refactor(ai): promote prompt cache key

packages/ai/src/protocols/open-responses.ts

@@ -542,7 +542,7 @@ const lowerOptions = (request: LLMRequest) => {
   return {
     ...(options.instructions ? { instructions: options.instructions } : {}),
     ...(options.store !== undefined ? { store: options.store } : {}),
-    ...(options.promptCacheKey ? { prompt_cache_key: options.promptCacheKey } : {}),
+    ...(request.promptCacheKey ? { prompt_cache_key: request.promptCacheKey } : {}),
     ...(options.include ? { include: options.include } : {}),
     ...(options.reasoningEffort || options.reasoningSummary
       ? { reasoning: { effort: options.reasoningEffort, summary: options.reasoningSummary } }

packages/ai/src/protocols/utils/open-responses-options.ts

@@ -33,7 +33,6 @@ export const ServiceTierSchema = Schema.Literals(ServiceTiers)
 export interface Resolved {
   readonly instructions?: string
   readonly store?: boolean
-  readonly promptCacheKey?: string
   readonly reasoningEffort?: string
   readonly reasoningSummary?: "auto" | "concise" | "detailed"
   readonly include?: ReadonlyArray<ResponseIncludable>
@@ -50,7 +49,6 @@ export const resolve = (request: LLMRequest): Resolved => {
   return {
     instructions: typeof input?.instructions === "string" ? input.instructions : undefined,
     store: typeof input?.store === "boolean" ? input.store : undefined,
-    promptCacheKey: typeof input?.promptCacheKey === "string" ? input.promptCacheKey : undefined,
     reasoningEffort: typeof input?.reasoningEffort === "string" ? input.reasoningEffort : undefined,
     reasoningSummary:
       reasoningSummary === "auto" || reasoningSummary === "concise" || reasoningSummary === "detailed"

packages/ai/src/providers/open-responses-options.ts

@@ -5,7 +5,6 @@ export interface OpenResponsesOptionsInput {
   readonly [key: string]: unknown
   readonly instructions?: string
   readonly store?: boolean
-  readonly promptCacheKey?: string
   readonly reasoningEffort?: ReasoningEffort
   readonly reasoningSummary?: "auto" | "concise" | "detailed"
   readonly include?: ReadonlyArray<ResponseIncludable>

packages/ai/src/providers/openai-options.ts

@@ -17,7 +17,6 @@ const openAIProviderOptions = (options: OpenAIOptionsInput | undefined): Provide
   const openai = Object.fromEntries(
     definedEntries({
       store: options?.store,
-      promptCacheKey: options?.promptCacheKey,
       reasoningEffort: options?.reasoningEffort,
       reasoningSummary: options?.reasoningSummary,
       include: options?.include,

packages/ai/src/providers/openrouter.ts

@@ -55,7 +55,6 @@ export interface OpenRouterOptions {
   readonly debug?: Readonly<{ echo_upstream_body?: boolean }>
   readonly models?: ReadonlyArray<string>
   readonly plugins?: ReadonlyArray<OpenRouterPlugin>
-  readonly promptCacheKey?: string
   readonly provider?: OpenRouterProviderRouting
   readonly reasoning?: Readonly<{
     enabled?: boolean
@@ -122,6 +121,7 @@ export const protocol = Protocol.make({
             ...body,
             messages,
             ...bodyOptions(request.providerOptions?.openrouter),
+            ...(request.promptCacheKey ? { prompt_cache_key: request.promptCacheKey } : {}),
           } as OpenRouterBody
         }),
       ),
@@ -161,7 +161,6 @@ const bodyOptions = (input: unknown) => {
     ...(isRecord(debug) ? { debug } : {}),
     ...(typeof user === "string" ? { user } : {}),
     ...(isRecord(reasoning) ? { reasoning } : {}),
-    ...(typeof promptCacheKey === "string" ? { prompt_cache_key: promptCacheKey } : {}),
   }
 }
 

packages/ai/src/schema/messages.ts

@@ -272,6 +272,8 @@ export class LLMRequest extends Schema.Class<LLMRequest>("LLM.Request")({
   providerOptions: Schema.optional(ProviderOptions),
   http: Schema.optional(HttpOptions),
   cache: Schema.optional(CachePolicy),
+  // Stable cache affinity for protocols that support provider-managed prompt caching.
+  promptCacheKey: Schema.optional(Schema.String),
   metadata: Schema.optional(Schema.Record(Schema.String, Schema.Unknown)),
 }) {}
 
@@ -289,6 +291,7 @@ export namespace LLMRequest {
     providerOptions: request.providerOptions,
     http: request.http,
     cache: request.cache,
+    promptCacheKey: request.promptCacheKey,
     metadata: request.metadata,
   })