Files
archie/deployments
sam 6048c8ba91 feat(archied): serve the daemon's own health endpoint
The update watchdog verifies archied's restart, so archied has to be what
answers. It was probing the dashboard's /healthz, which belongs to the
dashboard: switch [web] off and nothing answers, and in the extracted UI
topology that endpoint reports a different process entirely, which would
confirm a release while the daemon it was meant to verify is down.

[health].listen (127.0.0.1:8485, defaulted, always on) serves /healthz,
/health and /health/detailed for the life of the process. Liveness answers
503 until the daemon reaches its run loop: the listener binds before the
subsystems do, so an unconditional 200 would tell the watchdog a half-booted
release came up. Failing to bind is fatal, because a daemon nothing can probe
gets every update rolled back. The State Store's readiness surface now shares
the listener plumbing, keeping its log and error text verbatim.

Closes archie-core-exbz, which asked which of two bad options to take when
the dashboard is off. Neither: the daemon owns its own liveness.

Also deletes TestInstallUpdateDetachesInstallerFromCallbackContext. It has
failed intermittently under load more than once, racing its fake bot server's
multipart parse against the cancellation it induces.
2026-09-09 23:29:11 +10:00
..

Archie Core Deployment Examples

This directory contains configuration templates and guides for different deployment scenarios of Archie Core.

Directory Structure

  • single-forge-github.toml: Standard single-forge deployment managing multiple GitHub repositories under a single bot account and GitHub token.

  • multi-forge-github-gitea.toml: Multi-identity deployment running GitHub and a self-hosted Gitea instance simultaneously with distinct bot accounts, tokens, and repository sets.

  • local-ollama-standalone.toml: Self-hosted deployment running local LLM models via Ollama (e.g., llama3, qwen2.5) with optional standalone (forge-disabled) operation.

  • docker-nats-stack.toml: Host-run archied orchestrating sandboxed archie-agent containers over the repository's Compose-managed NATS service. Copy to ~/.config/archie/config.toml, start NATS with Compose, then start archied on the host.

  • systemd-user-service.md: Operational runbook for running archied as a persistent 24/7 background service via systemd user units and loginctl enable-linger.


Usage

Copy any scenario template to your XDG configuration directory (${XDG_CONFIG_HOME:-~/.config}/archie/config.toml):

mkdir -p ~/.config/archie
cp deployments/single-forge-github.toml ~/.config/archie/config.toml

Edit API keys in ~/.config/archie/env or directly in config.toml, then launch Archie Core:

archie-gateway -config ~/.config/archie/config.toml -listen 127.0.0.1:8585 &
archie-state-store -config ~/.config/archie/config.toml -listen 127.0.0.1:9090 &
archied -config ~/.config/archie/config.toml
# or via systemd:
systemctl --user start archied

The templates use the extracted Gateway Service by default. Start archie-gateway before archied; it owns the conversation SQLite file and serves the ChatContract gRPC API on the configured target.

The State Store service (archie-state-store) owns the single archie.db task SQLite file and serves the StateStore gRPC contract. After the in-process store path was deleted, BOTH archied and archie-gateway dial it via [services.state].target and never open archie.db themselves (docs/prds/state-store-contract.md §12 step 7). The templates set [services.state] accordingly: a host-only agent reaches a loopback bind (127.0.0.1:9090) with no token, while a container-mode agent needs the Docker bridge gateway address plus a matching bearer token (target_token / --token / STATE_STORE_TOKEN), because a container cannot reach the host's loopback.

# loopback (host-only agent)
archie-state-store -config ~/.config/archie/config.toml -listen 127.0.0.1:9090
# or container-mode: bind the bridge gateway with a token
archie-state-store -config ~/.config/archie/config.toml -listen 172.17.0.1:9090 -token <token>

Verifying the daemon

archied always serves its own liveness surface on [health].listen (127.0.0.1:8485 by default). It answers 503 for the whole of boot and 200 once the daemon is running, which is what makes it a usable restart check:

curl -s -o /dev/null -w '%{http_code}\n' http://127.0.0.1:8485/healthz      # 200 = daemon running, 503 = still booting
curl -s http://127.0.0.1:8485/health/detailed                               # readiness probes, 503 when degraded

The update watchdog polls this address after restarting the daemon and rolls the release back when it never answers, so a deployment that moves it must change [health].listen rather than relying on the script's fallback. The dashboard's /healthz is a separate surface on [web].listen and reports the dashboard's process, not the daemon's.

Verifying the State Store

archie-state-store exposes an optional HTTP readiness surface when launched with -ready-addr (the systemd unit uses 127.0.0.1:9091). Use it to confirm the process is up and the store is healthy before starting archied:

curl -s -o /dev/null -w '%{http_code}\n' http://127.0.0.1:9091/healthz        # 200 = process up
curl -s http://127.0.0.1:9091/health/detailed                                # state_db component -> 200, or 503 when degraded

A running State Store owns exactly one task SQLite file (<db_path>-tasks.sqlite); archied and archie-gateway never open archie.db directly, so a second store process on the same db_path, or a consumer that opens the task file, indicates dual-store ownership (docs/prds/state-store-contract.md §12 step 7/8). The readiness probe is the single-writer check the runbook has against a degraded store: a 503 from /health/detailed means archied should be started only after the store is healthy.