Wire 5 MCP servers into Claude Code agents spawned by the harness:
- Gitea MCP for repo/issue/PR management on self-hosted Gitea
- Kubernetes MCP with read-only RBAC for cluster inspection
- Postgres MCP with read-only user for database queries
- Filesystem and Git MCP scoped to task worktrees
Generates .claude/settings.json in each worktree before agent spawn.
Gracefully skips for Codex/OpenCode runtimes (no MCP support).
Also fixes node-pty build failure by using local Node.js headers
instead of downloading from unofficial-builds.nodejs.org (ECONNRESET).
Move Field component out of NewTaskTab to prevent React from
remounting input wrappers on every keystroke. Same root cause as
the ProjectsTab DetailView fix.
DetailView was defined as a component inside ProjectsTab's render,
causing React to unmount/remount it on every keystroke. Replace with
inline JSX so the input element identity stays stable across renders.
Browser-based interactive terminal sessions with agent CLIs via
WebSocket + node-pty. Supports full TUI rendering (colors, cursor,
ctrl-c) through xterm.js in the browser.
Architecture: xterm.js ←WebSocket→ pty-server.js ←PTY→ agent CLI
- Extract shared buildAgentEnv() from executor into agent-env.ts
- Add internal /api/agents/[id]/env endpoint for PTY server
- Add pty-server.js (WebSocket + node-pty, max 3 sessions, 2hr cleanup)
- Add custom server.js wrapping Next.js with WebSocket upgrade
- Add ChatTab component with agent selector and terminal
- Wire CHAT tab into dashboard nav and render
- Configure serverExternalPackages for node-pty
- Update Dockerfile with build tools and custom server
- Bump k8s memory limit 1Gi → 2Gi for PTY sessions
Next.js standalone output nests server.js under apps/harness/ when
built from a pnpm workspace. Preserve the directory structure and
update CMD to point to the correct server.js path.
Support Gitea alongside GitHub/GitLab for repo search, authenticated
cloning, and pull request creation via Gitea API. Tasks can specify
gitProvider and gitBaseUrl in their spec (defaults to github for
backwards compat). Auto-discovers GITEA_TOKEN from env on boot.
Add model fetchers for OpenCode Zen (https://opencode.ai/zen/v1/models) and
Go (https://opencode.ai/zen/go/v1/models) APIs. Register opencode-go as a new
provider, load shared credentials from auth.json, add known models with pricing,
and create default agents for both tiers on first boot.
Replace the manual "Add Model" form with a search bar that filters by model
name/ID and paginate the catalog at 25 models per page.
Switch harness Dockerfile to pnpm with repo root build context so
workspace:^ dependency on @homelab/db resolves. Use .dockercontext
marker file to opt individual apps into root context builds while
keeping web/api on their local app context.
Replace all in-memory Map-backed stores (credentials, models, agents,
tasks, iterations, usage) with Drizzle ORM queries against the
homelab-pg PostgreSQL cluster. All store functions are now async.
- Add 6 harness_* tables to @homelab/db schema
- Generate and apply initial Drizzle migration
- Add lazy DB connection proxy to avoid build-time errors
- Wire DATABASE_URL from sealed secret into harness deployment
- Update all API routes, orchestrator, executor, and boot to await
async store operations
Use globalThis for all in-memory stores (credentials, models, agents,
tasks) so the instrumentation hook and API route handlers share the
same data. Next.js bundles these as separate chunks with independent
module instances, causing boot-populated state to be invisible to
API routes.
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.
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.
act_runner v0.3.0 doesn't propagate workflow-level or job-level
env: blocks to job containers. Use export in run commands instead.
First run warms cache, subsequent runs will show reused packages.
Job containers need access to the DinD daemon for docker build/push.
Mount /var/run/docker.sock from DinD into job containers and set
docker_host in runner config.
- Set PNPM_STORE_DIR and COREPACK_HOME as job env vars instead of
relying on container.options -e flags which act_runner may ignore
- Replace fragile cross-job matrix with single-job loop for builds
- Both fixes: empty matrix app name and 0 reused packages
The act_runner entrypoint ignores CONFIG_FILE for the daemon
command, so container.options (pnpm cache volume) never loads.
Use a custom command that registers manually then runs daemon
with --config explicitly.
