feat: V1 noise fix, real progress animation via SSE

fix: drop naked keyword bullets + always re-extract on job switch

fix: add build-essential to Dockerfile for better-sqlite3 native compilation

fix: auto-retry on 503 wakeup; fix page content cut off by panel

fix: handle 503 Space-waking response with friendly retry message

perf+fix: parallelize V2 curate+rank; fix extension overlay covering page

feat(r36): keyword_placer wired into V2 pipeline — bullet-level placement guidance

feat: extract up to 100 keywords + match real-checker breadth (Jobalytics gap)

fix: order curated keywords by importance so the 55-cap keeps top keywords, not first 55

fix: broaden curated keyword extraction to match real checkers (Jobalytics 52% gap)

feat: coverage backstop — guaranteed >=90% ATS in Maximum ATS Mode (R35)

feat(phase-15): LLM-curated scoring denominator (generalizes) + weave-to-90 + fixes (R34)

feat: make V2 the default generation mode across all surfaces

docs(phase-14): mark complete in roadmap (R33)

feat(phase-14): reliable honest 90%+ ATS — skill-filter + weave-to-target + parseability (R33)

docs(phase-14): plan reliable 90%+ ATS — blocklist skill-filter + weave-to-target + parseability (R33)

docs(14-reliable-90plus-ats): create phase 14 plan

docs(phase-14): research reliable 90%+ ATS — skill-filter, weave loop, parseability, acronym doubling (R33)

docs(phase-13): mark complete in roadmap (atomic fix done; 90% needs Phase 14 denominator filter)

feat(phase-13): atomic ATS scoring + coverage-aware weave + feed isolation (R32)

docs(phase-13): plan reliable honest 90% ATS — atomic scoring + JD isolation + coverage-aware weave (R32)

docs(13-reliable-90-ats): create phase 13 plan

docs(phase-13): research atomic scoring + single-job isolation + coverage-aware weaving

feat(phase-12e): V2 JD sanitizer — strip scraped job-board page chrome (R31)

fix(extension): MV3 keep-alive so long V2 runs don't drop the message channel

feat(phase-12d): narrow fit-gate — no fabricating specialized domains

fix(phase-12c): clean V2 ATS scoring denominator — count genuine keywords only

feat(phase-12b): multi-agent keyword ranking in V2 (R29)

feat(phase-12): V2 reworked into true multi-agent natural integration

docs(phase-11): mark complete in roadmap (V2-only scope noted)

feat(phase-11): kill JD-scraping leak in keyword pool — V2-only

docs(phase-11): plan JD extraction leak fix (1 plan, Wave 1, R27)

docs(phase-11): research JD-scraping leak — code path trace + deterministic filter design

fix: designation → Associate Product Manager, filename → Saiteja_Tirunagari_<Company>_Resume.pdf

feat(phase-10): V2 natural sentence resume mode — Kimi LLM generates sentences, same V1 waterfall

docs(phase-10): plan V1/V2 resume modes (3 plans, checker PASSED)

docs(phase-10): research V1/V2 resume modes — fan-out architecture, touchpoint wiring, latency strategy

fix: server-side JD extraction takes the job description only (all platforms)

debug: telegram relay /whoami + robust allowlist parsing

feat: Telegram via Cloudflare Worker relay (HF blocks Telegram egress)

feat: telegram egress diag endpoint + proxy support for Bot API

fix: Telegram bot force IPv4 to api.telegram.org + send retries

chore: trigger HF rebuild (deploy telegram webhook route)

feat: Telegram bot touchpoint (job link or JD -> tailored resume PDF)

feat: universal JD extraction + friendlier reload error message

fix: Tectonic sanitizer regex must require uppercase after fa

fix: sanitize fontawesome OTF for Tectonic + dedupe keywords (no duplicates)

fix: warm-compile real resume in Docker + surface compiler log

docs(phase-9): mark plans + success criteria complete; HISTORY PM12

feat(09-03): structured keyword placement for hardcoded resume [R22]