fix(honcho): dialectic lifecycle — defaults, retry, prewarm consumption

optional-skills/autonomous-ai-agents/honcho/SKILL.md

@@ -145,10 +145,10 @@ Controls **how often** dialectic and context calls happen.
 | Key | Default | Description |
 |-----|---------|-------------|
 | `contextCadence` | `1` | Min turns between context API calls |
-| `dialecticCadence` | `3` | Min turns between dialectic API calls |
+| `dialecticCadence` | `2` | Min turns between dialectic API calls. Recommended 1–5 |
 | `injectionFrequency` | `every-turn` | `every-turn` or `first-turn` for base context injection |
 
-Higher cadence values reduce API calls and cost. `dialecticCadence: 3` (default) means the dialectic engine fires at most every 3rd turn.
+Higher cadence values fire the dialectic LLM less often. `dialecticCadence: 2` means the engine fires every other turn. Setting it to `1` fires every turn.
 
 ### Depth (how many)
 
@@ -180,6 +180,8 @@ If `dialecticDepthLevels` is omitted, rounds use **proportional levels** derived
 
 This keeps earlier passes cheap while using full depth on the final synthesis.
 
+**Depth at session start.** The session-start prewarm runs the full configured `dialecticDepth` in the background before turn 1. A single-pass prewarm on a cold peer often returns thin output — multi-pass depth runs the audit/reconcile cycle before the user ever speaks. Turn 1 consumes the prewarm result directly; if prewarm hasn't landed in time, turn 1 falls back to a synchronous call with a bounded timeout.
+
 ### Level (how hard)
 
 Controls the **intensity** of each dialectic reasoning round.
@@ -368,7 +370,7 @@ Config file: `$HERMES_HOME/honcho.json` (profile-local) or `~/.honcho/config.jso
 | `contextTokens` | uncapped | Max tokens for the combined base context injection (summary + representation + card). Opt-in cap — omit to leave uncapped, set to an integer to bound injection size. |
 | `injectionFrequency` | `every-turn` | `every-turn` or `first-turn` |
 | `contextCadence` | `1` | Min turns between context API calls |
-| `dialecticCadence` | `3` | Min turns between dialectic LLM calls |
+| `dialecticCadence` | `2` | Min turns between dialectic LLM calls (recommended 1–5) |
 
 The `contextTokens` budget is enforced at injection time. If the session summary + representation + card exceed the budget, Honcho trims the summary first, then the representation, preserving the card. This prevents context blowup in long sessions.
 

plugins/memory/honcho/cli.py

@@ -460,17 +460,37 @@ def cmd_setup(args) -> None:
             pass  # keep current
 
     # --- 7b. Dialectic cadence ---
-    current_dialectic = str(hermes_host.get("dialecticCadence") or cfg.get("dialecticCadence") or "3")
+    current_dialectic = str(hermes_host.get("dialecticCadence") or cfg.get("dialecticCadence") or "2")
     print("\n  Dialectic cadence:")
     print("    How often Honcho rebuilds its user model (LLM call on Honcho backend).")
-    print("    1 = every turn (aggressive), 3 = every 3 turns (recommended), 5+ = sparse.")
+    print("    1 = every turn, 2 = every other turn, 3+ = sparser.")
+    print("    Recommended: 1-5.")
     new_dialectic = _prompt("Dialectic cadence", default=current_dialectic)
     try:
         val = int(new_dialectic)
         if val >= 1:
             hermes_host["dialecticCadence"] = val
     except (ValueError, TypeError):
-        hermes_host["dialecticCadence"] = 3
+        hermes_host["dialecticCadence"] = 2
+
+    # --- 7c. Dialectic reasoning level ---
+    current_reasoning = (
+        hermes_host.get("dialecticReasoningLevel")
+        or cfg.get("dialecticReasoningLevel")
+        or "low"
+    )
+    print("\n  Dialectic reasoning level:")
+    print("    Depth Honcho uses when synthesizing user context on auto-injected calls.")
+    print("    minimal  -- quick factual lookups")
+    print("    low      -- straightforward questions (default)")
+    print("    medium   -- multi-aspect synthesis")
+    print("    high     -- complex behavioral patterns")
+    print("    max      -- thorough audit-level analysis")
+    new_reasoning = _prompt("Reasoning level", default=current_reasoning)
+    if new_reasoning in ("minimal", "low", "medium", "high", "max"):
+        hermes_host["dialecticReasoningLevel"] = new_reasoning
+    else:
+        hermes_host["dialecticReasoningLevel"] = "low"
 
     # --- 8. Session strategy ---
     current_strat = hermes_host.get("sessionStrategy") or cfg.get("sessionStrategy", "per-session")
@@ -636,8 +656,11 @@ def cmd_status(args) -> None:
     print(f"  Recall mode:    {hcfg.recall_mode}")
     print(f"  Context budget: {hcfg.context_tokens or '(uncapped)'} tokens")
     raw = getattr(hcfg, "raw", None) or {}
-    dialectic_cadence = raw.get("dialecticCadence") or 3
+    dialectic_cadence = raw.get("dialecticCadence") or 1
     print(f"  Dialectic cad:  every {dialectic_cadence} turn{'s' if dialectic_cadence != 1 else ''}")
+    reasoning_cap = raw.get("reasoningLevelCap") or hcfg.reasoning_level_cap
+    heuristic_on = "on" if hcfg.reasoning_heuristic else "off"
+    print(f"  Reasoning:      base={hcfg.dialectic_reasoning_level}, cap={reasoning_cap}, heuristic={heuristic_on}")
     print(f"  Observation:    user(me={hcfg.user_observe_me},others={hcfg.user_observe_others}) ai(me={hcfg.ai_observe_me},others={hcfg.ai_observe_others})")
     print(f"  Write freq:     {hcfg.write_frequency}")
 

plugins/memory/honcho/client.py

@@ -251,6 +251,11 @@ class HonchoClientConfig:
     # matching dialectic_depth length. When None, uses proportional defaults
     # derived from dialectic_reasoning_level.
     dialectic_depth_levels: list[str] | None = None
+    # When true, the auto-injected dialectic scales reasoning level up on
+    # longer queries. See HonchoMemoryProvider for thresholds.
+    reasoning_heuristic: bool = True
+    # Ceiling for the heuristic-selected reasoning level.
+    reasoning_level_cap: str = "high"
     # Honcho API limits — configurable for self-hosted instances
     # Max chars per message sent via add_messages() (Honcho cloud: 25000)
     message_max_chars: int = 25000
@@ -446,6 +451,16 @@ def from_global_config(
                 raw.get("dialecticDepthLevels"),
                 depth=_parse_dialectic_depth(host_block.get("dialecticDepth"), raw.get("dialecticDepth")),
             ),
+            reasoning_heuristic=_resolve_bool(
+                host_block.get("reasoningHeuristic"),
+                raw.get("reasoningHeuristic"),
+                default=True,
+            ),
+            reasoning_level_cap=(
+                host_block.get("reasoningLevelCap")
+                or raw.get("reasoningLevelCap")
+                or "high"
+            ),
             message_max_chars=int(
                 host_block.get("messageMaxChars")
                 or raw.get("messageMaxChars")

plugins/memory/honcho/session.py

@@ -78,6 +78,7 @@ def __init__(
         honcho: Honcho | None = None,
         context_tokens: int | None = None,
         config: Any | None = None,
+        runtime_user_peer_name: str | None = None,
     ):
         """
         Initialize the session manager.
@@ -87,10 +88,12 @@ def __init__(
             context_tokens: Max tokens for context() calls (None = Honcho default).
             config: HonchoClientConfig from global config (provides peer_name, ai_peer,
                     write_frequency, observation, etc.).
+            runtime_user_peer_name: Gateway user identity for per-user memory scoping.
         """
         self._honcho = honcho
         self._context_tokens = context_tokens
         self._config = config
+        self._runtime_user_peer_name = runtime_user_peer_name
         self._cache: dict[str, HonchoSession] = {}
         self._peers_cache: dict[str, Any] = {}
         self._sessions_cache: dict[str, Any] = {}
@@ -100,9 +103,11 @@ def __init__(
         self._write_frequency = write_frequency
         self._turn_counter: int = 0
 
-        # Prefetch caches: session_key → last result (consumed once per turn)
+        # Prefetch cache: session_key → last context result (consumed once per turn).
+        # Dialectic results are cached on the plugin side (HonchoMemoryProvider
+        # ._prefetch_result) so session-start prewarm and turn-driven fires share
+        # one source of truth; see __init__.py _do_session_init for the prewarm.
         self._context_cache: dict[str, dict] = {}
-        self._dialectic_cache: dict[str, str] = {}
         self._prefetch_cache_lock = threading.Lock()
         self._dialectic_reasoning_level: str = (
             config.dialectic_reasoning_level if config else "low"
@@ -272,8 +277,10 @@ def get_or_create(self, key: str) -> HonchoSession:
             logger.debug("Local session cache hit: %s", key)
             return self._cache[key]
 
-        # Use peer names from global config when available
-        if self._config and self._config.peer_name:
+        # Gateway sessions should use the runtime user identity when available.
+        if self._runtime_user_peer_name:
+            user_peer_id = self._sanitize_id(self._runtime_user_peer_name)
+        elif self._config and self._config.peer_name:
             user_peer_id = self._sanitize_id(self._config.peer_name)
         else:
             # Fallback: derive from session key
@@ -499,8 +506,8 @@ def dialectic_query(
         Query Honcho's dialectic endpoint about a peer.
 
         Runs an LLM on Honcho's backend against the target peer's full
-        representation. Higher latency than context() — call async via
-        prefetch_dialectic() to avoid blocking the response.
+        representation. Higher latency than context() — callers run this in
+        a background thread (see HonchoMemoryProvider) to avoid blocking.
 
         Args:
             session_key: The session key to query against.
@@ -555,42 +562,6 @@ def dialectic_query(
             logger.warning("Honcho dialectic query failed: %s", e)
             return ""
 
-    def prefetch_dialectic(self, session_key: str, query: str) -> None:
-        """
-        Fire a dialectic_query in a background thread, caching the result.
-
-        Non-blocking. The result is available via pop_dialectic_result()
-        on the next call (typically the following turn). Reasoning level
-        is selected dynamically based on query complexity.
-
-        Args:
-            session_key: The session key to query against.
-            query: The user's current message, used as the query.
-        """
-        def _run():
-            result = self.dialectic_query(session_key, query)
-            if result:
-                self.set_dialectic_result(session_key, result)
-
-        t = threading.Thread(target=_run, name="honcho-dialectic-prefetch", daemon=True)
-        t.start()
-
-    def set_dialectic_result(self, session_key: str, result: str) -> None:
-        """Store a prefetched dialectic result in a thread-safe way."""
-        if not result:
-            return
-        with self._prefetch_cache_lock:
-            self._dialectic_cache[session_key] = result
-
-    def pop_dialectic_result(self, session_key: str) -> str:
-        """
-        Return and clear the cached dialectic result for this session.
-
-        Returns empty string if no result is ready yet.
-        """
-        with self._prefetch_cache_lock:
-            return self._dialectic_cache.pop(session_key, "")
-
     def prefetch_context(self, session_key: str, user_message: str | None = None) -> None:
         """
         Fire get_prefetch_context in a background thread, caching the result.

tests/agent/test_memory_provider.py

@@ -971,8 +971,6 @@ def test_queue_prefetch_respects_dialectic_cadence(self):
         class FakeManager:
             def prefetch_context(self, key, query=None):
                 pass
-            def prefetch_dialectic(self, key, query):
-                pass
 
         p._manager = FakeManager()
 

tests/agent/test_memory_user_id.py

@@ -208,34 +208,81 @@ def test_different_users_get_different_ids(self):
 
 
 class TestHonchoUserIdScoping:
-    """Verify Honcho plugin uses gateway user_id for peer_name when provided."""
+    """Verify Honcho plugin keeps runtime user scoping separate from config peer_name."""
 
-    def test_gateway_user_id_overrides_peer_name(self):
-        """When user_id is in kwargs and no explicit peer_name, user_id should be used."""
+    def test_gateway_user_id_is_passed_as_runtime_peer(self):
+        """Gateway user_id should scope Honcho sessions without mutating config peer_name."""
         from plugins.memory.honcho import HonchoMemoryProvider
 
         provider = HonchoMemoryProvider()
 
-        # Create a mock config with NO explicit peer_name
         mock_cfg = MagicMock()
         mock_cfg.enabled = True
         mock_cfg.api_key = "test-key"
         mock_cfg.base_url = None
-        mock_cfg.peer_name = ""  # No explicit peer_name — user_id should fill it
-        mock_cfg.recall_mode = "tools"  # Use tools mode to defer session init
+        mock_cfg.peer_name = "static-user"
+        mock_cfg.recall_mode = "context"
+        mock_cfg.context_tokens = None
+        mock_cfg.raw = {}
+        mock_cfg.dialectic_depth = 1
+        mock_cfg.dialectic_depth_levels = None
+        mock_cfg.init_on_session_start = False
+        mock_cfg.ai_peer = "hermes"
+        mock_cfg.resolve_session_name.return_value = "test-sess"
+        mock_cfg.session_strategy = "shared"
 
         with patch(
             "plugins.memory.honcho.client.HonchoClientConfig.from_global_config",
             return_value=mock_cfg,
-        ):
+        ), patch(
+            "plugins.memory.honcho.client.get_honcho_client",
+            return_value=MagicMock(),
+        ), patch(
+            "plugins.memory.honcho.session.HonchoSessionManager",
+        ) as mock_manager_cls:
+            mock_manager = MagicMock()
+            mock_manager.get_or_create.return_value = MagicMock(messages=[])
+            mock_manager_cls.return_value = mock_manager
             provider.initialize(
                 session_id="test-sess",
                 user_id="discord_user_789",
                 platform="discord",
             )
 
-        # The config's peer_name should have been overridden with the user_id
-        assert mock_cfg.peer_name == "discord_user_789"
+        assert mock_cfg.peer_name == "static-user"
+        assert mock_manager_cls.call_args.kwargs["runtime_user_peer_name"] == "discord_user_789"
+
+    def test_session_manager_prefers_runtime_user_id_over_config_peer_name(self):
+        """Session manager should isolate gateway users even when config peer_name is static."""
+        from plugins.memory.honcho.session import HonchoSessionManager
+
+        mock_cfg = MagicMock()
+        mock_cfg.peer_name = "static-user"
+        mock_cfg.ai_peer = "hermes"
+        mock_cfg.write_frequency = "sync"
+        mock_cfg.dialectic_reasoning_level = "low"
+        mock_cfg.dialectic_dynamic = True
+        mock_cfg.dialectic_max_chars = 600
+        mock_cfg.observation_mode = "directional"
+        mock_cfg.user_observe_me = True
+        mock_cfg.user_observe_others = True
+        mock_cfg.ai_observe_me = True
+        mock_cfg.ai_observe_others = True
+
+        manager = HonchoSessionManager(
+            honcho=MagicMock(),
+            config=mock_cfg,
+            runtime_user_peer_name="discord_user_789",
+        )
+
+        with patch.object(manager, "_get_or_create_peer", return_value=MagicMock()), patch.object(
+            manager,
+            "_get_or_create_honcho_session",
+            return_value=(MagicMock(), []),
+        ):
+            session = manager.get_or_create("discord:channel-1")
+
+        assert session.user_peer_id == "discord_user_789"
 
     def test_no_user_id_preserves_config_peer_name(self):
         """Without user_id, the config peer_name should be preserved."""

tests/honcho_plugin/test_async_memory.py

@@ -460,10 +460,3 @@ def test_set_and_pop_context_result(self):
         assert mgr.pop_context_result("cli:test") == payload
         assert mgr.pop_context_result("cli:test") == {}
 
-    def test_set_and_pop_dialectic_result(self):
-        mgr = _make_manager(write_frequency="turn")
-
-        mgr.set_dialectic_result("cli:test", "Resume with toolset cleanup")
-
-        assert mgr.pop_dialectic_result("cli:test") == "Resume with toolset cleanup"
-        assert mgr.pop_dialectic_result("cli:test") == ""

tests/honcho_plugin/test_cli.py

@@ -26,6 +26,9 @@ class FakeConfig:
             write_frequency = "async"
             session_strategy = "per-session"
             context_tokens = 800
+            dialectic_reasoning_level = "low"
+            reasoning_level_cap = "high"
+            reasoning_heuristic = True
 
             def resolve_session_name(self):
                 return "hermes"