Haewon Kam 122b1915f0 fix: 2-stage discovery — Firecrawl first for clinicName, then Perplexity ... Previously Firecrawl and Perplexity ran in parallel, so Perplexity received raw URL instead of clinic name → poor search results. Now: Stage A: Firecrawl scrape+map (parallel) → extract clinicName from HTML Stage B: Perplexity searches using extracted clinicName → finds Instagram, YouTube, Facebook handles that Firecrawl HTML parsing missed Stage C: Merge 3 sources + verify all handles Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>		2026-04-04 01:02:30 +09:00
..
_shared	fix: YouTube channel ID (UC...) handling + handle-to-channelId resolution	2026-04-04 01:00:21 +09:00
analyze-market	feat: real API integration + YouTube Data API v3 + progressive loading	2026-04-02 10:57:14 +09:00
collect-channel-data	fix: YouTube channel ID (UC...) handling + handle-to-channelId resolution	2026-04-04 01:00:21 +09:00
discover-channels	fix: 2-stage discovery — Firecrawl first for clinicName, then Perplexity	2026-04-04 01:02:30 +09:00
enrich-channels	feat: Pipeline V2 — 3-phase analysis with verified channel discovery	2026-04-03 21:49:13 +09:00
generate-report	feat: Pipeline V2 — 3-phase analysis with verified channel discovery	2026-04-03 21:49:13 +09:00
scrape-website	feat: prototype gap closure — enrichment diagnosis + brand extraction + plan assets	2026-04-03 17:09:15 +09:00