agent/pi
2
0
Fork 0
mirror of https://github.com/earendil-works/pi.git synced 2026-06-18 15:54:04 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix(ai): detect Poolside context overflow

Browse Source 
Closes #4943
This commit is contained in:
Armin Ronacher
2026-05-26 08:58:21 +02:00
Unverified
parent fc8a155901
commit fa1180b6b7
3 changed files with 16 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
packages/ai/CHANGELOG.md
+4
View File
@@ -2,6 +2,10 @@
## [Unreleased]
### Fixed
- Fixed OpenRouter/Poolside context overflow detection for `maximum allowed input length` errors ([#4943](https://github.com/earendil-works/pi/issues/4943)).
## [0.75.5] - 2026-05-23
### Breaking Changes
packages/ai/src/utils/overflow.ts
+5 -2
View File
@@ -16,6 +16,7 @@ import type { AssistantMessage } from "../types.ts";
* - 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"
* - OpenRouter: "This endpoint's maximum context length is X tokens. However, you requested about Y tokens"
* - OpenRouter/Poolside: "Input length X exceeds the maximum allowed input length of Y tokens."
* - Together AI: "The input (X tokens) is longer than the model's context length (Y tokens)."
* - llama.cpp: "the request exceeds the available context size, try increasing it"
* - LM Studio: "tokens to keep from the initial prompt is greater than the context length"
@@ -39,7 +40,8 @@ const OVERFLOW_PATTERNS = [
/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
/maximum context length is \d+ tokens/i, // OpenRouter (all backends)
/maximum context length is \d+ tokens/i, // OpenRouter (most backends)
/exceeds (?:the )?maximum allowed input length of [\d,]+ tokens?/i, // OpenRouter/Poolside
/input \(\d+ tokens\) is longer than the model'?s context length \(\d+ tokens\)/i, // Together AI
/exceeds the limit of \d+/i, // GitHub Copilot
/exceeds the available context size/i, // llama.cpp server
@@ -89,7 +91,8 @@ const NON_OVERFLOW_PATTERNS = [
* - Groq: "reduce the length of the messages"
* - Cerebras: 400/413 status code (no body)
* - Mistral: "Prompt contains X tokens ... too large for model with Y maximum context length"
* - OpenRouter (all backends): "maximum context length is X tokens"
* - OpenRouter (most backends): "maximum context length is X tokens"
* - OpenRouter/Poolside: "Input length X exceeds the maximum allowed input length of Y tokens."
* - Together AI: "The input (X tokens) is longer than the model's context length (Y tokens)."
* - llama.cpp: "exceeds the available context size"
* - LM Studio: "greater than the context length"
packages/ai/test/overflow.test.ts
+7
View File
@@ -49,6 +49,13 @@ describe("isContextOverflow", () => {
expect(isContextOverflow(message, 131072)).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.",
);
expect(isContextOverflow(message, 131072)).toBe(true);
});
it("does not treat generic non-overflow Ollama errors as overflow", () => {
const message = createErrorMessage("500 `model runner crashed unexpectedly`");
expect(isContextOverflow(message, 32768)).toBe(false);