hermes/cto
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Include CTO cancel coverage in evals

Browse Source
This commit is contained in:
Svrnty
2026-05-25 13:15:28 -04:00
parent a576288d49
commit cf3d10f8b9
4 changed files with 27 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files
evals/runners/run-local-regression.py
+2 -1
View File
@@ -162,6 +162,7 @@ def build_report(output: Path) -> dict[str, Any]:
"tests/test_live_tool_callback_events.py",
"tests/test_cto_webui_journal_e2e.py",
"tests/test_cto_browser_e2e.py",
"tests/test_cancel_interrupt.py",
],
cwd=WEBUI_ROOT,
timeout=180,
@@ -197,7 +198,7 @@ def build_report(output: Path) -> dict[str, Any]:
_eval_result("promotion-fixture-execution", fixtures, ["cto/evals/reports/2026-05-25-promotion-fixture-execution.yaml"]),
_eval_result("live-promotion-readiness", live_readiness, ["cto/evals/reports/2026-05-25-live-promotion-readiness.yaml"]),
_eval_result("static-prd-contract", prd, ["tests/e2e/test_j_cto_webui_prd.py"]),
_eval_result("webui-cto-event-browser", webui, ["hermes-webui/tests/test_cto_browser_e2e.py"]),
_eval_result("webui-cto-event-browser", webui, ["hermes-webui/tests/test_cto_browser_e2e.py", "hermes-webui/tests/test_cancel_interrupt.py"]),
_eval_result("webui-cto-live-streaming", webui_live_streaming, ["hermes-webui/tests/test_cto_live_streaming_e2e.py"]),
_eval_result("live-profile-drift", drift, ["cto/evals/reports/2026-05-25-live-drift.yaml"]),
_eval_result("eval-report-scoring", score, ["cto/evals/reports/*.yaml"]),