✨ feat: WP-05 模型网关核心——逻辑模型、流式适配与 Run 真实执行
- 迁移 7+8:logical_model(能力目录)、provider_endpoint(密钥只存环境变量名,永不落库)、turn、model_call(每 attempt 单独持久化:usage/TTFT/错误,Provider 未返回保持 null 不估算——ADR-003);message.run_id 关联 - OpenAI-compatible 流式适配器:httpx SSE 解析、标准化 StreamChunk(delta/usage/done)、transport 可注入(测试与故障注入);密钥经环境变量读取不进日志 - Run 执行器:后台执行完整生命周期——running → content.block.started → 真实 content.block.delta*(流式产生,delta_index 单调)→ content.block.completed → message.completed → 终态;assistant 消息为权威快照;ModelCall 记录 usage 与 TTFT;无可用端点时 Run 显式失败并留 error 事件(fail-closed) - post_message:响应提交后由框架 BackgroundTasks 执行 Run(显式预提交保证 Run 落库);SSE 改为增量轮询(重放 + 等待新事件至终态,30s 上限) - 测试 54 项全绿(+2):端到端 mock 流验证 ModelCall usage/TTFT/assistant 权威消息、无端点 Run failed + content.block.failed 事件
This commit is contained in:
1 parent
40221170ae
commit
b4242f3844
10 files changed
+789
-56
No files matched your search
@@ -0,0 +1,6 @@
|
||||
"""模型网关:路由与 Run 执行(WP-05)。"""
|
||||
|
||||
from .adapters import AdapterRequest, GatewayError, stream_chat
|
||||
from .runner import execute_run
|
||||
|
||||
__all__ = ["AdapterRequest", "GatewayError", "stream_chat", "execute_run"]
|
||||
Reference in new issue
Block a user