agent: repoint FLM-NPU model roles off the retired provider; sync memory/skills

config.yml: vision -> llamacpp (dankclaw)/frank-large:auto,
tiny -> llamacpp (dankserver)/frank-small:off,
task -> llamacpp (dankclaw)/frank-large:medium (was flm dankclaw-npu),
matching the flm (dankclaw-npu) provider removal in models.yml.

Memories/managed skills: rollouts and learned notes from the frank-large
KV-pool + sampler work and the noctalia recolor; merged the duplicate
noctalia-palette-recolor skill into noctalia-custom-palette-recolor (adds
the dotfiles-tracking step and the +show-config delta gotcha) and dropped
the superseded legacy memory skills whose ghostty USR1 reload recipe is
wrong for this fleet.
This commit is contained in:
Frank committed 2026-09-13 23:51:43 -07:00
1 parent c32584e093
commit 872e86399a
56 files changed
+318 -178

No files matched your search

@@ -0,0 +1 @@
Manages frank-large/small inference routing, FLM NPU constraints, and Halogen runtime kwargs for thinking block preservation.
@@ -0,0 +1 @@
Pinned sampler: temp=1.0, top_p=0.95, top_k=20. Live config read on next cycle.
@@ -0,0 +1 @@
ls -l ~/.config/flm/xclbins/ | grep -E '\.xclbin' || echo 'Missing symlinks'
@@ -0,0 +1 @@
curl -s localhost:7771/status | jq .queue
@@ -0,0 +1 @@
enable_thinking: true\npreserve_thinking: true\nreasoning_effort: medium
@@ -0,0 +1 @@
{"thinkingLevelMap": true, "gemma4-it": "e4b"}