Several Windows fixes and other QoL improvements

.github/workflows/deploy-docs.yml

@@ -29,11 +29,12 @@ jobs:
           path: docs/.vitepress/dist
 
   deploy:
+    if: github.repository == 'jamubc/gemini-mcp-tool'
     environment:
       name: github-pages
       url: ${{ steps.deployment.outputs.page_url }}
     needs: build
     runs-on: ubuntu-latest
     steps:
       - id: deployment
-        uses: actions/deploy-pages@v4
+        uses: actions/deploy-pages@v4

AGENTS.md

@@ -0,0 +1,28 @@
+# AGENT Guidance
+
+## Development
+- Use TypeScript with an object-oriented approach when adding new features.
+- Follow test-driven development. Add or update tests under `tests` and run `npm test`.
+- Lint code with `npm run lint` before committing.
+- Build with `npm run build` to ensure TypeScript compiles. The compiled output
+  is written to `dist/`, which is gitignored and should not be committed.
+- A `prepare` script builds `dist/` when installing from git, so `npx -y <repo>`
+  works without committing compiled files.
+- Run `ruff` on any Python files with `select = ["ALL"]`. Only ignore rules with a strong justification.
+- Keep `@modelcontextprotocol/sdk` and `zod` listed as both peer and dev dependencies. Their versions should match across sections of `package.json`.
+- Ensure `@types/node` is installed and referenced via `tsconfig.json` under `compilerOptions.types`.
+
+## Windows Compatibility
+- The command executor uses `shell: process.platform === "win32"` to avoid ENOENT errors.
+- Documented in `docs/resources/troubleshooting.md`.
+- Prompts passed to the Gemini CLI on Windows are automatically quoted and escaped.
+- Unit tests verify quoting for multi-line prompts with special characters, including embedded double quotes, on Windows.
+
+## Repository Scripts
+- `npm test` – runs the Vitest suite.
+- `npm run lint` – checks TypeScript types via `tsc --noEmit`.
+- `npm run build` – compiles TypeScript to `dist/`.
+
+## Package.json Integrity
+- Ensure `package.json` is valid JSON. Running `npm install` or `npm run lint` will fail fast if syntax errors are present.
+

CHANGELOG.md

@@ -2,6 +2,9 @@
 
 ## [Unreleased]
 
+## [1.1.5]
+- Bump version to 1.1.5
+
 ## [1.1.3]
 - "gemini reads, claude edits"
 - Added `changeMode` parameter to ask-gemini tool for structured edit responses using claude edit diff.

README.md

@@ -40,6 +40,12 @@ Before using this tool, ensure you have:
 claude mcp add gemini-cli -- npx -y gemini-mcp-tool
 ```
 
+To run the latest development version from GitHub without installing from npm:
+
+```bash
+npx -y https://github.com/jamubc/gemini-mcp-tool
+```
+
 ### Verify Installation
 
 Type `/mcp` inside Claude Code to verify the gemini-cli MCP is active.
@@ -133,6 +139,16 @@ The sandbox mode allows you to safely test code changes, run scripts, or execute
 - `use gemini sandbox to install numpy and create a data visualization`
 - `test this code safely: Create a script that makes HTTP requests to an API`
 
+### Brainstorming Sessions
+
+- `brainstorm ways to improve developer onboarding using design-thinking`
+- `generate 5 marketing campaign ideas with constraints: budget under $500`
+
+### Handling Large Edit Suggestions
+
+- `ask gemini to refactor @src/**/*.ts changeMode:true`
+- `/gemini-cli:fetch-chunk cacheKey=<key> chunkIndex=2`
+
 ### Tools (for the AI)
 
 These tools are designed to be used by the AI assistant.
@@ -141,6 +157,18 @@ These tools are designed to be used by the AI assistant.
   - **`prompt`** (required): The analysis request. Use the `@` syntax to include file or directory references (e.g., `@src/main.js explain this code`) or ask general questions (e.g., `Please use a web search to find the latest news stories`).
   - **`model`** (optional): The Gemini model to use. Defaults to `gemini-2.5-pro`.
   - **`sandbox`** (optional): Set to `true` to run in sandbox mode for safe code execution.
+  - **`changeMode`** (optional): When `true`, returns structured edit suggestions that can be applied directly. Large change-mode responses can be retrieved in chunks using `fetch-chunk`.
+- **`brainstorm`**: Generates structured brainstorming ideas using frameworks like SCAMPER or design thinking.
+  - **`prompt`** (required): The challenge or question to explore.
+  - **`methodology`** (optional): The creative framework to use (e.g., `scamper`, `design-thinking`).
+  - **`domain`** (optional): The subject area for context (e.g., `software`, `marketing`).
+  - **`constraints`** (optional): Any limitations to consider (e.g., `budget under $500`).
+  - **`existingContext`** (optional): Background information to build upon.
+  - **`ideaCount`** (optional): The number of ideas to generate.
+  - **`includeAnalysis`** (optional): Whether to include analysis for each idea.
+- **`fetch-chunk`**: Retrieves cached chunks from a previous `ask-gemini` changeMode response.
+  - **`cacheKey`** (required): Provided in the initial changeMode response.
+  - **`chunkIndex`** (required): Which chunk to fetch (1-based index).
 - **`sandbox-test`**: Safely executes code or commands in Gemini's sandbox environment. Always runs in sandbox mode.
   - **`prompt`** (required): Code testing request (e.g., `Create and run a Python script that...` or `@script.py Run this safely`).
   - **`model`** (optional): The Gemini model to use.
@@ -151,12 +179,17 @@ These tools are designed to be used by the AI assistant.
 
 You can use these commands directly in Claude Code's interface (compatibility with other clients has not been tested).
 
-- **/analyze**: Analyzes files or directories using Gemini, or asks general questions.
-  - **`prompt`** (required): The analysis prompt. Use `@` syntax to include files (e.g., `/analyze prompt:@src/ summarize this directory`) or ask general questions (e.g., `/analyze prompt:Please use a web search to find the latest news stories`).
-- **/sandbox**: Safely tests code or scripts in Gemini's sandbox environment.
-  - **`prompt`** (required): Code testing request (e.g., `/sandbox prompt:Create and run a Python script that processes CSV data` or `/sandbox prompt:@script.py Test this script safely`).
-- **/help**: Displays the Gemini CLI help information.
-- **/ping**: Tests the connection to the server.
+- **/gemini-cli:analyze**: Analyzes files or directories using Gemini, or asks general questions.
+  - **`prompt`** (required): The analysis request. Use `@` syntax to include files (e.g., `/gemini-cli:analyze @src/ summarize this directory`) or ask general questions (e.g., `/gemini-cli:analyze Please use a web search to find the latest news stories`). Prefixing the request with `prompt:` is optional.
+  - **`changeMode`** (optional): Returns structured edit suggestions. Large change-mode responses will include a `cacheKey` for use with `/gemini-cli:fetch-chunk`.
+- **/gemini-cli:sandbox**: Safely tests code or scripts in Gemini's sandbox environment.
+  - **`prompt`** (required): Code testing request (e.g., `/gemini-cli:sandbox Create and run a Python script that processes CSV data` or `/gemini-cli:sandbox @script.py Test this script safely`). Prefix with `prompt:` if your client requires it.
+- **/gemini-cli:brainstorm**: Generates structured ideas using creative methodologies.
+  - **`prompt`** (required): The challenge to explore.
+  - Optional arguments: `methodology`, `domain`, `constraints`, `existingContext`, `ideaCount`, `includeAnalysis`.
+- **/gemini-cli:fetch-chunk**: Retrieves additional change-mode edits using a provided `cacheKey` and `chunkIndex`.
+- **/gemini-cli:help**: Displays the Gemini CLI help information.
+- **/gemini-cli:ping**: Tests the connection to the server.
   - **`message`** (optional): A message to echo back.
 
 ## Contributing

docs/.vitepress/theme/Layout.vue

@@ -6,7 +6,7 @@
     </template>
     <template #nav-bar-content-before>
       <div class="nav-warning">
-        🏷️ <span>1.1.4</span>
+        🏷️ <span>1.1.5</span>
       </div>
     </template>
     <template #sidebar-nav-after>

docs/funding.md

@@ -20,7 +20,7 @@ layout: funding
 
   <ul>
     <li><strong>Docs & Listing:</strong> Updating and maintaining the documentation website & outreach</li>
-    <li><strong>API Testing Credits:</strong> Funds are used for testing various deployements of gemini-mcp-tool on popular clients.</li>
+    <li><strong>API Testing Credits:</strong> Funds are used for testing various deployments of `Gemini MCP Tool` on popular clients.</li>
   </ul>
 
   <div class="progress-bar">

docs/index.md

@@ -24,7 +24,7 @@ features:
     details: We dont re-invent the wheel.
   - icon: 🤝
     title: Claude's new best friend
-    details: Let Claude use Gemini naturally, because 3 is a party. 
+    details: Let Claude use Gemini naturally, because 3 is a party.
   - icon: 🔌
     title: MCP Standards
     details: |
@@ -35,6 +35,12 @@ features:
   - icon: 🚦
     title: Model Selection
     details: Choose from Gemini-2.5-Pro and Gemini-2.5-Flash, using natural language.
+  - icon: 🧠
+    title: Structured Brainstorming
+    details: Generate creative ideas with SCAMPER, design thinking, or lateral thinking frameworks.
+  - icon: 📦
+    title: Large Edit Handling
+    details: Change-mode responses can be chunked and retrieved on demand.
 ---
 
 <div class="explore-hint" style="text-align: center; margin: 32px 0 48px; position: relative;">

docs/resources/troubleshooting.md

@@ -342,6 +342,8 @@ gemini "Hello"
 - **NPX flag issues**: Use `--yes` instead of `-y`
 - **Path problems**: Restart terminal after Node.js installation
 - **Connection issues**: Ensure Windows Defender isn't blocking Node.js
+- **Spawn ENOENT errors**: Upgrade to gemini-mcp-tool >=1.1.5 or ensure the
+  command executor sets `shell: process.platform === "win32"`
 
 ### macOS
 - **Permission issues**: Use `sudo` if npm install fails

docs/usage/commands.md

@@ -1,3 +1,4 @@
+
 # Commands Reference
 
 Complete list of available commands and their usage.
@@ -21,6 +22,20 @@ Execute code in a safe environment.
 /gemini-cli:sandbox test this function: [code]
 ```
 
+### `/gemini-cli:brainstorm`
+Generate structured ideas using creative methodologies.
+
+```
+/gemini-cli:brainstorm prompt:"Improve onboarding flow" methodology:scamper ideaCount:8
+```
+
+### `/gemini-cli:fetch-chunk`
+Retrieve additional change-mode edits using a cache key and chunk index.
+
+```
+/gemini-cli:fetch-chunk cacheKey=<key> chunkIndex=2
+```
+
 ### `/gemini-cli:help`
 Show help information and available tools.
 
@@ -43,7 +58,7 @@ Test connectivity with Gemini.
 /gemini-cli:<tool> [options] <arguments>
 ```
 
-- **tool**: The action to perform (analyze, sandbox, help, ping)
+- **tool**: The action to perform (analyze, sandbox, brainstorm, fetch-chunk, help, ping)
 - **options**: Optional flags (coming soon)
 - **arguments**: Input text, files, or questions
 
@@ -99,9 +114,21 @@ Instead of slash commands, you can use natural language:
 /gemini-cli:analyze @models/user.js generate TypeScript types for this model
 ```
 
+### Structured Edits and Chunks
+```
+/gemini-cli:analyze @src/**/*.ts changeMode:true
+# Fetch subsequent edits
+/gemini-cli:fetch-chunk cacheKey=<key> chunkIndex=2
+```
+
+### Brainstorming Ideas
+```
+/gemini-cli:brainstorm prompt:"New product features" methodology:design-thinking includeAnalysis:false
+```
+
 ## Tips
 
 1. **Start Simple**: Begin with single files before using patterns
 2. **Be Specific**: Clear questions get better answers
 3. **Use Context**: Include relevant files for better analysis
-4. **Iterate**: Refine your queries based on responses
+4. **Iterate**: Refine your queries based on responses

docs/usage/examples.md

@@ -1,3 +1,4 @@
+
 # Real-World Examples
 
 Practical examples of using Gemini MCP Tool in development workflows.
@@ -92,6 +93,13 @@ give me an overview of this project's architecture
 @src/auth/*.js does this follow security best practices?
 ```
 
+## Brainstorming
+
+### Generating Ideas
+```
+/gemini-cli:brainstorm prompt:"Ways to improve developer onboarding" methodology:design-thinking ideaCount:6
+```
+
 ## Migration
 
 ### Framework Upgrade
@@ -131,6 +139,18 @@ identify performance bottlenecks in the request pipeline
 @src/**/*.js look for potential memory leaks or inefficient patterns
 ```
 
+## Handling Large Edits
+
+When change mode returns more edits than fit in a single message, Gemini caches the response. Use `fetch-chunk` to continue.
+
+```bash
+# Initial request
+/gemini-cli:analyze @src/**/*.ts changeMode:true
+
+# Retrieve the next chunk
+/gemini-cli:fetch-chunk cacheKey=<key> chunkIndex=2
+```
+
 ## Real Project Example
 
 ### Full Stack Review
@@ -162,4 +182,4 @@ what critical paths lack test coverage?
 2. **Combine Related Files**: Include configs with source code
 3. **Ask Follow-up Questions**: Build on previous responses
 4. **Use Specific Criteria**: Tell Gemini what to look for
-5. **Iterate on Solutions**: Refine based on suggestions
+5. **Iterate on Solutions**: Refine based on suggestions