Commit Graph
12 Commits
Author SHA1 Message Date
Frank 970ceed554 niri: drop untracked noctalia.kdl include; sync memory skills
- remove 'include noctalia.kdl' from shared config.kdl: the file is a
  per-host noctalia template render (colors from local palette), was
  never committed, and made every config load fail hard on hosts where
  it was absent — niri 26.04 falls back to DEFAULT config on parse
  error, silently killing keybinds/rules/layout/autostart
- theme integration now only via keybinds (noctalia msg verbs) + the
  host-local rendered files (see managed skill noctalia-template-offline-render)
- sync agent memories: delete retired memory-store skills, add new ones
2026-09-14 17:46:31 -07:00
Frank fc049ce7fb agent: local role repoint + compaction 70%/-1; sync memories and managed skills 2026-09-14 14:32:16 -07:00
Frank 872e86399a 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the superseded legacy memory skills whose ghostty USR1 reload recipe is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.
2026-09-13 23:51:43 -07:00
Frank 60dc0bba92 models: set frank-large contextWindow to 200000
Also carries previously-uncommitted edits already in the working file:
maxTokens 262144 -> 65536 (HALOGEN_MAX_TOKENS_CAP) with the KV-pool
admission note, and removal of the flm (dankclaw-npu) provider block.

Live check: halogen /health reports context=262144, so 200000 is inside
the served window; 200000 + 65536 = 265536 against a 401408-position pool.
2026-09-13 23:14:21 -07:00
Frank 4b82f35354 Add blankpad-host auto-learn skills and memory store
Tracked the harness artifacts accumulated on blankpad (blank@), matching
the existing convention for the --home-dank-* memory stores and the 36
already-tracked managed-skills.

managed-skills (9): authentik-proxy-provider-app-link,
dankclaw-guard-chain-layer-diagnosis, e2e-arr-rawip-reachability-triage,
halogen-kv-pool-fit, lan-client-split-dns-fix, noctalia-reference,
rootless-quadlet-log-retrieval, ssh-key-bootstrap-no-sshpass,
swapfile-resize-safe-ordering.

memories (2 stores): --home-blank-.omp-- (dotfiles_git, handy_lifecycle,
input_permissions) and --home-blank-Projects-serverAppConfig--
(frank_large_quadlet).

Secret sweep before staging: no PEM blocks, no credential literals.
Content is fleet topology/IPs only, same class as the tracked dank stores.
2026-09-13 00:25:29 -07:00
Frank b60e95158c frank-large: pin Qwen3.8-Flash-Next sampler settings + preserve_thinking
halogen-flash-server has no server-side sampler defaults (temperature absent
or 0 = greedy), so the endpoint decoded greedy for OMP, whose global
sampling settings default to -1 (not sent).

compat.extraBody merges these top-level into every request body after the
compat policy, so they win:
  temperature=1.0 top_p=0.95 top_k=20 min_p=0.0
  presence_penalty=0.0 repetition_penalty=1.0 preserve_thinking=true

Verified against the live dankclaw endpoint: preserve_thinking is honoured
(350 vs 75 prompt tokens for a replayed reasoning turn), and the exact
body shape returns 200.
2026-09-12 23:58:38 -07:00
Frank a30cd771f3 chore(agent): thinking-block visibility toggle 2026-09-10 16:58:00 -07:00
Frank 35b871162c chore(memory): flush runtime memories and promote managed skills
Memory-file flush for the dotfiles-deploy session with the blankpad admin
credential scrubbed to a placeholder; sessions transcripts untracked
(gitignored) since harness transcripts can carry raw secrets.
Managed skills: command-center-dotfiles-import, ssh-fish-host-remote-exec,
stash-supersession-audit-before-drop.
2026-09-10 16:57:10 -07:00
Frank 2a3c0da740 chore(memory): flush runtime memory updates for .omp and serverAppConfigs roots
MEMORY.md/learned.md/memory_summary.md/raw_memories.md churn from live sessions
(DIFR deadlock diagnosis, model-swap ops, outpost verification etc.); new
memory root --home-dank-.omp-agent-- started with learned.md.
2026-09-09 16:20:42 -07:00
Frank 9bfa0be85d chore(skills): promote runbook skills to managed-skills; drop superseded SKILL.md
- 31 new managed skills (anubis/arr/authentik/hermes/freetoken/podman/llm-swap
  runbooks etc.) now tracked.
- Removed superseded skills: omp_harness_config, peon_ping_integration
  (replaced by user-authored peon-ping-* managed skills),
  rocmfp4-strix-benchmark-orchestration.
- New memory-root skills: niri_compositor_ops, omp_git_workflow,
  omp_model_config, quadlet-media-migration, homelab-service-triage,
  hermes-dankclaw-ops, frank-default-large-ops, caddy-auth-dns-playbook.
2026-09-09 16:20:28 -07:00
Frank 7be39d60dd feat(config): rewire model roles to frank-small/frank-large + NPU flm provider
- models.yml: rename frank-default-small -> frank-small (dankserver),
  frank-default-large -> frank-large (dankclaw-gpu, text-only input);
  add 'flm (dankclaw-npu)' provider with gemma4-it:e4b and nuextract3:4b.
- config.yml: point modelRoles at renamed models; vision -> nuextract3:4b:auto,
  tiny/task -> gemma4-it:e4b:off; compaction reorder (snapcompact added,
  idleThresholdTokens 200k->100k, thresholdPercent -1->85); hideThinkingBlock true;
  statusline transparency + compact thinking level; images.urls backends list.
2026-09-09 16:19:54 -07:00
Frank 552d1ef8bf chore: track live agent config (config, models, append-system, managed-skills, memories, plugin lock) 2026-08-28 07:56:47 -07:00