gahow/aituner
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add Stop-A SLO-boundary guard

Browse Source 
When a truncated probe's measured pass-rate lands within trace.adaptive_stop.
boundary_delta of the SLO target, re-measure on the full window and use that
verdict. Offered-L-C-A convergence cannot see engine-state drift in the window
tail, so a near-knee truncated verdict is untrustworthy (validated: prefix 0.96
vs full 0.946 at threshold 0.08594). The guard fires only on feasibility-knee
probes, so non-boundary probes keep the Stop-A saving. Default delta=0.02.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Gahow Wang
2026-06-15 16:25:24 +08:00
parent 9f52812753
commit dfc823f972
3 changed files with 114 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

55
tests/test_core_flow.py
View File

@@ -53,6 +53,7 @@ from aituner.store import StudyStore
from aituner.trace import load_trace_requests, summarize_window
from aituner.worker import (
_adaptive_replay_set,
_should_extend_on_boundary,
_best_feasible_probe_record,
_latency_summary,
_run_one_request,
@@ -476,6 +477,60 @@ class CoreFlowTests(unittest.TestCase):
self.assertIsNone(no_cert)
self.assertEqual(len(passthrough), len(requests))
def test_boundary_guard_extends_only_near_the_slo_knee(self) -> None:
converged = {"converged": True}
# Truncated, converged, pass-rate on the knee -> re-measure full.
self.assertTrue(
_should_extend_on_boundary(
pass_rate=0.961, target_pass_rate=0.95, certificate=converged,
truncated=True, boundary_delta=0.02,
)
)
self.assertTrue(
_should_extend_on_boundary(
pass_rate=0.946, target_pass_rate=0.95, certificate=converged,
truncated=True, boundary_delta=0.02,
)
)
# Clearly feasible / clearly infeasible -> trust the truncated verdict.
self.assertFalse(
_should_extend_on_boundary(
pass_rate=0.99, target_pass_rate=0.95, certificate=converged,
truncated=True, boundary_delta=0.02,
)
)
self.assertFalse(
_should_extend_on_boundary(
pass_rate=0.50, target_pass_rate=0.95, certificate=converged,
truncated=True, boundary_delta=0.02,
)
)
# Not truncated, not converged, guard disabled, or no certificate -> no extend.
self.assertFalse(
_should_extend_on_boundary(
pass_rate=0.95, target_pass_rate=0.95, certificate=converged,
truncated=False, boundary_delta=0.02,
)
)
self.assertFalse(
_should_extend_on_boundary(
pass_rate=0.95, target_pass_rate=0.95, certificate={"converged": False},
truncated=True, boundary_delta=0.02,
)
)
self.assertFalse(
_should_extend_on_boundary(
pass_rate=0.95, target_pass_rate=0.95, certificate=converged,
truncated=True, boundary_delta=0.0,
)
)
self.assertFalse(
_should_extend_on_boundary(
pass_rate=0.95, target_pass_rate=0.95, certificate=None,
truncated=True, boundary_delta=0.02,
)
)
def test_lca_similarity_matrix_separates_different_profiles(self) -> None:
window = WindowRecord(
window_id="base",