Ollama Autocoder

Generates code completions by sending text preceding the cursor position to a local Ollama instance, streaming tokens back to the editor in real-time. The extension reads the current file's text up to cursor position, constructs a prompt, and streams the model's output directly into the document at the cursor location. Context is strictly unidirectional — the model cannot see text ahead of the cursor, limiting completion awareness of surrounding code structure.

Exposes completion triggering as a configurable VS Code command (`Autocomplete with Ollama`) that can be bound to spacebar, other characters, or custom keybindings. The extension defines a `completion keys` setting that specifies which characters trigger autocompletion, with spacebar as default. Users can also bind the command to arbitrary keybindings via VS Code's keybindings.json, enabling workflows where completion is triggered on-demand rather than automatically.

Optionally displays a preview of the first line of generated completion before full generation completes, with a user-configurable delay before preview triggers. The `response preview` toggle enables/disables this feature, and `preview delay` controls how long the extension waits before showing the preview. The `continue inline` setting determines whether generation continues beyond the preview line when enabled. This allows developers to see early results without waiting for full generation, and cancel if the preview direction is wrong.

Allows users to specify which Ollama model to use for completion via the `model` setting (defaulting to `qwen2.5-coder:latest`) and configure the Ollama API endpoint address via settings. The extension connects to the configured endpoint and requests completions from the specified model. Users can swap models without restarting the extension by changing the setting, enabling experimentation with different model sizes and architectures. The endpoint is configurable to support non-standard Ollama deployments (e.g., remote machines, Docker containers, or custom ports).

Displays a VS Code notification with a 'Cancel' button during code generation, allowing users to interrupt completion mid-stream. Cancellation can also be triggered by typing any character, which discards the in-flight generation and returns control to the editor. The notification provides visual feedback that generation is in progress and offers an explicit cancel action without requiring keyboard shortcuts.

Exposes a `prompt window size` setting that controls how much of the file's preceding text is sent to the model as context. Users must manually configure this to match their model's maximum context window (e.g., 2048 tokens for smaller models, 4096+ for larger ones). The extension truncates the file content to this window size before sending to Ollama, preventing context overflow errors. However, no automatic detection or adaptive truncation strategy is documented — users must know their model's limits and configure manually.