feat. Revision of Agent Lopp & major clean-up

tests/test_storage.py

@@ -37,8 +37,8 @@ def test_history_db_job_and_events_roundtrip(tmp_path: Path) -> None:
     assert job["status"] == "completed"
     assert job["model"] == "gpt-5.4-mini"
     assert job["disabled_tools"] == ["click"]
-    assert job["response"]["return"] == "Done"
-    assert job["response"]["data"]["files"] == ["a.txt", "b.txt"]
+    assert job["return"] == "Done"
+    assert job["data"]["files"] == ["a.txt", "b.txt"]
     assert job["usage"]["estimated_cost_usd"] == 0.1234
 
     events = db.get_job_events(job_id, limit=10)
@@ -70,11 +70,11 @@ def test_storage_response_fallback_uses_result_when_json_missing(tmp_path: Path)
     db.update_job(job_id, status="completed", result="Legacy result string")
     job = db.get_job(job_id)
     assert job is not None
-    assert job["response"]["return"] == "Legacy result string"
-    assert job["response"]["data"] is None
+    assert job["return"] == "Legacy result string"
+    assert job["data"] is None
 
 
-def test_history_db_analytics_groups_by_category_and_day(tmp_path: Path) -> None:
+def test_history_db_analytics_groups_by_category(tmp_path: Path) -> None:
     db = HistoryDB(tmp_path / "screenjob_test_analytics.db")
 
     db.create_job(
@@ -108,14 +108,6 @@ def test_history_db_analytics_groups_by_category_and_day(tmp_path: Path) -> None
     db.update_job("job_terminal_ok", status="completed", steps=10, estimated_cost_usd=0.05)
 
     analytics = db.analytics()
-    assert analytics["total_jobs"] == 3
-    assert analytics["finished_jobs"] == 3
-    assert analytics["completed_jobs"] == 2
-    assert analytics["failed_jobs"] == 1
-    assert analytics["success_rate"] == 66.67
-    assert analytics["avg_steps"] == 6.67
-    assert analytics["avg_cost_usd"] == 0.136667
-
     browser = next(row for row in analytics["by_category"] if row["label"] == "Browser / web")
     terminal = next(row for row in analytics["by_category"] if row["label"] == "Files / terminal")
     assert browser["finished_jobs"] == 2
@@ -123,4 +115,30 @@ def test_history_db_analytics_groups_by_category_and_day(tmp_path: Path) -> None
     assert browser["avg_steps"] == 5.0
     assert terminal["success_rate"] == 100.0
 
-    assert [row["label"] for row in analytics["timeline"]] == ["2026-05-27", "2026-05-28"]
+
+def test_prune_older_than_removes_old_terminal_jobs(tmp_path: Path) -> None:
+    db = HistoryDB(tmp_path / "screenjob_prune.db")
+    db.create_job(
+        job_id="job_old",
+        objective="Old",
+        model="gpt-5.4-mini",
+        created_at="2000-01-01T00:00:00+00:00",
+        safety_override=False,
+        disabled_tools=[],
+    )
+    db.update_job("job_old", status="completed")
+    db.add_event(job_id="job_old", ts="2000-01-01T00:00:01+00:00", step=1, event_type="done", payload={})
+
+    db.create_job(
+        job_id="job_running",
+        objective="Running",
+        model="gpt-5.4-mini",
+        created_at="2000-01-01T00:00:00+00:00",
+        safety_override=False,
+        disabled_tools=[],
+    )
+    db.update_job("job_running", status="running")
+
+    assert db.prune_older_than(7) == 1
+    assert db.get_job("job_old") is None
+    assert db.get_job("job_running") is not None