| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| README.md | 2026-03-01 | 1.5 kB | |
| v1.6.0 -- Credibility Hardening source code.tar.gz | 2026-03-01 | 1.4 MB | |
| v1.6.0 -- Credibility Hardening source code.zip | 2026-03-01 | 1.6 MB | |
| Totals: 3 Items | 3.0 MB | 0 | |
What's New
Production Features Wired into Server
- API key authentication (
X-API-Keyheader, configurable viaapi_keys) - Correlation IDs (
X-Request-IDecho/generate on every response) - Audit logging wired into
/v1/reviewand/v1/processendpoints - Tenant routing via
X-Tenant-IDheader +/v1/tenantsmanagement API - Rate limiting via slowapi (
rate_limit_rpmconfig) - Streaming oversight via WebSocket
/v1/streamwithStreamingKernel
Streaming Debug Mode
streaming_debug=TrueonStreamingKernelemits per-token snapshots (window_avg,trend_drop,accumulated_tokens)TokenEvent.debug_infoandStreamSession.debug_logfor full trace
E2E Benchmark Proof
--baselinemode: unguarded hallucination rate--comparemode: side-by-side delta table (baseline vs guarded)--output-jsonfor CI artifact upload- New
benchmarks/ragbench_eval.pyfor real-world RAG pipeline evaluation - Regression suite: 6th test
test_e2e_heuristic_delta(catch=70%, FPR=10%)
Documentation
- Threshold Tuning Guide — heuristic vs NLI, domain presets, sweep instructions
- KB Ingestion Tutorial — GroundTruthStore, VectorGroundTruthStore, ChromaDB, multi-tenant
- Production Checklist — 12-item deployment readiness checklist
- Streaming Architecture — ASCII diagram, NLI construction, debug mode docs
Test Coverage
- 835 tests pass, 0 failures across Python 3.10/3.11/3.12
- 19 new tests (auth, audit, tenant, streaming debug)