VSCode Ollama

Provides a dedicated VS Code sidebar panel for conversational interaction with locally-running Ollama LLM instances via HTTP/REST API calls. Implements streaming response rendering to display model output token-by-token as it generates, reducing perceived latency. Maintains conversation history within the session, allowing multi-turn dialogue without re-sending full context each turn. Supports runtime model switching via UI dropdown without restarting the extension.

Augments chat responses with real-time web search results by querying external sources and synthesizing findings into LLM responses. The extension fetches search results (implementation method unknown — likely via a search API or web scraping) and injects them as context into the LLM prompt, allowing the model to cite and reference current information. Results are displayed with citations, enabling users to verify claims and access sources.

Provides configurable keybindings for chat input operations: Enter sends the message, and Shift+Enter inserts a newline without sending. Keybindings follow VS Code's standard conventions and can be customized via keybindings.json. Enables efficient chat interaction without mouse clicks.

Displays the LLM's intermediate reasoning steps or chain-of-thought process during response generation, allowing developers to inspect how the model arrived at its answer. Implementation details are undocumented, but likely involves parsing structured output from the LLM (e.g., XML tags, JSON reasoning blocks) or using Ollama's native reasoning APIs if available. Helps with debugging model behavior and understanding confidence levels.

Allows users to switch between different LLM models at runtime via a UI dropdown selector without restarting the extension or losing conversation context. The extension queries the Ollama server for available models (via Ollama's list models API endpoint) and dynamically populates the selector. Switching models applies to subsequent messages in the conversation; prior messages retain their original model attribution (behavior inferred).

Allows users to specify a custom Ollama server address (hostname and port) via VS Code settings, enabling connection to Ollama instances running on remote machines, Docker containers, or non-default ports. Configuration is stored in VS Code's settings.json and applied at extension initialization. Supports both localhost and network-accessible Ollama servers via HTTP/REST API.

Allows users to specify a default LLM model via VS Code settings, which is automatically selected when the extension starts or when no model is explicitly chosen. Configuration is stored in VS Code's settings.json and applied at extension initialization. Reduces friction by eliminating the need to manually select a model for each chat session.

Provides configurable performance modes (specific modes unknown) to optimize inference speed vs. quality trade-offs. Documentation mentions this feature but provides no technical details on which modes are available, how they map to Ollama parameters, or what impact they have on latency and output quality. Likely controls parameters like temperature, top-p, or model quantization.

Allows users to configure LLM inference parameters (specific parameters unknown) to customize model behavior. Documentation claims this feature exists but provides no details on which parameters are exposed (e.g., temperature, top-p, top-k, repeat-penalty, context-length), how they are configured (UI vs. settings.json), or what valid ranges are. Likely maps to Ollama's native parameter API.

Provides VS Code Command Palette commands for extension operations, including 'Ollama: Open Chat' to launch the chat interface and 'Ollama: Settings' to access configuration. Commands are discoverable via Ctrl+Shift+P (Windows/Linux) or Cmd+Shift+P (macOS) and follow VS Code's standard command naming conventions. Enables keyboard-driven workflow without mouse interaction.

Maintains a conversation history within the chat panel, displaying prior messages and responses in chronological order. History is session-scoped (lost on extension reload or VS Code restart) and stored in memory. Allows users to scroll through prior exchanges and reference previous context without re-typing. No persistence or export functionality documented.