fix: per-item drop of invalid brief facts; relax LLM-produced singleton fields

fix: tolerate malformed LLM-copied EvidenceRef fields

fix: allow metrics/analyst sources in CategorizedRisk and GuidancePoint

feat: merge Company Overview generation into single synthesis call

feat: multi-provider LLM support, prominent chat, design pass, and new analytics

feat: add since_release_price_reaction_pct — cumulative return from earnings release to today

fix: coerce tax_rate_and_effective_leverage to consensus_beat_mix + harden prompts

fix: normalize signal_type case-insensitively + fix subtext typo

feat: add SubtextRead + between_the_lines to BriefOutput schema

fix: coerce compound LLM source strings to prevent BriefOutput validation failures

feat: Analyst Edge layer — deterministic text delta signals (Phase 0+1)

feat: add impact badge to all sourced facts

feat: analytical edge section + fix HF Spaces fragment polling race

deploy: Primer app for HF Spaces — clean orphan history