Make the handoff start from the shortest verified recovery path

Constraint: The session handoff had become information-rich enough that the next session still needed manual triage, so the opening section had to be collapsed to one verified command path.
Rejected: Keep the handoff primarily as a reading list | That would preserve context but not minimize restart latency.
Confidence: high
Scope-risk: narrow
Directive: Start future sessions with the planner validation runner before reading deeper docs unless the task explicitly skips validation.
Tested: git diff --check; verified docs/session-handoff.md now points to scripts/run_planner_validation_commands_live.py backed by fresh data/pgvector_eval/music20/planner_validation_commands_runner_report.json evidence (executed_count=4, all_passed=true)
Not-tested: No new code-path execution was needed in this commit because it reorganizes the already-verified startup flow.

 ## 2026-06-04
 
+- 重构 `docs/session-handoff.md` 顶部为“首选启动流程（最短路径）”，直接给出 `run_planner_validation_commands_live.py` 的一条启动命令，以及基于 fresh runner 报告（`executed_count=4`, `all_passed=true`）的结果判断逻辑，减少下次 session 的恢复成本。
 - 新增 `scripts/run_planner_validation_commands_live.py` 与 `planner_validation_commands_runner_report.json`，可直接读取 `phase1_extraction_plan_report.json` 中的 `validation_commands` 并批量执行；当前 4 条 entrypoints 已全部执行成功，`executed_count=4`、`all_passed=true`。
 - 更新 `phase1_validation_commands_execution_report.json`，补齐 planner 中剩余两条 validation commands 的直接执行证据：`semantic_vector_negative_matrix` 与 `asset_level_upsert_validation` 也已 `returncode=0`，当前 4 条 validation entrypoints 已全部验证可被脚本直接消费。
 - 新增 `phase1_validation_commands_execution_report.json`，直接从 `phase1_extraction_plan_report.json` 读取并执行 `validation_commands.prereq_audit` 与 `validation_commands.worker_contract_smoke`，两条命令均返回 `0`，证明 planner 产物可被脚本化直接消费。

@@ -9,6 +9,44 @@
 
 ---
 
+## 首选启动流程（最短路径）
+
+下次启动如果目标是“先判断当前 host 能不能继续推进 Phase-1”，不要先手工翻很多文档，先直接跑：
+
+```bash
+cd /workspace/acr-engine
+/usr/local/miniconda3/bin/python scripts/run_planner_validation_commands_live.py   --dsn 'postgres://d2:d2pass@127.0.0.1:5432/d2'   --output data/pgvector_eval/music20/planner_validation_commands_runner_report.json
+```
+
+当前这条命令的 fresh evidence 已有：
+
+- `executed_count = 4`
+- `all_passed = true`
+
+它会一次性执行：
+
+1. `prereq_audit`
+2. `worker_contract_smoke`
+3. `semantic_vector_negative_matrix`
+4. `asset_level_upsert_validation`
+
+### 跑完之后怎么判断
+
+如果结果仍是当前状态：
+- `downloads_root_exists = false`
+- `ready_jobs = 0`
+- exact = `failed/unreadable_audio_assets`
+- semantic = `4/4 failed`
+
+那么说明：
+
+> 当前不该继续怀疑 PostgreSQL contract，而应该优先解决 **音频挂载** 与 **模型 runtime 依赖**。
+
+如果未来这条 runner 开始失败，才优先检查：
+- planner 报告是否变了
+- validation scripts 是否回归
+- schema / worker contract 是否被破坏
+
 ## 一页结论
 
 当前项目主线已经从“原型是否能跑通”切到：