feat: M1 — 立项→写章草稿(SSE)→自动保存;连一家 provider

- 薄自建 LLM 网关:OpenAI 兼容适配器(DeepSeek) + instructor 结构化输出 + usage_ledger 记账 + 档位路由
- 记忆服务 assemble:确定性选择(显式+主角+近况) + 渲染卡 + 缓存断点(中性文本)
- LangGraph 写章节点 + Postgres checkpointer + SSE 归一(token/done/error)
- API:立项 + 写章 draft(SSE) + PUT 自动保存 + 提供商凭据(Fernet 加密/测试连接)
- 前端:AppShell + 作品库 + 5 步立项向导 + 写作工作台(流式打字机+自动保存) + 设置页
- M1 E2E:真实 DB + mock 网关零 token 走通闭环
This commit is contained in:
Yaojia Wang
2026-06-18 11:38:28 +02:00
parent d3dc620a71
commit b523b4fd21
70 changed files with 6642 additions and 0 deletions

View File

@@ -0,0 +1,51 @@
"""适配器接口与中间数据形ARCH §4.2/§4.4)。
适配器把 `LlmRequest` 翻译成目标厂商请求,并把响应/流/usage 翻译回统一中间形。
"""
from __future__ import annotations
from collections.abc import AsyncIterator
from typing import Protocol, runtime_checkable
from pydantic import BaseModel, ConfigDict
from ..types import LlmRequest
class Capabilities(BaseModel):
structured_output: bool = False
prefix_cache: bool = False
thinking: bool = False
class ProviderUsage(BaseModel):
input_tokens: int
output_tokens: int
cache_read_tokens: int = 0
class ProviderResult(BaseModel):
model_config = ConfigDict(arbitrary_types_allowed=True)
text: str
usage: ProviderUsage
parsed: BaseModel | None = None # output_schema 命中时的结构化结果§4.4
class StreamChunk(BaseModel):
"""流式块文本增量usage=None或末尾用量块text="")。"""
text: str = ""
usage: ProviderUsage | None = None
@runtime_checkable
class ProviderAdapter(Protocol):
provider: str
def capabilities(self) -> Capabilities: ...
async def complete(self, req: LlmRequest, model: str) -> ProviderResult: ...
def stream(self, req: LlmRequest, model: str) -> AsyncIterator[StreamChunk]: ...