mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-08-04 22:32:12 +03:00
62e0920e5e
OpenAI / Codex / Azure-OpenAI use automatic prefix caching: the upstream caches the longest matching prefix of a request (system prompt + earliest messages) WITHOUT any explicit cache_control markers. The cache-aware compression guard only protected that prefix when the body carried explicit cache_control, so for automatic-cache providers the guard was skipped — and with compression active + preserveSystemPrompt:false (or a prefix-compressing mode) it rewrote the prefix, guaranteeing a cache miss and higher token spend through OmniRoute than going direct. getCacheAwareStrategy now treats isCachingProvider alone as sufficient to skip the system prompt and downgrade aggressive/ultra (the explicit cache_control path is a subset). openai/codex/azure are added to CACHING_PROVIDERS so they are recognized as automatic-cache providers (this also activates the intended prompt_cache_key cache-routing hint for OpenAI in chatCore). Compression remains off by default — this only affects operators who enabled it with prefix preservation turned off. TDD: tests/unit/compression-cache-guard-3955.test.ts (RED 5/7 fail → GREEN 7/7). Aligned the existing cachingAware / strategySelector-cache-aware / cache-control-policy / cache-control-claude-providers tests that encoded the old (buggy) "openai is non-caching" behavior. Refs #3955
61 lines
2.4 KiB
TypeScript
61 lines
2.4 KiB
TypeScript
/**
|
|
* Tests for #3890: the cache-aware `skipSystemPrompt` flag was computed by
|
|
* getCacheAwareStrategy() but dropped by selectCompressionStrategy() (which can only
|
|
* return a mode string). resolveCacheAwareConfig() applies it: in a caching context the
|
|
* system prompt must stay uncompressed (it is part of the cacheable prefix) even when the
|
|
* operator disabled preserveSystemPrompt.
|
|
*/
|
|
|
|
import { describe, it } from "node:test";
|
|
import assert from "node:assert/strict";
|
|
import { resolveCacheAwareConfig } from "../../../open-sse/services/compression/strategySelector.ts";
|
|
import type { CompressionConfig } from "../../../open-sse/services/compression/types.ts";
|
|
|
|
function cfg(overrides: Partial<CompressionConfig> = {}): CompressionConfig {
|
|
return {
|
|
enabled: true,
|
|
defaultMode: "standard",
|
|
autoTriggerTokens: 0,
|
|
cacheMinutes: 5,
|
|
preserveSystemPrompt: true,
|
|
comboOverrides: {},
|
|
...overrides,
|
|
} as CompressionConfig;
|
|
}
|
|
|
|
describe("resolveCacheAwareConfig (#3890)", () => {
|
|
it("forces preserveSystemPrompt on for a caching request that disabled it", () => {
|
|
const out = resolveCacheAwareConfig(
|
|
cfg({ preserveSystemPrompt: false }),
|
|
{ messages: [{ role: "system", content: "x", cache_control: { type: "ephemeral" } }] },
|
|
{ provider: "anthropic", targetFormat: "claude" }
|
|
);
|
|
assert.equal(out.preserveSystemPrompt, true);
|
|
});
|
|
|
|
it("leaves a non-caching request untouched (preserveSystemPrompt stays false)", () => {
|
|
// google has no prompt caching, so the prefix-protection guard does not apply.
|
|
// (openai/codex now count as automatic-cache providers per #3955.)
|
|
const out = resolveCacheAwareConfig(
|
|
cfg({ preserveSystemPrompt: false }),
|
|
{ messages: [{ role: "system", content: "x" }] },
|
|
{ provider: "google" }
|
|
);
|
|
assert.equal(out.preserveSystemPrompt, false);
|
|
});
|
|
|
|
it("returns the same config object when there is no body", () => {
|
|
const base = cfg({ preserveSystemPrompt: false });
|
|
assert.equal(resolveCacheAwareConfig(base), base);
|
|
});
|
|
|
|
it("does not change a config that already preserves the system prompt", () => {
|
|
const out = resolveCacheAwareConfig(
|
|
cfg({ preserveSystemPrompt: true }),
|
|
{ messages: [{ role: "system", content: "x", cache_control: { type: "ephemeral" } }] },
|
|
{ provider: "anthropic", targetFormat: "claude" }
|
|
);
|
|
assert.equal(out.preserveSystemPrompt, true);
|
|
});
|
|
});
|