ChatIDE - Coding Assistant (GPT/ChatGPT, Claude)

Provides a conversational chat interface within VSCode's side pane that routes user messages to either OpenAI (GPT-4, GPT-3.5-turbo) or Anthropic (Claude-v1.3) APIs based on user selection. Each conversation maintains separate message history per model, with API requests constructed using the selected model's native endpoint format and authentication headers stored in VSCode's encrypted secretStorage. Users can switch models mid-workflow without losing conversation context.

Exposes temperature, max_tokens, and custom system_prompt as user-configurable settings stored in VSCode's settings.json, allowing developers to tune model behavior (creativity, response length, role-playing) without modifying code. Settings auto-persist to VSCode configuration and apply globally across all conversations in the session. System prompts can be customized to enforce coding style, language preference, or domain expertise.

Enables users to export entire conversation threads (all messages, model selections, timestamps) to JSON files and re-import them later, preserving the full chat history. Export/import is triggered via command palette commands and stores conversation data in a structured JSON format that can be version-controlled, shared with teammates, or archived. This allows developers to maintain a searchable library of past interactions and solutions.

Stores OpenAI and Anthropic API keys in VSCode's native secretStorage (encrypted local storage), prompting users to enter keys on first use of each provider. Keys are never logged, transmitted to third parties, or stored in plaintext; they are retrieved from secretStorage on each API request and passed directly to the respective provider's endpoint. Users can update keys via command palette commands (>Update your OpenAI API Key for ChatIDE, >Update your Anthropic API Key for ChatIDE) without restarting VSCode.

Renders a conversational chat interface in VSCode's side pane (sidebar panel) accessible via keyboard shortcut (Cmd+Shift+I on macOS, Ctrl+Shift+I on other platforms). The pane displays message history in chronological order with sender attribution (user vs. assistant) and supports text input via a message box at the bottom. The UI integrates with VSCode's native theming and respects light/dark mode preferences.

Allows users to select which AI model (GPT-4, GPT-3.5-turbo, Claude-v1.3) to use before or during a conversation, with each model selection triggering routing to the appropriate API endpoint (OpenAI or Anthropic). The extension maintains separate message history per model, enabling users to ask the same question to multiple providers and compare responses. Model selection is persisted per conversation session.

Exposes ChatIDE functionality through VSCode's command palette (Cmd+Shift+P / Ctrl+Shift+P), including commands to open settings (>Open ChatIDE Settings), update API keys (>Update your OpenAI API Key for ChatIDE, >Update your Anthropic API Key for ChatIDE), and potentially other operations. This allows keyboard-driven access to configuration without navigating VSCode's settings UI or extension menus.

ChatIDE is explicitly labeled as an 'early prototype' with known critical bugs: closing the pane during generation causes non-recoverable errors requiring VSCode restart, and generation cannot be interrupted mid-response. The extension lacks production-grade error handling, recovery mechanisms, and stability guarantees. Users are warned to use 'at your own peril' and should expect breaking changes, data loss, or crashes.

Requires users to provide their own API keys for OpenAI and Anthropic rather than offering a managed backend or subscription model. The extension does not proxy requests through a ChatIDE-owned server; instead, API calls are made directly from the user's VSCode instance to OpenAI/Anthropic endpoints using the user's credentials. This eliminates ChatIDE's infrastructure costs but places billing and rate-limiting responsibility entirely on the user.