
diff --git a/tests/unit/test_video_split_cli.py b/tests/unit/test_video_split_cli.py
index b54a292..ef7447b 100644
--- a/tests/unit/test_video_split_cli.py
+++ b/tests/unit/test_video_split_cli.py
@@ -161,6 +161,42 @@ def test_dry_run_computes_fingerprint_without_llm(monkeypatch, tmp_path, capsys)
     assert not (tmp_path / "_dry_run_signals.db").exists()
 
 
+def test_build_diagnosis_deps_model_mismatch_fails_loud(monkeypatch, tmp_path):
+    """config.diag.model 与 .env SEARCH_LLM_MODEL 不一致 → fail loud（指纹漂移防护）。"""
+
+    class _FakeSettings:
+        search_llm_model = "actual-model-in-env"
+        search_llm_base_url = "https://api.example"
+        search_llm_api_key = "sk-xxx"
+
+    monkeypatch.setattr(cli, "_DiagLLMSettings", lambda: _FakeSettings())
+    with pytest.raises(SystemExit) as exc:
+        cli.build_diagnosis_deps(
+            harness_db=tmp_path / "h.db",
+            concurrency=2,
+            expected_model="deepseek-v4-pro",  # 与 env 不一致
+        )
+    # 报错须同时暴露两个值，便于人对齐
+    msg = str(exc.value)
+    assert "deepseek-v4-pro" in msg
+    assert "actual-model-in-env" in msg
+
+
+def test_build_diagnosis_deps_missing_credentials_fails_loud(monkeypatch, tmp_path):
+    """.env 缺 search LLM 凭证 → fail loud（先于模型一致性校验）。"""
+
+    class _EmptySettings:
+        search_llm_model = ""
+        search_llm_base_url = ""
+        search_llm_api_key = ""
+
+    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"
+        )
+
+
 def test_git_short_sha_nonempty():
     """仓库内 git_short_sha 返回非空短 SHA。"""
     sha = cli.git_short_sha()