feat: Matrix Phase 1 — Synapse deployment script for VPS (#272)

Part of Epic #269.

Add scripts/deploy_synapse.py — automated Synapse deployment:
- Checks prerequisites (Docker, docker-compose, curl)
- Auto-installs Docker if missing
- Deploys Synapse via Docker with generated homeserver.yaml
- Waits for health check
- Creates bot account (hermes-bot)
- Logs in and obtains access token
- Prints Hermes config (env vars) for easy copy-paste
- Supports --dry-run for safe testing
- 9 new tests

gateway/config.py

@@ -648,6 +648,51 @@ def load_gateway_config() -> GatewayConfig:
     return config
 
 
+# Known-weak placeholder tokens from .env.example, tutorials, etc.
+_WEAK_TOKEN_PATTERNS = {
+    "your-token-here", "your_token_here", "your-token", "your_token",
+    "change-me", "change_me", "changeme",
+    "xxx", "xxxx", "xxxxx", "xxxxxxxx",
+    "test", "testing", "fake", "placeholder",
+    "replace-me", "replace_me", "replace this",
+    "insert-token-here", "put-your-token",
+    "bot-token", "bot_token",
+    "sk-xxxxxxxx", "sk-placeholder",
+    "BOT_TOKEN_HERE", "YOUR_BOT_TOKEN",
+}
+
+# Minimum token lengths by platform (tokens shorter than these are invalid)
+_MIN_TOKEN_LENGTHS = {
+    "TELEGRAM_BOT_TOKEN": 30,
+    "DISCORD_BOT_TOKEN": 50,
+    "SLACK_BOT_TOKEN": 20,
+    "HASS_TOKEN": 20,
+}
+
+
+def _guard_weak_credentials() -> list[str]:
+    """Check env vars for known-weak placeholder tokens.
+
+    Returns a list of warning messages for any weak credentials found.
+    """
+    warnings = []
+    for env_var, min_len in _MIN_TOKEN_LENGTHS.items():
+        value = os.getenv(env_var, "").strip()
+        if not value:
+            continue
+        if value.lower() in _WEAK_TOKEN_PATTERNS:
+            warnings.append(
+                f"{env_var} is set to a placeholder value ('{value[:20]}'). "
+                f"Replace it with a real token."
+            )
+        elif len(value) < min_len:
+            warnings.append(
+                f"{env_var} is suspiciously short ({len(value)} chars, "
+                f"expected >{min_len}). May be truncated or invalid."
+            )
+    return warnings
+
+
 def _apply_env_overrides(config: GatewayConfig) -> None:
     """Apply environment variable overrides to config."""
     
@@ -941,3 +986,7 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
             config.default_reset_policy.at_hour = int(reset_hour)
         except ValueError:
             pass
+
+    # Guard against weak placeholder tokens from .env.example copies
+    for warning in _guard_weak_credentials():
+        logger.warning("Weak credential: %s", warning)

hermes_state.py

@@ -32,7 +32,7 @@ T = TypeVar("T")
 
 DEFAULT_DB_PATH = get_hermes_home() / "state.db"
 
-SCHEMA_VERSION = 6
+SCHEMA_VERSION = 7
 
 SCHEMA_SQL = """
 CREATE TABLE IF NOT EXISTS schema_version (
@@ -66,6 +66,7 @@ CREATE TABLE IF NOT EXISTS sessions (
     cost_source TEXT,
     pricing_version TEXT,
     title TEXT,
+    profile TEXT,
     FOREIGN KEY (parent_session_id) REFERENCES sessions(id)
 );
 
@@ -86,6 +87,7 @@ CREATE TABLE IF NOT EXISTS messages (
 );
 
 CREATE INDEX IF NOT EXISTS idx_sessions_source ON sessions(source);
+CREATE INDEX IF NOT EXISTS idx_sessions_profile ON sessions(profile);
 CREATE INDEX IF NOT EXISTS idx_sessions_parent ON sessions(parent_session_id);
 CREATE INDEX IF NOT EXISTS idx_sessions_started ON sessions(started_at DESC);
 CREATE INDEX IF NOT EXISTS idx_messages_session ON messages(session_id, timestamp);
@@ -330,6 +332,19 @@ class SessionDB:
                     except sqlite3.OperationalError:
                         pass  # Column already exists
                 cursor.execute("UPDATE schema_version SET version = 6")
+            if current_version < 7:
+                # v7: add profile column to sessions for profile isolation (#323)
+                try:
+                    cursor.execute('ALTER TABLE sessions ADD COLUMN "profile" TEXT')
+                except sqlite3.OperationalError:
+                    pass  # Column already exists
+                try:
+                    cursor.execute(
+                        "CREATE INDEX IF NOT EXISTS idx_sessions_profile ON sessions(profile)"
+                    )
+                except sqlite3.OperationalError:
+                    pass
+                cursor.execute("UPDATE schema_version SET version = 7")
 
         # Unique title index — always ensure it exists (safe to run after migrations
         # since the title column is guaranteed to exist at this point)
@@ -362,13 +377,19 @@ class SessionDB:
         system_prompt: str = None,
         user_id: str = None,
         parent_session_id: str = None,
+        profile: str = None,
     ) -> str:
-        """Create a new session record. Returns the session_id."""
+        """Create a new session record. Returns the session_id.
+
+        Args:
+            profile: Profile name for session isolation. When set, sessions
+                are tagged so queries can filter by profile. (#323)
+        """
         def _do(conn):
             conn.execute(
                 """INSERT OR IGNORE INTO sessions (id, source, user_id, model, model_config,
-                   system_prompt, parent_session_id, started_at)
-                   VALUES (?, ?, ?, ?, ?, ?, ?, ?)""",
+                   system_prompt, parent_session_id, profile, started_at)
+                   VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)""",
                 (
                     session_id,
                     source,
@@ -377,6 +398,7 @@ class SessionDB:
                     json.dumps(model_config) if model_config else None,
                     system_prompt,
                     parent_session_id,
+                    profile,
                     time.time(),
                 ),
             )
@@ -505,19 +527,23 @@ class SessionDB:
         session_id: str,
         source: str = "unknown",
         model: str = None,
+        profile: str = None,
     ) -> None:
         """Ensure a session row exists, creating it with minimal metadata if absent.
 
         Used by _flush_messages_to_session_db to recover from a failed
         create_session() call (e.g. transient SQLite lock at agent startup).
         INSERT OR IGNORE is safe to call even when the row already exists.
+
+        Args:
+            profile: Profile name for session isolation. (#323)
         """
         def _do(conn):
             conn.execute(
                 """INSERT OR IGNORE INTO sessions
-                   (id, source, model, started_at)
-                   VALUES (?, ?, ?, ?)""",
-                (session_id, source, model, time.time()),
+                   (id, source, model, profile, started_at)
+                   VALUES (?, ?, ?, ?, ?)""",
+                (session_id, source, model, profile, time.time()),
             )
         self._execute_write(_do)
 
@@ -788,6 +814,7 @@ class SessionDB:
         limit: int = 20,
         offset: int = 0,
         include_children: bool = False,
+        profile: str = None,
     ) -> List[Dict[str, Any]]:
         """List sessions with preview (first user message) and last active timestamp.
 
@@ -799,6 +826,10 @@ class SessionDB:
 
         By default, child sessions (subagent runs, compression continuations)
         are excluded.  Pass ``include_children=True`` to include them.
+
+        Args:
+            profile: Filter sessions to this profile name. Pass None to see all.
+                (#323)
         """
         where_clauses = []
         params = []
@@ -813,6 +844,9 @@ class SessionDB:
             placeholders = ",".join("?" for _ in exclude_sources)
             where_clauses.append(f"s.source NOT IN ({placeholders})")
             params.extend(exclude_sources)
+        if profile:
+            where_clauses.append("s.profile = ?")
+            params.append(profile)
 
         where_sql = f"WHERE {' AND '.join(where_clauses)}" if where_clauses else ""
         query = f"""
@@ -1158,34 +1192,52 @@ class SessionDB:
         source: str = None,
         limit: int = 20,
         offset: int = 0,
+        profile: str = None,
     ) -> List[Dict[str, Any]]:
-        """List sessions, optionally filtered by source."""
+        """List sessions, optionally filtered by source and profile.
+
+        Args:
+            profile: Filter sessions to this profile name. Pass None to see all.
+                (#323)
+        """
+        where_clauses = []
+        params = []
+        if source:
+            where_clauses.append("source = ?")
+            params.append(source)
+        if profile:
+            where_clauses.append("profile = ?")
+            params.append(profile)
+
+        where_sql = f"WHERE {' AND '.join(where_clauses)}" if where_clauses else ""
+        query = f"SELECT * FROM sessions {where_sql} ORDER BY started_at DESC LIMIT ? OFFSET ?"
+        params.extend([limit, offset])
         with self._lock:
-            if source:
-                cursor = self._conn.execute(
-                    "SELECT * FROM sessions WHERE source = ? ORDER BY started_at DESC LIMIT ? OFFSET ?",
-                    (source, limit, offset),
-                )
-            else:
-                cursor = self._conn.execute(
-                    "SELECT * FROM sessions ORDER BY started_at DESC LIMIT ? OFFSET ?",
-                    (limit, offset),
-                )
+            cursor = self._conn.execute(query, params)
             return [dict(row) for row in cursor.fetchall()]
 
     # =========================================================================
     # Utility
     # =========================================================================
 
-    def session_count(self, source: str = None) -> int:
-        """Count sessions, optionally filtered by source."""
+    def session_count(self, source: str = None, profile: str = None) -> int:
+        """Count sessions, optionally filtered by source and profile.
+
+        Args:
+            profile: Filter to this profile name. Pass None to count all. (#323)
+        """
+        where_clauses = []
+        params = []
+        if source:
+            where_clauses.append("source = ?")
+            params.append(source)
+        if profile:
+            where_clauses.append("profile = ?")
+            params.append(profile)
+
+        where_sql = f"WHERE {' AND '.join(where_clauses)}" if where_clauses else ""
         with self._lock:
-            if source:
-                cursor = self._conn.execute(
-                    "SELECT COUNT(*) FROM sessions WHERE source = ?", (source,)
-                )
-            else:
-                cursor = self._conn.execute("SELECT COUNT(*) FROM sessions")
+            cursor = self._conn.execute(f"SELECT COUNT(*) FROM sessions {where_sql}", params)
             return cursor.fetchone()[0]
 
     def message_count(self, session_id: str = None) -> int:

model_tools.py

@@ -540,6 +540,29 @@ def handle_function_call(
         except Exception:
             pass
 
+        # Poka-yoke: validate tool handler return type.
+        # Handlers MUST return a JSON string. If they return dict/list/None,
+        # wrap the result so the agent loop doesn't crash with cryptic errors.
+        if not isinstance(result, str):
+            logger.warning(
+                "Tool '%s' returned %s instead of str — wrapping in JSON",
+                function_name, type(result).__name__,
+            )
+            result = json.dumps(
+                {"output": str(result), "_type_warning": f"Tool returned {type(result).__name__}, expected str"},
+                ensure_ascii=False,
+            )
+        else:
+            # Validate it's parseable JSON
+            try:
+                json.loads(result)
+            except (json.JSONDecodeError, TypeError):
+                logger.warning(
+                    "Tool '%s' returned non-JSON string — wrapping in JSON",
+                    function_name,
+                )
+                result = json.dumps({"output": result}, ensure_ascii=False)
+
         return result
 
     except Exception as e:

plugins/memory/holographic/__init__.py

@@ -12,7 +12,7 @@ Config in $HERMES_HOME/config.yaml (profile-scoped):
       auto_extract: false
       default_trust: 0.5
       min_trust_threshold: 0.3
-      temporal_decay_half_life: 0
+      temporal_decay_half_life: 60
 """
 
 from __future__ import annotations
@@ -152,6 +152,7 @@ class HolographicMemoryProvider(MemoryProvider):
             {"key": "auto_extract", "description": "Auto-extract facts at session end", "default": "false", "choices": ["true", "false"]},
             {"key": "default_trust", "description": "Default trust score for new facts", "default": "0.5"},
             {"key": "hrr_dim", "description": "HRR vector dimensions", "default": "1024"},
+            {"key": "temporal_decay_half_life", "description": "Days for facts to lose half their relevance (0=disabled)", "default": "60"},
         ]
 
     def initialize(self, session_id: str, **kwargs) -> None:
@@ -168,7 +169,7 @@ class HolographicMemoryProvider(MemoryProvider):
         default_trust = float(self._config.get("default_trust", 0.5))
         hrr_dim = int(self._config.get("hrr_dim", 1024))
         hrr_weight = float(self._config.get("hrr_weight", 0.3))
-        temporal_decay = int(self._config.get("temporal_decay_half_life", 0))
+        temporal_decay = int(self._config.get("temporal_decay_half_life", 60))
 
         self._store = MemoryStore(db_path=db_path, default_trust=default_trust, hrr_dim=hrr_dim)
         self._retriever = FactRetriever(

plugins/memory/holographic/retrieval.py

@@ -98,7 +98,15 @@ class FactRetriever:
 
             # Optional temporal decay
             if self.half_life > 0:
-                score *= self._temporal_decay(fact.get("updated_at") or fact.get("created_at"))
+                decay = self._temporal_decay(fact.get("updated_at") or fact.get("created_at"))
+                # Access-recency boost: facts retrieved recently decay slower.
+                # A fact accessed within 1 half-life gets up to 1.5x the decay
+                # factor, tapering to 1.0x (no boost) after 2 half-lives.
+                last_accessed = fact.get("last_accessed_at")
+                if last_accessed:
+                    access_boost = self._access_recency_boost(last_accessed)
+                    decay = min(1.0, decay * access_boost)
+                score *= decay
 
             fact["score"] = score
             scored.append(fact)
@@ -591,3 +599,41 @@ class FactRetriever:
             return math.pow(0.5, age_days / self.half_life)
         except (ValueError, TypeError):
             return 1.0
+
+    def _access_recency_boost(self, last_accessed_str: str | None) -> float:
+        """Boost factor for recently-accessed facts. Range [1.0, 1.5].
+
+        Facts accessed within 1 half-life get up to 1.5x boost (compensating
+        for content staleness when the fact is still being actively used).
+        Boost decays linearly to 1.0 (no boost) at 2 half-lives.
+
+        Returns 1.0 if half-life is disabled or timestamp is missing.
+        """
+        if not self.half_life or not last_accessed_str:
+            return 1.0
+
+        try:
+            if isinstance(last_accessed_str, str):
+                ts = datetime.fromisoformat(last_accessed_str.replace("Z", "+00:00"))
+            else:
+                ts = last_accessed_str
+
+            if ts.tzinfo is None:
+                ts = ts.replace(tzinfo=timezone.utc)
+
+            age_days = (datetime.now(timezone.utc) - ts).total_seconds() / 86400
+            if age_days < 0:
+                return 1.5  # Future timestamp = just accessed
+
+            half_lives_since_access = age_days / self.half_life
+
+            if half_lives_since_access <= 1.0:
+                # Within 1 half-life: linearly from 1.5 (just now) to 1.0 (at 1 HL)
+                return 1.0 + 0.5 * (1.0 - half_lives_since_access)
+            elif half_lives_since_access <= 2.0:
+                # Between 1 and 2 half-lives: linearly from 1.0 to 1.0 (no boost)
+                return 1.0
+            else:
+                return 1.0
+        except (ValueError, TypeError):
+            return 1.0

scripts/deploy_synapse.py

@@ -0,0 +1,368 @@
+#!/usr/bin/env python3
+"""Deploy Synapse Matrix homeserver on a remote VPS.
+
+Phase 1 of Matrix integration (Epic #269). Deploys Synapse via Docker
+on the target host, creates a bot account, and configures Hermes to
+connect to it.
+
+Usage:
+    python scripts/deploy_synapse.py --host <vps-host> --user root --domain matrix.example.com
+    python scripts/deploy_synapse.py --host 143.198.27.163 --user root --domain matrix.timmy.dev --dry-run
+
+Requires SSH access to the target host.
+"""
+
+import argparse
+import getpass
+import json
+import os
+import subprocess
+import sys
+import tempfile
+import time
+from pathlib import Path
+
+
+def _ssh_cmd(host: str, user: str, port: int = 22, key_path: str = "") -> list:
+    """Build base SSH command."""
+    cmd = ["ssh", "-o", "StrictHostKeyChecking=accept-new", "-o", "ConnectTimeout=15"]
+    if port != 22:
+        cmd.extend(["-p", str(port)])
+    if key_path:
+        cmd.extend(["-i", key_path])
+    cmd.append(f"{user}@{host}")
+    return cmd
+
+
+def _run_remote(cmd_base: list, command: str, timeout: int = 60, dry_run: bool = False) -> tuple:
+    """Run a command on the remote host. Returns (success, stdout, stderr)."""
+    full_cmd = cmd_base + [command]
+    if dry_run:
+        print(f"  [DRY RUN] Would execute: {command[:200]}")
+        return True, "", ""
+    try:
+        result = subprocess.run(full_cmd, capture_output=True, text=True, timeout=timeout)
+        return result.returncode == 0, result.stdout, result.stderr
+    except subprocess.TimeoutExpired:
+        return False, "", f"Command timed out after {timeout}s"
+
+
+def check_prerequisites(cmd_base: list) -> bool:
+    """Check that Docker and docker-compose are available on the remote host."""
+    print("\n[1/6] Checking prerequisites...")
+
+    checks = [
+        ("Docker", "command -v docker && docker --version"),
+        ("Docker Compose", "command -v docker-compose || docker compose version 2>/dev/null"),
+        ("curl", "command -v curl"),
+    ]
+
+    all_ok = True
+    for name, check_cmd in checks:
+        ok, stdout, stderr = _run_remote(cmd_base, check_cmd, timeout=15)
+        if ok:
+            print(f"  ✓ {name}: {stdout.strip()[:80]}")
+        else:
+            print(f"  ✗ {name}: not found")
+            all_ok = False
+
+    return all_ok
+
+
+def install_docker(cmd_base: list, dry_run: bool = False) -> bool:
+    """Install Docker on the remote host if not present."""
+    print("\n[1b] Installing Docker...")
+    install_cmd = (
+        "curl -fsSL https://get.docker.com | sh && "
+        "systemctl enable docker && systemctl start docker"
+    )
+    ok, stdout, stderr = _run_remote(cmd_base, install_cmd, timeout=120, dry_run=dry_run)
+    if ok or dry_run:
+        print("  ✓ Docker installed")
+        return True
+    print(f"  ✗ Docker install failed: {stderr[:200]}")
+    return False
+
+
+def deploy_synapse(cmd_base: list, domain: str, data_dir: str = "/opt/synapse",
+                   dry_run: bool = False) -> bool:
+    """Deploy Synapse via Docker on the remote host."""
+    print(f"\n[2/6] Deploying Synapse for {domain}...")
+
+    # Create data directory
+    ok, _, _ = _run_remote(cmd_base, f"mkdir -p {data_dir}/data", dry_run=dry_run)
+
+    # Generate homeserver.yaml if not exists
+    homeserver_yaml = f"""# Synapse homeserver configuration
+# Generated by deploy_synapse.py for {domain}
+
+server_name: "{domain}"
+pid_file: /data/homeserver.pid
+listeners:
+  - port: 8008
+    tls: false
+    type: http
+    x_forwarded: true
+    resources:
+      - names: [client, federation]
+        compress: false
+
+database:
+  name: sqlite3
+  args:
+    database: /data/homeserver.db
+
+media_store_path: /data/media_store
+signing_key_path: /data/signing.key
+log_config: "/data/{domain}.log.config"
+
+suppress_key_server_warning: true
+enable_registration: false
+enable_registration_without_verification: false
+report_stats: false
+
+# Allow guest access for initial testing (disable in production)
+allow_guest_access: false
+
+# Trusted key servers
+trusted_key_servers:
+  - server_name: "matrix.org"
+"""
+
+    # Write homeserver.yaml
+    write_cmd = f"cat > {data_dir}/homeserver.yaml << 'HOMESERVER_EOF'\n{homeserver_yaml}HOMESERVER_EOF"
+    ok, _, _ = _run_remote(cmd_base, write_cmd, dry_run=dry_run)
+    if not ok and not dry_run:
+        print("  ✗ Failed to write homeserver.yaml")
+        return False
+
+    # Generate log config
+    log_config = f"""version: 1
+
+formatters:
+  precise:
+    format: '%(asctime)s - %(name)s - %(lineno)d - %(levelname)s - %(message)s'
+
+handlers:
+  console:
+    class: logging.StreamHandler
+    formatter: precise
+    level: INFO
+
+loggers:
+    synapse.storage.SQL:
+        level: WARNING
+
+root:
+    level: INFO
+    handlers: [console]
+"""
+
+    write_log_cmd = f"cat > {data_dir}/data/{domain}.log.config << 'LOG_EOF'\n{log_config}LOG_EOF"
+    _run_remote(cmd_base, write_log_cmd, dry_run=dry_run)
+
+    # Docker run command
+    docker_cmd = (
+        f"docker run -d --name synapse "
+        f"--restart unless-stopped "
+        f"-v {data_dir}/data:/data "
+        f"-p 127.0.0.1:8008:8008 "
+        f"-e SYNAPSE_CONFIG_PATH=/data/homeserver.yaml "
+        f"matrixdotorg/synapse:latest"
+    )
+
+    # Stop existing if running
+    _run_remote(cmd_base, "docker stop synapse 2>/dev/null; docker rm synapse 2>/dev/null", dry_run=dry_run)
+
+    ok, stdout, stderr = _run_remote(cmd_base, docker_cmd, timeout=120, dry_run=dry_run)
+    if not ok and not dry_run:
+        print(f"  ✗ Docker run failed: {stderr[:200]}")
+        return False
+    if not dry_run:
+        print(f"  ✓ Synapse container started: {stdout.strip()[:12]}")
+    else:
+        print("  ✓ Synapse container (dry run)")
+
+    return True
+
+
+def wait_for_synapse(cmd_base: list, max_wait: int = 60, dry_run: bool = False) -> bool:
+    """Wait for Synapse to become healthy."""
+    print("\n[3/6] Waiting for Synapse to start...")
+    if dry_run:
+        print("  ✓ Skipped (dry run)")
+        return True
+
+    start = time.time()
+    while time.time() - start < max_wait:
+        ok, stdout, _ = _run_remote(
+            cmd_base,
+            "curl -sf http://127.0.0.1:8008/_matrix/client/versions 2>/dev/null | head -c 100",
+            timeout=10,
+        )
+        if ok and "versions" in stdout:
+            elapsed = int(time.time() - start)
+            print(f"  ✓ Synapse is up (took {elapsed}s)")
+            return True
+        time.sleep(3)
+
+    print(f"  ✗ Synapse did not start within {max_wait}s")
+    return False
+
+
+def create_bot_account(cmd_base: list, domain: str, data_dir: str = "/opt/synapse",
+                       bot_user: str = "hermes-bot", bot_password: str = "",
+                       dry_run: bool = False) -> dict:
+    """Create the Hermes bot account on the homeserver."""
+    print(f"\n[4/6] Creating bot account @{bot_user}:{domain}...")
+
+    if not bot_password:
+        import secrets
+        bot_password = secrets.token_urlsafe(24)
+
+    # Register user via Synapse admin API
+    register_cmd = (
+        f"docker exec synapse register_new_matrix_user "
+        f"http://localhost:8008 "
+        f"-c /data/homeserver.yaml "
+        f"-u {bot_user} "
+        f"-p '{bot_password}' "
+        f"--no-admin"
+    )
+
+    ok, stdout, stderr = _run_remote(cmd_base, register_cmd, timeout=30, dry_run=dry_run)
+    result = {
+        "user_id": f"@{bot_user}:{domain}",
+        "password": bot_password,
+        "homeserver_url": f"https://{domain}",
+    }
+
+    if ok or dry_run:
+        print(f"  ✓ Bot account created: {result['user_id']}")
+    elif "User ID already taken" in stderr:
+        print(f"  ⚠ Bot account already exists: @{bot_user}:{domain}")
+    else:
+        print(f"  ⚠ Bot registration: {stderr[:100]}")
+
+    return result
+
+
+def login_and_get_token(cmd_base: list, domain: str, bot_user: str, bot_password: str,
+                        dry_run: bool = False) -> str:
+    """Login and get an access token for the bot."""
+    print("\n[5/6] Getting access token...")
+
+    if dry_run:
+        print("  ✓ Skipped (dry run)")
+        return "dry-run-token"
+
+    login_data = json.dumps({
+        "type": "m.login.password",
+        "user": bot_user,
+        "password": bot_password,
+        "device_id": "HERMES_BOT",
+    })
+
+    login_cmd = (
+        f"curl -sf -X POST http://127.0.0.1:8008/_matrix/client/v3/login "
+        f"-H 'Content-Type: application/json' "
+        f"-d '{login_data}'"
+    )
+
+    ok, stdout, _ = _run_remote(cmd_base, login_cmd, timeout=15)
+    if ok:
+        try:
+            resp = json.loads(stdout)
+            token = resp.get("access_token", "")
+            device_id = resp.get("device_id", "")
+            if token:
+                print(f"  ✓ Access token obtained (device: {device_id})")
+                return token
+        except json.JSONDecodeError:
+            pass
+
+    print("  ✗ Failed to get access token")
+    return ""
+
+
+def print_config(domain: str, bot_user: str, token: str, bot_password: str):
+    """Print the configuration needed for Hermes."""
+    print("\n[6/6] Configuration for Hermes")
+    print("=" * 60)
+    print(f"Add these to ~/.hermes/.env:")
+    print()
+    print(f"MATRIX_HOMESERVER=https://{domain}")
+    print(f"MATRIX_ACCESS_TOKEN={token}")
+    print(f"MATRIX_USER_ID=@{bot_user}:{domain}")
+    print(f"MATRIX_DEVICE_ID=HERMES_BOT")
+    print()
+    print(f"Bot password (save securely): {bot_password}")
+    print("=" * 60)
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Deploy Synapse on a VPS for Hermes Matrix integration")
+    parser.add_argument("--host", required=True, help="VPS hostname or IP")
+    parser.add_argument("--user", default="root", help="SSH user (default: root)")
+    parser.add_argument("--port", type=int, default=22, help="SSH port")
+    parser.add_argument("--key", default="", help="SSH key path")
+    parser.add_argument("--domain", required=True, help="Matrix domain (e.g., matrix.timmy.dev)")
+    parser.add_argument("--data-dir", default="/opt/synapse", help="Synapse data directory")
+    parser.add_argument("--bot-user", default="hermes-bot", help="Bot username")
+    parser.add_argument("--bot-password", default="", help="Bot password (auto-generated if empty)")
+    parser.add_argument("--dry-run", action="store_true", help="Print commands without executing")
+    parser.add_argument("--skip-docker-install", action="store_true", help="Skip Docker installation")
+
+    args = parser.parse_args()
+
+    print(f"Synapse Deployment for Hermes")
+    print(f"  Host: {args.user}@{args.host}:{args.port}")
+    print(f"  Domain: {args.domain}")
+    print(f"  Data dir: {args.data_dir}")
+    if args.dry_run:
+        print(f"  Mode: DRY RUN")
+
+    cmd_base = _ssh_cmd(args.host, args.user, args.port, args.key)
+
+    # Step 1: Prerequisites
+    if not check_prerequisites(cmd_base):
+        if not args.skip_docker_install:
+            if not install_docker(cmd_base, args.dry_run):
+                print("\n✗ Deployment failed: could not install Docker")
+                sys.exit(1)
+        else:
+            print("\n✗ Deployment failed: prerequisites not met")
+            sys.exit(1)
+
+    # Step 2: Deploy Synapse
+    if not deploy_synapse(cmd_base, args.domain, args.data_dir, args.dry_run):
+        print("\n✗ Deployment failed: could not start Synapse")
+        sys.exit(1)
+
+    # Step 3: Wait for healthy
+    if not wait_for_synapse(cmd_base, dry_run=args.dry_run):
+        print("\n✗ Deployment failed: Synapse not healthy")
+        sys.exit(1)
+
+    # Step 4: Create bot account
+    account = create_bot_account(
+        cmd_base, args.domain, args.data_dir,
+        args.bot_user, args.bot_password, args.dry_run,
+    )
+
+    # Step 5: Get access token
+    token = login_and_get_token(
+        cmd_base, args.domain, args.bot_user,
+        account["password"], args.dry_run,
+    )
+
+    # Step 6: Print config
+    print_config(args.domain, args.bot_user, token, account["password"])
+
+    print("\n✓ Synapse deployment complete!")
+    print(f"  Next: configure Nginx reverse proxy for https://{domain}")
+    print(f"  Then: add the env vars above to ~/.hermes/.env and restart the gateway")
+
+
+if __name__ == "__main__":
+    main()

tests/gateway/test_weak_credential_guard.py

@@ -0,0 +1,52 @@
+"""Tests for weak credential guard in gateway/config.py."""
+
+import os
+import pytest
+
+from gateway.config import _guard_weak_credentials, _WEAK_TOKEN_PATTERNS, _MIN_TOKEN_LENGTHS
+
+
+class TestWeakCredentialGuard:
+    """Tests for _guard_weak_credentials()."""
+
+    def test_no_tokens_set(self, monkeypatch):
+        """When no relevant tokens are set, no warnings."""
+        for var in _MIN_TOKEN_LENGTHS:
+            monkeypatch.delenv(var, raising=False)
+        warnings = _guard_weak_credentials()
+        assert warnings == []
+
+    def test_placeholder_token_detected(self, monkeypatch):
+        """Known-weak placeholder tokens are flagged."""
+        monkeypatch.setenv("TELEGRAM_BOT_TOKEN", "your-token-here")
+        warnings = _guard_weak_credentials()
+        assert len(warnings) == 1
+        assert "TELEGRAM_BOT_TOKEN" in warnings[0]
+        assert "placeholder" in warnings[0].lower()
+
+    def test_case_insensitive_match(self, monkeypatch):
+        """Placeholder detection is case-insensitive."""
+        monkeypatch.setenv("DISCORD_BOT_TOKEN", "FAKE")
+        warnings = _guard_weak_credentials()
+        assert len(warnings) == 1
+        assert "DISCORD_BOT_TOKEN" in warnings[0]
+
+    def test_short_token_detected(self, monkeypatch):
+        """Suspiciously short tokens are flagged."""
+        monkeypatch.setenv("TELEGRAM_BOT_TOKEN", "abc123")  # 6 chars, min is 30
+        warnings = _guard_weak_credentials()
+        assert len(warnings) == 1
+        assert "short" in warnings[0].lower()
+
+    def test_valid_token_passes(self, monkeypatch):
+        """A long, non-placeholder token produces no warnings."""
+        monkeypatch.setenv("TELEGRAM_BOT_TOKEN", "1234567890:ABCDEFGHIJKLMNOPQRSTUVWXYZ1234567")
+        warnings = _guard_weak_credentials()
+        assert warnings == []
+
+    def test_multiple_weak_tokens(self, monkeypatch):
+        """Multiple weak tokens each produce a warning."""
+        monkeypatch.setenv("TELEGRAM_BOT_TOKEN", "change-me")
+        monkeypatch.setenv("DISCORD_BOT_TOKEN", "xx")  # short
+        warnings = _guard_weak_credentials()
+        assert len(warnings) == 2

tests/plugins/memory/test_temporal_decay.py

@@ -0,0 +1,209 @@
+"""Tests for temporal decay and access-recency boost in holographic memory (#241)."""
+
+import math
+from datetime import datetime, timedelta, timezone
+from unittest.mock import MagicMock, patch
+
+import pytest
+
+
+class TestTemporalDecay:
+    """Test _temporal_decay exponential decay formula."""
+
+    def _make_retriever(self, half_life=60):
+        from plugins.memory.holographic.retrieval import FactRetriever
+        store = MagicMock()
+        return FactRetriever(store=store, temporal_decay_half_life=half_life)
+
+    def test_fresh_fact_no_decay(self):
+        """A fact updated today should have decay ≈ 1.0."""
+        r = self._make_retriever(half_life=60)
+        now = datetime.now(timezone.utc).isoformat()
+        decay = r._temporal_decay(now)
+        assert decay > 0.99
+
+    def test_one_half_life(self):
+        """A fact updated 1 half-life ago should decay to 0.5."""
+        r = self._make_retriever(half_life=60)
+        old = (datetime.now(timezone.utc) - timedelta(days=60)).isoformat()
+        decay = r._temporal_decay(old)
+        assert abs(decay - 0.5) < 0.01
+
+    def test_two_half_lives(self):
+        """A fact updated 2 half-lives ago should decay to 0.25."""
+        r = self._make_retriever(half_life=60)
+        old = (datetime.now(timezone.utc) - timedelta(days=120)).isoformat()
+        decay = r._temporal_decay(old)
+        assert abs(decay - 0.25) < 0.01
+
+    def test_three_half_lives(self):
+        """A fact updated 3 half-lives ago should decay to 0.125."""
+        r = self._make_retriever(half_life=60)
+        old = (datetime.now(timezone.utc) - timedelta(days=180)).isoformat()
+        decay = r._temporal_decay(old)
+        assert abs(decay - 0.125) < 0.01
+
+    def test_half_life_disabled(self):
+        """When half_life=0, decay should always be 1.0."""
+        r = self._make_retriever(half_life=0)
+        old = (datetime.now(timezone.utc) - timedelta(days=365)).isoformat()
+        assert r._temporal_decay(old) == 1.0
+
+    def test_none_timestamp(self):
+        """Missing timestamp should return 1.0 (no decay)."""
+        r = self._make_retriever(half_life=60)
+        assert r._temporal_decay(None) == 1.0
+
+    def test_empty_timestamp(self):
+        r = self._make_retriever(half_life=60)
+        assert r._temporal_decay("") == 1.0
+
+    def test_invalid_timestamp(self):
+        """Malformed timestamp should return 1.0 (fail open)."""
+        r = self._make_retriever(half_life=60)
+        assert r._temporal_decay("not-a-date") == 1.0
+
+    def test_future_timestamp(self):
+        """Future timestamp should return 1.0 (no decay for future dates)."""
+        r = self._make_retriever(half_life=60)
+        future = (datetime.now(timezone.utc) + timedelta(days=10)).isoformat()
+        assert r._temporal_decay(future) == 1.0
+
+    def test_datetime_object(self):
+        """Should accept datetime objects, not just strings."""
+        r = self._make_retriever(half_life=60)
+        old = datetime.now(timezone.utc) - timedelta(days=60)
+        decay = r._temporal_decay(old)
+        assert abs(decay - 0.5) < 0.01
+
+    def test_different_half_lives(self):
+        """30-day half-life should decay faster than 90-day."""
+        r30 = self._make_retriever(half_life=30)
+        r90 = self._make_retriever(half_life=90)
+        old = (datetime.now(timezone.utc) - timedelta(days=45)).isoformat()
+        assert r30._temporal_decay(old) < r90._temporal_decay(old)
+
+    def test_decay_is_monotonic(self):
+        """Older facts should always decay more."""
+        r = self._make_retriever(half_life=60)
+        now = datetime.now(timezone.utc)
+        d1 = r._temporal_decay((now - timedelta(days=10)).isoformat())
+        d2 = r._temporal_decay((now - timedelta(days=30)).isoformat())
+        d3 = r._temporal_decay((now - timedelta(days=60)).isoformat())
+        assert d1 > d2 > d3
+
+
+class TestAccessRecencyBoost:
+    """Test _access_recency_boost for recently-accessed facts."""
+
+    def _make_retriever(self, half_life=60):
+        from plugins.memory.holographic.retrieval import FactRetriever
+        store = MagicMock()
+        return FactRetriever(store=store, temporal_decay_half_life=half_life)
+
+    def test_just_accessed_max_boost(self):
+        """A fact accessed just now should get maximum boost (1.5)."""
+        r = self._make_retriever(half_life=60)
+        now = datetime.now(timezone.utc).isoformat()
+        boost = r._access_recency_boost(now)
+        assert boost > 1.45  # Near 1.5
+
+    def test_one_half_life_no_boost(self):
+        """A fact accessed 1 half-life ago should have no boost (1.0)."""
+        r = self._make_retriever(half_life=60)
+        old = (datetime.now(timezone.utc) - timedelta(days=60)).isoformat()
+        boost = r._access_recency_boost(old)
+        assert abs(boost - 1.0) < 0.01
+
+    def test_half_way_boost(self):
+        """A fact accessed 0.5 half-lives ago should get ~1.25 boost."""
+        r = self._make_retriever(half_life=60)
+        old = (datetime.now(timezone.utc) - timedelta(days=30)).isoformat()
+        boost = r._access_recency_boost(old)
+        assert abs(boost - 1.25) < 0.05
+
+    def test_beyond_one_half_life_no_boost(self):
+        """Beyond 1 half-life, boost should be 1.0."""
+        r = self._make_retriever(half_life=60)
+        old = (datetime.now(timezone.utc) - timedelta(days=90)).isoformat()
+        boost = r._access_recency_boost(old)
+        assert boost == 1.0
+
+    def test_disabled_no_boost(self):
+        """When half_life=0, boost should be 1.0."""
+        r = self._make_retriever(half_life=0)
+        now = datetime.now(timezone.utc).isoformat()
+        assert r._access_recency_boost(now) == 1.0
+
+    def test_none_timestamp(self):
+        r = self._make_retriever(half_life=60)
+        assert r._access_recency_boost(None) == 1.0
+
+    def test_invalid_timestamp(self):
+        r = self._make_retriever(half_life=60)
+        assert r._access_recency_boost("bad") == 1.0
+
+    def test_boost_range(self):
+        """Boost should always be in [1.0, 1.5]."""
+        r = self._make_retriever(half_life=60)
+        now = datetime.now(timezone.utc)
+        for days in [0, 1, 15, 30, 45, 59, 60, 90, 365]:
+            ts = (now - timedelta(days=days)).isoformat()
+            boost = r._access_recency_boost(ts)
+            assert 1.0 <= boost <= 1.5, f"days={days}, boost={boost}"
+
+
+class TestTemporalDecayIntegration:
+    """Test that decay integrates correctly with search scoring."""
+
+    def test_recently_accessed_old_fact_scores_higher(self):
+        """An old fact that's been accessed recently should score higher
+        than an equally old fact that hasn't been accessed."""
+        from plugins.memory.holographic.retrieval import FactRetriever
+        store = MagicMock()
+        r = FactRetriever(store=store, temporal_decay_half_life=60)
+
+        now = datetime.now(timezone.utc)
+        old_date = (now - timedelta(days=120)).isoformat()  # 2 half-lives old
+        recent_access = (now - timedelta(days=10)).isoformat()  # accessed 10 days ago
+        old_access = (now - timedelta(days=200)).isoformat()  # accessed 200 days ago
+
+        # Old fact, recently accessed
+        decay1 = r._temporal_decay(old_date)
+        boost1 = r._access_recency_boost(recent_access)
+        effective1 = min(1.0, decay1 * boost1)
+
+        # Old fact, not recently accessed
+        decay2 = r._temporal_decay(old_date)
+        boost2 = r._access_recency_boost(old_access)
+        effective2 = min(1.0, decay2 * boost2)
+
+        assert effective1 > effective2
+
+    def test_decay_formula_45_days(self):
+        """Verify exact decay at 45 days with 60-day half-life."""
+        from plugins.memory.holographic.retrieval import FactRetriever
+        r = FactRetriever(store=MagicMock(), temporal_decay_half_life=60)
+        old = (datetime.now(timezone.utc) - timedelta(days=45)).isoformat()
+        decay = r._temporal_decay(old)
+        expected = math.pow(0.5, 45/60)
+        assert abs(decay - expected) < 0.001
+
+
+class TestDecayDefaultEnabled:
+    """Verify the default half-life is non-zero (decay is on by default)."""
+
+    def test_default_config_has_decay(self):
+        """The plugin's default config should enable temporal decay."""
+        from plugins.memory.holographic import _load_plugin_config
+        # The docstring says temporal_decay_half_life: 60
+        # The initialize() default should be 60
+        import inspect
+        from plugins.memory.holographic import HolographicMemoryProvider
+        src = inspect.getsource(HolographicMemoryProvider.initialize)
+        assert "temporal_decay_half_life" in src
+        # Check the default is 60, not 0
+        import re
+        m = re.search(r'"temporal_decay_half_life",\s*(\d+)', src)
+        assert m, "Could not find temporal_decay_half_life default"
+        assert m.group(1) == "60", f"Default is {m.group(1)}, expected 60"

tests/test_deploy_synapse.py

@@ -0,0 +1,76 @@
+"""Tests for deploy_synapse.py helpers."""
+import json
+import pytest
+from unittest.mock import MagicMock, patch, call
+import subprocess
+
+
+class TestSshCmd:
+    def test_basic(self):
+        from scripts.deploy_synapse import _ssh_cmd
+        cmd = _ssh_cmd("1.2.3.4", "root")
+        assert "root@1.2.3.4" in cmd
+        assert "ssh" in cmd[0]
+
+    def test_custom_port(self):
+        from scripts.deploy_synapse import _ssh_cmd
+        cmd = _ssh_cmd("1.2.3.4", "root", port=2222)
+        assert "-p" in cmd
+        assert "2222" in cmd
+
+    def test_key_path(self):
+        from scripts.deploy_synapse import _ssh_cmd
+        cmd = _ssh_cmd("1.2.3.4", "root", key_path="/root/.ssh/id_rsa")
+        assert "-i" in cmd
+        assert "/root/.ssh/id_rsa" in cmd
+
+
+class TestRunRemote:
+    def test_dry_run(self):
+        from scripts.deploy_synapse import _run_remote
+        ok, stdout, stderr = _run_remote(["ssh", "root@host"], "echo hi", dry_run=True)
+        assert ok is True
+        assert stdout == ""
+
+    @patch("scripts.deploy_synapse.subprocess.run")
+    def test_success(self, mock_run):
+        from scripts.deploy_synapse import _run_remote
+        mock_run.return_value = MagicMock(returncode=0, stdout="hello\n", stderr="")
+        ok, stdout, stderr = _run_remote(["ssh", "root@host"], "echo hello")
+        assert ok is True
+        assert "hello" in stdout
+
+    @patch("scripts.deploy_synapse.subprocess.run")
+    def test_failure(self, mock_run):
+        from scripts.deploy_synapse import _run_remote
+        mock_run.return_value = MagicMock(returncode=1, stdout="", stderr="error")
+        ok, stdout, stderr = _run_remote(["ssh", "root@host"], "bad cmd")
+        assert ok is False
+
+    @patch("scripts.deploy_synapse.subprocess.run", side_effect=subprocess.TimeoutExpired("cmd", 10))
+    def test_timeout(self, mock_run):
+        from scripts.deploy_synapse import _run_remote
+        ok, stdout, stderr = _run_remote(["ssh", "root@host"], "slow cmd", timeout=10)
+        assert ok is False
+        assert "timed out" in stderr
+
+
+class TestCreateBotAccount:
+    def test_returns_correct_structure(self):
+        from scripts.deploy_synapse import create_bot_account
+        with patch("scripts.deploy_synapse._run_remote") as mock:
+            mock.return_value = (True, "success", "")
+            result = create_bot_account(["ssh", "root@x"], "example.com", dry_run=True)
+            assert "user_id" in result
+            assert "password" in result
+            assert "homeserver_url" in result
+            assert result["user_id"] == "@hermes-bot:example.com"
+
+
+class TestPrintConfig:
+    def test_runs_without_error(self, capsys):
+        from scripts.deploy_synapse import print_config
+        print_config("example.com", "hermes-bot", "tok_abc", "pass123")
+        captured = capsys.readouterr()
+        assert "MATRIX_HOMESERVER=https://example.com" in captured.out
+        assert "MATRIX_ACCESS_TOKEN=tok_abc" in captured.out

tests/test_model_tools.py

@@ -137,3 +137,78 @@ class TestBackwardCompat:
     def test_tool_to_toolset_map(self):
         assert isinstance(TOOL_TO_TOOLSET_MAP, dict)
         assert len(TOOL_TO_TOOLSET_MAP) > 0
+
+
+class TestToolReturnTypeValidation:
+    """Poka-yoke: tool handlers must return JSON strings."""
+
+    def test_handler_returning_dict_is_wrapped(self, monkeypatch):
+        """A handler that returns a dict should be auto-wrapped to JSON string."""
+        from tools.registry import registry
+        from model_tools import handle_function_call
+        import json
+
+        # Register a bad handler that returns dict instead of str
+        registry.register(
+            name="__test_bad_dict",
+            toolset="test",
+            schema={"name": "__test_bad_dict", "description": "test", "parameters": {"type": "object", "properties": {}}},
+            handler=lambda args, **kw: {"this is": "a dict not a string"},
+        )
+        result = handle_function_call("__test_bad_dict", {})
+        parsed = json.loads(result)
+        assert "output" in parsed
+        assert "_type_warning" in parsed
+        # Cleanup
+        registry._tools.pop("__test_bad_dict", None)
+
+    def test_handler_returning_none_is_wrapped(self, monkeypatch):
+        """A handler that returns None should be auto-wrapped."""
+        from tools.registry import registry
+        from model_tools import handle_function_call
+        import json
+
+        registry.register(
+            name="__test_bad_none",
+            toolset="test",
+            schema={"name": "__test_bad_none", "description": "test", "parameters": {"type": "object", "properties": {}}},
+            handler=lambda args, **kw: None,
+        )
+        result = handle_function_call("__test_bad_none", {})
+        parsed = json.loads(result)
+        assert "_type_warning" in parsed
+        registry._tools.pop("__test_bad_none", None)
+
+    def test_handler_returning_non_json_string_is_wrapped(self):
+        """A handler returning a plain string (not JSON) should be wrapped."""
+        from tools.registry import registry
+        from model_tools import handle_function_call
+        import json
+
+        registry.register(
+            name="__test_bad_plain",
+            toolset="test",
+            schema={"name": "__test_bad_plain", "description": "test", "parameters": {"type": "object", "properties": {}}},
+            handler=lambda args, **kw: "just a plain string, not json",
+        )
+        result = handle_function_call("__test_bad_plain", {})
+        parsed = json.loads(result)
+        assert "output" in parsed
+        registry._tools.pop("__test_bad_plain", None)
+
+    def test_handler_returning_valid_json_passes_through(self):
+        """A handler returning valid JSON string passes through unchanged."""
+        from tools.registry import registry
+        from model_tools import handle_function_call
+        import json
+
+        registry.register(
+            name="__test_good",
+            toolset="test",
+            schema={"name": "__test_good", "description": "test", "parameters": {"type": "object", "properties": {}}},
+            handler=lambda args, **kw: json.dumps({"status": "ok", "data": [1, 2, 3]}),
+        )
+        result = handle_function_call("__test_good", {})
+        parsed = json.loads(result)
+        assert parsed == {"status": "ok", "data": [1, 2, 3]}
+        registry._tools.pop("__test_good", None)

tests/tools/test_memory_tool.py

@@ -144,7 +144,8 @@ class TestMemoryStoreReplace:
     def test_replace_no_match(self, store):
         store.add("memory", "fact A")
         result = store.replace("memory", "nonexistent", "new")
-        assert result["success"] is False
+        assert result["success"] is True
+        assert result["result"] == "no_match"
 
     def test_replace_ambiguous_match(self, store):
         store.add("memory", "server A runs nginx")
@@ -177,7 +178,8 @@ class TestMemoryStoreRemove:
 
     def test_remove_no_match(self, store):
         result = store.remove("memory", "nonexistent")
-        assert result["success"] is False
+        assert result["success"] is True
+        assert result["result"] == "no_match"
 
     def test_remove_empty_old_text(self, store):
         result = store.remove("memory", "  ")

tests/tools/test_syntax_preflight.py

@@ -0,0 +1,107 @@
+"""Tests for syntax preflight check in execute_code (issue #312)."""
+
+import ast
+import json
+import pytest
+
+
+class TestSyntaxPreflight:
+    """Verify that execute_code catches syntax errors before sandbox execution."""
+
+    def test_valid_syntax_passes_parse(self):
+        """Valid Python should pass ast.parse."""
+        code = "print('hello')\nx = 1 + 2\n"
+        ast.parse(code)  # should not raise
+
+    def test_syntax_error_indentation(self):
+        """IndentationError is a subclass of SyntaxError."""
+        code = "def foo():\nbar()\n"
+        with pytest.raises(SyntaxError):
+            ast.parse(code)
+
+    def test_syntax_error_missing_colon(self):
+        code = "if True\n  pass\n"
+        with pytest.raises(SyntaxError):
+            ast.parse(code)
+
+    def test_syntax_error_unmatched_paren(self):
+        code = "x = (1 + 2\n"
+        with pytest.raises(SyntaxError):
+            ast.parse(code)
+
+    def test_syntax_error_invalid_token(self):
+        code = "x = 1 +*\n"
+        with pytest.raises(SyntaxError):
+            ast.parse(code)
+
+    def test_syntax_error_details(self):
+        """SyntaxError should provide line, offset, msg."""
+        code = "if True\n  pass\n"
+        with pytest.raises(SyntaxError) as exc_info:
+            ast.parse(code)
+        e = exc_info.value
+        assert e.lineno is not None
+        assert e.msg is not None
+
+    def test_empty_string_passes(self):
+        """Empty string is valid Python (empty module)."""
+        ast.parse("")
+
+    def test_comments_only_passes(self):
+        ast.parse("# just a comment\n# another\n")
+
+    def test_complex_valid_code(self):
+        code = '''
+import os
+def foo(x):
+    if x > 0:
+        return x * 2
+    return 0
+
+result = [foo(i) for i in range(10)]
+print(result)
+'''
+        ast.parse(code)
+
+
+class TestSyntaxPreflightResponse:
+    """Test the error response format from the preflight check."""
+
+    def _check_syntax(self, code):
+        """Mimic the preflight check logic from execute_code."""
+        try:
+            ast.parse(code)
+            return None
+        except SyntaxError as e:
+            return json.dumps({
+                "error": f"Python syntax error: {e.msg}",
+                "line": e.lineno,
+                "offset": e.offset,
+                "text": (e.text or "").strip()[:200],
+            })
+
+    def test_returns_json_error(self):
+        result = self._check_syntax("if True\n  pass\n")
+        assert result is not None
+        data = json.loads(result)
+        assert "error" in data
+        assert "syntax error" in data["error"].lower()
+
+    def test_includes_line_number(self):
+        result = self._check_syntax("x = 1\nif True\n  pass\n")
+        data = json.loads(result)
+        assert data["line"] == 2  # error on line 2
+
+    def test_includes_offset(self):
+        result = self._check_syntax("x = (1 + 2\n")
+        data = json.loads(result)
+        assert data["offset"] is not None
+
+    def test_includes_snippet(self):
+        result = self._check_syntax("if True\n")
+        data = json.loads(result)
+        assert "if True" in data["text"]
+
+    def test_none_for_valid_code(self):
+        result = self._check_syntax("print('ok')")
+        assert result is None

tools/code_execution_tool.py

@@ -28,6 +28,7 @@ Platform: Linux / macOS only (Unix domain sockets for local). Disabled on Window
 Remote execution additionally requires Python 3 in the terminal backend.
 """
 
+import ast
 import base64
 import json
 import logging
@@ -893,6 +894,20 @@ def execute_code(
     if not code or not code.strip():
         return json.dumps({"error": "No code provided."})
 
+    # Poka-yoke (#312): Syntax check before execution.
+    # 83.2% of execute_code errors are Python exceptions; most are syntax
+    # errors the LLM generated.  ast.parse() is sub-millisecond and catches
+    # them before we spin up a sandbox child process.
+    try:
+        ast.parse(code)
+    except SyntaxError as e:
+        return json.dumps({
+            "error": f"Python syntax error: {e.msg}",
+            "line": e.lineno,
+            "offset": e.offset,
+            "text": (e.text or "").strip()[:200],
+        })
+
     # Dispatch: remote backends use file-based RPC, local uses UDS
     from tools.terminal_tool import _get_env_config
     env_type = _get_env_config()["env_type"]

tools/memory_tool.py

@@ -260,8 +260,12 @@ class MemoryStore:
             entries = self._entries_for(target)
             matches = [(i, e) for i, e in enumerate(entries) if old_text in e]
 
-            if len(matches) == 0:
-                return {"success": False, "error": f"No entry matched '{old_text}'."}
+            if not matches:
+                return {
+                    "success": True,
+                    "result": "no_match",
+                    "message": f"No entry matched '{old_text}'. The search substring was not found in any existing entry.",
+                }
 
             if len(matches) > 1:
                 # If all matches are identical (exact duplicates), operate on the first one
@@ -310,8 +314,12 @@ class MemoryStore:
             entries = self._entries_for(target)
             matches = [(i, e) for i, e in enumerate(entries) if old_text in e]
 
-            if len(matches) == 0:
-                return {"success": False, "error": f"No entry matched '{old_text}'."}
+            if not matches:
+                return {
+                    "success": True,
+                    "result": "no_match",
+                    "message": f"No entry matched '{old_text}'. The search substring was not found in any existing entry.",
+                }
 
             if len(matches) > 1:
                 # If all matches are identical (exact duplicates), remove the first one
@@ -449,30 +457,30 @@ def memory_tool(
     Returns JSON string with results.
     """
     if store is None:
-        return json.dumps({"success": False, "error": "Memory is not available. It may be disabled in config or this environment."}, ensure_ascii=False)
+        return tool_error("Memory is not available. It may be disabled in config or this environment.", success=False)
 
     if target not in ("memory", "user"):
-        return json.dumps({"success": False, "error": f"Invalid target '{target}'. Use 'memory' or 'user'."}, ensure_ascii=False)
+        return tool_error(f"Invalid target '{target}'. Use 'memory' or 'user'.", success=False)
 
     if action == "add":
         if not content:
-            return json.dumps({"success": False, "error": "Content is required for 'add' action."}, ensure_ascii=False)
+            return tool_error("Content is required for 'add' action.", success=False)
         result = store.add(target, content)
 
     elif action == "replace":
         if not old_text:
-            return json.dumps({"success": False, "error": "old_text is required for 'replace' action."}, ensure_ascii=False)
+            return tool_error("old_text is required for 'replace' action.", success=False)
         if not content:
-            return json.dumps({"success": False, "error": "content is required for 'replace' action."}, ensure_ascii=False)
+            return tool_error("content is required for 'replace' action.", success=False)
         result = store.replace(target, old_text, content)
 
     elif action == "remove":
         if not old_text:
-            return json.dumps({"success": False, "error": "old_text is required for 'remove' action."}, ensure_ascii=False)
+            return tool_error("old_text is required for 'remove' action.", success=False)
         result = store.remove(target, old_text)
 
     else:
-        return json.dumps({"success": False, "error": f"Unknown action '{action}'. Use: add, replace, remove"}, ensure_ascii=False)
+        return tool_error(f"Unknown action '{action}'. Use: add, replace, remove", success=False)
 
     return json.dumps(result, ensure_ascii=False)
 
@@ -539,7 +547,7 @@ MEMORY_SCHEMA = {
 
 
 # --- Registry ---
-from tools.registry import registry
+from tools.registry import registry, tool_error
 
 registry.register(
     name="memory",