Files
tatlock/tests/agents/test_orchestration.py
T
jpmschweitzerandClaude Opus 4.5 9980e4764c
Build and Push / build (release) Successful in 1m49s
fix: remove <think> wrappers from think messages
Messages in reasoning_content should be plain text, not wrapped
in <think> tags. Removed wrappers from:
- delegation.py household think messages
- orchestration.py status messages

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

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-16 09:12:17 +01:00

762 lines
25 KiB
Python

"""
Tests for orchestration module.
Tests the multi-expert coordination infrastructure including
delegation parsing, think updates, result handling, and
multi-expert sequential/parallel execution.
"""
import pytest
from unittest.mock import AsyncMock, patch
from src.agents.orchestration import (
OrchestrationContext,
parse_delegation_from_steward_note,
execute_delegation,
orchestrate_with_think_updates,
extract_delegation_context,
ExecutionMode,
MultiExpertResult,
execute_sequential,
execute_parallel,
orchestrate_multi_expert,
_get_display_name,
)
from src.agents.delegation import DelegationTask, DelegationResult
@pytest.mark.unit
class TestParseDelegation:
"""Tests for parsing delegation from Steward's note."""
def test_parse_librarian_create(self):
"""Test parsing librarian create delegation."""
note = """DELEGATE: librarian to create a wiki page about CI/CD pipelines
REASON: User wants to document CI/CD concepts
COMPLEXITY: moderate
CONTEXT: none"""
task = parse_delegation_from_steward_note(note)
assert task is not None
assert task.expert_name == "librarian"
assert "create a wiki page about CI/CD pipelines" in task.task
def test_parse_librarian_search(self):
"""Test parsing librarian search delegation."""
note = """DELEGATE: librarian to search for information about Docker networking
REASON: User needs Docker documentation
COMPLEXITY: simple"""
task = parse_delegation_from_steward_note(note)
assert task is not None
assert task.expert_name == "librarian"
assert "search for information about Docker networking" in task.task
def test_parse_no_delegation(self):
"""Test parsing when no delegation needed."""
note = """DELEGATE: none (conversational response only)
REASON: Simple greeting requires no tools
COMPLEXITY: simple"""
task = parse_delegation_from_steward_note(note)
assert task is None
def test_parse_tatlock_core(self):
"""Test parsing tatlock_core delegation."""
note = """DELEGATE: tatlock_core to calculate the result
REASON: Math calculation needed
COMPLEXITY: simple"""
task = parse_delegation_from_steward_note(note)
assert task is not None
assert task.expert_name == "tatlock_core"
assert "calculate the result" in task.task
def test_parse_case_insensitive(self):
"""Test parsing is case insensitive."""
note = """delegate: LIBRARIAN to search docs
reason: Research query"""
task = parse_delegation_from_steward_note(note)
assert task is not None
assert task.expert_name == "librarian"
def test_parse_missing_delegate(self):
"""Test parsing when DELEGATE line is missing."""
note = """REASON: This has no delegation
COMPLEXITY: simple"""
task = parse_delegation_from_steward_note(note)
assert task is None
@pytest.mark.unit
class TestExtractDelegationContext:
"""Tests for extracting context from Steward's note."""
def test_extract_all_fields(self):
"""Test extracting all context fields."""
note = """DELEGATE: librarian to create wiki page
REASON: User wants documentation
COMPLEXITY: moderate
CONTEXT: Related to previous discussion about DevOps"""
context = extract_delegation_context(note)
assert context["reason"] == "User wants documentation"
assert context["complexity"] == "moderate"
assert "Related to previous discussion" in context["context"]
def test_extract_partial_fields(self):
"""Test extracting when some fields missing."""
note = """DELEGATE: librarian to search
REASON: Research query
COMPLEXITY: simple"""
context = extract_delegation_context(note)
assert context["reason"] == "Research query"
assert context["complexity"] == "simple"
assert context["context"] == ""
def test_extract_empty_note(self):
"""Test extracting from empty note."""
context = extract_delegation_context("")
assert context["reason"] == ""
assert context["complexity"] == ""
assert context["context"] == ""
@pytest.mark.unit
class TestExecuteDelegation:
"""Tests for executing delegation tasks."""
@pytest.mark.asyncio
async def test_execute_librarian_delegation(self):
"""Test executing delegation to librarian."""
task = DelegationTask(
expert_name="librarian",
task="search for Docker docs",
context="User learning Docker",
)
mock_result = DelegationResult(
expert_name="librarian",
task="search for Docker docs",
success=True,
output="Found Docker documentation...",
)
with patch(
"src.agents.orchestration.delegate_to_librarian",
new_callable=AsyncMock,
return_value=mock_result,
) as mock_delegate:
result = await execute_delegation(task)
mock_delegate.assert_called_once_with(
task="search for Docker docs",
context="User learning Docker",
)
assert result.success is True
assert "Docker" in result.output
@pytest.mark.asyncio
async def test_execute_unknown_expert(self):
"""Test executing delegation to unknown expert."""
task = DelegationTask(
expert_name="unknown_expert",
task="do something",
)
result = await execute_delegation(task)
assert result.success is False
assert "Unknown expert" in result.error
@pytest.mark.unit
class TestOrchestrateWithThinkUpdates:
"""Tests for orchestration with think updates."""
@pytest.mark.asyncio
async def test_orchestrate_emits_think_before_delegation(self):
"""Test that think update is emitted before delegation."""
mock_result = DelegationResult(
expert_name="librarian",
task="search docs",
success=True,
output="Found results",
)
with patch(
"src.agents.orchestration.delegate_to_librarian",
new_callable=AsyncMock,
return_value=mock_result,
):
updates = []
async for update in orchestrate_with_think_updates(
user_message="Search for Docker info",
steward_note="DELEGATE: librarian to search for Docker info",
):
updates.append(update)
# First update should be about consulting (no <think> wrappers anymore)
assert any("Consulting" in u for u in updates)
@pytest.mark.asyncio
async def test_orchestrate_emits_think_after_delegation(self):
"""Test that think update is emitted after delegation."""
mock_result = DelegationResult(
expert_name="librarian",
task="search docs",
success=True,
output="Found results",
)
with patch(
"src.agents.orchestration.delegate_to_librarian",
new_callable=AsyncMock,
return_value=mock_result,
):
updates = []
async for update in orchestrate_with_think_updates(
user_message="Search for Docker info",
steward_note="DELEGATE: librarian to search for Docker info",
):
updates.append(update)
# Should have message about completion (no <think> wrappers anymore)
assert any("completed" in u for u in updates)
@pytest.mark.asyncio
async def test_orchestrate_yields_expert_output(self):
"""Test that expert output is yielded."""
mock_result = DelegationResult(
expert_name="librarian",
task="search docs",
success=True,
output="Found Docker documentation with networking details",
)
with patch(
"src.agents.orchestration.delegate_to_librarian",
new_callable=AsyncMock,
return_value=mock_result,
):
updates = []
async for update in orchestrate_with_think_updates(
user_message="Search for Docker info",
steward_note="DELEGATE: librarian to search for Docker info",
):
updates.append(update)
# Should include expert output
all_output = "".join(updates)
assert "Docker documentation" in all_output
@pytest.mark.asyncio
async def test_orchestrate_handles_delegation_failure(self):
"""Test that delegation failure emits warning think update."""
mock_result = DelegationResult(
expert_name="librarian",
task="search docs",
success=False,
output="",
error="Connection timeout",
)
with patch(
"src.agents.orchestration.delegate_to_librarian",
new_callable=AsyncMock,
return_value=mock_result,
):
updates = []
async for update in orchestrate_with_think_updates(
user_message="Search for info",
steward_note="DELEGATE: librarian to search",
):
updates.append(update)
# Should have warning think update
all_output = "".join(updates)
assert "⚠️" in all_output or "issue" in all_output.lower()
@pytest.mark.asyncio
async def test_orchestrate_no_delegation_returns_empty(self):
"""Test that no delegation yields nothing."""
updates = []
async for update in orchestrate_with_think_updates(
user_message="Hello",
steward_note="DELEGATE: none (conversational)",
):
updates.append(update)
assert len(updates) == 0
@pytest.mark.asyncio
async def test_orchestrate_with_preparsed_task(self):
"""Test orchestration with pre-parsed delegation task."""
task = DelegationTask(
expert_name="librarian",
task="create wiki page",
)
mock_result = DelegationResult(
expert_name="librarian",
task="create wiki page",
success=True,
output="Wiki page created",
)
with patch(
"src.agents.orchestration.delegate_to_librarian",
new_callable=AsyncMock,
return_value=mock_result,
):
updates = []
async for update in orchestrate_with_think_updates(
user_message="Create wiki page",
steward_note="", # Empty note since task is pre-parsed
delegation_task=task,
):
updates.append(update)
assert len(updates) > 0
all_output = "".join(updates)
assert "Wiki page created" in all_output
@pytest.mark.unit
class TestOrchestrationContext:
"""Tests for OrchestrationContext dataclass."""
def test_context_creation(self):
"""Test creating orchestration context."""
ctx = OrchestrationContext(
user_message="Test message",
steward_note="Test note",
conversation_id="conv_123",
)
assert ctx.user_message == "Test message"
assert ctx.steward_note == "Test note"
assert ctx.conversation_id == "conv_123"
def test_context_defaults(self):
"""Test orchestration context default values."""
ctx = OrchestrationContext(
user_message="Test",
steward_note="Note",
)
assert ctx.conversation_id is None
# ============================================================================
# Multi-Expert Coordination Tests
# ============================================================================
@pytest.mark.unit
class TestMultiExpertResult:
"""Tests for MultiExpertResult aggregation."""
def test_result_creation(self):
"""Test creating empty MultiExpertResult."""
result = MultiExpertResult()
assert result.results == {}
assert result.all_succeeded is True
assert result.failed_experts == []
assert result.combined_output == ""
def test_add_successful_result(self):
"""Test adding a successful result."""
result = MultiExpertResult()
delegation_result = DelegationResult(
expert_name="librarian",
task="search docs",
success=True,
output="Found docs",
)
result.add_result(delegation_result)
assert "librarian" in result.results
assert result.all_succeeded is True
assert result.failed_experts == []
def test_add_failed_result(self):
"""Test adding a failed result."""
result = MultiExpertResult()
delegation_result = DelegationResult(
expert_name="librarian",
task="search docs",
success=False,
output="",
error="Connection error",
)
result.add_result(delegation_result)
assert "librarian" in result.results
assert result.all_succeeded is False
assert "librarian" in result.failed_experts
def test_aggregate_outputs(self):
"""Test aggregating outputs from multiple experts."""
result = MultiExpertResult()
result.add_result(DelegationResult(
expert_name="librarian",
task="search docs",
success=True,
output="Found Docker docs",
))
result.add_result(DelegationResult(
expert_name="memory",
task="get preferences",
success=True,
output="User prefers dark mode",
))
combined = result.aggregate_outputs()
assert "Librarian" in combined
assert "Found Docker docs" in combined
assert "Memory" in combined
assert "dark mode" in combined
def test_aggregate_excludes_failed(self):
"""Test that failed results are excluded from aggregate."""
result = MultiExpertResult()
result.add_result(DelegationResult(
expert_name="librarian",
task="search",
success=True,
output="Success output",
))
result.add_result(DelegationResult(
expert_name="memory",
task="get",
success=False,
output="",
error="Failed",
))
combined = result.aggregate_outputs()
assert "Success output" in combined
assert "Failed" not in combined
@pytest.mark.unit
class TestExecuteSequential:
"""Tests for sequential multi-expert execution."""
@pytest.mark.asyncio
async def test_sequential_all_succeed(self):
"""Test sequential execution when all tasks succeed."""
tasks = [
DelegationTask(expert_name="librarian", task="task 1"),
DelegationTask(expert_name="memory", task="task 2"),
]
mock_results = [
DelegationResult(expert_name="librarian", task="task 1", success=True, output="Result 1"),
DelegationResult(expert_name="memory", task="task 2", success=True, output="Result 2"),
]
with patch(
"src.agents.orchestration.execute_delegation",
new_callable=AsyncMock,
side_effect=mock_results,
):
result = await execute_sequential(tasks)
assert result.all_succeeded is True
assert len(result.results) == 2
assert result.failed_experts == []
@pytest.mark.asyncio
async def test_sequential_with_failure(self):
"""Test sequential execution when a task fails."""
tasks = [
DelegationTask(expert_name="librarian", task="task 1"),
DelegationTask(expert_name="memory", task="task 2"),
]
mock_results = [
DelegationResult(expert_name="librarian", task="task 1", success=True, output="OK"),
DelegationResult(expert_name="memory", task="task 2", success=False, output="", error="Failed"),
]
with patch(
"src.agents.orchestration.execute_delegation",
new_callable=AsyncMock,
side_effect=mock_results,
):
result = await execute_sequential(tasks)
assert result.all_succeeded is False
assert len(result.results) == 2
assert "memory" in result.failed_experts
@pytest.mark.asyncio
async def test_sequential_stop_on_failure(self):
"""Test sequential execution stops on failure when configured."""
tasks = [
DelegationTask(expert_name="librarian", task="task 1"),
DelegationTask(expert_name="memory", task="task 2"),
DelegationTask(expert_name="librarian", task="task 3"),
]
mock_results = [
DelegationResult(expert_name="librarian", task="task 1", success=False, output="", error="Error"),
]
with patch(
"src.agents.orchestration.execute_delegation",
new_callable=AsyncMock,
side_effect=mock_results,
):
result = await execute_sequential(tasks, stop_on_failure=True)
# Should only have 1 result (stopped after first failure)
assert len(result.results) == 1
assert result.all_succeeded is False
@pytest.mark.unit
class TestExecuteParallel:
"""Tests for parallel multi-expert execution."""
@pytest.mark.asyncio
async def test_parallel_all_succeed(self):
"""Test parallel execution when all tasks succeed."""
tasks = [
DelegationTask(expert_name="librarian", task="task 1"),
DelegationTask(expert_name="memory", task="task 2"),
]
mock_results = [
DelegationResult(expert_name="librarian", task="task 1", success=True, output="Result 1"),
DelegationResult(expert_name="memory", task="task 2", success=True, output="Result 2"),
]
with patch(
"src.agents.orchestration.execute_delegation",
new_callable=AsyncMock,
side_effect=mock_results,
):
result = await execute_parallel(tasks)
assert result.all_succeeded is True
assert len(result.results) == 2
@pytest.mark.asyncio
async def test_parallel_with_failure(self):
"""Test parallel execution with partial failure."""
tasks = [
DelegationTask(expert_name="librarian", task="task 1"),
DelegationTask(expert_name="memory", task="task 2"),
]
mock_results = [
DelegationResult(expert_name="librarian", task="task 1", success=True, output="OK"),
DelegationResult(expert_name="memory", task="task 2", success=False, output="", error="Timeout"),
]
with patch(
"src.agents.orchestration.execute_delegation",
new_callable=AsyncMock,
side_effect=mock_results,
):
result = await execute_parallel(tasks)
assert result.all_succeeded is False
assert len(result.results) == 2
assert "memory" in result.failed_experts
@pytest.mark.asyncio
async def test_parallel_handles_exception(self):
"""Test parallel execution handles exceptions gracefully."""
tasks = [
DelegationTask(expert_name="librarian", task="task 1"),
DelegationTask(expert_name="memory", task="task 2"),
]
async def mock_execute(task):
if task.expert_name == "memory":
raise RuntimeError("Connection lost")
return DelegationResult(
expert_name=task.expert_name,
task=task.task,
success=True,
output="OK",
)
with patch(
"src.agents.orchestration.execute_delegation",
new_callable=AsyncMock,
side_effect=mock_execute,
):
result = await execute_parallel(tasks)
assert result.all_succeeded is False
assert "memory" in result.failed_experts
assert "Connection lost" in result.results["memory"].error
@pytest.mark.unit
class TestOrchestrateMultiExpert:
"""Tests for multi-expert orchestration with think updates."""
@pytest.mark.asyncio
async def test_orchestrate_sequential_emits_think_updates(self):
"""Test sequential orchestration emits think updates for each task."""
tasks = [
DelegationTask(expert_name="librarian", task="task 1"),
DelegationTask(expert_name="memory", task="task 2"),
]
mock_results = [
DelegationResult(expert_name="librarian", task="task 1", success=True, output="Result 1"),
DelegationResult(expert_name="memory", task="task 2", success=True, output="Result 2"),
]
with patch(
"src.agents.orchestration.execute_delegation",
new_callable=AsyncMock,
side_effect=mock_results,
):
updates = []
async for update in orchestrate_multi_expert(tasks, mode=ExecutionMode.SEQUENTIAL):
updates.append(update)
all_output = "".join(updates)
# Should have think updates for both experts
assert "Consulting" in all_output
assert "completed" in all_output
assert "Librarian" in all_output
@pytest.mark.asyncio
async def test_orchestrate_parallel_emits_think_updates(self):
"""Test parallel orchestration emits appropriate think updates."""
tasks = [
DelegationTask(expert_name="librarian", task="task 1"),
DelegationTask(expert_name="memory", task="task 2"),
]
mock_results = [
DelegationResult(expert_name="librarian", task="task 1", success=True, output="Result 1"),
DelegationResult(expert_name="memory", task="task 2", success=True, output="Result 2"),
]
with patch(
"src.agents.orchestration.execute_delegation",
new_callable=AsyncMock,
side_effect=mock_results,
):
updates = []
async for update in orchestrate_multi_expert(tasks, mode=ExecutionMode.PARALLEL):
updates.append(update)
all_output = "".join(updates)
# Should mention parallel execution
assert "parallel" in all_output
@pytest.mark.asyncio
async def test_orchestrate_empty_tasks_yields_nothing(self):
"""Test orchestration with empty tasks yields nothing."""
updates = []
async for update in orchestrate_multi_expert([]):
updates.append(update)
assert len(updates) == 0
@pytest.mark.asyncio
async def test_orchestrate_success_summary(self):
"""Test orchestration emits success summary when all succeed."""
tasks = [
DelegationTask(expert_name="librarian", task="task 1"),
]
mock_result = DelegationResult(
expert_name="librarian",
task="task 1",
success=True,
output="Done",
)
with patch(
"src.agents.orchestration.execute_delegation",
new_callable=AsyncMock,
return_value=mock_result,
):
updates = []
async for update in orchestrate_multi_expert(tasks):
updates.append(update)
all_output = "".join(updates)
# Should have success message
assert "🎉" in all_output or "successfully" in all_output.lower()
@pytest.mark.asyncio
async def test_orchestrate_failure_summary(self):
"""Test orchestration emits failure summary when some fail."""
tasks = [
DelegationTask(expert_name="librarian", task="task 1"),
]
mock_result = DelegationResult(
expert_name="librarian",
task="task 1",
success=False,
output="",
error="Failed",
)
with patch(
"src.agents.orchestration.execute_delegation",
new_callable=AsyncMock,
return_value=mock_result,
):
updates = []
async for update in orchestrate_multi_expert(tasks):
updates.append(update)
all_output = "".join(updates)
# Should mention failure
assert "⚠️" in all_output or "failed" in all_output.lower()
@pytest.mark.unit
class TestGetDisplayName:
"""Tests for _get_display_name helper."""
def test_librarian_display_name(self):
"""Test librarian gets 'The Librarian' display name."""
assert _get_display_name("librarian") == "The Librarian"
def test_memory_display_name(self):
"""Test memory gets 'Memory' display name."""
assert _get_display_name("memory") == "Memory"
def test_unknown_expert_title_case(self):
"""Test unknown expert gets title-cased name."""
assert _get_display_name("some_expert") == "Some_Expert"
assert _get_display_name("newagent") == "Newagent"