FabledGrimoire/tests/test_after_write_hook.py

"""The PostToolUse after-write hook: code written through Bash — sed,
heredocs, scripts — gets the same prior-art / ledger checks as a Write/Edit.

Runs the real shell against a temp git repo and a throwaway HTTP sink, like
the pre-write hook's end-to-end tests. Skips where the hook's tools are
missing; asserts on content where they are present."""
from __future__ import annotations

import json
import os
import shutil
import subprocess
from pathlib import Path

import pytest

from tests.helpers import http_sink

PLUGIN = Path(__file__).resolve().parents[1] / "plugin"
HOOK = PLUGIN / "hooks" / "scribe_after_write.sh"


def _env(tmp_path, url="http://127.0.0.1:9"):
    for tool in ("git", "curl", "bash"):
        if shutil.which(tool) is None:
            pytest.skip(f"hook runtime tool {tool!r} not installed")
    return {"PATH": os.environ["PATH"], "SCRIBE_URL": url, "SCRIBE_TOKEN": "t",
            "TMPDIR": str(tmp_path), "HOME": str(tmp_path),
            "GIT_AUTHOR_NAME": "t", "GIT_AUTHOR_EMAIL": "t@x", 
            "GIT_COMMITTER_NAME": "t", "GIT_COMMITTER_EMAIL": "t@x"}


def _repo(tmp_path, env):
    repo = tmp_path / "repo"
    repo.mkdir()
    subprocess.run(["git", "init", "-q"], cwd=repo, check=True, env=env)
    (repo / "b.py").write_text("def one():\n    return 1\n")
    (repo / "c.py").write_text("def slug(t):\n    return t.lower()\n")
    subprocess.run(["git", "add", "."], cwd=repo, check=True, env=env)
    subprocess.run(["git", "commit", "-q", "-m", "base"], cwd=repo, check=True, env=env)
    return repo


def _run(repo, env, session="s-after-1", tool="Bash"):
    out = subprocess.run(
        ["bash", str(HOOK)],
        input=json.dumps({"session_id": session, "cwd": str(repo), "tool_name": tool,
                          "tool_input": {"command": "cat > x"}, "tool_response": {}}),
        capture_output=True, text=True, env=env,
    )
    assert out.returncode == 0, out.stderr
    return out.stdout


SINK_REPLY = b'{"context":"> family named","note_ids":[],"sync_note_ids":[],"derive_keys":["dup:483a"]}'


def test_after_write_names_what_bash_just_wrote_then_stays_quiet_until_the_next_change(tmp_path):
    with http_sink(SINK_REPLY) as (port, seen):
        env = _env(tmp_path, url=f"http://127.0.0.1:{port}")
        repo = _repo(tmp_path, env)
        # "A Bash call" wrote an untracked stylesheet and appended to a tracked file.
        (repo / "a.css").write_text(".log-empty {\n  color: red;\n}\n")
        (repo / "b.py").write_text("def one():\n    return 1\n\ndef slug(t):\n    return t\n")
        out = _run(repo, env)
        by_path = {q["path"][0]: q for q in seen}
        assert set(by_path) == {"a.css", "b.py"}           # repo-relative, like the pre hook
        assert by_path["a.css"]["shapes"] == ["css:log-empty"]
        assert by_path["b.py"]["shapes"] == ["sym:slug"]
        # Added lines only for the tracked file — the existing def is not "just written".
        assert "def slug" in by_path["b.py"]["code"][0] and "def one" not in by_path["b.py"]["code"][0]
        ctx = json.loads(out)["hookSpecificOutput"]
        assert ctx["hookEventName"] == "PostToolUse"
        assert "> family named" in ctx["additionalContext"]
        # The local by-name arm rides along: `slug` already lives in c.py.
        assert "`slug` is already defined in 1 other file(s): c.py" in ctx["additionalContext"]
        # Derive keys landed on the SHARED channel the pre-write hook reads.
        state = tmp_path / "scribe-priorart" / "s-after-1.derive.ids"
        assert "dup:483a" in state.read_text().split()

        # Nothing changed → one git status, no request, no output.
        seen.clear()
        assert _run(repo, env) == ""
        assert seen == []

        # Another change → only that file, and the dedup channel goes back up.
        (repo / "a.css").write_text(".log-empty {\n  color: red;\n}\n.other {\n  margin: 0;\n}\n")
        _run(repo, env)
        assert [q["path"][0] for q in seen] == ["a.css"]
        assert seen[0]["exclude_derive"] == ["dup:483a"]
        assert set(seen[0]["shapes"][0].split(",")) == {"css:log-empty", "css:other"}

def test_after_write_is_silent_where_it_has_nothing_to_say(tmp_path):
    env = _env(tmp_path)
    repo = _repo(tmp_path, env)
    # Not a Bash call → nothing (hooks.json matches Bash, the script re-checks).
    (repo / "a.css").write_text(".x {\n  color: red;\n}\n")
    assert _run(repo, env, tool="Write") == ""
    # Not a git repo → nothing.
    loose = tmp_path / "loose"
    loose.mkdir()
    (loose / "a.css").write_text(".x {\n  color: red;\n}\n")
    assert _run(loose, env, session="s-loose") == ""
    # A change that defines nothing (prose, a call-site edit) → nothing, even
    # with the server unreachable (port 9 refuses): no definitions, no call
    # owed, so not even the outage line. (a.css above is removed first:
    # it DOES define a shape, and an unanswered call for it would rightly speak.)
    (repo / "a.css").unlink()
    (repo / "README.md").write_text("# notes\n")
    (repo / "b.py").write_text("def one():\n    return one_more()\n")
    assert _run(repo, env, session="s-quiet") == ""


def test_after_write_local_arm_works_without_a_server_and_says_the_server_did_not_answer(tmp_path):
    """The local by-name arm needs no instance. A configured instance that
    does not ANSWER (a refused connection stands in for it) is said, once per
    outage — and the record nudge, which claims "nothing recorded",
    is withheld: no answer backs that claim."""
    env = _env(tmp_path)
    repo = _repo(tmp_path, env)
    (repo / "d.py").write_text("def slug(t):\n    return t.lower()\n")
    out = _run(repo, env, session="s-local")
    ctx = json.loads(out)["hookSpecificOutput"]["additionalContext"]
    assert "`slug` is already defined in 1 other file(s): c.py" in ctx
    assert "Grimoire did not answer the prior-art check for `d.py` within 8s" in ctx
    assert "UNCHECKED" in ctx
    assert "None of those existing copies is recorded" not in ctx
    marker = tmp_path / "scribe-priorart" / "s-local.unreached"
    assert marker.is_file() and marker.read_text().isdigit()
    # Still down a moment later: the local arm speaks, the outage line does not
    # repeat (once per outage, not once per write).
    (repo / "e.py").write_text("def slug(t):\n    return t.upper()\n")
    out = _run(repo, env, session="s-local")
    ctx = json.loads(out)["hookSpecificOutput"]["additionalContext"]
    assert "`slug` is already defined in" in ctx
    assert "did not answer" not in ctx


def test_after_write_unconfigured_install_owes_no_call_and_keeps_the_record_nudge(tmp_path):
    """No URL/token → no call was owed, so nothing is "unreached"; the local
    arm and the record nudge stand on their own."""
    env = {k: v for k, v in _env(tmp_path).items() if k not in ("SCRIBE_URL", "SCRIBE_TOKEN")}
    repo = _repo(tmp_path, env)
    (repo / "d.py").write_text("def slug(t):\n    return t.lower()\n")
    out = _run(repo, env, session="s-unconf")
    ctx = json.loads(out)["hookSpecificOutput"]["additionalContext"]
    assert "`slug` is already defined in 1 other file(s): c.py" in ctx
    assert "create_snippet" in ctx
    assert "did not answer" not in ctx
    assert not (tmp_path / "scribe-priorart" / "s-unconf.unreached").exists()