 Claude Code
|
ba4a2f4262
|
Switch all Ollama models to gemma3n:e4b on node-197 GPU
Bake-off results: gemma3n:e4b (80.6% cmd match, 100% safety, 5.9s)
outperforms qwen3-coder:30b on all metrics. Updated paper, shrink,
and langgraph gateway configs. Frees steel141 for LoRA training.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
2026-03-18 10:29:54 -04:00 |
|
|
Claude Code
|
40b4da345a
|
Add retrieval-grounded sudo flow and execution feedback loop
|
2026-03-17 19:53:32 -04:00 |
|
|
Claude Code
|
f4ce19db6d
|
Add paper bug_log flow and more ironic God persona
|
2026-03-17 14:53:54 -04:00 |
|
|
Claude Code
|
cf2aeb1a5e
|
Add server_type variable, gate fill/setblock/clone and template build on server_type=paper
|
2026-03-16 19:36:12 -04:00 |
|
|
Claude Code
|
b7451e3290
|
Add LangGraph gateway, template manager, teleport border guard, enchantment context, server_type prep, session persistence
|
2026-03-16 19:28:52 -04:00 |
|
 Seth
|
0c2902de8a
|
Add Paper advanced fork implementation
- Introduce dedicated paper AI script (mc_aigod_paper.py)
- Add expanded whitelist for structure ops: fill/setblock/clone
- Add deterministic sudo build templates (house/tower/wall/church)
- Keep prayer/sudo/memory/intervention architecture from base branch
- Add paper-specific config and systemd unit files
- Document deployment/runtime in rewritten README
|
2026-03-15 23:27:17 -04:00 |
|