a3bf1eb399
- Add NON_OVERFLOW_PATTERNS to explicitly exclude known non-overflow errors
- Consolidate Cerebras 400/413 no-body check into OVERFLOW_PATTERNS
- Format Bedrock errors as ${error.name}: ${error.message} for pattern matching
65 lines
2.1 KiB
TypeScript
65 lines
2.1 KiB
TypeScript
import { describe, expect, it } from "vitest";
|
|
import type { AssistantMessage } from "../src/types.js";
|
|
import { isContextOverflow } from "../src/utils/overflow.js";
|
|
|
|
function createErrorMessage(errorMessage: string): AssistantMessage {
|
|
return {
|
|
role: "assistant",
|
|
content: [],
|
|
api: "openai-completions",
|
|
provider: "ollama",
|
|
model: "qwen3.5:35b",
|
|
usage: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
totalTokens: 0,
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
total: 0,
|
|
},
|
|
},
|
|
stopReason: "error",
|
|
errorMessage,
|
|
timestamp: Date.now(),
|
|
};
|
|
}
|
|
|
|
describe("isContextOverflow", () => {
|
|
it("detects explicit Ollama prompt-too-long errors", () => {
|
|
const message = createErrorMessage("400 `prompt too long; exceeded max context length by 100918 tokens`");
|
|
expect(isContextOverflow(message, 32768)).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);
|
|
});
|
|
|
|
it("does not treat Bedrock throttling 'Too many tokens' as overflow", () => {
|
|
// Bedrock returns this for HTTP 429 rate limiting, NOT context overflow.
|
|
// formatBedrockError uses a human-readable prefix for ThrottlingException.
|
|
const message = createErrorMessage("Throttling error: Too many tokens, please wait before trying again.");
|
|
expect(isContextOverflow(message, 200000)).toBe(false);
|
|
});
|
|
|
|
it("does not treat Bedrock service unavailable as overflow", () => {
|
|
const message = createErrorMessage("Service unavailable: The service is temporarily unavailable.");
|
|
expect(isContextOverflow(message, 200000)).toBe(false);
|
|
});
|
|
|
|
it("does not treat generic rate limit errors as overflow", () => {
|
|
const message = createErrorMessage("Rate limit exceeded, please retry after 30 seconds.");
|
|
expect(isContextOverflow(message, 200000)).toBe(false);
|
|
});
|
|
|
|
it("does not treat HTTP 429 style errors as overflow", () => {
|
|
const message = createErrorMessage("Too many requests. Please slow down.");
|
|
expect(isContextOverflow(message, 200000)).toBe(false);
|
|
});
|
|
});
|