f41584e10b
* Refactor sub-agent architecture and introduce async support - Removed the legacy subagent.yaml file and replaced it with individual YAML files for each sub-agent in the subagents directory. - Updated the load_subagents function to support both directory and single file layouts for loading sub-agent configurations. - Added new langgraph_dev module for managing async sub-agent lifecycle and deployment. - Created graphs for async sub-agents (writing-agent, data-analysis-agent) and updated langgraph.json for deployment. - Introduced new sub-agent definitions for planner, research, debug, code, and writing agents with appropriate system prompts and configurations. - Enhanced package data inclusion in pyproject.toml to accommodate new sub-agent YAML files. * Refactor code for improved readability by consolidating conditional statements and formatting * feat: enhance async sub-agent support with workspace synchronization and user feedback - Added console status messages during async sub-agent server startup and workspace synchronization to improve user experience. - Implemented a new WorkspaceSyncWidget for live feedback during workspace sync operations. - Updated onboarding to reject occupied ports and ensure proper workspace handling for async sub-agents. - Introduced locking mechanisms to manage concurrent access to langgraph dev processes and workspace states. * feat: add async sub-agent configuration and server management functions * feat: improve port occupation handling and log file management in start_langgraph_dev * feat: enhance async sub-agent handling and introduce comprehensive tests - Updated `_maybe_swap_async_subagents` to improve async sub-agent management, ensuring internal flags are stripped before handoff. - Enhanced port management in `onboard.py` to allow reuse of occupied ports if already running by the same service. - Introduced file locking in `manager.py` to prevent race conditions during concurrent CLI invocations. - Added new tests for async sub-agent swapping and langgraph manager functionalities to ensure reliability and correctness. - Updated dependencies in `pyproject.toml` to include `psutil` and `filelock`. * fix(docs): clarify sub-agent configuration in README * test(manager): isolate _PID_DIR + tighten reuse-path assertion Addresses CodeRabbit review on tests/test_langgraph_manager.py: - Patch _PID_DIR to tmp_path so the FileLock setup in ensure_langgraph_dev doesn't mkdir the user's real ~/.config/evoscientist/ dir as a test side-effect. - Tighten "result is None or hasattr(result, 'poll')" to a strict "result is None" — the reuse path returns None unconditionally, so the OR clause was hiding potential regressions. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(manager): clean up stale PID file when unrelated process reuses PID * feat(tests): add validation tests for async flag in load_subagents * fix(load_subagents): restrict to .yaml files and clarify configuration handling * fix(load_subagents): improve error handling for non-dict specifications in YAML * feat(onboard): add "LangGraph Port" step to onboarding process * feat(langgraph): add concurrency configuration for langgraph dev workers * feat(async-subagents): enhance MCP tool routing for async sub-agents * fix(manager): update exception handling for connection errors and prevent zombie processes --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
142 lines
4.0 KiB
Python
142 lines
4.0 KiB
Python
"""Tests for ``EvoScientist.utils.load_subagents``.
|
|
|
|
Focused on schema-validation paths that are easy to silently misuse from
|
|
yaml — primarily the ``async:`` flag type check that prevents quoted-string
|
|
or integer values from being misinterpreted as booleans.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import textwrap
|
|
|
|
import pytest
|
|
|
|
from EvoScientist.utils import load_subagents
|
|
|
|
|
|
def _write_yaml(tmp_path, name: str, body: str):
|
|
"""Write ``body`` to ``tmp_path/name`` and return the directory path."""
|
|
(tmp_path / name).write_text(textwrap.dedent(body))
|
|
return tmp_path
|
|
|
|
|
|
def test_async_flag_accepts_real_bool(tmp_path):
|
|
"""``async: true`` (real yaml boolean) is accepted and carried through."""
|
|
config_path = _write_yaml(
|
|
tmp_path,
|
|
"writing.yaml",
|
|
"""
|
|
writing-agent:
|
|
description: Drafts reports
|
|
system_prompt: ""
|
|
tools: []
|
|
async: true
|
|
""",
|
|
)
|
|
subs = load_subagents(config_path, tool_registry={})
|
|
assert len(subs) == 1
|
|
assert subs[0]["name"] == "writing-agent"
|
|
assert subs[0]["_async"] is True
|
|
|
|
|
|
def test_async_flag_defaults_to_false_when_omitted(tmp_path):
|
|
"""No ``async:`` field → ``_async`` defaults to False."""
|
|
config_path = _write_yaml(
|
|
tmp_path,
|
|
"planner.yaml",
|
|
"""
|
|
planner-agent:
|
|
description: Plans experiments
|
|
system_prompt: ""
|
|
tools: []
|
|
""",
|
|
)
|
|
subs = load_subagents(config_path, tool_registry={})
|
|
assert subs[0]["_async"] is False
|
|
|
|
|
|
def test_async_flag_rejects_quoted_string(tmp_path):
|
|
"""``async: "false"`` (quoted) is a real user trap — bool("false") is True.
|
|
|
|
Without the explicit isinstance check, this would silently flip the agent
|
|
into async mode. We require the validator to fail loud instead.
|
|
"""
|
|
config_path = _write_yaml(
|
|
tmp_path,
|
|
"bad.yaml",
|
|
"""
|
|
bad-agent:
|
|
description: ""
|
|
system_prompt: ""
|
|
tools: []
|
|
async: "false"
|
|
""",
|
|
)
|
|
with pytest.raises(ValueError, match=r"'async' must be a boolean"):
|
|
load_subagents(config_path, tool_registry={})
|
|
|
|
|
|
def test_async_flag_rejects_integer(tmp_path):
|
|
"""``async: 1`` is also rejected — yaml integers are not booleans."""
|
|
config_path = _write_yaml(
|
|
tmp_path,
|
|
"bad.yaml",
|
|
"""
|
|
bad-agent:
|
|
description: ""
|
|
system_prompt: ""
|
|
tools: []
|
|
async: 1
|
|
""",
|
|
)
|
|
with pytest.raises(ValueError, match=r"'async' must be a boolean"):
|
|
load_subagents(config_path, tool_registry={})
|
|
|
|
|
|
def test_async_flag_error_includes_agent_name(tmp_path):
|
|
"""Error message must include the offending agent name for triage."""
|
|
config_path = _write_yaml(
|
|
tmp_path,
|
|
"bad.yaml",
|
|
"""
|
|
my-bad-agent:
|
|
description: ""
|
|
system_prompt: ""
|
|
tools: []
|
|
async: "yes"
|
|
""",
|
|
)
|
|
with pytest.raises(ValueError, match=r"my-bad-agent"):
|
|
load_subagents(config_path, tool_registry={})
|
|
|
|
|
|
def test_non_dict_spec_raises(tmp_path):
|
|
"""Yaml entries that aren't mappings must fail loud, not be silently dropped.
|
|
|
|
Previously ``_build_one`` had a ``if not isinstance(spec, dict): continue``
|
|
fallback that swallowed malformed entries — users would see their agent
|
|
quietly disappear with no error. Now caught during the merge loop.
|
|
"""
|
|
config_path = _write_yaml(
|
|
tmp_path,
|
|
"bad.yaml",
|
|
"""
|
|
bad-agent: 123
|
|
""",
|
|
)
|
|
with pytest.raises(ValueError, match=r"must map to a spec dict"):
|
|
load_subagents(config_path, tool_registry={})
|
|
|
|
|
|
def test_non_dict_spec_error_includes_filename_and_name(tmp_path):
|
|
"""Error must surface BOTH the offending file path and agent name."""
|
|
config_path = _write_yaml(
|
|
tmp_path,
|
|
"weird.yaml",
|
|
"""
|
|
weird-agent: "just a string"
|
|
""",
|
|
)
|
|
with pytest.raises(ValueError, match=r"weird\.yaml.*weird-agent"):
|
|
load_subagents(config_path, tool_registry={})
|