- prompts/collection.md: versioned collection system prompt extracted from workflow node yQaBxfrWjbRr with source/version/porting notes - llm.py: LLMService protocol; FakeLLMService (scripted, records calls); OpenAILLMService (async, wait_for timeout with cancellation, retry only on timeout/429/connection, errors normalized) - collect.py: run_collect reference impl - one LLM call produces state prefix + body, controlled repair (max 1 retry) for missing prefix or illegal stage proposal, whitelist guard, CollectReplyError without raw model content; dialogue history + confirmed fields injected into prompt so the model skips known info (作业4-5) - fields.py / clock.py: three-state field candidates (unknown/ candidate/confirmed), per-type validation (count not inferred from description, future time rejected), injectable Clock - graph.py: welcome node - first message returns fixed 1001 greeting without LLM (mirrors workflow is_first_message -> Assigned Reply#3), route empty stage to welcome - endpoints/delete_session: backend switch - langgraph clears graph checkpoint, fastgpt path unchanged - config: AGENT_LLM_PROVIDER fake|openai with validation - untrack .env (secrets), move template to root .env.example Verified: - pytest 103 passed; smoke turns 1/2/1 - Real LLM e2e: POST /chat multi-turn context works - Golden eval collection_skip_known_info: 12/12 cases pass - Golden eval no_false: 8/10 cases pass; 4 confirm/photo cases fail at final step - model routes on short reply '对' (prompt-adherence gap, photo/confirm stages are assignment 5 scope); recorded in evals/results/20261020-144856 Known limits: field extraction from model reply not wired (stub); photo/confirm nodes still scaffold; clarify counting is approximate.
2.9 KiB
2.9 KiB
AI 事故信息采集 API(LangGraph 迁移分支)
本分支是“将对话后端从 FastGPT 工作流迁移到 LangGraph”课程的迁移准备分支。
当前状态:对外 API 契约保持不变,/chat 的供应商细节已封装到后端适配层(FastGPT 仍
为唯一实现),迁移计划见 docs/langgraph-backend-migration-plan.md。
本阶段交付说明与验证证据见 docs/assignment-baseline.md。
环境要求
- Python 3.11(使用 Conda 环境
py3.11,见 AGENTS.md) fastgpt-clientSDK(当前以本地可编辑方式安装,见下文)
安装
conda activate py3.11
# 项目依赖
pip install -r requirements.txt
# FastGPT SDK(本地可编辑安装;SDK 源码在独立仓库维护)
pip install -e /path/to/fastgpt-python-sdk
配置
服务端通过环境变量读取 FastGPT 连接信息。复制示例配置并按环境填写:
cp .env.example .env
需要设置的变量:
| 变量 | 说明 |
|---|---|
ANALYSIS_SERVICE_URL |
FastGPT 服务地址 |
ANALYSIS_AUTH_TOKEN |
FastGPT API Key |
APP_ID |
FastGPT 应用 ID |
运行
python -m uvicorn src.main:app --host 127.0.0.1 --port 8000
GET /存活检查POST /chat对话(?stream=true为 SSE 流式)POST /set_info、POST /get_info、DELETE /delete_session业务数据接口
测试
conda run -n py3.11 python -m pytest -q
测试分三层:
test/api/test_public_schema_contract.py:公共请求/响应 schema 的契约冻结测试test/api/test_chat_backend_boundary.py:API 层与后端适配层的边界测试(fake 后端)test/backends/test_fastgpt_backend.py:FastGPT 适配器的翻译测试(fake SDK)
目录结构
src/
api/endpoints.py # HTTP 协议层:schema、state 前缀解析、SSE 事件
backends/chat.py # 后端中立契约(ChatBackend Protocol、ChatInput/ChatResult/事件)
backends/fastgpt.py # FastGPT 适配器:SDK 调用与响应翻译
core/fastgpt_client.py # 客户端生命周期与依赖注入(lifespan)
schemas/models.py # 公共 Pydantic 模型
docs/langgraph-backend-migration-plan.md # 十阶段迁移作业计划
evals/ # 调用真实服务的评测用例与 runner
已知限制
- LangGraph 脚手架与后端适配层骨架已就位(作业 1—2):
src/agent/、src/backends/langgraph.py、AGENT_BACKEND开关;节点逻辑与适配器实现 为待完成的 TODO,对应测试test/agent/、test/backends/test_langgraph_backend.py在完成前会失败,属预期状态。 set_info/get_info/delete_session仍直接依赖 FastGPT 状态与历史,迁移到共享 业务状态属于作业 6。- 服务启动需要有效的 FastGPT 配置;仅运行单元测试不需要。