### Minimal @Docs Setup in JetBrains IDEs
Source: https://docs.continue.dev/reference/deprecated-docs
This minimal example for Jetbrains requires setting up an embeddings provider, such as the LMStudio embedder.
```yaml
name: My Config
version: 0.0.1
schema: v1
models:
- name: LMStudio embedder
provider: lmstudio
model: nomic-ai/nomic-embed-text-v1.5-GGUF
roles:
- embed
context:
- provider: docs
docs:
- title: Nest.js
startUrl: https://docs.nestjs.com/
```
--------------------------------
### Install ClawRouter Globally
Source: https://docs.continue.dev/customize/model-providers/more/clawrouter
Install ClawRouter globally for command-line access. After installation, run the command to start the router.
```bash
npm install -g clawrouter
clawrouter
```
--------------------------------
### Start Local Development Server
Source: https://docs.continue.dev/CONTRIBUTING
Start the local development server for the documentation. Access the docs at http://localhost:3000.
```bash
npm run dev
```
--------------------------------
### Documentation Resources Rule Example
Source: https://docs.continue.dev/guides/codebase-documentation-awareness
Guide agent mode to relevant public documentation using rules with direct links. This helps the agent answer framework-specific questions accurately.
```markdown
# Documentation Resources
For framework-specific questions, refer to:
- React: https://react.dev/reference/react
- Next.js: https://nextjs.org/docs
- Tailwind CSS: https://tailwindcss.com/docs
Always cite documentation when explaining concepts.
```
--------------------------------
### Install ClawRouter Locally
Source: https://docs.continue.dev/customize/model-providers/more/clawrouter
Run ClawRouter locally to start the OpenAI-compatible API. This command installs and starts the router.
```bash
npx clawrouter
```
--------------------------------
### Start First Continue CLI Session
Source: https://docs.continue.dev/cli/quickstart
Navigates to your project directory and starts an interactive TUI session with the Continue CLI.
```bash
cd your-project
cn
```
--------------------------------
### Complete config.yaml Example
Source: https://docs.continue.dev/reference
This example shows a comprehensive config.yaml file that includes configurations for multiple models (Anthropic, OpenAI, Ollama), custom rules, prompts, context providers, development servers, and data ingestion.
```yaml
name: My Config
version: 1.0.0
schema: v1
models:
- uses: anthropic/claude-sonnet-4-6
with:
ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
override:
defaultCompletionOptions:
temperature: 0.8
- name: GPT-4
provider: openai
model: gpt-4
roles:
- chat
- edit
defaultCompletionOptions:
temperature: 0.5
maxTokens: 2000
requestOptions:
headers:
Authorization: Bearer YOUR_OPENAI_API_KEY
- name: Ollama Starcoder
provider: ollama
model: starcoder
roles:
- autocomplete
autocompleteOptions:
debounceDelay: 350
maxPromptTokens: 1024
onlyMyCode: true
defaultCompletionOptions:
temperature: 0.3
stop:
- "\n"
rules:
- Give concise responses
- Always assume TypeScript rather than JavaScript
prompts:
- name: test
description: Unit test a function
prompt: |
Please write a complete suite of unit tests for this function. You should use the Jest testing framework.
The tests should cover all possible edge cases and should be as thorough as possible.
You should also include a description of each test case.
- uses: myprofile/my-favorite-prompt
context:
- provider: diff
- provider: file
- provider: code
mcpServers:
- name: DevServer
command: npm
args:
- run
- dev
env:
PORT: "3000"
data:
- name: My Private Company
destination: https://mycompany.com/ingest
schema: 0.2.0
level: noCode
events:
- autocomplete
- chatInteraction
```
--------------------------------
### Verify Continue CLI Installation
Source: https://docs.continue.dev/cli/quickstart
Checks if the Continue CLI has been installed correctly by displaying its version.
```bash
cn --version
```
--------------------------------
### Install Dependencies
Source: https://docs.continue.dev/CONTRIBUTING
Install project dependencies using npm. Ensure Node.js v20 or higher is installed.
```bash
npm install
```
--------------------------------
### Create a Pirate Rule File
Source: https://docs.continue.dev/customize/deep-dives/rules
Example of a simple rule file with a name and instruction. Place this in your `.continue/rules` folder.
```markdown
---
name: Pirate rule
---
- Talk like a pirate.
```
--------------------------------
### Complete Check File Example
Source: https://docs.continue.dev/checks/reference
This example demonstrates a fully-specced check file, including the optional 'model' field for specifying the AI model.
```markdown
---
name: Migration Safety
description: Flag destructive database migrations
model: anthropic/claude-sonnet-4-5-20250514
---
Review database migration files in this pull request.
Flag as failing if any migration contains:
- DROP TABLE or DROP COLUMN without a corresponding backfill migration
- Data type changes that narrow the column (e.g., VARCHAR(255) → VARCHAR(100))
- Removing NOT NULL constraints without a default value
Pass if the migration is additive only (new tables, new columns, new indexes).
```
--------------------------------
### Add Frontmatter to New Guide
Source: https://docs.continue.dev/CONTRIBUTING
When creating a new guide, include frontmatter with a title and description at the beginning of the .mdx file.
```yaml
---
title: "Your Guide Title"
description: "Brief description of what this guide covers"
---
```
--------------------------------
### Install Continue CLI
Source: https://docs.continue.dev/cli/quickstart
Installs the Continue CLI using a curl command. This script is suitable for macOS and Linux.
```bash
curl -fsSL https://raw.githubusercontent.com/continuedev/continue/main/extensions/cli/scripts/install.sh | bash
```
--------------------------------
### Reference Hub Rules in config.yaml
Source: https://docs.continue.dev/customize/deep-dives/rules
Example of how to reference a Hub rule in your `config.yaml` file. This makes the Hub rule available in your local setup.
```yaml
rules:
- uses: username/my-hub-rule
```
--------------------------------
### External Dependencies Rule Example
Source: https://docs.continue.dev/guides/codebase-documentation-awareness
Create rules with hyperlinks to external codebases to guide the agent's understanding of dependencies. This is useful for open-source projects.
```markdown
# External Dependencies
Our authentication system is based on:
- [Auth.js documentation](https://authjs.dev/)
- [Example implementation](https://github.com/nextauthjs/next-auth-example)
When implementing auth features, reference these patterns.
```
--------------------------------
### Start Continue CLI
Source: https://docs.continue.dev/guides/cli
Launches the Continue CLI. Use interactive mode for conversational use or headless mode for automation.
```bash
# Interactive mode
cn
```
```bash
# Headless mode
cn -p "Generate a conventional commit name for the current git changes"
```
--------------------------------
### Configure Multiple Slash Commands
Source: https://docs.continue.dev/reference/json-reference
Example configuration showing multiple built-in slash commands enabled simultaneously.
```json
{
"slashCommands": [
{ "name": "commit", "description": "Generate a commit message" },
{ "name": "share", "description": "Export this session as markdown" },
{ "name": "cmd", "description": "Generate a shell command" }
]
}
```
--------------------------------
### Install the 'check' Skill
Source: https://docs.continue.dev/checks/running-locally
Install the check skill using npx. Ensure you have the 'check' skill available for local execution.
```bash
npx skills add continuedev/skills --skill check
```
--------------------------------
### GitHub CLI Usage Rule Example
Source: https://docs.continue.dev/guides/codebase-documentation-awareness
Add rules to guide the agent's usage of the `gh` CLI for interacting with GitHub repositories. This enables actions like searching issues or cloning repos.
```markdown
# Repository Access
You can use the `gh` CLI to:
- Search for issues: `gh issue list --repo owner/repo`
- View pull requests: `gh pr list --repo owner/repo`
- Clone repositories: `gh repo clone owner/repo`
```
--------------------------------
### Headless Mode Examples
Source: https://docs.continue.dev/cli/headless-mode
Demonstrates various use cases for headless mode, including git hooks, CI pipelines with file writes, generating documentation, and using specific assistants.
```bash
# Git hooks
cn -p "Review staged changes for obvious bugs" --silent
```
```bash
# CI pipeline — allow file writes for auto-fix
cn -p "Fix all ESLint errors in src/" --allow Write --allow Edit --allow Bash
```
```bash
# Generate docs from code
cn -p "@src/api/ Generate OpenAPI documentation for these endpoints" --silent > api-docs.yaml
```
```bash
# Use a specific assistant
cn -p "Triage this error log" --config my-org/error-triage-assistant
```
--------------------------------
### Mintlify Card Component Example
Source: https://docs.continue.dev/CONTRIBUTING
Example of a Mintlify Card component. Follow indentation and blank line rules for proper formatting.
```html
Always include blank lines and proper indentation:
- Use 2-space indentation
- Add blank lines after opening tags
- Format lists as bullet points
```
--------------------------------
### Project Architecture Rule Example
Source: https://docs.continue.dev/guides/codebase-documentation-awareness
Use markdown files in `.continue/rules` to provide context about your project's structure and coding standards. This helps the agent understand the codebase.
```markdown
# Project Architecture
This is a React application with:
- Components in `/src/components`
- API routes in `/src/api`
- State management using Redux in `/src/store`
## Coding Standards
- Use TypeScript for all new files
- Follow the existing naming conventions
- Write tests for all new features
```
--------------------------------
### Configure Documentation Sites
Source: https://docs.continue.dev/reference/json-reference
Define documentation sites to be indexed by Continue. Specify title, start URL, and crawling depth.
```json
"docs": [
{
"title": "Continue",
"startUrl": "https://docs.continue.dev/intro",
"faviconUrl": "https://docs.continue.dev/favicon.ico"
}
]
```
--------------------------------
### Configure Documentation Indexing
Source: https://docs.continue.dev/reference
List documentation sites to be indexed by Continue. Specify the name, start URL, and optionally a favicon URL.
```yaml
name: My Config
version: 1.0.0
schema: v1
docs:
- name: Continue
startUrl: https://docs.continue.dev/intro
favicon: https://docs.continue.dev/favicon.ico
```
--------------------------------
### Use Continue CLI Documentation Agent
Source: https://docs.continue.dev/CONTRIBUTING
Install the Continue CLI and use the pre-built documentation agent to generate content. The `--config` flag specifies the agent to use.
```bash
# Install the Continue CLI if you haven't already
npm install -g @continuedev/cli
# Use the agent from the command line
cn "Create a new guide for using the Continue CLI with Linear" --config continuedev/docs-mintlify
```
--------------------------------
### Mintlify Warning Component Example
Source: https://docs.continue.dev/CONTRIBUTING
Example of a Mintlify Warning component. Use clear, concise language and consistent formatting for important information.
```html
Important information should be formatted clearly:
- Each point on its own line
- Consistent indentation
- Clear, concise language
```
--------------------------------
### YAML Rule Configuration Example
Source: https://docs.continue.dev/customize/deep-dives/rules
Example of a rule defined in YAML format, including name, globs, and description. This format is supported but Markdown is recommended.
```yaml
---
name: Documentation Standards
globs: docs/**/*.{md,mdx}
alwaysApply: false
description: Standards for writing and maintaining Continue Docs
---
# Continue Docs Standards
- Follow Mintlify documentation standards
- Include YAML frontmatter with title, description, and keywords
- Use consistent heading hierarchy starting with h2 (##)
- Include relevant Admonition components for tips, warnings, and info
- Use descriptive alt text for images
- Include cross-references to related documentation
- Reference other docs with relative paths
- Keep paragraphs concise and scannable
- Use code blocks with appropriate language tags
```
--------------------------------
### Define a Custom Prompt File
Source: https://docs.continue.dev/reference
Example of a prompt file that defines a custom action, such as rewriting comments in a specific style.
```yaml
---
name: Make pirate comments
invokable: true
---
Rewrite all comments in the active file to talk like a pirate
```
--------------------------------
### Verify Remote Ollama Model Installation
Source: https://docs.continue.dev/faqs
Use 'ollama list' with the OLLAMA_HOST environment variable set to verify that the desired model is installed on the remote Ollama instance.
```bash
OLLAMA_HOST=192.168.1.136:11434 ollama list
```
--------------------------------
### Install Ollama on macOS and Linux
Source: https://docs.continue.dev/guides/ollama-guide
Use Homebrew to install Ollama on macOS or a curl script for Linux. For Windows, download from ollama.ai.
```bash
# macOS
brew install ollama
```
```bash
# Linux
curl -fsSL https://ollama.ai/install.sh | sh
```
--------------------------------
### Download Instinct Model with Ollama
Source: https://docs.continue.dev/guides/instinct
Use this command to download the Instinct model from Ollama. Ensure Ollama is installed and running.
```bash
ollama run nate/instinct
```
--------------------------------
### Use Custom Continue Agent
Source: https://docs.continue.dev/CONTRIBUTING
Install the Continue CLI and use your custom agent for documentation tasks. Replace 'your-org/your-agent-name' with your agent's identifier.
```bash
# Install the Continue CLI if you haven't already
npm install -g @continuedev/cli
# Use your agent from the command line
cn --config your-org/your-agent-name "Create a new guide for API authentication"
```
--------------------------------
### Minimal @Docs Setup in VS Code
Source: https://docs.continue.dev/reference/deprecated-docs
This minimal configuration works out of the box for VS Code, using the built-in embeddings provider with no reranking.
```yaml
name: My Config
version: 0.0.1
schema: v1
context:
- provider: docs
docs:
- title: Nest.js
startUrl: https://docs.nestjs.com/
```
--------------------------------
### Configure Request Headers
Source: https://docs.continue.dev/reference/json-reference
Add custom headers to HTTP requests. This example sets an 'X-Auth-Token' header for authentication.
```json
{ "requestOptions": { "headers": { "X-Auth-Token": "xxx" } } }
```
--------------------------------
### Moonshot AI Configuration with Options
Source: https://docs.continue.dev/customize/model-providers/more/moonshot
This example shows a complete configuration for Moonshot AI, including default completion options like temperature, topP, and maxTokens. Ensure your API key is correctly set.
```yaml
name: My Config
version: 0.0.1
schema: v1
models:
- name: Kimi K2
provider: moonshot
model: kimi-k2
apiKey:
defaultCompletionOptions:
temperature: 0.7
topP: 0.95
maxTokens: 2048
```
--------------------------------
### Start Agent with Task Description
Source: https://docs.continue.dev/mission-control/integrations/slack
Mention @Continue with a task description in any Slack channel or thread to initiate an agent. When mentioned in a thread, the agent uses the full conversation as context; in a new message, it only considers that single message.
```text
@Continue Fix the authentication timeout in /api/v1/auth/login — users are getting logged out after 5 minutes instead of 30.
```
--------------------------------
### Verify Ollama Installation and Service
Source: https://docs.continue.dev/guides/ollama-guide
Check the Ollama version and ensure the service is running by checking its version and making a local API request.
```bash
# Check Ollama version - verify it's installed
ollama --version
```
```bash
# Start Ollama (runs in background)
ollama serve
```
```bash
# Verify it's running
curl http://localhost:11434
# Should return "Ollama is running"
```
--------------------------------
### Configure MCP Servers
Source: https://docs.continue.dev/customize/deep-dives/custom-providers
Configure Model Context Protocol (MCP) servers to integrate with external services. This example shows how to set up a local SQLite MCP server.
```yaml
mcpServers:
- name: My MCP Server
command: uvx
args:
- mcp-server-sqlite
- --db-path
- /Users/NAME/test.db
```
--------------------------------
### Internal Documentation Rule Example
Source: https://docs.continue.dev/guides/codebase-documentation-awareness
Create rules with links to internal documentation resources to ensure the agent adheres to internal standards when suggesting code.
```markdown
# Internal Documentation
Our team documentation is available at:
- API Documentation: https://internal.docs/api
- Architecture Guide: https://internal.docs/architecture
- Deployment Process: https://internal.docs/deployment
Always follow our internal standards when suggesting code.
```
--------------------------------
### config.yaml with YAML Anchors
Source: https://docs.continue.dev/reference
This example demonstrates using YAML anchors (`&` and `*`) to define default model properties and reuse them across multiple model configurations, reducing duplication in the config.yaml file.
```yaml
%YAML 1.1
---
name: My Config
version: 1.0.0
schema: v1
model_defaults: &model_defaults
provider: openai
apiKey: my-api-key
apiBase: https://api.example.com/llm
models:
- name: mistral
<<: *model_defaults
model: mistral-7b-instruct
roles:
- chat
- edit
- name: qwen2.5-coder-7b-instruct
<<: *model_defaults
model: qwen2.5-coder-7b-instruct
roles:
- chat
- edit
- name: qwen2.5-coder-7b
<<: *model_defaults
model: qwen2.5-coder-7b
useLegacyCompletionsEndpoint: false
roles:
- autocomplete
autocompleteOptions:
debounceDelay: 350
maxPromptTokens: 1024
onlyMyCode: true
```
--------------------------------
### Advanced @Docs Setup with Custom Providers
Source: https://docs.continue.dev/reference/deprecated-docs
This configuration includes public and private documentation sources, a custom embeddings provider, a reranker model with customized parameters, and a GitHub token for GitHub crawling.
```yaml
name: My Config
version: 0.0.1
schema: v1
models:
- name: LMStudio Nomic Text
provider: lmstudio
model: nomic-ai/nomic-embed-text-v1.5-GGUF
roles:
- embed
- name: Voyage Rerank-2
provider: voyage
apiKey:
model: rerank-2
roles:
- rerank
context:
- provider: docs
params:
githubToken:
nRetrieve: 25
nFinal: 5
useReranking: true
docs:
- title: Nest.js
startUrl: https://docs.nestjs.com/
- title: My Private Docs
startUrl: http://10.2.1.2/docs
faviconUrl: http://10.2.1.2/docs/assets/favicon.ico
useLocalCrawling: true
```
--------------------------------
### Add TypeScript Code Example
Source: https://docs.continue.dev/CONTRIBUTING
Use language-specific code blocks for examples. This example shows how to add a TypeScript code snippet.
```typescript
// Your TypeScript code here
const example = "Hello, Continue!";
```
--------------------------------
### Start ClawRouter Service
Source: https://docs.continue.dev/customize/model-providers/more/clawrouter
Start the ClawRouter service if it is not running.
```bash
# Start ClawRouter if needed
npx clawrouter
```
--------------------------------
### Create config.yaml File
Source: https://docs.continue.dev/reference/yaml-migration
Initialize a config.yaml file with basic metadata. This file will be loaded if present, overriding config.json.
```yaml
name: my-configuration
version: 0.0.1
schema: v1
```
--------------------------------
### Install Writing Checks Skill
Source: https://docs.continue.dev/checks/generating-checks
Install the 'writing-checks' skill to enable your coding agent to create check files.
```bash
npx skills add continuedev/skills --skill writing-checks
```
--------------------------------
### Configure `@Operating System` Context Provider
Source: https://docs.continue.dev/customize/deep-dives/custom-providers
Use the `os` provider to reference the architecture and platform of your current operating system.
```yaml
context:
- provider: os
```
--------------------------------
### Add Documentation Site via Configuration
Source: https://docs.continue.dev/reference/deprecated-docs
Configure documentation sites by adding entries to the 'docs' array in your global configuration file. This is recommended for bulk adds or edits.
```yaml
name: My Config
version: 0.0.1
schema: v1
docs:
- title: Nest.js
startUrl: https://docs.nestjs.com/
faviconUrl: https://docs.nestjs.com/favicon.ico
```
--------------------------------
### Search Model Configuration Help
Source: https://docs.continue.dev/reference/continue-mcp
Use this query format to ask for help regarding model configuration within Continue.
```plaintext
How do I add Claude 4 Sonnet as a model from Bedrock in Continue?
```
--------------------------------
### Configure `@Problems` Context Provider
Source: https://docs.continue.dev/customize/deep-dives/custom-providers
Use the `problems` provider to get problems from the current file.
```yaml
context:
- provider: problems
```
--------------------------------
### Download Ollama Model for Autocomplete
Source: https://docs.continue.dev/customize/deep-dives/autocomplete
Run this command to download the Qwen2.5-coder 1.5B model for local autocomplete using Ollama.
```bash
ollama run qwen2.5-coder:1.5b
```
--------------------------------
### Configure Ask Sage Model
Source: https://docs.continue.dev/customize/model-providers/more/asksage
Add your Ask Sage model to the Continue configuration file. Ensure you replace `` with your actual API key.
```yaml
name: My Config
version: 0.0.1
schema: v1
models:
- name: GPT-4 gov
provider: askSage
model: gpt4-gov
apiBase: https://api.asksage.ai/server/
apiKey:
```
--------------------------------
### Configure Model Context Protocol (MCP) Servers
Source: https://docs.continue.dev/reference
Set up MCP servers to standardize prompt, context, and tool use. Configure the server name, command, arguments, environment variables, and working directory.
```yaml
name: My Config
version: 1.0.0
schema: v1
mcpServers:
- name: My MCP Server
command: uvx
args:
- mcp-server-sqlite
- --db-path
- ./test.db
cwd: /Users/NAME/project
env:
NODE_ENV: production
```
--------------------------------
### Define a Custom Rule File
Source: https://docs.continue.dev/reference
Example of a rules file that defines custom behavior, such as instructing the model to adopt a specific persona.
```yaml
---
name: Pirate rule
---
Talk like a pirate
```
--------------------------------
### Log in to Continue CLI
Source: https://docs.continue.dev/cli/quickstart
Initiates the browser-based authentication process for the Continue CLI, linking it to your Continue account.
```bash
cn login
```
--------------------------------
### Configure Tab Autocomplete Model in config.json
Source: https://docs.continue.dev/reference/json-reference
Specify the model for tab autocompletion. This example shows how to configure an Ollama instance for the 'starcoder2:3b' model.
```json
{
"tabAutocompleteModel": {
"title": "My Starcoder",
"provider": "ollama",
"model": "starcoder2:3b"
}
}
```
--------------------------------
### Generate Checks with Claude Code
Source: https://docs.continue.dev/checks/quickstart
Use this prompt to have Claude Code assist in writing checks for your codebase. It's recommended for a guided experience.
```markdown
Help me write checks for this codebase: https://continue.dev/walkthrough
```
--------------------------------
### Configure `@File` Context Provider
Source: https://docs.continue.dev/customize/deep-dives/custom-providers
Use the `file` provider to reference any file in your current workspace.
```yaml
context:
- provider: file
```
--------------------------------
### Configure Continue Documentation MCP Server
Source: https://docs.continue.dev/reference/continue-mcp
Add this YAML configuration to `.continue/mcpServers/continue-docs-mcp.yaml` to set up the MCP server. Ensure Continue is in agent mode for it to function.
```yaml
name: Continue Documentation MCP
version: 0.0.1
schema: v1
mcpServers:
- uses: continuedev/continue-docs-mcp
```
--------------------------------
### TypeScript-Specific Rule Configuration
Source: https://docs.continue.dev/customize/deep-dives/rules
Example of a project-specific rule for TypeScript files, specifying globs and outlining best practices. Rules are loaded in lexicographical order.
```yaml
---
name: TypeScript Best Practices
globs: ["**/*.ts", "**/*.tsx"]
---
# TypeScript Rules
- Always use TypeScript interfaces for object shapes
- Use type aliases sparingly, prefer interfaces
- Include proper JSDoc comments for public APIs
- Use strict null checks
- Prefer readonly arrays and properties where possible
- modularize components into smaller, reusable pieces
```
--------------------------------
### Invoke Prompt via CLI (TUI Mode)
Source: https://docs.continue.dev/customize/deep-dives/prompts
Start the Continue TUI (Terminal User Interface) mode with a specific prompt and an initial instruction.
```bash
cn --prompt supabase/create-functions "I need a function that checks for the health status"
```
--------------------------------
### Allow Writing Only to TypeScript Files
Source: https://docs.continue.dev/cli/tool-permissions
Utilize tool matching patterns with CLI flags to specify granular permissions. This example allows writing only to TypeScript files.
```bash
# Allow writing only to TypeScript files
cn --allow "Write(**/*.ts)"
# Allow bash but not for install commands
cn --allow Bash --exclude "Bash(npm install*)"
```
--------------------------------
### GitHub Issue Opened Event Summary
Source: https://docs.continue.dev/mission-control/integrations/github
This is an example of the summary an agent receives when triggered by a GitHub 'Issue Opened' event. It includes the issue number, title, and URL.
```text
Issue #123 was opened: Login page crashes on mobile devices
Issue URL: https://github.com/acme/webapp/issues/123
```
--------------------------------
### Importing Hub Models with Secrets
Source: https://docs.continue.dev/guides/configuring-models-rules-tools
Demonstrates how to import a model from the Continue hub and configure it using secrets for authentication.
```yaml
name: Team Config
version: 1.0.0
schema: v1
models:
- uses: anthropic/claude-4-sonnet
with:
ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }} # Use a hub secret
```
--------------------------------
### Configure Experimental Features in config.json
Source: https://docs.continue.dev/reference/json-reference
Set up experimental configurations, including model roles for specific actions and protocol server settings for model context.
```json
{
"experimental": {
"modelRoles": { "inlineEdit": "Edit Model" },
"modelContextProtocolServers": [
{
"transport": {
"type": "stdio",
"command": "uvx",
"args": ["mcp-server-sqlite", "--db-path", "/Users/NAME/test.db"]
}
}
]
}
}
```
--------------------------------
### Autocomplete: Implement Sorting Algorithm
Source: https://docs.continue.dev/ide-extensions/quick-start
Use Autocomplete to get AI-powered code suggestions. Place your cursor after the comment and press Enter. Press Tab to accept suggestions.
```javascript
// TODO: Implement a sorting algorithm function
function sortingAlgorithm(arr) {
// Place cursor here and press Enter
}
```
--------------------------------
### Create Ollama Modelfile for Optimizations
Source: https://docs.continue.dev/guides/ollama-guide
Create a custom model with optimizations by specifying parameters like `num_gpu`, `num_thread`, and `num_ctx` in an Ollama Modelfile.
```dockerfile
# Create custom model with optimizations
FROM deepseek-r1:32b
PARAMETER num_gpu 35
PARAMETER num_thread 8
PARAMETER num_ctx 4096
```
--------------------------------
### Basic OpenRouter Configuration
Source: https://docs.continue.dev/customize/model-providers/top-level/openrouter
Configure a model from OpenRouter by providing its name, model ID, API base, and your API key. This is the fundamental setup for using OpenRouter models.
```yaml
name: My Config
version: 0.0.1
schema: v1
models:
- name:
provider: openrouter
model:
apiBase: https://openrouter.ai/api/v1
apiKey:
```
--------------------------------
### Configure Prompt in `config.yaml`
Source: https://docs.continue.dev/customize/deep-dives/prompts
Add a prompt to your local `config.yaml` file using the `prompts` section and a `uses` directive to reference the prompt by its name.
```yaml
...
prompts:
- uses: supabase/create-functions
...
```
--------------------------------
### Basic Anthropic Model Configuration
Source: https://docs.continue.dev/customize/model-providers/top-level/anthropic
Configure an Anthropic model by specifying its name, provider, model ID, and API key. This is the fundamental setup required to use Claude models.
```yaml
name: My Config
version: 0.0.1
schema: v1
models:
- name:
provider: anthropic
model:
apiKey:
```
--------------------------------
### Clone Continue Repository
Source: https://docs.continue.dev/CONTRIBUTING
Fork and clone the Continue repository locally. Navigate to the docs directory after cloning.
```bash
gh repo fork continuedev/continue
cd continue/docs
```
--------------------------------
### Configure ClawRouter API Key for Self-Hosted Setups
Source: https://docs.continue.dev/customize/model-providers/more/clawrouter
Provide an API key for self-hosted ClawRouter instances that require custom authentication. The key is managed by ClawRouter, not Continue directly.
```yaml
models:
- name: ClawRouter
provider: clawrouter
model: blockrun/auto
apiBase: http://localhost:1337/v1/
apiKey: ${{ secrets.CLAWROUTER_API_KEY }}
```
--------------------------------
### Configure Ask Sage with DoD Certificates
Source: https://docs.continue.dev/customize/model-providers/more/asksage
For secure environments, specify the path to your DoD CA bundle file using `requestOptions.caBundlePath`. Replace `/path/to/dod/certificates` with the actual file path.
```yaml
name: My Config
version: 0.0.1
schema: v1
models:
- name: GPT-4 gov
provider: askSage
model: gpt4-gov
apiBase: https://api.asksage.ai/server/
apiKey:
requestOptions:
caBundlePath: /path/to/dod/certificates
```
--------------------------------
### Gemini Configuration in Continue
Source: https://docs.continue.dev/customize/model-providers/top-level/gemini
Configure Gemini models by specifying the provider, model ID, and your API key in the Continue configuration file. Ensure you have obtained your API key from Google AI Studio.
```yaml
name: My Config
version: 0.0.1
schema: v1
models:
- name:
provider: gemini
model:
apiKey:
```
--------------------------------
### Configure Model Provider in config.yaml
Source: https://docs.continue.dev/customize/model-providers/overview
Example of how to add a model provider, such as Anthropic's Claude, to your `config.yaml` file. Ensure you replace placeholder values with your specific model and API key.
```yaml
models:
- name: Claude 4 Sonnet
provider: anthropic # Choose provider from the lists above
model: claude-sonnet-4-20250514 # Specific model name
apiKey: ${{ secrets.OPENAI_API_KEY }}
roles:
- chat
- edit
- apply
```
--------------------------------
### Create Supabase Functions Prompt
Source: https://docs.continue.dev/customize/deep-dives/prompts
This prompt guides the AI to generate high-quality PostgreSQL functions for Supabase, adhering to best practices like `SECURITY INVOKER` and proper `search_path` configuration.
```yaml
---
name: Create Supabase functions
description: Guidelines for writing Supabase database functions
invokable: true
---
# Database: Create functions
You're a Supabase Postgres expert in writing database functions. Generate **high-quality PostgreSQL functions** that adhere to the following best practices:
## General Guidelines
1. **Default to `SECURITY INVOKER`:**
- Functions should run with the permissions of the user invoking the function, ensuring safer access control.
- Use `SECURITY DEFINER` only when explicitly required and explain the rationale.
2. **Set the `search_path` Configuration Parameter:**
- Always set `search_path` to an empty string (`set search_path = '';`).
- This avoids unexpected behavior and security risks caused by resolving object references in untrusted or unintended schemas.
- Use fully qualified names (e.g., `schema_name.table_name`) for all database objects referenced within the function.
3. **Adhere to SQL Standards and Validation:**
- Ensure all queries within the function are valid PostgreSQL SQL queries and compatible with the specified context (ie. Supabase).
...
```