Spec: prefer one local model for all roles; record host sharing, park vision #54

Merged
dongar merged 5 commits from spec-shared-inference-host into main 2026-09-28 01:47:08 +00:00
5 Commits
Author SHA1 Message Date
dongarandClaude Opus 5.5 2ab86bf0da Spec: OpenSCAD work needs vision, in nisse-dev or its own agent
CI / checks (push) Skipped
CI / checks (pull_request) Successful in 1m18s
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-09-28 01:32:20 +00:00
dongarandClaude Opus 5.5 75d96b4197 Spec: restore the blank line before the section rule
CI / checks (push) Skipped
CI / checks (pull_request) Failing after 1m14s
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-09-28 01:30:36 +00:00
dongarandClaude Opus 5.5 9239a56bd1 Spec: park vision as a need of future agents, not current ones
CI / checks (push) Skipped
CI / checks (pull_request) Successful in 1m20s
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-09-28 01:30:18 +00:00
dongarandClaude Opus 5.5 50a2a75342 Spec: prefer one local model; add vision as an open decision
CI / checks (push) Skipped
CI / checks (pull_request) Successful in 1m19s
The host-sharing item now records the operator's preference: one local
model for every local role, with agents tagging in and out of the host
as the fallback if no single model fits. A new item records vision as a
requirement (OpenSCAD renders, later video files) and what the text-only
agent needs before any vision work.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-09-28 01:29:29 +00:00
dongarandClaude Opus 5.5 e5c18b3bf4 Spec: record sharing the local inference host as an open decision
CI / checks (push) Skipped
CI / checks (pull_request) Successful in 1m15s
nisse-dev and nisse-ops both send local roles to the one 24GB host,
where llama-swap keeps one model resident. Different models per agent
would reload weights on every switch. Per-key rate limits don't help.
Lists the options, simplest first, to decide after the executor
benchmark and the ops evaluation.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-09-28 01:25:38 +00:00