Files
OmniRoute/open-sse/utils/cacheControlPolicy.ts
tombii 0bc557fb8b feat(sse): preserve client cache_control for Claude Code with deterministic routing
Adds intelligent cache control preservation for Claude Code clients:

- New cacheControlPolicy.ts module with detection logic:
  - isClaudeCodeClient(): Detects Claude Code via User-Agent
  - providerSupportsCaching(): Checks provider (claude, anthropic, zai, qwen)
  - isDeterministicStrategy(): Identifies priority/cost-optimized strategies
  - shouldPreserveCacheControl(): Main policy decision

- Cache control is preserved when:
  1. Client is Claude Code (detected via User-Agent)
  2. Provider supports prompt caching
  3. Request routing is deterministic:
     - Single model requests (always)
     - Combo with priority or cost-optimized strategy only

- Updated translator to accept preserveCacheControl option
- Updated chatCore and chat handler to propagate combo strategy
- Added comprehensive unit tests (24 tests)

Non-deterministic combo strategies (weighted, round-robin, random, etc.)
continue to use OmniRoute's managed caching strategy.

Refs: #cache-control-preservation
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-29 12:24:44 +02:00

101 lines
2.9 KiB
TypeScript

/**
* Cache Control Policy
*
* Determines when to preserve client-side prompt caching headers (cache_control)
* vs. applying OmniRoute's own caching strategy.
*
* Client-side caching (e.g., Claude Code) should be preserved when:
* 1. Client is Claude Code or similar caching-aware client
* 2. Request will hit a deterministic target (single model or deterministic combo strategy)
* 3. Provider supports prompt caching (Anthropic, Alibaba Qwen, etc.)
*/
import type { RoutingStrategyValue } from "../../src/shared/constants/routingStrategies";
/**
* Routing strategies that are deterministic (same request → same provider)
*/
const DETERMINISTIC_STRATEGIES: Set<RoutingStrategyValue> = new Set([
"priority",
"cost-optimized",
]);
/**
* Providers that support prompt caching
*/
const CACHING_PROVIDERS = new Set([
"claude",
"anthropic",
"zai",
"qwen", // Alibaba Qwen Coding Plan International
]);
/**
* Detect if the client is Claude Code or another caching-aware client
*/
export function isClaudeCodeClient(userAgent: string | null | undefined): boolean {
if (!userAgent) return false;
const ua = userAgent.toLowerCase();
// Claude Code user agents
if (ua.includes("claude-code") || ua.includes("claude_code")) return true;
if (ua.includes("anthropic") && ua.includes("cli")) return true;
return false;
}
/**
* Check if a provider supports prompt caching
*/
export function providerSupportsCaching(provider: string | null | undefined): boolean {
if (!provider) return false;
return CACHING_PROVIDERS.has(provider.toLowerCase());
}
/**
* Check if a routing strategy is deterministic
*/
export function isDeterministicStrategy(strategy: RoutingStrategyValue | null | undefined): boolean {
if (!strategy) return false;
return DETERMINISTIC_STRATEGIES.has(strategy);
}
/**
* Determine if client-side cache_control headers should be preserved
*
* @param userAgent - User-Agent header from the request
* @param isCombo - Whether this is a combo model
* @param comboStrategy - The combo's routing strategy (if applicable)
* @param targetProvider - The target provider for the request
* @returns true if cache_control should be preserved, false if OmniRoute should manage it
*/
export function shouldPreserveCacheControl({
userAgent,
isCombo,
comboStrategy,
targetProvider,
}: {
userAgent: string | null | undefined;
isCombo: boolean;
comboStrategy?: RoutingStrategyValue | null;
targetProvider: string | null | undefined;
}): boolean {
// Must be a caching-aware client
if (!isClaudeCodeClient(userAgent)) {
return false;
}
// Target provider must support caching
if (!providerSupportsCaching(targetProvider)) {
return false;
}
// Single model: always preserve (deterministic)
if (!isCombo) {
return true;
}
// Combo: only preserve if strategy is deterministic
return isDeterministicStrategy(comboStrategy);
}