mirror of
https://github.com/openclaw/openclaw.git
synced 2026-05-07 15:21:23 +00:00
perf(test): consolidate pi-embedded helpers e2e suites
This commit is contained in:
Peter Steinberger
@@ -1,8 +1,11 @@
|
||||
import { describe, expect, it } from "vitest";
|
||||
import type { OpenClawConfig } from "../config/config.js";
|
||||
import {
|
||||
buildBootstrapContextFiles,
|
||||
DEFAULT_BOOTSTRAP_MAX_CHARS,
|
||||
DEFAULT_BOOTSTRAP_TOTAL_MAX_CHARS,
|
||||
resolveBootstrapMaxChars,
|
||||
resolveBootstrapTotalMaxChars,
|
||||
} from "./pi-embedded-helpers.js";
|
||||
import { DEFAULT_AGENTS_FILENAME } from "./workspace.js";
|
||||
|
||||
@@ -100,3 +103,39 @@ describe("buildBootstrapContextFiles", () => {
|
||||
expect(result[0]?.content.startsWith("[MISSING]")).toBe(true);
|
||||
});
|
||||
});
|
||||
|
||||
describe("resolveBootstrapMaxChars", () => {
|
||||
it("returns default when unset", () => {
|
||||
expect(resolveBootstrapMaxChars()).toBe(DEFAULT_BOOTSTRAP_MAX_CHARS);
|
||||
});
|
||||
it("uses configured value when valid", () => {
|
||||
const cfg = {
|
||||
agents: { defaults: { bootstrapMaxChars: 12345 } },
|
||||
} as OpenClawConfig;
|
||||
expect(resolveBootstrapMaxChars(cfg)).toBe(12345);
|
||||
});
|
||||
it("falls back when invalid", () => {
|
||||
const cfg = {
|
||||
agents: { defaults: { bootstrapMaxChars: -1 } },
|
||||
} as OpenClawConfig;
|
||||
expect(resolveBootstrapMaxChars(cfg)).toBe(DEFAULT_BOOTSTRAP_MAX_CHARS);
|
||||
});
|
||||
});
|
||||
|
||||
describe("resolveBootstrapTotalMaxChars", () => {
|
||||
it("returns default when unset", () => {
|
||||
expect(resolveBootstrapTotalMaxChars()).toBe(DEFAULT_BOOTSTRAP_TOTAL_MAX_CHARS);
|
||||
});
|
||||
it("uses configured value when valid", () => {
|
||||
const cfg = {
|
||||
agents: { defaults: { bootstrapTotalMaxChars: 12345 } },
|
||||
} as OpenClawConfig;
|
||||
expect(resolveBootstrapTotalMaxChars(cfg)).toBe(12345);
|
||||
});
|
||||
it("falls back when invalid", () => {
|
||||
const cfg = {
|
||||
agents: { defaults: { bootstrapTotalMaxChars: -1 } },
|
||||
} as OpenClawConfig;
|
||||
expect(resolveBootstrapTotalMaxChars(cfg)).toBe(DEFAULT_BOOTSTRAP_TOTAL_MAX_CHARS);
|
||||
});
|
||||
});
|
||||
|
||||
@@ -1,47 +0,0 @@
|
||||
import { describe, expect, it } from "vitest";
|
||||
import { classifyFailoverReason } from "./pi-embedded-helpers.js";
|
||||
import { DEFAULT_AGENTS_FILENAME } from "./workspace.js";
|
||||
|
||||
const _makeFile = (overrides: Partial<WorkspaceBootstrapFile>): WorkspaceBootstrapFile => ({
|
||||
name: DEFAULT_AGENTS_FILENAME,
|
||||
path: "/tmp/AGENTS.md",
|
||||
content: "",
|
||||
missing: false,
|
||||
...overrides,
|
||||
});
|
||||
describe("classifyFailoverReason", () => {
|
||||
it("returns a stable reason", () => {
|
||||
expect(classifyFailoverReason("invalid api key")).toBe("auth");
|
||||
expect(classifyFailoverReason("no credentials found")).toBe("auth");
|
||||
expect(classifyFailoverReason("no api key found")).toBe("auth");
|
||||
expect(classifyFailoverReason("429 too many requests")).toBe("rate_limit");
|
||||
expect(classifyFailoverReason("resource has been exhausted")).toBe("rate_limit");
|
||||
expect(
|
||||
classifyFailoverReason(
|
||||
'{"type":"error","error":{"type":"overloaded_error","message":"Overloaded"}}',
|
||||
),
|
||||
).toBe("rate_limit");
|
||||
expect(classifyFailoverReason("invalid request format")).toBe("format");
|
||||
expect(classifyFailoverReason("credit balance too low")).toBe("billing");
|
||||
expect(classifyFailoverReason("deadline exceeded")).toBe("timeout");
|
||||
expect(classifyFailoverReason("request ended without sending any chunks")).toBe("timeout");
|
||||
expect(
|
||||
classifyFailoverReason(
|
||||
"521 <!DOCTYPE html><html><head><title>Web server is down</title></head><body>Cloudflare</body></html>",
|
||||
),
|
||||
).toBe("timeout");
|
||||
expect(classifyFailoverReason("string should match pattern")).toBe("format");
|
||||
expect(classifyFailoverReason("bad request")).toBeNull();
|
||||
expect(
|
||||
classifyFailoverReason(
|
||||
"messages.84.content.1.image.source.base64.data: At least one of the image dimensions exceed max allowed size for many-image requests: 2000 pixels",
|
||||
),
|
||||
).toBeNull();
|
||||
expect(classifyFailoverReason("image exceeds 5 MB maximum")).toBeNull();
|
||||
});
|
||||
it("classifies OpenAI usage limit errors as rate_limit", () => {
|
||||
expect(classifyFailoverReason("You have hit your ChatGPT usage limit (plus plan)")).toBe(
|
||||
"rate_limit",
|
||||
);
|
||||
});
|
||||
});
|
||||
@@ -1,78 +0,0 @@
|
||||
import { describe, expect, it } from "vitest";
|
||||
import { downgradeOpenAIReasoningBlocks } from "./pi-embedded-helpers.js";
|
||||
|
||||
describe("downgradeOpenAIReasoningBlocks", () => {
|
||||
it("keeps reasoning signatures when followed by content", () => {
|
||||
const input = [
|
||||
{
|
||||
role: "assistant",
|
||||
content: [
|
||||
{
|
||||
type: "thinking",
|
||||
thinking: "internal reasoning",
|
||||
thinkingSignature: JSON.stringify({ id: "rs_123", type: "reasoning" }),
|
||||
},
|
||||
{ type: "text", text: "answer" },
|
||||
],
|
||||
},
|
||||
];
|
||||
|
||||
// oxlint-disable-next-line typescript/no-explicit-any
|
||||
expect(downgradeOpenAIReasoningBlocks(input as any)).toEqual(input);
|
||||
});
|
||||
|
||||
it("drops orphaned reasoning blocks without following content", () => {
|
||||
const input = [
|
||||
{
|
||||
role: "assistant",
|
||||
content: [
|
||||
{
|
||||
type: "thinking",
|
||||
thinkingSignature: JSON.stringify({ id: "rs_abc", type: "reasoning" }),
|
||||
},
|
||||
],
|
||||
},
|
||||
{ role: "user", content: "next" },
|
||||
];
|
||||
|
||||
// oxlint-disable-next-line typescript/no-explicit-any
|
||||
expect(downgradeOpenAIReasoningBlocks(input as any)).toEqual([
|
||||
{ role: "user", content: "next" },
|
||||
]);
|
||||
});
|
||||
|
||||
it("drops object-form orphaned signatures", () => {
|
||||
const input = [
|
||||
{
|
||||
role: "assistant",
|
||||
content: [
|
||||
{
|
||||
type: "thinking",
|
||||
thinkingSignature: { id: "rs_obj", type: "reasoning" },
|
||||
},
|
||||
],
|
||||
},
|
||||
];
|
||||
|
||||
// oxlint-disable-next-line typescript/no-explicit-any
|
||||
expect(downgradeOpenAIReasoningBlocks(input as any)).toEqual([]);
|
||||
});
|
||||
|
||||
it("keeps non-reasoning thinking signatures", () => {
|
||||
const input = [
|
||||
{
|
||||
role: "assistant",
|
||||
content: [
|
||||
{
|
||||
type: "thinking",
|
||||
thinking: "t",
|
||||
thinkingSignature: "reasoning_content",
|
||||
},
|
||||
],
|
||||
},
|
||||
];
|
||||
|
||||
// oxlint-disable-next-line typescript/no-explicit-any
|
||||
expect(downgradeOpenAIReasoningBlocks(input as any)).toEqual(input);
|
||||
});
|
||||
});
|
||||
@@ -4,6 +4,7 @@ import {
|
||||
BILLING_ERROR_USER_MESSAGE,
|
||||
formatBillingErrorMessage,
|
||||
formatAssistantErrorText,
|
||||
formatRawAssistantErrorForUi,
|
||||
} from "./pi-embedded-helpers.js";
|
||||
|
||||
describe("formatAssistantErrorText", () => {
|
||||
@@ -114,3 +115,38 @@ describe("formatAssistantErrorText", () => {
|
||||
expect(formatAssistantErrorText(msg)).toBe("LLM request timed out.");
|
||||
});
|
||||
});
|
||||
|
||||
describe("formatRawAssistantErrorForUi", () => {
|
||||
it("renders HTTP code + type + message from Anthropic payloads", () => {
|
||||
const text = formatRawAssistantErrorForUi(
|
||||
'429 {"type":"error","error":{"type":"rate_limit_error","message":"Rate limited."},"request_id":"req_123"}',
|
||||
);
|
||||
|
||||
expect(text).toContain("HTTP 429");
|
||||
expect(text).toContain("rate_limit_error");
|
||||
expect(text).toContain("Rate limited.");
|
||||
expect(text).toContain("req_123");
|
||||
});
|
||||
|
||||
it("renders a generic unknown error message when raw is empty", () => {
|
||||
expect(formatRawAssistantErrorForUi("")).toContain("unknown error");
|
||||
});
|
||||
|
||||
it("formats plain HTTP status lines", () => {
|
||||
expect(formatRawAssistantErrorForUi("500 Internal Server Error")).toBe(
|
||||
"HTTP 500: Internal Server Error",
|
||||
);
|
||||
});
|
||||
|
||||
it("sanitizes HTML error pages into a clean unavailable message", () => {
|
||||
const htmlError = `521 <!DOCTYPE html>
|
||||
<html lang="en-US">
|
||||
<head><title>Web server is down | example.com | Cloudflare</title></head>
|
||||
<body>Ray ID: abc123</body>
|
||||
</html>`;
|
||||
|
||||
expect(formatRawAssistantErrorForUi(htmlError)).toBe(
|
||||
"The AI service is temporarily unavailable (HTTP 521). Please try again in a moment.",
|
||||
);
|
||||
});
|
||||
});
|
||||
|
||||
@@ -1,37 +0,0 @@
|
||||
import { describe, expect, it } from "vitest";
|
||||
import { formatRawAssistantErrorForUi } from "./pi-embedded-helpers.js";
|
||||
|
||||
describe("formatRawAssistantErrorForUi", () => {
|
||||
it("renders HTTP code + type + message from Anthropic payloads", () => {
|
||||
const text = formatRawAssistantErrorForUi(
|
||||
'429 {"type":"error","error":{"type":"rate_limit_error","message":"Rate limited."},"request_id":"req_123"}',
|
||||
);
|
||||
|
||||
expect(text).toContain("HTTP 429");
|
||||
expect(text).toContain("rate_limit_error");
|
||||
expect(text).toContain("Rate limited.");
|
||||
expect(text).toContain("req_123");
|
||||
});
|
||||
|
||||
it("renders a generic unknown error message when raw is empty", () => {
|
||||
expect(formatRawAssistantErrorForUi("")).toContain("unknown error");
|
||||
});
|
||||
|
||||
it("formats plain HTTP status lines", () => {
|
||||
expect(formatRawAssistantErrorForUi("500 Internal Server Error")).toBe(
|
||||
"HTTP 500: Internal Server Error",
|
||||
);
|
||||
});
|
||||
|
||||
it("sanitizes HTML error pages into a clean unavailable message", () => {
|
||||
const htmlError = `521 <!DOCTYPE html>
|
||||
<html lang="en-US">
|
||||
<head><title>Web server is down | example.com | Cloudflare</title></head>
|
||||
<body>Ray ID: abc123</body>
|
||||
</html>`;
|
||||
|
||||
expect(formatRawAssistantErrorForUi(htmlError)).toBe(
|
||||
"The AI service is temporarily unavailable (HTTP 521). Please try again in a moment.",
|
||||
);
|
||||
});
|
||||
});
|
||||
@@ -1,15 +0,0 @@
|
||||
import { describe, expect, it } from "vitest";
|
||||
import { isImageDimensionErrorMessage, parseImageDimensionError } from "./pi-embedded-helpers.js";
|
||||
|
||||
describe("image dimension errors", () => {
|
||||
it("parses anthropic image dimension errors", () => {
|
||||
const raw =
|
||||
'400 {"type":"error","error":{"type":"invalid_request_error","message":"messages.84.content.1.image.source.base64.data: At least one of the image dimensions exceed max allowed size for many-image requests: 2000 pixels"}}';
|
||||
const parsed = parseImageDimensionError(raw);
|
||||
expect(parsed).not.toBeNull();
|
||||
expect(parsed?.maxDimensionPx).toBe(2000);
|
||||
expect(parsed?.messageIndex).toBe(84);
|
||||
expect(parsed?.contentIndex).toBe(1);
|
||||
expect(isImageDimensionErrorMessage(raw)).toBe(true);
|
||||
});
|
||||
});
|
||||
@@ -1,13 +0,0 @@
|
||||
import { describe, expect, it } from "vitest";
|
||||
import { parseImageSizeError } from "./pi-embedded-helpers.js";
|
||||
|
||||
describe("parseImageSizeError", () => {
|
||||
it("parses max MB values from error text", () => {
|
||||
expect(parseImageSizeError("image exceeds 5 MB maximum")?.maxMb).toBe(5);
|
||||
expect(parseImageSizeError("Image exceeds 5.5 MB limit")?.maxMb).toBe(5.5);
|
||||
});
|
||||
|
||||
it("returns null for unrelated errors", () => {
|
||||
expect(parseImageSizeError("context overflow")).toBeNull();
|
||||
});
|
||||
});
|
||||
@@ -1,35 +0,0 @@
|
||||
import { describe, expect, it } from "vitest";
|
||||
import { isAuthErrorMessage } from "./pi-embedded-helpers.js";
|
||||
import { DEFAULT_AGENTS_FILENAME } from "./workspace.js";
|
||||
|
||||
const _makeFile = (overrides: Partial<WorkspaceBootstrapFile>): WorkspaceBootstrapFile => ({
|
||||
name: DEFAULT_AGENTS_FILENAME,
|
||||
path: "/tmp/AGENTS.md",
|
||||
content: "",
|
||||
missing: false,
|
||||
...overrides,
|
||||
});
|
||||
describe("isAuthErrorMessage", () => {
|
||||
it("matches credential validation errors", () => {
|
||||
const samples = [
|
||||
'No credentials found for profile "anthropic:default".',
|
||||
"No API key found for profile openai.",
|
||||
];
|
||||
for (const sample of samples) {
|
||||
expect(isAuthErrorMessage(sample)).toBe(true);
|
||||
}
|
||||
});
|
||||
it("matches OAuth refresh failures", () => {
|
||||
const samples = [
|
||||
"OAuth token refresh failed for anthropic: Failed to refresh OAuth token for anthropic. Please try again or re-authenticate.",
|
||||
"Please re-authenticate to continue.",
|
||||
];
|
||||
for (const sample of samples) {
|
||||
expect(isAuthErrorMessage(sample)).toBe(true);
|
||||
}
|
||||
});
|
||||
it("ignores unrelated errors", () => {
|
||||
expect(isAuthErrorMessage("rate limit exceeded")).toBe(false);
|
||||
expect(isAuthErrorMessage("billing issue detected")).toBe(false);
|
||||
});
|
||||
});
|
||||
@@ -1,14 +1,45 @@
|
||||
import { describe, expect, it } from "vitest";
|
||||
import { isBillingErrorMessage } from "./pi-embedded-helpers.js";
|
||||
import { DEFAULT_AGENTS_FILENAME } from "./workspace.js";
|
||||
import {
|
||||
classifyFailoverReason,
|
||||
isAuthErrorMessage,
|
||||
isBillingErrorMessage,
|
||||
isCloudCodeAssistFormatError,
|
||||
isCloudflareOrHtmlErrorPage,
|
||||
isCompactionFailureError,
|
||||
isContextOverflowError,
|
||||
isFailoverErrorMessage,
|
||||
isImageDimensionErrorMessage,
|
||||
isLikelyContextOverflowError,
|
||||
isTransientHttpError,
|
||||
parseImageDimensionError,
|
||||
parseImageSizeError,
|
||||
} from "./pi-embedded-helpers.js";
|
||||
|
||||
const _makeFile = (overrides: Partial<WorkspaceBootstrapFile>): WorkspaceBootstrapFile => ({
|
||||
name: DEFAULT_AGENTS_FILENAME,
|
||||
path: "/tmp/AGENTS.md",
|
||||
content: "",
|
||||
missing: false,
|
||||
...overrides,
|
||||
describe("isAuthErrorMessage", () => {
|
||||
it("matches credential validation errors", () => {
|
||||
const samples = [
|
||||
'No credentials found for profile "anthropic:default".',
|
||||
"No API key found for profile openai.",
|
||||
];
|
||||
for (const sample of samples) {
|
||||
expect(isAuthErrorMessage(sample)).toBe(true);
|
||||
}
|
||||
});
|
||||
it("matches OAuth refresh failures", () => {
|
||||
const samples = [
|
||||
"OAuth token refresh failed for anthropic: Failed to refresh OAuth token for anthropic. Please try again or re-authenticate.",
|
||||
"Please re-authenticate to continue.",
|
||||
];
|
||||
for (const sample of samples) {
|
||||
expect(isAuthErrorMessage(sample)).toBe(true);
|
||||
}
|
||||
});
|
||||
it("ignores unrelated errors", () => {
|
||||
expect(isAuthErrorMessage("rate limit exceeded")).toBe(false);
|
||||
expect(isAuthErrorMessage("billing issue detected")).toBe(false);
|
||||
});
|
||||
});
|
||||
|
||||
describe("isBillingErrorMessage", () => {
|
||||
it("matches credit / payment failures", () => {
|
||||
const samples = [
|
||||
@@ -65,3 +96,255 @@ describe("isBillingErrorMessage", () => {
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
describe("isCloudCodeAssistFormatError", () => {
|
||||
it("matches format errors", () => {
|
||||
const samples = [
|
||||
"INVALID_REQUEST_ERROR: string should match pattern",
|
||||
"messages.1.content.1.tool_use.id",
|
||||
"tool_use.id should match pattern",
|
||||
"invalid request format",
|
||||
];
|
||||
for (const sample of samples) {
|
||||
expect(isCloudCodeAssistFormatError(sample)).toBe(true);
|
||||
}
|
||||
});
|
||||
it("ignores unrelated errors", () => {
|
||||
expect(isCloudCodeAssistFormatError("rate limit exceeded")).toBe(false);
|
||||
expect(
|
||||
isCloudCodeAssistFormatError(
|
||||
'400 {"type":"error","error":{"type":"invalid_request_error","message":"messages.84.content.1.image.source.base64.data: At least one of the image dimensions exceed max allowed size for many-image requests: 2000 pixels"}}',
|
||||
),
|
||||
).toBe(false);
|
||||
});
|
||||
});
|
||||
|
||||
describe("isCloudflareOrHtmlErrorPage", () => {
|
||||
it("detects Cloudflare 521 HTML pages", () => {
|
||||
const htmlError = `521 <!DOCTYPE html>
|
||||
<html lang="en-US">
|
||||
<head><title>Web server is down | example.com | Cloudflare</title></head>
|
||||
<body><h1>Web server is down</h1></body>
|
||||
</html>`;
|
||||
|
||||
expect(isCloudflareOrHtmlErrorPage(htmlError)).toBe(true);
|
||||
});
|
||||
|
||||
it("detects generic 5xx HTML pages", () => {
|
||||
const htmlError = `503 <html><head><title>Service Unavailable</title></head><body>down</body></html>`;
|
||||
expect(isCloudflareOrHtmlErrorPage(htmlError)).toBe(true);
|
||||
});
|
||||
|
||||
it("does not flag non-HTML status lines", () => {
|
||||
expect(isCloudflareOrHtmlErrorPage("500 Internal Server Error")).toBe(false);
|
||||
expect(isCloudflareOrHtmlErrorPage("429 Too Many Requests")).toBe(false);
|
||||
});
|
||||
|
||||
it("does not flag quoted HTML without a closing html tag", () => {
|
||||
const plainTextWithHtmlPrefix = "500 <!DOCTYPE html> upstream responded with partial HTML text";
|
||||
expect(isCloudflareOrHtmlErrorPage(plainTextWithHtmlPrefix)).toBe(false);
|
||||
});
|
||||
});
|
||||
|
||||
describe("isCompactionFailureError", () => {
|
||||
it("matches compaction overflow failures", () => {
|
||||
const samples = [
|
||||
'Context overflow: Summarization failed: 400 {"message":"prompt is too long"}',
|
||||
"auto-compaction failed due to context overflow",
|
||||
"Compaction failed: prompt is too long",
|
||||
"Summarization failed: context window exceeded for this request",
|
||||
];
|
||||
for (const sample of samples) {
|
||||
expect(isCompactionFailureError(sample)).toBe(true);
|
||||
}
|
||||
});
|
||||
it("ignores non-compaction overflow errors", () => {
|
||||
expect(isCompactionFailureError("Context overflow: prompt too large")).toBe(false);
|
||||
expect(isCompactionFailureError("rate limit exceeded")).toBe(false);
|
||||
});
|
||||
});
|
||||
|
||||
describe("isContextOverflowError", () => {
|
||||
it("matches known overflow hints", () => {
|
||||
const samples = [
|
||||
"request_too_large",
|
||||
"Request exceeds the maximum size",
|
||||
"context length exceeded",
|
||||
"Maximum context length",
|
||||
"prompt is too long: 208423 tokens > 200000 maximum",
|
||||
"Context overflow: Summarization failed",
|
||||
"413 Request Entity Too Large",
|
||||
];
|
||||
for (const sample of samples) {
|
||||
expect(isContextOverflowError(sample)).toBe(true);
|
||||
}
|
||||
});
|
||||
|
||||
it("matches Anthropic 'Request size exceeds model context window' error", () => {
|
||||
// Anthropic returns this error format when the prompt exceeds the context window.
|
||||
// Without this fix, auto-compaction is NOT triggered because neither
|
||||
// isContextOverflowError nor pi-ai's isContextOverflow recognizes this pattern.
|
||||
// The user sees: "LLM request rejected: Request size exceeds model context window"
|
||||
// instead of automatic compaction + retry.
|
||||
const anthropicRawError =
|
||||
'{"type":"error","error":{"type":"invalid_request_error","message":"Request size exceeds model context window"}}';
|
||||
expect(isContextOverflowError(anthropicRawError)).toBe(true);
|
||||
});
|
||||
|
||||
it("matches 'exceeds model context window' in various formats", () => {
|
||||
const samples = [
|
||||
"Request size exceeds model context window",
|
||||
"request size exceeds model context window",
|
||||
'400 {"type":"error","error":{"type":"invalid_request_error","message":"Request size exceeds model context window"}}',
|
||||
"The request size exceeds model context window limit",
|
||||
];
|
||||
for (const sample of samples) {
|
||||
expect(isContextOverflowError(sample)).toBe(true);
|
||||
}
|
||||
});
|
||||
|
||||
it("ignores unrelated errors", () => {
|
||||
expect(isContextOverflowError("rate limit exceeded")).toBe(false);
|
||||
expect(isContextOverflowError("request size exceeds upload limit")).toBe(false);
|
||||
expect(isContextOverflowError("model not found")).toBe(false);
|
||||
expect(isContextOverflowError("authentication failed")).toBe(false);
|
||||
});
|
||||
|
||||
it("ignores normal conversation text mentioning context overflow", () => {
|
||||
// These are legitimate conversation snippets, not error messages
|
||||
expect(isContextOverflowError("Let's investigate the context overflow bug")).toBe(false);
|
||||
expect(isContextOverflowError("The mystery context overflow errors are strange")).toBe(false);
|
||||
expect(isContextOverflowError("We're debugging context overflow issues")).toBe(false);
|
||||
expect(isContextOverflowError("Something is causing context overflow messages")).toBe(false);
|
||||
});
|
||||
});
|
||||
|
||||
describe("isLikelyContextOverflowError", () => {
|
||||
it("matches context overflow hints", () => {
|
||||
const samples = [
|
||||
"Model context window is 128k tokens, you requested 256k tokens",
|
||||
"Context window exceeded: requested 12000 tokens",
|
||||
"Prompt too large for this model",
|
||||
];
|
||||
for (const sample of samples) {
|
||||
expect(isLikelyContextOverflowError(sample)).toBe(true);
|
||||
}
|
||||
});
|
||||
|
||||
it("excludes context window too small errors", () => {
|
||||
const samples = [
|
||||
"Model context window too small (minimum is 128k tokens)",
|
||||
"Context window too small: minimum is 1000 tokens",
|
||||
];
|
||||
for (const sample of samples) {
|
||||
expect(isLikelyContextOverflowError(sample)).toBe(false);
|
||||
}
|
||||
});
|
||||
|
||||
it("excludes rate limit errors that match the broad hint regex", () => {
|
||||
const samples = [
|
||||
"request reached organization TPD rate limit, current: 1506556, limit: 1500000",
|
||||
"rate limit exceeded",
|
||||
"too many requests",
|
||||
"429 Too Many Requests",
|
||||
"exceeded your current quota",
|
||||
"This request would exceed your account's rate limit",
|
||||
"429 Too Many Requests: request exceeds rate limit",
|
||||
];
|
||||
for (const sample of samples) {
|
||||
expect(isLikelyContextOverflowError(sample)).toBe(false);
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
describe("isTransientHttpError", () => {
|
||||
it("returns true for retryable 5xx status codes", () => {
|
||||
expect(isTransientHttpError("500 Internal Server Error")).toBe(true);
|
||||
expect(isTransientHttpError("502 Bad Gateway")).toBe(true);
|
||||
expect(isTransientHttpError("503 Service Unavailable")).toBe(true);
|
||||
expect(isTransientHttpError("521 <!DOCTYPE html><html></html>")).toBe(true);
|
||||
expect(isTransientHttpError("529 Overloaded")).toBe(true);
|
||||
});
|
||||
|
||||
it("returns false for non-retryable or non-http text", () => {
|
||||
expect(isTransientHttpError("504 Gateway Timeout")).toBe(false);
|
||||
expect(isTransientHttpError("429 Too Many Requests")).toBe(false);
|
||||
expect(isTransientHttpError("network timeout")).toBe(false);
|
||||
});
|
||||
});
|
||||
|
||||
describe("isFailoverErrorMessage", () => {
|
||||
it("matches auth/rate/billing/timeout", () => {
|
||||
const samples = [
|
||||
"invalid api key",
|
||||
"429 rate limit exceeded",
|
||||
"Your credit balance is too low",
|
||||
"request timed out",
|
||||
"invalid request format",
|
||||
];
|
||||
for (const sample of samples) {
|
||||
expect(isFailoverErrorMessage(sample)).toBe(true);
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
describe("parseImageSizeError", () => {
|
||||
it("parses max MB values from error text", () => {
|
||||
expect(parseImageSizeError("image exceeds 5 MB maximum")?.maxMb).toBe(5);
|
||||
expect(parseImageSizeError("Image exceeds 5.5 MB limit")?.maxMb).toBe(5.5);
|
||||
});
|
||||
|
||||
it("returns null for unrelated errors", () => {
|
||||
expect(parseImageSizeError("context overflow")).toBeNull();
|
||||
});
|
||||
});
|
||||
|
||||
describe("image dimension errors", () => {
|
||||
it("parses anthropic image dimension errors", () => {
|
||||
const raw =
|
||||
'400 {"type":"error","error":{"type":"invalid_request_error","message":"messages.84.content.1.image.source.base64.data: At least one of the image dimensions exceed max allowed size for many-image requests: 2000 pixels"}}';
|
||||
const parsed = parseImageDimensionError(raw);
|
||||
expect(parsed).not.toBeNull();
|
||||
expect(parsed?.maxDimensionPx).toBe(2000);
|
||||
expect(parsed?.messageIndex).toBe(84);
|
||||
expect(parsed?.contentIndex).toBe(1);
|
||||
expect(isImageDimensionErrorMessage(raw)).toBe(true);
|
||||
});
|
||||
});
|
||||
|
||||
describe("classifyFailoverReason", () => {
|
||||
it("returns a stable reason", () => {
|
||||
expect(classifyFailoverReason("invalid api key")).toBe("auth");
|
||||
expect(classifyFailoverReason("no credentials found")).toBe("auth");
|
||||
expect(classifyFailoverReason("no api key found")).toBe("auth");
|
||||
expect(classifyFailoverReason("429 too many requests")).toBe("rate_limit");
|
||||
expect(classifyFailoverReason("resource has been exhausted")).toBe("rate_limit");
|
||||
expect(
|
||||
classifyFailoverReason(
|
||||
'{"type":"error","error":{"type":"overloaded_error","message":"Overloaded"}}',
|
||||
),
|
||||
).toBe("rate_limit");
|
||||
expect(classifyFailoverReason("invalid request format")).toBe("format");
|
||||
expect(classifyFailoverReason("credit balance too low")).toBe("billing");
|
||||
expect(classifyFailoverReason("deadline exceeded")).toBe("timeout");
|
||||
expect(classifyFailoverReason("request ended without sending any chunks")).toBe("timeout");
|
||||
expect(
|
||||
classifyFailoverReason(
|
||||
"521 <!DOCTYPE html><html><head><title>Web server is down</title></head><body>Cloudflare</body></html>",
|
||||
),
|
||||
).toBe("timeout");
|
||||
expect(classifyFailoverReason("string should match pattern")).toBe("format");
|
||||
expect(classifyFailoverReason("bad request")).toBeNull();
|
||||
expect(
|
||||
classifyFailoverReason(
|
||||
"messages.84.content.1.image.source.base64.data: At least one of the image dimensions exceed max allowed size for many-image requests: 2000 pixels",
|
||||
),
|
||||
).toBeNull();
|
||||
expect(classifyFailoverReason("image exceeds 5 MB maximum")).toBeNull();
|
||||
});
|
||||
it("classifies OpenAI usage limit errors as rate_limit", () => {
|
||||
expect(classifyFailoverReason("You have hit your ChatGPT usage limit (plus plan)")).toBe(
|
||||
"rate_limit",
|
||||
);
|
||||
});
|
||||
});
|
||||
|
||||
@@ -1,32 +0,0 @@
|
||||
import { describe, expect, it } from "vitest";
|
||||
import { isCloudCodeAssistFormatError } from "./pi-embedded-helpers.js";
|
||||
import { DEFAULT_AGENTS_FILENAME } from "./workspace.js";
|
||||
|
||||
const _makeFile = (overrides: Partial<WorkspaceBootstrapFile>): WorkspaceBootstrapFile => ({
|
||||
name: DEFAULT_AGENTS_FILENAME,
|
||||
path: "/tmp/AGENTS.md",
|
||||
content: "",
|
||||
missing: false,
|
||||
...overrides,
|
||||
});
|
||||
describe("isCloudCodeAssistFormatError", () => {
|
||||
it("matches format errors", () => {
|
||||
const samples = [
|
||||
"INVALID_REQUEST_ERROR: string should match pattern",
|
||||
"messages.1.content.1.tool_use.id",
|
||||
"tool_use.id should match pattern",
|
||||
"invalid request format",
|
||||
];
|
||||
for (const sample of samples) {
|
||||
expect(isCloudCodeAssistFormatError(sample)).toBe(true);
|
||||
}
|
||||
});
|
||||
it("ignores unrelated errors", () => {
|
||||
expect(isCloudCodeAssistFormatError("rate limit exceeded")).toBe(false);
|
||||
expect(
|
||||
isCloudCodeAssistFormatError(
|
||||
'400 {"type":"error","error":{"type":"invalid_request_error","message":"messages.84.content.1.image.source.base64.data: At least one of the image dimensions exceed max allowed size for many-image requests: 2000 pixels"}}',
|
||||
),
|
||||
).toBe(false);
|
||||
});
|
||||
});
|
||||
@@ -1,29 +0,0 @@
|
||||
import { describe, expect, it } from "vitest";
|
||||
import { isCloudflareOrHtmlErrorPage } from "./pi-embedded-helpers.js";
|
||||
|
||||
describe("isCloudflareOrHtmlErrorPage", () => {
|
||||
it("detects Cloudflare 521 HTML pages", () => {
|
||||
const htmlError = `521 <!DOCTYPE html>
|
||||
<html lang="en-US">
|
||||
<head><title>Web server is down | example.com | Cloudflare</title></head>
|
||||
<body><h1>Web server is down</h1></body>
|
||||
</html>`;
|
||||
|
||||
expect(isCloudflareOrHtmlErrorPage(htmlError)).toBe(true);
|
||||
});
|
||||
|
||||
it("detects generic 5xx HTML pages", () => {
|
||||
const htmlError = `503 <html><head><title>Service Unavailable</title></head><body>down</body></html>`;
|
||||
expect(isCloudflareOrHtmlErrorPage(htmlError)).toBe(true);
|
||||
});
|
||||
|
||||
it("does not flag non-HTML status lines", () => {
|
||||
expect(isCloudflareOrHtmlErrorPage("500 Internal Server Error")).toBe(false);
|
||||
expect(isCloudflareOrHtmlErrorPage("429 Too Many Requests")).toBe(false);
|
||||
});
|
||||
|
||||
it("does not flag quoted HTML without a closing html tag", () => {
|
||||
const plainTextWithHtmlPrefix = "500 <!DOCTYPE html> upstream responded with partial HTML text";
|
||||
expect(isCloudflareOrHtmlErrorPage(plainTextWithHtmlPrefix)).toBe(false);
|
||||
});
|
||||
});
|
||||
@@ -1,19 +0,0 @@
|
||||
import { describe, expect, it } from "vitest";
|
||||
import { isCompactionFailureError } from "./pi-embedded-helpers/errors.js";
|
||||
describe("isCompactionFailureError", () => {
|
||||
it("matches compaction overflow failures", () => {
|
||||
const samples = [
|
||||
'Context overflow: Summarization failed: 400 {"message":"prompt is too long"}',
|
||||
"auto-compaction failed due to context overflow",
|
||||
"Compaction failed: prompt is too long",
|
||||
"Summarization failed: context window exceeded for this request",
|
||||
];
|
||||
for (const sample of samples) {
|
||||
expect(isCompactionFailureError(sample)).toBe(true);
|
||||
}
|
||||
});
|
||||
it("ignores non-compaction overflow errors", () => {
|
||||
expect(isCompactionFailureError("Context overflow: prompt too large")).toBe(false);
|
||||
expect(isCompactionFailureError("rate limit exceeded")).toBe(false);
|
||||
});
|
||||
});
|
||||
@@ -1,57 +0,0 @@
|
||||
import { describe, expect, it } from "vitest";
|
||||
import { isContextOverflowError } from "./pi-embedded-helpers.js";
|
||||
|
||||
describe("isContextOverflowError", () => {
|
||||
it("matches known overflow hints", () => {
|
||||
const samples = [
|
||||
"request_too_large",
|
||||
"Request exceeds the maximum size",
|
||||
"context length exceeded",
|
||||
"Maximum context length",
|
||||
"prompt is too long: 208423 tokens > 200000 maximum",
|
||||
"Context overflow: Summarization failed",
|
||||
"413 Request Entity Too Large",
|
||||
];
|
||||
for (const sample of samples) {
|
||||
expect(isContextOverflowError(sample)).toBe(true);
|
||||
}
|
||||
});
|
||||
|
||||
it("matches Anthropic 'Request size exceeds model context window' error", () => {
|
||||
// Anthropic returns this error format when the prompt exceeds the context window.
|
||||
// Without this fix, auto-compaction is NOT triggered because neither
|
||||
// isContextOverflowError nor pi-ai's isContextOverflow recognizes this pattern.
|
||||
// The user sees: "LLM request rejected: Request size exceeds model context window"
|
||||
// instead of automatic compaction + retry.
|
||||
const anthropicRawError =
|
||||
'{"type":"error","error":{"type":"invalid_request_error","message":"Request size exceeds model context window"}}';
|
||||
expect(isContextOverflowError(anthropicRawError)).toBe(true);
|
||||
});
|
||||
|
||||
it("matches 'exceeds model context window' in various formats", () => {
|
||||
const samples = [
|
||||
"Request size exceeds model context window",
|
||||
"request size exceeds model context window",
|
||||
'400 {"type":"error","error":{"type":"invalid_request_error","message":"Request size exceeds model context window"}}',
|
||||
"The request size exceeds model context window limit",
|
||||
];
|
||||
for (const sample of samples) {
|
||||
expect(isContextOverflowError(sample)).toBe(true);
|
||||
}
|
||||
});
|
||||
|
||||
it("ignores unrelated errors", () => {
|
||||
expect(isContextOverflowError("rate limit exceeded")).toBe(false);
|
||||
expect(isContextOverflowError("request size exceeds upload limit")).toBe(false);
|
||||
expect(isContextOverflowError("model not found")).toBe(false);
|
||||
expect(isContextOverflowError("authentication failed")).toBe(false);
|
||||
});
|
||||
|
||||
it("ignores normal conversation text mentioning context overflow", () => {
|
||||
// These are legitimate conversation snippets, not error messages
|
||||
expect(isContextOverflowError("Let's investigate the context overflow bug")).toBe(false);
|
||||
expect(isContextOverflowError("The mystery context overflow errors are strange")).toBe(false);
|
||||
expect(isContextOverflowError("We're debugging context overflow issues")).toBe(false);
|
||||
expect(isContextOverflowError("Something is causing context overflow messages")).toBe(false);
|
||||
});
|
||||
});
|
||||
@@ -1,25 +0,0 @@
|
||||
import { describe, expect, it } from "vitest";
|
||||
import { isFailoverErrorMessage } from "./pi-embedded-helpers.js";
|
||||
import { DEFAULT_AGENTS_FILENAME } from "./workspace.js";
|
||||
|
||||
const _makeFile = (overrides: Partial<WorkspaceBootstrapFile>): WorkspaceBootstrapFile => ({
|
||||
name: DEFAULT_AGENTS_FILENAME,
|
||||
path: "/tmp/AGENTS.md",
|
||||
content: "",
|
||||
missing: false,
|
||||
...overrides,
|
||||
});
|
||||
describe("isFailoverErrorMessage", () => {
|
||||
it("matches auth/rate/billing/timeout", () => {
|
||||
const samples = [
|
||||
"invalid api key",
|
||||
"429 rate limit exceeded",
|
||||
"Your credit balance is too low",
|
||||
"request timed out",
|
||||
"invalid request format",
|
||||
];
|
||||
for (const sample of samples) {
|
||||
expect(isFailoverErrorMessage(sample)).toBe(true);
|
||||
}
|
||||
});
|
||||
});
|
||||
@@ -1,40 +0,0 @@
|
||||
import { describe, expect, it } from "vitest";
|
||||
import { isLikelyContextOverflowError } from "./pi-embedded-helpers.js";
|
||||
|
||||
describe("isLikelyContextOverflowError", () => {
|
||||
it("matches context overflow hints", () => {
|
||||
const samples = [
|
||||
"Model context window is 128k tokens, you requested 256k tokens",
|
||||
"Context window exceeded: requested 12000 tokens",
|
||||
"Prompt too large for this model",
|
||||
];
|
||||
for (const sample of samples) {
|
||||
expect(isLikelyContextOverflowError(sample)).toBe(true);
|
||||
}
|
||||
});
|
||||
|
||||
it("excludes context window too small errors", () => {
|
||||
const samples = [
|
||||
"Model context window too small (minimum is 128k tokens)",
|
||||
"Context window too small: minimum is 1000 tokens",
|
||||
];
|
||||
for (const sample of samples) {
|
||||
expect(isLikelyContextOverflowError(sample)).toBe(false);
|
||||
}
|
||||
});
|
||||
|
||||
it("excludes rate limit errors that match the broad hint regex", () => {
|
||||
const samples = [
|
||||
"request reached organization TPD rate limit, current: 1506556, limit: 1500000",
|
||||
"rate limit exceeded",
|
||||
"too many requests",
|
||||
"429 Too Many Requests",
|
||||
"exceeded your current quota",
|
||||
"This request would exceed your account's rate limit",
|
||||
"429 Too Many Requests: request exceeds rate limit",
|
||||
];
|
||||
for (const sample of samples) {
|
||||
expect(isLikelyContextOverflowError(sample)).toBe(false);
|
||||
}
|
||||
});
|
||||
});
|
||||
@@ -1,18 +0,0 @@
|
||||
import { describe, expect, it } from "vitest";
|
||||
import { isTransientHttpError } from "./pi-embedded-helpers.js";
|
||||
|
||||
describe("isTransientHttpError", () => {
|
||||
it("returns true for retryable 5xx status codes", () => {
|
||||
expect(isTransientHttpError("500 Internal Server Error")).toBe(true);
|
||||
expect(isTransientHttpError("502 Bad Gateway")).toBe(true);
|
||||
expect(isTransientHttpError("503 Service Unavailable")).toBe(true);
|
||||
expect(isTransientHttpError("521 <!DOCTYPE html><html></html>")).toBe(true);
|
||||
expect(isTransientHttpError("529 Overloaded")).toBe(true);
|
||||
});
|
||||
|
||||
it("returns false for non-retryable or non-http text", () => {
|
||||
expect(isTransientHttpError("504 Gateway Timeout")).toBe(false);
|
||||
expect(isTransientHttpError("429 Too Many Requests")).toBe(false);
|
||||
expect(isTransientHttpError("network timeout")).toBe(false);
|
||||
});
|
||||
});
|
||||
@@ -1,82 +0,0 @@
|
||||
import { describe, expect, it } from "vitest";
|
||||
import { isMessagingToolDuplicate, normalizeTextForComparison } from "./pi-embedded-helpers.js";
|
||||
|
||||
describe("normalizeTextForComparison", () => {
|
||||
it("lowercases text", () => {
|
||||
expect(normalizeTextForComparison("Hello World")).toBe("hello world");
|
||||
});
|
||||
|
||||
it("trims whitespace", () => {
|
||||
expect(normalizeTextForComparison(" hello ")).toBe("hello");
|
||||
});
|
||||
|
||||
it("collapses multiple spaces", () => {
|
||||
expect(normalizeTextForComparison("hello world")).toBe("hello world");
|
||||
});
|
||||
|
||||
it("strips emoji", () => {
|
||||
expect(normalizeTextForComparison("Hello 👋 World 🌍")).toBe("hello world");
|
||||
});
|
||||
|
||||
it("handles mixed normalization", () => {
|
||||
expect(normalizeTextForComparison(" Hello 👋 WORLD 🌍 ")).toBe("hello world");
|
||||
});
|
||||
});
|
||||
|
||||
describe("isMessagingToolDuplicate", () => {
|
||||
it("returns false for empty sentTexts", () => {
|
||||
expect(isMessagingToolDuplicate("hello world", [])).toBe(false);
|
||||
});
|
||||
|
||||
it("returns false for short texts", () => {
|
||||
expect(isMessagingToolDuplicate("short", ["short"])).toBe(false);
|
||||
});
|
||||
|
||||
it("detects exact duplicates", () => {
|
||||
expect(
|
||||
isMessagingToolDuplicate("Hello, this is a test message!", [
|
||||
"Hello, this is a test message!",
|
||||
]),
|
||||
).toBe(true);
|
||||
});
|
||||
|
||||
it("detects duplicates with different casing", () => {
|
||||
expect(
|
||||
isMessagingToolDuplicate("HELLO, THIS IS A TEST MESSAGE!", [
|
||||
"hello, this is a test message!",
|
||||
]),
|
||||
).toBe(true);
|
||||
});
|
||||
|
||||
it("detects duplicates with emoji variations", () => {
|
||||
expect(
|
||||
isMessagingToolDuplicate("Hello! 👋 This is a test message!", [
|
||||
"Hello! This is a test message!",
|
||||
]),
|
||||
).toBe(true);
|
||||
});
|
||||
|
||||
it("detects substring duplicates (LLM elaboration)", () => {
|
||||
expect(
|
||||
isMessagingToolDuplicate('I sent the message: "Hello, this is a test message!"', [
|
||||
"Hello, this is a test message!",
|
||||
]),
|
||||
).toBe(true);
|
||||
});
|
||||
|
||||
it("detects when sent text contains block reply (reverse substring)", () => {
|
||||
expect(
|
||||
isMessagingToolDuplicate("Hello, this is a test message!", [
|
||||
'I sent the message: "Hello, this is a test message!"',
|
||||
]),
|
||||
).toBe(true);
|
||||
});
|
||||
|
||||
it("returns false for non-matching texts", () => {
|
||||
expect(
|
||||
isMessagingToolDuplicate("This is completely different content.", [
|
||||
"Hello, this is a test message!",
|
||||
]),
|
||||
).toBe(false);
|
||||
});
|
||||
});
|
||||
@@ -1,52 +0,0 @@
|
||||
import { describe, expect, it } from "vitest";
|
||||
import type { OpenClawConfig } from "../config/config.js";
|
||||
import {
|
||||
DEFAULT_BOOTSTRAP_MAX_CHARS,
|
||||
DEFAULT_BOOTSTRAP_TOTAL_MAX_CHARS,
|
||||
resolveBootstrapMaxChars,
|
||||
resolveBootstrapTotalMaxChars,
|
||||
} from "./pi-embedded-helpers.js";
|
||||
import { DEFAULT_AGENTS_FILENAME } from "./workspace.js";
|
||||
|
||||
const _makeFile = (overrides: Partial<WorkspaceBootstrapFile>): WorkspaceBootstrapFile => ({
|
||||
name: DEFAULT_AGENTS_FILENAME,
|
||||
path: "/tmp/AGENTS.md",
|
||||
content: "",
|
||||
missing: false,
|
||||
...overrides,
|
||||
});
|
||||
describe("resolveBootstrapMaxChars", () => {
|
||||
it("returns default when unset", () => {
|
||||
expect(resolveBootstrapMaxChars()).toBe(DEFAULT_BOOTSTRAP_MAX_CHARS);
|
||||
});
|
||||
it("uses configured value when valid", () => {
|
||||
const cfg = {
|
||||
agents: { defaults: { bootstrapMaxChars: 12345 } },
|
||||
} as OpenClawConfig;
|
||||
expect(resolveBootstrapMaxChars(cfg)).toBe(12345);
|
||||
});
|
||||
it("falls back when invalid", () => {
|
||||
const cfg = {
|
||||
agents: { defaults: { bootstrapMaxChars: -1 } },
|
||||
} as OpenClawConfig;
|
||||
expect(resolveBootstrapMaxChars(cfg)).toBe(DEFAULT_BOOTSTRAP_MAX_CHARS);
|
||||
});
|
||||
});
|
||||
|
||||
describe("resolveBootstrapTotalMaxChars", () => {
|
||||
it("returns default when unset", () => {
|
||||
expect(resolveBootstrapTotalMaxChars()).toBe(DEFAULT_BOOTSTRAP_TOTAL_MAX_CHARS);
|
||||
});
|
||||
it("uses configured value when valid", () => {
|
||||
const cfg = {
|
||||
agents: { defaults: { bootstrapTotalMaxChars: 12345 } },
|
||||
} as OpenClawConfig;
|
||||
expect(resolveBootstrapTotalMaxChars(cfg)).toBe(12345);
|
||||
});
|
||||
it("falls back when invalid", () => {
|
||||
const cfg = {
|
||||
agents: { defaults: { bootstrapTotalMaxChars: -1 } },
|
||||
} as OpenClawConfig;
|
||||
expect(resolveBootstrapTotalMaxChars(cfg)).toBe(DEFAULT_BOOTSTRAP_TOTAL_MAX_CHARS);
|
||||
});
|
||||
});
|
||||
@@ -1,104 +0,0 @@
|
||||
import type { AgentMessage } from "@mariozechner/pi-agent-core";
|
||||
import { describe, expect, it } from "vitest";
|
||||
import { sanitizeSessionMessagesImages } from "./pi-embedded-helpers.js";
|
||||
|
||||
describe("sanitizeSessionMessagesImages", () => {
|
||||
it("keeps tool call + tool result IDs unchanged by default", async () => {
|
||||
const input = [
|
||||
{
|
||||
role: "assistant",
|
||||
content: [
|
||||
{
|
||||
type: "toolCall",
|
||||
id: "call_123|fc_456",
|
||||
name: "read",
|
||||
arguments: { path: "package.json" },
|
||||
},
|
||||
],
|
||||
},
|
||||
{
|
||||
role: "toolResult",
|
||||
toolCallId: "call_123|fc_456",
|
||||
toolName: "read",
|
||||
content: [{ type: "text", text: "ok" }],
|
||||
isError: false,
|
||||
},
|
||||
] satisfies AgentMessage[];
|
||||
|
||||
const out = await sanitizeSessionMessagesImages(input, "test");
|
||||
|
||||
const assistant = out[0] as unknown as { role?: string; content?: unknown };
|
||||
expect(assistant.role).toBe("assistant");
|
||||
expect(Array.isArray(assistant.content)).toBe(true);
|
||||
const toolCall = (assistant.content as Array<{ type?: string; id?: string }>).find(
|
||||
(b) => b.type === "toolCall",
|
||||
);
|
||||
expect(toolCall?.id).toBe("call_123|fc_456");
|
||||
|
||||
const toolResult = out[1] as unknown as {
|
||||
role?: string;
|
||||
toolCallId?: string;
|
||||
};
|
||||
expect(toolResult.role).toBe("toolResult");
|
||||
expect(toolResult.toolCallId).toBe("call_123|fc_456");
|
||||
});
|
||||
|
||||
it("sanitizes tool call + tool result IDs in strict mode (alphanumeric only)", async () => {
|
||||
const input = [
|
||||
{
|
||||
role: "assistant",
|
||||
content: [
|
||||
{
|
||||
type: "toolCall",
|
||||
id: "call_123|fc_456",
|
||||
name: "read",
|
||||
arguments: { path: "package.json" },
|
||||
},
|
||||
],
|
||||
},
|
||||
{
|
||||
role: "toolResult",
|
||||
toolCallId: "call_123|fc_456",
|
||||
toolName: "read",
|
||||
content: [{ type: "text", text: "ok" }],
|
||||
isError: false,
|
||||
},
|
||||
] satisfies AgentMessage[];
|
||||
|
||||
const out = await sanitizeSessionMessagesImages(input, "test", {
|
||||
sanitizeToolCallIds: true,
|
||||
toolCallIdMode: "strict",
|
||||
});
|
||||
|
||||
const assistant = out[0] as unknown as { role?: string; content?: unknown };
|
||||
expect(assistant.role).toBe("assistant");
|
||||
expect(Array.isArray(assistant.content)).toBe(true);
|
||||
const toolCall = (assistant.content as Array<{ type?: string; id?: string }>).find(
|
||||
(b) => b.type === "toolCall",
|
||||
);
|
||||
// Strict mode strips all non-alphanumeric characters
|
||||
expect(toolCall?.id).toBe("call123fc456");
|
||||
|
||||
const toolResult = out[1] as unknown as {
|
||||
role?: string;
|
||||
toolCallId?: string;
|
||||
};
|
||||
expect(toolResult.role).toBe("toolResult");
|
||||
expect(toolResult.toolCallId).toBe("call123fc456");
|
||||
});
|
||||
it("does not synthesize tool call input when missing", async () => {
|
||||
const input = [
|
||||
{
|
||||
role: "assistant",
|
||||
content: [{ type: "toolCall", id: "call_1", name: "read" }],
|
||||
},
|
||||
] satisfies AgentMessage[];
|
||||
|
||||
const out = await sanitizeSessionMessagesImages(input, "test");
|
||||
const assistant = out[0] as { content?: Array<Record<string, unknown>> };
|
||||
const toolCall = assistant.content?.find((b) => b.type === "toolCall");
|
||||
expect(toolCall).toBeTruthy();
|
||||
expect("input" in (toolCall ?? {})).toBe(false);
|
||||
expect("arguments" in (toolCall ?? {})).toBe(false);
|
||||
});
|
||||
});
|
||||
@@ -1,8 +1,111 @@
|
||||
import type { AgentMessage } from "@mariozechner/pi-agent-core";
|
||||
import { describe, expect, it } from "vitest";
|
||||
import { sanitizeSessionMessagesImages } from "./pi-embedded-helpers.js";
|
||||
import {
|
||||
sanitizeGoogleTurnOrdering,
|
||||
sanitizeSessionMessagesImages,
|
||||
} from "./pi-embedded-helpers.js";
|
||||
|
||||
describe("sanitizeSessionMessagesImages", () => {
|
||||
it("keeps tool call + tool result IDs unchanged by default", async () => {
|
||||
const input = [
|
||||
{
|
||||
role: "assistant",
|
||||
content: [
|
||||
{
|
||||
type: "toolCall",
|
||||
id: "call_123|fc_456",
|
||||
name: "read",
|
||||
arguments: { path: "package.json" },
|
||||
},
|
||||
],
|
||||
},
|
||||
{
|
||||
role: "toolResult",
|
||||
toolCallId: "call_123|fc_456",
|
||||
toolName: "read",
|
||||
content: [{ type: "text", text: "ok" }],
|
||||
isError: false,
|
||||
},
|
||||
] satisfies AgentMessage[];
|
||||
|
||||
const out = await sanitizeSessionMessagesImages(input, "test");
|
||||
|
||||
const assistant = out[0] as unknown as { role?: string; content?: unknown };
|
||||
expect(assistant.role).toBe("assistant");
|
||||
expect(Array.isArray(assistant.content)).toBe(true);
|
||||
const toolCall = (assistant.content as Array<{ type?: string; id?: string }>).find(
|
||||
(b) => b.type === "toolCall",
|
||||
);
|
||||
expect(toolCall?.id).toBe("call_123|fc_456");
|
||||
|
||||
const toolResult = out[1] as unknown as {
|
||||
role?: string;
|
||||
toolCallId?: string;
|
||||
};
|
||||
expect(toolResult.role).toBe("toolResult");
|
||||
expect(toolResult.toolCallId).toBe("call_123|fc_456");
|
||||
});
|
||||
|
||||
it("sanitizes tool call + tool result IDs in strict mode (alphanumeric only)", async () => {
|
||||
const input = [
|
||||
{
|
||||
role: "assistant",
|
||||
content: [
|
||||
{
|
||||
type: "toolCall",
|
||||
id: "call_123|fc_456",
|
||||
name: "read",
|
||||
arguments: { path: "package.json" },
|
||||
},
|
||||
],
|
||||
},
|
||||
{
|
||||
role: "toolResult",
|
||||
toolCallId: "call_123|fc_456",
|
||||
toolName: "read",
|
||||
content: [{ type: "text", text: "ok" }],
|
||||
isError: false,
|
||||
},
|
||||
] satisfies AgentMessage[];
|
||||
|
||||
const out = await sanitizeSessionMessagesImages(input, "test", {
|
||||
sanitizeToolCallIds: true,
|
||||
toolCallIdMode: "strict",
|
||||
});
|
||||
|
||||
const assistant = out[0] as unknown as { role?: string; content?: unknown };
|
||||
expect(assistant.role).toBe("assistant");
|
||||
expect(Array.isArray(assistant.content)).toBe(true);
|
||||
const toolCall = (assistant.content as Array<{ type?: string; id?: string }>).find(
|
||||
(b) => b.type === "toolCall",
|
||||
);
|
||||
// Strict mode strips all non-alphanumeric characters
|
||||
expect(toolCall?.id).toBe("call123fc456");
|
||||
|
||||
const toolResult = out[1] as unknown as {
|
||||
role?: string;
|
||||
toolCallId?: string;
|
||||
};
|
||||
expect(toolResult.role).toBe("toolResult");
|
||||
expect(toolResult.toolCallId).toBe("call123fc456");
|
||||
});
|
||||
|
||||
it("does not synthesize tool call input when missing", async () => {
|
||||
const input = [
|
||||
{
|
||||
role: "assistant",
|
||||
content: [{ type: "toolCall", id: "call_1", name: "read" }],
|
||||
},
|
||||
] satisfies AgentMessage[];
|
||||
|
||||
const out = await sanitizeSessionMessagesImages(input, "test");
|
||||
const assistant = out[0] as { content?: Array<Record<string, unknown>> };
|
||||
const toolCall = assistant.content?.find((b) => b.type === "toolCall");
|
||||
expect(toolCall).toBeTruthy();
|
||||
expect("input" in (toolCall ?? {})).toBe(false);
|
||||
expect("arguments" in (toolCall ?? {})).toBe(false);
|
||||
});
|
||||
|
||||
it("removes empty assistant text blocks but preserves tool calls", async () => {
|
||||
const input = [
|
||||
{
|
||||
@@ -117,4 +220,50 @@ describe("sanitizeSessionMessagesImages", () => {
|
||||
expect(out[0]?.role).toBe("user");
|
||||
expect(out[1]?.role).toBe("toolResult");
|
||||
});
|
||||
|
||||
describe("thought_signature stripping", () => {
|
||||
it("strips msg_-prefixed thought_signature from assistant message content blocks", async () => {
|
||||
const input = [
|
||||
{
|
||||
role: "assistant",
|
||||
content: [
|
||||
{ type: "text", text: "hello", thought_signature: "msg_abc123" },
|
||||
{
|
||||
type: "thinking",
|
||||
thinking: "reasoning",
|
||||
thought_signature: "AQID",
|
||||
},
|
||||
],
|
||||
},
|
||||
] satisfies AgentMessage[];
|
||||
|
||||
const out = await sanitizeSessionMessagesImages(input, "test");
|
||||
|
||||
expect(out).toHaveLength(1);
|
||||
const content = (out[0] as { content?: unknown[] }).content;
|
||||
expect(content).toHaveLength(2);
|
||||
expect("thought_signature" in ((content?.[0] ?? {}) as object)).toBe(false);
|
||||
expect((content?.[1] as { thought_signature?: unknown })?.thought_signature).toBe("AQID");
|
||||
});
|
||||
});
|
||||
});
|
||||
|
||||
describe("sanitizeGoogleTurnOrdering", () => {
|
||||
it("prepends a synthetic user turn when history starts with assistant", () => {
|
||||
const input = [
|
||||
{
|
||||
role: "assistant",
|
||||
content: [{ type: "toolCall", id: "call_1", name: "exec", arguments: {} }],
|
||||
},
|
||||
] satisfies AgentMessage[];
|
||||
|
||||
const out = sanitizeGoogleTurnOrdering(input);
|
||||
expect(out[0]?.role).toBe("user");
|
||||
expect(out[1]?.role).toBe("assistant");
|
||||
});
|
||||
it("is a no-op when history starts with user", () => {
|
||||
const input = [{ role: "user", content: "hi" }] satisfies AgentMessage[];
|
||||
const out = sanitizeGoogleTurnOrdering(input);
|
||||
expect(out).toBe(input);
|
||||
});
|
||||
});
|
||||
|
||||
@@ -1,31 +0,0 @@
|
||||
import type { AgentMessage } from "@mariozechner/pi-agent-core";
|
||||
import { describe, expect, it } from "vitest";
|
||||
import { sanitizeGoogleTurnOrdering } from "./pi-embedded-helpers.js";
|
||||
import { DEFAULT_AGENTS_FILENAME } from "./workspace.js";
|
||||
|
||||
const _makeFile = (overrides: Partial<WorkspaceBootstrapFile>): WorkspaceBootstrapFile => ({
|
||||
name: DEFAULT_AGENTS_FILENAME,
|
||||
path: "/tmp/AGENTS.md",
|
||||
content: "",
|
||||
missing: false,
|
||||
...overrides,
|
||||
});
|
||||
describe("sanitizeGoogleTurnOrdering", () => {
|
||||
it("prepends a synthetic user turn when history starts with assistant", () => {
|
||||
const input = [
|
||||
{
|
||||
role: "assistant",
|
||||
content: [{ type: "toolCall", id: "call_1", name: "exec", arguments: {} }],
|
||||
},
|
||||
] satisfies AgentMessage[];
|
||||
|
||||
const out = sanitizeGoogleTurnOrdering(input);
|
||||
expect(out[0]?.role).toBe("user");
|
||||
expect(out[1]?.role).toBe("assistant");
|
||||
});
|
||||
it("is a no-op when history starts with user", () => {
|
||||
const input = [{ role: "user", content: "hi" }] satisfies AgentMessage[];
|
||||
const out = sanitizeGoogleTurnOrdering(input);
|
||||
expect(out).toBe(input);
|
||||
});
|
||||
});
|
||||
@@ -1,37 +0,0 @@
|
||||
import type { AgentMessage } from "@mariozechner/pi-agent-core";
|
||||
import { describe, expect, it } from "vitest";
|
||||
import { sanitizeSessionMessagesImages } from "./pi-embedded-helpers.js";
|
||||
import { DEFAULT_AGENTS_FILENAME } from "./workspace.js";
|
||||
|
||||
const _makeFile = (overrides: Partial<WorkspaceBootstrapFile>): WorkspaceBootstrapFile => ({
|
||||
name: DEFAULT_AGENTS_FILENAME,
|
||||
path: "/tmp/AGENTS.md",
|
||||
content: "",
|
||||
missing: false,
|
||||
...overrides,
|
||||
});
|
||||
describe("sanitizeSessionMessagesImages - thought_signature stripping", () => {
|
||||
it("strips msg_-prefixed thought_signature from assistant message content blocks", async () => {
|
||||
const input = [
|
||||
{
|
||||
role: "assistant",
|
||||
content: [
|
||||
{ type: "text", text: "hello", thought_signature: "msg_abc123" },
|
||||
{
|
||||
type: "thinking",
|
||||
thinking: "reasoning",
|
||||
thought_signature: "AQID",
|
||||
},
|
||||
],
|
||||
},
|
||||
] satisfies AgentMessage[];
|
||||
|
||||
const out = await sanitizeSessionMessagesImages(input, "test");
|
||||
|
||||
expect(out).toHaveLength(1);
|
||||
const content = (out[0] as { content?: unknown[] }).content;
|
||||
expect(content).toHaveLength(2);
|
||||
expect("thought_signature" in ((content?.[0] ?? {}) as object)).toBe(false);
|
||||
expect((content?.[1] as { thought_signature?: unknown })?.thought_signature).toBe("AQID");
|
||||
});
|
||||
});
|
||||
@@ -1,43 +0,0 @@
|
||||
import { describe, expect, it } from "vitest";
|
||||
import { sanitizeToolCallId } from "./pi-embedded-helpers.js";
|
||||
|
||||
describe("sanitizeToolCallId", () => {
|
||||
describe("strict mode (default)", () => {
|
||||
it("keeps valid alphanumeric tool call IDs", () => {
|
||||
expect(sanitizeToolCallId("callabc123")).toBe("callabc123");
|
||||
});
|
||||
it("strips underscores and hyphens", () => {
|
||||
expect(sanitizeToolCallId("call_abc-123")).toBe("callabc123");
|
||||
expect(sanitizeToolCallId("call_abc_def")).toBe("callabcdef");
|
||||
});
|
||||
it("strips invalid characters", () => {
|
||||
expect(sanitizeToolCallId("call_abc|item:456")).toBe("callabcitem456");
|
||||
});
|
||||
it("returns default for empty IDs", () => {
|
||||
expect(sanitizeToolCallId("")).toBe("defaulttoolid");
|
||||
});
|
||||
});
|
||||
|
||||
describe("strict mode (alphanumeric only)", () => {
|
||||
it("strips all non-alphanumeric characters", () => {
|
||||
expect(sanitizeToolCallId("call_abc-123", "strict")).toBe("callabc123");
|
||||
expect(sanitizeToolCallId("call_abc|item:456", "strict")).toBe("callabcitem456");
|
||||
expect(sanitizeToolCallId("whatsapp_login_1768799841527_1", "strict")).toBe(
|
||||
"whatsapplogin17687998415271",
|
||||
);
|
||||
});
|
||||
it("returns default for empty IDs", () => {
|
||||
expect(sanitizeToolCallId("", "strict")).toBe("defaulttoolid");
|
||||
});
|
||||
});
|
||||
|
||||
describe("strict9 mode (Mistral tool call IDs)", () => {
|
||||
it("returns alphanumeric IDs with length 9", () => {
|
||||
const out = sanitizeToolCallId("call_abc|item:456", "strict9");
|
||||
expect(out).toMatch(/^[a-zA-Z0-9]{9}$/);
|
||||
});
|
||||
it("returns default for empty IDs", () => {
|
||||
expect(sanitizeToolCallId("", "strict9")).toMatch(/^[a-zA-Z0-9]{9}$/);
|
||||
});
|
||||
});
|
||||
});
|
||||
@@ -1,5 +1,12 @@
|
||||
import { describe, expect, it } from "vitest";
|
||||
import { sanitizeUserFacingText } from "./pi-embedded-helpers.js";
|
||||
import {
|
||||
downgradeOpenAIReasoningBlocks,
|
||||
isMessagingToolDuplicate,
|
||||
normalizeTextForComparison,
|
||||
sanitizeToolCallId,
|
||||
sanitizeUserFacingText,
|
||||
stripThoughtSignatures,
|
||||
} from "./pi-embedded-helpers.js";
|
||||
|
||||
describe("sanitizeUserFacingText", () => {
|
||||
it("strips final tags", () => {
|
||||
@@ -114,3 +121,257 @@ describe("sanitizeUserFacingText", () => {
|
||||
expect(sanitizeUserFacingText(" \n ")).toBe("");
|
||||
});
|
||||
});
|
||||
|
||||
describe("stripThoughtSignatures", () => {
|
||||
it("returns non-array content unchanged", () => {
|
||||
expect(stripThoughtSignatures("hello")).toBe("hello");
|
||||
expect(stripThoughtSignatures(null)).toBe(null);
|
||||
expect(stripThoughtSignatures(undefined)).toBe(undefined);
|
||||
expect(stripThoughtSignatures(123)).toBe(123);
|
||||
});
|
||||
it("removes msg_-prefixed thought_signature from content blocks", () => {
|
||||
const input = [
|
||||
{ type: "text", text: "hello", thought_signature: "msg_abc123" },
|
||||
{ type: "thinking", thinking: "test", thought_signature: "AQID" },
|
||||
];
|
||||
const result = stripThoughtSignatures(input);
|
||||
|
||||
expect(result).toHaveLength(2);
|
||||
expect(result[0]).toEqual({ type: "text", text: "hello" });
|
||||
expect(result[1]).toEqual({
|
||||
type: "thinking",
|
||||
thinking: "test",
|
||||
thought_signature: "AQID",
|
||||
});
|
||||
expect("thought_signature" in result[0]).toBe(false);
|
||||
expect("thought_signature" in result[1]).toBe(true);
|
||||
});
|
||||
it("preserves blocks without thought_signature", () => {
|
||||
const input = [
|
||||
{ type: "text", text: "hello" },
|
||||
{ type: "toolCall", id: "call_1", name: "read", arguments: {} },
|
||||
];
|
||||
const result = stripThoughtSignatures(input);
|
||||
|
||||
expect(result).toEqual(input);
|
||||
});
|
||||
it("handles mixed blocks with and without thought_signature", () => {
|
||||
const input = [
|
||||
{ type: "text", text: "hello", thought_signature: "msg_abc" },
|
||||
{ type: "toolCall", id: "call_1", name: "read", arguments: {} },
|
||||
{ type: "thinking", thinking: "hmm", thought_signature: "msg_xyz" },
|
||||
];
|
||||
const result = stripThoughtSignatures(input);
|
||||
|
||||
expect(result).toEqual([
|
||||
{ type: "text", text: "hello" },
|
||||
{ type: "toolCall", id: "call_1", name: "read", arguments: {} },
|
||||
{ type: "thinking", thinking: "hmm" },
|
||||
]);
|
||||
});
|
||||
it("handles empty array", () => {
|
||||
expect(stripThoughtSignatures([])).toEqual([]);
|
||||
});
|
||||
it("handles null/undefined blocks in array", () => {
|
||||
const input = [null, undefined, { type: "text", text: "hello" }];
|
||||
const result = stripThoughtSignatures(input);
|
||||
expect(result).toEqual([null, undefined, { type: "text", text: "hello" }]);
|
||||
});
|
||||
});
|
||||
|
||||
describe("sanitizeToolCallId", () => {
|
||||
describe("strict mode (default)", () => {
|
||||
it("keeps valid alphanumeric tool call IDs", () => {
|
||||
expect(sanitizeToolCallId("callabc123")).toBe("callabc123");
|
||||
});
|
||||
it("strips underscores and hyphens", () => {
|
||||
expect(sanitizeToolCallId("call_abc-123")).toBe("callabc123");
|
||||
expect(sanitizeToolCallId("call_abc_def")).toBe("callabcdef");
|
||||
});
|
||||
it("strips invalid characters", () => {
|
||||
expect(sanitizeToolCallId("call_abc|item:456")).toBe("callabcitem456");
|
||||
});
|
||||
it("returns default for empty IDs", () => {
|
||||
expect(sanitizeToolCallId("")).toBe("defaulttoolid");
|
||||
});
|
||||
});
|
||||
|
||||
describe("strict mode (alphanumeric only)", () => {
|
||||
it("strips all non-alphanumeric characters", () => {
|
||||
expect(sanitizeToolCallId("call_abc-123", "strict")).toBe("callabc123");
|
||||
expect(sanitizeToolCallId("call_abc|item:456", "strict")).toBe("callabcitem456");
|
||||
expect(sanitizeToolCallId("whatsapp_login_1768799841527_1", "strict")).toBe(
|
||||
"whatsapplogin17687998415271",
|
||||
);
|
||||
});
|
||||
it("returns default for empty IDs", () => {
|
||||
expect(sanitizeToolCallId("", "strict")).toBe("defaulttoolid");
|
||||
});
|
||||
});
|
||||
|
||||
describe("strict9 mode (Mistral tool call IDs)", () => {
|
||||
it("returns alphanumeric IDs with length 9", () => {
|
||||
const out = sanitizeToolCallId("call_abc|item:456", "strict9");
|
||||
expect(out).toMatch(/^[a-zA-Z0-9]{9}$/);
|
||||
});
|
||||
it("returns default for empty IDs", () => {
|
||||
expect(sanitizeToolCallId("", "strict9")).toMatch(/^[a-zA-Z0-9]{9}$/);
|
||||
});
|
||||
});
|
||||
});
|
||||
|
||||
describe("downgradeOpenAIReasoningBlocks", () => {
|
||||
it("keeps reasoning signatures when followed by content", () => {
|
||||
const input = [
|
||||
{
|
||||
role: "assistant",
|
||||
content: [
|
||||
{
|
||||
type: "thinking",
|
||||
thinking: "internal reasoning",
|
||||
thinkingSignature: JSON.stringify({ id: "rs_123", type: "reasoning" }),
|
||||
},
|
||||
{ type: "text", text: "answer" },
|
||||
],
|
||||
},
|
||||
];
|
||||
|
||||
// oxlint-disable-next-line typescript/no-explicit-any
|
||||
expect(downgradeOpenAIReasoningBlocks(input as any)).toEqual(input);
|
||||
});
|
||||
|
||||
it("drops orphaned reasoning blocks without following content", () => {
|
||||
const input = [
|
||||
{
|
||||
role: "assistant",
|
||||
content: [
|
||||
{
|
||||
type: "thinking",
|
||||
thinkingSignature: JSON.stringify({ id: "rs_abc", type: "reasoning" }),
|
||||
},
|
||||
],
|
||||
},
|
||||
{ role: "user", content: "next" },
|
||||
];
|
||||
|
||||
// oxlint-disable-next-line typescript/no-explicit-any
|
||||
expect(downgradeOpenAIReasoningBlocks(input as any)).toEqual([
|
||||
{ role: "user", content: "next" },
|
||||
]);
|
||||
});
|
||||
|
||||
it("drops object-form orphaned signatures", () => {
|
||||
const input = [
|
||||
{
|
||||
role: "assistant",
|
||||
content: [
|
||||
{
|
||||
type: "thinking",
|
||||
thinkingSignature: { id: "rs_obj", type: "reasoning" },
|
||||
},
|
||||
],
|
||||
},
|
||||
];
|
||||
|
||||
// oxlint-disable-next-line typescript/no-explicit-any
|
||||
expect(downgradeOpenAIReasoningBlocks(input as any)).toEqual([]);
|
||||
});
|
||||
|
||||
it("keeps non-reasoning thinking signatures", () => {
|
||||
const input = [
|
||||
{
|
||||
role: "assistant",
|
||||
content: [
|
||||
{
|
||||
type: "thinking",
|
||||
thinking: "t",
|
||||
thinkingSignature: "reasoning_content",
|
||||
},
|
||||
],
|
||||
},
|
||||
];
|
||||
|
||||
// oxlint-disable-next-line typescript/no-explicit-any
|
||||
expect(downgradeOpenAIReasoningBlocks(input as any)).toEqual(input);
|
||||
});
|
||||
});
|
||||
|
||||
describe("normalizeTextForComparison", () => {
|
||||
it("lowercases text", () => {
|
||||
expect(normalizeTextForComparison("Hello World")).toBe("hello world");
|
||||
});
|
||||
|
||||
it("trims whitespace", () => {
|
||||
expect(normalizeTextForComparison(" hello ")).toBe("hello");
|
||||
});
|
||||
|
||||
it("collapses multiple spaces", () => {
|
||||
expect(normalizeTextForComparison("hello world")).toBe("hello world");
|
||||
});
|
||||
|
||||
it("strips emoji", () => {
|
||||
expect(normalizeTextForComparison("Hello 👋 World 🌍")).toBe("hello world");
|
||||
});
|
||||
|
||||
it("handles mixed normalization", () => {
|
||||
expect(normalizeTextForComparison(" Hello 👋 WORLD 🌍 ")).toBe("hello world");
|
||||
});
|
||||
});
|
||||
|
||||
describe("isMessagingToolDuplicate", () => {
|
||||
it("returns false for empty sentTexts", () => {
|
||||
expect(isMessagingToolDuplicate("hello world", [])).toBe(false);
|
||||
});
|
||||
|
||||
it("returns false for short texts", () => {
|
||||
expect(isMessagingToolDuplicate("short", ["short"])).toBe(false);
|
||||
});
|
||||
|
||||
it("detects exact duplicates", () => {
|
||||
expect(
|
||||
isMessagingToolDuplicate("Hello, this is a test message!", [
|
||||
"Hello, this is a test message!",
|
||||
]),
|
||||
).toBe(true);
|
||||
});
|
||||
|
||||
it("detects duplicates with different casing", () => {
|
||||
expect(
|
||||
isMessagingToolDuplicate("HELLO, THIS IS A TEST MESSAGE!", [
|
||||
"hello, this is a test message!",
|
||||
]),
|
||||
).toBe(true);
|
||||
});
|
||||
|
||||
it("detects duplicates with emoji variations", () => {
|
||||
expect(
|
||||
isMessagingToolDuplicate("Hello! 👋 This is a test message!", [
|
||||
"Hello! This is a test message!",
|
||||
]),
|
||||
).toBe(true);
|
||||
});
|
||||
|
||||
it("detects substring duplicates (LLM elaboration)", () => {
|
||||
expect(
|
||||
isMessagingToolDuplicate('I sent the message: "Hello, this is a test message!"', [
|
||||
"Hello, this is a test message!",
|
||||
]),
|
||||
).toBe(true);
|
||||
});
|
||||
|
||||
it("detects when sent text contains block reply (reverse substring)", () => {
|
||||
expect(
|
||||
isMessagingToolDuplicate("Hello, this is a test message!", [
|
||||
'I sent the message: "Hello, this is a test message!"',
|
||||
]),
|
||||
).toBe(true);
|
||||
});
|
||||
|
||||
it("returns false for non-matching texts", () => {
|
||||
expect(
|
||||
isMessagingToolDuplicate("This is completely different content.", [
|
||||
"Hello, this is a test message!",
|
||||
]),
|
||||
).toBe(false);
|
||||
});
|
||||
});
|
||||
|
||||
@@ -1,67 +0,0 @@
|
||||
import { describe, expect, it } from "vitest";
|
||||
import { stripThoughtSignatures } from "./pi-embedded-helpers.js";
|
||||
import { DEFAULT_AGENTS_FILENAME } from "./workspace.js";
|
||||
|
||||
const _makeFile = (overrides: Partial<WorkspaceBootstrapFile>): WorkspaceBootstrapFile => ({
|
||||
name: DEFAULT_AGENTS_FILENAME,
|
||||
path: "/tmp/AGENTS.md",
|
||||
content: "",
|
||||
missing: false,
|
||||
...overrides,
|
||||
});
|
||||
describe("stripThoughtSignatures", () => {
|
||||
it("returns non-array content unchanged", () => {
|
||||
expect(stripThoughtSignatures("hello")).toBe("hello");
|
||||
expect(stripThoughtSignatures(null)).toBe(null);
|
||||
expect(stripThoughtSignatures(undefined)).toBe(undefined);
|
||||
expect(stripThoughtSignatures(123)).toBe(123);
|
||||
});
|
||||
it("removes msg_-prefixed thought_signature from content blocks", () => {
|
||||
const input = [
|
||||
{ type: "text", text: "hello", thought_signature: "msg_abc123" },
|
||||
{ type: "thinking", thinking: "test", thought_signature: "AQID" },
|
||||
];
|
||||
const result = stripThoughtSignatures(input);
|
||||
|
||||
expect(result).toHaveLength(2);
|
||||
expect(result[0]).toEqual({ type: "text", text: "hello" });
|
||||
expect(result[1]).toEqual({
|
||||
type: "thinking",
|
||||
thinking: "test",
|
||||
thought_signature: "AQID",
|
||||
});
|
||||
expect("thought_signature" in result[0]).toBe(false);
|
||||
expect("thought_signature" in result[1]).toBe(true);
|
||||
});
|
||||
it("preserves blocks without thought_signature", () => {
|
||||
const input = [
|
||||
{ type: "text", text: "hello" },
|
||||
{ type: "toolCall", id: "call_1", name: "read", arguments: {} },
|
||||
];
|
||||
const result = stripThoughtSignatures(input);
|
||||
|
||||
expect(result).toEqual(input);
|
||||
});
|
||||
it("handles mixed blocks with and without thought_signature", () => {
|
||||
const input = [
|
||||
{ type: "text", text: "hello", thought_signature: "msg_abc" },
|
||||
{ type: "toolCall", id: "call_1", name: "read", arguments: {} },
|
||||
{ type: "thinking", thinking: "hmm", thought_signature: "msg_xyz" },
|
||||
];
|
||||
const result = stripThoughtSignatures(input);
|
||||
|
||||
expect(result).toEqual([
|
||||
{ type: "text", text: "hello" },
|
||||
{ type: "toolCall", id: "call_1", name: "read", arguments: {} },
|
||||
{ type: "thinking", thinking: "hmm" },
|
||||
]);
|
||||
});
|
||||
it("handles empty array", () => {
|
||||
expect(stripThoughtSignatures([])).toEqual([]);
|
||||
});
|
||||
it("handles null/undefined blocks in array", () => {
|
||||
const input = [null, undefined, { type: "text", text: "hello" }];
|
||||
const result = stripThoughtSignatures(input);
|
||||
expect(result).toEqual([null, undefined, { type: "text", text: "hello" }]);
|
||||
});
|
||||
});
|
||||
Reference in New Issue
Block a user