The template catalog is now Example 1-4: one stage, two stages (handoff), feedback loop (runner-owned limits, retries, timeout) and human decision (type=human approve/revise/abort with notify hooks). All read-only or leave changes uncommitted; none commits, pushes or deploys. A brand-new database (schema created by this Open) gets the examples once at server start, bound to the configured default model and harness. A server_settings marker records the decision, so removed examples never come back and existing installs are marked without any pipeline being added or rewritten.
4.9 KiB
Alpha tester walkthrough
Pipelines is a single-user alpha for supervised workflows, not a multi-user service or a guarantee that a model's answer is correct.
Setup
- Use macOS or Linux with an existing configured harness and the prerequisites listed in installation.
- From a Git checkout, run
./install. Native host installation is the default; Docker is optional with./install --docker. - Open the web address reported by setup. For terminal use, put the installation's
bindirectory on PATH and runpipelinesfrom your project directory. - Setup also starts the authenticated web proxy, server, and ntfy and enables
login startup. See installation for the private web credential
location. The installed CLI's
pipelines service enable/service statusmanage that same service; do not start another server manually.
Native setup reuses host harness configuration. Docker has separate persistent credentials. Never start both installations on the same ports. Do not run the installer against a shared instance while work is in flight.
The browser proxy requires authentication. The underlying Pipelines/harness control APIs do not: keep them private and never expose them to the Internet. Use trusted networks and TLS/VPN as appropriate; authentication is not an OS sandbox for model tools.
First supervised run
- Pick a disposable project without secrets or valuable uncommitted changes. A remote browser selects a directory on the server, not its own computer.
- A fresh database already holds the four example pipelines
(
examples/README.md). Run the read-only Example 1: one stage first. - Ask it to review one short file. Watch the graph and inspect the retained report and the stage's Audit → Session evidence.
- Try Example 2: two stages on a few local files. Check the result against the sources yourself; a successful stage is not proof of factual accuracy.
- Only then try an editing example (feedback loop, human decision). Inspect actual changes and test evidence, not just the model's summary. Keep version control/backups.
Editing a draft does not publish it. Publication creates an immutable version; runs retain the version they used. Export/import bundles contain definitions only, not credentials, projects, sessions, drafts, or history.
Sessions and stopping
Model stages settle their exact native session and verify its export before handoff. An export failure retains computed output and waits for export-only recovery; when that bounded recovery is exhausted the run continues with the incomplete export recorded as a warning. Retry export only reads that session again; it does not rerun the stage. A genuinely missing historical conversation cannot be reconstructed by inventing messages.
Cancellation/retry is not rollback. Earlier file edits or commands remain; a new execution can repeat side effects. Never delete data/volumes to fix a run.
Notifications
Browser alerts require the page to be open; closed-app web push is not supported. The Android app delivers notifications in the background over its own connection. ntfy is an optional fallback channel that works without the Pipelines Android app. Installation verifies publishing, not reception. Check device reception before relying on it. See Notifications.
Known limits
- Sequential stages within a run; independent workspaces can run concurrently.
- Tools can read/edit files and execute commands. Permissions are not an OS sandbox.
- Diffs, inventories, and session exports have explicit bounds. Partial or missing evidence must not be interpreted as “nothing changed” or a complete capture.
- Usage budgets depend on provider-reported usage and can overshoot in flight. Set provider spending limits too.
- Native Windows, every terminal/browser combination, fresh provider OAuth, and phone dispatch are not established by automated macOS checks. Linux installer mocks are not a substitute for a real Linux host trial.
Report a problem
Include OS/architecture, native or Docker install, exact reproduction steps, expected/actual behavior, and the affected run ID. Capture:
pipelines version --json
pipelines ping --json
pipelines status --json
The client and server can be different builds. Redact tokens, private paths, prompts, files, diffs, and session content before sharing. Do not post your database or harness credential/session storage.
Maintainer checks (no live deployment)
go test ./...
go vet ./...
node --test web/test/*.test.mjs
python3 -m unittest discover -s scripts -p 'test_*.py'
python3 scripts/smoke-first-install.py
Use isolated prefixes, loopback ports, and scratch databases. The smoke check does not run models or send alerts. Browser capture instructions are in web verification. Do not restart the operator's services to test source changes.