test(ssh): Add tests for remote hermes path validation

Add comprehensive tests for:
1. validate_remote_hermes_path() - found, not found, error cases
2. _get_default_hermes_path() - path discovery logic
3. execute_hermes_command() - success, validation failure, timeout cases

Resolves #350

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

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_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/test_ssh_hermes_validation.py

@@ -0,0 +1,129 @@
+"""
+Test remote hermes path validation functions.
+"""
+
+import pytest
+import subprocess
+from unittest.mock import Mock, patch
+from tools.environments.ssh import SSHEnvironment
+
+
+class TestHermesPathValidation:
+    """Test hermes path validation functions."""
+    
+    def test_validate_remote_hermes_path_found(self):
+        """Test validation when hermes binary exists."""
+        # Mock SSHEnvironment
+        ssh_env = Mock(spec=SSHEnvironment)
+        ssh_env.run = Mock(return_value="FOUND")
+        
+        # Call validation
+        result = SSHEnvironment.validate_remote_hermes_path(ssh_env, "/usr/local/bin/hermes")
+        
+        # Verify result
+        assert result["available"] is True
+        assert result["path"] == "/usr/local/bin/hermes"
+        assert result["error"] is None
+    
+    def test_validate_remote_hermes_path_not_found(self):
+        """Test validation when hermes binary doesn't exist."""
+        # Mock SSHEnvironment
+        ssh_env = Mock(spec=SSHEnvironment)
+        ssh_env.run = Mock(return_value="NOT_FOUND")
+        
+        # Call validation
+        result = SSHEnvironment.validate_remote_hermes_path(ssh_env, "/invalid/path/hermes")
+        
+        # Verify result
+        assert result["available"] is False
+        assert result["path"] == "/invalid/path/hermes"
+        assert "not found" in result["error"].lower()
+    
+    def test_validate_remote_hermes_path_error(self):
+        """Test validation when SSH command fails."""
+        # Mock SSHEnvironment
+        ssh_env = Mock(spec=SSHEnvironment)
+        ssh_env.run = Mock(side_effect=subprocess.TimeoutExpired("cmd", 10))
+        
+        # Call validation
+        result = SSHEnvironment.validate_remote_hermes_path(ssh_env, "/usr/local/bin/hermes")
+        
+        # Verify result
+        assert result["available"] is False
+        assert "error" in result["error"].lower()
+    
+    def test_get_default_hermes_path(self):
+        """Test getting default hermes path."""
+        # Mock SSHEnvironment
+        ssh_env = Mock(spec=SSHEnvironment)
+        
+        # Test with local bin path found
+        ssh_env.run = Mock(return_value="/home/user/.local/bin/hermes")
+        result = SSHEnvironment._get_default_hermes_path(ssh_env)
+        assert result == "/home/user/.local/bin/hermes"
+        
+        # Test with wizard pattern
+        ssh_env.run = Mock(side_effect=["", "/root/wizards/ezra/hermes-agent/venv/bin/hermes"])
+        result = SSHEnvironment._get_default_hermes_path(ssh_env)
+        assert result == "/root/wizards/ezra/hermes-agent/venv/bin/hermes"
+    
+    def test_execute_hermes_command_success(self):
+        """Test successful hermes command execution."""
+        # Mock SSHEnvironment
+        ssh_env = Mock(spec=SSHEnvironment)
+        ssh_env.run = Mock(return_value="Job output here")
+        ssh_env.validate_remote_hermes_path = Mock(return_value={
+            "available": True,
+            "path": "/usr/local/bin/hermes",
+            "error": None
+        })
+        
+        # Call execution
+        result = SSHEnvironment.execute_hermes_command(ssh_env, "cron list", validate_path=True)
+        
+        # Verify result
+        assert result["success"] is True
+        assert result["stdout"] == "Job output here"
+        assert result["exit_code"] == 0
+        assert result["error"] is None
+    
+    def test_execute_hermes_command_validation_failed(self):
+        """Test hermes command execution when validation fails."""
+        # Mock SSHEnvironment
+        ssh_env = Mock(spec=SSHEnvironment)
+        ssh_env.validate_remote_hermes_path = Mock(return_value={
+            "available": False,
+            "path": "/invalid/path/hermes",
+            "error": "Hermes binary not found"
+        })
+        
+        # Call execution
+        result = SSHEnvironment.execute_hermes_command(ssh_env, "cron list", validate_path=True)
+        
+        # Verify result
+        assert result["success"] is False
+        assert "not found" in result["error"].lower()
+        assert result["exit_code"] == 1
+    
+    def test_execute_hermes_command_timeout(self):
+        """Test hermes command execution timeout."""
+        # Mock SSHEnvironment
+        ssh_env = Mock(spec=SSHEnvironment)
+        ssh_env.run = Mock(side_effect=subprocess.TimeoutExpired("cmd", 300))
+        ssh_env.validate_remote_hermes_path = Mock(return_value={
+            "available": True,
+            "path": "/usr/local/bin/hermes",
+            "error": None
+        })
+        
+        # Call execution
+        result = SSHEnvironment.execute_hermes_command(ssh_env, "cron list", validate_path=True)
+        
+        # Verify result
+        assert result["success"] is False
+        assert "timeout" in result["error"].lower()
+        assert result["exit_code"] == -1
+
+
+if __name__ == "__main__":
+    pytest.main([__file__])

tools/environments/ssh.py

@@ -311,3 +311,152 @@ class SSHEnvironment(PersistentShellMixin, BaseEnvironment):
                 self.control_socket.unlink()
             except OSError:
                 pass
+
+
+
+    def validate_remote_hermes_path(self, hermes_path: str = None) -> dict:
+        """
+        Validate that hermes binary exists and is executable on the remote host.
+        
+        Args:
+            hermes_path: Path to hermes binary. If None, uses default path.
+            
+        Returns:
+            dict with keys:
+                - available: bool (True if hermes is available)
+                - path: str (actual path found)
+                - error: str (error message if not available)
+        """
+        if hermes_path is None:
+            hermes_path = self._get_default_hermes_path()
+        
+        # Check if hermes binary exists and is executable
+        check_cmd = f"test -x {hermes_path} && echo 'FOUND' || echo 'NOT_FOUND'"
+        
+        try:
+            result = self.run(check_cmd, timeout=10)
+            if "FOUND" in result:
+                return {
+                    "available": True,
+                    "path": hermes_path,
+                    "error": None
+                }
+            else:
+                return {
+                    "available": False,
+                    "path": hermes_path,
+                    "error": f"Hermes binary not found or not executable: {hermes_path}"
+                }
+        except Exception as e:
+            return {
+                "available": False,
+                "path": hermes_path,
+                "error": f"Error validating hermes path: {str(e)}"
+            }
+    
+    def _get_default_hermes_path(self) -> str:
+        """Get the default hermes path for this host."""
+        # Try common paths in order of preference
+        paths_to_try = [
+            "~/.local/bin/hermes",  # Standard install location
+            "/root/wizards/*/hermes-agent/venv/bin/hermes",  # Wizard pattern
+            "/usr/local/bin/hermes",  # System install
+        ]
+        
+        for path_pattern in paths_to_try:
+            if "*" in path_pattern:
+                # Use find for glob patterns
+                find_cmd = f"find {path_pattern.replace('*', '*')} -maxdepth 0 2>/dev/null | head -1"
+                try:
+                    result = self.run(find_cmd, timeout=5)
+                    if result.strip():
+                        return result.strip()
+                except:
+                    continue
+            else:
+                # Direct path check
+                check_cmd = f"test -x {path_pattern} && echo {path_pattern}"
+                try:
+                    result = self.run(check_cmd, timeout=5)
+                    if result.strip():
+                        return result.strip()
+                except:
+                    continue
+        
+        # Fallback to wizard pattern
+        return "/root/wizards/*/hermes-agent/venv/bin/hermes"
+    
+    def execute_hermes_command(self, command: str, validate_path: bool = True) -> dict:
+        """
+        Execute a hermes command on the remote host with proper validation.
+        
+        Args:
+            command: Hermes command to execute (e.g., "cron list")
+            validate_path: Whether to validate hermes path before execution
+            
+        Returns:
+            dict with keys:
+                - success: bool (True if command executed successfully)
+                - stdout: str (command output)
+                - stderr: str (error output)
+                - exit_code: int (command exit code)
+                - error: str (error message if failed)
+        """
+        # Validate hermes path if requested
+        if validate_path:
+            validation = self.validate_remote_hermes_path()
+            if not validation["available"]:
+                return {
+                    "success": False,
+                    "stdout": "",
+                    "stderr": validation["error"],
+                    "exit_code": 1,
+                    "error": validation["error"]
+                }
+            hermes_path = validation["path"]
+        else:
+            hermes_path = self._get_default_hermes_path()
+        
+        # Build full command
+        full_command = f"{hermes_path} {command}"
+        
+        try:
+            # Execute command
+            result = self.run(full_command, timeout=300)
+            
+            # Check exit code - only mark success if exit code is 0
+            # Note: self.run() raises an exception on non-zero exit code,
+            # so if we get here, the command succeeded
+            return {
+                "success": True,
+                "stdout": result,
+                "stderr": "",
+                "exit_code": 0,
+                "error": None
+            }
+            
+        except subprocess.CalledProcessError as e:
+            # Command failed with non-zero exit code
+            return {
+                "success": False,
+                "stdout": e.stdout or "",
+                "stderr": e.stderr or "",
+                "exit_code": e.returncode,
+                "error": f"Command failed with exit code {e.returncode}"
+            }
+        except subprocess.TimeoutExpired:
+            return {
+                "success": False,
+                "stdout": "",
+                "stderr": "",
+                "exit_code": -1,
+                "error": "Command timed out"
+            }
+        except Exception as e:
+            return {
+                "success": False,
+                "stdout": "",
+                "stderr": "",
+                "exit_code": -1,
+                "error": f"Error executing command: {str(e)}"
+            }