Restructure into a monorepo: models, VS Code extension, daemon, shared

- models/: GGUFs (Git LFS), manifest.json, model card, Apache-2.0 LICENSE + NOTICE
- extensions/vscode/: the Local Autocomplete extension (v0.5.0, publisher harvmaster)
- daemon/: acd completion daemon (bundled into the extension; also runs standalone)
- shared/: prompt layout + symbol extraction shared with the training pipeline
- scripts/: make-model-release.mjs, publish-extension-release.mjs (Gitea releases)
- README with quick start, settings, architecture, build and release instructions;
  MIT license for code; CHANGELOG

The default model manifest URL moves to models/manifest.json.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

README.md

@@ -1,10 +1,121 @@
-# Local autocomplete models
+# Local Autocomplete
 
-Q8_0 GGUF models for the Local Autocomplete VS Code extension (managed mode). The extension reads
-`manifest.json`, downloads the selected model, verifies its SHA-256 and runs it locally via llama.cpp.
+Fast, private, inline code completion for **TypeScript, Vue and Node.js**, from a small model that runs on your own machine.
 
-- **stage-c**: Qwen2.5-Coder-0.5B fine-tuned for suffix-first FIM on TS/Vue + personal code, with symbol-context headers (default). Prompt order spm, context modes: symbols, simple. 531 MB.
-- **stage-b**: Previous stage, no context header (plain suffix-first FIM). Prompt order spm, context modes: raw. 531 MB.
+- **Local:** a 0.5B model (fine-tuned Qwen2.5-Coder) runs through llama.cpp on your CPU or Apple GPU. No code leaves your machine.
+- **Fast:** ~90–100 ms per keystroke on a laptop CPU. Prompts are laid out suffix-first so the KV cache survives typing (~2 tokens re-processed per keystroke).
+- **Context-aware:** an optional `symbols` mode feeds the model signatures from the TypeScript language service, and a missing `this.` is repaired automatically.
+- **Zero setup:** the VS Code extension downloads the model and llama.cpp on first use and manages the background daemon itself.
 
-Set `localAutocomplete.modelManifestUrl` to the URL of this folder's `manifest.json`.
-License: Apache-2.0 (see LICENSE and NOTICE).
+| Model (held-out private code, never trained on) | exact match | edit similarity |
+|---|---:|---:|
+| Qwen2.5-Coder-0.5B base | 0.270 | 0.506 |
+| Qwen2.5-Coder-1.5B base | 0.366 | 0.623 |
+| **`stage-c` (this repo)** | **0.397** | **0.681** |
+
+See [models/](models/) for details.
+
+## Quick start
+
+1. Download the latest `local-autocomplete-<version>.vsix` from **[Releases](https://git.harvmaster.com/Harvmaster/autocomplete-model/releases)**.
+2. Install it: `code --install-extension local-autocomplete-<version>.vsix`, or in VS Code: Extensions → `⋯` → *Install from VSIX…*
+3. Open a TypeScript or Vue file. On first use the extension downloads the model (~530 MB) and llama.cpp (~15 MB), then starts. A progress notification shows this.
+4. Start typing: ghost text appears. **Tab** accepts, **Ctrl/Cmd+→** accepts word by word.
+
+Turn off other inline-completion providers (Copilot, …) so they don't compete.
+
+**Remote-SSH:** install the extension in the remote window. Everything (model, daemon, symbol lookups) then runs on the remote machine, next to your code.
+
+**Cursor:** the VSIX installs in Cursor too.
+
+### The status bar
+
+`AC: simple · 42 ms`. Click it for the menu:
+
+- **Context mode:**
+  - `symbols`: available symbols from the TypeScript language service (best for TS/Vue projects)
+  - `simple`: repo + file path only
+  - `raw`: no header, for older models
+
+  The menu only offers modes the active model was trained for.
+- **Model:** switch between models in the manifest (downloaded on first use).
+- **On/off**, **Restart daemon**, **Open daemon log**.
+
+### Settings
+
+| setting | default | |
+|---|---|---|
+| `localAutocomplete.modelManifestUrl` | this repo's `models/manifest.json` | where models are downloaded from |
+| `localAutocomplete.model` | manifest default | which model to use |
+| `localAutocomplete.modelPath` | | use a local `.gguf` instead (set `modelProfile` to match its prompt layout) |
+| `localAutocomplete.llamaServerPath` | | use your own `llama-server` (e.g. Homebrew's) instead of the downloaded build |
+| `localAutocomplete.excludeGlobs` | `.env*`, keys, `secrets/`, … | never sent to the model |
+| `localAutocomplete.recordEdits` | `false` | record your edits locally, as future training data for next-edit prediction |
+| `localAutocomplete.daemon.mode` | `managed` | `external` = use a daemon you run yourself (`serverUrl`) |
+
+## How it works
+
+```
+VS Code extension ──HTTP──▶ acd daemon ──▶ llama-server (llama.cpp, CPU / Metal)
+ ghost text, toggle,         builds the exact prompt layout the model was trained on,
+ edit recorder               symbol context (TypeScript language service, worker thread),
+                             KV-cache-friendly truncation, cancellation, this.-repair
+```
+
+- In **managed mode** (the default) the extension bundles the daemon and runs it on VS Code's own Node runtime. One daemon is shared by all windows, and it exits when idle.
+- The daemon can also run standalone ([daemon/](daemon/)); that's how other editors (Zed is planned) and the `acctl` CLI use it.
+- Design details: [docs/architecture.md](docs/architecture.md).
+
+## Repository layout
+
+| path | |
+|---|---|
+| [`models/`](models/) | GGUF models (Git LFS), `manifest.json`, model card, license |
+| [`extensions/vscode/`](extensions/vscode/) | the VS Code extension |
+| [`daemon/`](daemon/) | `acd`, the completion daemon (bundled into the extension; also runs standalone) |
+| [`shared/`](shared/) | prompt layout + symbol extraction, shared with the training pipeline so prompts match training exactly |
+| [`scripts/`](scripts/) | publish models and extension releases |
+| [`docs/`](docs/) | architecture |
+
+## Building from source
+
+Requires **Node ≥ 22.18** (the daemon and shared code run as TypeScript directly) and **Git LFS** for the models.
+
+```sh
+git clone https://git.harvmaster.com/Harvmaster/autocomplete-model.git local-autocomplete
+# code only, without the ~1 GB of models:  GIT_LFS_SKIP_SMUDGE=1 git clone …
+cd local-autocomplete
+npm run setup          # installs shared/, daemon/ and extensions/vscode/ dependencies
+npm run build          # → extensions/vscode/local-autocomplete-<version>.vsix
+npm test
+```
+
+Running the daemon standalone (external mode) is covered in [daemon/README.md](daemon/README.md).
+
+## Releasing
+
+**Extension:**
+1. Bump `version` in `extensions/vscode/package.json` and add a `## vscode <version>` section to [CHANGELOG.md](CHANGELOG.md).
+2. Run `npm run build`, then commit and push.
+3. Run `npm run release:extension`. This creates the `vscode-v<version>` release with the VSIX attached, using a Gitea token (see the script header).
+
+**Models:**
+1. Run `node scripts/make-model-release.mjs --from <dir> stage-d stage-c`. It updates `models/` (hard links, manifest, model card).
+2. Commit and push. Installed extensions pick up the new manifest on their next start.
+
+## Privacy
+
+- **Nothing leaves your machine.** Completions run locally, and the only network access is the one-time model and llama.cpp download.
+- **Excluded files are never read:** anything matching `excludeGlobs` (`.env*`, keys, …) is never sent to the model or recorded.
+- **Telemetry and edit recording are off by default.** If you enable them, they're written to local files only.
+
+## Roadmap
+
+- Better multi-line completions: continuing onto the next line, closing blocks, whole methods.
+- **Next-edit prediction:** e.g. removing a leftover `)` after unwrapping a call, or updating call sites after adding a parameter.
+- Token healing for completions that start mid-identifier.
+- Zed support via the daemon's OpenAI-compatible endpoint.
+
+## License
+
+Code: [MIT](LICENSE). Models: Apache-2.0 ([models/LICENSE](models/LICENSE), [models/NOTICE](models/NOTICE)), as derivatives of Qwen2.5-Coder.