fix(core): recover v2 context overflow (#31005)

packages/llm/test/executor.test.ts

@@ -73,6 +73,46 @@ const expectLLMError = (error: unknown) => {
 const errorHttp = (error: LLMError) => ("http" in error.reason ? error.reason.http : undefined)
 
 describe("RequestExecutor", () => {
+  it.effect("classifies context overflow responses", () =>
+    Effect.gen(function* () {
+      const executor = yield* RequestExecutor.Service
+      const error = yield* executor.execute(request).pipe(Effect.flip)
+
+      expectLLMError(error)
+      expect(error.reason).toMatchObject({ _tag: "InvalidRequest", classification: "context-overflow" })
+    }).pipe(
+      Effect.provide(
+        responsesLayer([
+          new Response('{"error":{"code":"context_length_exceeded","message":"prompt too long"}}', {
+            status: 400,
+          }),
+        ]),
+      ),
+    ),
+  )
+
+  it.effect("does not classify generic HTTP 413 payload errors as context overflow", () =>
+    Effect.gen(function* () {
+      const executor = yield* RequestExecutor.Service
+      const error = yield* executor.execute(request).pipe(Effect.flip)
+
+      expectLLMError(error)
+      expect(error.reason).toMatchObject({ _tag: "InvalidRequest" })
+      expect("classification" in error.reason ? error.reason.classification : undefined).toBeUndefined()
+    }).pipe(Effect.provide(responsesLayer([new Response("request too large", { status: 413 })]))),
+  )
+
+  it.effect("does not classify ordinary invalid requests as context overflow", () =>
+    Effect.gen(function* () {
+      const executor = yield* RequestExecutor.Service
+      const error = yield* executor.execute(request).pipe(Effect.flip)
+
+      expectLLMError(error)
+      expect(error.reason).toMatchObject({ _tag: "InvalidRequest" })
+      expect("classification" in error.reason ? error.reason.classification : undefined).toBeUndefined()
+    }).pipe(Effect.provide(responsesLayer([new Response("invalid parameter", { status: 400 })]))),
+  )
+
   it.effect("returns redacted diagnostics for retryable rate limits", () =>
     Effect.gen(function* () {
       const executor = yield* RequestExecutor.Service

packages/llm/test/provider/anthropic-messages.test.ts

@@ -477,6 +477,29 @@ describe("Anthropic Messages route", () => {
     }),
   )
 
+  it.effect("classifies prompt-too-long provider errors", () =>
+    Effect.gen(function* () {
+      const response = yield* LLMClient.generate(request).pipe(
+        Effect.provide(
+          fixedResponse(
+            sseEvents({
+              type: "error",
+              error: { type: "invalid_request_error", message: "prompt is too long: 210000 tokens" },
+            }),
+          ),
+        ),
+      )
+
+      expect(response.events).toEqual([
+        {
+          type: "provider-error",
+          message: "invalid_request_error: prompt is too long: 210000 tokens",
+          classification: "context-overflow",
+        },
+      ])
+    }),
+  )
+
   it.effect("falls back to error type when no message is present", () =>
     Effect.gen(function* () {
       const response = yield* LLMClient.generate(request).pipe(

packages/llm/test/provider/bedrock-converse.test.ts

@@ -351,6 +351,23 @@ describe("Bedrock Converse route", () => {
     }),
   )
 
+  it.effect("classifies input-too-long validation exceptions", () =>
+    Effect.gen(function* () {
+      const response = yield* LLMClient.generate(baseRequest).pipe(
+        Effect.provide(
+          fixedBytes(eventStreamBody(["validationException", { message: "Input is too long for requested model" }])),
+        ),
+      )
+
+      expect(response.events.find((event) => event.type === "provider-error")).toEqual({
+        type: "provider-error",
+        message: "Input is too long for requested model",
+        classification: "context-overflow",
+        retryable: false,
+      })
+    }),
+  )
+
   it.effect("rejects requests with no auth path", () =>
     Effect.gen(function* () {
       const unsignedModel = AmazonBedrock.configure({

packages/llm/test/provider/openai-responses.test.ts

@@ -1351,7 +1351,13 @@ describe("OpenAI Responses route", () => {
         ),
       )
 
-      expect(response.events).toEqual([{ type: "provider-error", message: "context_length_exceeded: prompt too long" }])
+      expect(response.events).toEqual([
+        {
+          type: "provider-error",
+          message: "context_length_exceeded: prompt too long",
+          classification: "context-overflow",
+        },
+      ])
     }),
   )