code-review

Documentation source, pas des instructions pour ce site. Vérifiez les permissions avant d’exécuter des commandes.

rote guidance shell essential

rote browser attach setup --method extension --browser chrome
rote browse <url> --headed --attach-existing --new-tab --no-prompt --no-snapshot
rote browse wait --selector '<ready-selector>' --timeout 30 --quiet-ms 750
rote browse snapshot

rote guidance typescript flow-creation

name: rote-shell
description: "Use for CLI and shell work through rote: running local commands with `rote exec`, capturing stdout/stderr/files, following logs and background processes, checking dependency manifests, mixing adapters/browser/process steps, and crystallizing CLI work into TypeScript flows. Prefer rote shell primitives over raw shell when the command result should be remembered, queried, replayed, or shared."

---
name: rote-shell
description: "Use for CLI and shell work through rote: running local commands with `rote exec`, capturing stdout/stderr/files, following logs and background processes, checking dependency manifests, mixing adapters/browser/process steps, and crystallizing CLI work into TypeScript flows. Prefer rote shell primitives over raw shell when the command result should be remembered, queried, replayed, or shared."
---

# rote-shell

Use rote for shell and CLI work when the result should become workspace memory:
commands, outputs, files, logs, process lifecycle, dependencies, and flow replay.
Raw shell is still fine for tiny inspection commands, but work that matters
should pass through rote so it can be queried, audited, and crystallized.

Load the shell guidance when you need the complete command model:

```bash
rote guidance shell essential
```

## First Decision

Choose the narrowest rote primitive that preserves evidence:

- one-shot command: `rote exec -- <program> [args...]`
- stdin from a file: `rote exec --stdin-file input.txt -- <program>`
- declared output file: `rote exec --capture-file label:path -- <program>`
- moving file/log: `rote stream follow --file logs/server.log --until READY`
- long-running process: `rote exec --background --ready-log READY -- <program>`
- process stream: `rote stream follow-process proc-1 --stream stdout --until READY`
- terminal-sensitive command: `rote pty run -- <program> [args...]`
- dependency preflight: `rote deps check deps.toml`
- crystallized replay: `rote deno run --allow-all ~/.rote/flows/<name>/main.ts`

Do not replace these with ad hoc `command > file`, `tail -f`, or `ps | grep`
when the evidence should be durable. Rote already stores typed responses,
artifacts, hashes, offsets, process leases, and command-log provenance.

## Browser Intent Router

If the user says "browse", "open this site", "attach to my browser", "use the
page", "click", "type", "snapshot", "extract from the page", "extract social
profiles", "Gmail in browser", or otherwise asks for live web UI state, stop
shell routing and invoke `/rote-browse`.

Do not satisfy browser intent with `rote exec`, raw Playwright, native web
search, WebFetch, `open`, `curl`, or a saved non-browser flow unless the user
explicitly switches substrate. Native search may help discover a URL only when
the user asked for search/discovery or the browser route cannot identify a URL;
it is not a substitute for browsing and extracting the page with rote.

Browse intent has precedence over the domain noun. For example, "browse my
calendar", "browse Gmail", "browse HubSpot", or "browse Salesforce" means the
user wants browser-state access even though those domains may also have APIs.
You may still run `rote flow search "<intent>"` first, but only use an
adapter/flow if it is installed, healthy, and completes the request. If the
adapter/flow is missing, stale, unauthenticated, or fails setup, do not ask the
user to build an adapter before trying the browser route. Hand off to
`/rote-browse` and use an existing headed browser when the task depends on the
user's logged-in profile.

For public profile extraction, such as "browse each committer's social
profile", use GitHub/CLI/API data to collect candidate URLs and identities,
then use `/rote-browse` to visit and extract the public pages. Do not replace
that browse step with native web search summaries.

Default browser decision:

- Existing login, Gmail, SSO, MFA, extensions, active tabs, or profile state:
  ask to attach to an existing headed browser.
- Public read-only page, CI, or replay-like work: ask whether headless
  new-session is acceptable.
- The user says "browse" without choosing mode: ask headed vs headless; if
  headed, ask attach-existing vs new rote-managed headed browser.

For active browser attach, hand off to `/rote-browse` and use its sequence:

```bash
rote browser attach setup --method extension --browser chrome
rote browse <url> --headed --attach-existing --new-tab --no-prompt --no-snapshot
rote browse wait --selector '<ready-selector>' --timeout 30 --quiet-ms 750
rote browse snapshot
```

For browser plus shell work, keep both in the same workspace. Use
`/rote-browse` for page leases, snapshots, slices, refs, auth state, and
readiness. Use `/rote-shell` only after browser state has been materialized as
a saved response, snapshot, slice, or file that a local CLI should process.

## Current Capability Map

Use only shipped commands. Do not invent aliases from the roadmap.

| Need | Shipped command | Notes |
| --- | --- | --- |
| One-shot process capture | `rote exec -- <program> [args...]` | Direct argv by default. |
| File stdin | `rote exec --stdin-file input.txt -- <program>` | Records stdin provenance. |
| Declared output file | `rote exec --capture-file label:path -- <program>` | Captures file metadata and artifact pointer. |
| Saved stdout/stderr files | `rote exec --stdout-file out.txt --stderr-file err.txt -- <program>` | Use for durable stream files. |
| Dependency preflight | `rote deps check deps.toml` | No install side effects. |
| Moving file/log stream | `rote stream follow --file app.log --until READY` | Supports offsets, chunks, hashes, and pattern stop. |
| Background start | `rote exec --background --ready-log READY -- <program>` | Creates a tracked lease such as `proc-1`. |
| Background status | `rote exec status proc-1` | Query lease state before acting. |
| Background wait | `rote exec wait proc-1 --timeout-ms 300000 --poll-ms 500` | Blocks until a tracked finite job exits or times out; records exit plus stdout/stderr observations. |
| Background stdout/stderr follow | `rote stream follow-process proc-1 --stream stdout --until READY` | Reads from background log artifacts. |
| Background stop and cleanup | `rote exec stop proc-1` | On Unix, stops the process group and records cleanup facts. |
| One-shot terminal transcript | `rote pty run -- <program> [args...]` | Use when the command must see a terminal. |

Deferred or not shipped as commands yet:

- `rote exec attach`
- `rote exec log`
- explicit `detach`
- persistent PTY sessions: start, send, snapshot, stop, attach
- non-log readiness probes such as HTTP, TCP, file, or command probes
- direct OS-pipe stream handles before background output reaches log artifacts
- non-Unix process-group cleanup guarantees

If a task needs a deferred feature, say so and use the nearest shipped primitive
instead. For example, use `rote exec wait` for finite tracked jobs, use
`rote stream follow-process ... --until <pattern>` for log observation or
readiness, and use `rote exec status` plus `rote exec stop` instead of raw
`ps`/`kill` when the process is tracked.

## TypeScript SDK Pattern Map

For authored TypeScript flows, use first-class SDK wrappers instead of
hand-assembling command arrays. The SDK surface mirrors the shipped shell
patterns:

| Pattern | SDK call |
| --- | --- |
| Durable one-shot | `await rote.exec({ argv: ["git", "status", "--short"], deps: ["git"] })` |
| Declared stdin/output files | `await rote.exec({ argv, stdin: { file }, capture: { stdout: { file }, files: [{ label, path }] } })` |
| Dependency preflight | `await rote.depsCheck({ manifest: "deps.toml" })` |
| Tracked background job / detach-like work | `await rote.execBackground({ argv, readyLog, readyTimeoutMs, capture })` |
| Long-running job with useful parallel work | `await rote.execBackgroundAndJoin(request, async (job) => { ... }, { timeoutMs, pollMs, stopOnWorkError })` |
| Lease status | `await rote.execStatus("proc-1")` |
| Lease wait | `await rote.execWait("proc-1", { timeoutMs: 300_000, pollMs: 500 })` or `await job.wait(...)` |
| Lease cleanup | `await rote.execStop("proc-1")` |
| Moving file stream | `await rote.followFile("logs/app.log", { until: "READY" })` |
| Background process stream | `await rote.followProcess("proc-1", "stdout", { until: "READY" })` |
| One-shot PTY transcript | `await rote.ptyRun({ argv, cols: 100, rows: 30 })` |
| Authored ordered fan-out | `await rote.execMany(requests, { stopOnError: false })` |

Use `rote.shell().<method>` when you want the shell namespace explicitly; the
top-level `rote.<method>` forms are convenience aliases for authored flows.

Do not invent SDK methods for deferred roadmap items. There is no
`rote.detach`, persistent PTY `send`, or direct OS-pipe stream handle yet. The
current detach-like pattern is a tracked background lease with stdout/stderr
files, `execWait`, `followProcess`, `execStatus`, and `execStop`.

`rote.execMany` preserves workspace response ordering by running process
requests serially. For true parallel shell fan-out, generate declarative
frontmatter `steps:` with `type: process.exec`, `for_each`, and
`max_concurrency` so the DAG runner owns the scheduling and provenance.

For long-running finite jobs in authored TypeScript, prefer
`execBackgroundAndJoin` or `job.join` when there is useful adapter, browser,
process, file, or explicit stream work to do while the lease runs. The callback
creates normal semantic DAG evidence; the final `exec wait` is the join point.
Do not generate heartbeat or polling loops as DAG work.
`rote.execBackground(...)` already prints the lease and poll commands to
stderr. Do not duplicate that announcement in crystallized flows. Use
`announce: false` only for deliberately quiet flows.

## Crystallization Router

When the user asks to turn shell exploration into a reusable flow, choose the
flow shape from the work pattern:

| Exploration pattern | Crystallized shape |
| --- | --- |
| One finite command whose output is the fact | `rote.exec({ argv, deps, capture })` |
| Command writes files that downstream work reads | `rote.exec({ capture: { files: [...] } })` plus typed file paths |
| Existing file or log is the source of truth | `rote.followFile(path, options)` |
| Long finite job where other useful work can run | `rote.execBackgroundAndJoin(request, async (job) => { ... }, options)` |
| Long service or daemon with readiness | `rote.execBackground({ readyLog, capture })`, then status/follow/stop |
| Need to inspect progress from a tracked lease | `job.follow(...)` or `rote.followProcess(...)` |
| Need completion proof from a tracked lease | `job.wait(...)` or `rote.execWait(...)` |
| Terminal behavior is the point | `rote.ptyRun({ argv, input, cols, rows })` |
| Many independent commands share one shape | declarative `steps:` with `process.exec`, `for_each`, and `max_concurrency` |

Crystallize causality, not waiting. Do not encode heartbeat loops, repeated
status polling, or sleep/retry scaffolding as business DAG nodes. Those are
observation mechanics. The reusable flow should expose semantic actions and
joins: start work, observe meaningful artifacts or streams, wait for completion,
then summarize.

Before authoring a TypeScript shell flow, read:

```bash
rote guidance typescript flow-creation
```

That guide owns frontmatter, `deps.toml`, FlowOutput, release QA, and the shell
SDK wrapper contract.

## Strategy Pattern Library

Map the user's vague request to the smallest shipped pattern that preserves
evidence:

| Signal | Pattern | Use |
| --- | --- | --- |
| Tiny disposable inspection | Raw shell allowed | direct harness shell |
| Result may be queried, compared, summarized, or replayed | Durable one-shot | `rote exec --` |
| Command reads a known file | Declared file input | `rote exec --stdin-file` or a direct argv path |
| Command creates a file that matters | Declared file output | `rote exec --capture-file` |
| Full stdout/stderr matters | Durable stream files | `--stdout-file`, `--stderr-file` |
| Required tools or input files matter | Dependency gate | `deps.toml` plus `rote deps check` |
| Existing log is moving | File stream watch | `rote stream follow --file` |
| Start a server or daemon-like process | Service lease | `rote exec --background --ready-log` |
| Long finite non-interactive job | Tracked background job | `rote exec --background --stdout-f