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/evaluation_tests/experiment_test.py

@@ -0,0 +1,159 @@
+"""Tests for linking existing review traces into dataset runs."""
+import os
+import sys
+
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", "..", "..", "pilot"))
+
+import eval_experiment as ex  # noqa: E402
+
+
+def trace(tid, repo="o/r", pr=1, model="M2", ts="2026-08-01T00:00:00Z", **md):
+    meta = {"repo": repo, "pr": pr}
+    meta.update(md)
+    return {
+        "id": tid,
+        "timestamp": ts,
+        "tags": [f"model:{model}", "engine:opencode"],
+        "metadata": meta,
+    }
+
+
+# --- trace_model ----------------------------------------------------------
+
+def test_model_read_from_tag():
+    assert ex.trace_model(trace("t1", model="MiniMax-M2.7")) == "MiniMax-M2.7"
+
+
+def test_model_falls_back_when_untagged():
+    assert ex.trace_model({"tags": ["engine:opencode"]}) == "unknown"
+
+
+def test_model_falls_back_when_tags_absent():
+    assert ex.trace_model({}) == "unknown"
+
+
+# --- trace_item_id --------------------------------------------------------
+
+def test_item_id_matches_the_bootstrap_scheme():
+    assert ex.trace_item_id(trace("t1", repo="netcracker/interview", pr=29)) == \
+        "netcracker__interview__pr29"
+
+
+def test_trace_without_repo_is_not_an_item():
+    assert ex.trace_item_id({"metadata": {"pr": 1}}) is None
+
+
+def test_trace_without_pr_is_not_an_item():
+    assert ex.trace_item_id({"metadata": {"repo": "o/r"}}) is None
+
+
+def test_trace_without_metadata_is_not_an_item():
+    assert ex.trace_item_id({}) is None
+
+
+# --- plan_runs ------------------------------------------------------------
+
+ITEMS = {"o__r__pr1", "o__r__pr2"}
+
+
+def test_traces_group_by_model():
+    plan = ex.plan_runs(
+        [trace("a", pr=1, model="x"), trace("b", pr=2, model="y")], ITEMS
+    )
+    assert set(plan["runs"]) == {"x", "y"}
+
+
+def test_group_by_none_collapses_to_one_run():
+    plan = ex.plan_runs(
+        [trace("a", pr=1, model="x"), trace("b", pr=2, model="y")],
+        ITEMS,
+        group_by="none",
+    )
+    assert list(plan["runs"]) == ["all-traces"]
+
+
+def test_only_the_newest_trace_per_item_is_kept():
+    """A re-reviewed PR has many traces; a run takes one output per input."""
+    plan = ex.plan_runs(
+        [
+            trace("old", pr=1, ts="2026-08-01T00:00:00Z"),
+            trace("new", pr=1, ts="2026-08-09T00:00:00Z"),
+        ],
+        ITEMS,
+    )
+    assert plan["runs"]["M2"]["o__r__pr1"]["id"] == "new"
+
+
+def test_newest_wins_regardless_of_input_order():
+    older = trace("old", pr=1, ts="2026-08-01T00:00:00Z")
+    newer = trace("new", pr=1, ts="2026-08-09T00:00:00Z")
+    for order in ([older, newer], [newer, older]):
+        plan = ex.plan_runs(order, ITEMS)
+        assert plan["runs"]["M2"]["o__r__pr1"]["id"] == "new"
+
+
+def test_trace_for_a_pr_outside_the_dataset_is_skipped():
+    plan = ex.plan_runs([trace("a", pr=99)], ITEMS)
+    assert plan["runs"] == {}
+    assert plan["skipped_not_in_dataset"] == 1
+
+
+def test_non_review_trace_is_counted_separately():
+    plan = ex.plan_runs([{"id": "x", "metadata": {}}], ITEMS)
+    assert plan["skipped_not_a_review"] == 1
+    assert plan["skipped_not_in_dataset"] == 0
+
+
+def test_same_pr_different_models_lands_in_both_runs():
+    plan = ex.plan_runs([trace("a", pr=1, model="x"), trace("b", pr=1, model="y")], ITEMS)
+    assert plan["runs"]["x"]["o__r__pr1"]["id"] == "a"
+    assert plan["runs"]["y"]["o__r__pr1"]["id"] == "b"
+
+
+# --- run_name -------------------------------------------------------------
+
+def test_run_name_prefixed():
+    assert ex.run_name("baseline", "MiniMax-M2.7") == "baseline-MiniMax-M2.7"
+
+
+def test_empty_prefix_leaves_the_key_bare():
+    assert ex.run_name("", "MiniMax-M2.7") == "MiniMax-M2.7"
+
+
+# --- create_run -----------------------------------------------------------
+
+def test_create_run_posts_one_item_per_pair(monkeypatch):
+    calls = []
+
+    def fake_call(method, path, body=None, timeout=20.0):
+        calls.append((method, path, body))
+        return 201, {}
+
+    monkeypatch.setattr(ex.eb, "_call", fake_call)
+    res = ex.create_run("run-1", {"o__r__pr1": trace("t1"), "o__r__pr2": trace("t2", pr=2)})
+    assert res["items_linked"] == 2
+    assert res["failed"] == []
+    assert {c[1] for c in calls} == {"/api/public/dataset-run-items"}
+    assert {c[2]["runName"] for c in calls} == {"run-1"}
+
+
+def test_create_run_links_the_trace_to_the_item(monkeypatch):
+    seen = {}
+
+    def fake_call(method, path, body=None, timeout=20.0):
+        seen.update(body)
+        return 201, {}
+
+    monkeypatch.setattr(ex.eb, "_call", fake_call)
+    ex.create_run("run-1", {"o__r__pr1": trace("t1")})
+    assert seen["datasetItemId"] == "o__r__pr1"
+    assert seen["traceId"] == "t1"
+    assert seen["metadata"]["model"] == "M2"
+
+
+def test_create_run_reports_rejected_items(monkeypatch):
+    monkeypatch.setattr(ex.eb, "_call", lambda *a, **k: (400, "nope"))
+    res = ex.create_run("run-1", {"o__r__pr1": trace("t1")})
+    assert res["items_linked"] == 0
+    assert res["failed"][0]["item"] == "o__r__pr1"
+    assert res["failed"][0]["status"] == 400