Fix location/freshness filters and make ever-jobs URL configurable

Generate a CSV report and persist report files to HF Dataset

Persist run history + resumes to a private HF Dataset (Option B)

Add address/location to resume contact header for ATS checks

Add per-job resume download buttons on result cards

Fix file uploader styling and show deploy timestamp

Add model-independent LLM provider abstraction with schema validation

feat(ui): batch risk column + bulk vault controls; isolate test vaults

feat(ats): AUTO_AGGRESSIVE mode + risk severity levels

feat(ats): vault source labels + risky-term table + batch summary table

feat(ats): independent validator + anti-cheat — break circular self-scoring

feat(ats): Candidate Experience Vault + UI status tiers (90%+ pipeline complete)

feat(ats): no-compromise 90%+ pipeline — fit expansion + auto-repair + status

feat(ats): v2 pipeline — structured JD, evidence matching, weighted 2-part score

feat(ats): push coverage to 90% — LLM jd_skills union + comprehensive Skills

fix(resume): move SKILLS section after KEY ACHIEVEMENTS

feat(ats): redesign to industry standard — skills-only extraction + Skills section

feat(ats): smart fill — keep ALL keywords (distributed), drop buzzwords

fix(ats): honest meaningful JD-driven keywords — no stuffing, no inflation

feat(ats): comprehensive JD keyword extraction (match Jobalytics breadth)

feat(ats): maximum keyword coverage — inject ALL missing terms (uncapped)

fix(platforms): visible ever-jobs sidecar status + Node20 ESM CommonJS fix

feat: honest+conservative ATS score + broader keywords + 6hr/1day freshness

fix(ui): re-upload replaces resume + show built profile on same page

feat(ui): custom role entry + expanded role list (step 2)

fix(ui): white text on download + link buttons (was black-on-black)

feat(ux): incremental per-job results + early history checkpoint

feat(phase5.3): guardrail — restrict resume tailoring to capable-tier models

feat(phase5.1): calibrated keyword extraction — match real ATS checkers

docs(phase5): plan ATS scorer calibration to real third-party checkers

fix(phase4.5): natural keyword weaving + lemma-dedup (prose quality)

fix(phase4.4): allowlist keyword extraction — the real root-cause fix

fix(hf): allow extensionless ESM imports in ever-jobs sidecar

fix(phase4.3): systemic JD keyword extraction — works on any new JD

fix(phase4.2): backfill dropped roles + enforce recruiter pitch

fix(phase4.1): aggressive bullet weaving + canonical-tuned scoring

feat(phase4): canonical Resume model + single locked visual format

fix(resume): bugs A/B/C from production audit — table-header noise, orphan lines, duplicate dates

docs: add AGENT_CONTEXT.md — full project handoff doc for new agents/IDEs

fix(ui+ats): remove title, fix dark-on-dark inputs, aggressive injection for 90%+

feat(ats): Phase 3 — lemma+phrase scorer + liberal LLM policy + recruiter pitch

feat(resume): v2 bullet-rewriter contract — no CORE COMPETENCIES section

fix(resume): remove duplicate header in template path + canonical skill casing

fix(resume): remove footer, mirror DOCX in PDF, ATS scores 90%+

fix(resume+ats): preserve full resume content; honest ATS scoring

fix(ui): prevent resume upload rerun loop, show start button on all steps

fix(ui+docker): persist wizard state across steps, disable webpack in nest-cli

feat(ui): convert setup into step-by-step wizard with stepper navigation

feat(ui): redesign to light-themed SaaS dashboard with guided setup flow

fix(hf-spaces): use nest start (ts-node) instead of nest build to avoid webpack