connor
275a5bfb2b
oc-work: local models only on the local key, edits and most commands ask, loads instructions/work.md. oc-local (also oc, opencode): every model, defaults to qwen3.8-flash-next-iq3s-med, edits and commands run except destructive and outward-facing ones. On sctfw004 oc-local presents the work key. personal.json and work-strict.json removed. Agents: drop variant, which has no effect on LiteLLM models. dev takes its permissions from the profile. The read-only agents deny redirects and the write/exec flags of allowed commands, swap find for fd, and only allow listing forms of git branch. review defaults to the uncommitted diff. CLAUDE.md: add the comment, process and shell-tool rules from the laptop's AGENTS.md, and note that OpenCode reads this file.
1.9 KiB
name, description, metadata
| name | description | metadata | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| llm-work-personal-profiles | Work is US-gov adjacent (local + OpenAI, never Anthropic); OpenCode profiles are oc-work (local only, tight) and oc-local (all models, looser) |
|
The LiteLLM stack serves two profiles with different permitted providers:
- Work — US-government-adjacent.
openai/*and local models ONLY. Anthropic is not an employer-approved vendor, soanthropic/*is excluded there by policy, not by preference. PRC-origin models are not formally banned by his office but should be treated as prohibited until the security office gives written approval. That restriction is about HOSTED PRC-origin models (Moonshot/Kimi etc.). A PRC-origin model running locally (a Qwen model on llama-swap) is fine for work, since nothing leaves the machine. Connor's ruling, 2026-10-22. - Personal —
anthropic/*,openai/*, and local. zen/*is blocked for both, see zen-tos-hold.
Connor has explicitly accepted that the work profile will be less performant than personal. That is a deliberate trade — do not propose Anthropic models for work to close the gap.
Since 2026-11-02 Connor leans toward local models for all OpenCode work because
of his employer's AI policy. OpenCode has two profiles: oc-work (local models
only via the LiteLLM local key, tight permissions, extra work instructions)
and oc-local (every model, defaults to local Qwen3.8, looser permissions,
personal key except on sctfw004 where it presents the work key).
How to apply: when recommending a model for anything work-related, prefer
local, then openai/*. Enforcement is by LiteLLM virtual key, so the thing to
check after any launcher change is which key each command presents on each
host. Details in ~/guides/llm/robots.md §2.