Codellm: Use Ollama and OpenAI to write code

Generates code via configurable backend selection between local OLLAMA models (offline-capable) and cloud OpenAI models (GPT-3/GPT-4/ChatGPT), with temperature and token limits adjustable per query. The extension maintains a unified prompt interface that routes to either backend without requiring code changes, enabling developers to switch between offline and cloud inference within VS Code preferences. Context is passed as selected code blocks or free-form queries through the sidebar input box.

Analyzes selected code blocks and generates natural-language explanations by sending the selection to the configured LLM backend (local OLLAMA or OpenAI). The explanation capability is triggered via right-click context menu or command palette (`Codellm: Explain selection`) and returns formatted text in the editor panel. The extension preserves code context by passing only the selected block, avoiding full-file overhead while maintaining semantic accuracy.

Integrates code-specific LLM commands (Explain, Refactor, Find Problems, Optimize) into VS Code's right-click context menu. When a code block is selected, right-clicking displays menu options for each command, triggering the corresponding LLM action on the selection. This integration eliminates command-palette navigation for frequent tasks and provides a discoverable interface for code-specific operations.

Offers the extension as freemium software with free access to OpenAI's free-tier models (ChatGPT, code-davinci-002) and local OLLAMA models. Paid OpenAI models (GPT-3, GPT-4, text-davinci-003) require an OpenAI API key and incur usage costs. The extension does not charge for its own usage; costs are determined by the underlying LLM provider (OpenAI or OLLAMA). This pricing model enables developers to start using the extension without upfront costs.

Generates refactoring suggestions for selected code by routing the selection through a customizable prompt template to the configured LLM backend. The `Codellm: Refactor selection` command applies user-defined prompt customization (configurable via VS Code preferences) to guide the LLM toward specific refactoring goals (e.g., performance, readability, design patterns). Suggestions are returned as text in the editor panel and can be manually applied or copied into the editor.

Scans selected code blocks for potential bugs, anti-patterns, and code smells by submitting the selection to the configured LLM backend with a problem-detection prompt. The `Codellm: Find problems` command returns a list of identified issues with explanations in the editor panel. The extension does not modify code; it only reports findings for manual review. Problem detection leverages the LLM's training data on common vulnerabilities and code issues.

Generates performance and efficiency optimization suggestions for selected code by routing the selection through a performance-focused prompt to the LLM backend. The `Codellm: Optimize selection` command applies customizable optimization prompts (configurable via VS Code preferences) to guide the LLM toward specific optimization goals (e.g., algorithmic complexity, memory usage, I/O efficiency). Suggestions are returned as text and can be manually reviewed and applied.

Maintains a local conversation history of all queries and LLM responses within the extension, accessible via the sidebar panel. The extension supports pinning important conversations, saving history as JSON for export/import, and retrieving past context for follow-up queries. Conversation state is stored locally (storage location unknown) and persists across VS Code sessions. The sidebar displays conversation history with pin/save controls, enabling developers to reference past interactions without re-querying the LLM.

Embeds entire codebases into vector storage (Redis locally or OpenAI cloud) to enable context-aware code generation and queries. The extension supports uploading files (PDF, DOCX, JSON, TXT) and indexing them for semantic search. When generating code or explanations, the extension can retrieve relevant code snippets from the vector store to augment prompts, improving LLM accuracy for codebase-specific tasks. Embeddings are generated via local or OpenAI embedding models (configurable).

Enables one-click insertion of code snippets from LLM responses directly into the active editor. When the LLM generates code, the response is displayed in the editor panel with clickable code blocks. Clicking a snippet inserts it at the current cursor position or replaces the selected text. This capability eliminates manual copy-paste workflows and integrates code generation output directly into the editing flow.

Provides a dedicated sidebar panel in VS Code with a text input box for free-form queries to the configured LLM backend. The sidebar maintains conversation context across queries, displays responses in a scrollable panel, and integrates with the editor's selection context (selected code can be included in queries). The `Ask Codellm` command activates the sidebar input, enabling developers to ask general questions, request code generation, or seek explanations without using command palette.

Exposes LLM model selection, temperature, and token count as configurable parameters in VS Code preferences. Developers can switch between OLLAMA local models and OpenAI cloud models (GPT-3, GPT-4, ChatGPT, text-davinci-003, code-davinci-002) without restarting the extension. Temperature and token limits are adjustable globally (specific ranges and defaults unknown). Configuration is persisted in VS Code settings and applied to all subsequent queries.