state/agent/logs/engine.latest.log

Hint: The `hf-cli` skill is not installed. Run `hf skills add -g --claude` to teach your AI agents how to use the `hf` CLI.
Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads.
✓ Downloaded
  path: /mnt/data/models/Ling-3.0-tiny-GGUF/Ling-3.0-tiny-Q4_K_M.gguf
[local-llama] staging: 4.49 GiB bucket -> local SSD
[local-llama] staged: 4.49 GiB in 5.7s
[local-llama] loading: llama.cpp via LLama-GUI · threads=2 · ctx=65536 · batch=2048/512 · KV=q8_0/q8_0 · reasoning=low/128
[local-llama] LLama-GUI launch: --model /tmp/local-agent-models/Ling-3.0-tiny-Q4_K_M.gguf --host 127.0.0.1 --port 43126 --ctx-size 65536 --threads 2 --threads-batch 2 --parallel 1 --cont-batching --flash-attn auto --jinja --reasoning on --reasoning-effort low --reasoning-budget 128 --batch-size 2048 --ubatch-size 512 --threads-http 1 --cache-type-k q8_0 --cache-type-v q8_0 --cache-prompt --cache-reuse 256 --metrics --slots --slot-save-path /tmp/local-agent-kv/51ce7225fcdf53b0 --gpu-layers 0 --no-warmup
[local-llama] ready
[local-llama] saved local KV slot tokens=0 bytes=480 in 0.05s reason=manual
[local-llama] saved local KV slot tokens=0 bytes=480 in 0.03s reason=shutdown