- Add parenthetical hints to block reasons so AI knows what each tool
saves (session summary, quotes/decisions/code)
- Remove dead config file creation from test_stop_hook_disabled_by_config
- Add missing test for MEMPALACE_HOOKS_AUTO_SAVE=no env var
- Replace bare except: with except Exception: in shell scripts
Add a clean opt-out for auto-save hook blocking (closes#494).
- New `hooks.auto_save` config option (default: true) in
~/.mempalace/config.json and MEMPALACE_HOOKS_AUTO_SAVE env var
- When disabled, stop and precompact hooks pass through without blocking
- Shorten block reason text from 6-line instructions to single-line
prompts — reduces UI noise while keeping tool names explicit
- Both Python (hooks_cli.py) and standalone shell scripts respect the
toggle via config file or env var
Follow-up on c271e7b after the bot review and an adversarial pass.
- Replace `echo "$INPUT"` with `printf '%s' "$INPUT"` in both hooks
so payloads with leading `-n`/`-e`/`-E` or backslashes are not
eaten by echo flag parsing.
- Wrap the `last_python_err.log` and `last_input.log` writes in a
`( umask 077; ... )` subshell so the files are created at mode
0600 atomically. The existing `chmod 600` calls stay as
belt-and-suspenders.
- Refactor the `_run_hook` test helper: internal assert on
returncode with stderr surfaced in the failure message; new
`extra_env=` kwarg subsumes the ad-hoc `subprocess.run` in the
UTF-8 locale test.
- Promote the world-readable, bounded-overwrite, UTF-8, unicode and
literal-unknown tests to a shared `_BOTH_HOOKS` parametrize with
readable ids so the symmetry across both hooks is enforced.
- `test_sed_extraction_present` strips line comments before counting
`sed -n '` occurrences so a regression that swapped sed back to
mapfile while keeping the prose cannot false-pass.
- Rewrite the precompact hook header docblock: the previous
"ALWAYS blocks" wording was stale (the hook returns `{}` and
does not emit a `decision: block` payload to the Stop-hook
protocol; the "always run" guarantee comes from the synchronous
mine call).
- Apply ruff 0.4.x format to the new test file (matches CI pin
`pip install "ruff>=0.4.0,<0.5"`).
Tests: 1749 passed (was 21 cases in c271e7b's test file; now 26 after
parametrize promotions, +5 cases).
The legacy hook scripts used `mapfile -t` (introduced in #1231) to read
sanitized values from the inline Python JSON parser. On stock macOS
/bin/bash is GNU 3.2.57 (Apple GPLv3 freeze) and `mapfile` only landed
in bash 4.0, so the hook silently failed: every parsed value fell back
to its default, the log wrote "Session unknown: 0 exchanges", and zero
drawers were saved.
This commit replaces the array read with `sed -n 'Np'` line extraction,
which is POSIX and runs on /bin/bash 3.2 unmodified. It also adds a
defense-in-depth fail-loud guard: Python prints a `__MEMPAL_PARSE_OK__`
sentinel and the hook surfaces the raw input plus Python traceback to
0600-mode sibling files when the sentinel is missing, so the next silent
failure has a debuggable trail instead of an unsolved zero-drawer day.
Address Copilot review on #1231:
1. Stop double-mining the transcript on the Python side. ``_get_mine_targets``
now returns only the ``MEMPAL_DIR`` projects target — the convos target
for the transcript dir is dropped because ``_ingest_transcript`` already
handles it on every hook fire. The duplicate spawn was using
``sys.executable`` (vs ``_mempalace_python()``) and a different ``--wing``,
so each Stop/PreCompact event was writing the same transcript into two
wings under asymmetric interpreters and overwriting the single
``_MINE_PID_FILE`` lock.
2. ``_maybe_auto_ingest`` and ``_mine_sync`` now spawn via
``_mempalace_python()`` so the resolved interpreter matches the venv
that owns mempalace (matters under GUI-launched harnesses where
``sys.executable`` may resolve to a system Python without chromadb).
3. Replace ``eval $(...)`` in both shell hooks with a ``mapfile``-based
reader. Sanitized values are still emitted by the same Python parser,
but the shell now does plain variable assignment instead of executing
the parser's stdout — smaller blast radius if the sanitizer is ever
bypassed.
4. Mirror ``_validate_transcript_path`` in the shell hooks via a
``is_valid_transcript_path`` helper — extension + traversal-segment
rejection, parity with the Python validator. The convos mine in each
shell hook is now gated on the validator instead of bare ``-f``.
5. Tighten the ``..`` traversal test that previously exercised the
suffix gate by mistake (``../../etc/passwd`` lacks ``.json[l]``).
Use ``.jsonl`` paths with traversal segments to actually hit the
``..`` rejection branch.
6. README: add a one-liner pointing at ``mempalace sweep`` for users
who want per-message recall on top of the file-level chunks the
hooks produce. The sweeper was undiscoverable previously.
Tests: 1418 passed, 1 skipped (full suite minus benchmarks).
#1230 fixed --mode convos for the case where MEMPAL_DIR was unset, but
left two configurations broken:
- MEMPAL_DIR set to a project dir: convos never mined (MEMPAL_DIR
overrode the transcript path); only project files were ingested.
- MEMPAL_DIR set to a conversations dir per the old hooks/README: the
projects miner ran on JSONL — same wrong-miner behaviour.
The shell hooks (mempal_save_hook.sh, mempal_precompact_hook.sh) had
the same MEMPAL_DIR-overrides-transcript bug AND were missing --mode
on every spawned `mempalace mine` call.
Make the auto-ingest *additive*. _get_mine_dir → _get_mine_targets,
returning a list of (dir, mode) pairs:
- MEMPAL_DIR (when valid) contributes (dir, "projects")
- A valid transcript JSONL contributes (parent, "convos")
- Both can appear together; the hook spawns one ingest per target
Same change applied to the shell save and precompact hooks. Precompact
also gained transcript_path parsing so it can run the convos mine
synchronously before context is compressed. hooks/README.md updated to
describe MEMPAL_DIR as a project-files target, never a convos target.
The legacy hook scripts `hooks/mempal_save_hook.sh` and
`hooks/mempal_precompact_hook.sh` shell out to `python3` for JSON
parsing and transcript-message counting. On macOS GUI launches of
Claude Code — `open -a`, Spotlight, the dock — the harness inherits
`PATH` from launchd (`/usr/bin:/bin:/usr/sbin:/sbin`), which may not
contain a `python3` at all, or may contain only a system Python that
lacks what the hook needs. The hook then fails silently in the
background log where users never look.
`mempalace` auto-ingest itself is unaffected — #340 switched that
path to the `mempalace` CLI entry point, which pipx/uv install on a
stable global PATH.
This PR adds a `MEMPAL_PYTHON` environment variable that users can
set to point the hook at any Python 3 interpreter. Resolution order
applied at each `python3` invocation site inside the two hooks:
1. $MEMPAL_PYTHON (if set and executable)
2. $(command -v python3) on PATH
3. bare `python3` as a last resort
The interpreter does not need `mempalace` installed in it — only the
standard-library `json` and `sys` modules. The hook's `mempalace mine`
call runs via the CLI, independent of this override.
hooks/README.md documents the macOS GUI PATH issue and the
MEMPAL_PYTHON override. tests/test_hooks_shell.py adds 3 regression
tests (Linux/macOS only, POSIX bash):
- MEMPAL_PYTHON override wins over PATH (proved via a
marker-emitting shim that proxies to the real interpreter).
- Non-executable MEMPAL_PYTHON falls back to PATH rather than
crashing on permission denied.
- Unset MEMPAL_PYTHON resolves via PATH.
`hooks_cli.py` (the Python implementation invoked via
`mempalace hook run ...`) already uses `sys.executable` and is
therefore trivially correct — no changes needed there.
Supersedes abandoned branch `fix/hook-bugs`.
Co-Authored-By: MSL <232237854+milla-jovovich@users.noreply.github.com>
hooks/mempal_precompact_hook.sh and hooks/mempal_save_hook.sh used
python3 -m mempalace mine which fails when mempalace is installed via
pipx or uv. Switch to the mempalace CLI entry point which pipx/uv put
on PATH. Also removes the now-unused PYTHON variable from mempal_save_hook.sh.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Closes#872. The top-level decision field only recognizes "block".
To not block, return empty JSON {}. "allow" was silently ignored
by Claude Code, causing unpredictable behavior.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The save hook and precompact hook were telling the agent to write
diary entries, add drawers, and add KG triples IN THE CHAT WINDOW.
Every line written stays in conversation history and retransmits on
every subsequent turn — ~$1/session in wasted tokens.
Fix: hooks now say "saved in background, no action needed" and use
decision: allow instead of block. The agent continues working without
interruption. All filing happens via the background pipeline.
Also updated hooks README with:
- Known limitation: hooks require session restart after install
- Updated cost section: zero tokens, background-only
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Igor Lins e Silva
fatkobra
sha2fiddy
mvalentsev
Pim Messelink
MSL
Milla Jovovich