refactor(honcho): rename recallMode "auto" to "hybrid"

Matches the mental model: hybrid = context + tools,
context = context only, tools = tools only.

honcho_integration/cli.py

@@ -147,13 +147,13 @@ def cmd_setup(args) -> None:
         cfg["writeFrequency"] = new_wf if new_wf in ("async", "turn", "session") else "async"
 
     # Recall mode
-    current_recall = cfg.get("recallMode", "auto")
+    current_recall = cfg.get("recallMode", "hybrid")
     print(f"\n  Recall mode options:")
-    print("    auto    — pre-warmed context + memory tools available (default)")
+    print("    hybrid  — pre-warmed context + memory tools available (default)")
     print("    context — pre-warmed context only, memory tools suppressed")
     print("    tools   — no pre-loaded context, rely on tool calls only")
     new_recall = _prompt("Recall mode", default=current_recall)
-    if new_recall in ("auto", "context", "tools"):
+    if new_recall in ("hybrid", "context", "tools"):
         cfg["recallMode"] = new_recall
 
     # Session strategy

honcho_integration/client.py

@@ -90,10 +90,10 @@ class HonchoClientConfig:
     # Max chars of dialectic result to inject into Hermes system prompt
     dialectic_max_chars: int = 600
     # Recall mode: how memory retrieval works when Honcho is active.
-    # "auto"    — pre-warmed context + memory tools available (model decides)
+    # "hybrid"  — pre-warmed context + memory tools available (model decides)
     # "context" — pre-warmed context only, honcho memory tools removed
     # "tools"   — no pre-loaded context, rely on tool calls only
-    recall_mode: str = "auto"
+    recall_mode: str = "hybrid"
     # Session resolution
     session_strategy: str = "per-session"
     session_peer_prefix: bool = False
@@ -199,7 +199,7 @@ class HonchoClientConfig:
             recall_mode=(
                 host_block.get("recallMode")
                 or raw.get("recallMode")
-                or "auto"
+                or "hybrid"
             ),
             session_strategy=raw.get("sessionStrategy", "per-session"),
             session_peer_prefix=raw.get("sessionPeerPrefix", False),

run_agent.py

@@ -1580,7 +1580,7 @@ class AIAgent:
             hcfg = self._honcho_config
             mode = hcfg.memory_mode if hcfg else "hybrid"
             freq = hcfg.write_frequency if hcfg else "async"
-            recall_mode = hcfg.recall_mode if hcfg else "auto"
+            recall_mode = hcfg.recall_mode if hcfg else "hybrid"
             honcho_block = (
                 "# Honcho memory integration\n"
                 f"Active. Session: {self._honcho_session_key}. "
@@ -3382,7 +3382,7 @@ class AIAgent:
         # Honcho: read cached context from last turn's background fetch (non-blocking),
         # then fire both fetches for next turn.  Skip in "tools" mode (no context injection).
         self._honcho_context = ""
-        _recall_mode = (self._honcho_config.recall_mode if self._honcho_config else "auto")
+        _recall_mode = (self._honcho_config.recall_mode if self._honcho_config else "hybrid")
         if self._honcho and self._honcho_session_key and not conversation_history and _recall_mode != "tools":
             try:
                 self._honcho_context = self._honcho_prefetch(user_message)

tests/honcho_integration/test_client.py

@@ -26,7 +26,7 @@ class TestHonchoClientConfigDefaults:
         assert config.enabled is False
         assert config.save_messages is True
         assert config.session_strategy == "per-session"
-        assert config.recall_mode == "auto"
+        assert config.recall_mode == "hybrid"
         assert config.session_peer_prefix is False
         assert config.linked_hosts == []
         assert config.sessions == {}
@@ -168,7 +168,7 @@ class TestFromGlobalConfig:
         config_file = tmp_path / "config.json"
         config_file.write_text(json.dumps({"apiKey": "key"}))
         config = HonchoClientConfig.from_global_config(config_path=config_file)
-        assert config.recall_mode == "auto"
+        assert config.recall_mode == "hybrid"
 
     def test_corrupt_config_falls_back_to_env(self, tmp_path):
         config_file = tmp_path / "config.json"