mirror of https://github.com/jackwener/OpenCLI.git synced 2026-09-14 18:25:42 +08:00

Files

T

flizzywine ba3a674d7b feat(grok): add image command for grok.com image generation (#906 )

* feat(grok): add image command for grok.com image generation

Add `opencli grok image <prompt>` which submits a prompt via the existing
grok.com browser session and returns the generated image URLs from the
latest assistant bubble.

Because assets.grok.com URLs are gated by Cloudflare and cannot be
downloaded with a plain HTTP client, the --out flag triggers an in-page
fetch(credentials: 'include') so the browser session's cookies and
referer are attached, then writes the decoded blob to disk.

Flags:
- --new       start a fresh chat before sending
- --timeout   max seconds to wait for the image (default 240)
- --count     minimum number of images to wait for before returning
- --out       directory to save downloaded images

Ships with unit tests for the helpers (isOnGrok, normalizeBooleanFlag,
dedupeBySrc, imagesSignature, extFromContentType, buildFilename).

* fix(grok): harden image composer and bubble detection

* fix(grok): harden image flow and docs

---------

Co-authored-by: jackwener <jakevingoo@gmail.com>

2026-04-14 20:42:43 +08:00

2.6 KiB

Raw Permalink Blame History

Grok

Mode: Default Grok adapter + optional explicit consumer web path · Domain: grok.com

Commands

Command	Description
`opencli grok ask`	Keep the default Grok ask behavior
`opencli grok ask --web`	Use the explicit grok.com consumer web UI flow
`opencli grok image`	Generate images via the Grok web UI and return the latest image URLs

Usage Examples

# Default / compatibility path
opencli grok ask --prompt "Explain quantum computing in simple terms"

# Explicit consumer web path
opencli grok ask --prompt "Explain quantum computing in simple terms" --web

# Best-effort fresh chat on the consumer web path
opencli grok ask --prompt "Hello" --web --new

# Set custom timeout (default: 120s)
opencli grok ask --prompt "Write a long essay" --web --timeout 180

# Generate an image and return the URLs
opencli grok image "a cyberpunk mechanical owl, neon purple and blue" --new true

# Save generated images to disk
opencli grok image "a watercolor lighthouse on a cliff" --out /tmp/grok-img --timeout 300

Options

Option	Description
`--prompt`	The message to send (required)
`--timeout`	Wait timeout in seconds (default: 120)
`--new`	Start a new chat before sending (default: false)
`--web`	Opt into the explicit grok.com consumer web flow (default: false)
`--count`	Minimum images to wait for before returning (default: 1, `image` only)
`--out`	Directory to save generated images to disk (`image` only)

Behavior

opencli grok ask keeps the upstream/default behavior intact.
opencli grok ask --web switches to the newer hardened consumer-web implementation.
The --web path adds stricter composer detection, clearer blocked/session-gated hints, and waits for a stabilized assistant bubble before returning.
opencli grok image reuses the existing browser-backed Grok session, waits for the latest assistant image bubble to stabilize, and can optionally download the resulting images through the authenticated page context.

Prerequisites

The Grok adapter still depends on browser-backed access to grok.com
For --web, Chrome should already be running with an authenticated Grok consumer session
Browser Bridge extension installed

Caveats

--web drives the Grok consumer web UI in the browser, not an API.
It depends on an already-authenticated session and can fail if Grok shows login, challenge, rate-limit, or other session-gating UI.
It may break when the Grok composer DOM, submit button behavior, or message bubble structure changes.

2.6 KiB Raw Permalink Blame History