Phase 2A scaffolding complete (per spec §7.2): - oracle.rs: OracleAction enum + 3 oracle policies (flat, drift, OU) - harness.rs: BehavioralResult + evaluate_policy_on_market stub. Trainer-side methods (eval_actions_on_features, read_isv_for_test) are documented gap #7; Phase 2B tests add them per-test as needed. - pre-commit hook: cargo test -p ml --test behavioral_suite gates argo-train.sh per spec §4.5 discipline rule. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
22 lines
720 B
Bash
Executable File
22 lines
720 B
Bash
Executable File
#!/bin/bash
|
|
# .claude/helpers/pre_commit_behavioral_suite.sh
|
|
#
|
|
# SP15 Phase 2 — behavioral suite gate. Blocks argo-train.sh if any
|
|
# behavioral test fails. Suite runs <10 min on dev RTX 3050 Ti.
|
|
set -euo pipefail
|
|
|
|
cd "$(git rev-parse --show-toplevel)"
|
|
|
|
echo "Running SP15 behavioral suite (gate for argo-train.sh)..."
|
|
|
|
if ! SQLX_OFFLINE=true CUDA_COMPUTE_CAP=86 \
|
|
cargo test -p ml --test behavioral_suite --features cuda \
|
|
-- --include-ignored --test-threads=1 2>&1 \
|
|
| tee /tmp/sp15_behavioral_suite.log; then
|
|
echo "Behavioral suite FAILED. argo-train.sh blocked."
|
|
echo " See /tmp/sp15_behavioral_suite.log for details."
|
|
exit 1
|
|
fi
|
|
|
|
echo "Behavioral suite PASS — argo-train.sh unblocked."
|