refactor(agents): delete dead coordination/streaming delegation stack

One delegation implementation remains (src/agents/delegation.py).
Removed, after verifying zero live importers post-Phase-A/B:

- src/agents/coordination.py: CoordinationEngine, duplicate
  delegate_to_librarian, AGENT_EXECUTORS/AGENT_STREAM_EXECUTORS
  (only importer was its own test module)
- run_librarian_stream: documented-broken path (Ollama streaming +
  tool call bug, PydanticAI #1292/#2256), only called by the deleted
  coordination engine
- stream_delegate_to_* wrappers + STREAMING_DELEGATION_WRAPPERS and
  the never-parsed __DELEGATION_RESULT__ marker in delegation.py
- HouseholdRegistry.get_streaming_delegation_tools() (no callers)
- tests/agents/test_coordination.py and the wrapper/stream tests

Note: the STREAMING_DELEGATION_WRAPPERS import in
src/responses/streaming.py was already removed by Phase A (7ce1c1a);
nothing to delete there.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01QbFZyDvYksazX6nYQYZ67L
This commit is contained in:
2026-07-14 11:52:36 +02:00
co-authored by Claude Fable 5
parent c00224222b
commit 31b948a748
9 changed files with 9 additions and 1018 deletions
+4
View File
@@ -7,6 +7,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
## [Unreleased]
### Removed
- **Dead delegation stack** - deleted the duplicate, never-wired coordination layer so exactly ONE delegation implementation remains (`src/agents/delegation.py`): `src/agents/coordination.py` (`CoordinationEngine`, its own `delegate_to_librarian`, `AGENT_EXECUTORS`/`AGENT_STREAM_EXECUTORS`), the broken-by-design `run_librarian_stream` path it used (Ollama streaming + tool call bug), the `stream_delegate_to_*` wrappers with their never-parsed `__DELEGATION_RESULT__` marker, and `HouseholdRegistry.get_streaming_delegation_tools()` (no callers)
### Added
- **Test-suite tenant guard** - `tests/conftest.py` hard-fails the whole pytest session (exit code 1, zero tests run) if the effective tenant resolves to the production tenant `jpmschweitzer`, mirroring the guard library-desk applies on its side. Suite-level assertions pin that the session runs under `llm_tester` namespaces (Qdrant `memories_llm_tester`, Redis `session:llm_tester:*`), and the e2e isolation constants now derive from the shared `TEST_TENANT`/`PRODUCTION_TENANT` config constants instead of string literals
-412
View File
@@ -1,412 +0,0 @@
"""
Multi-agent coordination engine.
Orchestrates delegation from Tatlock to expert agents (Librarian, etc.)
based on Steward recommendations. Handles:
- Routing tasks to appropriate agents
- Parallel and sequential execution
- Result aggregation
- Error handling and graceful degradation
"""
import asyncio
import time
from collections.abc import AsyncGenerator
from typing import Any
from src.agents.librarian import run_librarian, run_librarian_stream
from src.agents.protocol import (
AgentError,
AgentRequest,
AgentResponse,
AgentTimeoutError,
AgentUnavailableError,
CoordinationResult,
DelegationIntent,
DelegationReason,
)
from src.core.config import config
from src.core.household_registry import get_household_registry
from src.core.logging_config import get_logger
logger = get_logger(__name__)
# Agent execution functions registry
AGENT_EXECUTORS: dict[str, Any] = {
"librarian": run_librarian,
}
AGENT_STREAM_EXECUTORS: dict[str, Any] = {
"librarian": run_librarian_stream,
}
class CoordinationEngine:
"""
Coordinates multi-agent task execution.
Routes tasks from Tatlock to appropriate expert agents,
handles execution, and aggregates results.
"""
def __init__(self):
"""Initialize the coordination engine."""
self.registry = get_household_registry()
logger.info("coordination_engine_initialized")
def get_available_agents(self) -> list[str]:
"""
Get list of available expert agents.
Returns:
List of agent names that can accept delegations
"""
available = []
for name in self.registry.list_members():
member = self.registry.get_member(name)
if member and member.agent is not None:
available.append(name)
return available
def can_delegate_to(self, agent_name: str) -> bool:
"""
Check if delegation to an agent is possible.
Args:
agent_name: Name of the target agent
Returns:
True if agent is available and can accept tasks
"""
if agent_name not in AGENT_EXECUTORS:
return False
member = self.registry.get_member(agent_name)
return member is not None and member.agent is not None
async def execute_delegation(
self,
intent: DelegationIntent,
context: str = "",
message_history: list[Any] | None = None,
) -> AgentResponse:
"""
Execute a single delegation to an expert agent.
Args:
intent: The delegation intent with task details
context: Additional context for the agent
message_history: Optional conversation history
Returns:
AgentResponse with results
Raises:
AgentUnavailableError: If agent is not available
AgentTimeoutError: If execution times out
AgentError: For other execution errors
"""
start_time = time.time()
agent_name = intent.target_agent
logger.info(
"delegation_started",
agent=agent_name,
task=intent.task[:100],
reason=intent.reason.value,
)
# Check if agent is available
if not self.can_delegate_to(agent_name):
raise AgentUnavailableError(
f"Agent '{agent_name}' is not available for delegation",
agent_name=agent_name,
)
# Get the executor
executor = AGENT_EXECUTORS.get(agent_name)
if not executor:
raise AgentUnavailableError(
f"No executor found for agent '{agent_name}'",
agent_name=agent_name,
)
try:
# Build the request
request = AgentRequest(
task=intent.task,
context=context,
delegation_reason=intent.reason,
)
# Execute with timeout (explicit request value or configured budget)
timeout = request.timeout_seconds or config.LIBRARIAN_TIMEOUT
result = await asyncio.wait_for(
executor(
task=request.task,
context=request.context,
message_history=message_history,
),
timeout=timeout,
)
duration_ms = int((time.time() - start_time) * 1000)
logger.info(
"delegation_completed",
agent=agent_name,
duration_ms=duration_ms,
output_length=len(result),
)
return AgentResponse(
success=True,
result=result,
reasoning=f"Delegated to {agent_name}: {intent.expected_outcome}",
duration_ms=duration_ms,
)
except TimeoutError as e:
duration_ms = int((time.time() - start_time) * 1000)
logger.error(
"delegation_timeout",
agent=agent_name,
duration_ms=duration_ms,
)
raise AgentTimeoutError(
f"Agent '{agent_name}' timed out after {duration_ms}ms",
agent_name=agent_name,
) from e
except Exception as e:
duration_ms = int((time.time() - start_time) * 1000)
logger.error(
"delegation_error",
agent=agent_name,
error=str(e),
duration_ms=duration_ms,
exc_info=True,
)
return AgentResponse(
success=False,
result="",
error_message=str(e),
duration_ms=duration_ms,
)
async def execute_delegation_stream(
self,
intent: DelegationIntent,
context: str = "",
message_history: list[Any] | None = None,
) -> AsyncGenerator[str, None]:
"""
Execute a delegation with streaming output.
Args:
intent: The delegation intent with task details
context: Additional context for the agent
message_history: Optional conversation history
Yields:
Text deltas from the agent
Raises:
AgentUnavailableError: If agent is not available
"""
agent_name = intent.target_agent
logger.info(
"delegation_stream_started",
agent=agent_name,
task=intent.task[:100],
)
# Check if agent is available
if agent_name not in AGENT_STREAM_EXECUTORS:
raise AgentUnavailableError(
f"Agent '{agent_name}' does not support streaming",
agent_name=agent_name,
)
executor = AGENT_STREAM_EXECUTORS[agent_name]
try:
async for delta in executor(
task=intent.task,
context=context,
message_history=message_history,
):
yield delta
logger.info("delegation_stream_completed", agent=agent_name)
except Exception as e:
# Exception detail stays in the logs; yield a curated
# user-safe sentence instead of leaking internals.
from src.agents.delegation import get_think_message
logger.error(
"delegation_stream_error",
agent=agent_name,
error=str(e),
exc_info=True,
)
yield "\n\n" + get_think_message(agent_name, intent.task, "error")
async def coordinate(
self,
intents: list[DelegationIntent],
context: str = "",
message_history: list[Any] | None = None,
) -> CoordinationResult:
"""
Coordinate execution of multiple delegations.
Handles parallel execution for independent tasks and
sequential execution for dependent tasks.
Args:
intents: List of delegation intents to execute
context: Shared context for all agents
message_history: Optional conversation history
Returns:
CoordinationResult with aggregated results
"""
start_time = time.time()
agent_responses: dict[str, AgentResponse] = {}
agents_consulted: list[str] = []
logger.info(
"coordination_started",
intent_count=len(intents),
agents=[i.target_agent for i in intents],
)
# Sort by priority
sorted_intents = sorted(intents, key=lambda x: x.priority)
# Group by dependencies (simple version: sequential for now)
# TODO: Implement parallel execution for independent tasks
for intent in sorted_intents:
try:
response = await self.execute_delegation(
intent=intent,
context=context,
message_history=message_history,
)
agent_responses[intent.target_agent] = response
if response.success:
agents_consulted.append(intent.target_agent)
except AgentError as e:
agent_responses[intent.target_agent] = AgentResponse(
success=False,
result="",
error_message=str(e),
)
# Aggregate results
successful_results = [
r.result for r in agent_responses.values() if r.success and r.result
]
final_response = "\n\n---\n\n".join(successful_results) if successful_results else ""
total_duration = int((time.time() - start_time) * 1000)
logger.info(
"coordination_completed",
total_duration_ms=total_duration,
agents_consulted=agents_consulted,
success_count=len(successful_results),
)
return CoordinationResult(
final_response=final_response,
agent_responses=agent_responses,
delegation_intents=intents,
total_duration_ms=total_duration,
agents_consulted=agents_consulted,
)
# Global coordination engine instance
_coordination_engine: CoordinationEngine | None = None
def get_coordination_engine() -> CoordinationEngine:
"""Get the global coordination engine instance."""
global _coordination_engine
if _coordination_engine is None:
_coordination_engine = CoordinationEngine()
return _coordination_engine
async def delegate_to_librarian(
task: str,
context: str = "",
reason: DelegationReason = DelegationReason.DOMAIN_EXPERTISE,
message_history: list[Any] | None = None,
) -> AgentResponse:
"""
Convenience function to delegate a task to The Librarian.
Args:
task: Research task description
context: Additional context
reason: Why delegating to Librarian
message_history: Optional conversation history
Returns:
AgentResponse with research results
"""
engine = get_coordination_engine()
intent = DelegationIntent(
target_agent="librarian",
task=task,
reason=reason,
expected_outcome="Research findings and relevant information",
)
return await engine.execute_delegation(
intent=intent,
context=context,
message_history=message_history,
)
async def delegate_to_librarian_stream(
task: str,
context: str = "",
message_history: list[Any] | None = None,
) -> AsyncGenerator[str, None]:
"""
Convenience function to delegate to Librarian with streaming.
Args:
task: Research task description
context: Additional context
message_history: Optional conversation history
Yields:
Text deltas from The Librarian
"""
engine = get_coordination_engine()
intent = DelegationIntent(
target_agent="librarian",
task=task,
reason=DelegationReason.DOMAIN_EXPERTISE,
expected_outcome="Research findings",
)
async for delta in engine.execute_delegation_stream(
intent=intent,
context=context,
message_history=message_history,
):
yield delta
-98
View File
@@ -9,7 +9,6 @@ This implements the agent-as-tool pattern recommended by PydanticAI:
agents call other agents via tool wrappers, keeping each agent focused.
"""
import asyncio
from collections.abc import AsyncGenerator
from dataclasses import dataclass, field
from enum import Enum
@@ -572,103 +571,6 @@ async def delegate_to_housekeeper(
)
# =============================================================================
# Streaming Delegation Wrappers (with Think Messages)
# =============================================================================
async def stream_delegate_to_librarian(
task: str,
context: str = "",
) -> AsyncGenerator[str, None]:
"""
Stream delegation to Librarian with automatic think messages.
Yields butler-perspective think messages before and after the delegation,
allowing the UI to show progress to the user.
Args:
task: Task description
context: Additional context
Yields:
str: Think messages and final result marker
"""
# Yield start message (deterministic)
yield get_think_message("librarian", task, "start") + "\n"
# Execute delegation
result = await delegate_to_librarian(task, context)
# Yield completion message (deterministic)
if result.success:
yield get_think_message("librarian", task, "success") + "\n"
else:
yield get_think_message("librarian", task, "error") + "\n"
# Yield result marker for extraction
yield f"__DELEGATION_RESULT__:librarian:{result.output}"
async def stream_delegate_to_biographer(
task: str,
context: str = "",
) -> AsyncGenerator[str, None]:
"""
Stream delegation to Biographer with automatic think messages.
Args:
task: Task description
context: Additional context
Yields:
str: Think messages and final result marker
"""
yield get_think_message("biographer", task, "start") + "\n"
result = await delegate_to_biographer(task, context)
if result.success:
yield get_think_message("biographer", task, "success") + "\n"
else:
yield get_think_message("biographer", task, "error") + "\n"
yield f"__DELEGATION_RESULT__:biographer:{result.output}"
async def stream_delegate_to_housekeeper(
task: str,
context: str = "",
) -> AsyncGenerator[str, None]:
"""
Stream delegation to Housekeeper with automatic think messages.
Args:
task: Task description
context: Additional context
Yields:
str: Think messages and final result marker
"""
yield get_think_message("housekeeper", task, "start") + "\n"
result = await delegate_to_housekeeper(task, context)
if result.success:
yield get_think_message("housekeeper", task, "success") + "\n"
else:
yield get_think_message("housekeeper", task, "error") + "\n"
yield f"__DELEGATION_RESULT__:housekeeper:{result.output}"
# Mapping of streaming delegation wrappers
STREAMING_DELEGATION_WRAPPERS = {
"librarian": stream_delegate_to_librarian,
"biographer": stream_delegate_to_biographer,
"housekeeper": stream_delegate_to_housekeeper,
}
# Future expert delegation wrappers will be added here:
# - delegate_to_developer(task, context) -> DelegationResult
# - delegate_to_secretary(task, context) -> DelegationResult
-2
View File
@@ -10,7 +10,6 @@ Connects to the library-desk API to provide:
from src.agents.librarian.agent import (
get_librarian_agent,
run_librarian,
run_librarian_stream,
)
from src.agents.librarian.capability import (
LIBRARIAN_CAPABILITY,
@@ -26,5 +25,4 @@ __all__ = [
"register_librarian",
"unregister_librarian",
"run_librarian",
"run_librarian_stream",
]
-64
View File
@@ -273,67 +273,3 @@ async def run_librarian(
raise AgentError(
"Research task failed", agent_name="librarian"
) from e
async def run_librarian_stream(
task: str,
context: str = "",
message_history: list[Any] | None = None,
):
"""
Execute a research task with streaming output.
Yields text deltas as The Librarian generates the response.
Args:
task: The research task or question
context: Additional context from conversation
message_history: Optional conversation history
Yields:
str: Text deltas from the response
Raises:
AgentError: If the research task fails. Exception detail is
logged here; callers map the failure to a user-safe message.
Example:
async for delta in run_librarian_stream("Find Docker docs"):
print(delta, end="", flush=True)
"""
agent = get_librarian_agent()
# Build prompt with context if provided
prompt = task
if context:
prompt = f"Context: {context}\n\nTask: {task}"
logger.info(
"librarian_stream_started",
task=task[:100],
)
try:
# One shared library-desk connection for all tool calls in this run
async with library_client_session():
async with agent.run_stream(
prompt,
message_history=message_history,
) as response:
async for delta in response.stream_text(delta=True):
yield delta
logger.info("librarian_stream_completed", task=task[:50])
except Exception as e:
# Full detail stays in the logs; raise instead of yielding error
# text into the stream as if it were research output.
logger.error(
"librarian_stream_error",
task=task[:50],
error=str(e),
exc_info=True,
)
raise AgentError(
"Research task failed", agent_name="librarian"
) from e
-59
View File
@@ -273,65 +273,6 @@ class HouseholdRegistry:
return tools
def get_streaming_delegation_tools(self, names: list[str]) -> list[Any]:
"""
Get streaming delegation wrapper tools for specified capabilities.
Similar to get_delegation_tools() but returns streaming wrappers
that yield butler-perspective think messages during execution.
These wrappers emit think slugs like:
- "Allow me to consult the archives, sir."
- "The Librarian has compiled the relevant findings."
Args:
names: List of member names to include
Returns:
List of streaming delegation wrappers and/or raw tools
Example:
>>> tools = registry.get_streaming_delegation_tools(["librarian"])
>>> async for chunk in tools[0](task="Search for Docker"):
... print(chunk) # Yields think messages then result
"""
from src.agents.delegation import STREAMING_DELEGATION_WRAPPERS
tools = []
for name in names:
member = self._members.get(name)
if not member:
logger.warning(
"household_member_not_found",
requested_name=name,
available_names=list(self._members.keys()),
)
continue
# Check if this member has a streaming delegation wrapper
if name in STREAMING_DELEGATION_WRAPPERS and member.agent is not None:
tools.append(STREAMING_DELEGATION_WRAPPERS[name])
logger.debug(
"streaming_delegation_wrapper_added",
member=name,
)
else:
# No agent = direct tools (e.g., tatlock_core)
tools.extend(member.tools)
logger.debug(
"raw_tools_added",
member=name,
tool_count=len(member.tools),
)
logger.info(
"streaming_delegation_tools_created",
requested_members=names,
total_tools=len(tools),
)
return tools
def list_members(self) -> list[str]:
"""
List all registered member names.
+5 -26
View File
@@ -1,16 +1,16 @@
"""
Tests for structured failure behavior of The Librarian entry points.
Tests for structured failure behavior of The Librarian entry point.
run_librarian and run_librarian_stream must raise AgentError on failure
instead of returning/yielding error text as if it were research output,
and the raised error must not leak exception detail (internal URLs etc.).
run_librarian must raise AgentError on failure instead of returning
error text as if it were research output, and the raised error must
not leak exception detail (internal URLs etc.).
"""
from unittest.mock import AsyncMock, MagicMock, patch
import pytest
from src.agents.librarian.agent import run_librarian, run_librarian_stream
from src.agents.librarian.agent import run_librarian
from src.agents.protocol import AgentError
@@ -37,24 +37,3 @@ class TestRunLibrarianFailures:
# Exception detail stays in logs only
assert "internal" not in str(exc_info.value)
assert "Connection refused" not in str(exc_info.value)
@pytest.mark.asyncio
async def test_run_librarian_stream_raises_agent_error(self):
"""Streaming failures raise instead of yielding error text."""
mock_agent = MagicMock()
mock_agent.run_stream = MagicMock(
side_effect=RuntimeError("Connection refused to http://internal:8089")
)
with patch(
"src.agents.librarian.agent.get_librarian_agent",
return_value=mock_agent,
):
collected: list[str] = []
with pytest.raises(AgentError) as exc_info:
async for delta in run_librarian_stream(task="Find Docker docs"):
collected.append(delta)
assert exc_info.value.agent_name == "librarian"
assert collected == [], "no error text may be yielded as output"
assert "internal" not in str(exc_info.value)
-339
View File
@@ -1,339 +0,0 @@
"""
Tests for multi-agent coordination engine.
"""
import pytest
from unittest.mock import AsyncMock, MagicMock, patch
from src.agents.coordination import (
CoordinationEngine,
get_coordination_engine,
delegate_to_librarian,
)
from src.agents.protocol import (
AgentResponse,
AgentUnavailableError,
DelegationIntent,
DelegationReason,
)
@pytest.fixture
def coordination_engine():
"""Create a fresh coordination engine for testing."""
return CoordinationEngine()
@pytest.fixture
def mock_registry():
"""Mock the household registry."""
with patch("src.agents.coordination.get_household_registry") as mock:
registry = MagicMock()
mock.return_value = registry
yield registry
@pytest.fixture
def librarian_intent():
"""Create a standard librarian delegation intent."""
return DelegationIntent(
target_agent="librarian",
task="Find information about Docker networking",
reason=DelegationReason.DOMAIN_EXPERTISE,
expected_outcome="Documentation and examples",
)
@pytest.mark.unit
class TestCoordinationEngine:
"""Tests for CoordinationEngine class."""
def test_initialization(self, coordination_engine):
"""Test engine initializes correctly."""
assert coordination_engine is not None
assert coordination_engine.registry is not None
def test_get_available_agents_empty(self, mock_registry):
"""Test getting available agents when none have agents."""
mock_registry.list_members.return_value = ["tatlock_core"]
mock_member = MagicMock()
mock_member.agent = None # No agent
mock_registry.get_member.return_value = mock_member
engine = CoordinationEngine()
available = engine.get_available_agents()
assert available == []
def test_get_available_agents_with_librarian(self, mock_registry):
"""Test getting available agents with librarian registered."""
mock_registry.list_members.return_value = ["tatlock_core", "librarian"]
# tatlock_core has no agent
core_member = MagicMock()
core_member.agent = None
# librarian has an agent
librarian_member = MagicMock()
librarian_member.agent = MagicMock()
def get_member_side_effect(name):
if name == "tatlock_core":
return core_member
elif name == "librarian":
return librarian_member
return None
mock_registry.get_member.side_effect = get_member_side_effect
engine = CoordinationEngine()
available = engine.get_available_agents()
assert "librarian" in available
assert "tatlock_core" not in available
def test_can_delegate_to_unknown_agent(self, mock_registry):
"""Test checking delegation to unknown agent."""
mock_registry.get_member.return_value = None
engine = CoordinationEngine()
assert engine.can_delegate_to("unknown_agent") is False
def test_can_delegate_to_librarian(self, mock_registry):
"""Test checking delegation to librarian."""
mock_member = MagicMock()
mock_member.agent = MagicMock() # Has an agent
mock_registry.get_member.return_value = mock_member
engine = CoordinationEngine()
assert engine.can_delegate_to("librarian") is True
@pytest.mark.unit
class TestDelegationExecution:
"""Tests for delegation execution."""
@pytest.mark.asyncio
async def test_execute_delegation_unavailable_agent(
self, mock_registry, librarian_intent
):
"""Test delegation fails for unavailable agent."""
mock_registry.get_member.return_value = None
engine = CoordinationEngine()
with pytest.raises(AgentUnavailableError) as exc_info:
await engine.execute_delegation(librarian_intent)
assert "librarian" in str(exc_info.value)
@pytest.mark.asyncio
async def test_execute_delegation_success(
self, mock_registry, librarian_intent
):
"""Test successful delegation execution."""
# Setup mock member with agent
mock_member = MagicMock()
mock_member.agent = MagicMock()
mock_registry.get_member.return_value = mock_member
# Mock the executor
with patch(
"src.agents.coordination.AGENT_EXECUTORS",
{"librarian": AsyncMock(return_value="Research results here")},
):
engine = CoordinationEngine()
response = await engine.execute_delegation(librarian_intent)
assert response.success is True
assert response.result == "Research results here"
# Duration might be 0 for very fast mock execution
assert response.duration_ms >= 0
@pytest.mark.asyncio
async def test_execute_delegation_error(
self, mock_registry, librarian_intent
):
"""Test delegation handles executor errors."""
mock_member = MagicMock()
mock_member.agent = MagicMock()
mock_registry.get_member.return_value = mock_member
# Mock executor that raises
async def failing_executor(**kwargs):
raise ValueError("API connection failed")
with patch(
"src.agents.coordination.AGENT_EXECUTORS",
{"librarian": failing_executor},
):
engine = CoordinationEngine()
response = await engine.execute_delegation(librarian_intent)
assert response.success is False
assert "API connection failed" in response.error_message
@pytest.mark.unit
class TestCoordinate:
"""Tests for multi-agent coordination."""
@pytest.mark.asyncio
async def test_coordinate_single_intent(self, mock_registry, librarian_intent):
"""Test coordinating a single delegation."""
mock_member = MagicMock()
mock_member.agent = MagicMock()
mock_registry.get_member.return_value = mock_member
with patch(
"src.agents.coordination.AGENT_EXECUTORS",
{"librarian": AsyncMock(return_value="Found docs")},
):
engine = CoordinationEngine()
result = await engine.coordinate([librarian_intent])
assert result.final_response == "Found docs"
assert "librarian" in result.agents_consulted
# Duration might be 0 for very fast mock execution
assert result.total_duration_ms >= 0
@pytest.mark.asyncio
async def test_coordinate_empty_intents(self, mock_registry):
"""Test coordinating with no intents."""
engine = CoordinationEngine()
result = await engine.coordinate([])
assert result.final_response == ""
assert result.agents_consulted == []
@pytest.mark.asyncio
async def test_coordinate_multiple_intents(self, mock_registry):
"""Test coordinating multiple delegations."""
mock_member = MagicMock()
mock_member.agent = MagicMock()
mock_registry.get_member.return_value = mock_member
intents = [
DelegationIntent(
target_agent="librarian",
task="Task 1",
reason=DelegationReason.DOMAIN_EXPERTISE,
expected_outcome="Result 1",
priority=1,
),
DelegationIntent(
target_agent="librarian",
task="Task 2",
reason=DelegationReason.DOMAIN_EXPERTISE,
expected_outcome="Result 2",
priority=2,
),
]
call_count = 0
async def mock_executor(**kwargs):
nonlocal call_count
call_count += 1
return f"Result {call_count}"
with patch(
"src.agents.coordination.AGENT_EXECUTORS",
{"librarian": mock_executor},
):
engine = CoordinationEngine()
result = await engine.coordinate(intents)
# Both intents were executed (check agents_consulted count)
assert len(result.agents_consulted) == 2
# Current implementation replaces same-agent responses in dict
# So final_response has the last result (or combined if different agents)
assert len(result.final_response) > 0
@pytest.mark.unit
class TestDelegateToLibrarian:
"""Tests for convenience delegation function."""
@pytest.mark.asyncio
async def test_delegate_to_librarian(self, mock_registry):
"""Test the delegate_to_librarian helper."""
mock_member = MagicMock()
mock_member.agent = MagicMock()
mock_registry.get_member.return_value = mock_member
with patch(
"src.agents.coordination.AGENT_EXECUTORS",
{"librarian": AsyncMock(return_value="Wiki search results")},
):
# Reset global engine
with patch(
"src.agents.coordination._coordination_engine",
None,
):
response = await delegate_to_librarian(
task="Search for Docker docs",
context="Setting up homelab",
)
assert response.success is True
assert response.result == "Wiki search results"
@pytest.mark.unit
class TestGetCoordinationEngine:
"""Tests for engine singleton."""
def test_get_coordination_engine_singleton(self):
"""Test engine is singleton."""
with patch("src.agents.coordination._coordination_engine", None):
engine1 = get_coordination_engine()
engine2 = get_coordination_engine()
# Should be same instance
assert engine1 is engine2
@pytest.mark.unit
class TestDelegationStreaming:
"""Tests for streaming delegation."""
@pytest.mark.asyncio
async def test_execute_delegation_stream_unavailable(
self, mock_registry, librarian_intent
):
"""Test streaming fails for unavailable agent."""
engine = CoordinationEngine()
# Change target to an agent that doesn't have a stream executor
librarian_intent.target_agent = "nonexistent_agent"
with pytest.raises(AgentUnavailableError):
async for _ in engine.execute_delegation_stream(librarian_intent):
pass
@pytest.mark.asyncio
async def test_execute_delegation_stream_success(
self, mock_registry, librarian_intent
):
"""Test successful streaming delegation."""
mock_member = MagicMock()
mock_member.agent = MagicMock()
mock_registry.get_member.return_value = mock_member
async def mock_stream(**kwargs):
yield "Hello "
yield "world"
with patch(
"src.agents.coordination.AGENT_STREAM_EXECUTORS",
{"librarian": mock_stream},
):
engine = CoordinationEngine()
chunks = []
async for chunk in engine.execute_delegation_stream(librarian_intent):
chunks.append(chunk)
assert chunks == ["Hello ", "world"]
-18
View File
@@ -10,7 +10,6 @@ import pytest
from src.agents.delegation import (
HOUSEHOLD_THINK_MESSAGES,
STREAMING_DELEGATION_WRAPPERS,
ActionType,
DelegationResult,
DelegationTask,
@@ -430,20 +429,3 @@ class TestGetThinkMessage:
msg = get_think_message("unknown_expert", "some task", "start")
assert "<think>" not 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"