fix(ai): send Baseten session affinity headers

Enable session affinity for cataloged Baseten models so related requests reach the same replica and benefit from prompt caching.

Closes #9629

packages/ai/CHANGELOG.md

@@ -20,6 +20,7 @@
 - Removed GPT-5.4 and GPT-5.4 mini from the OpenAI Codex catalog after they became unavailable to ChatGPT accounts ([#9394](https://github.com/earendil-works/pi/issues/9394)).
 - Fixed Mistral-hosted GLM-5.2 reasoning requests to use `reasoning_effort` instead of the ignored `prompt_mode` ([#9375](https://github.com/earendil-works/pi/issues/9375)).
 - Fixed OpenAI-compatible Responses errors to identify the actual provider instead of always labeling them as OpenAI errors ([#9298](https://github.com/earendil-works/pi/issues/9298)).
+- Fixed Baseten requests to send session-affinity headers from `sessionId` for automatic prompt-cache routing ([#9629](https://github.com/earendil-works/pi/issues/9629)).
 
 ## [0.85.1] - 2026-09-05
 

packages/ai/scripts/generate-models.ts

@@ -1333,6 +1333,10 @@ function processBasetenModels(provider: ModelsDevProvider | undefined): Model<Ap
 		supportsUsageInStreaming: true,
 		maxTokensField: "max_tokens",
 		supportsStrictMode: true,
+		// Baseten automatic prompt caching needs session affinity so related
+		// requests land on the same replica. See:
+		// https://docs.baseten.co/inference/model-apis/pricing-and-limits
+		sendSessionAffinityHeaders: true,
 		supportsLongCacheRetention: false,
 	};
 	const reasoningEffortCompat: OpenAICompletionsCompat = {

packages/ai/test/openai-completions-prompt-cache.test.ts

@@ -181,6 +181,14 @@ describe("openai-completions prompt caching", () => {
 		},
 	);
 
+	it("sends Baseten session affinity for built-in catalog models", async () => {
+		const model = getModel("baseten", "zai-org/GLM-5.2");
+		const { headers } = await captureRequest({ sessionId: "baseten-catalog-session" }, model);
+
+		expect(headers["x-session-affinity"]).toBe("baseten-catalog-session");
+		expect(headers["x-client-request-id"]).toBe("baseten-catalog-session");
+	});
+
 	it("uses OpenAI no-session format when configured", async () => {
 		const model = createModel({
 			compat: { sendSessionAffinityHeaders: true, sessionAffinityFormat: "openai-nosession" },