Chelsea
6cf35ca034
Implements the parallel.md workstreams (Agents A-E) toward REFACTOR_GOAL.md. Phase 1 — app factory + blueprints + /api/v1: - app.py -> create_app() factory (no module-level app); entrypoints updated - routes/ (auth, pages, settings, admin, assets) + blueprints/api.py at /api/v1 - config.py / extensions.py / security.py extracted; services/ layer added - endpoint names preserved so template url_for() calls keep resolving (static check: all 27 template url_for endpoints are defined routes) Phase 2 — one pluggable filter system: - filter_pipeline/registry.py: @register_stage / @register_plugin + discover_modules - engine._init_stages() instantiates registered stages (no hardcoded dict); process_batch is AI-aware: only short-circuits to the AI-disabled path when a filterset's stages declare requires_ai, so offline filtersets run with AI off - BaseFilterPlugin gets a consumer (stages/plugins.py); Keyword/Quality re-enabled via filter_config.json plugins config - comment tree modes ported to stages/comment_filter.py + shared rules.py; wired into /api/v1/posts/<uuid> and /api/v1/comments/<uuid> via FilterEngine.filter_comments() (fails open) - offline quality_filter filterset exercises plugins+ranker without AI - legacy filter_lib / comment_lib / html_generation_lib / generate_html / active_html path deleted Phase 3 prep — pluggable fetchers + Postgres models: - Post / Comment SQLAlchemy models added to models.py - migrate_content_to_db.py backfill (idempotent by uuid, batched, --dry-run) - platforms/ fetcher registry (extension point) - live reads/writes still go through PostService (disk JSON); cutover deferred Phase 6 — test harness: - pytest.ini + tests/ (conftest with in-memory SQLite fixture, no Postgres; stubbed polling/filter singletons) - test_app_factory.py (route registration, no module-level app), test_api_contracts.py (posts/post_detail/comments/filters shape with monkeypatched post_service + get_filter_engine), test_filter_pipeline.py + test_plugin_contract.py (Flask-free; validated locally 12/12 incl. drop-in stage/plugin discovered with zero core edits) Other: .gitignore added (__pycache__, data/, secrets); pytest in requirements. Verification: py_compile clean across the project; the Flask-free filter-pipeline and plugin-contract tests pass locally. App-factory / API-contract tests need deps+docker to run; runtime flask routes / Auth0-repeated-create_app also gated on docker. Co-Authored-By: Claude <noreply@anthropic.com>
90 lines
2.8 KiB
Python
90 lines
2.8 KiB
Python
"""Plugin/stage contract test (Phase 6).
|
|
|
|
A drop-in stage and plugin, defined ONLY in this test module via the public
|
|
``@register_stage`` / ``@register_plugin`` decorators, are picked up by the
|
|
engine with zero edits to core files. This is the pluggability guarantee: a
|
|
new filter behavior is a new module + a config entry, never an edit to
|
|
``engine.py``.
|
|
"""
|
|
|
|
from filter_pipeline.engine import FilterEngine
|
|
from filter_pipeline.models import FilterResult
|
|
from filter_pipeline.plugins.base import BaseFilterPlugin
|
|
from filter_pipeline.registry import (
|
|
get_plugin_class,
|
|
get_stage_class,
|
|
register_plugin,
|
|
register_stage,
|
|
)
|
|
from filter_pipeline.stages.base_stage import BaseStage
|
|
|
|
|
|
@register_stage("sentinel_dropin_stage")
|
|
class SentinelStage(BaseStage):
|
|
"""Drop-in stage that tags any result it sees."""
|
|
|
|
def get_name(self):
|
|
return "Sentinel"
|
|
|
|
def process(self, post, result):
|
|
result.tags.append("sentinel_ran")
|
|
return result
|
|
|
|
|
|
@register_plugin("sentinel_dropin_plugin")
|
|
class SentinelPlugin(BaseFilterPlugin):
|
|
"""Drop-in plugin: never rejects, returns a fixed score."""
|
|
|
|
def get_name(self):
|
|
return "SentinelPlugin"
|
|
|
|
def should_filter(self, post, context=None):
|
|
return False
|
|
|
|
def score(self, post, context=None):
|
|
return 0.9
|
|
|
|
|
|
def test_dropin_stage_is_registered():
|
|
assert get_stage_class("sentinel_dropin_stage") is SentinelStage
|
|
|
|
|
|
def test_dropin_plugin_is_registered():
|
|
assert get_plugin_class("sentinel_dropin_plugin") is SentinelPlugin
|
|
|
|
|
|
def test_engine_instantiates_dropin_stage():
|
|
eng = FilterEngine("filter_config.json", "filtersets.json")
|
|
eng._init_stages()
|
|
assert "sentinel_dropin_stage" in eng._stages
|
|
stage = eng._stages["sentinel_dropin_stage"]
|
|
# Running the stage through the contract it claims to implement works.
|
|
result = FilterResult(post_uuid="x", passed=True, score=0.5)
|
|
out = stage.process({"uuid": "x"}, result)
|
|
assert "sentinel_ran" in out.tags
|
|
|
|
|
|
def test_dropin_stage_can_be_selected_in_a_filterset(tmp_path):
|
|
"""A filterset that lists the drop-in stage actually runs it.
|
|
|
|
Builds a throwaway config + filterset on disk so no core file is edited.
|
|
"""
|
|
import json
|
|
|
|
cfg = tmp_path / "cfg.json"
|
|
cfg.write_text(json.dumps({
|
|
"ai": {"enabled": False},
|
|
"cache": {"enabled": False},
|
|
"pipeline": {"default_stages": ["sentinel_dropin_stage"], "enable_parallel": False},
|
|
"plugins": {"enabled": [], "configs": {}},
|
|
}))
|
|
fs = tmp_path / "fs.json"
|
|
fs.write_text(json.dumps({"custom": {"post_rules": {}, "comment_rules": {}}}))
|
|
|
|
eng = FilterEngine(str(cfg), str(fs))
|
|
eng._init_stages()
|
|
results = eng.process_batch(
|
|
[{"uuid": "p1", "title": "t", "content": "", "score": 0, "timestamp": 0}],
|
|
"custom",
|
|
)
|
|
assert "sentinel_ran" in results[0].tags |