You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
config: support Anthropic, OpenAI, Gemini, and OpenCode Zen providers
- Add ANTHROPIC_API_KEY, OPENAI_API_KEY, GEMINI_API_KEY to .env.schema
- OPENCODE_ZEN_API_KEY no longer required (any one provider suffices)
- start.sh auto-detects provider and picks model:
- Orchestration/coding: opus-4-6 / gpt-5.3-codex / gemini-3-pro
- Triage (sentry): haiku-4-5 / gpt-5-mini / gemini-3-flash
- install.sh prompts for all four providers
- Remove hardcoded defaultProvider/defaultModel from settings.json
- Update control-agent skill with model selection tables
- Update CI simulated input for new prompt order
Make `OPENCODE_ZEN_API_KEY` optional (no longer @required) since users can use any of the three providers. None of the three should be @required — at least one must be set but we can't express that in varlock.
**Model note**: Use `opencode-zen/*` models for headless agents. `github-copilot/*` models reject Personal Access Tokens and will fail in non-interactive sessions.
245
+
**Model note**: `github-copilot/*` models reject Personal Access Tokens and will fail in non-interactive sessions.
226
246
227
247
The sentry-agent operates in **on-demand mode** — it does NOT poll. Sentry alerts arrive via the Slack bridge in real-time and are forwarded by you. The sentry-agent uses `sentry_monitor get <issue_id>` to investigate when asked.
0 commit comments