Till JS 121a0c0a6f feat(api): POST /api/v1/context/import-url — crawler + optional LLM summary ... New backend endpoint that wraps mana-crawler + mana-llm in a single call so the Kontext "Aus URL" UI can hit one route: - Starts a crawl job (single page or up-to-20-page deep crawl) via mana-crawler's /api/v1/crawl, polls status up to 90s, then fetches paginated results. - When multiple pages are returned, joins them into one markdown document with H1-per-page section headers separated by ---. - When summarize=true, routes the collected markdown through mana-llm/chat/completions with a system prompt that asks for "Überblick / Kernaussagen / Details" H2 structure in the source language. sanitizeSummary() strips the common local-LLM artefacts (```markdown fences, "Hier ist …:" preamble, stray leading H1) so the output drops cleanly into the Kontext doc. On summary failure the endpoint returns 502 rather than silently falling back to the raw crawl. - Credits are validated + consumed via @mana/shared-hono/credits (1 credit crawl-only, 5 crawl+summary) under the new AI_CONTEXT_IMPORT_URL action. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>		2026-04-15 14:24:19 +02:00
..
lib	refactor: rename planta → plants, clean up codebase	2026-04-12 18:59:44 +02:00
modules	feat(api): POST /api/v1/context/import-url — crawler + optional LLM summary	2026-04-15 14:24:19 +02:00
index.ts	refactor: rename nutriphi module to food (Essen)	2026-04-14 15:30:07 +02:00