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.
The command override bypasses the entrypoint that handles
registration. Use CONFIG_FILE env var which the entrypoint
respects, keeping the registration flow intact.
Mount volume at /pnpm-store and set PNPM_STORE_DIR and
COREPACK_HOME env vars in job containers so pnpm and corepack
both write to the cached volume. Corepack cache avoids
re-downloading pnpm binary each run.
Allows manual trigger to build all apps (or specific ones).
Empty input builds web, api, harness. Useful for initial
registry population after migration.
Pre-install pnpm 9.15.4 via corepack in the image so it doesn't
download every run. Use --config CLI flag instead of CONFIG_FILE
env var to ensure container.options volume mount is applied.
Mount a named Docker volume (pnpm-store) into every job container
at the default pnpm store path. The volume persists in the DinD
sidecar across job runs, so pnpm install reuses cached packages.
