refactor: organize pilot packages

Group review, feedback, evaluation, observability, and entrypoint code into packages. Keep thin top-level compatibility shims for existing scripts and imports, and mirror the structure in the tests.

tests/pilot/conftest.py

@@ -0,0 +1,9 @@
+"""Make the pilot package roots available to every categorized test."""
+from __future__ import annotations
+
+import os
+import sys
+
+PILOT_ROOT = os.path.abspath(os.path.join(os.path.dirname(__file__), "..", "..", "pilot"))
+if PILOT_ROOT not in sys.path:
+    sys.path.insert(0, PILOT_ROOT)

tests/pilot/entrypoint_tests/__init__.py

@@ -0,0 +1 @@
+"""Entrypoint tests."""

tests/pilot/entrypoint_tests/webhook_test.py

@@ -5,7 +5,7 @@ import sys
 import threading
 
 HERE = os.path.dirname(os.path.abspath(__file__))
-ROOT = os.path.abspath(os.path.join(HERE, "..", ".."))
+ROOT = os.path.abspath(os.path.join(HERE, "..", "..", ".."))
 sys.path.insert(0, os.path.join(ROOT, "pilot"))
 
 import webhook_server as ws  # noqa: E402

tests/pilot/evaluation_tests/__init__.py

@@ -0,0 +1 @@
+"""Evaluation tests."""

tests/pilot/evaluation_tests/bootstrap_test.py

@@ -4,7 +4,7 @@ import sqlite3
 import sys
 import urllib.parse
 
-sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", "..", "pilot"))
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", "..", "..", "pilot"))
 
 import eval_bootstrap as eb  # noqa: E402
 

tests/pilot/evaluation_tests/experiment_test.py

@@ -2,7 +2,7 @@
 import os
 import sys
 
-sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", "..", "pilot"))
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", "..", "..", "pilot"))
 
 import eval_experiment as ex  # noqa: E402
 

tests/pilot/evaluation_tests/scores_test.py

@@ -4,7 +4,7 @@ import sys
 
 import pytest
 
-sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", "..", "pilot"))
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", "..", "..", "pilot"))
 
 import eval_scores as es  # noqa: E402
 

tests/pilot/feedback_tests/__init__.py

@@ -0,0 +1 @@
+"""Feedback tests."""

tests/pilot/feedback_tests/analyze_test.py

@@ -16,7 +16,7 @@ import tempfile
 import unittest
 
 HERE = os.path.dirname(os.path.abspath(__file__))
-sys.path.insert(0, os.path.join(HERE, "..", "..", "pilot"))
+sys.path.insert(0, os.path.join(HERE, "..", "..", "..", "pilot"))
 
 import feedback  # noqa: E402
 import feedback_analyze  # noqa: E402
@@ -228,4 +228,4 @@ class TestPosthashAggregation(unittest.TestCase):
 
 
 if __name__ == "__main__":
-    unittest.main()
+    unittest.main()

tests/pilot/feedback_tests/harvest_test.py

@@ -17,7 +17,7 @@ import unittest
 from unittest.mock import patch
 
 HERE = os.path.dirname(os.path.abspath(__file__))
-sys.path.insert(0, os.path.join(HERE, "..", "..", "pilot"))
+sys.path.insert(0, os.path.join(HERE, "..", "..", "..", "pilot"))
 
 import ai_review  # noqa: E402
 import feedback  # noqa: E402
@@ -240,4 +240,4 @@ class TestParseHelpers(unittest.TestCase):
 
 
 if __name__ == "__main__":
-    unittest.main()
+    unittest.main()

tests/pilot/feedback_tests/post_test.py

@@ -11,7 +11,7 @@ import unittest
 from unittest.mock import patch
 
 HERE = os.path.dirname(os.path.abspath(__file__))
-sys.path.insert(0, os.path.join(HERE, "..", "..", "pilot"))
+sys.path.insert(0, os.path.join(HERE, "..", "..", "..", "pilot"))
 
 import feedback  # noqa: E402
 import feedback_analyze  # noqa: E402
@@ -94,4 +94,4 @@ class TestDeliver(unittest.TestCase):
 
 
 if __name__ == "__main__":
-    unittest.main()
+    unittest.main()

tests/pilot/feedback_tests/scores_test.py

@@ -4,7 +4,7 @@ import sys
 
 import pytest
 
-sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", "..", "pilot"))
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", "..", "..", "pilot"))
 
 import feedback  # noqa: E402
 import feedback_scores as fs  # noqa: E402

tests/pilot/observability_tests/__init__.py

@@ -0,0 +1 @@
+"""Observability tests."""

tests/pilot/observability_tests/cost_test.py

@@ -3,7 +3,7 @@ import os
 import sys
 
 HERE = os.path.dirname(os.path.abspath(__file__))
-ROOT = os.path.abspath(os.path.join(HERE, "..", ".."))
+ROOT = os.path.abspath(os.path.join(HERE, "..", "..", ".."))
 sys.path.insert(0, os.path.join(ROOT, "pilot"))
 
 import cost_model as cm  # noqa: E402

tests/pilot/observability_tests/langfuse_test.py

@@ -8,7 +8,7 @@ import os
 import sys
 
 HERE = os.path.dirname(os.path.abspath(__file__))
-ROOT = os.path.abspath(os.path.join(HERE, "..", ".."))
+ROOT = os.path.abspath(os.path.join(HERE, "..", "..", ".."))
 sys.path.insert(0, os.path.join(ROOT, "pilot"))
 
 import langfuse_trace as lt  # noqa: E402

tests/pilot/review_tests/__init__.py

@@ -0,0 +1 @@
+"""Review tests."""

tests/pilot/review_tests/ai_review_test.py

@@ -6,7 +6,7 @@ import sys
 
 # Allow running without install: add repo root to path.
 HERE = os.path.dirname(os.path.abspath(__file__))
-ROOT = os.path.abspath(os.path.join(HERE, "..", ".."))
+ROOT = os.path.abspath(os.path.join(HERE, "..", "..", ".."))
 sys.path.insert(0, os.path.join(ROOT, "pilot"))
 
 import ai_review  # noqa: E402
@@ -2149,4 +2149,3 @@ def test_format_review_body_confidence_clamps_out_of_range():
     body_lo = format_review_body("- x", "glm-5.2:cloud", "abcdef1234567890", confidence=0)
     assert "Merge confidence: 1/5 🔴" in body_lo
 
-

tests/pilot/review_tests/diff_test.py

@@ -4,7 +4,7 @@ import re
 import sys
 
 HERE = os.path.dirname(os.path.abspath(__file__))
-ROOT = os.path.abspath(os.path.join(HERE, "..", ".."))
+ROOT = os.path.abspath(os.path.join(HERE, "..", "..", ".."))
 sys.path.insert(0, os.path.join(ROOT, "pilot"))
 
 import diff_compress  # noqa: E402

tests/pilot/review_tests/opencode_test.py

@@ -6,7 +6,7 @@ import sys
 import tarfile
 
 HERE = os.path.dirname(os.path.abspath(__file__))
-ROOT = os.path.abspath(os.path.join(HERE, "..", ".."))
+ROOT = os.path.abspath(os.path.join(HERE, "..", "..", ".."))
 sys.path.insert(0, os.path.join(ROOT, "pilot"))
 
 import opencode_review as oc  # noqa: E402

tests/pilot/review_tests/parse_dropped_test.py

@@ -9,7 +9,7 @@ import os
 import sys
 
 HERE = os.path.dirname(os.path.abspath(__file__))
-sys.path.insert(0, os.path.abspath(os.path.join(HERE, "..", "..", "pilot")))
+sys.path.insert(0, os.path.abspath(os.path.join(HERE, "..", "..", "..", "pilot")))
 
 import ai_review  # noqa: E402