3 Commits

Author	SHA1	Message	Date
Julia McGhee	25b4769ff8	Auto-discover credentials, models, and agents on harness startup ... Read mounted secret files (Claude OAuth, OpenCode auth.json) and env vars on boot, register them as credentials, fetch available models from provider APIs, and create default agent configs for each viable runtime+provider+model combination.	2026-03-21 19:53:29 +00:00
Julia McGhee	df1111da15	Remove mock data from harness and add agent credential healthchecks ... Strip all seed/mock data (fake tasks, models, usage entries, agent configs) so the dashboard starts clean and populates from real API state. Add /api/agents/health endpoint that validates each agent's provider credentials and CLI availability.	2026-03-21 19:42:53 +00:00
Julia McGhee	6dde7c8aef	Add harness app: agent orchestrator with cluster deployment ... - Next.js app for orchestrating coding agent benchmarks (Claude Code, Codex, OpenCode) - Dockerfile installs git, gh CLI, and agent CLIs for headless execution - K8s deployment with workspace volume, sealed credentials for Claude + OpenCode - Traefik IngressRoute at harness.coreworlds.io with internal-only middleware + TLS - CI pipeline path filter for harness builds - Fix OpenCode runtime flags (subcommand-based headless mode)	2026-03-21 15:26:09 +00:00