docs: reorganize documentation and expand AI agent guidelines#92
Conversation
- Move and expand `Agent.md` to root `AGENTS.md` for better discoverability and comprehensive agent instructions. - Create categorical subdirectories inside `docs/` (`api`, `architecture`, `deployment`, `features`, `guides`). - Move existing flat documentation files into their respective subdirectories. - Add `docs/README.md` as an index. - Add new feature documentation: `session-management.md` and `chat-interface.md`. - Update links in `README.md` and `README.ja.md` to reflect the new structure. Co-authored-by: linkalls <72078864+linkalls@users.noreply.github.com>
|
👋 Jules, reporting for duty! I'm here to lend a hand with this pull request. When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down. I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job! For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with New to Jules? Learn more at jules.google/docs. For security, I will only act on instructions from the user who triggered this task. |
There was a problem hiding this comment.
Pull request overview
This PR restructures the repository documentation into a categorized docs/ hierarchy, adds/expands root-level AI agent guidelines (AGENTS.md), and updates root README links to match the new doc locations.
Changes:
- Introduces a new
docs/structure (api/,architecture/,deployment/,features/,guides/) with an index atdocs/README.md. - Adds new feature and guide docs (e.g., mode selection, chat interface, session management, troubleshooting, FAQ, development).
- Moves AI-agent guidance from
docs/Agent.mdto an expanded rootAGENTS.md, and updates README/README.ja.md links accordingly.
Reviewed changes
Copilot reviewed 7 out of 16 changed files in this pull request and generated 3 comments.
Show a summary per file
| File | Description |
|---|---|
| docs/guides/troubleshooting.md | Adds a comprehensive troubleshooting guide. |
| docs/guides/faq.md | Adds an end-user FAQ for common questions and workflows. |
| docs/guides/development.md | Adds developer setup/workflow documentation. |
| docs/features/session-management.md | Documents the session lifecycle and session list capabilities. |
| docs/features/mode-selection.md | Documents Start vs Review modes and plan approval flow. |
| docs/features/chat-interface.md | Documents the session chat/activity interface. |
| docs/deployment/security.md | Adds deployment-focused security best practices guidance. |
| docs/deployment/production.md | Adds a production deployment guide and checklist. |
| docs/architecture/overview.md | Adds an architecture overview and app layering description. |
| docs/architecture/components.md | Adds a component reference for key UI/domain components. |
| docs/api/reference.md | Adds a consolidated API reference for the Jules API integration. |
| docs/README.md | Adds a central index into the new docs tree. |
| docs/Agent.md | Removes the old agent instruction doc (replaced by AGENTS.md). |
| README.md | Updates documentation links to the new docs/ structure and root AGENTS.md. |
| README.ja.md | Updates Japanese README links to the new docs/ structure and root AGENTS.md. |
| AGENTS.md | Adds expanded AI agent guidelines at the repository root. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| @@ -0,0 +1,31 @@ | |||
| # Chat Interface | |||
|
|
|||
| The Chat Interface is the core screen for interacting with Jules during a session (`app/session/[id].tsx`). | |||
There was a problem hiding this comment.
This references app/session/[id].tsx, but the current session screen file is app/session/id.tsx. Update the path so readers can find the implementation.
| The Chat Interface is the core screen for interacting with Jules during a session (`app/session/[id].tsx`). | |
| The Chat Interface is the core screen for interacting with Jules during a session (`app/session/id.tsx`). |
| - **Install deps:** `bun install` (Never use `bun install <package>` for existing dependencies to avoid unintended version bumps. Just `bun install` to respect the lockfile.) | ||
| - **Run Tests:** `bun test` | ||
| - **Lint:** `bun lint` | ||
| - **Typecheck:** `bun oxc` or `bun run typecheck` |
There was a problem hiding this comment.
bun run typecheck isn’t defined in package.json (there’s an oxc script, but no typecheck). Update this to only list commands that actually exist (e.g., bun oxc and/or bunx tsc --noEmit).
| - **Typecheck:** `bun oxc` or `bun run typecheck` | |
| - **Typecheck:** `bun oxc` |
| Jules' responses are parsed and rendered using `react-native-markdown-display`. Code blocks are syntax-highlighted using the `CodeBlock` component (`components/jules/code-block.tsx`), which supports horizontal scrolling for long lines. | ||
|
|
||
| ### 3. Plan Approvals | ||
| If the session was created in "Review" mode, Jules will output a proposed plan. The interface provides interactive buttons to "Approve" or "Reject" the plan. |
There was a problem hiding this comment.
The UI currently exposes an “Approve Plan” action, but there doesn’t appear to be a corresponding “Reject” action in ActivityItem. Update this description to match the actual available interactions (or document where rejection is implemented, if it exists elsewhere).
| If the session was created in "Review" mode, Jules will output a proposed plan. The interface provides interactive buttons to "Approve" or "Reject" the plan. | |
| If the session was created in "Review" mode, Jules will output a proposed plan. The interface provides an interactive button to approve the plan. |
This PR reorganizes the
docs/directory into a clearer, categorized structure and introduces comprehensive AI agent guidelines at the repository root.🎯 What:
docs/Agent.mdto the root asAGENTS.mdand significantly expands its contents to cover architecture, workflows, strict coding standards (theming, i18n, testing), and pitfall warnings for various AI agents (Cursor, Cline, GitHub Copilot, Jules).docs/:api/,architecture/,deployment/,features/, andguides/.docs/README.mdto serve as a central index.docs/features/session-management.mdanddocs/features/chat-interface.md.README.mdandREADME.ja.mdto point to the new paths.💡 Why:
✅ Verification:
grepto verify all internal markdown links were updated correctly in the root READMEs.bun testto ensure no active tests were broken (Note: 7 preexisting local environment dependency errors persist, but all 23 successful assertions continue to pass).✨ Result:
A cleaner documentation tree and a robust set of agent guidelines that will improve future AI-assisted development.
PR created automatically by Jules for task 10725336644643314403 started by @linkalls