lam-agent-vicinae/src/__tests__/code.test.ts

import { describe, expect, it } from "vitest";
import {
  inferLanguage,
  labelCodeFences,
  promoteStandaloneCodeSpans,
  repairCodeBlocks,
  restoreUrlLinks,
} from "../lib/code";

describe("inferLanguage", () => {
  it("returns nothing for empty or whitespace-only code", () => {
    expect(inferLanguage("")).toBeUndefined();
    expect(inferLanguage("   \n  ")).toBeUndefined();
  });

  describe("shell", () => {
    it("recognises a command as the first word", () => {
      expect(inferLanguage("pwd")).toBe("bash");
      expect(inferLanguage("git status")).toBe("bash");
      expect(inferLanguage("brew install ripgrep")).toBe("bash");
    });

    it("recognises an explicit prompt marker", () => {
      expect(inferLanguage("$ git status")).toBe("bash");
      expect(inferLanguage("> ls -la")).toBe("bash");
    });

    it("recognises a home-relative path", () => {
      expect(inferLanguage("~/Documents/Code")).toBe("bash");
    });

    it("recognises a pipeline between known commands", () => {
      expect(inferLanguage("git log --oneline | head -20")).toBe("bash");
    });

    it("ignores comments when looking at the first word", () => {
      expect(inferLanguage("# check the branch\ngit branch --show-current")).toBe("bash");
    });
  });

  describe("json", () => {
    it("recognises a parseable object", () => {
      expect(inferLanguage('{\n  "model": "gpt-oss"\n}')).toBe("json");
    });

    it("recognises a parseable array", () => {
      expect(inferLanguage('["a", "b"]')).toBe("json");
    });

    it("does not claim malformed braces", () => {
      expect(inferLanguage("{ not actually json")).not.toBe("json");
    });
  });

  describe("typescript", () => {
    it("recognises type annotations", () => {
      expect(inferLanguage("function add(a: number, b: number) {\n  return a + b;\n}")).toBe("ts");
    });

    it("recognises interfaces and type aliases", () => {
      expect(inferLanguage("interface User {\n  id: string;\n}")).toBe("ts");
      expect(inferLanguage("type Id = string | number;")).toBe("ts");
    });

    it("does not label plain JavaScript, which is ambiguous", () => {
      // Guessing wrong costs the highlighting, so this stays unlabelled.
      expect(inferLanguage("console.log('hi')")).toBeUndefined();
      expect(inferLanguage("const x = [1, 2, 3].map((n) => n * 2);")).toBeUndefined();
    });
  });

  describe("python", () => {
    it("recognises a function definition", () => {
      expect(inferLanguage("def greet(name):\n    return f'hi {name}'")).toBe("python");
    });

    it("recognises imports and self", () => {
      expect(inferLanguage("from pathlib import Path")).toBe("python");
      expect(inferLanguage("class A:\n    def go(self):\n        pass")).toBe("python");
    });
  });

  it("leaves genuinely ambiguous content alone", () => {
    expect(inferLanguage("some plain text\nacross two lines")).toBeUndefined();
  });
});

describe("promoteStandaloneCodeSpans", () => {
  it("promotes a paragraph that is one inline span", () => {
    // The reported case: asking for a command and getting a lone chip back.
    expect(promoteStandaloneCodeSpans("`pwd`")).toBe("```bash\npwd\n```");
  });

  it("promotes the same span on its own line within a larger answer", () => {
    const promoted = promoteStandaloneCodeSpans("Here you go:\n\n`pwd`\n\nThat prints the path.");

    expect(promoted).toContain("```bash\npwd\n```");
    expect(promoted).toContain("Here you go:");
    expect(promoted).toContain("That prints the path.");
  });

  it("tolerates a sentence-ending period", () => {
    expect(promoteStandaloneCodeSpans("`pwd`.")).toBe("```bash\npwd\n```");
  });

  it("leaves a span embedded in a sentence alone", () => {
    const input = "Run `pwd` to see where you are.";
    expect(promoteStandaloneCodeSpans(input)).toBe(input);
  });

  it("leaves a bulleted span alone", () => {
    const input = "- `pwd -P` resolves symlinks";
    expect(promoteStandaloneCodeSpans(input)).toBe(input);
  });

  it("never rewrites a span-like line inside an existing fence", () => {
    const input = "```bash\n`not-a-span`\n```";
    expect(promoteStandaloneCodeSpans(input)).toBe(input);
  });

  it("fences a span whose language cannot be inferred, without guessing one", () => {
    expect(promoteStandaloneCodeSpans("`Get-Location`")).toBe("```\nGet-Location\n```");
  });

  it("is idempotent", () => {
    const once = promoteStandaloneCodeSpans("`pwd`");
    expect(promoteStandaloneCodeSpans(once)).toBe(once);
  });

  it("is a no-op on ordinary prose", () => {
    const input = "There is no code here at all.";
    expect(promoteStandaloneCodeSpans(input)).toBe(input);
  });
});

describe("restoreUrlLinks", () => {
  it("unwraps a fence that is nothing but URLs", () => {
    // The reported case: "here are the links" arriving as a code block, so the
    // one thing a URL is for, being clicked, does not work.
    const input = [
      "```",
      "https://github.com/jasonkneen/openclicky",
      "https://github.com/unn-Known1/clickyX",
      "```",
    ].join("\n");

    expect(restoreUrlLinks(input)).toBe(
      [
        "[https://github.com/jasonkneen/openclicky](https://github.com/jasonkneen/openclicky)",
        "[https://github.com/unn-Known1/clickyX](https://github.com/unn-Known1/clickyX)",
      ].join("\n"),
    );
  });

  it("unwraps a URL fence even when the model labelled it", () => {
    expect(restoreUrlLinks("```bash\nhttps://example.com\n```")).toBe(
      "[https://example.com](https://example.com)",
    );
  });

  it("links a bare URL standing alone on a line", () => {
    expect(restoreUrlLinks("https://example.com")).toBe("[https://example.com](https://example.com)");
  });

  it("links a lone inline span holding a URL", () => {
    expect(restoreUrlLinks("`https://example.com`")).toBe(
      "[https://example.com](https://example.com)",
    );
  });

  it("keeps a bulleted list of links a bulleted list", () => {
    const input = "- https://a.example\n- https://b.example";

    expect(restoreUrlLinks(input)).toBe(
      "- [https://a.example](https://a.example)\n- [https://b.example](https://b.example)",
    );
  });

  it("keeps an ordered list marker", () => {
    expect(restoreUrlLinks("1. https://example.com")).toBe(
      "1. [https://example.com](https://example.com)",
    );
  });

  it("drops sentence punctuation that is not part of the address", () => {
    expect(restoreUrlLinks("See this:\n\nhttps://example.com.")).toContain(
      "[https://example.com](https://example.com)",
    );
  });

  it("brackets a destination that contains parentheses", () => {
    const url = "https://en.wikipedia.org/wiki/Foo_(bar)";
    expect(restoreUrlLinks(url)).toBe(`[${url}](<${url}>)`);
  });

  it("escapes brackets in the label, which an IPv6 literal contains", () => {
    // Unescaped, the `]` in the label ends the link text early and the rest of
    // the address is left as prose outside the link.
    expect(restoreUrlLinks("http://[::1]:8080/")).toBe(
      "[http://\\[::1\\]:8080/](http://[::1]:8080/)",
    );
  });

  it("never touches a fence holding real code", () => {
    const input = "```bash\ncurl https://example.com | jq .\n```";
    expect(restoreUrlLinks(input)).toBe(input);
  });

  it("never touches a fence when one line is not a URL", () => {
    const input = "```\nhttps://example.com\nnot a url\n```";
    expect(restoreUrlLinks(input)).toBe(input);
  });

  it("leaves a URL embedded in a sentence alone", () => {
    const input = "The docs at https://example.com cover it.";
    expect(restoreUrlLinks(input)).toBe(input);
  });

  it("leaves a markdown link the model already wrote alone", () => {
    const input = "[OpenClickly](https://github.com/jasonkneen/openclicky)";
    expect(restoreUrlLinks(input)).toBe(input);
  });

  it("preserves a fence that is never closed and is real code", () => {
    expect(restoreUrlLinks("```\ngit log")).toBe("```\ngit log");
  });

  it("is idempotent", () => {
    const once = restoreUrlLinks("```\nhttps://example.com\n```");
    expect(restoreUrlLinks(once)).toBe(once);
  });

  it("is a no-op on ordinary prose", () => {
    const input = "There are no addresses in this sentence.";
    expect(restoreUrlLinks(input)).toBe(input);
  });
});

describe("repairCodeBlocks", () => {
  it("promotes a lone command and labels it in one pass", () => {
    expect(repairCodeBlocks("`pwd`")).toBe("```bash\npwd\n```");
  });

  it("does not fence a lone URL", () => {
    // Restoring links runs before promotion, so a recovered URL never becomes a
    // fence again. Fencing it here was the bug the user saw.
    const repaired = repairCodeBlocks("`https://example.com`");

    expect(repaired).not.toContain("```");
    expect(repaired).toBe("[https://example.com](https://example.com)");
  });

  it("unwraps a fenced list of links and leaves no fence behind", () => {
    const repaired = repairCodeBlocks("```\nhttps://a.example\nhttps://b.example\n```");

    expect(repaired).not.toContain("```");
    expect(repaired).toContain("[https://a.example](https://a.example)");
  });

  it("still labels a bare multi-line fence", () => {
    expect(repairCodeBlocks("```\ngit status\n```")).toBe("```bash\ngit status\n```");
  });

  it("handles a promoted block and a plain fence in the same answer", () => {
    const repaired = repairCodeBlocks("First:\n\n`pwd`\n\nThen:\n\n```\nls -la\n```");

    expect(repaired).toContain("```bash\npwd\n```");
    expect(repaired).toContain("```bash\nls -la\n```");
  });
});

describe("labelCodeFences", () => {
  it("labels a bare fence", () => {
    const labelled = labelCodeFences("```\ngit status\n```");
    expect(labelled).toBe("```bash\ngit status\n```");
  });

  it("leaves an already labelled fence exactly as the model wrote it", () => {
    expect(labelCodeFences("```rust\nfn main() {}\n```")).toBe("```rust\nfn main() {}\n```");
  });

  it("labels each block independently", () => {
    const labelled = labelCodeFences(["```", "pwd", "```", "", "```", '{"a": 1}', "```"].join("\n"));

    expect(labelled).toContain("```bash");
    expect(labelled).toContain("```json");
  });

  it("leaves an unlabellable block bare rather than guessing", () => {
    const input = "```\njust some words\n```";
    expect(labelCodeFences(input)).toBe(input);
  });

  it("preserves surrounding prose", () => {
    const labelled = labelCodeFences("Before:\n\n```\nls\n```\n\nAfter.");

    expect(labelled).toContain("Before:");
    expect(labelled).toContain("After.");
    expect(labelled).toContain("```bash");
  });

  it("handles a fence that is never closed", () => {
    expect(labelCodeFences("```\ngit log")).toContain("```bash");
  });

  it("is a no-op on markdown with no fences", () => {
    const input = "Just a paragraph with `inline code` in it.";
    expect(labelCodeFences(input)).toBe(input);
  });

  it("is idempotent", () => {
    const once = labelCodeFences("```\nls\n```");
    expect(labelCodeFences(once)).toBe(once);
  });

  it("does not mistake a closing fence for a new opening one", () => {
    // A closing ``` and an opening bare ``` are identical lines. Treating the
    // closing one as an opening fence swallowed everything after it, so the
    // second block never got labelled.
    const input = "```bash\npwd\n```\n\n```\nls -la\n```";
    expect(labelCodeFences(input)).toContain("```bash\nls -la\n```");
  });

  it("labels a later block even when an earlier one is already labelled", () => {
    const input = "```rust\nfn main() {}\n```\n\n```\npwd\n```";
    const labelled = labelCodeFences(input);

    expect(labelled).toContain("```rust");
    expect(labelled).toContain("```bash\npwd\n```");
  });

  it("preserves a language the model chose, including multi-word freeform tags", () => {
    expect(labelCodeFences("```c++\nint main() {}\n```")).toContain("```c++");
    expect(labelCodeFences("```objective-c\nint x;\n```")).toContain("```objective-c");
  });

  it("preserves indentation of a nested fence", () => {
    expect(labelCodeFences("  ```\n  ls\n  ```")).toContain("  ```bash");
  });
});