Liking cljdoc? Tell your friends :D

Fleet demo: one bridge, a UI and two services

One autonomous bridge drives three apps at once, each hosting its own agent surface and reached through its own nREPL:

appruns onnREPLwhat the agent gets
todothe browser (shadow-cljs build :app, page on http://localhost:8280)shadow's, 7888todo__todo_add, todo__todos_visible, the app-db
ordersa JVM (clojure -M:example/orders)example/orders/.nrepl-portorders__orders_place, orders__orders_list, refunds (billing)
inventorybabashka (bb --init boot.clj nrepl-server)7872inventory__inventory_reserve, inventory__inventory_item, ...

The scripted agent workflow (example/fleet/probe.edn): customer lin wants two mice. The agent

  1. checks stock in inventory (6 available) and reserves 2,
  2. places the order in orders,
  3. adds "ship order to lin" to the team's list in the todo UI: a re-frame event in the browser tab, visible on the page,
  4. reads it back through the UI's own subscription and app-db, finds the order in orders, is refused by the inventory domain when it over-promises and by the scope check when it tries a write-off (audit scope not granted),
  5. reads the one fleet ledger, where every call is attributed to its app.

Run it with hive-compose

The apps are declared as hive-compose host programs in the repository: example/fleet/hive-compose.edn (the project and its three programs) and example/fleet/compose.yaml (one do-nothing anchor service, because a section starts its programs once its containers are up). hive-compose takes its projects from the operator's config, so add this once under :addons {"hive.compose" {...}} in ~/.config/hive-mcp/config.edn (replace <repo> with the absolute path of this checkout):

{:compose/projects
 [{:project/id "autonomous-fleet"
   :project/dir "<repo>/example/fleet"
   :project/ttl-minutes 30
   :project/programs
   [{:program/id "todo"
     :program/dir "../.."
     :program/kind :shadow
     :program/command ["clojure" "-J-Xmx2g" "-M:cljs" "-m" "shadow.cljs.devtools.cli" "watch" "app"]
     :program/nrepl-port 7888}
    {:program/id "orders"
     :program/dir "../orders"
     :program/kind :plain
     :program/command "cd ../.. && exec clojure -M:example/orders"}
    {:program/id "inventory"
     :program/dir "../inventory"
     :program/kind :bb
     :program/command ["bb" "--init" "boot.clj" "nrepl-server" "127.0.0.1:7872"]
     :program/nrepl-port 7872}]}]}

It is the content of example/fleet/hive-compose.edn, which stays the single source: bb fleet-demo reads the same file. Then compose reload, and:

compose up target=autonomous-fleet/anchor     # busybox anchor + the three programs
compose programs                              # pid, log, nREPL port, nrepl-ready?
compose claim target=autonomous-fleet/anchor note="fleet demo"   # optional: hold it

Open http://localhost:8280 (the todo page is the UI's runtime), then run the bridge, by hand or registered with Claude Code:

bb serve --dir . --build app --target-id todo \
         --dir example/orders --clj \
         --port 7872 --target-id inventory \
         --actor fleet-agent --scopes read,write,billing
claude mcp add fleet -- bb --config "$PWD/bb.edn" serve --dir "$PWD" --build app \
  --target-id todo --dir "$PWD/example/orders" --clj --port 7872 --target-id inventory \
  --actor fleet-agent --scopes read,write,billing

compose release target=autonomous-fleet/anchor stop=true (or compose down target=autonomous-fleet/anchor) stops the programs and the anchor; otherwise the reaper stops them after 30 idle minutes. Nothing outside the section is touched.

Run it without hive-compose

bb fleet-demo              # start the three programs, print the bridge command; Ctrl-C stops them
bb fleet-demo --headless   # also open the todo page in a headless Chromium
bb fleet-demo --probe      # start, open headless, run the workflow, stop everything

bb fleet-demo starts exactly the commands of example/fleet/hive-compose.edn, in the same directories, with logs in target/fleet-demo/. A program whose nREPL already answers (say hive-compose runs it) is reused and left running. Two JVMs are started (shadow -Xmx2g, orders -Xmx512m), so before each the launcher

  • waits while 3 or more test-run JVMs run on the host (pgrep -fc 'java.*-M:[a-z:]*test'; services and watchers do not count; limit FLEET_MAX_JVMS, wait FLEET_JVM_WAIT_S, default 1200 s), and
  • refuses with less than 15 GiB available (FLEET_MIN_AVAIL_GB).

The headless browser is Playwright's chrome-headless-shell when installed, else chromium on the PATH, or FLEET_CHROMIUM.

The probe

bb fleet-demo --probe reruns the whole demo and exits 0 only when every step answered as expected. It reuses example/probe.clj, which now also takes :contains (text a result must hold) and [:str ..] (a string built from earlier results, e.g. the new order id). With the fleet already up, the probe alone:

bb example/probe.clj example/fleet/probe.edn \
  bb serve --dir . --build app --target-id todo --dir example/orders --clj \
  --port 7872 --target-id inventory --actor fleet-agent --scopes read,write,billing

The services keep their state, so rerun the probe against a fresh fleet (the reservation in step 3 grows on each run; step 2 expects the seed).

Can you improve this documentation?Edit on GitHub

cljdoc builds & hosts documentation for Clojure/Script libraries

Keyboard shortcuts
Ctrl+kJump to recent docs
←Move to previous article
→Move to next article
Ctrl+/Jump to the search field
× close