Skip to content

README: showcase real capabilities, use new screenshot, drop stale refs - #11

Merged
aciderix merged 1 commit into
mainfrom
claude/readme-rework
Apr 22, 2026
Merged

aciderix merged 1 commit into
mainfrom
claude/readme-rework

Conversation

@aciderix

@aciderix aciderix commented Apr 22, 2026 •

Copy link
Copy Markdown
Owner

Summary

  • Replaces the broken docs/screenshots/chat.png reference with the newly uploaded docs/screenshot.jpg (centred <p align="center"><img width="360" />).
  • Adds a new top section "What you can actually do with it" that leads with concrete scenarios (project editing, shell execution, image gen, multimodal input, long sessions, export) rather than just a flat feature list.
  • Updates the feature breakdown: mentions 9 tools now (added generate_image, run_shell_command foreground/background), top-bar quick pickers, clickable links in markdown, image thumbnails.
  • New Advanced configuration subsections: Image generation (Imagen + Nano Banana, billing note), Background shell commands.
  • Drops the roadmap section (target file docs/ROADMAP.md was deleted on main).
  • Adds Gemma caveat under Gemini compatibility — those models are in the picker but don't support function calling.
  • EN and FR kept in full parity.

https://claude.ai/code/session_015dVKN2jG34HKP9SeBpSvS5

Summary by Sourcery

Refresh English and French READMEs to better showcase real-world capabilities, updated tooling, and current model compatibility while removing stale roadmap references.

Enhancements:

  • Replace the broken screenshot reference with a new centered chat screenshot shared by both READMEs.

Documentation:

  • Rewrite intro and add a new scenario-focused section describing concrete coding, shell, image, multimodal, long-session, and export workflows.
  • Expand the feature breakdown to mention all 9 tools, background shell commands, inline image generation, top-bar quick pickers, clickable markdown links, and multimodal input details.
  • Update prerequisites, installation, and first-run setup instructions to reflect current APK distribution, required billing for image models, and streamlined configuration steps.
  • Add advanced configuration guidance for image generation (Imagen and Gemini 2.5 Flash Image/Nano Banana) and background shell commands, including billing caveats and storage locations.
  • Clarify Gemini model compatibility, including support for gemini-2.5-flash-image-preview and the lack of function-calling support for Gemma models.
  • Keep English and French READMEs in sync, mirroring content and structure across both languages while removing the outdated roadmap section.

Summary by CodeRabbit

  • Documentation
    • Reframed documentation as a coding workstation with enhanced capabilities: file editing with diffs, inline image generation and analysis, live token reporting with auto-compression, autosave snapshots, and background shell command execution.
    • Updated supported models including gemini-2.5-flash-image-preview; added configuration options for auto-compression control and image generation billing guidance.

- New '🎯 What you can actually do with it' section leading with concrete
  user-facing scenarios (project editing, shell execution, image gen,
  multimodal input, long sessions).
- Feature list updated with tool count (9 tools), background shell,
  generate_image, top-bar quick pickers, Gemma caveat on function calling.
- Screenshot: switch from missing docs/screenshots/chat.png to the newly
  uploaded docs/screenshot.jpg, centred 360 px wide.
- Drop roadmap section (docs/ROADMAP.md was deleted).
- Advanced config gains 'Image generation' + 'Background shell' blocks.
- EN/FR kept in parity.
@sourcery-ai

sourcery-ai Bot commented Apr 22, 2026 •

Copy link
Copy Markdown

Reviewer's Guide

Refreshes both English and French READMEs to better showcase real-world capabilities (coding workflows, shell, images, multimodal, long sessions), swaps in a new chat screenshot, documents new tools and configuration (image generation and background shell), removes the stale roadmap, and clarifies Gemini/Gemma compatibility while keeping EN/FR in parity.

Flow diagram for advanced configuration: image generation and background shell commands

flowchart TD
  A["User opens Settings"] --> B["Configure image generation"]
  A --> C["Configure shell commands"]

  subgraph Image_generation
    B --> B1["Select Imagen model in Settings_Model"]
    B --> B2["Select gemini_2_5_flash_image_preview in top_bar"]
    B1 --> B3["App exposes generate_image function tool"]
    B2 --> B4["App sets responseModalities TEXT + IMAGE"]
    B3 --> B5["Model calls generate_image when appropriate"]
    B4 --> B6["Model returns inline images in chat"]
    B5 --> B7["Images saved under filesDir_attachments and shown as thumbnails"]
    B6 --> B7
  end

  subgraph Background_shell_commands
    C --> C1["Install Termux and run termux_setup_storage"]
    C1 --> C2["Enable Termux shell bridge in Settings_Termux_shell"]
    C2 --> C3["Model uses run_shell_command with background true"]
    C3 --> C4["Long_running process continues after model turn"]
    C4 --> C5["Output written to HOME_gemini_bg_run_id_log"]
  end
Loading

File-Level Changes

Change Details Files
Reworked intro and hero section to position the app as a pocket coding workstation and updated the main screenshot reference.
  • Replaced the generic Gemini-client intro with a coding-focused description that emphasises file edits, shell commands, image generation, and long-context sessions.
  • Swapped the broken docs/screenshots/chat.png image with the new centered docs/screenshot.jpg block in both languages.
  • Tightened wording and removed references to the official Google app or Gemini CLI where no longer needed.
README.md
fr/README.md
Replaced the flat features list with a scenario-driven "what you can do" section and a more detailed feature breakdown.
  • Added a new top-level section (EN: "What you can actually do with it", FR: "Ce que vous pouvez réellement faire avec") that walks through concrete workflows (project editing, shell usage, image generation, multimodal input, long sessions, autosave, export).
  • Renamed and expanded the features section into a detailed breakdown that explicitly lists 9 tools including generate_image and foreground/background run_shell_command.
  • Documented rich markdown rendering capabilities, clickable links, top-bar quick pickers for model and workspace selection, and multimodal input with image thumbnails and size limits.
README.md
fr/README.md
Clarified installation, first-run configuration, and prerequisites including image-generation billing requirements.
  • Updated prerequisites to distinguish free-tier chat usage from paid image generation, noting the need for Cloud billing and the 0 free-tier quota for image models.
  • Simplified installation instructions: describe release-tagged debug and release APKs, and compress build-from-source steps into a single shell block.
  • Split out initial setup into explicit ordered steps (API key, workspace folder via top bar, optional Termux shell bridge, model selection) in both languages.
README.md
fr/README.md
Extended advanced configuration docs to cover image generation flows and background shell commands, and adjusted auto-compression/Autosave wording.
  • Added an "Image generation" subsection explaining how Imagen (generate_image tool) and Gemini 2.5 Flash Image (Nano Banana) are wired, image storage paths, and persistence across exports and reloads, including billing caveats.
  • Added a "Background shell commands" subsection explaining the run_shell_command background flag, Termux timeout constraints, and log file locations.
  • Tweaked auto-compression docs to mention disabling it entirely, and briefly referenced Autosave behaviour where relevant, while keeping the rest of the architecture description intact.
README.md
fr/README.md
Updated Gemini compatibility notes and removed the now-stale roadmap section.
  • Extended the tested-models list to include gemini-2.5-flash-image-preview and clarified that Gemma models appear in the picker but do not support function calling, limiting them to pure chat.
  • Removed the Roadmap section and associated links since docs/ROADMAP.md was deleted on main.
  • Kept contributing, license, and credits sections but streamlined some phrasing and inlined git commands for brevity.
README.md
fr/README.md

Tips and commands

Interacting with Sourcery

  • Trigger a new review: Comment @sourcery-ai review on the pull request.
  • Continue discussions: Reply directly to Sourcery's review comments.
  • Generate a GitHub issue from a review comment: Ask Sourcery to create an
    issue from a review comment by replying to it. You can also reply to a
    review comment with @sourcery-ai issue to create an issue from it.
  • Generate a pull request title: Write @sourcery-ai anywhere in the pull
    request title to generate a title at any time. You can also comment
    @sourcery-ai title on the pull request to (re-)generate the title at any time.
  • Generate a pull request summary: Write @sourcery-ai summary anywhere in
    the pull request body to generate a PR summary at any time exactly where you
    want it. You can also comment @sourcery-ai summary on the pull request to
    (re-)generate the summary at any time.
  • Generate reviewer's guide: Comment @sourcery-ai guide on the pull
    request to (re-)generate the reviewer's guide at any time.
  • Resolve all Sourcery comments: Comment @sourcery-ai resolve on the
    pull request to resolve all Sourcery comments. Useful if you've already
    addressed all the comments and don't want to see them anymore.
  • Dismiss all Sourcery reviews: Comment @sourcery-ai dismiss on the pull
    request to dismiss all existing Sourcery reviews. Especially useful if you
    want to start fresh with a new review - don't forget to comment
    @sourcery-ai review to trigger a new review!

Customizing Your Experience

Access your dashboard to:

  • Enable or disable review features such as the Sourcery-generated pull request
    summary, the reviewer's guide, and others.
  • Change the review language.
  • Add, remove or edit custom review instructions.
  • Adjust other review settings.

Getting Help

@coderabbitai

coderabbitai Bot commented Apr 22, 2026 •

Copy link
Copy Markdown

Caution

Review failed

The pull request is closed.

ℹ️ Recent review info
⚙️ Run configuration

Configuration used: defaults

Review profile: CHILL

Plan: Pro

Run ID: faec6d93-9edf-4610-81d4-83b0a5412002

📥 Commits

Reviewing files that changed from the base of the PR and between 2cdc67f and 9aeddd3.

📒 Files selected for processing (2)
  • README.md
  • fr/README.md

📝 Walkthrough

Walkthrough

The README and French README are rewritten to reframe the application as a Gemini coding workstation rather than a native chat client, restructuring sections, consolidating installation instructions, and expanding descriptions of capabilities including project editing, image generation, background shell commands, and updated model compatibility.

Changes

Cohort / File(s) Summary
Documentation Restructuring
README.md, fr/README.md
Content reframed from chat client to coding workstation; Table of Contents removed; "Usage" section replaced with "First-run setup"; installation steps consolidated; new sections added for image generation, background shell commands, and advanced configuration; model compatibility updated to include gemini-2.5-flash-image-preview and notes on Gemma model limitations; contribution instructions condensed.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~15 minutes

Poem

🐰 A coding warren now awaits, the docs say,
With images conjured and shells running free,
Background tasks logged in hoppy array,
Gemini's workstation, as clear as can be! ✨

✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Commit unit tests in branch claude/readme-rework

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

Comment @coderabbitai help to get the list of available commands and usage tips.

@aciderix
aciderix merged commit 188ba36 into main Apr 22, 2026
3 of 4 checks passed

@sourcery-ai sourcery-ai Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Hey - I've found 1 issue

Prompt for AI Agents
Please address the comments from this code review:

## Individual Comments

### Comment 1
<location path="README.md" line_range="45-47" />
<code_context>
+- **Survive long sessions.** The app reports live token usage and
+  auto-compresses the conversation into a fresh summary once the context
+  window fills up, so you keep talking without 400 errors.
+- **Autosave every turn.** Close the app, come back three days later,
+  the conversation is exactly where you left it. Name and save snapshots
+  from the drawer for archive.
+- **Export anywhere.** Drawer → Export as Markdown opens the Android
</code_context>
<issue_to_address>
**suggestion (typo):** Formulation "for archive" un peu étrange en anglais.

La phrase « Name and save snapshots from the drawer for archive. » sonne un peu maladroit. Je suggère plutôt « for archiving » ou « for your archives » qui sont plus naturels en anglais.

```suggestion
- **Autosave every turn.** Close the app, come back three days later,
  the conversation is exactly where you left it. Name and save snapshots
  from the drawer for your archives.
```
</issue_to_address>

Sourcery is free for open source - if you like our reviews please consider sharing them ✨
Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.

Comment thread README.md
Comment on lines +45 to +47
- **Autosave every turn.** Close the app, come back three days later,
the conversation is exactly where you left it. Name and save snapshots
from the drawer for archive.

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

suggestion (typo): Formulation "for archive" un peu étrange en anglais.

La phrase « Name and save snapshots from the drawer for archive. » sonne un peu maladroit. Je suggère plutôt « for archiving » ou « for your archives » qui sont plus naturels en anglais.

Suggested change
- **Autosave every turn.** Close the app, come back three days later,
the conversation is exactly where you left it. Name and save snapshots
from the drawer for archive.
- **Autosave every turn.** Close the app, come back three days later,
the conversation is exactly where you left it. Name and save snapshots
from the drawer for your archives.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants