style: Fix markdown lint errors across all documentation

Wrap long lines to stay under 80 characters, add blank lines around
lists and headings, fix ordered list prefixes, add language specifiers
to code blocks, and convert emphasis headers to proper headings.

Signed-off-by: Eden Reich <eden.reich@gmail.com>

Author: edenreich

CLAUDE.md

@@ -0,0 +1,87 @@
+# CLAUDE.md
+
+This file provides guidance to Claude Code (claude.ai/code) when working with
+code in this repository.
+
+## Project Overview
+
+TypeScript SDK for the [Inference Gateway][ig] - a unified API for multiple
+LLM providers (OpenAI, Anthropic, Groq, Cohere, Ollama, Cloudflare, DeepSeek,
+Google, Mistral).
+
+[ig]: https://github.com/edenreich/inference-gateway
+
+## Commands
+
+```bash
+# Build
+npm run build
+
+# Test
+npm run test
+
+# Run a single test
+npx jest tests/client.test.ts -t "test name pattern"
+
+# Lint
+npm run lint
+
+# Format
+npm run format
+
+# Generate types from OpenAPI spec (downloads spec first)
+task oas-download && task generate-types
+```
+
+## Architecture
+
+### Source Structure
+
+- `src/index.ts` - Package entry point, re-exports client and types
+- `src/client.ts` - Main `InferenceGatewayClient` class with all API methods
+- `src/types/generated/index.ts` - Auto-generated TypeScript types from OpenAPI
+  spec (do not edit manually)
+
+### Client Architecture
+
+The SDK centers around `InferenceGatewayClient` which provides:
+
+- `listModels(provider?)` - List available models
+- `listTools()` - List MCP tools (when EXPOSE_MCP enabled)
+- `createChatCompletion(request, provider?)` - Non-streaming completions
+- `streamChatCompletion(request, callbacks, provider?, abortSignal?)` -
+  Streaming completions with SSE
+- `proxy(provider, path, options)` - Direct provider proxy
+- `healthCheck()` - Gateway health check
+- `withOptions(options)` - Create new client with merged options
+
+### Streaming Implementation
+
+`StreamProcessor` class handles SSE parsing with callbacks for:
+
+- `onContent` - Text content chunks
+- `onReasoning` - Reasoning content (DeepSeek, Groq models)
+- `onTool` - Client-provided tool calls
+- `onMCPTool` - MCP tool calls (tools not in client's tool list)
+- `onUsageMetrics` - Token usage statistics
+
+### Type Generation
+
+Types in `src/types/generated/index.ts` are auto-generated from the OpenAPI
+spec using `openapi-typescript`. Regenerate with `task generate-types` after
+downloading the latest spec.
+
+### Path Aliases
+
+- `@/*` maps to `./src/*`
+- `@tests/*` maps to `./tests/*`
+
+## Testing
+
+Tests use Jest with ts-jest. Tests mock the fetch function to simulate API
+responses including streaming SSE events. Test file: `tests/client.test.ts`.
+
+## Commit Message Convention
+
+Use conventional commits: `feat:`, `fix:`, `refactor:`, `docs:`, `style:`,
+`test:`, `chore:`, `ci:`, `perf:`

CONTRIBUTING.md

@@ -1,6 +1,7 @@
 # Contributing to the Inference Gateway Typescript SDK
 
-Thank you for your interest in contributing to the Inference Gateway Typescript SDK! This document provides guidelines and steps for contributing.
+Thank you for your interest in contributing to the Inference Gateway Typescript
+SDK! This document provides guidelines and steps for contributing.
 
 ## Table of Contents
 
@@ -16,16 +17,17 @@ Thank you for your interest in contributing to the Inference Gateway Typescript
 
 1. Prerequisites:
 
-- docker
+   - docker
 
-2. Clone and setup:
+1. Clone and setup:
 
 ```sh
 git clone https://github.com/inference-gateway/typescript-sdk
 code typescript-sdk
 ```
 
-3. Click on the `Reopen in Container` button in the bottom right corner of the window.
+1. Click on the `Reopen in Container` button in the bottom right corner of
+   the window.
 
 ## Development Process
 
@@ -35,15 +37,15 @@ code typescript-sdk
 git checkout -b my-feature
 ```
 
-2. Make changes and test:
+1. Make changes and test:
 
 ```sh
 task test
 ```
 
-3. Add tests for new features or fix tests for refactoring and bug fixes.
+1. Add tests for new features or fix tests for refactoring and bug fixes.
 
-4. Run linter:
+1. Run linter:
 
 ```sh
 task lint
@@ -66,11 +68,12 @@ Types:
 - docs: documentation
 - style: formatting, missing semi colons, etc; no code change
 - test: adding missing tests
-- chore: updating build tasks, package manager configs, etc; no production code change
+- chore: updating build tasks, package manager configs, etc; no production
+  code change
 - ci: changes to CI configuration files and scripts
 - perf: code change that improves performance
 
-2. Ensure your PR:
+1. Ensure your PR:
 
 - Passes all tests
 - Updates documentation as needed
@@ -80,9 +83,9 @@ Types:
 ## Release Process
 
 1. Merging to main triggers CI checks
-2. Manual release workflow can be triggered from Actions
-3. Version is determined by commit messages
-4. Changelog is automatically generated
+1. Manual release workflow can be triggered from Actions
+1. Version is determined by commit messages
+1. Changelog is automatically generated
 
 ## Getting Help
 

README.md

@@ -62,7 +62,8 @@ try {
 
 ### Listing MCP Tools
 
-To list available Model Context Protocol (MCP) tools (only available when EXPOSE_MCP is enabled):
+To list available Model Context Protocol (MCP) tools (only available when
+EXPOSE_MCP is enabled):
 
 ```typescript
 import { InferenceGatewayClient } from '@inference-gateway/sdk';
@@ -300,7 +301,8 @@ For more examples, check the [examples directory](./examples).
 
 ## Contributing
 
-Please refer to the [CONTRIBUTING.md](CONTRIBUTING.md) file for information about how to get involved. We welcome issues, questions, and pull requests.
+Please refer to the [CONTRIBUTING.md](CONTRIBUTING.md) file for information
+about how to get involved. We welcome issues, questions, and pull requests.
 
 ## License
 

Taskfile.yml

@@ -11,6 +11,7 @@ tasks:
     desc: Lint the SDK
     cmds:
       - npm run lint
+      - markdownlint . --ignore **/node_modules/** --ignore CHANGELOG.md
 
   build:
     desc: Build the SDK

examples/QUICKSTART.md

@@ -17,6 +17,7 @@ This guide will help you run all TypeScript SDK examples quickly.
    ```
 
 2. Add your API keys to `.env`:
+
    ```bash
    # Choose one or more providers
    GROQ_API_KEY=your_groq_key_here

examples/README.md

@@ -4,7 +4,8 @@ This directory contains examples that demonstrate how to use the Typescript SDK.
 
 ## Pre-requisites
 
-You should have docker installed or use the dev container in VS Code which has all the tools you might need.
+You should have docker installed or use the dev container in VS Code which has
+all the tools you might need.
 
 ## Quick Start
 
@@ -25,9 +26,13 @@ You should have docker installed or use the dev container in VS Code which has a
 
 4. Review the different examples in the specific directories:
 
-   - [List](./list): Demonstrates listing models, MCP tools, health checks, and provider proxy functionality.
-   - [Chat](./chat): Shows chat completions, streaming responses, multi-turn conversations, and function calling.
-   - [MCP](./mcp): Illustrates Model Context Protocol integration with file operations, web scraping, and multi-tool conversations using Docker Compose.
+   - [List](./list): Demonstrates listing models, MCP tools, health checks,
+     and provider proxy functionality.
+   - [Chat](./chat): Shows chat completions, streaming responses, multi-turn
+     conversations, and function calling.
+   - [MCP](./mcp): Illustrates Model Context Protocol integration with file
+     operations, web scraping, and multi-tool conversations using Docker
+     Compose.
 
 ## Examples Overview
 
@@ -57,7 +62,8 @@ You should have docker installed or use the dev container in VS Code which has a
 - Function/tool calling with AI models
 - Temperature comparison examples
 
-**Best for**: Building chat applications and understanding different interaction patterns
+**Best for**: Building chat applications and understanding different
+interaction patterns
 
 ### [MCP Example](./mcp)
 

examples/chat/README.md

@@ -1,6 +1,8 @@
 # Chat Example
 
-This example demonstrates how to use the Inference Gateway SDK for chat applications. It includes creating chat completions, streaming responses, multi-turn conversations, and function calling using the TypeScript SDK.
+This example demonstrates how to use the Inference Gateway SDK for chat
+applications. It includes creating chat completions, streaming responses,
+multi-turn conversations, and function calling using the TypeScript SDK.
 
 ## Features Demonstrated
 
@@ -11,7 +13,9 @@ This example demonstrates how to use the Inference Gateway SDK for chat applicat
 
 ## Getting Started
 
-1. Ensure you have the Inference Gateway running locally or have access to an instance. If not, please read the [Quick Start](../README.md#quick-start) section in the main README.
+1. Ensure you have the Inference Gateway running locally or have access to an
+   instance. If not, please read the [Quick Start](../README.md#quick-start)
+   section in the main README.
 
 2. Install the SDK if you haven't already:
 
@@ -62,7 +66,8 @@ This example works with any provider supported by the Inference Gateway:
 
 ## Notes
 
-- The function calling example simulates weather API calls - in a real application, you would implement actual function execution
+- The function calling example simulates weather API calls - in a real
+  application, you would implement actual function execution
 - Streaming responses provide real-time output, perfect for interactive applications
 - Multi-turn conversations maintain context across multiple exchanges
 - Temperature and max_tokens parameters can be adjusted for different use cases

examples/list/README.md

@@ -1,6 +1,8 @@
 # List Example
 
-This example demonstrates how to use the Inference Gateway SDK for listing models and MCP tools. It includes making requests to the SDK and handling responses using the TypeScript SDK.
+This example demonstrates how to use the Inference Gateway SDK for listing
+models and MCP tools. It includes making requests to the SDK and handling
+responses using the TypeScript SDK.
 
 ## Features Demonstrated
 
@@ -11,7 +13,9 @@ This example demonstrates how to use the Inference Gateway SDK for listing model
 
 ## Getting Started
 
-1. Ensure you have the Inference Gateway running locally or have access to an instance. If not, please read the [Quick Start](../README.md#quick-start) section in the main README.
+1. Ensure you have the Inference Gateway running locally or have access to an
+   instance. If not, please read the [Quick Start](../README.md#quick-start)
+   section in the main README.
 
 2. Install the SDK if you haven't already: