Promote the one-command song-centric runner as the default handoff path

Constraint: Reduce resume friction for future sessions by making the current live-validated runner the first-class entrypoint in docs and artifacts.
Rejected: Keep the active song-centric workflow scattered across multiple lower-level commands in the handoff docs | It slows recovery and increases cognitive overhead.
Confidence: high
Scope-risk: narrow
Directive: For current development, start with run_songcentric_directory_pipeline_live.py before dropping to the lower-level builder/enricher/importer commands.
Tested: /usr/local/miniconda3/bin/python acr-engine/scripts/run_songcentric_directory_pipeline_live.py --dsn postgres://d2:d2pass@127.0.0.1:5432/d2 --schema acr_songcentric_test --input-root acr-engine/data/songcentric_builder_smoke --output-dir acr-engine/data/pgvector_eval/music20; git diff --check; /usr/local/miniconda3/bin/python scripts/check_markdown_links.py --root docs returned OK for 11 active markdown files
Not-tested: alternate input roots beyond the current smoke directory

 ## 2026-06-04
 
+- 将 `run_songcentric_directory_pipeline_live.py` 提升为当前默认主线入口，并把 fresh runner 结果同步到 `docs/README.md`、`docs/start-here.md`、`docs/session-handoff.md`，降低下次 session 的恢复成本。
+
 - 新增 `acr-engine/scripts/run_songcentric_directory_pipeline_live.py`，把“真实目录 -> manifest -> 特征补全 -> live PostgreSQL 导入”收敛为一条可重复执行的 runner，并输出 exact/semantic backend 选择与导入计数摘要。
 
 - 升级 `enrich_songcentric_manifest_with_local_features.py` 为 runtime-aware 语义适配器选择：当前 host 上因缺少 `torch/torchaudio/transformers`，semantic lane 明确写入 `local_wavehash_embed` fallback，并把缺失依赖固化到 report/metadata 中。

@@ -6,6 +6,19 @@
 
 ## 0. 新同学先做什么
 
+如果当前要继续 song-centric 主线，先跑：
+
+```bash
+cd /workspace
+/usr/local/miniconda3/bin/python acr-engine/scripts/run_songcentric_directory_pipeline_live.py \
+  --dsn 'postgres://d2:d2pass@127.0.0.1:5432/d2' \
+  --schema acr_songcentric_test \
+  --input-root acr-engine/data/songcentric_builder_smoke \
+  --output-dir acr-engine/data/pgvector_eval/music20
+```
+
+如果要回归旧的 planner/worker 合同，再跑：
+
 ```bash
 cd /workspace/acr-engine
 /usr/local/miniconda3/bin/python scripts/run_planner_validation_commands_live.py \

@@ -11,7 +11,27 @@
 
 ## 0. 下次启动先做什么
 
-先执行：
+如果下次启动要继续当前主线（**song-centric 真实目录 -> feature -> PostgreSQL**），先执行：
+
+```bash
+cd /workspace
+/usr/local/miniconda3/bin/python acr-engine/scripts/run_songcentric_directory_pipeline_live.py \
+  --dsn 'postgres://d2:d2pass@127.0.0.1:5432/d2' \
+  --schema acr_songcentric_test \
+  --input-root acr-engine/data/songcentric_builder_smoke \
+  --output-dir acr-engine/data/pgvector_eval/music20
+```
+
+当前 fresh evidence：
+- `song_count = 2`
+- `window_count = 5`
+- `matcher_fingerprint_count = 5`
+- `fallback_fingerprint_count = 0`
+- `semantic_runtime_available = false`
+- `semantic_runtime_missing = [torch, torchaudio, transformers]`
+- `import_counts = media_entity:9 / audio_object:22 / feature_fact:24 / set_membership:9`
+
+如果只是回归历史 Phase-1 planner/worker 合同，再执行：
 
 ```bash
 cd /workspace/acr-engine

@@ -6,6 +6,27 @@
 
 ## 1. 先执行这条命令
 
+如果当前目标是验证 **song-centric 真实目录 -> feature -> PostgreSQL** 主链，优先跑：
+
+```bash
+cd /workspace
+/usr/local/miniconda3/bin/python acr-engine/scripts/run_songcentric_directory_pipeline_live.py \
+  --dsn 'postgres://d2:d2pass@127.0.0.1:5432/d2' \
+  --schema acr_songcentric_test \
+  --input-root acr-engine/data/songcentric_builder_smoke \
+  --output-dir acr-engine/data/pgvector_eval/music20
+```
+
+当前 fresh evidence：
+- `song_count = 2`
+- `window_count = 5`
+- `matcher_fingerprint_count = 5`
+- `fallback_fingerprint_count = 0`
+- `semantic_runtime_available = false`
+- `import_counts.feature_fact = 24`
+
+如果你当前目标是验证老的 Phase-1 planner/worker 合同，再跑下面这条：
+
 ```bash
 cd /workspace/acr-engine
 /usr/local/miniconda3/bin/python scripts/run_planner_validation_commands_live.py \