fix(hooks): always mine the active transcript as convos, additive to MEMPAL_DIR

README.md

@@ -149,6 +149,10 @@ system prompt:
 Two Claude Code hooks save periodically and before context compression:
 [mempalaceofficial.com/guide/hooks](https://mempalaceofficial.com/guide/hooks.html).
 
+For per-message recall on top of the file-level chunks the hooks produce,
+run `mempalace sweep <transcript-dir>` periodically — it stores one
+verbatim drawer per user/assistant message, idempotent and resume-safe.
+
 ---
 
 ## Requirements

hooks/README.md

@@ -67,7 +67,7 @@ Edit `mempal_save_hook.sh` to change:
 
 - **`SAVE_INTERVAL=15`** — How many human messages between saves. Lower = more frequent saves, higher = less interruption.
 - **`STATE_DIR`** — Where hook state is stored (defaults to `~/.mempalace/hook_state/`)
-- **`MEMPAL_DIR`** — Optional. Set to a conversations directory to auto-run `mempalace mine <dir>` on each save trigger. Leave blank (default) to let the AI handle saving via the block reason message.
+- **`MEMPAL_DIR`** — Optional **project directory** (code, notes, docs) to also mine on each save trigger, with `--mode projects`. The hook ALWAYS mines the active conversation transcript automatically with `--mode convos` — `MEMPAL_DIR` is purely additive, never an override. Leave blank if you don't want to ingest project files.
 - **`MEMPALACE_PYTHON`** — Optional env var. Python interpreter with mempalace + chromadb installed. Auto-detects: `MEMPALACE_PYTHON` env var → repo `venv/bin/python3` → system `python3`. Set this if your venv is in a non-standard location.
 
 ### mempalace CLI

hooks/mempal_precompact_hook.sh

@@ -41,17 +41,18 @@
 # to save everything. After the AI saves, compaction proceeds normally.
 #
 # === MEMPALACE CLI ===
-# This repo uses: mempalace mine <dir>
-# or:            mempalace mine <dir> --mode convos
-# Set MEMPAL_DIR below if you want the hook to auto-ingest before compaction.
-# Leave blank to rely on the AI's own save instructions.
+# The hook ALWAYS mines the active conversation transcript synchronously
+# before compaction (via `mempalace mine <transcript-dir> --mode convos`).
+# MEMPAL_DIR is an *additional*, optional target for project files — it
+# does not replace the conversation mine.
 
 STATE_DIR="$HOME/.mempalace/hook_state"
 mkdir -p "$STATE_DIR"
 
-# Optional: set to the directory you want auto-ingested before compaction.
-# Example: MEMPAL_DIR="$HOME/conversations"
-# Leave empty to skip auto-ingest (AI handles saving via the block reason).
+# Optional: project directory (code / notes / docs) to also mine before
+# compaction. Mined with `--mode projects`. The conversation transcript
+# is always mined regardless — this is purely additive.
+# Example: MEMPAL_DIR="$HOME/projects/my_app"
 MEMPAL_DIR=""
 
 # Resolve the Python interpreter. Same contract as mempal_save_hook.sh:
@@ -64,15 +65,57 @@ fi
 # Read JSON input from stdin
 INPUT=$(cat)
 
-SESSION_ID=$(echo "$INPUT" | "$MEMPAL_PYTHON_BIN" -c "import sys,json; print(json.load(sys.stdin).get('session_id','unknown'))" 2>/dev/null)
+# Parse session_id and transcript_path in one call. Sanitize both, then
+# read sanitized values from one-per-line stdout into shell variables —
+# avoids ``eval`` on generated code (#1231 review). Same contract as
+# mempal_save_hook.sh.
+mapfile -t _mempal_parsed < <(echo "$INPUT" | "$MEMPAL_PYTHON_BIN" -c "
+import sys, json, re
+data = json.load(sys.stdin)
+sid = data.get('session_id', 'unknown')
+tp = data.get('transcript_path', '')
+safe = lambda s: re.sub(r'[^a-zA-Z0-9_/.\-~]', '', str(s))
+print(safe(sid))
+print(safe(tp))
+" 2>/dev/null)
+SESSION_ID="${_mempal_parsed[0]:-unknown}"
+TRANSCRIPT_PATH="${_mempal_parsed[1]:-}"
+
+# Expand ~ in path
+TRANSCRIPT_PATH="${TRANSCRIPT_PATH/#\~/$HOME}"
+
+# Validate that TRANSCRIPT_PATH looks like a transcript file. Mirrors
+# mempalace.hooks_cli._validate_transcript_path so the shell hook
+# rejects the same shapes the Python hook rejects (#1231 review).
+is_valid_transcript_path() {
+    local path="$1"
+    [ -n "$path" ] || return 1
+    case "$path" in
+        *.json|*.jsonl) ;;
+        *) return 1 ;;
+    esac
+    case "/$path/" in
+        */../*) return 1 ;;
+    esac
+    return 0
+}
 
 echo "[$(date '+%H:%M:%S')] PRE-COMPACT triggered for session $SESSION_ID" >> "$STATE_DIR/hook.log"
 
-# Optional: run mempalace ingest synchronously so memories land before compaction
+# Run ingest synchronously so memories land before compaction. Two
+# independent targets — both run if both are set:
+#   1. TRANSCRIPT_PATH (from Claude Code) → parent dir, --mode convos
+#   2. MEMPAL_DIR → --mode projects
+if is_valid_transcript_path "$TRANSCRIPT_PATH" && [ -f "$TRANSCRIPT_PATH" ]; then
+    mempalace mine "$(dirname "$TRANSCRIPT_PATH")" --mode convos \
+        >> "$STATE_DIR/hook.log" 2>&1
+elif [ -n "$TRANSCRIPT_PATH" ]; then
+    echo "[$(date '+%H:%M:%S')] Skipping invalid transcript path: $TRANSCRIPT_PATH" \
+        >> "$STATE_DIR/hook.log"
+fi
 if [ -n "$MEMPAL_DIR" ] && [ -d "$MEMPAL_DIR" ]; then
-    SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-    REPO_DIR="$(dirname "$SCRIPT_DIR")"
-    mempalace mine "$MEMPAL_DIR" >> "$STATE_DIR/hook.log" 2>&1
+    mempalace mine "$MEMPAL_DIR" --mode projects \
+        >> "$STATE_DIR/hook.log" 2>&1
 fi
 
 # Silent: return empty JSON to not block. "decision": "allow" is invalid —

hooks/mempal_save_hook.sh

@@ -45,20 +45,21 @@
 # stop_hook_active=true so we let it through. No infinite loop.
 #
 # === MEMPALACE CLI ===
-# This repo uses: mempalace mine <dir>
-# or:            mempalace mine <dir> --mode convos
-# Set MEMPAL_DIR below if you want the hook to auto-ingest after blocking.
-# Leave blank to rely on the AI's own save instructions.
+# The hook ALWAYS mines the active conversation transcript automatically
+# (via `mempalace mine <transcript-dir> --mode convos`). MEMPAL_DIR is an
+# *additional*, optional target for project files — it does not replace
+# the conversation mine.
 #
 # === CONFIGURATION ===
 
 SAVE_INTERVAL=15  # Save every N human messages (adjust to taste)
 STATE_DIR="$HOME/.mempalace/hook_state"
 mkdir -p "$STATE_DIR"
 
-# Optional: set to the directory you want auto-ingested on each save trigger.
-# Example: MEMPAL_DIR="$HOME/conversations"
-# Leave empty to skip auto-ingest (AI handles saving via the block reason).
+# Optional: project directory (code / notes / docs) to also mine each
+# save trigger. Mined with `--mode projects`. The conversation transcript
+# is always mined regardless — this is purely additive.
+# Example: MEMPAL_DIR="$HOME/projects/my_app"
 MEMPAL_DIR=""
 
 # Resolve the Python interpreter the hook should use.
@@ -82,9 +83,11 @@ fi
 INPUT=$(cat)
 
 # Parse all fields in a single Python call (3x faster than separate invocations)
-# SECURITY: All values are sanitized before being interpolated into shell assignments.
-# stop_hook_active is coerced to a strict True/False to prevent command injection via eval.
-eval $(echo "$INPUT" | "$MEMPAL_PYTHON_BIN" -c "
+# without invoking ``eval`` on generated code: Python prints one sanitized
+# value per line, the shell reads them via ``mapfile`` and does plain
+# variable assignment — same data, smaller blast radius if the sanitizer
+# is ever bypassed (#1231 review).
+mapfile -t _mempal_parsed < <(echo "$INPUT" | "$MEMPAL_PYTHON_BIN" -c "
 import sys, json, re
 data = json.load(sys.stdin)
 sid = data.get('session_id', 'unknown')
@@ -94,14 +97,36 @@ tp = data.get('transcript_path', '')
 safe = lambda s: re.sub(r'[^a-zA-Z0-9_/.\-~]', '', str(s))
 # Coerce stop_hook_active to strict boolean string
 sha = 'True' if sha_raw is True or str(sha_raw).lower() in ('true', '1', 'yes') else 'False'
-print(f'SESSION_ID=\"{safe(sid)}\"')
-print(f'STOP_HOOK_ACTIVE=\"{sha}\"')
-print(f'TRANSCRIPT_PATH=\"{safe(tp)}\"')
+print(safe(sid))
+print(sha)
+print(safe(tp))
 " 2>/dev/null)
+SESSION_ID="${_mempal_parsed[0]:-unknown}"
+STOP_HOOK_ACTIVE="${_mempal_parsed[1]:-False}"
+TRANSCRIPT_PATH="${_mempal_parsed[2]:-}"
 
 # Expand ~ in path
 TRANSCRIPT_PATH="${TRANSCRIPT_PATH/#\~/$HOME}"
 
+# Validate that TRANSCRIPT_PATH looks like a transcript file:
+#   - non-empty
+#   - .jsonl or .json suffix
+#   - no traversal segments (.. components)
+# Mirrors mempalace.hooks_cli._validate_transcript_path so the shell hook
+# rejects the same shapes the Python hook rejects (#1231 review).
+is_valid_transcript_path() {
+    local path="$1"
+    [ -n "$path" ] || return 1
+    case "$path" in
+        *.json|*.jsonl) ;;
+        *) return 1 ;;
+    esac
+    case "/$path/" in
+        */../*) return 1 ;;
+    esac
+    return 0
+}
+
 # If we're already in a save cycle, let the AI stop normally
 # This is the infinite-loop prevention: block once → AI saves → tries to stop again → we let it through
 if [ "$STOP_HOOK_ACTIVE" = "True" ] || [ "$STOP_HOOK_ACTIVE" = "true" ]; then
@@ -157,19 +182,23 @@ if [ "$SINCE_LAST" -ge "$SAVE_INTERVAL" ] && [ "$EXCHANGE_COUNT" -gt 0 ]; then
 
     echo "[$(date '+%H:%M:%S')] TRIGGERING SAVE at exchange $EXCHANGE_COUNT" >> "$STATE_DIR/hook.log"
 
-    # Auto-mine the transcript. Two paths:
-    # 1. TRANSCRIPT_PATH (from Claude Code) — mine the directory it lives in
-    # 2. MEMPAL_DIR (user-configured) — mine that directory
-    # At least one should work. If neither is set, nothing mines.
-    MINE_DIR=""
-    if [ -n "$TRANSCRIPT_PATH" ] && [ -f "$TRANSCRIPT_PATH" ]; then
-        MINE_DIR="$(dirname "$TRANSCRIPT_PATH")"
+    # Auto-mine. Two independent targets — both run if both are set:
+    #   1. TRANSCRIPT_PATH (from Claude Code) → parent dir, --mode convos
+    #      (Claude Code session JSONL — must use the convo miner)
+    #   2. MEMPAL_DIR (user-configured project) → --mode projects
+    #      (code, notes, docs)
+    # MEMPAL_DIR is *additive*, not an override: a user with MEMPAL_DIR
+    # pointed at their project still gets the active conversation mined.
+    if is_valid_transcript_path "$TRANSCRIPT_PATH" && [ -f "$TRANSCRIPT_PATH" ]; then
+        mempalace mine "$(dirname "$TRANSCRIPT_PATH")" --mode convos \
+            >> "$STATE_DIR/hook.log" 2>&1 &
+    elif [ -n "$TRANSCRIPT_PATH" ]; then
+        echo "[$(date '+%H:%M:%S')] Skipping invalid transcript path: $TRANSCRIPT_PATH" \
+            >> "$STATE_DIR/hook.log"
     fi
     if [ -n "$MEMPAL_DIR" ] && [ -d "$MEMPAL_DIR" ]; then
-        MINE_DIR="$MEMPAL_DIR"
-    fi
-    if [ -n "$MINE_DIR" ]; then
-        mempalace mine "$MINE_DIR" >> "$STATE_DIR/hook.log" 2>&1 &
+        mempalace mine "$MEMPAL_DIR" --mode projects \
+            >> "$STATE_DIR/hook.log" 2>&1 &
     fi
 
     # MEMPAL_VERBOSE toggle:

mempalace/hooks_cli.py

@@ -197,16 +197,23 @@ def _output(data: dict):
     sys.stdout.buffer.flush()
 
 
-def _get_mine_dir(transcript_path: str = "") -> str:
-    """Determine directory to mine from MEMPAL_DIR or transcript path."""
+def _get_mine_targets() -> list[tuple[str, str]]:
+    """Return the list of ``(dir, mode)`` targets for auto-ingest.
+
+    MEMPAL_DIR (when set and resolvable) contributes a ``"projects"``
+    target. Transcript ingestion is handled separately by
+    ``_ingest_transcript`` — emitting it here too would double-mine the
+    same JSONL into a different wing on every hook fire (#1231 review).
+
+    An empty list means no MEMPAL_DIR ingest should run.
+    """
+    targets: list[tuple[str, str]] = []
     mempal_dir = os.environ.get("MEMPAL_DIR", "")
-    if mempal_dir and os.path.isdir(mempal_dir):
-        return mempal_dir
-    if transcript_path:
-        path = Path(transcript_path).expanduser()
-        if path.is_file():
-            return str(path.parent)
-    return ""
+    if mempal_dir:
+        resolved = Path(mempal_dir).expanduser().resolve()
+        if resolved.is_dir():
+            targets.append((str(resolved), "projects"))
+    return targets
 
 
 _MINE_PID_FILE = STATE_DIR / "mine.pid"
@@ -263,37 +270,58 @@ def _spawn_mine(cmd: list) -> None:
     _MINE_PID_FILE.write_text(str(proc.pid))
 
 
-def _maybe_auto_ingest(transcript_path: str = ""):
-    """Run mempalace mine in background if a mine directory is available."""
-    mine_dir = _get_mine_dir(transcript_path)
-    if not mine_dir:
+def _maybe_auto_ingest():
+    """Background-mine MEMPAL_DIR (project files) if set.
+
+    Transcript convos are ingested separately via ``_ingest_transcript``
+    in the hook handlers — this function does not handle them, to avoid
+    asymmetric interpreter handling and PID-file overwrite when both
+    targets fire from a single hook call (#1231 review).
+    """
+    targets = _get_mine_targets()
+    if not targets:
         return
     if _mine_already_running():
         _log("Skipping auto-ingest: mine already running")
         return
-    try:
-        _spawn_mine([sys.executable, "-m", "mempalace", "mine", mine_dir])
-    except OSError:
-        pass
+    for mine_dir, mode in targets:
+        try:
+            _spawn_mine([_mempalace_python(), "-m", "mempalace", "mine", mine_dir, "--mode", mode])
+        except OSError:
+            pass
+
 
+def _mine_sync():
+    """Synchronously mine MEMPAL_DIR (precompact path).
 
-def _mine_sync(transcript_path: str = ""):
-    """Run mempalace mine synchronously (for precompact -- data must land first)."""
-    mine_dir = _get_mine_dir(transcript_path)
-    if not mine_dir:
+    Transcript convos are ingested separately via ``_ingest_transcript``
+    in ``hook_precompact`` — keeping them out of this function avoids
+    timeout stacking against the harness 30s ceiling (#1231 review).
+    """
+    targets = _get_mine_targets()
+    if not targets:
         return
-    try:
-        STATE_DIR.mkdir(parents=True, exist_ok=True)
-        log_path = STATE_DIR / "hook.log"
-        with open(log_path, "a") as log_f:
-            subprocess.run(
-                [sys.executable, "-m", "mempalace", "mine", mine_dir],
-                stdout=log_f,
-                stderr=log_f,
-                timeout=60,
-            )
-    except (OSError, subprocess.TimeoutExpired):
-        pass
+    STATE_DIR.mkdir(parents=True, exist_ok=True)
+    log_path = STATE_DIR / "hook.log"
+    for mine_dir, mode in targets:
+        try:
+            with open(log_path, "a") as log_f:
+                subprocess.run(
+                    [
+                        _mempalace_python(),
+                        "-m",
+                        "mempalace",
+                        "mine",
+                        mine_dir,
+                        "--mode",
+                        mode,
+                    ],
+                    stdout=log_f,
+                    stderr=log_f,
+                    timeout=60,
+                )
+        except (OSError, subprocess.TimeoutExpired):
+            pass
 
 
 def _desktop_toast(body: str, title: str = "MemPalace"):
@@ -592,7 +620,7 @@ def hook_stop(data: dict, harness: str):
                     transcript_path, session_id, wing=project_wing, toast=toast
                 )
                 _ingest_transcript(transcript_path)
-            _maybe_auto_ingest(transcript_path)
+            _maybe_auto_ingest()
             # Only advance save marker after successful save
             count = result.get("count", 0)
             if count > 0:
@@ -622,7 +650,7 @@ def hook_stop(data: dict, harness: str):
                 pass
             if transcript_path:
                 _ingest_transcript(transcript_path)
-            _maybe_auto_ingest(transcript_path)
+            _maybe_auto_ingest()
             reason = STOP_BLOCK_REASON + f" Write diary entry to wing={project_wing}."
             _output({"decision": "block", "reason": reason})
     else:
@@ -655,8 +683,10 @@ def hook_precompact(data: dict, harness: str):
     if transcript_path:
         _ingest_transcript(transcript_path)
 
-    # Mine synchronously so data lands before compaction proceeds
-    _mine_sync(transcript_path)
+    # Mine MEMPAL_DIR synchronously so project data lands before
+    # compaction proceeds. Transcript convos were already kicked off
+    # above via _ingest_transcript.
+    _mine_sync()
 
     _output({})