Spaces:
Sleeping
Sleeping
Commit History
-
Parallel GitHub prefetch + JD Requirements Matrix
- pipeline: parse all resumes first, then prefetch unique GitHub snapshots concurrently (ThreadPoolExecutor, 4 workers) into the TTL cache before the sequential LLM loop; cache access now lock-guarded - new resumesort/requirements_matrix.py: LLM parses the JD into atomic requirements (deterministic bullet-split fallback), each candidate graded met/partial/none per requirement via verified-claim and skill matching; refuted claims veto the skill shortcut so a contradicted flagship claim can never grade "met" - Compare page: Requirements Matrix section - must-haves first, badge cells, evidence links, JD-hash session cache - 4 new tests incl. matrix rendering and the refuted-veto case (48 total) Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>c3998ce -
UI overhaul: dark teal theme, editable ranking, tabbed detail, sample demo mode
- Theme: dark blue-charcoal + verification-teal accent, semantic badge hues (green=SUPPORTED, yellow=NEI, red=REFUTED/high, orange=warn), Inter font - Landing: hero + value-prop cards + one-click "Try sample data" (3 fictional candidates covering strong/inflated/no-github archetypes, zero API calls) - Ranking: st.data_editor with inline shortlist SelectboxColumn, ProgressColumn final score, pinned candidate column; Tinker banners folded into a Run-health popover; downloads into an Export popover; 4 bordered KPI metrics - Detail: header card (skills chips + score meter bars), segmented-control decision, tabs (Overview / Claims & evidence / Authenticity / Interview kit); raw JSON blobs replaced with a field grid + Raw-data popover; claim cards sorted REFUTED-first with verdict filter pills - Compare: bordered cards, per-metric winner highlighting, verdict/fraud chips - Methodology: tabbed, badge vocabulary matching the app - New AppTest smoke tests execute all three pages h…a36589b -
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