agnes-the-ai-analyst/tests/test_lib_hooks.py
ZdenekSrotyr 7fc5365891
release: 0.46.3 — self-heal session pipeline + clearer diagnose (#220)
## Summary

Verified against production: `claude -p` headless mode doesn't fire SessionEnd hooks (proven via `--output-format stream-json --include-hook-events`: zero `SessionEnd` events), so any session JSONLs from `-p` invocations stay orphaned locally and never reach the server. Fix: add `agnes push --quiet` as a third SessionStart entry — symmetric self-heal alongside the existing `agnes pull` entry. Existing workspaces pick this up on their next `agnes init` via the marker-based migration already in `cli/lib/hooks.py`.

Separately: a colleague's fresh install showed `agnes diagnose` warning "uploads are not being processed", which led them to suspect their `agnes push` was broken. The warning is actually about the LLM-based `verification-detector` backlog (uploads themselves were arriving fine — confirmed by 23+3 JSONLs landed on the server while the warning was firing). Reword the warning to "verification-detector backlog" + add `last_processed` to the diagnose dict so operators don't have to grep logs to confirm.

## Test plan

- [x] `pytest tests/test_lib_hooks.py` — updated count + added `agnes push in SessionStart` assertion.
- [x] `pytest tests/test_setup_hooks_template.py` — updated.
- [x] `pytest tests/test_clean_install_integration.py` — updated.
- [x] `pytest tests/test_health_session_pipeline.py` — updated warning text + asserted `last_processed` field.
<!-- devin-review-badge-begin -->

---

<a href="https://app.devin.ai/review/keboola/agnes-the-ai-analyst/pull/220" target="_blank">
  <picture>
    <source media="(prefers-color-scheme: dark)" srcset="https://static.devin.ai/assets/gh-open-in-devin-review-dark.svg?v=1">
    <img src="https://static.devin.ai/assets/gh-open-in-devin-review-light.svg?v=1" alt="Open in Devin Review">
  </picture>
</a>
<!-- devin-review-badge-end -->
2026-05-07 17:41:22 +02:00

229 lines
9.5 KiB
Python

"""Tests for cli/lib/hooks.py:install_claude_hooks."""
import json
from pathlib import Path
from cli.lib.hooks import install_claude_hooks
def _read_settings(workspace: Path) -> dict:
return json.loads((workspace / ".claude" / "settings.json").read_text())
def _commands_for(cfg: dict, event: str) -> list[str]:
"""Flatten the per-event command list — each entry has a list of hooks,
each hook has a `command` field. We treat each entry as one command for
assertion purposes (matches the install_claude_hooks contract: one
entry per command)."""
return [
entry["hooks"][0]["command"]
for entry in cfg["hooks"].get(event, [])
if entry.get("hooks")
]
def test_install_creates_settings_file(tmp_path):
install_claude_hooks(tmp_path)
cfg = _read_settings(tmp_path)
starts = _commands_for(cfg, "SessionStart")
# SessionStart has three entries: (1) chained self-upgrade ; pull —
# self-upgrade runs first so a wire-protocol bump lands before pull
# tries to use the new CLI; (2) refresh-marketplace as a separate
# entry so a failure (e.g. fresh workspace with no clone) doesn't
# suppress the data pull above; (3) push as a self-heal for orphan
# session JSONLs from `claude -p` headless mode (where Claude Code
# does NOT fire SessionEnd) or abnormal exits.
assert len(starts) == 3
chain = next(
(c for c in starts if "agnes self-upgrade" in c and "agnes pull" in c),
None,
)
assert chain is not None, (
"Expected one SessionStart entry chaining self-upgrade and pull"
)
assert "agnes self-upgrade --quiet" in chain
assert "agnes pull --quiet" in chain
# The refresh-marketplace command is wrapped in `bash -c "..."` so the
# `2>/dev/null || true` shell syntax is interpreted on Windows, where
# Claude Code runs hook commands directly without invoking a shell.
refresh = next((c for c in starts if "agnes refresh-marketplace" in c), None)
assert refresh is not None
assert refresh.startswith("bash -c "), (
f"refresh-marketplace hook must be wrapped in bash -c for Windows; got: {refresh!r}"
)
# The push self-heal entry is also bash-c-wrapped for Windows parity.
push_start = next((c for c in starts if "agnes push" in c), None)
assert push_start is not None, (
"Expected SessionStart self-heal `agnes push` entry for orphan JSONLs"
)
assert push_start.startswith("bash -c "), (
f"push self-heal hook must be wrapped in bash -c for Windows; got: {push_start!r}"
)
ends = _commands_for(cfg, "SessionEnd")
assert len(ends) == 1
assert "agnes push --quiet" in ends[0]
def test_install_idempotent(tmp_path):
install_claude_hooks(tmp_path)
install_claude_hooks(tmp_path)
cfg = _read_settings(tmp_path)
# Three SessionStart entries (pull + refresh-marketplace + push self-heal),
# one SessionEnd entry (push). Re-install must NOT duplicate them.
assert len(cfg["hooks"]["SessionStart"]) == 3
assert len(cfg["hooks"]["SessionEnd"]) == 1
def test_install_replaces_old_da_sync_entries(tmp_path):
"""Hook from a pre-rewrite workspace gets replaced cleanly — legacy
`da sync` entries are removed, both new agnes hooks land in their place."""
settings_path = tmp_path / ".claude" / "settings.json"
settings_path.parent.mkdir(parents=True)
settings_path.write_text(json.dumps({
"hooks": {
"SessionStart": [{"hooks": [{"type": "command", "command": "da sync --quiet"}]}],
"SessionEnd": [{"hooks": [{"type": "command", "command": "da sync --upload-only --quiet"}]}],
}
}))
install_claude_hooks(tmp_path)
cfg = _read_settings(tmp_path)
starts = _commands_for(cfg, "SessionStart")
assert len(starts) == 3
assert any("agnes pull" in c for c in starts)
assert any("agnes refresh-marketplace" in c for c in starts)
assert any("agnes push" in c for c in starts)
# Legacy command must be gone from BOTH starts.
assert not any("da sync" in c for c in starts)
def test_install_replaces_prior_single_pull_entry(tmp_path):
"""Workspaces bootstrapped by a CLI version that only installed a
single SessionStart entry (`agnes pull`, no refresh-marketplace) must
upgrade to the three-entry layout on the next install — not end up
with four entries (one old + three new)."""
settings_path = tmp_path / ".claude" / "settings.json"
settings_path.parent.mkdir(parents=True)
settings_path.write_text(json.dumps({
"hooks": {
"SessionStart": [
{"hooks": [{"type": "command", "command": "agnes pull --quiet 2>/dev/null || true"}]},
],
}
}))
install_claude_hooks(tmp_path)
cfg = _read_settings(tmp_path)
starts = _commands_for(cfg, "SessionStart")
assert len(starts) == 3
assert any("agnes pull" in c for c in starts)
assert any("agnes refresh-marketplace" in c for c in starts)
assert any("agnes push" in c for c in starts)
def test_install_replaces_v0_43_chained_self_upgrade_pull_entry(tmp_path):
"""Workspaces bootstrapped on v0.43.0 had a single SessionStart entry
chaining `agnes self-upgrade; agnes pull` in one shell line. Upgrading
those workspaces to v0.44.0+ must collapse that entry and re-install
the new two-entry layout — not stack the v0.44 entries on top of the
v0.43 chained one (which would re-run self-upgrade twice on every
session and leave the old format around forever).
"""
settings_path = tmp_path / ".claude" / "settings.json"
settings_path.parent.mkdir(parents=True)
settings_path.write_text(json.dumps({
"hooks": {
"SessionStart": [
{"hooks": [{"type": "command", "command": (
"agnes self-upgrade --quiet 2>/dev/null || true; "
"agnes pull --quiet 2>/dev/null || true"
)}]},
],
"SessionEnd": [
{"hooks": [{"type": "command", "command": "agnes push --quiet 2>/dev/null || true"}]},
],
}
}))
install_claude_hooks(tmp_path)
cfg = _read_settings(tmp_path)
starts = _commands_for(cfg, "SessionStart")
# Exactly three entries — the v0.43 chained line was replaced, not stacked.
assert len(starts) == 3, starts
chain = next(
(c for c in starts if "agnes self-upgrade" in c and "agnes pull" in c),
None,
)
assert chain is not None
assert any("agnes refresh-marketplace" in c for c in starts)
assert any("agnes push" in c for c in starts)
# SessionEnd untouched (single push entry).
ends = _commands_for(cfg, "SessionEnd")
assert len(ends) == 1
assert "agnes push --quiet" in ends[0]
def test_install_preserves_third_party_hooks(tmp_path):
settings_path = tmp_path / ".claude" / "settings.json"
settings_path.parent.mkdir(parents=True)
settings_path.write_text(json.dumps({
"hooks": {
"SessionStart": [{"hooks": [{"type": "command", "command": "echo hi from another tool"}]}],
"PreToolUse": [{"hooks": [{"type": "command", "command": "echo pre"}]}],
}
}))
install_claude_hooks(tmp_path)
cfg = _read_settings(tmp_path)
starts = _commands_for(cfg, "SessionStart")
# Third-party entry stays + all three agnes entries get added.
assert len(starts) == 4
assert any("echo hi from another tool" in c for c in starts)
assert any("agnes pull" in c for c in starts)
assert any("agnes refresh-marketplace" in c for c in starts)
assert any("agnes push" in c for c in starts)
# Other event types untouched.
assert cfg["hooks"]["PreToolUse"][0]["hooks"][0]["command"] == "echo pre"
def test_install_handles_missing_settings_file(tmp_path):
install_claude_hooks(tmp_path)
assert (tmp_path / ".claude" / "settings.json").exists()
def test_install_handles_invalid_json(tmp_path, capsys):
settings_path = tmp_path / ".claude" / "settings.json"
settings_path.parent.mkdir(parents=True)
settings_path.write_text("not valid json {")
install_claude_hooks(tmp_path)
captured = capsys.readouterr()
assert "not valid JSON" in captured.err or "warning" in captured.err.lower()
def test_install_chains_self_upgrade_then_pull_in_one_entry(tmp_path):
install_claude_hooks(tmp_path)
cfg = _read_settings(tmp_path)
starts = _commands_for(cfg, "SessionStart")
# SessionStart has two entries: the chain (self-upgrade + pull) and
# the standalone refresh-marketplace. This test pins the chain
# invariant — order, both `|| true`-guarded — independent of the
# refresh-marketplace entry being present.
chain = next(
(c for c in starts if "agnes self-upgrade" in c and "agnes pull" in c),
None,
)
assert chain is not None, starts
assert "agnes self-upgrade --quiet" in chain
assert "agnes pull --quiet" in chain
# Order is encoded in the shell — self-upgrade must appear first
assert chain.index("agnes self-upgrade") < chain.index("agnes pull")
# Both segments carry || true so neither failure aborts the line
assert chain.count("|| true") >= 2
def test_install_idempotent_chained_entry(tmp_path):
install_claude_hooks(tmp_path)
install_claude_hooks(tmp_path)
cfg = _read_settings(tmp_path)
# Three SessionStart entries (chained self-upgrade+pull, refresh-
# marketplace, and the push self-heal) — re-install must not
# duplicate any of them.
assert len(cfg["hooks"]["SessionStart"]) == 3
assert len(cfg["hooks"]["SessionEnd"]) == 1