From 748a969e0e0dbec0a1760b4227f9938ac2a45d01 Mon Sep 17 00:00:00 2001 From: iomgaa Date: Wed, 15 Jul 2026 22:01:20 -0400 Subject: [PATCH] docs: implementation plan for diagnosis tree_data fix --- research-wiki/graph/edges.json | 12 + research-wiki/index.md | 5 +- research-wiki/log.md | 3 + .../fix-diagnosis-tree-data-link-plan.md | 632 ++++++++++++++++++ 4 files changed, 650 insertions(+), 2 deletions(-) create mode 100644 research-wiki/plans/fix-diagnosis-tree-data-link-plan.md diff --git a/research-wiki/graph/edges.json b/research-wiki/graph/edges.json index a6a0bc5..23ef519 100644 --- a/research-wiki/graph/edges.json +++ b/research-wiki/graph/edges.json @@ -235,6 +235,11 @@ "id": "design:fix-diagnosis-tree-data-link", "label": "修复诊断 tree_data 断链 bug（TRM4→TRM5 迁移 regression）", "type": "design" + }, + { + "id": "plan:fix-diagnosis-tree-data-link-plan", + "label": "实现计划: 修复诊断 tree_data 断链 bug", + "type": "plan" } ], "links": [ @@ -475,6 +480,13 @@ "relation": "refines", "evidence": "修正 error_type/evolution_target 列取值不再坍缩", "added": "2026-07-16T01:31:37.792648+00:00" + }, + { + "source": "plan:fix-diagnosis-tree-data-link-plan", + "target": "design:fix-diagnosis-tree-data-link", + "relation": "implements", + "evidence": "实现修复设计的 5 个 Task", + "added": "2026-07-16T02:01:19.350441+00:00" } ] } \ No newline at end of file diff --git a/research-wiki/index.md b/research-wiki/index.md index 815d39f..907c552 100644 --- a/research-wiki/index.md +++ b/research-wiki/index.md @@ -1,6 +1,6 @@ # Research Wiki 索引 -> 自动生成，更新时间：2026-07-16 01:31 UTC +> 自动生成，更新时间：2026-07-16 02:01 UTC ## design (34) - [2026-07-06-core-agent-adapters-llm-design](designs/2026-07-06-core-agent-adapters-llm-design.md) `design:2026-07-06-core-agent-adapters-llm-design` @@ -50,7 +50,7 @@ - [v3 §9 帧感知抽取机制 — 小样本实证验证结果](findings/2026-07-15-v3-frame-perception-spike-validation.md) `finding:2026-07-15-v3-frame-perception-spike-validation` - [出题范式转变 — 从"生成-打分-过滤"转向"构造优先 + 两正交独立信号"（六篇原文深读）](findings/2026-07-15-question-gen-paradigm-shift-construction-over-filtering.md) `finding:2026-07-15-question-gen-paradigm-shift-construction-over-filtering` -## plan (39) +## plan (40) - [2026-07-06-core-agent-adapters-llm](plans/2026-07-06-core-agent-adapters-llm.md) `plan:2026-07-06-core-agent-adapters-llm` - [2026-07-07-app-harness](plans/2026-07-07-app-harness.md) `plan:2026-07-07-app-harness` - [2026-07-07-core-evolution](plans/2026-07-07-core-evolution.md) `plan:2026-07-07-core-evolution` @@ -85,6 +85,7 @@ - [Spec-2 建树批量并行实现计划](plans/batch-tree-build-plan.md) `plan:batch-tree-build-plan` - [TaskTypeStrategy 框架实现计划 (Plan A)](plans/task-type-strategy-framework.md) `plan:task-type-strategy-framework` - [出题管线 v2 实现计划](plans/2026-07-11-question-gen-v2.md) `plan:2026-07-11-question-gen-v2` +- [实现计划: 修复诊断 tree_data 断链 bug](plans/fix-diagnosis-tree-data-link-plan.md) `plan:fix-diagnosis-tree-data-link-plan` - [建树修复管线三项改造实现计划](plans/tree-repair-resilience.md) `plan:tree-repair-resilience` - [建树模块竖切实现计划](plans/tree-module-vertical-slice.md) `plan:tree-module-vertical-slice` - [结果驱动的视频级切分实现计划](plans/results-driven-video-split-plan.md) `plan:results-driven-video-split-plan` diff --git a/research-wiki/log.md b/research-wiki/log.md index 9d16572..ac7aadb 100644 --- a/research-wiki/log.md +++ b/research-wiki/log.md @@ -118,3 +118,6 @@ - [2026-07-16 01:31 UTC] 新增边: design:fix-diagnosis-tree-data-link --informs--> design:results-driven-video-split - [2026-07-16 01:31 UTC] 新增边: design:fix-diagnosis-tree-data-link --refines--> schema:baseline-diagnosis - [2026-07-16 01:31 UTC] 重建索引: 97 篇页面 +- [2026-07-16 01:49 UTC] 新增 plan: 实现计划: 修复诊断 tree_data 断链 bug (plan:fix-diagnosis-tree-data-link-plan) +- [2026-07-16 02:01 UTC] 新增边: plan:fix-diagnosis-tree-data-link-plan --implements--> design:fix-diagnosis-tree-data-link +- [2026-07-16 02:01 UTC] 重建索引: 98 篇页面 diff --git a/research-wiki/plans/fix-diagnosis-tree-data-link-plan.md b/research-wiki/plans/fix-diagnosis-tree-data-link-plan.md new file mode 100644 index 0000000..73cb012 --- /dev/null +++ b/research-wiki/plans/fix-diagnosis-tree-data-link-plan.md @@ -0,0 +1,632 @@ +--- +type: plan +node_id: plan:fix-diagnosis-tree-data-link-plan +title: "实现计划: 修复诊断 tree_data 断链 bug" +date: 2026-07-15 +--- + +# 修复诊断 tree_data 断链 bug Implementation Plan + +> **For agentic workers:** REQUIRED SUB-SKILL: Use subagent-driven-development to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking. + +**Goal:** 接通 TRM4→TRM5 迁移时断掉的诊断树加载环，让 `evaluate_span` 拿到真实 ground_truth、error_type 归因不再坍缩。 + +**Architecture:** app 层新增树展平器（递归遍历 tree.json 的嵌套 roots → 扁平 `{"nodes":{id:{card,level,time_range}}}`），在离线诊断（`video_split_cli`）与训练循环（`runner`）两个注入点按诊断涉及的 video 加载填充 `tree_data`；core 侧把 `run_diagnosis` 的静默回退改为缺失即 fail-loud。core 只消费 dict，不碰归因瀑布（算法保真 §4.7#7）。 + +**Tech Stack:** Python 3.11、pytest、loguru、asyncio；参考 TRM4 `core/harness/diagnose.py:1677` 的 tree_cache 语义。 + +--- + +## 设计来源 +`research-wiki/designs/fix-diagnosis-tree-data-link.md`（已含 Codex 审查修订）。 + +## 文件结构映射 + +| 文件 | 动作 | 责任 | +|------|------|------| +| `app/harness/tree_nodes.py` | 新建 | 树展平器：`load_tree_nodes` + `load_tree_data_for_videos` | +| `core/evolution/diagnose.py` | 改 `:2144-2145` | 视频未覆盖即 raise（fail-loud，唯一 core 改动） | +| `app/harness/video_split_cli.py` | 改 `build_diagnosis_deps`(`:262-337`) + `_execute_real`(`:590-600`) | 离线注入：wrong_ids→video 加载填充 tree_data | +| `app/harness/runner.py` | 改 `_run_diagnosis`(`:2163-2187`) | 训练注入：question_ids→video 加载注入 | +| `tests/unit/test_tree_nodes.py` | 新建 | 展平器单测 | +| `tests/integration/test_baseline_diagnosis.py` | 改 `:99` | 更新传 `tree_data={}` 的用例为真实/伪造树 | +| `tests/integration/test_diagnosis_tree_link.py` | 新建 | ground_truth 接通 + 依赖方向 | + +## 关键代码事实（Codex 已核验） +- 仅 `L1Node` 有 `to_dict`（`app/tree/index.py:260`）；L2/L3 为其内部闭包；输出无 `level`、L3 用 `timestamp` 无 `time_range` → **不走对象层，直接遍历 json**。 +- node_id 累积式 `..._L1_000_L2_000_L3_000` → level **按遍历深度赋值**，不解析 node_id。 +- `GeneratedQuestion.video_id: str`（`core/types.py:60`）；`load_questions_by_id(dir) -> dict[str, GeneratedQuestion]`（`video_split_cli.py:443`）。 +- `run_diagnosis` else 分支已支持 `{video_id: {...}}` 形态（`diagnose.py:2068-2074`）。 +- `diagnose.py:2145` 的 `td = ...get(vid,{})` 在 `:2148` try 之前 → 在此处 raise **不会**被 `:2159` 的 `except ValueError`（judge 降级）吞。 +- store 根 = `Path("store")`，tree.json 在 `store/videos//tree.json`（与 `factory.py:85` 一致）。 + +--- + +### Task 1: 树展平器 `app/harness/tree_nodes.py` + +**Files:** +- Create: `app/harness/tree_nodes.py` +- Test: `tests/unit/test_tree_nodes.py` + +- [ ] **Step 1: 写失败测试（正确性 + level + fail-loud）** + +```python +# tests/unit/test_tree_nodes.py +"""树展平器单测：用真实 store/videos/0RxMZBLeqRI/tree.json 验证展平正确性与 fail-loud。""" +import json +from pathlib import Path + +import pytest + +from app.harness.tree_nodes import load_tree_data_for_videos, load_tree_nodes + +_STORE = Path("store") +_VID = "0RxMZBLeqRI" # 真实样本，111 节点 + + +def _recursive_count(tree_json: dict) -> int: + def walk(n: dict) -> int: + return 1 + sum(walk(c) for c in (n.get("children") or [])) + return sum(walk(r) for r in tree_json["roots"]) + + +def test_load_tree_nodes_flattens_all_nodes(): + result = load_tree_nodes(_STORE, _VID) + assert set(result.keys()) == {"nodes"} + nodes = result["nodes"] + raw = json.loads((_STORE / "videos" / _VID / "tree.json").read_text(encoding="utf-8")) + assert len(nodes) == _recursive_count(raw) + sample = next(iter(nodes.values())) + assert set(sample.keys()) == {"card", "level", "time_range"} + assert isinstance(sample["card"], dict) + + +def test_level_assigned_by_depth_not_node_id(): + nodes = load_tree_nodes(_STORE, _VID)["nodes"] + l1_id = f"{_VID}_L1_000" + l3_id = f"{_VID}_L1_000_L2_000_L3_000" + assert nodes[l1_id]["level"] == 1 + assert nodes[l3_id]["level"] == 3 # 若按 node_id 首个 _L\d_ 会误判成 1 + + +def test_missing_tree_raises_file_not_found(): + with pytest.raises(FileNotFoundError): + load_tree_nodes(_STORE, "__no_such_video__") + + +def test_empty_roots_raises_value_error(tmp_path): + vdir = tmp_path / "videos" / "vX" + vdir.mkdir(parents=True) + (vdir / "tree.json").write_text(json.dumps({"metadata": {}, "roots": []}), encoding="utf-8") + with pytest.raises(ValueError): + load_tree_nodes(tmp_path, "vX") + + +def test_load_for_videos_dedups(): + data = load_tree_data_for_videos(_STORE, [_VID, _VID]) + assert set(data.keys()) == {_VID} + assert data[_VID]["nodes"] +``` + +- [ ] **Step 2: 运行确认失败** + +Run: `conda run -n Video-Tree-TRM pytest tests/unit/test_tree_nodes.py -q` +Expected: FAIL（`ModuleNotFoundError: No module named 'app.harness.tree_nodes'`） + +- [ ] **Step 3: 实现展平器** + +```python +# app/harness/tree_nodes.py +"""诊断侧树读取适配：把嵌套 tree.json 展平成诊断消费的扁平 nodes dict。 + +诊断编排（core/evolution/diagnose.py）期望 tree_data 形如 +{"nodes": {node_id: {card, level, time_range}}}，但 TRM5 建树产物 +store/videos//tree.json 是嵌套 {"metadata","roots":[...]}。本模块递归展平， +接通 TRM4→TRM5 迁移时断掉的 ground_truth 加载环。 + +不走 TreeIndex 对象层：仅 L1Node 有 to_dict（app/tree/index.py:260），L2/L3 为其内部闭包， +且 to_dict 输出无 level、L3 用 timestamp 无 time_range。直接遍历 json 更省且零改建树模块。 +""" + +from __future__ import annotations + +import json +from pathlib import Path +from typing import Any + + +def load_tree_nodes(store_dir: Path, video_id: str) -> dict[str, Any]: + """加载单视频 tree.json 并展平成扁平 nodes dict。 + + 参数: + store_dir: store 根目录（含 videos//tree.json）。 + video_id: 视频标识。 + + 返回: + {"nodes": {node_id: {"card": dict, "level": int, "time_range": list}}}。 + + 异常: + FileNotFoundError: tree.json 不存在（沿用 factory.py fail-loud 先例）。 + ValueError: 树无有效 roots、节点缺 id、或展平后 nodes 为空。 + + 关键实现: + level 由遍历深度赋值（root=1/child=2/孙=3），不解析 node_id——node_id 累积式 + （..._L1_..._L2_..._L3_）用正则首匹配会把 L2/L3 误判成 1。 + L3 无 time_range，用 timestamp 合成 [t, t]。 + """ + tree_path = store_dir / "videos" / video_id / "tree.json" + if not tree_path.exists(): + raise FileNotFoundError(f"树索引文件不存在: {tree_path}（诊断需真实树，P5 fail loud）") + tree = json.loads(tree_path.read_text(encoding="utf-8")) + roots = tree.get("roots") + if not isinstance(roots, list) or not roots: + raise ValueError(f"树无有效 roots: {tree_path}") + + nodes: dict[str, Any] = {} + + def _walk(node: dict[str, Any], level: int) -> None: + node_id = node.get("id") + if not isinstance(node_id, str) or not node_id: + raise ValueError(f"节点缺 id: {tree_path}") + time_range = node.get("time_range") + if time_range is None: + ts = node.get("timestamp") + time_range = [ts, ts] if ts is not None else [0, 0] + nodes[node_id] = { + "card": node.get("card", {}), + "level": level, + "time_range": time_range, + } + for child in node.get("children", []) or []: + _walk(child, level + 1) + + for root in roots: + _walk(root, 1) + + if not nodes: + raise ValueError(f"展平后 nodes 为空: {tree_path}") + return {"nodes": nodes} + + +def load_tree_data_for_videos(store_dir: Path, video_ids: list[str]) -> dict[str, Any]: + """按一组 video_id 去重加载展平树，供诊断按 video 注入。 + + 参数: + store_dir: store 根目录。 + video_ids: 视频标识列表（可含重复，内部按首次出现顺序去重）。 + + 返回: + {video_id: {"nodes": {...}}}。 + + 异常: + 同 load_tree_nodes（任一视频树缺失/无效即 fail-loud）。 + """ + return {vid: load_tree_nodes(store_dir, vid) for vid in dict.fromkeys(video_ids)} +``` + +- [ ] **Step 4: 运行确认通过** + +Run: `conda run -n Video-Tree-TRM pytest tests/unit/test_tree_nodes.py -q` +Expected: PASS（5 passed） + +- [ ] **Step 5: Commit** + +```bash +git add app/harness/tree_nodes.py tests/unit/test_tree_nodes.py +git commit -m "feat: add tree.json flattener for diagnosis ground_truth" +``` + +--- + +### Task 2: core 视频覆盖 fail-loud（`diagnose.py`） + +**Files:** +- Modify: `core/evolution/diagnose.py:2144-2145` +- Modify: `tests/integration/test_baseline_diagnosis.py:99`（更新受影响用例） + +- [ ] **Step 1: 写失败测试（缺树 video → raise，不降级）** + +在 `tests/integration/test_baseline_diagnosis.py` 追加： + +```python +@pytest.mark.asyncio +async def test_run_diagnosis_raises_when_video_tree_missing(): + """诊断视频未被 tree_data 覆盖时 fail-loud（不静默回退、不走 judge 降级）。""" + from core.evolution.diagnose import run_diagnosis + + q = _make_one_wrong_question(video_id="vMISS", question_id="vMISS-1") + with pytest.raises(ValueError, match="诊断视频树未覆盖"): + await run_diagnosis( + run_id="infer_adhoc", + questions=[q], + tree_data={"vOTHER": {"nodes": {}}}, # 故意不含 vMISS + llm=_FakeLLM(), + run_log=_fake_run_log_with_one_wrong(q), + skill_store=_FakeSkillStore(), + prompts=_fake_diagnose_prompts(), + concurrency=1, + question_ids=["vMISS-1"], + ) +``` + +> helper（`_make_one_wrong_question` / `_fake_run_log_with_one_wrong` / `_FakeLLM` / `_FakeSkillStore` / `_fake_diagnose_prompts`）：复用该测试文件已有的伪造装配；若无 `_make_one_wrong_question`，构造 `GeneratedQuestion(question_id="vMISS-1", video_id="vMISS", task_type="Object Reasoning", ...)` 并让 run_log 返回一条 `correct=0` 且带非空 `steps_json`（含一个 `view_node` 步）的 prediction。 + +- [ ] **Step 2: 运行确认失败** + +Run: `conda run -n Video-Tree-TRM pytest tests/integration/test_baseline_diagnosis.py::test_run_diagnosis_raises_when_video_tree_missing -q` +Expected: FAIL（当前静默回退 `{}`，不抛异常） + +- [ ] **Step 3: 改 core 加 fail-loud** + +`core/evolution/diagnose.py` 的 `_process_question`，把 `:2144-2145` 的： + +```python + vid = prediction.get("video_id", "") + td = tree_data_by_video.get(vid, {}) +``` + +改为（位置在 `:2148` 的 `try` 之前，故不被 `:2159` 的 `except ValueError` 吞）： + +```python + vid = prediction.get("video_id", "") + if vid not in tree_data_by_video: + # P5 fail-loud：诊断需真实树，调用方须为每个诊断视频加载 tree_data； + # 静默回退空树会让 ground_truth 恒空、error_type 归因坍缩（本次修复的根因）。 + raise ValueError( + f"诊断视频树未覆盖: video_id={vid!r} 不在注入的 tree_data 中" + "（调用方须为每个诊断视频加载树，P5 fail loud）" + ) + td = tree_data_by_video[vid] +``` + +- [ ] **Step 4: 更新既有传 `tree_data={}` 的三处用例** + +`tests/integration/test_baseline_diagnosis.py` 有**三处** `tree_data={}`（`:99` / `:224` / `:311`，形参分别在 `:66` / `:197` / `:283`）。逐处判断： + +- 若该用例**真诊断题**（`wrong_ids` 非空、进 `run_diagnosis`）→ 改为覆盖其诊断 video 的伪造树： + ```python + tree_data={"<该用例的 video_id>": {"nodes": {"": {"card": {}, "level": 1, "time_range": [0, 0]}}}}, + ``` + （`video_id`/`node_id` 填该用例 prediction 实际用的值。） +- 若该用例期望**"无题诊断"早返回**（`wrong_ids=[]`，不进 `run_diagnosis`）→ `tree_data={}` 可保留，并在该用例加一行注释说明豁免原因。 + +逐处核对：读每个用例构造的 prediction 是否 `correct=0` 且被诊断——是则改树，否则注释豁免。 + +- [ ] **Step 4b: 全仓兜底扫描其它 `tree_data={}` 调用点** + +Run: `conda run -n Video-Tree-TRM grep -rn "tree_data={}\|tree_data = {}" tests/ app/` +对每个命中判断：进 `run_diagnosis` 且诊断非空题的必须提供覆盖树；dry-run `fake_deps`（`video_split_cli.py` 内，`wrong_ids=[]` 早返回）豁免。确保 core fail-loud 不误伤既有用例。 + +- [ ] **Step 5: 运行确认通过** + +Run: `conda run -n Video-Tree-TRM pytest tests/integration/test_baseline_diagnosis.py -q` +Expected: PASS + +- [ ] **Step 6: Commit** + +```bash +git add core/evolution/diagnose.py tests/integration/test_baseline_diagnosis.py +git commit -m "fix: fail loud when diagnosis video tree not covered (algo #7 input)" +``` + +--- + +### Task 3: 离线注入（`video_split_cli.py`） + +**Files:** +- Modify: `app/harness/video_split_cli.py`（新增 `_DEFAULT_STORE_DIR` + `--store-dir` CLI、`_resolve_paths` 返回 store_dir、改 `build_diagnosis_deps` 签名与 tree_data、`_execute_real` 传 store_dir/video_ids、删模块顶层假注释 `:19-21`） +- Modify: `tests/unit/test_video_split_cli.py:269-273` 与 `:290-292`（两处旧调用补 `store_dir`/`video_ids`，否则改签名后先抛 TypeError 而非期望的 SystemExit） +- Test: `tests/unit/test_video_split_cli_tree_inject.py`（新建） + +- [ ] **Step 1: 写失败测试（build_diagnosis_deps 填充真实树）** + +```python +# tests/unit/test_video_split_cli_tree_inject.py +"""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 S, \ + patch("adapters.llm.GovernedLLMClient"), \ + patch("adapters.telemetry.SQLiteTelemetryRecorder"), \ + patch("app.harness.video_split_cli._build_redis_cache", return_value=None): + s = S.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"] +``` + +> `GovernedLLMClient` / `SQLiteTelemetryRecorder` 在 `build_diagnosis_deps` 内是函数级 import，patch 其源模块（`adapters.llm` / `adapters.telemetry`）。测试目的仅验证 `deps.tree_data` 被真实树填充；若装配桩不足以走到 return，可进一步 patch `RunLogImpl`/`VersionedSkillStore`。 + +- [ ] **Step 2: 运行确认失败** + +Run: `conda run -n Video-Tree-TRM pytest tests/unit/test_video_split_cli_tree_inject.py -q` +Expected: FAIL（当前 `build_diagnosis_deps` 无 `store_dir`/`video_ids` 参数 → `TypeError`） + +- [ ] **Step 3: 加常量 + `--store-dir` + `_resolve_paths` + 删模块假注释 + 改签名 + 填 tree_data** + +(a) `app/harness/video_split_cli.py` 路径常量区（`:65-67` 附近）新增： + +```python +_DEFAULT_STORE_DIR = Path("store") # tree.json 在 store/videos// +``` + +(b) argparse（`:732` `--out-dir` 之后）新增： + +```python + parser.add_argument("--store-dir", type=Path, default=None, dest="store_dir") +``` + +(c) `_resolve_paths`（`:582-587`）改为返回 4 元组（含 store_dir）： + +```python +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 + store_dir = args.store_dir or _DEFAULT_STORE_DIR + return harness_db, questions_dir, out_dir, store_dir +``` + +(d) 删模块顶层假注释：`app/harness/video_split_cli.py:19-21` 把 “+ tree_data={}（由诊断管线内部按需加载）” 改为 “+ tree_data 按 wrong_ids 涉及 video 预加载（store/videos//tree.json 展平）”。 + +(e) `build_diagnosis_deps` 签名（`:262-264`）改为： + +```python +def build_diagnosis_deps( + *, + harness_db: Path, + store_dir: Path, + video_ids: list[str], + concurrency: int, + expected_model: str, +) -> DiagnosisDeps: +``` + +函数末尾 `return DiagnosisDeps(...)`（`:330-337`）改为按 video 加载（并删 docstring 里"tree_data={} 由诊断管线内部按需加载"假注释）： + +```python + 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=load_tree_data_for_videos(store_dir, video_ids), + concurrency=concurrency, + ) +``` + +- [ ] **Step 4: `_execute_real` 解包 store_dir 并算 video_ids 传入** + +`app/harness/video_split_cli.py:592`（解包改 4 元组）+ `:595-600`： + +```python + 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, + store_dir=store_dir, + video_ids=video_ids, + concurrency=args.concurrency, + expected_model=config.model, + ) +``` + +> 全仓其它 `_resolve_paths(args)` 解包处（如 dry-run `_execute_dry` 路径若有）同步改 4 元组解包，避免 `ValueError: too many values to unpack`。先 `grep -n "_resolve_paths(args)" app/harness/video_split_cli.py` 逐处核对。 + +- [ ] **Step 5: 更新受签名影响的既有单测** + +`tests/unit/test_video_split_cli.py:269-273` 与 `:290-292` 两处 `cli.build_diagnosis_deps(...)` 调用补必填参数（这俩测试验的是**凭证/模型漂移 fail-loud（SystemExit）**，该校验在 tree_data 加载之前，故 `video_ids` 传空即可）： + +```python + cli.build_diagnosis_deps( + harness_db=tmp_path / "h.db", + store_dir=tmp_path, + video_ids=[], + concurrency=2, + expected_model="deepseek-v4-pro", + ) +``` + +（两处调用都照此加 `store_dir=tmp_path, video_ids=[]`。） + +- [ ] **Step 6: 运行确认通过 + 回归** + +Run: `conda run -n Video-Tree-TRM pytest tests/unit/test_video_split_cli_tree_inject.py tests/unit/test_video_split_cli.py tests/unit/test_generate_questions.py -q` +Expected: PASS + +- [ ] **Step 7: Commit** + +```bash +git add app/harness/video_split_cli.py tests/unit/test_video_split_cli_tree_inject.py tests/unit/test_video_split_cli.py +git commit -m "fix: load real tree_data for offline diagnosis (video_split_cli)" +``` + +--- + +### Task 4: 训练注入（`runner._run_diagnosis`） + +**Files:** +- Modify: `app/harness/runner.py:2163-2187` +- Test: `tests/unit/test_runner_diag_tree_inject.py` + +- [ ] **Step 1: 写失败测试（_run_diagnosis 注入非空树）** + +```python +# tests/unit/test_runner_diag_tree_inject.py +"""训练循环诊断注入：_run_diagnosis 按 batch question_ids 加载真实树注入 run_diagnosis。""" +from unittest.mock import AsyncMock, patch + +import pytest + + +@pytest.mark.asyncio +async def test_run_diagnosis_injects_tree_data(runner_with_real_store): + """question_ids 对应的 video 树被加载并作为 tree_data 传入 run_diagnosis。""" + captured = {} + + async def _fake_run_diagnosis(**kwargs): + captured["tree_data"] = kwargs["tree_data"] + return _empty_diagnosis_result() + + with patch("core.evolution.diagnose.run_diagnosis", new=AsyncMock(side_effect=_fake_run_diagnosis)): + await runner_with_real_store._run_diagnosis("infer_adhoc", question_ids=["604-2"]) + + assert "0RxMZBLeqRI" in captured["tree_data"] # 604-2 属于 0RxMZBLeqRI + assert captured["tree_data"]["0RxMZBLeqRI"]["nodes"] +``` + +> `runner_with_real_store` fixture：构造 `self._config.store_dir="store"`、`self._paths.questions_dir` 指向含 604-2 的真实 benchmark 的 runner（复用该测试目录已有 runner helper；若无，最小构造使 `load_benchmark` 能取到 604-2）。`_empty_diagnosis_result()`：返回 `DiagnosisResult` 空壳（error_attributions=[]、infra=[]、degraded=[]）。`_run_diagnosis` 内 `run_diagnosis` 为函数级 import，patch 其源符号 `core.evolution.diagnose.run_diagnosis`。 + +- [ ] **Step 2: 运行确认失败** + +Run: `conda run -n Video-Tree-TRM pytest tests/unit/test_runner_diag_tree_inject.py -q` +Expected: FAIL（当前 `tree_data={}` → captured 不含 `0RxMZBLeqRI`） + +- [ ] **Step 3: 改 `_run_diagnosis` 注入树** + +`app/harness/runner.py:2172-2187`，在 `questions = load_benchmark(...)` 后、`run_diagnosis(...)` 调用处： + +```python + questions = load_benchmark(self._paths.questions_dir) + run_log = RunLogImpl(str(self._paths.db_path)) + skill_store = VersionedSkillStore(self._paths.skills_dir) + diagnose_prompts = self._load_diagnose_prompts() + + from app.harness.tree_nodes import load_tree_data_for_videos + + if question_ids is not None: + qid_set = set(question_ids) + video_ids = [q.video_id for q in questions if q.question_id in qid_set] + else: + video_ids = [q.video_id for q in questions] + tree_data = load_tree_data_for_videos(Path(self._config.store_dir), video_ids) + + return await run_diagnosis( + run_id=run_id, + questions=questions, + tree_data=tree_data, + llm=self._llm, + run_log=run_log, + skill_store=skill_store, + prompts=diagnose_prompts, + concurrency=self._config.concurrency, + question_ids=question_ids, + ) +``` + +（删 `tree_data={}, # tree_data 由诊断管线内部按需加载` 假注释；确认文件顶部已 `from pathlib import Path`，否则补 import。） + +- [ ] **Step 4: 运行确认通过** + +Run: `conda run -n Video-Tree-TRM pytest tests/unit/test_runner_diag_tree_inject.py -q` +Expected: PASS + +- [ ] **Step 5: Commit** + +```bash +git add app/harness/runner.py tests/unit/test_runner_diag_tree_inject.py +git commit -m "fix: load real tree_data for training-loop diagnosis (runner)" +``` + +--- + +### Task 5: 集成验证 ground_truth 接通 + 依赖方向 + +**Files:** +- Create: `tests/integration/test_diagnosis_tree_link.py` + +- [ ] **Step 1: 写 integration 测试（ground_truth 非空 + 依赖方向）** + +```python +# tests/integration/test_diagnosis_tree_link.py +"""集成验证：真实树注入后 evaluate_span 收到非空 ground_truth；core 不依赖 app。""" +from pathlib import Path + +from app.harness.tree_nodes import load_tree_nodes +from core.evolution.diagnose import _get_ground_truth_for_trace + + +def test_ground_truth_nonempty_with_real_tree(): + """对真实 T2 样本 604-2（video 0RxMZBLeqRI）的 view_node 调用，ground_truth 非空。""" + td = load_tree_nodes(Path("store"), "0RxMZBLeqRI") + node_id = "0RxMZBLeqRI_L1_000" # 该视频真实存在的节点 + gt = _get_ground_truth_for_trace(td, "view_node", {"node_id": node_id}) + assert gt and gt != "{}" # 拿到该节点 card 的 JSON，非空 + + +def test_core_diagnose_does_not_import_app(): + """算法保真 + 依赖方向：core/evolution/diagnose.py 不 import app。""" + src = Path("core/evolution/diagnose.py").read_text(encoding="utf-8") + assert "import app." not in src + assert "from app." not in src +``` + +- [ ] **Step 2: 运行确认通过** + +Run: `conda run -n Video-Tree-TRM pytest tests/integration/test_diagnosis_tree_link.py -q` +Expected: PASS + +- [ ] **Step 3: 全量回归** + +Run: `conda run -n Video-Tree-TRM pytest tests/ -q` +Expected: PASS（无回归；诊断相关用例因 core fail-loud 需补树的已在 Task 2 Step 4 处理） + +- [ ] **Step 4: Commit** + +```bash +git add tests/integration/test_diagnosis_tree_link.py +git commit -m "test: integration for diagnosis tree_data link + core dep direction" +``` + +--- + +## 重跑与重冻衔接（代码计划外的运行步骤） + +代码合入后 git short SHA 变 → `diag_fingerprint` 变 → 需全量重跑： + +1. **重跑诊断 + 重冻切分**（一条命令走完两阶段）： + `CUDA_VISIBLE_DEVICES=0 CONCURRENCY=12 bash scripts/build_video_split.sh` +2. **实测校验 tier**：重跑后查新 fingerprint 的 `baseline_diagnosis`，确认 `T2≈82 / T1≈152`（缓存命中预期）；偏差需归因（设计 §6：C3 异常吞并等非 tree_data 不稳定源）。 +3. **观察 error_type 恢复多值**：确认 `error_type` 不再 100% extraction_failure、`evolution_target` 不再全 tool（软验收，充分性依赖 judge）。 +4. **接受 pools.json 成员变化**：test/train 具体成员随多样性维恢复而变，floor/代表性 ε 约束仍保证 test 代表性合格（设计 §6，用户已确认重冻覆盖）。 + +## 算法保真校验（§4.7） + +| 算法 | 是否涉及 | 结论 | +|------|---------|------| +| #7 诊断瀑布 | 是（仅接通输入） | **不改** `attribute_error`（`diagnose.py:910-941`）、severity 函数、defect/lapse 判定；Task 2 仅在 `_process_question` 加 fail-loud 输入护栏。参考 TRM4 `core/harness/diagnose.py:1677` tree_cache 语义对齐 ground_truth。 | +| #12 训练循环编排 | 是（仅换 tree_data 来源） | `runner._run_diagnosis` 只把 `tree_data={}` 换成真实加载，不改三级嵌套/慢更新/断点续训。 | +| 其余 11 项 | 否 | 不涉及。 | + +## 验收标准 +- 5 个 Task 全绿；`pytest tests/` 无回归。 +- `evaluate_span`/`_get_ground_truth_for_trace` 在真实树下拿到非空 ground_truth（Task 5）。 +- `core/evolution/diagnose.py` 不 import app（依赖方向）。 +- 两**生产注入点**（离线 `build_diagnosis_deps` + 训练 `_run_diagnosis`）均加载真实树。允许保留 `tree_data={}` 的**豁免场景**：dry-run `fake_deps`（`wrong_ids=[]` 早返回）、以及测试里走"无题诊断早返回"路径的用例（须带注释说明）。Step 4b 的 grep 兜底确保无遗漏的会真正进 `run_diagnosis` 的空树调用。