Skip to content

Expose public submission failure diagnostics #524

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
msaroufim merged 1 commit into from
Jul 29, 2026
Merged

Expose public submission failure diagnostics #524

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 12 additions & 0 deletions src/kernelbot/api/main.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1133,6 +1133,18 @@ async def get_user_submission(
response_run = {key: run[key] for key in run_fields}
if not run["secret"] and run["mode"] in ("test", "benchmark"):
response_run["result"] = run["result"]
# Runtime tracebacks, compiler errors, and process failures are
# stored separately from the structured evaluator result. Expose
# them only for the authenticated owner's public runs; secret-run
# diagnostics can contain private validation details.
meta = run.get("meta") or {}
response_run["diagnostics"] = {
key: meta[key]
for key in ("stdout", "stderr", "success", "exit_code", "duration")
if key in meta
}
if run.get("compilation") is not None:
response_run["diagnostics"]["compilation"] = run["compilation"]
runs.append(response_run)
runner_queue = await get_submission_runner_queue_status(submission)
return {
Expand Down
39 changes: 39 additions & 0 deletions tests/test_admin_api.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -289,6 +289,14 @@ def test_submission_details_include_stored_run_results(self, test_client, mock_b
"score": None,
"passed": False,
"result": test_result,
"meta": {
"stdout": "",
"stderr": "Traceback: public test failure",
"success": False,
"exit_code": 1,
"duration": 1.25,
},
"compilation": None,
},
{
"start_time": "2026-07-06T12:00:00Z",
Expand All @@ -299,6 +307,18 @@ def test_submission_details_include_stored_run_results(self, test_client, mock_b
"score": None,
"passed": True,
"result": benchmark_result,
"meta": {
"stdout": "benchmark output",
"stderr": "",
"success": True,
"exit_code": 0,
"duration": 2.5,
},
"compilation": {
"success": True,
"stdout": "",
"stderr": "",
},
},
{
"start_time": "2026-07-06T12:00:00Z",
Expand All @@ -309,6 +329,13 @@ def test_submission_details_include_stored_run_results(self, test_client, mock_b
"score": None,
"passed": True,
"result": {"secret-result": "must not be exposed"},
"meta": {
"stderr": "SECRET_TRACEBACK_SENTINEL",
"exit_code": 1,
},
"compilation": {
"stderr": "SECRET_COMPILER_SENTINEL",
},
},
{
"start_time": "2026-07-06T12:00:00Z",
Expand Down Expand Up @@ -353,14 +380,26 @@ def test_submission_details_include_stored_run_results(self, test_client, mock_b
assert response.status_code == 200
runs = response.json()["runs"]
assert runs[0]["result"] == test_result
assert runs[0]["diagnostics"] == {
"stdout": "",
"stderr": "Traceback: public test failure",
"success": False,
"exit_code": 1,
"duration": 1.25,
}
assert runs[1]["result"] == benchmark_result
assert runs[1]["diagnostics"]["stdout"] == "benchmark output"
assert runs[1]["diagnostics"]["compilation"]["success"] is True
assert "result" not in runs[2]
assert "diagnostics" not in runs[2]
assert runs[2]["secret"] is True
assert runs[2]["passed"] is True
assert "result" not in runs[3]
assert "result" not in runs[4]
assert "must not be exposed" not in response.text
assert "PROFILE_SENTINEL" not in response.text
assert "SECRET_TRACEBACK_SENTINEL" not in response.text
assert "SECRET_COMPILER_SENTINEL" not in response.text


class TestAdminStats:
Expand Down
Loading