import { describe, expect, it } from "vitest"; import { downgradeOpenAIReasoningBlocks, isMessagingToolDuplicate, normalizeTextForComparison, sanitizeToolCallId, sanitizeUserFacingText, stripThoughtSignatures, } from "./pi-embedded-helpers.js"; describe("sanitizeUserFacingText", () => { it("strips final tags", () => { expect(sanitizeUserFacingText("Hello")).toBe("Hello"); expect(sanitizeUserFacingText("Hi there!")).toBe("Hi there!"); }); it("does not clobber normal numeric prefixes", () => { expect(sanitizeUserFacingText("202 results found")).toBe("202 results found"); expect(sanitizeUserFacingText("400 days left")).toBe("400 days left"); }); it("sanitizes role ordering errors", () => { const result = sanitizeUserFacingText("400 Incorrect role information", { errorContext: true }); expect(result).toContain("Message ordering conflict"); }); it("sanitizes HTTP status errors with error hints", () => { expect(sanitizeUserFacingText("500 Internal Server Error", { errorContext: true })).toBe( "HTTP 500: Internal Server Error", ); }); it("sanitizes direct context-overflow errors", () => { expect( sanitizeUserFacingText( "Context overflow: prompt too large for the model. Try /reset (or /new) to start a fresh session, or use a larger-context model.", { errorContext: true }, ), ).toContain("Context overflow: prompt too large for the model."); expect( sanitizeUserFacingText("Request size exceeds model context window", { errorContext: true }), ).toContain("Context overflow: prompt too large for the model."); }); it("does not swallow assistant text that quotes the canonical context-overflow string", () => { const text = "Changelog note: we fixed false positives for `Context overflow: prompt too large for the model. Try /reset (or /new) to start a fresh session, or use a larger-context model.` in 2026.2.9"; expect(sanitizeUserFacingText(text)).toBe(text); }); it("does not rewrite conversational mentions of context overflow", () => { const text = "nah it failed, hit a context overflow. the prompt was too large for the model. want me to retry it with a different approach?"; expect(sanitizeUserFacingText(text)).toBe(text); }); it("does not rewrite technical summaries that mention context overflow", () => { const text = "Problem: When a subagent reads a very large file, it can exceed the model context window. Auto-compaction cannot help in that case."; expect(sanitizeUserFacingText(text)).toBe(text); }); it("does not rewrite conversational billing/help text without errorContext", () => { const text = "If your API billing is low, top up credits in your provider dashboard and retry payment verification."; expect(sanitizeUserFacingText(text)).toBe(text); }); it("does not rewrite normal text that mentions billing and plan", () => { const text = "Firebase downgraded us to the free Spark plan; check whether we need to re-enable billing."; expect(sanitizeUserFacingText(text)).toBe(text); }); it("rewrites billing error-shaped text", () => { const text = "billing: please upgrade your plan"; expect(sanitizeUserFacingText(text)).toContain("billing error"); }); it("sanitizes raw API error payloads", () => { const raw = '{"type":"error","error":{"message":"Something exploded","type":"server_error"}}'; expect(sanitizeUserFacingText(raw, { errorContext: true })).toBe( "LLM error server_error: Something exploded", ); }); it("returns a friendly message for rate limit errors in Error: prefixed payloads", () => { expect(sanitizeUserFacingText("Error: 429 Rate limit exceeded", { errorContext: true })).toBe( "⚠️ API rate limit reached. Please try again later.", ); }); it("collapses consecutive duplicate paragraphs", () => { const text = "Hello there!\n\nHello there!"; expect(sanitizeUserFacingText(text)).toBe("Hello there!"); }); it("does not collapse distinct paragraphs", () => { const text = "Hello there!\n\nDifferent line."; expect(sanitizeUserFacingText(text)).toBe(text); }); it("strips leading newlines from LLM output", () => { expect(sanitizeUserFacingText("\n\nHello there!")).toBe("Hello there!"); expect(sanitizeUserFacingText("\nHello there!")).toBe("Hello there!"); expect(sanitizeUserFacingText("\n\n\nMultiple newlines")).toBe("Multiple newlines"); }); it("strips leading whitespace and newlines combined", () => { expect(sanitizeUserFacingText("\n \nHello")).toBe("Hello"); expect(sanitizeUserFacingText(" \n\nHello")).toBe("Hello"); }); it("preserves trailing whitespace and internal newlines", () => { expect(sanitizeUserFacingText("Hello\n\nWorld\n")).toBe("Hello\n\nWorld\n"); expect(sanitizeUserFacingText("Line 1\nLine 2")).toBe("Line 1\nLine 2"); }); it("returns empty for whitespace-only input", () => { expect(sanitizeUserFacingText("\n\n")).toBe(""); 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); }); it("is idempotent for orphaned reasoning cleanup", () => { const input = [ { role: "assistant", content: [ { type: "thinking", thinkingSignature: JSON.stringify({ id: "rs_orphan", type: "reasoning" }), }, ], }, { role: "user", content: "next" }, ]; // oxlint-disable-next-line typescript/no-explicit-any const once = downgradeOpenAIReasoningBlocks(input as any); // oxlint-disable-next-line typescript/no-explicit-any const twice = downgradeOpenAIReasoningBlocks(once as any); expect(twice).toEqual(once); }); }); 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); }); });