From e9073bfdc20d05607842dca7d02b5ab1b3958194 Mon Sep 17 00:00:00 2001
From: iomgaa <iomgaaycz@gmail.com>
Date: Sat, 11 Jul 2026 11:14:45 -0400
Subject: [PATCH] feat(tree): expose build_async and accept injected API
 semaphore

Core algorithms #1/#2/#3 unchanged: only entry wrapping and semaphore
source switch (injected vs self-built); build logic untouched.
- rename _build_async to public build_async (body unchanged)
- __init__ accepts keyword-only api_semaphore for cross-video sharing
- default path (no injection) is verbatim-equivalent to previous code
---
 app/tree/video_builder.py        | 27 ++++++++++++++------
 tests/unit/test_video_builder.py | 42 ++++++++++++++++++++++++++++++++
 2 files changed, 61 insertions(+), 8 deletions(-)

diff --git a/app/tree/video_builder.py b/app/tree/video_builder.py
index ca3e51a..fc2166f 100644
--- a/app/tree/video_builder.py
+++ b/app/tree/video_builder.py
@@ -13,8 +13,8 @@
 
 并发模型（异步版）::
 
-    build() → asyncio.run(_build_async())
-    _build_async():
+    build() → asyncio.run(build_async())
+    build_async():
         asyncio.Semaphore(concurrency) 控制最大 VLM/LLM 并发数
         各 L1 段并发构建，段内 L2 clip 各启动 _chain 协程：
             提取全部 L3 帧 → 采样 L2 代表帧 → L2 VLM → L3 VLM
@@ -156,8 +156,8 @@ class VideoTreeBuilder:
     转化为三层 TreeIndex。
 
     并发架构:
-        build() 为同步壳，内部调用 asyncio.run(_build_async())。
-        _build_async() 使用 asyncio.Semaphore(concurrency) 控制并发 VLM/LLM 数量。
+        build() 为同步壳，内部调用 asyncio.run(build_async())。
+        build_async() 使用 asyncio.Semaphore(concurrency) 控制并发 VLM/LLM 数量。
         所有 VLM 调用通过 VLMProvider 的异步接口发起，零线程阻塞。
         所有 LLM 调用通过 LLMProvider 的异步接口发起（L1 摘要）。
         ffmpeg 提帧在独立 ThreadPoolExecutor 中并行，不阻塞事件循环。
@@ -166,6 +166,7 @@ class VideoTreeBuilder:
         _vlm: VLM 图文调用端口。
         _llm: LLM 文本调用端口（L1 摘要）。
         _config: 树构建配置。
+        _api_semaphore: 外部注入的全局 API 并发信号量（None 时 build_async 自建）。
         _ffmpeg_pool: ffmpeg 专用线程池（max_workers=_FFMPEG_MAX_WORKERS）。
     """
 
@@ -174,6 +175,8 @@ class VideoTreeBuilder:
         vlm: VLMProvider,
         llm: LLMProvider,
         config: TreeConfig,
+        *,
+        api_semaphore: asyncio.Semaphore | None = None,
     ) -> None:
         """初始化视频树构建器。
 
@@ -183,10 +186,14 @@ class VideoTreeBuilder:
             config: 树构建配置（TreeConfig），关键字段：
                     l1_segment_duration, l2_clip_duration, l3_fps,
                     l2_representative_frames, cache_dir, concurrency。
+            api_semaphore: 外部注入的全局 VLM/LLM 并发信号量（批量建树时跨视频共享）；
+                           None 时 build_async 内部按 config.concurrency 自建，
+                           单视频行为零变化。
         """
         self._vlm = vlm
         self._llm = llm
         self._config = config
+        self._api_semaphore = api_semaphore
         self._ffmpeg_pool = ThreadPoolExecutor(max_workers=_FFMPEG_MAX_WORKERS)
         self._cache_root = Path(self._config.cache_dir)
         self._session_id: str = ""
@@ -296,13 +303,13 @@ class VideoTreeBuilder:
         返回:
             三层 TreeIndex 对象。
         """
-        return asyncio.run(self._build_async(video_path, srt_entries))
+        return asyncio.run(self.build_async(video_path, srt_entries))
 
     # ------------------------------------------------------------------
     # 核心异步构建逻辑（保真算法 #1：L2→L3 链式触发）
     # ------------------------------------------------------------------
 
-    async def _build_async(
+    async def build_async(
         self,
         video_path: str,
         srt_entries: list[SRTEntry] | None = None,
@@ -353,8 +360,12 @@ class VideoTreeBuilder:
         # Phase 1.1: 读取已有进度（保真算法 #3：断点续跑）
         finished_l1_ids = self._load_resume_state(source_id, total_l1)
 
-        # 创建 VLM/LLM 并发控制信号量
-        vlm_sem = asyncio.Semaphore(self._config.concurrency)
+        # 创建 VLM/LLM 并发控制信号量（外部注入时跨视频全局共享，Spec-2）
+        vlm_sem = (
+            self._api_semaphore
+            if self._api_semaphore is not None
+            else asyncio.Semaphore(self._config.concurrency)
+        )
 
         # Phase 2-5: 按 L1 段并发，段内 L2→L3 链式触发（保真算法 #1）
         async def _build_segment(
diff --git a/tests/unit/test_video_builder.py b/tests/unit/test_video_builder.py
index 5a9addf..91f2e83 100644
--- a/tests/unit/test_video_builder.py
+++ b/tests/unit/test_video_builder.py
@@ -14,6 +14,7 @@
 
 from __future__ import annotations
 
+import asyncio
 import json
 from pathlib import Path
 from typing import Any
@@ -997,3 +998,44 @@ class TestHelpers:
         long_name = "a" * 100 + ".mp4"
         stem = VideoTreeBuilder._source_stem(f"/path/{long_name}")
         assert len(stem) == 64
+
+
+# ── Semaphore 注入与异步入口（Spec-2）─────────────────────────
+
+
+class TestApiSemaphoreInjection:
+    """API Semaphore 注入与 build_async 公开入口。"""
+
+    def test_injected_semaphore_stored(
+        self,
+        mock_vlm: MockVLMProvider,
+        mock_llm: MockLLMProvider,
+        tree_config: TreeConfig,
+    ) -> None:
+        """构造器注入的 Semaphore 应被保存供 build_async 使用。"""
+        sem = asyncio.Semaphore(3)
+        builder = VideoTreeBuilder(
+            vlm=mock_vlm, llm=mock_llm, config=tree_config, api_semaphore=sem
+        )
+        assert builder._api_semaphore is sem
+
+    def test_default_no_injection(
+        self,
+        mock_vlm: MockVLMProvider,
+        mock_llm: MockLLMProvider,
+        tree_config: TreeConfig,
+    ) -> None:
+        """未注入时属性为 None（build_async 内部自建，单视频行为零变化）。"""
+        builder = VideoTreeBuilder(vlm=mock_vlm, llm=mock_llm, config=tree_config)
+        assert builder._api_semaphore is None
+
+    def test_build_async_is_public(
+        self,
+        mock_vlm: MockVLMProvider,
+        mock_llm: MockLLMProvider,
+        tree_config: TreeConfig,
+    ) -> None:
+        """build_async 必须是公开协程方法（供批量编排在事件循环内调用）。"""
+        builder = VideoTreeBuilder(vlm=mock_vlm, llm=mock_llm, config=tree_config)
+        assert hasattr(builder, "build_async")
+        assert asyncio.iscoroutinefunction(builder.build_async)