feat: implement multi-stage candidate ingestion and matching pipeline with UI tracking and backend schema support

feat: implement stage 1 candidate retrieval and scoring logic using Qdrant and multi-factor heuristics

feat: add candidate detail page for viewing role alignment and skill coverage analysis

feat: implement matching router and stage 2 neural reranking logic

feat: slider max dynamically set from CSV row count (header excluded)

fix: use real candidate count, remove stage2 cap, add full error logging

feat: enforce native preloading of neural model to prevent HTTP connection timeouts

fix(ml): restrict cross-encoder batch_size to prevent OOM kills on uncapped arrays

feat: implement matching router with two-stage retrieval, reranking, and async explanation generation

chore(db): create alembic migration script to append session_id to job_descriptions

fix(ui): add navbar link to API Docs alongside system reset

fix: resolve TS type mismatch for parsed_summary array and add percentage sign to match list UI

fix(ui): add percentage sign to match score on candidate list vie

fix: render db array profile summary as bullet points instead of raw string

fix: replace backend RRF with true percentage math so Stage2 final score aligns with frontend weights

fix: resolve TS build error for ComponentScores casting

fix: Duplicate state Removed from tsx

feat: candidate search bar + full student-perspective redesign of profile page

fix: cross-session JD leak, show match% not rank, pass all candidates through pipeline, fix growth_velocity always 60

fix: growth_velocity always 60% bug - handle JSON string and empty work_exp

feat: user-controlled pipeline depth sliders for stage1/stage2 retrieval caps

fix: cap reranker input to top-40 and fix nginx send timeout to prevent 504

fix: merge all process stderr to stdout for full HF log visibility

feat: implement matching router with support for retrieval, reranking, and candidate explanation workflows

feat: add system reset page and centralize API utility functions

feat: add admin endpoint to reset Postgres schema and Qdrant collection via Alembic migrations

feat: implement admin endpoint and UI for database and vector store reset

feat: initialize SQLAlchemy async database engine and session management with Neon-compatible configuration

feat: implement backend matching pipeline and update project documentation

feat: implement async SQLAlchemy database engine and session management with Neon-compatible configurations

feat: implement session management UI and pre-bake AI models into Docker image

feat: add frontend system health diagnostics and mute HF Celery gossip

feat: implement backend ingestion pipeline with Celery workers, Qdrant integration, and session management

feat: implement FastAPI application with Pinecone/Redis integration and candidate matching router

feat: implement backend candidate matching pipeline with Pinecone integration, FastAPI routers, and ingestion workers.

fix: resolve JSX syntax error in sessions page

fix: resolve JSX syntax error in sessions page

feat: complete rewrite of UI/UX for streamlining and pruning

fix: enforce relative api routing in production

feat: implement automated ingestion pipeline with state persistence and add database maintenance utilities

feat: migrate aesthetic UI icons to lucide-react vector blocks

feat: resolve promise racing in sessions UI and build smart background tracking loaders

feat: stabilize celery loops, add redis caching, and scale stage 2 neural limit to 250

refactor: unified session view, pipeline polling, db wipe

feat: updated pipeline to support matching against multiple JDs sequentially

fix: resolve TypeScript errors and finalize frontend build

feat: add pipeline page, session delete with Qdrant cleanup, explain worker, and final frontend polish

feat: finalize frontend candidate UI and containerization workflow

fix: resolve asyncpg ssl connection errors and Qdrant strict payload filtering

feat: implement session-based candidate matching architecture