From 121f0edbf48ca0a93fb0941fb1d5ed2ce6f81407 Mon Sep 17 00:00:00 2001
From: Armin Ronacher <armin.ronacher@active-4.com>
Date: Sat, 13 Jun 2026 00:01:14 +0200
Subject: [PATCH] fix(ai): detect parenthesized context overflow errors

closes #5677
---
 packages/ai/CHANGELOG.md          | 1 +
 packages/ai/src/utils/overflow.ts | 5 +++--
 packages/ai/test/overflow.test.ts | 7 +++++++
 3 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/packages/ai/CHANGELOG.md b/packages/ai/CHANGELOG.md
index b7b1112d..167908b6 100644
--- a/packages/ai/CHANGELOG.md
+++ b/packages/ai/CHANGELOG.md
@@ -6,6 +6,7 @@
 
 ### Fixed
 
+- Fixed OpenAI-compatible context overflow detection for parenthesized `maximum context length (N)` errors ([#5677](https://github.com/earendil-works/pi/issues/5677)).
 - Fixed OpenAI GPT-5.4/GPT-5.5 and OpenAI Codex GPT-5.4/GPT-5.4 mini/GPT-5.5 context window metadata to match current OpenAI limits ([#5644](https://github.com/earendil-works/pi/issues/5644)).
 - Increased the OpenAI Codex Responses SSE response-header timeout to 20 seconds to reduce false-positive stalls while retaining the bounded wait introduced for zero-event hangs ([#4945](https://github.com/earendil-works/pi/issues/4945)).
 - Fixed Claude Fable 5 thinking-off requests to omit Anthropic's unsupported `thinking.type: "disabled"` payload ([#5567](https://github.com/earendil-works/pi/pull/5567) by [@tmustier](https://github.com/tmustier)).
diff --git a/packages/ai/src/utils/overflow.ts b/packages/ai/src/utils/overflow.ts
index e3a9b37a..623b873a 100644
--- a/packages/ai/src/utils/overflow.ts
+++ b/packages/ai/src/utils/overflow.ts
@@ -12,6 +12,7 @@ import type { AssistantMessage } from "../types.ts";
  * - Anthropic: "413 {\"error\":{\"type\":\"request_too_large\",\"message\":\"Request exceeds the maximum size\"}}"
  * - OpenAI: "Your input exceeds the context window of this model"
  * - OpenAI/LiteLLM: "Requested token count exceeds the model's maximum context length of 131072 tokens"
+ * - OpenAI-compatible: "Input length (265330) exceeds model's maximum context length (262144)."
  * - Google: "The input token count (1196265) exceeds the maximum number of tokens allowed (1048575)"
  * - xAI: "This model's maximum prompt length is 131072 but the request contains 537812 tokens"
  * - Groq: "Please reduce the length of the messages or completion"
@@ -36,7 +37,7 @@ const OVERFLOW_PATTERNS = [
 	/request_too_large/i, // Anthropic request byte-size overflow (HTTP 413)
 	/input is too long for requested model/i, // Amazon Bedrock
 	/exceeds the context window/i, // OpenAI (Completions & Responses API)
-	/exceeds (?:the )?(?:model'?s )?maximum context length of [\d,]+ tokens?/i, // OpenAI-compatible proxies (LiteLLM)
+	/exceeds (?:the )?(?:model'?s )?maximum context length(?: of [\d,]+ tokens?|\s*\([\d,]+\))/i, // OpenAI-compatible proxies (LiteLLM)
 	/input token count.*exceeds the maximum/i, // Google (Gemini)
 	/maximum prompt length is \d+/i, // xAI (Grok)
 	/reduce the length of the messages/i, // Groq
@@ -85,7 +86,7 @@ const NON_OVERFLOW_PATTERNS = [
  *
  * **Reliable detection (returns error with detectable message):**
  * - Anthropic: "prompt is too long: X tokens > Y maximum" or "request_too_large"
- * - OpenAI (Completions & Responses): "exceeds the context window" or "exceeds the model's maximum context length of X tokens"
+ * - OpenAI (Completions & Responses): "exceeds the context window", "exceeds the model's maximum context length of X tokens", or "exceeds model's maximum context length (X)"
  * - Google Gemini: "input token count exceeds the maximum"
  * - xAI (Grok): "maximum prompt length is X but request contains Y"
  * - Groq: "reduce the length of the messages"
diff --git a/packages/ai/test/overflow.test.ts b/packages/ai/test/overflow.test.ts
index 346d2006..62108911 100644
--- a/packages/ai/test/overflow.test.ts
+++ b/packages/ai/test/overflow.test.ts
@@ -49,6 +49,13 @@ describe("isContextOverflow", () => {
 		expect(isContextOverflow(message, 131072)).toBe(true);
 	});
 
+	it("detects OpenAI-compatible parenthesized maximum context length errors", () => {
+		const message = createErrorMessage(
+			"Error: 400 Input length (265330) exceeds model's maximum context length (262144).",
+		);
+		expect(isContextOverflow(message, 262144)).toBe(true);
+	});
+
 	it("detects OpenRouter Poolside maximum allowed input length errors", () => {
 		const message = createErrorMessage(
 			"Provider returned error: Input length 131393 exceeds the maximum allowed input length of 131040 tokens.",