getcompanion-ai/co-mono
1
0
Fork 0
mirror of https://github.com/getcompanion-ai/co-mono.git synced 2026-04-19 23:01:32 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(ai): 429 rate limit errors no longer trigger auto-compaction

Browse source 
429 (Too Many Requests) was incorrectly classified as context overflow,
triggering compaction instead of retry with backoff. The original logic
assumed token-based rate limiting correlates with context overflow, but
these are different concepts:

- Rate limiting (429): requests/tokens per time period (throughput)
- Context overflow: single request exceeds context window (size)

Now 429 errors are handled by the existing retry logic with exponential
backoff, while 400/413 remain as potential context overflow indicators.

fixes #1038
This commit is contained in:
Mario Zechner 2026-01-29 00:43:38 +01:00
parent a373dce747
commit 25707f9ad4
2 changed files with 8 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

14
packages/ai/src/utils/overflow.ts
View file

@ -18,8 +18,8 @@ import type { AssistantMessage } from "../types.js";
* - LM Studio: "tokens to keep from the initial prompt is greater than the context length"
* - GitHub Copilot: "prompt token count of X exceeds the limit of Y"
* - MiniMax: "invalid params, context window exceeds limit"
* - Cerebras: Returns "400 status code (no body)" - handled separately below
* - Mistral: Returns "400 status code (no body)" - handled separately below
* - Cerebras: Returns "400/413 status code (no body)" - handled separately below
* - Mistral: Returns "400/413 status code (no body)" - handled separately below
* - z.ai: Does NOT error, accepts overflow silently - handled via usage.input > contextWindow
* - Ollama: Silently truncates input - not detectable via error message
*/
@ -57,8 +57,8 @@ const OVERFLOW_PATTERNS = [
* - 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"
* - Cerebras: 400/413/429 status code (no body)
* - Mistral: 400/413/429 status code (no body)
* - Cerebras: 400/413 status code (no body)
* - Mistral: 400/413 status code (no body)
* - OpenRouter (all backends): "maximum context length is X tokens"
* - llama.cpp: "exceeds the available context size"
* - LM Studio: "greater than the context length"
@ -92,9 +92,9 @@ export function isContextOverflow(message: AssistantMessage, contextWindow?: num
return true;
}
// Cerebras and Mistral return 400/413/429 with no body - check for status code pattern
// 429 can indicate token-based rate limiting which correlates with context overflow
if (/^4(00|13|29)\s*(status code)?\s*\(no body\)/i.test(message.errorMessage)) {
// Cerebras and Mistral return 400/413 with no body for context overflow
// Note: 429 is rate limiting (requests/tokens per time), NOT context overflow
if (/^4(00|13)\s*(status code)?\s*\(no body\)/i.test(message.errorMessage)) {
return true;
}
}