feat: two-phase execution, think slugs, query enrichment (v1.6.0)

Two-Phase Tatlock Execution:
- orchestrate_tool_calls() for Phase 1 coordination
- synthesize_from_results() for Phase 2 butler-toned synthesis
- Guarantees butler personality in all responses

Automatic Think Slugs:
- Deterministic butler-perspective messages during expert delegation
- ActionType enum: RETRIEVE, RESEARCH, CREATE, CONTROL, RECORD
- HOUSEHOLD_THINK_MESSAGES mapping for all experts
- Streaming delegation wrappers with automatic think messages

Steward Query Enrichment:
- Auto-fill user context (location, timezone) when not specified
- _build_enriched_query() with regex word boundary matching
- enriched_query field in StewardRecommendation schema

Documentation:
- ORCHESTRATION_SCENARIOS.md rewritten with Mermaid diagrams
- New Housekeeper and Biographer scenarios
- TESTING_IMPROVEMENTS.md for future LLM testing patterns

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

tests/agents/steward/test_steward_service.py

@@ -8,7 +8,7 @@ from unittest.mock import AsyncMock, MagicMock, patch
 import pytest
 
 from src.agents.steward.schemas import ConversationContext, StewardRecommendation
-from src.agents.steward.service import analyze_request, format_steward_note
+from src.agents.steward.service import analyze_request, format_steward_note, _build_enriched_query
 from src.core.startup import initialize_application
 
 
@@ -199,3 +199,102 @@ class TestFormatStewardNote:
 
         assert "⚠️  Missing:" in note
         assert "Advanced research" in note
+
+
+@pytest.mark.unit
+class TestBuildEnrichedQuery:
+    """Tests for _build_enriched_query function."""
+
+    def test_no_enrichment_without_context(self):
+        """Test no enrichment when memory context is empty."""
+        query = "What's the weather?"
+        result = _build_enriched_query(query, {})
+
+        assert result == query
+
+    def test_enrichment_adds_location(self):
+        """Test location is appended for weather queries."""
+        query = "What's the weather?"
+        memory_context = {
+            "profile": {"location": "Amsterdam", "timezone": "Europe/Amsterdam"}
+        }
+
+        result = _build_enriched_query(query, memory_context)
+
+        assert "location=Amsterdam" in result
+        assert query in result
+        assert "[User Context:" in result
+
+    def test_no_location_when_specified(self):
+        """Test location is not appended when already specified."""
+        query = "What's the weather in London?"
+        memory_context = {
+            "profile": {"location": "Amsterdam"}
+        }
+
+        result = _build_enriched_query(query, memory_context)
+
+        # Should not add Amsterdam since location is specified
+        assert result == query
+
+    def test_enrichment_adds_timezone(self):
+        """Test timezone is appended for time queries."""
+        query = "What time is it?"
+        memory_context = {
+            "profile": {"timezone": "Europe/Amsterdam"}
+        }
+
+        result = _build_enriched_query(query, memory_context)
+
+        assert "timezone=Europe/Amsterdam" in result
+
+    def test_no_timezone_when_specified(self):
+        """Test timezone is not appended when already specified."""
+        query = "What time is it in UTC?"
+        memory_context = {
+            "profile": {"timezone": "Europe/Amsterdam"}
+        }
+
+        result = _build_enriched_query(query, memory_context)
+
+        assert result == query
+
+    def test_enrichment_adds_temperature_unit(self):
+        """Test temperature unit is appended for weather queries."""
+        query = "What's the weather?"
+        memory_context = {
+            "profile": {"location": "Amsterdam"},
+            "preferences": {"temperature_unit": "celsius"}
+        }
+
+        result = _build_enriched_query(query, memory_context)
+
+        assert "temperature_unit=celsius" in result
+
+    def test_multiple_context_fields(self):
+        """Test multiple context fields are appended."""
+        query = "What time and weather today?"
+        memory_context = {
+            "profile": {
+                "location": "Amsterdam",
+                "timezone": "Europe/Amsterdam"
+            },
+            "preferences": {"temperature_unit": "celsius"}
+        }
+
+        result = _build_enriched_query(query, memory_context)
+
+        assert "location=Amsterdam" in result
+        assert "timezone=Europe/Amsterdam" in result
+        assert "temperature_unit=celsius" in result
+
+    def test_no_enrichment_for_unrelated_query(self):
+        """Test no enrichment for queries that don't need context."""
+        query = "Tell me a joke"
+        memory_context = {
+            "profile": {"location": "Amsterdam", "timezone": "Europe/Amsterdam"}
+        }
+
+        result = _build_enriched_query(query, memory_context)
+
+        assert result == query

tests/agents/test_delegation.py

@@ -8,9 +8,14 @@ import pytest
 from unittest.mock import AsyncMock, patch, MagicMock
 
 from src.agents.delegation import (
+    ActionType,
     DelegationTask,
     DelegationResult,
+    HOUSEHOLD_THINK_MESSAGES,
+    STREAMING_DELEGATION_WRAPPERS,
     delegate_to_librarian,
+    get_think_message,
+    _detect_action_type,
 )
 
 
@@ -193,3 +198,158 @@ class TestDelegateToLibrarian:
             result = await delegate_to_librarian(task=original_task)
 
             assert result.task == original_task
+
+
+@pytest.mark.unit
+class TestActionType:
+    """Tests for the ActionType enum."""
+
+    def test_action_type_values(self):
+        """Test ActionType enum values."""
+        assert ActionType.RETRIEVE.value == "retrieve"
+        assert ActionType.RESEARCH.value == "research"
+        assert ActionType.CREATE.value == "create"
+        assert ActionType.CONTROL.value == "control"
+        assert ActionType.RECORD.value == "record"
+
+    def test_action_type_is_enum(self):
+        """Test ActionType is proper enum."""
+        assert len(ActionType) == 5
+
+
+@pytest.mark.unit
+class TestHouseholdThinkMessages:
+    """Tests for HOUSEHOLD_THINK_MESSAGES mapping."""
+
+    def test_librarian_has_messages(self):
+        """Test librarian has think messages."""
+        assert "librarian" in HOUSEHOLD_THINK_MESSAGES
+        assert ActionType.RETRIEVE in HOUSEHOLD_THINK_MESSAGES["librarian"]
+        assert ActionType.RESEARCH in HOUSEHOLD_THINK_MESSAGES["librarian"]
+        assert ActionType.CREATE in HOUSEHOLD_THINK_MESSAGES["librarian"]
+
+    def test_biographer_has_messages(self):
+        """Test biographer has think messages."""
+        assert "biographer" in HOUSEHOLD_THINK_MESSAGES
+        assert ActionType.RETRIEVE in HOUSEHOLD_THINK_MESSAGES["biographer"]
+        assert ActionType.RECORD in HOUSEHOLD_THINK_MESSAGES["biographer"]
+
+    def test_housekeeper_has_messages(self):
+        """Test housekeeper has think messages."""
+        assert "housekeeper" in HOUSEHOLD_THINK_MESSAGES
+        assert ActionType.RETRIEVE in HOUSEHOLD_THINK_MESSAGES["housekeeper"]
+        assert ActionType.CONTROL in HOUSEHOLD_THINK_MESSAGES["housekeeper"]
+
+    def test_messages_have_phases(self):
+        """Test each action type has start/success/error messages."""
+        for expert, action_types in HOUSEHOLD_THINK_MESSAGES.items():
+            for action_type, messages in action_types.items():
+                assert "start" in messages, f"{expert}/{action_type} missing 'start'"
+                assert "success" in messages, f"{expert}/{action_type} missing 'success'"
+                assert "error" in messages, f"{expert}/{action_type} missing 'error'"
+
+    def test_messages_are_think_tags(self):
+        """Test messages are wrapped in <think> tags."""
+        for expert, action_types in HOUSEHOLD_THINK_MESSAGES.items():
+            for action_type, messages in action_types.items():
+                for phase, msg in messages.items():
+                    assert msg.startswith("<think>"), f"{expert}/{action_type}/{phase}"
+                    assert msg.endswith("</think>"), f"{expert}/{action_type}/{phase}"
+
+
+@pytest.mark.unit
+class TestDetectActionType:
+    """Tests for _detect_action_type function."""
+
+    def test_librarian_search_is_retrieve(self):
+        """Test librarian search tasks are RETRIEVE."""
+        assert _detect_action_type("librarian", "search for Docker info") == ActionType.RETRIEVE
+        assert _detect_action_type("librarian", "find information about CI/CD") == ActionType.RETRIEVE
+        assert _detect_action_type("librarian", "look up Kubernetes docs") == ActionType.RETRIEVE
+
+    def test_librarian_web_search_is_research(self):
+        """Test librarian web search tasks are RESEARCH."""
+        assert _detect_action_type("librarian", "search the web for news") == ActionType.RESEARCH
+        assert _detect_action_type("librarian", "find online resources") == ActionType.RESEARCH
+        assert _detect_action_type("librarian", "research internet sources") == ActionType.RESEARCH
+
+    def test_librarian_create_is_create(self):
+        """Test librarian creation tasks are CREATE."""
+        assert _detect_action_type("librarian", "create a wiki page") == ActionType.CREATE
+        assert _detect_action_type("librarian", "write a new article") == ActionType.CREATE
+        assert _detect_action_type("librarian", "add a new entry") == ActionType.CREATE
+
+    def test_biographer_recall_is_retrieve(self):
+        """Test biographer recall tasks are RETRIEVE."""
+        assert _detect_action_type("biographer", "what car do I drive?") == ActionType.RETRIEVE
+        assert _detect_action_type("biographer", "what is my job?") == ActionType.RETRIEVE
+
+    def test_biographer_record_is_record(self):
+        """Test biographer record tasks are RECORD."""
+        assert _detect_action_type("biographer", "remember that I work at Acme") == ActionType.RECORD
+        assert _detect_action_type("biographer", "note that my car is a Tesla") == ActionType.RECORD
+        assert _detect_action_type("biographer", "save my preference for dark mode") == ActionType.RECORD
+
+    def test_housekeeper_status_is_retrieve(self):
+        """Test housekeeper status tasks are RETRIEVE."""
+        assert _detect_action_type("housekeeper", "what devices are in the bedroom?") == ActionType.RETRIEVE
+        assert _detect_action_type("housekeeper", "is the living room light on?") == ActionType.RETRIEVE
+
+    def test_housekeeper_control_is_control(self):
+        """Test housekeeper control tasks are CONTROL."""
+        assert _detect_action_type("housekeeper", "turn on the lights") == ActionType.CONTROL
+        assert _detect_action_type("housekeeper", "set brightness to 50%") == ActionType.CONTROL
+        assert _detect_action_type("housekeeper", "activate the movie scene") == ActionType.CONTROL
+        assert _detect_action_type("housekeeper", "toggle the fan") == ActionType.CONTROL
+
+
+@pytest.mark.unit
+class TestGetThinkMessage:
+    """Tests for get_think_message function."""
+
+    def test_librarian_retrieve_start(self):
+        """Test getting librarian retrieve start message."""
+        msg = get_think_message("librarian", "search for Docker", "start")
+        assert "<think>" in msg
+        assert "</think>" in msg
+
+    def test_librarian_create_success(self):
+        """Test getting librarian create success message."""
+        msg = get_think_message("librarian", "create a wiki page", "success")
+        assert "<think>" in msg
+        assert "catalogued" in msg.lower()
+
+    def test_biographer_record_start(self):
+        """Test getting biographer record start message."""
+        msg = get_think_message("biographer", "remember my preference", "start")
+        assert "<think>" in msg
+        assert "note" in msg.lower() or "biographer" in msg.lower()
+
+    def test_housekeeper_control_success(self):
+        """Test getting housekeeper control success message."""
+        msg = get_think_message("housekeeper", "turn on the lights", "success")
+        assert "<think>" in msg
+        assert "configured" in msg.lower()
+
+    def test_unknown_expert_fallback(self):
+        """Test unknown expert gets fallback message."""
+        msg = get_think_message("unknown_expert", "some task", "start")
+        assert "<think>" in msg
+        assert "unknown_expert" in msg.lower()
+
+
+@pytest.mark.unit
+class TestStreamingDelegationWrappers:
+    """Tests for streaming delegation wrapper mapping."""
+
+    def test_streaming_wrappers_exist(self):
+        """Test streaming wrappers mapping has all experts."""
+        assert "librarian" in STREAMING_DELEGATION_WRAPPERS
+        assert "biographer" in STREAMING_DELEGATION_WRAPPERS
+        assert "housekeeper" in STREAMING_DELEGATION_WRAPPERS
+
+    def test_streaming_wrappers_are_async_generators(self):
+        """Test streaming wrappers are async generator functions."""
+        import inspect
+        for name, wrapper in STREAMING_DELEGATION_WRAPPERS.items():
+            assert inspect.isasyncgenfunction(wrapper), f"{name} is not an async generator"