From 208ea0e0f7bfcaa9a3da411c558d5c1564fc8937 Mon Sep 17 00:00:00 2001 From: Aiden Cline <63023139+rekram1-node@users.noreply.github.com> Date: Fri, 30 Oct 2026 15:40:56 -0500 Subject: [PATCH] fix(ai): recognize LiteLLM context overflow errors (#60692) --- packages/ai/src/provider-error.ts | 2 ++ packages/ai/test/provider-error.test.ts | 2 ++ packages/core/test/session-runner.test.ts | 20 ++++++++++++++++++++ 3 files changed, 24 insertions(+) diff --git a/packages/ai/src/provider-error.ts b/packages/ai/src/provider-error.ts index 3b3817d4f80..c34160b6065 100644 --- a/packages/ai/src/provider-error.ts +++ b/packages/ai/src/provider-error.ts @@ -42,6 +42,8 @@ const patterns = [ // Hugging Face Text Generation Inference, e.g. Together /`inputs` tokens \+ `max_new_tokens` must be <= \d+/i, /context window exceeds limit/i, + // LiteLLM's ContextWindowExceededError + /context window exceeded/i, /exceeded model token limit/i, /context[_ ]length[_ ]exceeded/i, /context length is only \d+ tokens/i, diff --git a/packages/ai/test/provider-error.test.ts b/packages/ai/test/provider-error.test.ts index 9f1e46ad37d..84c38fa1605 100644 --- a/packages/ai/test/provider-error.test.ts +++ b/packages/ai/test/provider-error.test.ts @@ -21,6 +21,8 @@ describe("provider error classification", () => { "Prompt exceeds max length", "The input is too long for the selected model.", "This text request is too large for the model's configured input limit.", + // LiteLLM's own check, before it calls the model. + "litellm.ContextWindowExceededError: litellm.BadRequestError: litellm._pre_call_checks: Context Window exceeded for given call. No models have context window large enough for this call.", ] expect(messages.every(isContextOverflow)).toBe(true) diff --git a/packages/core/test/session-runner.test.ts b/packages/core/test/session-runner.test.ts index 948d3d86176..d91c8d18dd6 100644 --- a/packages/core/test/session-runner.test.ts +++ b/packages/core/test/session-runner.test.ts @@ -5952,6 +5952,26 @@ describe("SessionRunnerLLM", () => { }) } + scenario("compacts when the provider cuts an oversized prompt to its window and replies with nothing", function* (s) { + // Xiaomi MiMo answers an oversized prompt with HTTP 200, finish "length", no output, and a prompt count that fills + // the window instead of rejecting it. + s.currentModel = recoveryModel + yield* s.llm.push( + TestLLM.complete({ reason: { normalized: "length" }, usage: { inputTokens: 199_994, nonCachedInputTokens: 199_994, outputTokens: 0 } }), + TestLLM.text("## Objective\n- summary", "summary"), + TestLLM.text("Done", "done"), + ) + + yield* s.runPrompt("Large prompt") + + expect(s.requests).toHaveLength(3) + expect(userTexts(s.requests[1]).at(-1)).toContain("Summarize only what the user and the assistant said and did") + expect((yield* s.messages).filter((message) => message.type === "compaction")).toMatchObject([ + { status: "completed" }, + ]) + expect((yield* s.context).at(-1)).toMatchObject(Expected.assistant({ finish: "stop" }, [Expected.text("Done")])) + }) + for (const tools of ["hosted", "unfinished"] as const) { scenario(`caps output token limit continuations and resets for new input (${tools})`, function* (s) { const toolEvents =