fix(llm): expand context overflow patterns

packages/llm/src/provider-error.ts

@@ -3,13 +3,17 @@ import { LLMError, ProviderErrorEvent } from "./schema"
 
 const patterns = [
   /prompt is too long/i,
+  /request_too_large/i,
   /input is too long for requested model/i,
   /exceeds the context window/i,
+  /exceeds (?:the )?(?:model'?s )?maximum context length(?: of [\d,]+ tokens?|\s*\([\d,]+\))/i,
   /input token count.*exceeds the maximum/i,
   /tokens in request more than max tokens allowed/i,
   /maximum prompt length is \d+/i,
   /reduce the length of the messages/i,
   /maximum context length is \d+ tokens/i,
+  /exceeds (?:the )?maximum allowed input length of [\d,]+ tokens?/i,
+  /input \(\d+ tokens\) is longer than the model'?s context length \(\d+ tokens\)/i,
   /exceeds the limit of \d+/i,
   /exceeds the available context size/i,
   /greater than the context length/i,
@@ -21,11 +25,17 @@ const patterns = [
   /input length.*exceeds.*context length/i,
   /prompt too long; exceeded (?:max )?context length/i,
   /too large for model with \d+ maximum context length/i,
+  /prompt has [\d,]+ tokens?, but the configured context size is [\d,]+ tokens?/i,
   /model_context_window_exceeded/i,
+  /too many tokens/i,
+  /token limit exceeded/i,
 ]
 
+const exclusions = [/^(throttling error|service unavailable):/i, /rate limit/i, /too many requests/i]
+
 export const isContextOverflow = (message: string) =>
-  patterns.some((pattern) => pattern.test(message)) || /^4(00|13)\s*(status code)?\s*\(no body\)/i.test(message)
+  !exclusions.some((pattern) => pattern.test(message)) &&
+  (patterns.some((pattern) => pattern.test(message)) || /^4(00|13)\s*(status code)?\s*\(no body\)/i.test(message))
 
 export const isContextOverflowFailure = (failure: unknown) =>
   failure instanceof LLMError

packages/llm/test/provider-error.test.ts

@@ -2,7 +2,29 @@ import { describe, expect, test } from "bun:test"
 import { isContextOverflow } from "../src"
 
 describe("provider error classification", () => {
-  test("classifies Z.AI GLM token limit messages as context overflow", () => {
-    expect(isContextOverflow("tokens in request more than max tokens allowed")).toBe(true)
+  test("classifies provider token limit messages as context overflow", () => {
+    const messages = [
+      "tokens in request more than max tokens allowed",
+      '{"error":{"type":"request_too_large","message":"Request exceeds the maximum size"}}',
+      "Requested token count exceeds the model's maximum context length of 131072 tokens.",
+      "Input length (265330) exceeds model's maximum context length (262144).",
+      "Input length 131393 exceeds the maximum allowed input length of 131040 tokens.",
+      "The input (516368 tokens) is longer than the model's context length (262144 tokens).",
+      "Prompt has 5,958,968 tokens, but the configured context size is 256,000 tokens",
+      "Too many tokens",
+      "Token limit exceeded",
+    ]
+
+    expect(messages.every(isContextOverflow)).toBe(true)
+  })
+
+  test("does not classify rate limits as context overflow", () => {
+    const messages = [
+      "Throttling error: Too many tokens, please wait before trying again.",
+      "Rate limit exceeded, please retry after 30 seconds.",
+      "Too many requests. Please slow down.",
+    ]
+
+    expect(messages.some(isContextOverflow)).toBe(false)
   })
 })