Ghost añade el título del post automáticamente en el frontend,
por lo que el <h1> generado desde el markdown aparecía duplicado.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
El campo "html" en Ghost Admin API v5 (Lexical editor) es de solo
lectura. El contenido se debe enviar via mobiledoc con HTML card,
que Ghost acepta en todas las versiones de v5 y renderiza sin
conversión. Añadidos logs de diagnóstico y validación de HTML vacío.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Use Claude Haiku (via ANTHROPIC_API_KEY) for all output generation.
Falls back to Ollama qwen2.5:3b if no API key is set.
Also translates all user-turn prompts to Spanish for consistency.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Add "Escribe SIEMPRE en español" at the start of all system prompts
(podcast, blog, report, thread) so Ollama generates content in Spanish.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
database.py: enable PRAGMA journal_mode=WAL + synchronous=NORMAL so
/status reads from concurrent connections see committed data without
blocking behind the scraper's writes; add 'skipped' to get_session_stats
bot.py: show skipped count in fmt_progress and cmd_status; use 'or 0'
to guard against NULL from SUM(); label active research in /status
processor.py: raise generate() temperature default to 0.7 + add
repeat_penalty=1.15/repeat_last_n=128 to Ollama options to stop
qwen2.5:3b from looping; scoring prompt keeps temperature=0.1
generator.py: rewrite all prompts with explicit "NEVER repeat"
constraints and distinct-content rules per section; podcast prompt
now asks for spoken-word style (no formal headers); reduce thread
to 12-18 tweets (was 15-25) to fit model context; pass temperature=0.7
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
ChemaVX