fix(honcho): harden tool gating and migration peer routing

Prevent stale Honcho tool exposure in context/local modes, restore reliable async write retry behavior, and ensure SOUL.md migration uploads target the AI peer instead of the user peer. Also align Honcho CLI key checks with host-scoped apiKey resolution and lock the fixes with regression tests.

Made-with: Cursor

tests/honcho_integration/test_async_memory.py

@@ -380,10 +380,10 @@ class TestAsyncWriterThread:
         sess.add_message("user", "async msg")
 
         flushed = []
-        original = mgr._flush_session
 
         def capture(s):
             flushed.append(s)
+            return True
 
         mgr._flush_session = capture
         mgr._async_queue.put(sess)
@@ -457,6 +457,66 @@ class TestAsyncWriterRetry:
         assert call_count[0] == 2
         assert not mgr._async_thread.is_alive()
 
+    def test_retries_when_flush_reports_failure(self):
+        mgr = _make_manager(write_frequency="async")
+        sess = _make_session()
+        sess.add_message("user", "msg")
+
+        call_count = [0]
+
+        def fail_then_succeed(_session):
+            call_count[0] += 1
+            return call_count[0] > 1
+
+        mgr._flush_session = fail_then_succeed
+
+        with patch("time.sleep"):
+            mgr._async_queue.put(sess)
+            deadline = time.time() + 3.0
+            while call_count[0] < 2 and time.time() < deadline:
+                time.sleep(0.05)
+
+        mgr.shutdown()
+        assert call_count[0] == 2
+
+
+class TestMemoryFileMigrationTargets:
+    def test_soul_upload_targets_ai_peer(self, tmp_path):
+        mgr = _make_manager(write_frequency="turn")
+        session = _make_session(
+            key="cli:test",
+            user_peer_id="custom-user",
+            assistant_peer_id="custom-ai",
+            honcho_session_id="cli-test",
+        )
+        mgr._cache[session.key] = session
+
+        user_peer = MagicMock(name="user-peer")
+        ai_peer = MagicMock(name="ai-peer")
+        mgr._peers_cache[session.user_peer_id] = user_peer
+        mgr._peers_cache[session.assistant_peer_id] = ai_peer
+
+        honcho_session = MagicMock()
+        mgr._sessions_cache[session.honcho_session_id] = honcho_session
+
+        (tmp_path / "MEMORY.md").write_text("memory facts", encoding="utf-8")
+        (tmp_path / "USER.md").write_text("user profile", encoding="utf-8")
+        (tmp_path / "SOUL.md").write_text("ai identity", encoding="utf-8")
+
+        uploaded = mgr.migrate_memory_files(session.key, str(tmp_path))
+
+        assert uploaded is True
+        assert honcho_session.upload_file.call_count == 3
+
+        peer_by_upload_name = {}
+        for call_args in honcho_session.upload_file.call_args_list:
+            payload = call_args.kwargs["file"]
+            peer_by_upload_name[payload[0]] = call_args.kwargs["peer"]
+
+        assert peer_by_upload_name["consolidated_memory.md"] is user_peer
+        assert peer_by_upload_name["user_profile.md"] is user_peer
+        assert peer_by_upload_name["agent_soul.md"] is ai_peer
+
 
 # ---------------------------------------------------------------------------
 # HonchoClientConfig dataclass defaults for new fields

tests/honcho_integration/test_cli.py

@@ -0,0 +1,29 @@
+"""Tests for Honcho CLI helpers."""
+
+from honcho_integration.cli import _resolve_api_key
+
+
+class TestResolveApiKey:
+    def test_prefers_host_scoped_key(self):
+        cfg = {
+            "apiKey": "root-key",
+            "hosts": {
+                "hermes": {
+                    "apiKey": "host-key",
+                }
+            },
+        }
+        assert _resolve_api_key(cfg) == "host-key"
+
+    def test_falls_back_to_root_key(self):
+        cfg = {
+            "apiKey": "root-key",
+            "hosts": {"hermes": {}},
+        }
+        assert _resolve_api_key(cfg) == "root-key"
+
+    def test_falls_back_to_env_key(self, monkeypatch):
+        monkeypatch.setenv("HONCHO_API_KEY", "env-key")
+        assert _resolve_api_key({}) == "env-key"
+        monkeypatch.delenv("HONCHO_API_KEY", raising=False)
+

tests/test_run_agent.py

@@ -1277,6 +1277,82 @@ class TestHonchoActivation:
         )
         mock_client.assert_not_called()
 
+    def test_recall_mode_context_suppresses_honcho_tools(self):
+        hcfg = HonchoClientConfig(
+            enabled=True,
+            api_key="honcho-key",
+            memory_mode="hybrid",
+            peer_name="user",
+            ai_peer="hermes",
+            recall_mode="context",
+        )
+        manager = MagicMock()
+        manager._config = hcfg
+        manager.get_or_create.return_value = SimpleNamespace(messages=[])
+        manager.get_prefetch_context.return_value = {"representation": "Known user", "card": ""}
+
+        with (
+            patch(
+                "run_agent.get_tool_definitions",
+                side_effect=[
+                    _make_tool_defs("web_search"),
+                    _make_tool_defs(
+                        "web_search",
+                        "honcho_context",
+                        "honcho_profile",
+                        "honcho_search",
+                        "honcho_conclude",
+                    ),
+                ],
+            ),
+            patch("run_agent.check_toolset_requirements", return_value={}),
+            patch("run_agent.OpenAI"),
+            patch("tools.honcho_tools.set_session_context"),
+        ):
+            agent = AIAgent(
+                api_key="test-key-1234567890",
+                quiet_mode=True,
+                skip_context_files=True,
+                skip_memory=False,
+                honcho_session_key="gateway-session",
+                honcho_manager=manager,
+                honcho_config=hcfg,
+            )
+
+        assert "web_search" in agent.valid_tool_names
+        assert "honcho_context" not in agent.valid_tool_names
+        assert "honcho_profile" not in agent.valid_tool_names
+        assert "honcho_search" not in agent.valid_tool_names
+        assert "honcho_conclude" not in agent.valid_tool_names
+
+    def test_inactive_honcho_strips_stale_honcho_tools(self):
+        hcfg = HonchoClientConfig(
+            enabled=True,
+            api_key="honcho-key",
+            memory_mode="local",
+            peer_name="user",
+            ai_peer="hermes",
+        )
+
+        with (
+            patch("run_agent.get_tool_definitions", return_value=_make_tool_defs("web_search", "honcho_context")),
+            patch("run_agent.check_toolset_requirements", return_value={}),
+            patch("run_agent.OpenAI"),
+            patch("honcho_integration.client.HonchoClientConfig.from_global_config", return_value=hcfg),
+            patch("honcho_integration.client.get_honcho_client") as mock_client,
+        ):
+            agent = AIAgent(
+                api_key="test-key-1234567890",
+                quiet_mode=True,
+                skip_context_files=True,
+                skip_memory=False,
+            )
+
+        assert agent._honcho is None
+        assert "web_search" in agent.valid_tool_names
+        assert "honcho_context" not in agent.valid_tool_names
+        mock_client.assert_not_called()
+
 
 class TestHonchoPrefetchScheduling:
     def test_honcho_prefetch_includes_cached_dialectic(self, agent):