odyssey-review-test-fix

<purpose>
Deep code review with exhaustive fix: archaeology → explore → multi-dimensional review →
fix ALL findings → confirm → generalize → discover → persist. Zero-residual philosophy.
</purpose>

<boundary>
**范围内:** 目标代码的多维度深度审查 → 穷尽修复 ALL 发现（按 severity 递降）→ 泛化 pattern 到全项目
**范围外:** 深度根因调查（根因不明时）→ `/odyssey-debug` | 需求实现 → `/odyssey-planex` | UI 视觉优化 → `/odyssey-ui`
**探索自由度:** 边界内自由探索 — 可跨维度关联发现、追溯 git 历史、泛化扫描全项目。修复 ALL findings within fix_threshold（默认 all = 穷尽所有 severity）。
**Zero-residual principle:** Every finding MUST have a concrete action (fix / issue / decision). "Report and shelve" is not allowed. "Pre-existing issue" is not a valid skip reason — if discovered within scope, it must be addressed.
</boundary>

<execution_discipline>
**三条铁律（所有阶段适用）:**

1. **Phase auto-commit** — 每个阶段完成后**自动** `git commit`，无需用户确认
   - 代码变更 + understanding.md → `git add` → `git commit -m "odyssey-review({slug}): {phase} — {摘要}"`
   - session.json / evidence.ndjson 为运行时状态，不纳入 commit

2. **Confident edits only, but must attempt** — only modify what you're confident about; record decisions only when genuinely requiring human judgment
   - Confident → edit code directly, commit
   - Needs decision → record `evidence.ndjson {"phase":"decision","status":"pending"}`, don't touch code
   - No speculative changes
   - ⚠️ **Decision gate** — ONLY these qualify as decisions (not fixes):
     - Cross-module architectural tradeoffs requiring human direction
     - Ambiguous business semantics where the fix could alter intended behavior
     - Requires new dependency or breaking API change
   - ❌ "Unsure how to fix", "Large scope", "Pre-existing issue" are NOT valid decision reasons — either fix it, or explain specifically why it's unfixable

3. **多 CLI 辅助** — 利用 `maestro delegate` 调用多个 CLI 工具交叉验证
   - 关键判断用不同 `--role`（analyze / review / explore）获取多视角
   - 修复前后各做一次 CLI review 确认

4. **禁止以上下文消耗为由中断** — harness 自动处理 context compression，以"上下文不足"或"已执行 N 个阶段"为由中断属于纪律违反；必须完整走完状态机直到 S_RECORD → END
</execution_discipline>

<context>
$ARGUMENTS — target and optional flags.

**Target resolution:**
| Input | Resolution |
|-------|-----------|
| File/dir path | Review those files |
| `HEAD` / `staged` | `git diff HEAD` / `git diff --staged` |
| Phase number | Resolve via state.json → changed files |
| PR number | `git diff main...HEAD` |

**Flags:**
| Flag | Effect | Default |
|------|--------|---------|
| `--dimensions <list>` | Comma-separated subset | correctness,security,performance,architecture |
| `--fix-threshold <severity>` | 修复到哪个 severity 为止（all = 全部修复）| `all` |
| `--skip-fix` | Review-only — skip S_FIX and S_CONFIRM | false |
| `--skip-generalize` | Skip S_GENERALIZE and S_DISCOVER | false |
| `--auto` | CLI delegates without confirmation | false |
| `-y` | Auto-confirm at decision points (see appendix) | false |
| `-c` | Resume most recent session | — |

**Session**: `SESSION_DIR = .workflow/scratch/{YYYYMMDD}-review-odyssey-{slug}/`

**Output — 4 files:**
```
SESSION_DIR/
  ├── session.json       # state + review_result + confirmation + patterns + phase_goals
  ├── evidence.ndjson    # ALL evidence (phase: archaeology|explore|review|fix|discovery|decision)
  ├── explore.json       # CLI exploration snapshot
  └── understanding.md   # 8-section evolving narrative (§1-§8, one per major phase)
```

**session.json schema:**
```json
{
  "session_id": "review-odyssey-{YYYYMMDD-HHmmss}",
  "target": "", "dimensions": [],
  "flags": { "skip_fix": false, "skip_generalize": false, "fix_threshold": "all", "auto": false, "auto_confirm": false },
  "current_state": "S_INTAKE",
  "review_result": { "dimensions_reviewed": [], "finding_count": 0, "severity_distribution": { "critical": 0, "high": 0, "medium": 0, "low": 0 }, "remaining_actionable": 0 },
  "patterns": [{ "id": "P1", "source_finding": "F1", "layer": "syntax|semantic|structural", "signature": "", "description": "", "risk": "", "fix_template": "", "confidence": "high|medium|low" }],
  "confirmation": { "test_result": {}, "cli_review": {}, "overall": "confirmed|needs_rework" },
  "generalization_stats": { "patterns_extracted": 0, "total_hits": 0, "true_positives": 0, "false_positives": 0, "uncertain": 0, "cross_layer_confirmed": 0, "regression_risks": 0, "by_layer": {}, "deepening_triggered": false, "self_iteration_rounds": 0 },
  "phase_goals": [], "phase_goals_all_done": false,
  "self_iteration_log": [],
  "cross_phase_loops": 0, "max_loops": 5,
  "created_at": "", "updated_at": ""
}
```

**evidence.ndjson unified schema:** `{"ts":"","phase":"<phase>","type":"<type>","dimension":"","title":"","severity":"","file":"","line":0,"description":"","suggestion":"","files_modified":[]}`

**phase_goals[]:**
| ID | Goal | Done When | Phase | skip_when |
|----|------|-----------|-------|-----------|
| G1 | Review completed | all dimensions reviewed, findings logged | S_REVIEW | — |
| G2 | Explore context gathered | explore.json populated | S_EXPLORE | — |
| G3 | Zero remaining: all findings fixed | `remaining_actionable == 0` within fix_threshold | S_CONFIRM | skip_fix |
| G4 | Pattern generalized | patterns[] ≥1 entry | S_GENERALIZE | skip_generalize |
| G5 | Discoveries triaged | all scan hits classified | S_DISCOVER | skip_generalize |
| G6 | Learnings persisted | spec entries created OR no actionable | S_RECORD | — |

Lifecycle: `pending → done | skipped | failed` (all set `completion_confirmed`)

### Pre-load（可选，缺失不阻塞）

| 层级 | 命令 | 作用 |
|------|------|------|
| Codebase docs | Read `.workflow/codebase/ARCHITECTURE.md` | 模块边界，架构约束 |
| Wiki search | `maestro search "<target keywords>" --json` | 先前 review、已知问题（取 top 5） |
| Specs | `maestro load --type spec --category review` | review 标准、checklist、knowhow 工具 |
| Role knowledge | `maestro search --category review` → 选相关 → `maestro load --type knowhow --id <id>` | 累积 review 领域知识 |
| Prior sessions | `Glob(".workflow/scratch/*-review-odyssey-*")` | 相关 odyssey 会话 |

### Knowledge Persistence（S_RECORD 中写入产出文件）

S_RECORD 阶段将可沉淀知识