mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-08-17 04:32:31 +03:00
2b2d947faf
* fix(cache): add latency marker + per-key bypass for semantic cache
Semantic cache silently corrupts latency measurements: a 10s upstream
call served from cache looks like 19ms. Three fixes:
A. Latency marker: cache HIT responses now carry
X-OmniRoute-Cache-Latency: synthetic so measurement tools can
distinguish real vs cached latency.
B. Per-key bypass: new apiKeys.cacheDefaultMode ('legacy' | 'bypass')
lets latency-sensitive clients opt out of cache reads entirely.
- DB column + migration (134)
- rowParser parseCacheDefaultMode
- API create default + PATCH update
- checkSemanticCache returns null on bypass
C. Type safety: ApiKeyRow/ApiKeyView/params updated, superRefine
guard includes cacheDefaultMode.
Cache write path intentionally unchanged: apiKeyId is already in the
cache signature (semanticCache.ts:140), so per-key isolation prevents
cross-key pollution.
Changed test files:
- tests/unit/chatcore-semantic-cache.test.ts (3 new tests)
Signed-off-by: Minxi Hou <houminxi@gmail.com>
* docs: document semantic cache latency impact + bypass configuration
---------
Signed-off-by: Minxi Hou <houminxi@gmail.com>
19 lines
673 B
TypeScript
19 lines
673 B
TypeScript
export const OMNIROUTE_RESPONSE_HEADERS = {
|
|
cache: "X-OmniRoute-Cache",
|
|
cacheHit: "X-OmniRoute-Cache-Hit",
|
|
cacheLatency: "X-OmniRoute-Cache-Latency",
|
|
compression: "X-OmniRoute-Compression",
|
|
costSaved: "X-OmniRoute-Cost-Saved",
|
|
decision: "X-OmniRoute-Decision",
|
|
fallbackAttempts: "X-OmniRoute-Fallback-Attempts",
|
|
latencyMs: "X-OmniRoute-Latency-Ms",
|
|
model: "X-OmniRoute-Model",
|
|
progress: "X-OmniRoute-Progress",
|
|
provider: "X-OmniRoute-Provider",
|
|
requestId: "X-OmniRoute-Request-Id",
|
|
responseCost: "X-OmniRoute-Response-Cost",
|
|
tokensIn: "X-OmniRoute-Tokens-In",
|
|
tokensOut: "X-OmniRoute-Tokens-Out",
|
|
version: "X-OmniRoute-Version",
|
|
} as const;
|