Skip to content

Codebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and architectural decisions via MCP.

fix(mcp): give get_change_risk's truncated test list a way back (#1869)

Raghav Chamadiyaf73290ebc679
diff --git a/docs/agent/MCP_TOOLS.md b/docs/agent/MCP_TOOLS.md
index beb78f825..2e80a98dc 100644
--- a/docs/agent/MCP_TOOLS.md
+++ b/docs/agent/MCP_TOOLS.md
@@ -482,10 +482,13 @@ subject. `baseline_sample_size` reports how many filtered commits informed the
percentile; `features`, `drivers`, and combined `exclude_patterns` make the
result auditable.
-It also returns `impacted_tests`: the tests the per-test coverage map proves
-execute the change's changed *lines* (line-precise, so a narrower set than
-`get_risk`'s file-level `tests_to_run`), capped at ten with `total` and
-`truncated` reporting any overflow. Its `missing_tests` buckets flag
+It also returns `impacted_tests`, whose `tests_to_run` names the tests the
+per-test coverage map proves execute the change's changed *lines* (line-precise,
+so a narrower set than `get_risk`'s file-level `tests_to_run` — same field name,
+because it is the same concern). It is capped at ten, with `total` and
+`truncated` reporting the overflow and the tail written to the omission store:
+on `truncated: true` the response carries an `omission_marker`, and
+`repowise expand <ref>` returns the rest. Its `missing_tests` buckets flag
`untested_changes` (covered file, uncovered change), `stale_test_candidates`
(covered lines whose guarding test file is absent from the diff), `covered`, and
`no_coverage_data` (files absent from the map). When no map is ingested the
@@ -497,6 +500,9 @@ the same distinction in one word: `measured`, `inferred`, or absent. Build the
measured map with `coverage run --contexts=test` followed by
`repowise coverage add`.
+> **Output-schema change.** `impacted_tests.tests` is now
+> `impacted_tests.tests_to_run`, matching `get_risk`'s directive.
+
When the changed files carry counted bug fixes, the response also holds
`prior_fixes`: per file, how many past bug-fix commits touched it
(`fix_count`), how many of the change's lines fall inside the ranges one of
diff --git a/packages/server/src/repowise/server/mcp_server/tool_change_risk.py b/packages/server/src/repowise/server/mcp_server/tool_change_risk.py
index 692676cfd..cfdf0f559 100644
--- a/packages/server/src/repowise/server/mcp_server/tool_change_risk.py
+++ b/packages/server/src/repowise/server/mcp_server/tool_change_risk.py
@@ -21,6 +21,7 @@ from repowise.core.analysis.change_risk import (
)
from repowise.core.analysis.pr_blast import rank_tests_by_reach
from repowise.core.registry import mcp_tool_registry as mcp
+from repowise.server.mcp_server._budget import OmissionCollector
from repowise.server.mcp_server._helpers import (
_get_repo,
_resolve_repo_context,
@@ -29,8 +30,8 @@ from repowise.server.mcp_server._helpers import (
from repowise.server.mcp_server._meta import build_meta as _build_meta
#: Cap on the line-precise impacted-test list, matching the get_risk directive's
-#: ``tests_to_run`` cap so both surfaces stay glanceable. ``total`` and
-#: ``truncated`` report the overflow rather than silently dropping it.
+#: ``tests_to_run`` cap so both surfaces stay glanceable. The tail goes to the
+#: omission store, so ``truncated: true`` is recoverable rather than a dead end.
_IMPACTED_TESTS_LIMIT = 10
#: Cap on the per-file prior-fix list, matching ``_IMPACTED_TESTS_LIMIT`` so both
@@ -49,22 +50,22 @@ async def get_change_risk(
"""Score a live commit, ``base..head`` range, or uncommitted work.
Use this for a pre-merge read on a commit or PR range. Distinct from
- ``get_risk``, which assesses indexed files and PR blast radius. The filters
- below also apply to the baseline behind the repository percentile.
+ ``get_risk``, which scores indexed files and PR blast radius. The filters
+ below also apply to the percentile baseline.
Lead with ``fix_history``: the recency-weighted bug-fix record of the files
touched, ``files`` naming where the pressure sits. It separates a surgical
- edit to a file that keeps breaking from a bulk rename of files that never
- have. ``score`` measures diff size and spread, not where the change lands
+ edit to a bug magnet from a bulk rename of files that never break. ``score`` measures diff size and spread, not where the change lands
(see ``score_measures``); calibrated per commit, so a PR-sized change reads
high by construction. ``risk_percentile`` ranks that shape against recent
commits.
- ``impacted_tests`` names the tests for this change; ``missing_tests`` the
- uncovered lines. ``basis``: ``measured`` = a coverage map proves those tests
- run the changed *lines*; ``inferred`` = test files the graph shows
- reaching it (candidates, file-level, no ingest needed). No map is never
- "untested": ``status`` ``no_map`` means run the suite. ``prior_fixes``
+ ``impacted_tests.tests_to_run`` names the tests for this change;
+ ``missing_tests`` the uncovered lines. ``basis``: ``measured`` = a coverage
+ map proves those tests run the changed *lines*; ``inferred`` = test files
+ the graph shows reaching it (candidates, file-level). No map is never
+ "untested": ``no_map`` means run the suite. On ``truncated``, expand
+ ``omission_marker`` for the tail. ``prior_fixes``
counts past fixes whose lines overlap this diff.
Args:
@@ -117,7 +118,10 @@ async def get_change_risk(
result.riskignore_excludes + result.request_excludes,
working_tree=result.working_tree,
)
- payload["impacted_tests"] = await _impacted_tests_block(ctx, changed, changed_error)
+ collector = OmissionCollector("get_change_risk", repo_root=ctx.path)
+ payload["impacted_tests"] = await _impacted_tests_block(
+ ctx, changed, changed_error, collector
+ )
prior_fixes = await _prior_fixes_block(ctx, changed)
if prior_fixes is not None:
payload["prior_fixes"] = prior_fixes
@@ -132,6 +136,7 @@ async def get_change_risk(
targets=sorted(changed) or None,
extra={"source": "live_git"},
)
+ collector.attach(payload)
return payload
@@ -197,7 +202,7 @@ def _empty_impacted(status: str, summary: str) -> dict[str, Any]:
return {
"status": status,
"map_present": False,
- "tests": [],
+ "tests_to_run": [],
"total": 0,
"truncated": False,
"missing_tests": {
@@ -420,8 +425,19 @@ def _overlap_count(changed_lines_now: set[int], old_ranges_json: str) -> int:
return hits
+def _cap_tests(tests: list[str], collector: OmissionCollector, label: str) -> list[str]:
+ """First _IMPACTED_TESTS_LIMIT ids; the tail goes to the omission store."""
+ if len(tests) > _IMPACTED_TESTS_LIMIT:
+ collector.add(
+ f"impacted_tests.tests_to_run ({label}) beyond cap={_IMPACTED_TESTS_LIMIT} "
+ f"({len(tests) - _IMPACTED_TESTS_LIMIT} dropped)",
+ tests[_IMPACTED_TESTS_LIMIT:],
+ )
+ return tests[:_IMPACTED_TESTS_LIMIT]
+
+
async def _inferred_impacted(
- session: Any, repo_id: str, changed_files: list[str]
+ session: Any, repo_id: str, changed_files: list[str], collector: OmissionCollector
) -> dict[str, Any]:
"""Graph-inferred candidates for a repo with no coverage map.
@@ -460,7 +476,7 @@ async def _inferred_impacted(
block.update(
{
"basis": "inferred",
- "tests": tests[:_IMPACTED_TESTS_LIMIT],
+ "tests_to_run": _cap_tests(tests, collector, "inferred"),
"total": total,
"truncated": total > _IMPACTED_TESTS_LIMIT,
"summary": (
@@ -482,6 +498,7 @@ async def _impacted_tests_block(
ctx: Any,
changed: dict[str, set[int]],
changed_error: tuple[str, str] | None,
+ collector: OmissionCollector,
) -> dict[str, Any]:
"""Line-precise impacted tests + honest missing-test buckets for the change.
@@ -510,7 +527,7 @@ async def _impacted_tests_block(
repo_id = (await _get_repo(session)).id
report = await detect_missing_tests(session, repo_id, changed)
if report.map_empty:
- return await _inferred_impacted(session, repo_id, sorted(changed))
+ return await _inferred_impacted(session, repo_id, sorted(changed), collector)
by_file: dict[str, list[str]] = {}
for source_file, lines in changed.items():
rows = await tests_covering(session, repo_id, source_file, lines=lines)
@@ -526,7 +543,7 @@ async def _impacted_tests_block(
"status": "map_present",
"basis": "measured",
"map_present": True,
- "tests": tests[:_IMPACTED_TESTS_LIMIT],
+ "tests_to_run": _cap_tests(tests, collector, "measured"),
"total": total,
"truncated": total > _IMPACTED_TESTS_LIMIT,
"missing_tests": _serialize_missing(report),
diff --git a/tests/unit/server/mcp/test_change_risk.py b/tests/unit/server/mcp/test_change_risk.py
index cbb625af5..49b34dfdc 100644
--- a/tests/unit/server/mcp/test_change_risk.py
+++ b/tests/unit/server/mcp/test_change_risk.py
@@ -217,7 +217,7 @@ async def test_impacted_tests_line_precise_hit_and_miss(tmp_path, monkeypatch) -
assert it["basis"] == "measured"
assert it["map_present"] is True
# app.py line 3 is covered -> its test is named; other/new are not covering.
- assert it["tests"] == ["tests/test_app.py::test_app"]
+ assert it["tests_to_run"] == ["tests/test_app.py::test_app"]
assert it["total"] == 1
assert it["truncated"] is False
@@ -254,7 +254,7 @@ async def test_impacted_tests_no_map_is_unknown_not_untested(tmp_path, monkeypat
# Nothing is seeded in the graph either, so neither tier can speak.
assert it["status"] == "no_map"
assert it["map_present"] is False
- assert it["tests"] == []
+ assert it["tests_to_run"] == []
# Honest degradation: no untested claim, a "run the suite" summary instead.
assert it["missing_tests"]["untested_changes"] == []
assert "run the full suite" in it["summary"]
@@ -304,7 +304,7 @@ async def test_impacted_tests_falls_back_to_the_graph_without_a_map(tmp_path, mo
assert it["status"] == "inferred"
assert it["basis"] == "inferred"
assert it["map_present"] is False
- assert it["tests"] == ["tests/test_round_trips.py"]
+ assert it["tests_to_run"] == ["tests/test_round_trips.py"]
assert it["missing_tests"]["untested_changes"] == []
# Answered by the import tier: there is no call edge here, which is exactly
# when the weaker tier is allowed to speak.
@@ -337,8 +337,11 @@ async def test_impacted_tests_overflow_cap_is_honest(tmp_path, monkeypatch) -> N
it = result["impacted_tests"]
assert it["total"] == 12
- assert len(it["tests"]) == 10
+ assert len(it["tests_to_run"]) == 10
assert it["truncated"] is True
+ # The 2 over the cap are recoverable, not dropped.
+ assert "omission_marker" in result
+ assert result["_meta"]["omitted"]["refs"]
@pytest.mark.asyncio