test descriptions

tests/test_adaptive_audit_sampling.py

@@ -21,27 +21,32 @@ MODEL = "stub-model"
 
 
 def test_newcomer_gets_elevated_audit_rate():
+    "Newcomer gets elevated audit rate\n\nTags: general"
+
     sampler = AdaptiveAuditSampler()
     rate = sampler.wallet_base_rate(completed_job_count=0, reputation=1.0)
     assert 0.20 <= rate <= 0.30
 
 
 def test_veteran_in_good_standing_floors_near_target():
+    "Veteran in good standing floors near target\n\nTags: general"
+
     sampler = AdaptiveAuditSampler()
     rate = sampler.wallet_base_rate(completed_job_count=1000, reputation=1.0)
     assert rate == pytest.approx(0.02)
 
 
 def test_veteran_rate_never_drops_below_floor():
+    "Veteran rate never drops below floor\n\nTags: general"
+
     sampler = AdaptiveAuditSampler(AuditRateConfig(veteran_floor=0.02))
     rate = sampler.wallet_base_rate(completed_job_count=10_000, reputation=1.0)
     assert rate >= 0.02
 
 
 def test_low_reputation_wallet_sampled_more_than_high_reputation_wallet():
-    """Red (test-first item 1): a uniform sampler ignores reputation. A
-    low-reputation wallet must get a higher rate than a high-reputation one
-    with the same tenure."""
+    "Red (test-first item 1): a uniform sampler ignores reputation.\n\nTags: security, wallet"
+
     sampler = AdaptiveAuditSampler()
     low_rep_rate = sampler.sample_rate_for(completed_job_count=200, reputation=0.1)
     high_rep_rate = sampler.sample_rate_for(completed_job_count=200, reputation=1.0)
@@ -49,6 +54,8 @@ def test_low_reputation_wallet_sampled_more_than_high_reputation_wallet():
 
 
 def test_low_reputation_escalates_even_for_a_tenured_wallet():
+    "Low reputation escalates even for a tenured wallet\n\nTags: security, wallet"
+
     sampler = AdaptiveAuditSampler()
     rate = sampler.wallet_base_rate(completed_job_count=1000, reputation=0.0)
     assert rate == pytest.approx(sampler.config.newcomer_rate)
@@ -58,9 +65,8 @@ def test_low_reputation_escalates_even_for_a_tenured_wallet():
 
 
 def test_fleet_wide_audit_rate_tracks_configured_target_within_one_point():
-    """Test-first item 2: over >=1000 requests with a fixed seed and a mixed
-    wallet population, the measured fleet audit rate lands within +-1.0
-    percentage point of the configured 5% target."""
+    "Test-first item 2: over >=1000 requests with a fixed seed and a mixed\n\nTags: general"
+
     sampler = AdaptiveAuditSampler(random_seed=1234)
     rng = random.Random(99)
 
@@ -82,6 +88,8 @@ def test_fleet_wide_audit_rate_tracks_configured_target_within_one_point():
 
 
 def test_fleet_wide_audit_rate_respects_custom_target():
+    "Fleet wide audit rate respects custom target\n\nTags: general"
+
     sampler = AdaptiveAuditSampler(AuditRateConfig(target_rate=0.10), random_seed=42)
     audited = sum(
         1
@@ -93,6 +101,8 @@ def test_fleet_wide_audit_rate_respects_custom_target():
 
 
 def test_sampling_is_deterministic_for_a_fixed_seed():
+    "Sampling is deterministic for a fixed seed\n\nTags: general"
+
     sampler_a = AdaptiveAuditSampler(random_seed=7)
     sampler_b = AdaptiveAuditSampler(random_seed=7)
     decisions_a = [sampler_a.should_audit(completed_job_count=0, reputation=1.0) for _ in range(200)]
@@ -104,6 +114,8 @@ def test_sampling_is_deterministic_for_a_fixed_seed():
 
 
 def test_tripwire_flag_bumps_audit_rate_for_that_wallet():
+    "Tripwire flag bumps audit rate for that wallet\n\nTags: security, wallet"
+
     sampler = AdaptiveAuditSampler()
     normal_rate = sampler.sample_rate_for(completed_job_count=800, reputation=1.0, tripwire=False)
     flagged_rate = sampler.sample_rate_for(completed_job_count=800, reputation=1.0, tripwire=True)
@@ -111,11 +123,8 @@ def test_tripwire_flag_bumps_audit_rate_for_that_wallet():
 
 
 def test_tripwire_does_not_change_other_wallets_rate():
-    """A tripwire hit must never leak the multiplier into the shared
-    budget-balance history -- only the wallet's un-boosted base rate is
-    recorded, so a flagged decision affects the running budget scale exactly
-    like a plain decision for the same wallet would, and never inflates or
-    depresses everyone else's rate on top of that."""
+    "A tripwire hit must never leak the multiplier into the shared\n\nTags: security, wallet"
+
     flagged = AdaptiveAuditSampler(random_seed=5)
     flagged.should_audit(completed_job_count=800, reputation=1.0, tripwire=True)
 
@@ -128,15 +137,21 @@ def test_tripwire_does_not_change_other_wallets_rate():
 
 
 def test_detect_output_tripwire_flags_repetition_loop():
+    "Detect output tripwire flags repetition loop\n\nTags: general"
+
     degenerate = " ".join(["loop"] * 20)
     assert detect_output_tripwire(degenerate) is True
 
 
 def test_detect_output_tripwire_flags_empty_output():
+    "Detect output tripwire flags empty output\n\nTags: general"
+
     assert detect_output_tripwire("") is True
 
 
 def test_detect_output_tripwire_passes_normal_prose():
+    "Detect output tripwire passes normal prose\n\nTags: general"
+
     normal = "The quick brown fox jumps over the lazy dog near the riverbank."
     assert detect_output_tripwire(normal) is False
 
@@ -163,8 +178,8 @@ def _record_event(contracts, session_id: str, wallet: str) -> None:
 
 
 def test_validator_uses_audit_sampler_when_configured(reference_node):
-    """A flagged low-reputation wallet gets audited far more often than a
-    veteran in good standing when routed through the same validator."""
+    "A flagged low-reputation wallet gets audited far more often than a\n\nTags: general"
+
     contracts = LocalSolanaContracts()
     contracts.registry.record_completed_jobs("wallet-veteran", 800)
     for _ in range(9):