Spaces:
Running
Running
Commit History
15 days ago
-
feat(ui): gold for the dashboard start button and strong-match highlights
Claude +1: Claude Sonnet 5.5Unverified signature- Dashboard "Enable agent reports" (primary empty-state action) uses the gold gradient with matching hover/focus/disabled states. - Strong result hero gets a gold hairline edge and a soft glow on the percentage; verdict colours stay green so "possible" (gold) stays distinct. - Success score bars sweep a gold sheen instead of white. Gold value, logo and brand assets are unchanged. Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Q54vp7U5MJ3JrbTQk45zmtecf7f15
-
feat: add premium loading motion across scorer and agent
Cursor Agent +1: Zimuzo EjinkeonyeUnverified signatureGive scoring, agent thinking, and internal loading states a shared night-signal treatment—orbiting desk mark, scan rails, and score reveals—without changing theme, logo, or behavior. Co-authored-by: Zimuzo Ejinkeonye <zimejin07@users.noreply.github.com>97f9abe
-
feat(ui): bring the agent stage to life
Cursor Agent +1: Zimuzo EjinkeonyeUnverified signatureAdd a living signal mark on the empty agent view, search-light and arrival motion for messages, matches, and scores, and keep the existing logo and palette. Co-authored-by: Zimuzo Ejinkeonye <zimejin07@users.noreply.github.com>92b63b1
-
fix(discovery+ui): reject aggregator hubs and polish match cards
Drop Matcha/Indeed/Fossjobs-style index pages before scoring, keep ATS-first angles when the planner LLM is down, and tighten card hierarchy so chat and dashboard feel consistent. Co-authored-by: Cursor <cursoragent@cursor.com>a360cf0
-
feat: deepen specialised job scoring as a standalone fit report
Cursor Agent +1: Zimuzo EjinkeonyeUnverified signatureMake the manual scorer a destination for listings found anywhere: structured extraction, evidence-backed dimensions, confidence, legitimacy cautions, per-user weights and dealbreakers, plus a lean browser extension that hands the current page into /?url=&autorun=1. Unify post-LLM finalize so every score (success and heuristic fallback) attaches accessibility, visa flags, and the new specialised insights. Co-authored-by: Zimuzo Ejinkeonye <zimejin07@users.noreply.github.com>72185bf
-
Put the score explanation first again, and keep the apply-anyway note quieter.
Co-authored-by: Cursor <cursoragent@cursor.com>22241cc -
Lead scored jobs with a match percent, not only a verdict.
Co-authored-by: Cursor <cursoragent@cursor.com>57e740d
-
Bold UI refresh with shared tokens and CSS-only surface updates.
Refresh marketing, agent, dashboard, and ScoreBar styling while keeping routes and behavior unchanged. Co-authored-by: Cursor <cursoragent@cursor.com>e0402df