mirror of
https://github.com/pewdiepie-archdaemon/odysseus.git
synced 2026-10-15 11:22:21 +02:00
Alexandre Teixeira
b2e717e28f
* refactor(skills): extract evaluation and audit orchestration * chore(security): scope OpenAPI digest Gitleaks exception * refactor(skills): establish domain-oriented service boundaries * refactor(skills): address architecture review feedback * fix(skills): restore prompt seams and harden signature contracts * test(skills): restore ReDoS coverage and simplify API baseline
486 lines
22 KiB
Python
486 lines
22 KiB
Python
"""Offline contracts captured against the merged skills baseline before extraction."""
|
|
import asyncio
|
|
from dataclasses import fields, is_dataclass
|
|
from difflib import unified_diff
|
|
import inspect
|
|
import json
|
|
from contextvars import ContextVar
|
|
from pathlib import Path
|
|
from typing import Annotated, get_args, get_origin
|
|
|
|
import pytest
|
|
from fastapi import FastAPI
|
|
from starlette.requests import Request
|
|
|
|
from routes import skills_routes as routes
|
|
|
|
|
|
FIXTURES = Path(__file__).parent / 'fixtures'
|
|
|
|
|
|
def _qualified_name(value):
|
|
return f'{value.__module__}.{value.__qualname__}'
|
|
|
|
|
|
def _value_contract(value):
|
|
if value is inspect.Signature.empty:
|
|
return {'empty': True}
|
|
if value is None or type(value) in (bool, int, float, str):
|
|
return {'type': _qualified_name(type(value)), 'value': value}
|
|
if type(value) in (list, tuple):
|
|
return {'type': _qualified_name(type(value)),
|
|
'items': [_value_contract(item) for item in value]}
|
|
if type(value) is dict and all(type(key) is str for key in value):
|
|
return {'type': 'builtins.dict',
|
|
'items': {key: _value_contract(item) for key, item in value.items()}}
|
|
if is_dataclass(value) and not isinstance(value, type):
|
|
return {'type': _qualified_name(type(value)), 'fields': {
|
|
field.name: _value_contract(getattr(value, field.name))
|
|
for field in fields(value)
|
|
}}
|
|
raise TypeError(f'Unsupported contract value: {type(value)}')
|
|
|
|
|
|
def _annotation_contract(annotation):
|
|
if annotation is inspect.Signature.empty or annotation is None:
|
|
return _value_contract(annotation)
|
|
origin = get_origin(annotation)
|
|
if origin is Annotated:
|
|
base, *metadata = get_args(annotation)
|
|
return {'origin': _qualified_name(origin),
|
|
'annotation': _annotation_contract(base),
|
|
'metadata': [_value_contract(item) for item in metadata]}
|
|
if origin is not None:
|
|
return {'origin': _qualified_name(origin), 'module': annotation.__module__,
|
|
'arguments': [_annotation_contract(arg) for arg in get_args(annotation)]}
|
|
return {'type': _qualified_name(annotation)}
|
|
|
|
|
|
def _factory_contract(factory):
|
|
# Names do not identify closure state, partial arguments or arbitrary code.
|
|
# Only these known builtin constructors have a supported default contract.
|
|
if not any(factory is builtin for builtin in (list, tuple, dict, set, frozenset)):
|
|
raise TypeError('Unsupported default factory; requires an explicit compatibility contract')
|
|
return _qualified_name(factory)
|
|
|
|
|
|
def _signature_contract(target):
|
|
"""Freeze supported constructor structure without executing default factories."""
|
|
signature = inspect.signature(target)
|
|
model_fields = getattr(target, 'model_fields', {})
|
|
parameters = []
|
|
for parameter in signature.parameters.values():
|
|
field = model_fields.get(parameter.name)
|
|
if field is not None and field.default_factory is not None:
|
|
default = {'factory': _factory_contract(field.default_factory),
|
|
'marker': _qualified_name(type(parameter.default))}
|
|
else:
|
|
default = _value_contract(parameter.default)
|
|
parameters.append({'name': parameter.name, 'kind': parameter.kind.name,
|
|
'annotation': _annotation_contract(parameter.annotation),
|
|
'default': default})
|
|
contract = {'parameters': parameters,
|
|
'return': _annotation_contract(signature.return_annotation)}
|
|
if model_fields:
|
|
# Field names can be absent from the Python signature (validation aliases).
|
|
# These public FieldInfo attributes affect input validation independently
|
|
# of the generated signature and JSON schema. Rebuilt annotations retain
|
|
# field metadata, including constraints and strict/union validation modes.
|
|
contract['model_fields'] = {
|
|
name: {
|
|
'annotation': _annotation_contract(field.rebuild_annotation()),
|
|
'default': ({'factory': _factory_contract(field.default_factory),
|
|
'takes_validated_data': field.default_factory_takes_validated_data}
|
|
if field.default_factory is not None else
|
|
_value_contract(inspect.Signature.empty if field.is_required() else field.default)),
|
|
'validation': {attribute: _value_contract(getattr(field, attribute))
|
|
for attribute in ('alias', 'alias_priority', 'validation_alias',
|
|
'discriminator', 'validate_default')},
|
|
}
|
|
for name, field in model_fields.items()
|
|
}
|
|
# Includes inherited model settings such as validate_default and strict.
|
|
# Unsupported callables or values fail closed through _value_contract.
|
|
contract['model_config'] = _value_contract(target.model_config)
|
|
return contract
|
|
|
|
|
|
def _canonical_openapi(schema):
|
|
return json.dumps(schema, sort_keys=True, indent=2, ensure_ascii=True) + '\n'
|
|
|
|
|
|
def _assert_openapi_matches_baseline(schema):
|
|
expected = (FIXTURES / 'skills_openapi_baseline.json').read_text(encoding='utf-8')
|
|
actual = _canonical_openapi(schema)
|
|
if actual != expected:
|
|
baseline = json.loads(expected)
|
|
affected = []
|
|
for label, before, after in [
|
|
('paths', baseline.get('paths', {}), schema.get('paths', {})),
|
|
('schemas', baseline.get('components', {}).get('schemas', {}),
|
|
schema.get('components', {}).get('schemas', {})),
|
|
]:
|
|
changed = [key for key in sorted(before.keys() | after.keys())
|
|
if _canonical_openapi(before.get(key)) != _canonical_openapi(after.get(key))]
|
|
if changed:
|
|
affected.append(f'Changed {label}: {", ".join(changed)}\n')
|
|
pytest.fail('OpenAPI contract changed:\n' + ''.join(affected) + ''.join(unified_diff(
|
|
expected.splitlines(keepends=True), actual.splitlines(keepends=True),
|
|
fromfile='skills_openapi_baseline.json', tofile='generated OpenAPI',
|
|
)))
|
|
|
|
|
|
def endpoint(method, path, manager=None):
|
|
return next(r.endpoint for r in routes.setup_skills_routes(manager).routes
|
|
if method in r.methods and r.path == '/api/skills' + path)
|
|
|
|
|
|
def request(owner='alice', body=None):
|
|
async def receive():
|
|
return {'type': 'http.request', 'body': json.dumps(body or {}).encode()}
|
|
return Request({'type': 'http', 'method': 'POST', 'path': '/',
|
|
'headers': [(b'content-type', b'application/json')],
|
|
'state': {'user': owner}}, receive)
|
|
|
|
|
|
def test_api_and_python_signatures_match_baseline():
|
|
baseline = json.loads((FIXTURES / 'skills_api_baseline.json').read_text(encoding='utf-8'))
|
|
app = FastAPI()
|
|
router = routes.setup_skills_routes(object())
|
|
app.include_router(router)
|
|
schema = app.openapi()
|
|
_assert_openapi_matches_baseline(schema)
|
|
declarations = [[sorted(r.methods), r.path, r.name] for r in router.routes]
|
|
assert declarations == baseline['routes']
|
|
for name, signature in baseline['signatures'].items():
|
|
assert _signature_contract(getattr(routes, name)) == signature, name
|
|
|
|
|
|
def test_signature_contract_ignores_annotated_repr(monkeypatch):
|
|
target = routes.SkillImportUrlRequest
|
|
before = _signature_contract(target)
|
|
annotation = inspect.signature(target).parameters['url'].annotation
|
|
monkeypatch.setattr(type(annotation), '__repr__', lambda self: 'different Python rendering')
|
|
assert _signature_contract(target) == before
|
|
|
|
|
|
@pytest.mark.parametrize('change', ['name', 'order', 'kind', 'default', 'annotation', 'return'])
|
|
def test_signature_contract_detects_interface_changes(change):
|
|
def original(first: str, second: int = 1) -> bool:
|
|
pass
|
|
signature = inspect.signature(original)
|
|
first, second = signature.parameters.values()
|
|
parameters = [first, second]
|
|
if change == 'order':
|
|
parameters = [second.replace(default=inspect.Parameter.empty),
|
|
first.replace(default='')]
|
|
elif change == 'return':
|
|
signature = signature.replace(return_annotation=str)
|
|
else:
|
|
changes = {
|
|
'name': {'name': 'renamed'},
|
|
'kind': {'kind': inspect.Parameter.KEYWORD_ONLY},
|
|
'default': {'default': 2},
|
|
'annotation': {'annotation': float},
|
|
}
|
|
parameters[1] = second.replace(**changes[change])
|
|
def changed():
|
|
pass
|
|
changed.__signature__ = signature.replace(parameters=parameters)
|
|
assert _signature_contract(changed) != _signature_contract(original)
|
|
|
|
|
|
@pytest.mark.parametrize('change', ['constraint', 'factory'])
|
|
def test_signature_contract_detects_model_changes(change):
|
|
from pydantic import BaseModel, Field
|
|
|
|
class Original(BaseModel):
|
|
text: str = Field(max_length=8)
|
|
tags: list[str] = Field(default_factory=list)
|
|
|
|
class Changed(BaseModel):
|
|
text: str = Field(max_length=9 if change == 'constraint' else 8)
|
|
tags: list[str] = Field(default_factory=tuple if change == 'factory' else list)
|
|
|
|
assert _signature_contract(Changed) != _signature_contract(Original)
|
|
|
|
|
|
@pytest.mark.parametrize('validated_data', [False, True])
|
|
def test_signature_contract_rejects_custom_factories_without_calling_them(validated_data):
|
|
from pydantic import BaseModel, Field
|
|
|
|
calls = []
|
|
def make_factory(value):
|
|
def plain():
|
|
calls.append(value)
|
|
return [value]
|
|
def with_data(data):
|
|
calls.append(value)
|
|
return [data['prefix'], value]
|
|
return with_data if validated_data else plain
|
|
|
|
class Before(BaseModel):
|
|
prefix: str = 'validated'
|
|
tags: list[str] = Field(default_factory=make_factory('before'))
|
|
|
|
class After(BaseModel):
|
|
prefix: str = 'validated'
|
|
tags: list[str] = Field(default_factory=make_factory('after'))
|
|
|
|
assert Before().tags != After().tags
|
|
assert Before.model_fields['tags'].default_factory_takes_validated_data is validated_data
|
|
calls.clear()
|
|
for model in (Before, After):
|
|
with pytest.raises(TypeError, match='Unsupported default factory'):
|
|
_signature_contract(model)
|
|
assert calls == []
|
|
|
|
|
|
def test_signature_contract_detects_default_validation_outside_signature_and_openapi():
|
|
from pydantic import BaseModel, Field, ValidationError
|
|
|
|
class Before(BaseModel):
|
|
count: int = Field(default='invalid', validate_default=False)
|
|
|
|
class After(BaseModel):
|
|
count: int = Field(default='invalid', validate_default=True)
|
|
|
|
assert Before().count == 'invalid'
|
|
with pytest.raises(ValidationError):
|
|
After()
|
|
assert inspect.signature(Before) == inspect.signature(After)
|
|
before_schema, after_schema = Before.model_json_schema(), After.model_json_schema()
|
|
before_schema.pop('title')
|
|
after_schema.pop('title')
|
|
assert before_schema == after_schema
|
|
assert _signature_contract(Before) != _signature_contract(After)
|
|
|
|
|
|
def test_signature_contract_detects_validation_alias_paths():
|
|
from pydantic import AliasPath, BaseModel, Field, ValidationError
|
|
|
|
class Before(BaseModel):
|
|
count: int = Field(validation_alias=AliasPath('before', 0))
|
|
|
|
class After(BaseModel):
|
|
count: int = Field(validation_alias=AliasPath('after', 0))
|
|
|
|
assert Before(before=[1]).count == 1
|
|
with pytest.raises(ValidationError):
|
|
After(before=[1])
|
|
assert inspect.signature(Before) == inspect.signature(After)
|
|
before_schema, after_schema = Before.model_json_schema(), After.model_json_schema()
|
|
before_schema.pop('title')
|
|
after_schema.pop('title')
|
|
assert before_schema == after_schema
|
|
assert _signature_contract(Before) != _signature_contract(After)
|
|
|
|
|
|
@pytest.mark.parametrize('setting', ['validate_default', 'strict'])
|
|
def test_signature_contract_detects_model_validation_configuration(setting):
|
|
from pydantic import BaseModel, ConfigDict, ValidationError
|
|
|
|
class Before(BaseModel):
|
|
model_config = ConfigDict({setting: False})
|
|
count: int = 'invalid' if setting == 'validate_default' else 1
|
|
|
|
class After(BaseModel):
|
|
model_config = ConfigDict({setting: True})
|
|
count: int = 'invalid' if setting == 'validate_default' else 1
|
|
|
|
data = {} if setting == 'validate_default' else {'count': '1'}
|
|
Before(**data)
|
|
with pytest.raises(ValidationError):
|
|
After(**data)
|
|
assert inspect.signature(Before) == inspect.signature(After)
|
|
assert _signature_contract(Before) != _signature_contract(After)
|
|
|
|
|
|
def test_openapi_golden_is_canonical():
|
|
golden = (FIXTURES / 'skills_openapi_baseline.json').read_text(encoding='utf-8')
|
|
schema = json.loads(golden)
|
|
assert golden == _canonical_openapi(schema)
|
|
|
|
|
|
@pytest.mark.parametrize('section, key', [
|
|
('paths', '/api/skills/add'), ('schemas', 'SkillAddRequest'),
|
|
])
|
|
def test_openapi_failure_identifies_changed_endpoint_or_schema(section, key):
|
|
schema = json.loads((FIXTURES / 'skills_openapi_baseline.json').read_text(encoding='utf-8'))
|
|
target = schema['paths'] if section == 'paths' else schema['components']['schemas']
|
|
if section == 'paths':
|
|
target[key]['post']['responses']['200']['description'] = 'changed contract'
|
|
else:
|
|
target[key]['properties']['solution']['anyOf'][0]['maxLength'] = 4999
|
|
with pytest.raises(pytest.fail.Exception) as failure:
|
|
_assert_openapi_matches_baseline(schema)
|
|
diagnostic = str(failure.value)
|
|
assert '--- skills_openapi_baseline.json' in diagnostic
|
|
assert '+++ generated OpenAPI' in diagnostic
|
|
assert f'Changed {section}: {key}' in diagnostic
|
|
expected_change = '"description": "changed contract"' if section == 'paths' else '"maxLength": 4999'
|
|
assert any(line.startswith('+') and expected_change in line
|
|
for line in diagnostic.splitlines())
|
|
|
|
|
|
@pytest.mark.parametrize('raw, expected', [
|
|
('<think>{"verdict":"fail"}</think>{"verdict":"PASS","confidence":2,}', 'pass'),
|
|
('{"verdict":"fail"} text {"verdict":"needs_work"}', 'needs_work'),
|
|
('Verdict: INCONCLUSIVE', 'inconclusive'),
|
|
('<think>{"verdict":"pass"}', 'unknown'),
|
|
('{"verdict":"invalid"}', 'unknown'),
|
|
])
|
|
async def test_run_verdict_parsing_and_retry(monkeypatch, raw, expected):
|
|
calls = []
|
|
async def call(url, model, messages, **kwargs):
|
|
calls.append((messages, kwargs))
|
|
return raw
|
|
monkeypatch.setattr('src.llm_core.llm_call_async', call)
|
|
monkeypatch.setattr(routes, 'effort_for_call', lambda url, model, owner: 'high' if owner == 'alice' else None)
|
|
result = await routes._eval_skill_run('md', 'task', 'transcript', 'url', 'm', {},
|
|
workload='background', owner='alice')
|
|
assert result['verdict'] == expected
|
|
assert len(calls) == (2 if expected == 'unknown' else 1)
|
|
for _, kwargs in calls:
|
|
assert kwargs['reasoning_effort'] == 'high'
|
|
assert kwargs['workload'] == 'background'
|
|
assert kwargs['timeout'] == 180
|
|
assert kwargs['max_tokens'] == 32768
|
|
if len(calls) == 2:
|
|
assert "must START with '{'" in calls[1][0][0]['content']
|
|
|
|
|
|
async def test_review_transient_failure_and_result_coercion(monkeypatch):
|
|
calls = []
|
|
async def call(*args, **kwargs):
|
|
calls.append(kwargs)
|
|
if len(calls) == 1:
|
|
raise TimeoutError('offline')
|
|
return json.dumps({'verdict': 'pass', 'confidence': '-1', 'summary': 'x' * 500,
|
|
'issues': ['y' * 250] * 10, 'baseline_verdict': 'invalid',
|
|
'usefulness': '2', 'saved_turns': '-2', 'saved_tool_calls': 'bad'})
|
|
monkeypatch.setattr('src.llm_core.llm_call_async', call)
|
|
result = await routes._eval_skill_run('', '', '', 'url', 'm', None)
|
|
assert result == {'verdict': 'pass', 'confidence': 0.0, 'summary': 'x' * 400,
|
|
'issues': ['y' * 200] * 8, 'baseline_verdict': 'unknown',
|
|
'usefulness': 1.0, 'saved_turns': -2, 'saved_tool_calls': 0}
|
|
|
|
|
|
async def test_review_failure_schema_and_transcript_tail(monkeypatch):
|
|
seen = []
|
|
async def call(url, model, messages, **kwargs):
|
|
seen.append(messages)
|
|
raise RuntimeError('offline')
|
|
monkeypatch.setattr('src.llm_core.llm_call_async', call)
|
|
result = await routes._eval_skill_run('m' * 5000, 'TASK', 'HEAD' + 'x' * 30000 + 'TAIL', 'url', 'm', None)
|
|
assert result == {'verdict': 'unknown', 'confidence': 0,
|
|
'summary': 'Review call failed: offline', 'issues': []}
|
|
assert len(seen) == 2
|
|
assert 'HEAD' in seen[0][1]['content'] and 'TAIL' in seen[0][1]['content']
|
|
assert 'm' * 4001 not in seen[0][1]['content']
|
|
|
|
|
|
@pytest.mark.parametrize('name, raw, expected, tokens, timeout', [
|
|
('_eval_skill_necessity', '<think>x</think>{"necessary":false,"redundant_with":["demo"],"reason":"duplicate",}',
|
|
{'necessary': False, 'redundant_with': ['demo'], 'reason': 'duplicate'}, 8192, 120),
|
|
('_eval_skill_retrieval_precision', '{"ok":false,"summary":"broad","issues":["metadata: retrieval: narrow"]}',
|
|
{'ok': False, 'summary': 'broad', 'issues': ['metadata: retrieval: narrow']}, 4096, 90),
|
|
('_eval_skill_necessity', '<think>unfinished', None, 8192, 120),
|
|
('_eval_skill_retrieval_precision', '[]', None, 4096, 90),
|
|
])
|
|
async def test_advisory_schema_budget_and_owner(monkeypatch, name, raw, expected, tokens, timeout):
|
|
async def call(*args, **kwargs):
|
|
assert kwargs['max_tokens'] == tokens
|
|
assert kwargs['timeout'] == timeout
|
|
assert kwargs['reasoning_effort'] == 'medium'
|
|
return raw
|
|
monkeypatch.setattr('src.llm_core.llm_call_async', call)
|
|
monkeypatch.setattr(routes, 'effort_for_call', lambda url, model, owner: 'medium' if owner == 'alice' else None)
|
|
assert await getattr(routes, name)('md', [], 'url', 'm', None, owner='alice') == expected
|
|
|
|
|
|
@pytest.mark.parametrize('name', ['_eval_skill_necessity', '_eval_skill_retrieval_precision', '_improve_skill_md'])
|
|
async def test_advisory_exceptions_return_none(monkeypatch, name):
|
|
async def call(*args, **kwargs):
|
|
raise TimeoutError('offline')
|
|
monkeypatch.setattr('src.llm_core.llm_call_async', call)
|
|
args = ('md', {}, '', 'url', 'm', None) if name == '_improve_skill_md' else ('md', [], 'url', 'm', None)
|
|
assert await getattr(routes, name)(*args) is None
|
|
|
|
|
|
async def test_cancelled_audit_closes_stream_in_originating_context(monkeypatch):
|
|
bound = ContextVar('audit_characterization', default=None)
|
|
opened = asyncio.Event()
|
|
closed = []
|
|
async def stream(*args, **kwargs):
|
|
token = bound.set('bound')
|
|
try:
|
|
yield 'data: {"delta":"started"}\n\n'
|
|
opened.set()
|
|
await asyncio.Event().wait()
|
|
finally:
|
|
bound.reset(token)
|
|
closed.append(asyncio.current_task())
|
|
monkeypatch.setattr('src.agent_loop.stream_agent_loop', stream)
|
|
task = asyncio.create_task(routes._run_skill_audit_arm([], 'url', 'm', {}, 'alice'))
|
|
await opened.wait()
|
|
task.cancel()
|
|
with pytest.raises(asyncio.CancelledError):
|
|
await task
|
|
assert closed == [task]
|
|
assert bound.get() is None
|
|
|
|
|
|
async def test_cancelled_batch_skips_finalization_and_cleans_task(monkeypatch):
|
|
opened = asyncio.Event()
|
|
async def audit(*args, **kwargs):
|
|
opened.set()
|
|
await asyncio.Event().wait()
|
|
class Manager:
|
|
def load(self, owner=None):
|
|
assert owner == 'alice'
|
|
return [{'name': 'demo'}]
|
|
job = {'status': 'running', 'log': [], 'results': [], 'done': 0}
|
|
monkeypatch.setattr(routes, '_skill_audit_jobs', {('alice',): job})
|
|
monkeypatch.setattr(routes, '_audit_one_skill', audit)
|
|
monkeypatch.setattr(routes, '_finalize_audit_batch', lambda *args: pytest.fail('cancelled batch finalized'))
|
|
task = asyncio.create_task(routes._run_audit_all_job(('alice',), Manager(), ['demo'], 'url', 'm', {}, None, 'alice'))
|
|
job['task'] = task
|
|
await opened.wait()
|
|
task.cancel()
|
|
await task
|
|
assert job['status'] == 'cancelled'
|
|
assert job['current'] is None and 'task' not in job and 'finished' in job
|
|
assert job['results'] == [] and job['done'] == 0
|
|
|
|
|
|
async def test_test_polling_is_owner_scoped_and_hides_continuation(monkeypatch):
|
|
class Manager:
|
|
def load(self, owner=None):
|
|
return [{'name': 'demo'}]
|
|
monkeypatch.setattr(routes, 'get_current_user', lambda req: req.state.user)
|
|
job = {'status': 'awaiting_approval', 'task': 'task', 'model': 'm', 'log': [],
|
|
'verdict': None, 'approval': {'approval_id': 'id'},
|
|
'_run': {'headers': {'Authorization': 'secret'}}, '_transcript': ['private']}
|
|
monkeypatch.setattr(routes, '_skill_test_jobs', {('alice', 'demo'): job})
|
|
poll = endpoint('GET', '/{skill_id}/test-status', Manager())
|
|
assert await poll(request('bob'), 'demo') == {'status': 'none'}
|
|
assert await poll(request(), 'demo') == {k: job[k] for k in ('status', 'task', 'model', 'log', 'verdict', 'approval')}
|
|
|
|
|
|
def test_batch_finalizer_protects_approval_required_and_unprocessed_skills(monkeypatch):
|
|
class Manager:
|
|
def __init__(self):
|
|
self.updated = []
|
|
def load(self, owner=None):
|
|
assert owner == 'alice'
|
|
return [{'name': name, 'status': 'published', 'source': 'learned',
|
|
'audit_verdict': 'fail', 'confidence': .9} for name in ('demo', 'demo-1', 'demo-2')]
|
|
def update_skill(self, name, fields, owner=None):
|
|
self.updated.append((name, fields, owner))
|
|
monkeypatch.setattr(routes, '_audit_auto_publish_policy', lambda owner: (True, .8))
|
|
manager = Manager()
|
|
routes._finalize_audit_batch(manager, [{'skill': 'demo', 'result': 'approval_required'},
|
|
{'skill': 'demo-1', 'result': 'flagged'}], 'alice', lambda msg: None)
|
|
assert manager.updated == [('demo-1', {'status': 'draft'}, 'alice')]
|