chore: drop non-code junk (pi-mono-reference, runtime state, root duplicates)
Remove files that should never have been tracked: - pi-mono-reference/: 688-file copy of an upstream monorepo, zero imports, used only as offline human reference - build/electron-builder.runtime.json: environment-specific build artifact with hardcoded local paths - state/cancel-signal-state.json: runtime state written by the app - prompt.txt, logo.svg (root): exact duplicates of the canonical copies under .planning/archive/ and assets/ Add state/ to .gitignore so future runtime state stays out.
This commit is contained in:
1 parent
34ca5b77f1
commit
1f7230fe87
691 files changed
+3
-190434
No files matched your search
@@ -1,64 +0,0 @@
|
||||
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);
|
||||
});
|
||||
});
|
||||
Reference in new issue
Block a user