Nam Pham Dinh ThanhandClaude Sonnet 4.6
838b2473b6
WV4-A: Added 16 Vitest/RTL tests to frontend (jsdom env, fail-before proof verified) WV4-B: Created 12 stub traces for pipeline retention gap; fixed MSYS2/Python path mismatch in context-validate.sh; run-casan4-harness-tests.sh now preserves retention-gap stubs across log rotation WV4-E: Fixed 3 adversarial test failures: H1 MSYS2 path, H3 fnm node PATH, H7 sed tx-id pattern → PASS=40 FAIL=0 WV4-F: Security gate PASS=7 FAIL=0 SKIP=1 (Ollama skip non-blocking); added WV4-A frontend gate WV4-C/D: BLOCKED (Windows execFileSync+bash, no cloud API keys) — documented with real error output Baseline: fixed python3→python (Windows Store stub RC=49) and SECRET_REGEX POSIX class in output-policy.yaml Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
13 lines
511 B
Bash
Executable File
13 lines
511 B
Bash
Executable File
#!/usr/bin/env bash
|
|
set -euo pipefail
|
|
|
|
# CASAN model router (Phase 3, Wave 1) — entry point.
|
|
# model-router.sh <prompt-file> <out-json> [--role classify|judge|generate] [--model ollama:ornith:9b]
|
|
#
|
|
# Thin dispatcher over model-call.py (the HTTP/parse/hardening workhorse) so the
|
|
# documented interface stays stable. All real behavior, allowlist, fail-closed,
|
|
# and usage logging live in model-call.py.
|
|
|
|
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
|
exec python "$SCRIPT_DIR/model-call.py" "$@"
|