docs(plans): add Spec-3 question-gen-v2 implementation plan

9 tasks: type extension → postprocess → families → sampler_v2 →
generator_v2 → gates → run_store → pipeline_v2 → CLI integration.
Includes structured-logging schemas/metrics and Codex review revisions.
This commit is contained in:
2026-07-11 22:57:47 -04:00
parent 8c9adfd3fa
commit 043d4aa46f
10 changed files with 964 additions and 3 deletions
@@ -0,0 +1,97 @@
---
type: schema
node_id: schema:question-gen-items
title: "表结构: question_gen_items(逐题门判定)"
date: 2026-07-12
---
# 表结构: question_gen_items(逐题门判定)
出题管线 v2 的逐题门判定记录。每题每轮(含重出)产生一行。
## 列定义
| 列名 | 类型 | 约束 | 说明 |
|------|------|------|------|
| `item_id` | TEXT | PK | 题目唯一 IDUUID,每轮独立) |
| `run_id` | TEXT | NOT NULL FK→question_gen_runs | 关联批次 |
| `slot_id` | TEXT | NOT NULL | 逻辑 slot 标识(同 slot 多次重出共享) |
| `video_id` | TEXT | NOT NULL | 视频 ID |
| `family` | TEXT | NOT NULL | 题族(retrieval/reasoning/enumeration/visual/spatial |
| `task_type` | TEXT | NOT NULL | Video-MME 12 类主标签 |
| `skill_target` | TEXT | | M1-M5 + 题族子标签 |
| `attempt` | INTEGER | NOT NULL | 当前重出轮次(1-based,≤3 |
| `gate_key_verify` | TEXT | | pass / reject / NULL(未执行) |
| `gate_blind_answer` | TEXT | | pass / reject / NULL |
| `gate_multi_true` | TEXT | | pass / reject / NULL |
| `gate_leak_test` | TEXT | | pass / reject / NULL |
| `reject_reason` | TEXT | | 拒因文本(首个拒绝门的判定摘要) |
| `final_status` | TEXT | NOT NULL | accepted / rejected / pending |
| `difficulty_steps` | INTEGER | | 重量抽检产出 Agent 步数(NULL=未抽检) |
| `created_at` | TEXT | NOT NULL | ISO8601 |
## DDL
```sql
CREATE TABLE IF NOT EXISTS question_gen_items (
item_id TEXT PRIMARY KEY,
run_id TEXT NOT NULL REFERENCES question_gen_runs(run_id),
slot_id TEXT NOT NULL,
video_id TEXT NOT NULL,
family TEXT NOT NULL,
task_type TEXT NOT NULL,
skill_target TEXT,
attempt INTEGER NOT NULL DEFAULT 1,
gate_key_verify TEXT,
gate_blind_answer TEXT,
gate_multi_true TEXT,
gate_leak_test TEXT,
reject_reason TEXT,
final_status TEXT NOT NULL DEFAULT 'pending',
difficulty_steps INTEGER,
created_at TEXT NOT NULL
);
CREATE INDEX idx_items_run ON question_gen_items(run_id);
CREATE INDEX idx_items_family ON question_gen_items(family);
CREATE INDEX idx_items_task_type ON question_gen_items(task_type);
CREATE INDEX idx_items_slot ON question_gen_items(slot_id);
```
## 埋点位置
| 代码位置 | 动作 | 时机 |
|---------|------|------|
| `synthesizer.py::generate_one_v2` 返回后 | INSERTgates=NULL, status=pending | 每题生成后 |
| `gates.py::run_gates` 返回后 | UPDATE gate_* 列 + reject_reason + final_status | 门跑完后 |
| 重出循环入口 | INSERT 新行(same slot_id, attempt+1 | 重出时 |
| `heavy_check.py` 完成 | UPDATE difficulty_steps | 抽检完成 |
## 查询模式
```sql
-- 各门拦截率
SELECT
gate_key_verify,
COUNT(*) as cnt
FROM question_gen_items WHERE run_id=?
GROUP BY gate_key_verify;
-- 按题族切片拦截率
SELECT family,
SUM(CASE WHEN final_status='rejected' THEN 1 ELSE 0 END) as rejected,
COUNT(*) as total
FROM question_gen_items WHERE run_id=?
GROUP BY family;
-- 重出收敛率
SELECT
COUNT(DISTINCT slot_id) FILTER (WHERE final_status='accepted') as converged,
COUNT(DISTINCT slot_id) as total_slots
FROM question_gen_items WHERE run_id=?;
-- 按 task_type 分布
SELECT task_type, COUNT(*) FROM question_gen_items
WHERE run_id=? AND final_status='accepted'
GROUP BY task_type;
```