fix(core): run HTTP hooks for session generate (#42965)

Co-authored-by: Aiden Cline <rekram1-node@users.noreply.github.com>

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

@@ -11,6 +11,7 @@ import { SessionContext } from "./context.js"
 import { SessionGenerate } from "./generate.js"
 import { SessionHistory } from "./history.js"
 import { SessionModelHeaders } from "./model-headers.js"
+import { SessionModelHttp } from "./model-http.js"
 import { SessionPromptCacheKey } from "./prompt-cache-key.js"
 import { SessionRunnerModel } from "./runner/model.js"
 import { SessionSystemPrompt } from "./system-prompt.js"
@@ -79,6 +80,13 @@ export const layer = Layer.effect(
             messages: contextEvent.messages,
             tools: hookedTools,
           }),
+          {
+            http: SessionModelHttp.middleware(hooks, {
+              sessionID: selection.session.id,
+              agent: selection.agent.id,
+              model: model.ref,
+            }),
+          },
         )
         yield* Effect.logInfo("session generation usage diagnostic", { usage: response.usage })
         return response.text

packages/core/test/session-generate.test.ts

@@ -51,15 +51,17 @@ import { Effect, Layer, Schema, Stream } from "effect"
 import { testEffect } from "./lib/effect"
 
 const requests: LLMRequest[] = []
+let hasHttpMiddleware = false
 let instruction: string | Instructions.Unavailable = "Initial context"
 const sessionID = SessionSchema.ID.make("ses_generate_test")
 
 const model = LanguageModel.make({ id: "generate-model", provider: "test", route: OpenAIChat.route })
 const client = Layer.mock(LLMClient.Service)({
   stream: () => Stream.die(new Error("unused")),
-  generate: (request) =>
+  generate: (request, options) =>
     Effect.sync(() => {
       requests.push(request)
+      hasHttpMiddleware = typeof options?.http === "function"
       const response = LLMResponse.fromEvents([
         LLMEvent.stepStart({ index: 0 }),
         LLMEvent.textStart({ id: "generate" }),
@@ -221,6 +223,7 @@ const setup = Effect.gen(function* () {
 it.effect("generates from fresh settled Session context without durable mutation", () =>
   Effect.gen(function* () {
     requests.length = 0
+    hasHttpMiddleware = false
     instruction = "Initial context"
     const { db, bus, instructions } = yield* setup
     yield* InstructionState.prepare(db, bus, instructions, sessionID)
@@ -298,6 +301,7 @@ it.effect("generates from fresh settled Session context without durable mutation
 
     expect(result).toBe("Transient answer")
     expect(requests).toHaveLength(1)
+    expect(hasHttpMiddleware).toBe(true)
     expect(requests[0]?.model).toBe(model)
     expect(requests[0]?.system[0]?.text).toBe("Hooked system")
     expect(requests[0]?.system.map((part) => part.text)).toContain("Initial context")