Two new textareas in Content settings let admins provide custom
instructions for the analysis and chief editor LLM stages, matching
the Writing Instructions field added in v0.4.4. All three pipeline
stages now have user-controllable system prompt customization.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Two-pronged fix for repeated article topics:
1. Feed last 30 days of published article titles into the LLM analysis
prompt with explicit "avoid these" instruction. Zero cost — just
extra context in an existing API call.
2. Replace keyword-overlap dedup (60% word match) with embedding-based
cosine similarity via sentence-transformers/all-MiniLM-L12-v2 on
OpenRouter. Catches rephrasings that keyword matching misses
(e.g. "BPC-157 dosing" vs "how much BPC-157 to take"). Falls back
to keyword matching if the embedding API is unavailable.
Cost: ~$0.00001 per generation run ($0.02/M tokens, ~500 tokens/run).
New files:
- class-semantic-dedup.php — Embedding cosine similarity + keyword fallback
- class-open-router-embedding-provider.php — OpenRouter /embeddings client
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Move system prompt, user prompt, and performance context builders into
PRAutoBlogger_Analysis_Prompts. Analyzer retains orchestration, data
fetch, parsing, and storage. Backward-compatible private proxies kept.
Both files well under 300-line limit.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
