Pipelines
Reusable, sequential workflows for your repositories, with a Go CLI/TUI, OpenCode model stages, retained run history, and optional phone notifications.
Install
./install.sh defaults to full Docker server + ntfy setup; use --native for
native binaries only. Docker mode needs Docker Compose and Python 3; native
mode needs Go 1.27+ and uses your existing OpenCode for model stages.
For the host CLI/TUI walkthrough below, also install Go 1.27+; the Docker
installer installs/updates those clients when host Go is available.
git clone https://git.a-wan.net/alan/pipelines.git
cd pipelines
./install.sh # configure/start Docker services and connect a provider
# Optional host CLI/TUI binaries: ./install.sh --native
Go uses GOBIN or its normal GOPATH/bin default; put that directory on PATH.
The Docker installer automatically detects/configures LAN networking for ntfy;
you do not need to look up your IP or supply a URL/listen address.
Both Docker services bind 0.0.0.0; reinstall normalizes those bind settings
without replacing your URLs, timezone, ports or credentials.
Native mode installs the Go binaries and shared OpenCode pipelines skill without
login checks or automatic services. Docker mode configures ntfy accounts/token,
checks publishing/health, and opens container OpenCode provider login on first setup;
existing settings, credentials and volumes are retained on reinstall.
Docker provider credentials live in its persistent container volume, separately
from your host OpenCode login. Setup asks for ntfy account passwords, then your
model-provider login and a model; it validates that model with a small real
generation (provider charges may apply).
With plain go install ./cmd/..., also run pipelines skill install.
For system-wide use, install the binaries into your chosen system bin directory
with the appropriate permissions. Configuration and data remain per-user.
Docker setup starts the server and saves its client endpoint (default host port
8081). Do not also start pipelines serve for this setup. Explicit --url
and PIPELINES_URL override the saved endpoint; restart existing TUIs after setup.
Docker mounts your home and installation checkout at their original paths and
uses your UID/GID. Other host repositories need a bind mount at the same absolute
path; repositories on another client computer are not automatically transferred.
These unauthenticated server ports are for trusted networks only—do not expose
them to the public Internet.
Native server instead (optional)
Start a native server explicitly; fresh databases contain no pipelines:
pipelines serve # foreground server
# In another terminal:
pipelines
Optional autostart at login (starts the server now):
pipelines service enable
pipelines service status
Uses user-level systemd on Linux or launchd on macOS; no sudo. Runs use the
directory you invoke pipelines run from. Preview with --print. Stop any existing
foreground/legacy server first. Disable with pipelines service disable before
uninstalling. See installation for environment and boot options.
Your first pipeline and run
Start in the repository you want the workflow to operate on:
cd /path/to/your/repository
pipelines
- Create: press n or use :new. Choose OpenCode to author a workflow together, or nvim to edit the Markdown yourself. The selected editor must be installed on your client computer. Describe the stages, their inputs/outputs, and the tools they need. Templates (b on Home) are optional; a fresh installation has no published pipelines.
- Keep a draft: finish/exit the editor. Nothing is published just because you edited it. Press d / :drafts to find retained drafts; e edits and v validates the selected draft.
- Publish: press s in Drafts. If it has no name, type one into the name prompt and press Enter. Then review and explicitly confirm submission. The server validates it and creates an immutable pipeline version; the draft stays.
- Run: select the published pipeline, press Enter to open it, then :run to start a run. Supply your task and review the confirmation. The run uses the directory from which you launched the client, not the installer checkout.
- Inspect: watch the full graph and stage progress. Tab expands/focuses panes; n/p select recorded stage visits; hjkl pan a focused graph. On a failed run, D / :debug opens a fresh OpenCode debugging conversation; retry requires confirmation and restarts the pinned workflow, so earlier side effects may happen again.
Quit with :quit; q does not exit. For a terminal-only run after publication:
pipelines run "your pipeline name" "Describe the task"
Phone notifications
Open :status for the server and ntfy connection details. In the ntfy phone
app, add the displayed ntfy server, sign in as phone-reader with the password
you set during installation, and subscribe to the displayed topic. Stages must
include a notify block to send notifications; see ntfy setup.
Installation checks publishing, not reception on your phone.
For Tailscale, both devices must be connected; use
http://<server-Tailscale-IP>:8090. Binding to 0.0.0.0 does not bypass firewalls:
UFW/Docker forwarding rules can allow LAN sources but drop Tailscale sources.
See Tailscale troubleshooting.
Uninstall
pipelines uninstall # remove Go binaries; keep history, drafts, and ntfy data
A three-stage pipeline
Plan → Implement → Review. Each stage receives the previous stage's output;
the first receives your task prompt. One outcome selects the next stage—no
parallel branches. Definitions use Markdown output, prompt, tools,
configs, and edges blocks. For example:
# stage planner
```output
{ task, plan, acceptance_checks }
```
```prompt
Turn input.prompt into a focused plan and acceptance checks.
```
```tools
```
```configs
provider=opencode-go
model=deepseek-v4.1-flash
retries=0
```
```edges
success -> implementer
error -> #failure
```
The complete three-stage example adds the implementer and reviewer. Review and explicitly submit it:
pipelines validate examples/three-stage.md
pipelines submit examples/three-stage.md --name "three stage" --create-only
pipelines run "three stage"
Every submission is validated and creates an immutable version. Examples are optional; nothing is imported automatically. Run from your repository directory; stage tools are enabled automatically. Edits support any language/file type and new files. No file list or typed RUN confirmation is required.
Useful commands
pipelines # dashboard; b browses templates
pipelines list
pipelines run # fuzzy selection + multiline prompt
pipelines run "bug fix" "Fix the layout" # run in the current repository
pipelines new "daily digest" "Summarize changes"
pipelines edit "bug fix" "Add a review step"
pipelines drafts --json
pipelines validate /path/to/draft.md
pipelines submit /path/to/draft.md # explicit publication
pipelines runs
pipelines inspect 1
pipelines serve # foreground server; Ctrl+C stops it
pipelines ping
pipelines help edit
CLI new/edit open OpenCode directly with @pipelines. The installed skill asks
missing questions; pipelines new needs no preliminary questionnaire. Changes stay
as drafts by default; CLI and TUI share validation and draft storage. Most
commands support --json for agents and scripts.
In the TUI, press d (or use :drafts) to browse retained drafts, including CLI-created ones. e reopens a draft, v validates it, and s opens explicit submission confirmation, asking for a name first if needed. Drafts remain retained after submission.
From a run, press P / :pipeline to open the pipeline version it used.
Initial run input also records pwd. Press r / :retry on a failed run
(or pipelines retry <run-id>) to start a new attempt with the same original
input, directory, and pipeline version. Completed side effects are not undone.
Retries restart at the entry stage with fresh OpenCode sessions, never the previous
conversation or intermediate stage output. Pipelines does not automatically delete
generation, agent, or formatting-repair sessions, including on failure/cancellation.
Primary session IDs are retained in run steps (pipelines inspect <run-id> --json).
On Home, r opens global run history; / fuzzy-searches it. Inside a pipeline,
r / :runs opens only that pipeline's history.
Quit the TUI with :quit; q does not exit. Ctrl+C remains an interrupt.
Starting/retrying/canceling runs and deleting drafts require confirmation. CLI
publication also prompts; use --yes only for explicitly approved automation.
n / :new and creating from a template offer a Tab-navigable, fuzzy-searchable
picker: nvim opens the draft Markdown file; OpenCode authors it with you.
Canceling the picker creates no draft and publishes nothing.
Wide terminals show runs and pipelines side by side; narrow terminals stack them.
The TUI uses soft light/dark-adaptive cards, muted metadata, subtle selections,
and local loading animations instead of heavy character borders and inverted bars.
The dashboard includes all-history usage, success rate, average completed duration,
per-pipeline usage, and a 14-day activity chart. CLI: pipelines stats [--json].
Use :status for two panels: server addresses and ntfy phone connection details.
CLI: pipelines status [--json]. Candidate URLs are not
verified reachable; publishing endpoints and credentials are not disclosed.
Retry is offered only after the failed run and its agent have fully stopped.
The run inspector shows the entire pinned graph above the details, dimming stages
and routes not executed. g focuses the graph; hjkl or arrows pan it.
The path and elapsed duration update while running. a opens the active/latest
OpenCode session's recorded tool evidence; this does not attach a live OpenCode UI.
Press D / :debug (or pipelines debug <run-id>) for a fresh OpenCode
conversation about that run. It uses CLI queries rather than resuming or retrying
the implementing agent. Pipeline Edit offers a fuzzy-searchable nvim /
OpenCode picker; Tab and Shift+Tab navigate it.
In the draft browser, x then y deletes the selected retained draft and
metadata. CLI: pipelines draft-delete <draft.md>. Published history is untouched.
Model results use native JSON-schema output where supported, precise parsing errors, and bounded format-only repair without replaying tools. Optional stage permissions narrow file/command access without imposing a language-specific default. See model result recovery and permissions. The run graph header shows start time and elapsed/final duration, plus finish time for completed runs.
More: CLI · installation · pipeline format.