Spaces:
Sleeping
Sleeping
Commit History
-
Wave 4: doc deltas, language-alias coverage, LLM output budgets
- SKILL_ALIASES: add Rust/Go/C#/Ruby/PHP/Swift/Kotlin/Scala/Dart/Elixir/Haskell (kept in sync with fraud.LANGUAGE_SKILLS) plus Spring Boot/Rails/Terraform/ Redis/Spark/Streamlit - the A8 vocabulary filter was silently dropping languages the fraud engine cross-checks, killing the language_not_found signal - interview questions + JD parse: raise max_tokens (900->1600, 700->1200); reasoning models spend completion budget thinking, and a tight cap truncated content to empty, silently forcing the template fallback - PRD/ARCHITECTURE: document requirements matrix, sample demo mode, parallel prefetch, blind-aware exports, 3-strike circuit breaker, scoring discipline Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>e70399f -
Grifter Filter v0.2: evidence-verified resume screening with fraud detection
Full rewrite of the pipeline into a deployable product: - Tinker integration via the documented OpenAI-compatible endpoint (openai/gpt-oss-20b, reasoning separated server-side, ~$0.003/candidate), with circuit breaker and full heuristic fallback - 7-signal fraud engine (contributor share, commit clustering, star anomalies, identity mismatch, language cross-check, account-age gap, AI-authorship markers) over a cached GitHubSnapshot - FEVER-discipline claim judging: REFUTED requires contradicting evidence, evidence_index resolved locally to kill hallucinated links - Recruiter UX: per-candidate PDF reports, targeted interview questions, side-by-side Compare page, shortlist tagging, evidence deep-links - Trust layer: blind-screening mode, published Methodology page, audit-log export, no-auto-reject disclaimers - PRD.md + ARCHITECTURE.md, HF Spaces front-matter, 29 passing tests Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>b78196e