content=null is rejected even when tool_calls is set, which 400d the U19 follow-up turn after the first graph query.
Co-authored-by: Cursor <cursoragent@cursor.com>
Resume reuses pintables, skips LCSC/DigiKey before review, and emits a waiting heartbeat so a long DeepSeek turn is visible instead of a freeze.
Co-authored-by: Cursor <cursoragent@cursor.com>
Empty assistant content is still treated as unset; replay a placeholder and retry once with thinking disabled.
Co-authored-by: Cursor <cursoragent@cursor.com>
A thinking-only turn was replayed as content=null with no tool_calls, which the API rejects with 400 and skipped IC review.
Co-authored-by: Cursor <cursoragent@cursor.com>
Auto-resolve of passives was 400ing because thinking mode cannot be combined with named tool_choice. Also strip BOM descriptions after an em dash before DigiKey search.
Co-authored-by: Cursor <cursoragent@cursor.com>
Based on manvalan/pinscope main. Default LLM is DeepSeek with local
skills and PDF ingest. Datasheets are fetched from LCSC/TI, stored in
the component library, and review extracts abs-max with a deeper
checklist. Adds scripts/update-pinscope.sh for the production host.
Agentic schematic validation: datasheet extraction via Claude Console
Skills, netlist/BOM design graph, per-IC direct datasheet review with
page citations, capacitor derating, Next.js report UI.
Extracted from the Pinscope cloud codebase. Auth and billing live in the
private gateway repo behind stable seams (billing_hook.py, adapter files
listed in CLAUDE.md).
micheleandCursor