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.
2026-09-01 00:59:51 +00:00
parent 3a110ab52c
commit 7a510a926d
66 changed files with 8174 additions and 8039 deletions
@@ -0,0 +1 @@
+"""Evaluation tests."""
@@ -0,0 +1,158 @@
+"""Tests for the eval bootstrap's dataset-item construction."""
+import os
+import sqlite3
+import sys
+import urllib.parse
+
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", "..", "..", "pilot"))
+
+import eval_bootstrap as eb  # noqa: E402
+
+
+# --- item_id --------------------------------------------------------------
+
+def test_item_id_has_no_path_separator():
+    """A `/` would split the UI's item route into extra path segments."""
+    assert "/" not in eb.item_id("netcracker/interview", 29)
+
+
+def test_item_id_has_no_fragment_marker():
+    """Everything after a `#` is a fragment the browser never sends."""
+    assert "#" not in eb.item_id("netcracker/interview", 29)
+
+
+def test_item_id_survives_a_url_round_trip():
+    """The id must appear verbatim in a path, needing no percent-encoding."""
+    ident = eb.item_id("netcracker/interview", 29)
+    assert urllib.parse.quote(ident, safe="") == ident
+
+
+def test_item_id_keeps_repo_and_pr_readable():
+    assert eb.item_id("netcracker/interview", 29) == "netcracker__interview__pr29"
+
+
+def test_item_id_is_unique_per_pr():
+    assert eb.item_id("o/r", 1) != eb.item_id("o/r", 2)
+
+
+def test_item_id_is_unique_per_repo():
+    assert eb.item_id("o/one", 1) != eb.item_id("o/two", 1)
+
+
+def test_item_id_accepts_a_string_pr():
+    assert eb.item_id("o/r", "29") == eb.item_id("o/r", 29)
+
+
+# --- read_review_items ----------------------------------------------------
+
+def _db(tmp_path, rows, findings=()):
+    path = str(tmp_path / "feedback.db")
+    conn = sqlite3.connect(path)
+    conn.execute(
+        "CREATE TABLE review (repo TEXT, pr INTEGER, posted_at INTEGER, head_sha TEXT)"
+    )
+    conn.execute(
+        "CREATE TABLE inline_finding (repo TEXT, pr INTEGER, path TEXT, line INTEGER,"
+        " severity TEXT, problem TEXT, fix TEXT)"
+    )
+    conn.executemany("INSERT INTO review VALUES (?,?,?,?)", rows)
+    conn.executemany("INSERT INTO inline_finding VALUES (?,?,?,?,?,?,?)", findings)
+    conn.commit()
+    conn.close()
+    return path
+
+
+def test_items_use_url_safe_ids(tmp_path):
+    path = _db(tmp_path, [("netcracker/interview", 29, 100, "abc")])
+    items = eb.read_review_items(path)
+    assert [i["id"] for i in items] == ["netcracker__interview__pr29"]
+
+
+def test_item_input_keeps_the_real_repo_name(tmp_path):
+    """The id is mangled for the URL; the payload must stay faithful."""
+    path = _db(tmp_path, [("netcracker/interview", 29, 100, "abc")])
+    item = eb.read_review_items(path)[0]
+    assert item["input"]["repo"] == "netcracker/interview"
+    assert item["input"]["pr"] == 29
+
+
+def test_one_item_per_pr_not_per_review(tmp_path):
+    path = _db(
+        tmp_path,
+        [
+            ("o/r", 1, 100, "a"),
+            ("o/r", 1, 200, "b"),
+            ("o/r", 2, 300, "c"),
+        ],
+    )
+    items = eb.read_review_items(path)
+    assert [i["id"] for i in items] == ["o__r__pr1", "o__r__pr2"]
+    assert items[0]["metadata"]["reviews_run"] == 2
+
+
+def test_items_are_not_flagged_as_human_labelled(tmp_path):
+    path = _db(tmp_path, [("o/r", 1, 100, "a")])
+    assert eb.read_review_items(path)[0]["metadata"]["labelled_by_human"] is False
+
+
+# --- metadata facets ------------------------------------------------------
+
+def _md(findings=(), repo="netcracker/interview", pr=29):
+    return eb._item_metadata(
+        repo=repo, pr=pr, head_sha="abc", reviews_run=2, last_seen=1788189422,
+        findings=[{"severity": s} for s in findings],
+    )
+
+
+def test_metadata_carries_the_repo_for_filtering():
+    assert _md()["repo"] == "netcracker/interview"
+
+
+def test_metadata_splits_owner_from_repo_name():
+    """A filter on the joined repo can match one repo; owner matches an org."""
+    md = _md()
+    assert md["owner"] == "netcracker"
+    assert md["repo_name"] == "interview"
+
+
+def test_owner_falls_back_when_the_repo_is_unqualified():
+    md = _md(repo="standalone")
+    assert md["owner"] == "standalone"
+    assert md["repo_name"] == "standalone"
+
+
+def test_metadata_values_are_filterable_primitives():
+    """Nested objects and lists are not reachable from the filter bar."""
+    for key, value in _md(["high"]).items():
+        assert isinstance(value, (str, int, float, bool)), key
+
+
+def test_max_severity_is_the_worst_finding():
+    assert _md(["low", "critical", "medium"])["max_severity"] == "critical"
+
+
+def test_max_severity_is_none_not_absent_for_a_silent_review():
+    md = _md([])
+    assert md["max_severity"] == "none"
+    assert md["has_findings"] is False
+
+
+def test_unknown_severity_does_not_win_the_max():
+    assert _md(["banana", "low"])["max_severity"] == "low"
+
+
+def test_severity_comparison_ignores_case():
+    assert _md(["HIGH"])["max_severity"] == "high"
+
+
+def test_finding_count_matches_the_findings():
+    md = _md(["low", "low"])
+    assert md["finding_count"] == 2
+    assert md["has_findings"] is True
+
+
+def test_last_reviewed_is_exposed_both_ways():
+    """The epoch sorts; the ISO string is what a human reads in a filter."""
+    md = _md()
+    assert md["last_reviewed_at"] == 1788189422
+    assert md["last_reviewed_iso"].startswith("2026-08-31T")
@@ -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
@@ -0,0 +1,132 @@
+
+
+"""Tests for the LLM-as-judge evaluator bootstrap."""
+import os
+import sys
+
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", "..", "pilot"))
+
+import eval_judges as ej  # noqa: E402
+
+
+# --- rule_body ------------------------------------------------------------
+
+def test_rule_body_targets_traces():
+    """Trace target matches the path `/api/public/ingestion` triggers.
+
+    Observation rules only fire from the OTel ingestion pipeline; this
+    pilot uses standard ingestion, so its jobs only come from
+    `evalService.createEvalJobs` and that dispatcher handles
+    `targetObject ∈ {TRACE, DATASET}`.
+    """
+    body = ej.rule_body("rule-x", "finding_actionability", 1.0)
+    assert body["target"] == "trace"
+    assert body["enabled"] is True
+
+
+def test_rule_body_filters_on_trace_name():
+    """`name` isn't a stringOptions column; only `traceName` is."""
+    body = ej.rule_body("rule-x", "finding_actionability", 1.0)
+    f = body["filter"][0]
+    assert f["column"] == "traceName"
+    assert f["operator"] == "any of"
+    assert f["type"] == "stringOptions"
+    assert "pr-review" in f["value"]
+
+
+def test_rule_body_references_evaluator_by_name():
+    """Ids are version-specific; rules must name the evaluator across versions."""
+    body = ej.rule_body("rule-x", "finding_actionability", 1.0)
+    assert body["evaluator"]["name"] == "finding_actionability"
+    assert body["evaluator"]["scope"] == "project"
+
+
+def test_rule_body_maps_input_and_output():
+    """Both judges read the observation's own input/output."""
+    body = ej.rule_body("rule-x", "any", 1.0)
+    sources = {m["source"] for m in body["mapping"]}
+    assert sources == {"input", "output"}
+
+
+def test_rule_body_carries_mapping_at_both_levels():
+    """The server validates `mapping` at the rule root and echoes it on the evaluator."""
+    body = ej.rule_body("rule-x", "any", 1.0)
+    assert body["mapping"]
+    assert body["evaluator"]["variableMapping"] == body["mapping"]
+
+
+def test_rule_body_passes_sampling_through():
+    assert ej.rule_body("r", "any", 0.25)["sampling"] == 0.25
+
+
+# --- ensure_evaluators idempotency ---------------------------------------
+
+def test_ensure_evaluators_skips_existing(monkeypatch):
+    seen = []
+
+    def fake_call(method, path, body=None, timeout=20.0):
+        seen.append(path)
+        return 200, {}
+
+    monkeypatch.setattr(ej.eb, "_call", fake_call)
+    monkeypatch.setattr(ej, "existing_evaluators",
+                        lambda: {"finding_actionability": "id-1", "review_self_consistency": "id-2"})
+    res = ej.ensure_evaluators()
+    assert res["created"] == {}
+    assert sorted(res["skipped"]) == ["finding_actionability", "review_self_consistency"]
+    assert res["failed"] == []
+    assert seen == []
+
+
+def test_ensure_evaluators_records_failures(monkeypatch):
+    def fake_call(method, path, body=None, timeout=20.0):
+        return 422, "boom"
+
+    monkeypatch.setattr(ej.eb, "_call", fake_call)
+    monkeypatch.setattr(ej, "existing_evaluators", lambda: {})
+    res = ej.ensure_evaluators()
+    assert res["created"] == {}
+    assert res["failed"][0]["status"] == 422
+
+
+# --- ensure_rules idempotency --------------------------------------------
+
+def test_ensure_rules_skips_existing(monkeypatch):
+    calls = []
+    monkeypatch.setattr(ej.eb, "_call",
+                        lambda *a, **k: calls.append(a) or (200, {}))
+    monkeypatch.setattr(ej, "existing_evaluators",
+                        lambda: {"finding_actionability": "id-1",
+                                 "review_self_consistency": "id-2"})
+    monkeypatch.setattr(ej, "existing_rule_names",
+                        lambda: {"finding_actionability-on-reviews",
+                                 "review_self_consistency-on-reviews"})
+    res = ej.ensure_rules({"finding_actionability": "id-1",
+                           "review_self_consistency": "id-2"}, 1.0)
+    assert res["created"] == []
+    assert sorted(res["skipped"]) == ["finding_actionability", "review_self_consistency"]
+    assert calls == []
+
+
+def test_ensure_rules_creates_when_missing(monkeypatch):
+    calls = []
+    monkeypatch.setattr(ej.eb, "_call",
+                        lambda *a, **k: calls.append(a) or (201, {}))
+    monkeypatch.setattr(ej, "existing_rule_names", lambda: set())
+    res = ej.ensure_rules({"finding_actionability": "id-1"}, 1.0)
+    assert res["created"] == ["finding_actionability"]
+    assert calls[0][0] == "POST"
+    assert calls[0][1] == "/api/public/unstable/evaluation-rules"
+
+
+# --- judge shape ----------------------------------------------------------
+
+def test_judges_have_required_keys():
+    for j in ej.JUDGES:
+        assert j["prompt"]
+        assert j["outputDefinition"]["dataType"] in ("NUMERIC", "BOOLEAN", "CATEGORICAL")
+
+
+def test_default_base_url_points_at_the_thinking_patch_proxy():
+    """`8802` is the judge-proxy that adds a `signature` to thinking blocks."""
+    assert "8802" in ej.JUDGE_BASE_URL
@@ -0,0 +1,200 @@
+"""Tests for the deterministic review scorers."""
+import os
+import sys
+
+import pytest
+
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", "..", "..", "pilot"))
+
+import eval_scores as es  # noqa: E402
+
+
+def f(sev, path="a.py", line=1):
+    return {"severity": sev, "path": path, "line": line, "problem": "p", "fix": ""}
+
+
+# --- finding_rate ---------------------------------------------------------
+
+def test_finding_rate_counts_findings():
+    assert es.finding_rate([f("high"), f("low")]) == 2.0
+
+
+def test_finding_rate_zero_for_silent_review():
+    assert es.finding_rate([]) == 0.0
+    assert es.finding_rate(None) == 0.0
+
+
+# --- severity_info_ratio --------------------------------------------------
+
+def test_info_ratio_all_advisory():
+    assert es.severity_info_ratio([f("info"), f("trivial")]) == 1.0
+
+
+def test_info_ratio_mixed():
+    assert es.severity_info_ratio([f("info"), f("high")]) == 0.5
+
+
+def test_info_ratio_none_when_no_findings():
+    # Undefined, not zero — zero would read as perfectly calibrated.
+    assert es.severity_info_ratio([]) is None
+
+
+def test_info_ratio_unknown_severity_treated_as_medium():
+    # Matches _normalize_finding's fallback, so an odd severity is not
+    # silently counted as advisory.
+    assert es.severity_info_ratio([f("bogus")]) == 0.0
+
+
+# --- severity_max ---------------------------------------------------------
+
+def test_severity_max_picks_highest():
+    assert es.severity_max([f("info"), f("critical"), f("low")]) == "critical"
+
+
+def test_severity_max_none_when_silent():
+    assert es.severity_max([]) == "none"
+
+
+def test_severity_max_case_insensitive():
+    assert es.severity_max([f("HIGH")]) == "high"
+
+
+# --- dropped_findings -----------------------------------------------------
+
+def test_dropped_findings_delta():
+    assert es.dropped_findings(5, 2) == 3.0
+
+
+def test_dropped_findings_never_negative():
+    assert es.dropped_findings(1, 3) == 0.0
+
+
+def test_dropped_findings_none_when_unknown():
+    assert es.dropped_findings(None, 2) is None
+
+
+# --- cost_per_finding -----------------------------------------------------
+
+def test_cost_per_finding_divides():
+    assert es.cost_per_finding(1.0, [f("high"), f("low")]) == 0.5
+
+
+def test_cost_per_finding_silent_review_divides_by_one():
+    # The run still cost money; attributing all of it to "found nothing" is
+    # the honest reading, and it avoids a division by zero.
+    assert es.cost_per_finding(0.25, []) == 0.25
+
+
+def test_cost_per_finding_none_when_unpriced():
+    assert es.cost_per_finding(None, [f("high")]) is None
+
+
+def test_cost_per_finding_none_on_garbage():
+    assert es.cost_per_finding("abc", [f("high")]) is None
+
+
+# --- build_scores ---------------------------------------------------------
+
+def _by_name(events):
+    return {e["body"]["name"]: e["body"] for e in events}
+
+
+def test_build_scores_emits_expected_set():
+    events = es.build_scores(
+        trace_id="t1", findings=[f("high"), f("info")], environment="claude",
+        cost_usd=0.5, dropped_count=2, timestamp="2026-01-01T00:00:00Z",
+    )
+    names = _by_name(events)
+    assert set(names) == {
+        es.FINDING_RATE, es.SEVERITY_INFO_RATIO, es.SEVERITY_MAX,
+        es.DROPPED_FINDINGS, es.COST_PER_FINDING,
+    }
+    assert names[es.FINDING_RATE]["value"] == 2.0
+    assert names[es.SEVERITY_MAX]["value"] == "high"
+    assert names[es.DROPPED_FINDINGS]["value"] == 2.0
+    assert names[es.COST_PER_FINDING]["value"] == 0.25
+
+
+def test_build_scores_all_events_are_score_create_on_the_trace():
+    events = es.build_scores(
+        trace_id="t9", findings=[f("low")], environment="ollama", cost_usd=1.0,
+    )
+    assert all(e["type"] == "score-create" for e in events)
+    assert all(e["body"]["traceId"] == "t9" for e in events)
+    assert all(e["body"]["environment"] == "ollama" for e in events)
+
+
+def test_build_scores_omits_undefined_scores():
+    # No cost and no drop count measured -> those scores are absent, not zero.
+    events = es.build_scores(trace_id="t2", findings=[], environment="ollama")
+    names = set(_by_name(events))
+    assert es.COST_PER_FINDING not in names
+    assert es.DROPPED_FINDINGS not in names
+    assert es.SEVERITY_INFO_RATIO not in names
+    assert names == {es.FINDING_RATE, es.SEVERITY_MAX}
+
+
+def test_build_scores_categorical_value_is_string():
+    events = es.build_scores(trace_id="t3", findings=[f("high")], environment="claude")
+    sev = _by_name(events)[es.SEVERITY_MAX]
+    assert sev["dataType"] == "CATEGORICAL"
+    assert isinstance(sev["value"], str)
+
+
+def test_build_scores_numeric_values_are_floats():
+    events = es.build_scores(
+        trace_id="t4", findings=[f("high")], environment="claude", cost_usd=1,
+    )
+    for name, body in _by_name(events).items():
+        if body["dataType"] == "NUMERIC":
+            assert isinstance(body["value"], float), name
+
+
+def test_build_scores_comment_propagates():
+    events = es.build_scores(
+        trace_id="t5", findings=[f("high")], environment="claude",
+        cost_usd=1.0, comment="cost basis: equivalent:claude-sonnet-5",
+    )
+    assert all("equivalent" in e["body"]["comment"] for e in events)
+
+
+# --- score configs --------------------------------------------------------
+
+def test_every_emitted_score_has_a_config():
+    configured = {c["name"] for c in es.SCORE_CONFIGS}
+    events = es.build_scores(
+        trace_id="t6", findings=[f("high")], environment="claude",
+        cost_usd=1.0, dropped_count=0,
+    )
+    assert set(_by_name(events)) <= configured
+
+
+def test_severity_max_config_covers_every_severity_it_can_emit():
+    labels = {c["label"] for c in
+              next(c for c in es.SCORE_CONFIGS if c["name"] == es.SEVERITY_MAX)["categories"]}
+    assert set(es.SEVERITY_RANK) | {"none"} == labels
+
+
+# --- ingestion envelope ---------------------------------------------------
+
+def test_every_event_carries_a_timestamp():
+    # Ingestion rejects events without one, and reports the rejection as a
+    # per-event 400 inside an HTTP 207 that reads as success.
+    events = es.build_scores(
+        trace_id="t7", findings=[f("high")], environment="claude", cost_usd=1.0,
+    )
+    assert events
+    assert all(e.get("timestamp") for e in events)
+
+
+def test_timestamp_defaults_when_caller_omits_it():
+    events = es.build_scores(trace_id="t8", findings=[f("low")], environment="claude")
+    assert all(isinstance(e["timestamp"], str) and e["timestamp"].endswith("Z") for e in events)
+
+
+def test_explicit_timestamp_is_used():
+    events = es.build_scores(
+        trace_id="t9", findings=[f("low")], environment="claude",
+        timestamp="2026-01-02T03:04:05Z",
+    )
+    assert all(e["timestamp"] == "2026-01-02T03:04:05Z" for e in events)