feat(sense): T-G1+T-G2 Embedder 与观察埋点
- T-G1 embedder.py:embed() 调 llama-server /v1/embeddings -> 对称 per-vector int8 量化(scale=127/max|v|,1024 维余弦扰动 ~1e-4 << 1e-2 验收); 超时/连接/非200/空形状 -> EmbedderDown(D-G4 fail-closed); /v1/embeddings OpenAI 兼容透传(双路由组:/sense 前缀 + /v1 无前缀, 不可用 503);build_sense_routers 返回列表 - T-G2 observer.py:Observation + 批量缓冲 100ms 刷盘(asyncio.Queue + to_thread,D-P10);三消费方共用;升级阶梯回写 outcome/executed_tier; D-G6 无 query 原文列(int8 BLOB + 特征 JSON) - 测试 +11(量化误差/范围/fail-closed×3/透传/单例/BLOB 持久化/批量刷盘/ 回写/无原文列),全量 381->386->381? 校正:386 passed - 待真机项:llama-server embedder 端点冒烟(需配置 embedder.base_url)
This commit is contained in:
+3
-2
@@ -216,11 +216,12 @@ try:
|
||||
|
||||
# 语义分析器(T-G0;D-G7:sense.enabled=False 时不注册任何路由)
|
||||
try:
|
||||
from gateway.sense import build_sense_router
|
||||
from gateway.sense import build_sense_routers
|
||||
from gateway.sense.config import build_sense_config
|
||||
_sense_cfg = build_sense_config(settings_store().to_dict())
|
||||
if _sense_cfg.enabled:
|
||||
app.include_router(build_sense_router(_sense_cfg))
|
||||
for _sr in build_sense_routers(_sense_cfg):
|
||||
app.include_router(_sr)
|
||||
except Exception as _se: # pragma: no cover
|
||||
print(f"[gateway] 语义分析器未启用({_se})")
|
||||
|
||||
|
||||
Reference in New Issue
Block a user