docs(design): main.py 推理入口 + 初始 Prompt 集设计
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
@@ -0,0 +1,246 @@
|
||||
---
|
||||
id: main-inference-entry
|
||||
title: main.py 推理入口 + 初始 Prompt 集设计
|
||||
type: design
|
||||
status: approved
|
||||
created: 2026-07-09
|
||||
---
|
||||
|
||||
# main.py 推理入口 + 初始 Prompt 集设计
|
||||
|
||||
## 1. 目标
|
||||
|
||||
完成第一版 900 道题推理基线,具体交付:
|
||||
|
||||
| 交付物 | 说明 |
|
||||
|--------|------|
|
||||
| `main.py` | CLI Composition Root,本次仅实现 infer 模式 |
|
||||
| `app/harness/deps_router.py` | 按 video_id 懒加载 InferenceDeps 的路由器 |
|
||||
| `app/ports.py` 扩展 | 新增 `ToolDispatchFactory` / `PromptBuilderFactory` Protocol |
|
||||
| `app/harness/runner.py` 小改 | `__init__` 注入 factory,替换 noop 占位 |
|
||||
| `store/skills/v1/` | 14 个 skill(从 TRM4 v1 精简 + 注入 TRM5 card 字段) |
|
||||
| `store/prompts/v1/` | 目录重组(从 `store/prompts/` 扁平结构迁入) |
|
||||
| 配置变更 | concurrency=24, max_steps=40, breaker_threshold=48 |
|
||||
|
||||
## 2. 架构
|
||||
|
||||
### 2.1 依赖流(Clean Architecture Composition Root)
|
||||
|
||||
```
|
||||
main.py (Composition Root — 最外层)
|
||||
│
|
||||
├─ 构建 adapters ──────────────────────────────┐
|
||||
│ CircuitBreaker │
|
||||
│ RedisResponseCache (可选,降级为 None) │ adapters/
|
||||
│ SQLiteTelemetryRecorder │
|
||||
│ GovernedLLMClient (search) │
|
||||
│ GovernedLLMClient (evolve, 本次传同一实例) │
|
||||
│ GovernedVLMClient │
|
||||
│ LocalEmbeddingProvider │
|
||||
│ MonkeyOCRClient (可选) │
|
||||
│ │
|
||||
├─ 构建 InferenceDepsRouter ───────────────────┤
|
||||
│ 接收: store_dir, embed, llm, vlm, ocr │ app/harness/deps_router.py
|
||||
│ 复用: factory.build_inference_deps() │
|
||||
│ │
|
||||
├─ 构建 Runner ────────────────────────────────┤
|
||||
│ 注入: config, llm, evolve_llm, vlm, │ app/harness/runner.py
|
||||
│ telemetry, │
|
||||
│ tool_dispatch_factory, │
|
||||
│ prompt_builder_factory │
|
||||
│ │
|
||||
└─ asyncio.run(runner.infer()) ────────────────┘
|
||||
```
|
||||
|
||||
依赖只向内:`main.py` → `adapters/` + `app/` → `core/`。
|
||||
|
||||
### 2.2 InferenceDepsRouter
|
||||
|
||||
**位置**:`app/harness/deps_router.py`
|
||||
|
||||
**职责**:将 Runner 的全局统一 dispatch/prompt_builder 接口路由到 per-video 的 `InferenceDeps`。
|
||||
|
||||
```
|
||||
prompt_builder(qa) ← 先调用,注册 qid→vid 映射
|
||||
↓
|
||||
AgentLoop.run()
|
||||
↓
|
||||
dispatch(tool, args, ctx) ← 后调用,通过 ctx["session_id"] 查映射
|
||||
```
|
||||
|
||||
核心伪代码:
|
||||
|
||||
```python
|
||||
class InferenceDepsRouter:
|
||||
_deps_cache: dict[tuple, InferenceDeps] # (vid, skills_dir, prompts_dir) → deps
|
||||
_qid_to_vid: dict[str, str] # question_id → video_id
|
||||
|
||||
def create_dispatch(self, *, skills_dir=None):
|
||||
async def _dispatch(tool_name, args, *, context):
|
||||
vid = self._qid_to_vid[context["session_id"]]
|
||||
deps = self._ensure_deps(vid, skills_dir, ...)
|
||||
return await deps.tool_dispatch_fn(tool_name, args, context=context)
|
||||
return _dispatch
|
||||
|
||||
def create_prompt_builder(self, *, skills_dir=None, prompts_dir=None):
|
||||
def _builder(qa):
|
||||
self._qid_to_vid[qa.question_id] = qa.video_id # 注册映射
|
||||
deps = self._ensure_deps(qa.video_id, skills_dir, prompts_dir)
|
||||
return deps.prompt_builder(qa)
|
||||
return _builder
|
||||
|
||||
def _ensure_deps(self, video_id, skills_dir, prompts_dir):
|
||||
key = (video_id, str(skills_dir or ""), str(prompts_dir or ""))
|
||||
if key not in self._deps_cache:
|
||||
self._deps_cache[key] = build_inference_deps(...)
|
||||
return self._deps_cache[key]
|
||||
```
|
||||
|
||||
**时序保证**:`run_inference()` 中每道题先调 `prompt_builder(qa)` 构建 prompt,再启动 AgentLoop(调 dispatch)。映射注册总先于使用。
|
||||
|
||||
### 2.3 Runner 改动
|
||||
|
||||
`__init__` 新增 2 个可选参数(向后兼容):
|
||||
|
||||
```python
|
||||
def __init__(self, config, *, llm, evolve_llm, vlm, telemetry,
|
||||
tool_dispatch_factory=None,
|
||||
prompt_builder_factory=None):
|
||||
```
|
||||
|
||||
`_make_tool_dispatch_fn` / `_make_prompt_builder` 优先用注入值,缺省保留 noop fallback。
|
||||
|
||||
### 2.4 Protocol 定义
|
||||
|
||||
`app/ports.py` 新增:
|
||||
|
||||
```python
|
||||
class ToolDispatchFactory(Protocol):
|
||||
def __call__(self, *, skills_dir: Path | None = None) -> Callable[..., Any]: ...
|
||||
|
||||
class PromptBuilderFactory(Protocol):
|
||||
def __call__(self, *, skills_dir: Path | None = None,
|
||||
prompts_dir: Path | None = None
|
||||
) -> Callable[[GeneratedQuestion], tuple[str, str]]: ...
|
||||
```
|
||||
|
||||
### 2.5 main.py 结构
|
||||
|
||||
使用 argparse(复用 `RunConfig` + `load_config()` 的 YAML/CLI 三层合并逻辑)。
|
||||
|
||||
```python
|
||||
def _build_parser(): # CLI 参数定义,与 TRM4 main.py 保持一致
|
||||
def _build_adapters(): # 从 .env 构建全套 adapters,返回 NamedTuple
|
||||
def _log_result(): # 输出推理结果摘要
|
||||
def main(): # Composition Root:load_config → adapters → router → runner
|
||||
```
|
||||
|
||||
本次只实现 `mode == "infer"` 分支,其余模式 `raise SystemExit("尚未实现")`。
|
||||
|
||||
## 3. 初始 Prompt 集
|
||||
|
||||
### 3.1 设计原则
|
||||
|
||||
```
|
||||
进化能学到的 → v1 留框架、去细节(给进化留空间)
|
||||
进化学不到的 → v1 用人类版(否则永远缺失)
|
||||
```
|
||||
|
||||
依据 TRM4 进化历史(v1→v40):skills 进化 39 轮(主力),system prompt 仅 1 轮,tool prompts 未变。
|
||||
|
||||
### 3.2 三类 Prompt 处理
|
||||
|
||||
| 类别 | 是否进化 | v1 来源 | 处理 |
|
||||
|------|---------|---------|------|
|
||||
| system.md | 微量 | TRM5 现有版本 | 保留(已含 card 字段说明,是基础设施) |
|
||||
| skills/v1/ (14个) | 主力 | TRM4 v1 精简 + TRM5 注入 | 见 §3.3 |
|
||||
| extract/verify (8个) | 不变 | TRM5 现有版本 | 保留(已适配 card 结构) |
|
||||
|
||||
### 3.3 Skills v1 内容策略
|
||||
|
||||
每个 skill 文件的改造规则:
|
||||
|
||||
| 内容层次 | 进化能学到? | v1 处理 |
|
||||
|----------|------------|---------|
|
||||
| YAML frontmatter(task_type) | 否 | 保留原版 |
|
||||
| Step 标题 + 一句话基本意图 | 否 | 保留原版 |
|
||||
| reflect/plan/action JSON schema | 否 | 保留原版 |
|
||||
| **TRM5 card 字段索引** | **否** | **新增**(注入各层字段名及适用场景) |
|
||||
| 数据驱动统计 | 是 | 移除 |
|
||||
| 步骤间精确转换条件 | 是 | 移除 |
|
||||
| 详细操作性规则 | 是 | 移除 |
|
||||
| 大多数自检信号 | 是 | 移除(保留最基本 1 条) |
|
||||
| 特定失败模式陷阱 | 是 | 移除(保留 1-2 条通用警告) |
|
||||
|
||||
**card 字段索引表**(注入每个 skill):
|
||||
|
||||
| 层级 | 字段 | 适用场景 |
|
||||
|------|------|---------|
|
||||
| L1 | scene_summary | 整体概况 |
|
||||
| L1 | key_entities | 查找人物/物体 |
|
||||
| L1 | main_actions | 主要动作 |
|
||||
| L1 | temporal_flow | 时间线概览 |
|
||||
| L1 | topic_keywords | 主题定位 |
|
||||
| L2 | event_description | 事件因果 |
|
||||
| L2 | entities / actions | 实体和动作细节 |
|
||||
| L2 | state_changes | 状态转变 |
|
||||
| L2 | spatial_relations | 空间关系变化 |
|
||||
| L3 | frame_summary | 精确视觉证据 |
|
||||
| L3 | visible_entities | 具体物体确认 |
|
||||
| L3 | ongoing_actions | 正在发生的动作 |
|
||||
| L3 | spatial_layout | 精确空间位置 |
|
||||
| L3 | visual_attributes | 光照、色调、机位 |
|
||||
| 全层 | visible_text | 画面文字(OCR) |
|
||||
| 全层 | subtitle | 字幕转写 |
|
||||
|
||||
### 3.4 store/ 目录重组
|
||||
|
||||
```
|
||||
store/
|
||||
prompts/
|
||||
v1/ ← 新建(从 store/prompts/*.md 移入)
|
||||
system.md
|
||||
observe_frame_extract.md
|
||||
observe_frame_verify.md
|
||||
search_similar_extract.md
|
||||
search_similar_verify.md
|
||||
view_node_extract.md
|
||||
view_node_verify.md
|
||||
view_node_children_extract.md
|
||||
view_node_children_verify.md
|
||||
skills/
|
||||
v1/ ← 新建(14 个文件)
|
||||
default-strategy.md
|
||||
action-reasoning.md
|
||||
action-recognition.md
|
||||
attribute-perception.md
|
||||
counting-problem.md
|
||||
information-synopsis.md
|
||||
object-reasoning.md
|
||||
object-recognition.md
|
||||
ocr-problems.md
|
||||
spatial-perception.md
|
||||
spatial-reasoning.md
|
||||
temporal-perception.md
|
||||
temporal-reasoning.md
|
||||
```
|
||||
|
||||
## 4. 配置变更
|
||||
|
||||
| 参数 | 原值 | 新值 | 位置 |
|
||||
|------|------|------|------|
|
||||
| concurrency | 12 | 24 | config/default.yaml |
|
||||
| max_steps | 15 | 40 | config/default.yaml |
|
||||
| breaker_threshold | 5 | 48 | .env |
|
||||
|
||||
熔断器行为:所有 24 并发 agent 共享同一 CircuitBreaker 实例,`record_success()` 归零计数。48 = 连续 2 波全失败才触发开路,间歇抖动不会误触。
|
||||
|
||||
## 5. 拒绝的方案
|
||||
|
||||
| 方案 | 拒绝原因 |
|
||||
|------|---------|
|
||||
| Runner 子类覆盖 `_make_*` | Template Method 反模式,违反依赖反转 |
|
||||
| 绕过 Runner 直接调 `run_inference` | 不复用 workspace 管理、日志、报告逻辑 |
|
||||
| 照搬 TRM4 v1 skills | 进化空间不足,且缺少 TRM5 card 字段知识 |
|
||||
| 极简骨架 skills | 基线质量过低,可能不收敛 |
|
||||
| typer CLI | 需重写 `RunConfig` 的 YAML/CLI 合并逻辑,ROI 不值 |
|
||||
Reference in New Issue
Block a user