LineLoom

Write less. Build more. Stay in control.

LineLoom is a free MIT-licensed VS Code extension for context-aware inline autocomplete with your own Ollama model. It uses native editor ghost text, and does not require a LineLoom account, cloud inference provider, or telemetry.

Stable GitHub release: v1.0.0 is the first major release. Automated tests verify packaging and mocked-model behavior; actual model quality, interactive editor acceptance and hardware latency are not independently certified. See v1.0.0 release notes for verified tests and known limitations.

Install the GitHub stable release

The GitHub v1.0.0 release includes a LineLoom-1.0.0.vsix package packaged for the VS Code stable channel. Download it from the v1.0.0 release page once published and use VS Code → Extensions → ... → Install from VSIX (or code --install-extension LineLoom-1.0.0.vsix).

Important for Windows: Do not double-click the VSIX file. Windows may open Visual Studio VSIX Installer, which correctly rejects VS Code extensions and displays “One or more extensions are for Visual Studio Code.” Open Visual Studio Code and select Extensions → … → Install from VSIX… instead. Step-by-step installation and troubleshooting.

Registry status: the GitHub stable release is distinct from Microsoft Visual Studio Marketplace and Open VSX listings. Neither listing should be advertised before publication is confirmed. The extension publisher ID is SanskarCodes, not the GitHub user ID sanskarIN. Publisher onboarding / registry instructions.

Project website and documentation

The LineLoom static website is maintained in site/ and deployed through the GitHub Pages workflow, subject to repository GitHub Pages being enabled under Settings → Pages → GitHub Actions. Intended URL: https://sanskarin.github.io/LineLoom/. See the deployment guide to verify when it is actually live.

Website content is excluded from the extension VSIX package. This does not add hosted inference, an account requirement or telemetry.

Release verification status

The v1.0.0 stable packaging workflow checks archive integrity and installs the packaged VSIX in an isolated real VS Code command-line profile. This is stronger than ZIP validation, but it does not prove real Ollama inference or interactive ghost-text acceptance. Manual verification matrix tracks the remaining Windows, macOS, Linux, privacy, offline and model-performance tests. Visual Studio Marketplace/Open VSX publication still requires separate publisher authorization, and real-model QA remains ongoing.

Features

• Stricter send-time privacy controls: rechecks active model, file exclusions, workspace trust and remote-endpoint permission before sending completion context. Pending model-picker choices are also discarded if the Ollama endpoint or remote approval changes.
• Per-language Ollama models: assign a different installed model to each supported language using LineLoom: Assign Language Model or the status-bar Quick Actions picker. Unassigned languages use the default lineloom.model; JSX/TSX use the JavaScript/TypeScript override. No automatic model downloads.
• Native VS Code inline suggestions for nine language IDs: Python, JavaScript/JSX, TypeScript/TSX, Rust, Kotlin, Go, Java, C and C++. Go, Java, C and C++ remain experimental.
• Smarter automatic request timing: suppresses background inference directly before existing identifier characters (including Unicode letters, combining marks, connector punctuation and joiners). Configure lineloom.suppressMidTokenAuto (default on) to opt out; manual requests always work, and skip the typing debounce.
• Typed suggestion continuation: when you type the beginning of an inline suggestion, LineLoom can offer the remaining text immediately from short-lived memory without another Ollama generation. Context, settings, active editor, workspace privacy and the actual single-insertion edit event must all match. Multi-edit changes, selection replacements and edits elsewhere invalidate reuse. No cross-file reads.
• Multi-line continuation, bounded prefix/suffix context, and optional FIM using a recognized Qwen2.5 Coder model family. Improved cleanup removes common model control tokens and explanations outside leading fenced code blocks. Ollama streams have total-byte, event-count and per-event safety limits.
• Quick Actions from the status bar: enable/disable completion, pause/resume automatic suggestions, trigger manually, choose a default or per-language model, manage languages, check connection, open diagnostics or settings. Model discovery and connection checks run only when selected by the user.
• User-selected installed model, endpoint, timeouts, output limits, temperature, automatic-trigger controls and per-language opt-in/out settings.
• Cancellation on newer requests, active cursor/editor changes and timeouts; a short-lived backoff stops repeatedly sending identical automatic requests after an empty model result. Explicit user-triggered requests bypass this backoff. Additional checks run before sending code or reusing a cached suggestion. No insertion is attempted for selected text or multiple cursors, and automatic suggestions defer to active native IntelliSense completions.
• Only the active trusted-workspace document is used for completion; rejects symlinks escaping the workspace and excludes sensitive filenames and nested .gitignore, .lineloomignore and user-specified patterns.
• Local loopback by default; remote HTTPS needs both a setting and per-origin interactive approval. HTTP redirects are rejected to prevent transferring code to an unapproved destination. No background model downloads.
• Automatic completion requires two non-whitespace characters on the active line by default (configurable 0–32); manual triggers bypass this threshold. Active-document context is read through bounded editor ranges, even in large files.

Getting started

1. Install VS Code and Ollama for Windows, Linux or macOS.
2. Start Ollama according to its platform instructions. Confirm that http://127.0.0.1:11434/api/tags is reachable locally.
3. Install a coding model yourself: ollama pull qwen2.5-coder:1.5b. Downloads consume storage; see model licensing and system requirements.
4. Install the VSIX from the GitHub stable release as described above. For local development from source instead, run npm ci, npm run build, open the repo in VS Code and press F5.
5. In VS Code (or the Extension Development Host), open a trusted folder containing a supported source file (e.g. .py, .js, .ts, .rs, .kt, .go, .java, .c, or .cpp).
6. Type some code, or run LineLoom: Trigger Completion. Accept native inline text with your VS Code inline-suggest keybinding.
7. Run LineLoom: Check Ollama Connection or LineLoom: Select Model if suggestions do not appear.

Open the Command Palette and run LineLoom: Show Setup Guide for the short interactive guide. Click LineLoom in the VS Code status bar to open Quick Actions. Pausing automatic suggestions keeps manual LineLoom: Trigger Completion available; the pause choice remains in VS Code settings until you resume.

Commands

Quick Actions · Pause or Resume Automatic Suggestions · Enable Autocomplete · Disable Autocomplete · Trigger Completion · Select Model · Manage Autocomplete Languages · Check Ollama Connection · Open Settings · Open Diagnostics · Show Setup Guide · Show Completion Performance.

Settings are under lineloom.* in VS Code Settings. lineloom.enabledLanguages lists which of the nine language IDs can receive suggestions; the JSX and TSX editor modes follow the JavaScript and TypeScript choices. An empty list disables suggestions for all languages. Defaults: model qwen2.5-coder:1.5b, endpoint http://127.0.0.1:11434, debounce 250 ms, timeout 12 s, 8,000 context characters, 128 generated tokens, eight maximum suggestion lines (configurable 1–20), two minimum automatic-trigger characters (configurable 0–32), and mid-token auto-suppression enabled. Cross-file context is not implemented in v1.0.0 even if the reserved setting is enabled.

Privacy and safety

The extension transmits a bounded snippet from the current document to the configured Ollama endpoint to generate suggestions. Localhost requests stay on the local network stack; using a remote endpoint sends snippets to that server. No telemetry or repository indexing exists. A local model is not a guarantee of safe, correct, or licensed output; review code before use.

• Privacy policy and ignore rules
• Architecture
• Development and testing
• Troubleshooting
• v1.0.0 stable release notes and ongoing manual QA checklist

Development

npm install
npm run check
npm run package

The GitHub v1.0.0 stable release ships an installable VSIX for community testing, including nine language IDs, per-language selection, nested ignore protection, bounded editor context, foreground-editor preflight checks, a short-lived empty-result retry backoff, typed-prefix continuation reuse, bounded NDJSON parsing and redirect-safe Ollama requests. It includes a mocked-Ollama editor-level integration check. Real Ollama model quality, offline behavior and manual cross-platform verification remain unverified; see the release notes. External registry publication remains a separate authorized publishing step. Roadmap.

Maintainer

GitHub: sanskarIN · X · LinkedIn

Voluntary support

LineLoom is free and has no subscription or paywall. If useful, you may support maintenance via Buy Me a Coffee, Razorpay, or PayPal.Me.

License

MIT License. Licensing history and third-party notices. LineLoom is an independent project; no affiliation or endorsement by Microsoft, GitHub, Ollama or model providers is implied.