auth: fix ntfy notifications dying on em-dash in Title header

auth: diagnose silent ntfy failures

chat: stop hallucinating diversity gaps on tech-recruiter offers

auth: add email + password signup/login alongside OAuth

auth: push notification on new user signup via ntfy.sh

security: remove ADMIN_SECRET-gated debug endpoints

security round 2: payload caps, traceback strip, GDPR delete, path allowlist

security: top-5 audit findings — auth namespacing, SSRF guard, OAuth URL hygiene, rate limit, CSP

editorial: tighten typography + page-budget warning + per-finding skip flag

audit: one-click grammar fixes with rollback

audit: AI CV audit + structured contract/headcount/exit fields

bullet UX: AI improve + drag-to-reorder across 10 HTML templates

bored-cv: shareable public CV snapshots via /v/:slug

chat: in-chat tone picker with real-bullet samples (spec 46afe50)

cv: mark unknowns with {GAP: ...} tokens instead of fabricating

llm: generate CV in the chat language, not the UI locale

chat: stop re-asking the same theme — explicit 'already asked' block

analyze: coerce LLM list fields to flat list[str]

voice: tokenize context_bias so Voxtral accepts multi-word names

voice: normalize audio to 16kHz mono WAV server-side + wire context_bias

chat: use mistral-small for next-question — 30s→~5s on 'go' first turn

voice+transcribe: fix review P1s

transcribe: pass file as {file_name,content} dict — mistral SDK rejects raw handle

voice: mistral voxtral only — drop web speech + groq

chat: render markdown in assistant bubbles (bullets, bold, headings)

feat(chat): rank themes by leverage, bundle questions across experiences

fix: coerce language dicts to strings + stop asking headcount in chat

fix: bump rate limits 50/500, catch empty Mistral responses

fix: chat now finishes — question counter + forced completion after 8

feat: company context fields in editor — sector, stage, headcount, team

feat: rewrite chat from scratch — goal-driven, no more loops

fix: structured conversation flow — stay on one company before moving on

feat: switch chat to Mistral Large + radically simplified prompt

fix: remove experience cleanup prompt — was causing deletion loop

feat: auto-fix misheard company names in voice + Voxtral context_bias

feat: two-pass LinkedIn parser handles multi-role companies correctly

fix: voice puts text in input for review + never auto-delete experiences

fix: use Mistral SDK for Voxtral transcription instead of raw HTTP

fix: use voxtral-mini-latest for STT + Groq Whisper fallback

fix: correct mistralai import path — Mistral is in mistralai.client

feat: switch entire backend from Gemini to Mistral (LLM + STT)

fix: use dict for thinking_config — SDK version on HF lacks ThinkingConfig class

fix: transcription timeout 30s→90s backend, 120s client + HF fallback

perf: disable thinking on chat + analyze — all 3000 tokens go to output

fix: bump chat token budget 1500→3000 to prevent truncated JSON

feat: switch voice transcription to Groq Whisper + fix truncated JSON

fix: use inline base64 audio for Gemini transcription + client timeout

feat: replace Web Speech API with MediaRecorder + Gemini transcription

fix: voice accumulates across auto-restarts + rate limit 30/200 per day

perf: cut token budget 16K→8K + force user-select on chat containers