FabledScribe/tests/test_precompact_hook.py

"""The PreCompact hook steers the summary and never blocks the compaction (#3680).

The mechanism this pins was read out of the installed Claude Code build, not
out of the documentation, which describes a different one. Three facts decide
whether the hook works at all, and all three are properties of what the shell
writes rather than of anything Scribe runs:

  * **Exit 0.** The handler keeps a hook's stdout only when it `succeeded`,
    which is `status === 0`. A non-zero exit sends the same bytes down the
    failure branch instead, where they become a line on the operator's screen
    and reach the model not at all.

  * **Plain text on stdout.** That text is returned as `newCustomInstructions`
    and merged into the prompt that writes the summary. JSON is not unwrapped
    for this event — the hook-output schema has no PreCompact variant — so a
    JSON envelope would be spliced into the summarizer's instructions verbatim,
    braces and all.

  * **Never blocked.** `exit 2` or `{"decision": "block"}` makes the handler
    SKIP the compaction. The model is never told; the session simply runs on
    uncompacted toward its context limit with no summary. That is strictly
    worse than having no hook, and it is the outcome the spike existed to keep
    out of the plugin — so it is pinned here rather than left to review.

The fourth test is the one that catches a rewrite drifting back toward the
original design: a future edit that reaches for `additionalContext` would look
correct beside every other hook in this directory and would inject nothing.
"""
from __future__ import annotations

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

import pytest

ROOT = Path(__file__).resolve().parents[1]
HOOK = ROOT / "plugin" / "hooks" / "scribe_precompact_preserve.sh"
HOOKS_JSON = ROOT / "plugin" / "hooks" / "hooks.json"

EVENT = {"session_id": "s1", "transcript_path": "/tmp/t.jsonl", "cwd": "/repo",
         "hook_event_name": "PreCompact", "trigger": "manual",
         "custom_instructions": None}


def _run(event: dict, tmpdir: str | None = None) -> subprocess.CompletedProcess:
    """Run the hook with its ledger directory ISOLATED.

    The hook reads this session's rule ledgers since #4216, and they live under
    `$TMPDIR/scribe-priorart`. Without an override these tests would read the
    machine's real /tmp: on a developer box mid-session that is not empty, and
    the output would depend on what some other session happened to leave
    behind. None of the assertions below would fail on it today, which is
    exactly why it is worth closing now rather than after it starts flaking.
    """
    if shutil.which("bash") is None:
        pytest.skip("bash not installed")
    env = dict(os.environ)
    env["TMPDIR"] = tmpdir or tempfile.mkdtemp()
    return subprocess.run(["bash", str(HOOK)], input=json.dumps(event),
                          capture_output=True, text=True, timeout=30, env=env)


def _code() -> str:
    """The script with its comments and its heredoc removed.

    The static checks below are about what the shell DOES. Run over the whole
    file they also read the header — which quotes `{"decision":"block"}` in the
    course of explaining why this hook must never emit one — and the emitted
    instructions, which use the word "decision" in a sentence. Both are the
    file doing its job, and neither is code.
    """
    lines, in_heredoc = [], False
    for line in HOOK.read_text().splitlines():
        if in_heredoc:
            in_heredoc = line.strip() != "EOF"
            continue
        if line.lstrip().startswith("cat <<'EOF'"):
            in_heredoc = True
            continue
        if not line.lstrip().startswith("#"):
            lines.append(line)
    return "\n".join(lines)


def test_the_comment_stripper_still_leaves_the_shell_behind():
    """Guard on the three checks below it. `_code()` returning nothing would
    make every one of them pass while checking an empty string — the same
    circularity the plugin version check has to defend against."""
    code = _code()
    assert "set -uo pipefail" in code and "exit 0" in code
    # It really did strip: both of the words the checks look for are present
    # in the file, and neither is in the code.
    assert "decision" in HOOK.read_text()


@pytest.mark.parametrize("trigger", ["manual", "auto"])
def test_it_exits_zero_with_instructions_on_stdout(trigger):
    """Exit 0 plus non-empty stdout is the entire contract for reaching the
    summarizer; either half missing and the hook is decoration."""
    out = _run({**EVENT, "trigger": trigger})
    assert out.returncode == 0, out.stderr
    assert out.stdout.strip(), "empty stdout is dropped by the handler"


def test_the_instructions_name_what_has_to_survive():
    """The summary is the next turn's only copy of these, so the hook says so
    in the words a summarizer can act on."""
    said = _run(EVENT).stdout.lower()
    assert "id" in said and "title" in said
    for anchor in ("in progress", "scribe", "not yet recorded"):
        assert anchor in said, f"the instruction no longer mentions {anchor!r}"


def test_it_emits_text_and_not_a_json_envelope():
    """Every other hook here answers in JSON. This one must not: for PreCompact
    the envelope is not unwrapped, it is pasted into the summarizer's prompt."""
    assert not _run(EVENT).stdout.lstrip().startswith("{")


def test_it_never_blocks_the_compaction():
    """A block skips compaction silently from the model's side. Nothing in the
    script may produce one — not an exit code, not a decision."""
    code = _code()
    assert "decision" not in code, "a block decision would skip the compaction"
    assert "exit 2" not in code
    # A truncated or absent event must not turn into a non-zero exit either.
    env = dict(os.environ)
    env["TMPDIR"] = tempfile.mkdtemp()
    for event in ("", "not json", "{}"):
        out = subprocess.run(["bash", str(HOOK)], input=event,
                             capture_output=True, text=True, timeout=30, env=env)
        assert out.returncode == 0, f"{event!r} → {out.returncode}: {out.stderr}"


def test_additional_context_is_not_how_this_event_works():
    """SessionStart's channel, which does not exist on PreCompact. A rewrite
    that reaches for it would read as consistent with the other hooks and
    inject nothing at all."""
    assert "additionalContext" not in _code()


def test_the_plugin_registers_it_on_precompact():
    entries = json.loads(HOOKS_JSON.read_text())["hooks"]["PreCompact"]
    commands = [h["command"] for e in entries for h in e["hooks"]]
    assert any(HOOK.name in c for c in commands)
    assert all(h["type"] == "command" for e in entries for h in e["hooks"]), (
        "PreCompact accepts command hooks only — a prompt or agent hook is "
        "rejected at registration"
    )