# CLI and agent authoring `pipelines help` lists commands; `pipelines help edit` (or `edit --help`) shows command-specific flags and examples. Installed commands work from any directory. The installed command is a compiled Go binary. Optional autostart uses the OS user service manager directly. Legacy Python-managed installations require an explicit `PIPELINES_PREFIX`; no configuration is inferred from the executable's location. For source development, use `go run ./cmd/pipelines help`; start the native server separately. Set `PIPELINES_URL` or pass `--url` to select another server. ## Draft-first OpenCode workflow ```sh pipelines new # OpenCode asks what to build and names it pipelines edit # fuzzy pipeline selection pipelines edit "bug fix" # ask OpenCode what to change pipelines edit "bug fix" "Add a review step" pipelines new "release notes" "Summarize changes and notify my phone" pipelines new "weekly digest" --template scheduled-summary ``` `new` opens OpenCode immediately when its name/request is omitted. The skill asks only for missing decisions and records the chosen name in draft metadata. `edit` accepts an exact name or ID, with names taking precedence over numeric IDs. Both retain private drafts and launch the host interface once with a short `@pipelines` reference and context-file path. There is no preliminary OpenCode API call, temporary service, session creation, or instruction preload. `install.sh` installs/updates the global skill and format reference. Plain `go install` users run `pipelines skill install` separately. Shared login/config and user-modified skills are preserved; OpenCode permissions remain in effect. The skill encourages editing only the draft, running server validation, summarizing the changes, and leaving submission to the user. This is an instruction, not a security sandbox: an agent with CLI/shell access can submit when explicitly asked. Every submission, including agent-issued `submit`/`rpc`, still uses server validation. ## Drafts in the TUI Press `d` on the dashboard or use `:drafts` to browse the same retained drafts as `pipelines drafts`. Use `n/p` to select, `j/k` to scroll source, `e`/Enter to reopen the existing draft, `v` for server validation, and `s` for submission confirmation. `r` refreshes the list. Submission preserves create-only/version guards and rejects drafts belonging to another server. An unnamed draft must be named through OpenCode or CLI `submit --name`. Draft selection/editor completion never publishes it. New unnamed drafts open OpenCode so the skill can name them. For named drafts, the default editor is OpenCode; explicit `VISUAL`/`EDITOR` overrides remain. For agents or scripts that should not open a terminal: ```sh pipelines new "release notes" --no-open pipelines edit "bug fix" --json pipelines drafts --json pipelines validate /path/to/pipeline-123.md --json pipelines submit /path/to/pipeline-123.md --json ``` `--json` never opens an editor or picker; provide a name explicitly. It returns draft metadata including `path`, `name`, `server`, `create_only`, and `base_version`. `--no-open` prints the path and review commands. `$PIPELINES_DRAFT_DIR` overrides the shared cache directory. CLI and TUI drafts use private Markdown plus metadata sidecars; `submit FILE` can publish either. External files require `--name NAME`. New drafts use create-only submissions and cannot overwrite existing names. Edits carry a latest-version guard checked atomically by the server. On conflict, inspect/export the latest version and reconcile the draft. `--force` explicitly bypasses the version guard only, **never** syntax, graph, model, tool, schedule, or notification validation. Original versions/sources remain immutable. Submitting activates included schedules, so review them before publishing. ## CLI/TUI capability map | TUI action | Agent-capable CLI | | --- | --- | | Browse/search pipelines | `list --json`, `show NAME --json` | | Original source and history | `export NAME --version N`, `versions NAME --json` | | Browse templates/source | `templates --json`, `template KEY --source` | | Create or edit a definition | `new`, `edit`, `drafts` | | Validate and publish | `validate FILE`, `submit FILE` | | Start a run | `run NAME PROMPT --yes --json` | | Run history/inspection | `runs --json`, `inspect ID --json` | | Cancel | `cancel ID --json` | | Connection and phone settings | `connection --json`, `ping --json` | | Operational diagnostics | installed `logs`, `status`, `doctor` | The TUI does not spawn CLI processes for each request. Both front ends share `internal/client`'s command transport and `internal/draft`'s persisted drafts; the server owns all validation, persistence, execution, and schedules. `rpc` exposes the full protocol as an escape hatch, so no server command is TUI-only: ```sh printf '%s' '{"type":"get_pipeline","pipeline_id":1,"version":1}' | pipelines rpc - ``` Existing protocol commands: `ping`, `list_pipelines`, `get_pipeline`, `list_templates`, `validate`, `submit`, `run_pipeline`, `list_runs`, `get_run`, `cancel_run`, `retry_run`. See `internal/protocol/message.go` for JSON envelopes. Mutating RPCs have real effects; they are not previews. TUI-only animation, scrolling, and transient client logs are presentation, not separate server capabilities. ## Scripted runs On either the runs list or run inspector, press `p` (or use `:pipeline`) to open the selected run's exact pipeline version. Navigation does not cancel the run. Initial input includes `pwd`, the resolved run directory (normally the directory you invoked Pipelines from), alongside the task and any custom input fields. It is recorded by the server and shown in the run's Input section. Press `r` or use `:retry` on a failed run to restart it from the first stage. CLI equivalent: `pipelines retry ` (optional `--json`, `--wait`, and `--request-key`). The new attempt retains the initial input, directory, pinned pipeline version, and edit scope, and records `retry_of`. Original history is unchanged. Legacy runs gain `pwd` from their recorded workspace on retry. Retry replays the entire workflow; earlier edits or notifications are not undone and may happen again. A missing original directory blocks retry rather than silently using your current directory. Retry is hidden and rejected while a run is executing or agent cleanup remains active, even if a terminal status was already persisted. Run RPCs report `executing` alongside status so clients can distinguish cleanup from completion. The run inspector's upper half shows the actual execution path using the shared pipeline graph renderer and viewport. Visits are numbered, including repeated visits in loops; only recorded routing decisions become edges. No unchosen stage is added to the run path. On small terminals the details take precedence. Press `g` to focus the graph, arrows to pan, and `j/k` or PgUp/PgDn to scroll. Press `g` or Tab to return to details. When not focused, the graph follows the latest visit or selected stage. Existing polling refreshes the graph once per second, and running durations show elapsed time rather than “in progress.” Press `a` to select the active/latest retained OpenCode agent session and open its tool evidence. Session ID is available during execution; tool transcripts appear when persisted (currently after generation). This does not attach a live OpenCode client or stream its messages. Supporting live attachment consistently across the shared and privately owned OpenCode backends is deliberately deferred. ## Investigating runs in OpenCode On the runs list or inspector, press `D` or use `:debug`; CLI equivalent: `pipelines debug `. This opens a fresh normal OpenCode conversation, not the implementing session. It supplies exact commands for `inspect --json` (including stage history, inputs/outputs, diagnostics, notifications, session IDs and transcripts), `show --version N --json`, and `runs --pipeline --json`. All retrieval remains available through the CLI and can be repeated while execution is active. No new model API or live attachment integration is required. `debug --json` returns the context and prompt without launching OpenCode; `--no-open` prints the prompt. `--opencode` selects the executable. Debugging works for active and terminal runs and does not automatically retry, cancel, or resume them. If the recorded directory is unavailable, OpenCode launches from your current directory and retrieves historical evidence through the CLI. ## Editor choice and draft cleanup On the pipeline detail page, `e` / `:edit` opens an editor picker: **nvim** or **OpenCode**. Type to fuzzy-search; Tab/Shift+Tab (or arrows) choose; Enter opens; Esc cancels without creating a draft. Explicit choice overrides VISUAL/EDITOR. Both choices edit a retained copy with the normal version guard, never the published definition. Submission remains separate and explicit. In the draft browser, `x` asks to delete the selected draft; `y` confirms and Esc or `n` keeps it. The CLI equivalent, `pipelines draft-delete `, is an explicit deletion command and needs no server connection; `--json` reports the result. Only managed drafts inside the configured draft cache are accepted. Source and metadata symlinks/directories and external Markdown files are rejected. Published definitions and run history are not deleted. Cleanup can also remove orphaned metadata when a draft source was already removed. ```sh cd ~/repos/project pipelines run "bug fix" "Fix the layout" --json pipelines run "bug fix" "Fix the layout" --json --wait --timeout 10m pipelines run "bug fix" "Fix the layout" --json --request-key my-unique-task ``` Runs default to the client's current directory and latest accepted version. The server resolves that directory without a repository allowlist. `--version` chooses an immutable version in JSON mode. Starting a run enables its stage-declared tools without a second approval. Editing supports all file types and new files within the run directory; no file list is required. Shell commands use the repository's actual tooling. `--write-paths` is an optional narrower scope, not a prerequisite. `--yes` and `--allow-tools` remain compatibility flags but are not required. `--wait` polls until terminal status, returns nonzero on failure/cancellation, and does not cancel a run when waiting times out. Reuse `--request-key` to prevent duplicate work. A supplied pipeline/task starts immediately with a live inspector. When a task is omitted, Enter inserts a newline and Ctrl+S runs the composed task. There is no file-list question or typed RUN confirmation. Shell runs with your user's authority: the run directory and tool policy are not an OS sandbox. JSON results go to stdout, errors to stderr (JSON error envelopes when requested), and failures exit nonzero. Export/template `--source` deliberately prints raw Markdown. `--timeout` bounds each server request and the optional wait duration. ## Verification scope CLI integration tests exercise draft/validate/submit/history/conflict handling and scripted run/inspection/cancellation through a real local WebSocket server (the run test uses a controlled executor, not a model). The isolated installed CLI also exercised the actual OpenCode API's session creation and skill activation, while capturing interactive launch arguments to avoid a model turn. Full model-driven authoring and Linux execution are **not tested**.