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 |
|
||||||
@@ -70,6 +70,11 @@
|
|||||||
"id": "plan:question-gen-synth",
|
"id": "plan:question-gen-synth",
|
||||||
"label": "赛题生成工具实现计划",
|
"label": "赛题生成工具实现计划",
|
||||||
"type": "plan"
|
"type": "plan"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"id": "design:main-inference-entry",
|
||||||
|
"label": "main.py 推理入口 + 初始 Prompt 集设计",
|
||||||
|
"type": "design"
|
||||||
}
|
}
|
||||||
],
|
],
|
||||||
"links": [
|
"links": [
|
||||||
|
|||||||
@@ -1,13 +1,15 @@
|
|||||||
# Research Wiki 索引
|
# Research Wiki 索引
|
||||||
|
|
||||||
> 自动生成,更新时间:2026-07-09 09:05 UTC
|
> 自动生成,更新时间:2026-07-09 12:41 UTC
|
||||||
|
|
||||||
## design (13)
|
## design (15)
|
||||||
- [2026-07-06-core-agent-adapters-llm-design](designs/2026-07-06-core-agent-adapters-llm-design.md) `design:2026-07-06-core-agent-adapters-llm-design`
|
- [2026-07-06-core-agent-adapters-llm-design](designs/2026-07-06-core-agent-adapters-llm-design.md) `design:2026-07-06-core-agent-adapters-llm-design`
|
||||||
- [2026-07-07-app-harness-design](designs/2026-07-07-app-harness-design.md) `design:2026-07-07-app-harness-design`
|
- [2026-07-07-app-harness-design](designs/2026-07-07-app-harness-design.md) `design:2026-07-07-app-harness-design`
|
||||||
- [2026-07-07-core-evolution-design](designs/2026-07-07-core-evolution-design.md) `design:2026-07-07-core-evolution-design`
|
- [2026-07-07-core-evolution-design](designs/2026-07-07-core-evolution-design.md) `design:2026-07-07-core-evolution-design`
|
||||||
- [2026-07-08-tree-repair-resilience-design](designs/2026-07-08-tree-repair-resilience-design.md) `design:2026-07-08-tree-repair-resilience-design`
|
- [2026-07-08-tree-repair-resilience-design](designs/2026-07-08-tree-repair-resilience-design.md) `design:2026-07-08-tree-repair-resilience-design`
|
||||||
- [2026-07-09-paper-main-figure-design](designs/2026-07-09-paper-main-figure-design.md) `design:2026-07-09-paper-main-figure-design`
|
- [2026-07-09-paper-main-figure-design](designs/2026-07-09-paper-main-figure-design.md) `design:2026-07-09-paper-main-figure-design`
|
||||||
|
- [main.py 推理入口 + 初始 Prompt 集设计](designs/2026-07-09-main-inference-entry-design.md) `design:2026-07-09-main-inference-entry-design`
|
||||||
|
- [main.py 推理入口 + 初始 Prompt 集设计](designs/main-inference-entry.md) `design:main-inference-entry`
|
||||||
- [出题模块迁移设计(question_gen)](designs/2026-07-07-question-gen-design.md) `design:2026-07-07-question-gen-design`
|
- [出题模块迁移设计(question_gen)](designs/2026-07-07-question-gen-design.md) `design:2026-07-07-question-gen-design`
|
||||||
- [建树修复管线:熔断根因修复 + 断点续跑 + 并发改造](designs/tree-repair-resilience.md) `design:tree-repair-resilience`
|
- [建树修复管线:熔断根因修复 + 断点续跑 + 并发改造](designs/tree-repair-resilience.md) `design:tree-repair-resilience`
|
||||||
- [建树模块竖切设计:数据结构 + 建树 + 修复 + 迁移](designs/2026-07-07-tree-module-design.md) `design:2026-07-07-tree-module-design`
|
- [建树模块竖切设计:数据结构 + 建树 + 修复 + 迁移](designs/2026-07-07-tree-module-design.md) `design:2026-07-07-tree-module-design`
|
||||||
|
|||||||
@@ -33,3 +33,5 @@
|
|||||||
- [2026-07-09 09:05 UTC] 新增 plan: 赛题生成工具实现计划 (plan:question-gen-synth)
|
- [2026-07-09 09:05 UTC] 新增 plan: 赛题生成工具实现计划 (plan:question-gen-synth)
|
||||||
- [2026-07-09 09:05 UTC] 新增边: plan:question-gen-synth --implements--> design:question-gen-synth
|
- [2026-07-09 09:05 UTC] 新增边: plan:question-gen-synth --implements--> design:question-gen-synth
|
||||||
- [2026-07-09 09:05 UTC] 重建索引: 28 篇页面
|
- [2026-07-09 09:05 UTC] 重建索引: 28 篇页面
|
||||||
|
- [2026-07-09 12:41 UTC] 新增 design: main.py 推理入口 + 初始 Prompt 集设计 (design:main-inference-entry)
|
||||||
|
- [2026-07-09 12:41 UTC] 重建索引: 30 篇页面
|
||||||
|
|||||||
Reference in New Issue
Block a user