refactor(ai): promote prompt cache key (#39965)

packages/core/src/aisdk-native.ts

@@ -263,6 +263,7 @@ function mapOpenRouterOptions(settings: Readonly<Record<string, unknown>>) {
           "extraBody",
           "fetch",
           "headers",
+          "promptCacheKey",
           "timeout",
         ].includes(key),
     ),
@@ -279,7 +280,6 @@ function mapXAIOptions(settings: Readonly<Record<string, unknown>>) {
   const options = {
     ...(typeof settings.reasoningEffort === "string" ? { reasoningEffort: settings.reasoningEffort } : {}),
     ...(typeof settings.store === "boolean" ? { store: settings.store } : {}),
-    ...(typeof settings.promptCacheKey === "string" ? { promptCacheKey: settings.promptCacheKey } : {}),
   }
   if (Object.keys(options).length === 0) return {}
   return { providerOptions: { xai: options } }

packages/core/src/session/compaction.ts

@@ -11,6 +11,7 @@ import { llmClient } from "../effect/app-node-platform"
 import { SessionEvent } from "./event"
 import type { SessionMessage } from "./message"
 import { SessionModelHeaders } from "./model-headers"
+import { SessionPromptCacheKey } from "./prompt-cache-key"
 import { App } from "../app"
 import { SessionRunnerModel } from "./runner/model"
 import { SessionSchema } from "./schema"
@@ -258,6 +259,7 @@ const make = (dependencies: Dependencies) => {
       .stream(
         LLM.request({
           model: plan.model,
+          promptCacheKey: SessionPromptCacheKey.make(plan.session.id),
           http: { headers: SessionModelHeaders.make(plan.session, dependencies.app) },
           messages: [Message.user(plan.prompt)],
           tools: [],

packages/core/src/session/generate-node.ts

@@ -11,6 +11,7 @@ import { SessionContext } from "./context"
 import { SessionGenerate } from "./generate"
 import { SessionHistory } from "./history"
 import { SessionModelHeaders } from "./model-headers"
+import { SessionPromptCacheKey } from "./prompt-cache-key"
 import { SessionRunnerModel } from "./runner/model"
 import PROMPT_DEFAULT from "./runner/prompt/base.txt"
 import { toLLMMessages } from "./runner/to-llm-message"
@@ -31,9 +32,6 @@ export const layer = Layer.effect(
         const model = yield* models.resolve(selection.session)
         const history = yield* SessionHistory.preview(database.db, selection.session.id, selection.instructions)
         const providerMetadataKey = model.model.route.providerMetadataKey ?? model.model.provider
-        const promptCacheKey = /^ses_[0-9a-f]{64}$/.test(selection.session.id)
-          ? selection.session.id.slice(4)
-          : selection.session.id
         const tools = selection.tools
         const toolDefinitions = tools.definitions
         const toolsByName = new Map(toolDefinitions.map((tool) => [tool.name, tool]))
@@ -71,7 +69,7 @@ export const layer = Layer.effect(
           LLM.request({
             model: model.model,
             http: { headers: SessionModelHeaders.make(selection.session, app) },
-            providerOptions: { [providerMetadataKey]: { promptCacheKey } },
+            promptCacheKey: SessionPromptCacheKey.make(selection.session.id),
             system: contextEvent.system,
             messages: contextEvent.messages,
             tools: hookedTools,

packages/core/src/session/model-request.ts

@@ -15,6 +15,7 @@ import { QuestionTool } from "../tool/plugin/question"
 import { Tool } from "../tool"
 import { SessionContext } from "./context"
 import { SessionModelHeaders } from "./model-headers"
+import { SessionPromptCacheKey } from "./prompt-cache-key"
 import { PromptCacheDiagnostics } from "./prompt-cache-diagnostics"
 import { MAX_STEPS_PROMPT } from "./runner/max-steps"
 import PROMPT_DEFAULT from "./runner/prompt/base.txt"
@@ -181,7 +182,6 @@ export const layer = Layer.effect(
       // The final Step keeps definitions available to protocols with native "none",
       // preserving their prompt cache prefix. Calls are still rejected at execution.
       const tools = input.context.tools
-      const promptCacheKey = /^ses_[0-9a-f]{64}$/.test(session.id) ? session.id.slice(4) : session.id
       const system = [agent.info.system ? agent.info.system : PROMPT_DEFAULT, input.context.initial]
         .filter((part) => part.length > 0)
         .map(SystemPart.make)
@@ -220,7 +220,7 @@ export const layer = Layer.effect(
         http: {
           headers: SessionModelHeaders.make(session, app),
         },
-        providerOptions: { [providerMetadataKey]: { promptCacheKey } },
+        promptCacheKey: SessionPromptCacheKey.make(session.id),
         system: context.system,
         messages: boundImages(unsupportedParts(context.messages, resolved.capabilities)),
         tools: Array.from(hooked, ([name, tool]) => ({ ...tool, name })),

packages/core/src/session/prompt-cache-key.ts

@@ -0,0 +1,6 @@
+export * as SessionPromptCacheKey from "./prompt-cache-key"
+
+import { SessionSchema } from "./schema"
+
+export const make = (sessionID: SessionSchema.ID) =>
+  /^ses_[0-9a-f]{64}$/.test(sessionID) ? sessionID.slice(4) : sessionID