homelab/telegram/personas
Mikkel Georgsen 2d0d4da992 fix(02-02): typing indicator lifecycle, model identity, tool permissions
- Fix typing indicator not showing: clean up stale typing tasks between
  messages and use dynamic event lookup in callbacks instead of capturing
  a specific event at creation time
- Fix stream-json input format: use nested message object for stdin NDJSON
- Switch --system-prompt to --append-system-prompt so Claude Code's
  default system prompt (with model identity) is preserved
- Add --dangerously-skip-permissions for full tool access in subprocess
- Use full model ID (claude-sonnet-4-5-20250929) in default persona

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-02-04 22:10:02 +00:00
..
brainstorm.json feat(01-01): restructure personas with pipeline workflow 2026-02-04 18:13:21 +00:00
default.json fix(02-02): typing indicator lifecycle, model identity, tool permissions 2026-02-04 22:10:02 +00:00
homelab.json feat(01-01): restructure personas with pipeline workflow 2026-02-04 18:13:21 +00:00
planner.json feat(01-01): restructure personas with pipeline workflow 2026-02-04 18:13:21 +00:00
research.json fix(01-01): update persona models to claude-sonnet-4-5-20250929 2026-02-04 18:06:08 +00:00