Files
selfheal-lab-gitops/vm/ai-env/ai.env
T
seon d7ecd59b4c chore: ai/harness images 53ff243 (per-run model, usage, Claude provider) and the Anthropic key file
ai-env·harness 이미지를 53ff243 로 올린다. apply.sh 가 Secret Manager 의
selfheal-anthropic-api-key 를 받아 /run/secrets/anthropic-api-key 로 두고 compose 가
ANTHROPIC_KEY_FILE 로 넘긴다. 값이 없으면 기존처럼 저하 모드로 기동한다.
2026-10-14 23:21:50 +09:00

25 lines
1.7 KiB
Bash

# Non-secret settings of the AI VM (merged into /opt/selfheal/ai.env by apply.sh). Secrets never go here.
# Discord server "Selfheal Lab" (created 2026-10-08): approvals channel for layer-2 buttons, escalation channel for layer 3.
DISCORD_GUILD_ID=1557424985793101824
DISCORD_APPROVALS_CHANNEL_ID=1557425140302872698
DISCORD_ESCALATION_CHANNEL_ID=1557425282363691048
# optional: restrict button decisions to one role id (empty = any member of the server)
DISCORD_APPROVER_ROLE_ID=
# Discord message language of the hitl bot: en or ja (runbooks and prompt free text are written in Japanese)
HITL_LANG=ja
# experiment design 11.1: candidates gpt-6-astra / gpt-6.1-sol / gpt-6-luna (OpenAI model page 2026-10-08). luna for the first live checks and campaign (budget), compare with sol afterwards
# default when a campaign does not name a model. Since apps 53ff243 the harness passes the campaign's model on every /diagnose
# (console "model" field); ids starting with claude- go to the Claude Messages API (secret selfheal-anthropic-api-key).
OPENAI_MODEL=gpt-6.1-sol
EMBED_MODEL=text-embedding-3-small
HARNESS_URL=http://10.20.0.11:8080
MIMIR_URL=http://10.20.0.10:9009/prometheus
LOKI_URL=http://10.20.0.10:3100
K8S_API=https://10.10.0.10:6443
# Jev gates (2026-10-08): off | shadow | enforce. shadow records TypeSafe System One answers (triage before the LLM, review after it)
# next to each diagnosis in ai.jev_shadow and in the harness diagnosis event without changing the disposition. enforce additionally
# downgrades a catalogue proposal to escalate when review.best_action disagrees with confidence >= 0.9 or target_valid < 0.5
# (campaign-2 report 3.3). Kept at shadow until the C-G1 re-run shows the rules catching a real misjudgement.
JEV_MODE=enforce
JEV_MODEL=jev-1.13.0