@dvai-bridge/ios-llama-core 4.0.0 → 4.0.1

package/ios/Tests/DVAILlamaCoreTests/ModelDownloaderTest.swift

@@ -1,89 +1,89 @@
-import XCTest
-import CryptoKit
-@testable import DVAILlamaCore
-
-final class ModelDownloaderTest: XCTestCase {
-    /// Per-test cache dir so tests don't pollute the real App Support folder.
-    private var tmpCacheDir: URL!
-    private var downloader: ModelDownloader!
-
-    override func setUp() {
-        super.setUp()
-        let base = FileManager.default.temporaryDirectory
-        tmpCacheDir = base.appendingPathComponent("dvai-modeldownloader-test-\(UUID().uuidString)")
-        downloader = ModelDownloader(cacheDirOverride: tmpCacheDir)
-    }
-
-    override func tearDown() {
-        if let dir = tmpCacheDir {
-            try? FileManager.default.removeItem(at: dir)
-        }
-        downloader = nil
-        tmpCacheDir = nil
-        super.tearDown()
-    }
-
-    /// Calling `cacheDirURL()` should create the directory if missing and
-    /// return a path that resolves under the override.
-    func testCacheDirCreates() async throws {
-        let url = try await downloader.cacheDirURL()
-        XCTAssertEqual(url.path, tmpCacheDir.path)
-        var isDir: ObjCBool = false
-        XCTAssertTrue(FileManager.default.fileExists(atPath: url.path, isDirectory: &isDir))
-        XCTAssertTrue(isDir.boolValue)
-    }
-
-    /// Cache hit: writing a known file with a known sha256 to the cache dir
-    /// then calling `downloadModel(...)` with that sha must return
-    /// `cached: true` without ever touching the network — proven by passing
-    /// a deliberately broken URL.
-    func testCacheHitReturnsCached() async throws {
-        let dir = try await downloader.cacheDirURL()
-        let filename = "fixture.bin"
-        let payload = "hello, dvai cache!".data(using: .utf8)!
-        try payload.write(to: dir.appendingPathComponent(filename))
-
-        let digest = SHA256.hash(data: payload)
-        let hex = digest.map { String(format: "%02x", $0) }.joined()
-
-        // URL is intentionally bogus — a real network call would fail. The
-        // cache-hit fast path bypasses network entirely.
-        let bogusURL = URL(string: "https://invalid.dvai.test/should-not-fetch.bin")!
-        let result = try await downloader.downloadModel(
-            url: bogusURL,
-            expectedSha256: hex,
-            destFilename: filename,
-            headers: [:],
-            onProgress: { _, _ in }
-        )
-        XCTAssertTrue(result.cached, "expected cache-hit short-circuit")
-        XCTAssertEqual(result.path, dir.appendingPathComponent(filename).path)
-    }
-
-    /// `listCachedModels()` enumerates regular files (skipping `.partial`
-    /// and dotfiles) and `deleteCachedModel(...)` removes them.
-    func testListAndDelete() async throws {
-        let dir = try await downloader.cacheDirURL()
-        let a = "alpha".data(using: .utf8)!
-        let b = "bravo".data(using: .utf8)!
-        try a.write(to: dir.appendingPathComponent("a.gguf"))
-        try b.write(to: dir.appendingPathComponent("b.gguf"))
-        // Files that must be ignored:
-        try Data().write(to: dir.appendingPathComponent("c.gguf.partial"))
-        try Data().write(to: dir.appendingPathComponent(".hidden"))
-
-        let listed = try await downloader.listCachedModels()
-        let names = Set(listed.map { $0.filename })
-        XCTAssertEqual(names, ["a.gguf", "b.gguf"])
-        XCTAssertEqual(listed.count, 2)
-        // Bytes + sha255 are populated.
-        for info in listed {
-            XCTAssertGreaterThan(info.bytes, 0)
-            XCTAssertEqual(info.sha256.count, 64)
-        }
-
-        try await downloader.deleteCachedModel(filename: "a.gguf")
-        let listed2 = try await downloader.listCachedModels()
-        XCTAssertEqual(Set(listed2.map { $0.filename }), ["b.gguf"])
-    }
-}
+import XCTest
+import CryptoKit
+@testable import DVAILlamaCore
+
+final class ModelDownloaderTest: XCTestCase {
+    /// Per-test cache dir so tests don't pollute the real App Support folder.
+    private var tmpCacheDir: URL!
+    private var downloader: ModelDownloader!
+
+    override func setUp() {
+        super.setUp()
+        let base = FileManager.default.temporaryDirectory
+        tmpCacheDir = base.appendingPathComponent("dvai-modeldownloader-test-\(UUID().uuidString)")
+        downloader = ModelDownloader(cacheDirOverride: tmpCacheDir)
+    }
+
+    override func tearDown() {
+        if let dir = tmpCacheDir {
+            try? FileManager.default.removeItem(at: dir)
+        }
+        downloader = nil
+        tmpCacheDir = nil
+        super.tearDown()
+    }
+
+    /// Calling `cacheDirURL()` should create the directory if missing and
+    /// return a path that resolves under the override.
+    func testCacheDirCreates() async throws {
+        let url = try await downloader.cacheDirURL()
+        XCTAssertEqual(url.path, tmpCacheDir.path)
+        var isDir: ObjCBool = false
+        XCTAssertTrue(FileManager.default.fileExists(atPath: url.path, isDirectory: &isDir))
+        XCTAssertTrue(isDir.boolValue)
+    }
+
+    /// Cache hit: writing a known file with a known sha256 to the cache dir
+    /// then calling `downloadModel(...)` with that sha must return
+    /// `cached: true` without ever touching the network — proven by passing
+    /// a deliberately broken URL.
+    func testCacheHitReturnsCached() async throws {
+        let dir = try await downloader.cacheDirURL()
+        let filename = "fixture.bin"
+        let payload = "hello, dvai cache!".data(using: .utf8)!
+        try payload.write(to: dir.appendingPathComponent(filename))
+
+        let digest = SHA256.hash(data: payload)
+        let hex = digest.map { String(format: "%02x", $0) }.joined()
+
+        // URL is intentionally bogus — a real network call would fail. The
+        // cache-hit fast path bypasses network entirely.
+        let bogusURL = URL(string: "https://invalid.dvai.test/should-not-fetch.bin")!
+        let result = try await downloader.downloadModel(
+            url: bogusURL,
+            expectedSha256: hex,
+            destFilename: filename,
+            headers: [:],
+            onProgress: { _, _ in }
+        )
+        XCTAssertTrue(result.cached, "expected cache-hit short-circuit")
+        XCTAssertEqual(result.path, dir.appendingPathComponent(filename).path)
+    }
+
+    /// `listCachedModels()` enumerates regular files (skipping `.partial`
+    /// and dotfiles) and `deleteCachedModel(...)` removes them.
+    func testListAndDelete() async throws {
+        let dir = try await downloader.cacheDirURL()
+        let a = "alpha".data(using: .utf8)!
+        let b = "bravo".data(using: .utf8)!
+        try a.write(to: dir.appendingPathComponent("a.gguf"))
+        try b.write(to: dir.appendingPathComponent("b.gguf"))
+        // Files that must be ignored:
+        try Data().write(to: dir.appendingPathComponent("c.gguf.partial"))
+        try Data().write(to: dir.appendingPathComponent(".hidden"))
+
+        let listed = try await downloader.listCachedModels()
+        let names = Set(listed.map { $0.filename })
+        XCTAssertEqual(names, ["a.gguf", "b.gguf"])
+        XCTAssertEqual(listed.count, 2)
+        // Bytes + sha255 are populated.
+        for info in listed {
+            XCTAssertGreaterThan(info.bytes, 0)
+            XCTAssertEqual(info.sha256.count, 64)
+        }
+
+        try await downloader.deleteCachedModel(filename: "a.gguf")
+        let listed2 = try await downloader.listCachedModels()
+        XCTAssertEqual(Set(listed2.map { $0.filename }), ["b.gguf"])
+    }
+}

package/ios/Tests/DVAILlamaCoreTests/PluginStateTest.swift

@@ -1,51 +1,51 @@
-import XCTest
-@testable import DVAILlamaCore
-
-final class PluginStateTest: XCTestCase {
-    func testStartFailsWhenModelPathMissing() async {
-        let state = PluginState()
-        do {
-            _ = try await state.start(opts: [:])
-            XCTFail("should have thrown")
-        } catch let error as NSError {
-            XCTAssertTrue(error.localizedDescription.contains("modelPath is required"))
-        }
-    }
-
-    func testStartFailsWhenModelPathEmpty() async {
-        let state = PluginState()
-        do {
-            _ = try await state.start(opts: ["modelPath": ""])
-            XCTFail("should have thrown")
-        } catch {
-            // expected
-        }
-    }
-
-    func testStatusInfoReportsNotRunning() async {
-        let state = PluginState()
-        let info = await state.statusInfo()
-        XCTAssertEqual(info["running"] as? Bool, false)
-    }
-
-    /// With the real LlamaCppBridge implementation, loading a non-existent GGUF
-    /// fails at `llama_load_model_from_file`. The full `start → server-bind →
-    /// success` happy-path needs a real model file and is exercised by the
-    /// device-level tests in Task 37's milestone. Here we assert that the
-    /// failure surfaces cleanly and the state stays "not running".
-    func testStartFailsOnFakeModelPath() async {
-        let state = PluginState()
-        do {
-            _ = try await state.start(opts: [
-                "modelPath": "/tmp/definitely-does-not-exist.gguf",
-                "httpBasePort": 39200,
-                "httpMaxPortAttempts": 4,
-            ])
-            XCTFail("expected start() to throw for fake model path")
-        } catch {
-            // expected
-        }
-        let info = await state.statusInfo()
-        XCTAssertEqual(info["running"] as? Bool, false)
-    }
-}
+import XCTest
+@testable import DVAILlamaCore
+
+final class PluginStateTest: XCTestCase {
+    func testStartFailsWhenModelPathMissing() async {
+        let state = PluginState()
+        do {
+            _ = try await state.start(opts: [:])
+            XCTFail("should have thrown")
+        } catch let error as NSError {
+            XCTAssertTrue(error.localizedDescription.contains("modelPath is required"))
+        }
+    }
+
+    func testStartFailsWhenModelPathEmpty() async {
+        let state = PluginState()
+        do {
+            _ = try await state.start(opts: ["modelPath": ""])
+            XCTFail("should have thrown")
+        } catch {
+            // expected
+        }
+    }
+
+    func testStatusInfoReportsNotRunning() async {
+        let state = PluginState()
+        let info = await state.statusInfo()
+        XCTAssertEqual(info["running"] as? Bool, false)
+    }
+
+    /// With the real LlamaCppBridge implementation, loading a non-existent GGUF
+    /// fails at `llama_load_model_from_file`. The full `start → server-bind →
+    /// success` happy-path needs a real model file and is exercised by the
+    /// device-level tests in Task 37's milestone. Here we assert that the
+    /// failure surfaces cleanly and the state stays "not running".
+    func testStartFailsOnFakeModelPath() async {
+        let state = PluginState()
+        do {
+            _ = try await state.start(opts: [
+                "modelPath": "/tmp/definitely-does-not-exist.gguf",
+                "httpBasePort": 39200,
+                "httpMaxPortAttempts": 4,
+            ])
+            XCTFail("expected start() to throw for fake model path")
+        } catch {
+            // expected
+        }
+        let info = await state.statusInfo()
+        XCTAssertEqual(info["running"] as? Bool, false)
+    }
+}

package/package.json

@@ -1,13 +1,13 @@
 {
   "name": "@dvai-bridge/ios-llama-core",
-  "version": "4.0.0",
+  "version": "4.0.1",
   "description": "DVAI-Bridge iOS llama.cpp core — pure Swift / ObjC++ embedded HTTP server + handlers + bridge. Capacitor-free.",
   "author": "Deep Chakraborty <https://github.com/dk013>",
   "license": "Custom (See LICENSE)",
   "main": "Package.swift",
   "files": [
-    "Package.swift",
-    "ios",
+    "ios/Sources",
+    "ios/Tests",
     "README.md",
     "LICENSE"
   ],

package/README.md

@@ -1,199 +0,0 @@
-![DVAI-Bridge](/assets/banner.png)
-
-# DVAI-Bridge
-
-<!-- [![Smoke — real models](https://github.com/Westenets/dvai-bridge/actions/workflows/smoke-real-models.yml/badge.svg?branch=main)](https://github.com/Westenets/dvai-bridge/actions/workflows/smoke-real-models.yml) -->
-
-[![License](https://img.shields.io/badge/License-Commercial-blue.svg)](LICENSE) ![Node.js](https://img.shields.io/badge/Node.js-22+-green?logo=node.js) ![TypeScript](https://img.shields.io/badge/TypeScript-5.6+-blue?logo=typescript) ![Swift](https://img.shields.io/badge/Swift-5.9+-F05138?logo=swift) ![Kotlin](https://img.shields.io/badge/Kotlin-2.0+-7F52FF?logo=kotlin) ![Flutter](https://img.shields.io/badge/Flutter-3.39+-02569B?logo=flutter) ![.NET](https://img.shields.io/badge/.NET-10.0_LTS-512BD4?logo=dotnet)
-
-> **The local OpenAI server you embed inside your app.**
-> One library. One HTTP wire. Every platform. Zero install for your users.
-
-**Docs:** [dvai-bridge.deepvoiceai.co](https://dvai-bridge.deepvoiceai.co)
-
-```ts
-import { DVAI } from "@dvai-bridge/core";
-import OpenAI from "openai";
-
-const dvai = new DVAI({ backend: "transformers" });
-await dvai.initialize();
-
-const openai = new OpenAI({ baseURL: dvai.baseUrl, apiKey: "ignored" });
-await openai.chat.completions.create({
-  model: dvai.transformersModelId,
-  messages: [{ role: "user", content: "Hello!" }],
-});
-```
-
-That's it. A real OpenAI-compatible server is now running inside your app's
-own process. Point any OpenAI client — LangChain, the OpenAI SDK, the Vercel
-AI SDK, anything — at `dvai.baseUrl` and your agent code keeps working.
-
-Built by **[Deep Voice AI](https://deepvoiceai.co)**.
-
----
-
-## Why it exists
-
-Local AI works beautifully on a laptop with **Ollama + LangChain**. Then you
-try to ship the app and your users don't have Ollama. Mobile can't run it.
-Corporate IT won't add another daemon. So you reinvent the same plumbing —
-spawn an inference engine, bind a port, translate to OpenAI HTTP, handle
-CORS, manage lifecycle, wrap the accelerator of the day per platform — and
-do it all over again for every target OS.
-
-DVAI-Bridge is that plumbing, packaged as a library, for every client
-platform.
-
----
-
-## What you get
-
-- **One OpenAI HTTP surface.** Bound on `127.0.0.1` (or `0.0.0.0` for
-  device-to-device). Streaming, embeddings, models, recovery — all built in.
-- **Six SDKs.** `@dvai-bridge/core` + `react` + `vanilla` + `capacitor`,
-  `DVAIBridge` (Swift / iOS), `co.deepvoiceai:dvai-bridge` (Kotlin / Android),
-  `@dvai-bridge/react-native`, `dvai_bridge` (Flutter), `co.deepvoiceai.dvai-bridge` (.NET).
-- **Nine backends.** WebLLM, Transformers.js, llama.cpp, Apple Foundation
-  Models, MLX, CoreML / ANE, MediaPipe LLM, LiteRT, ONNX Runtime GenAI —
-  selected per-platform, invisible to your agent code.
-- **Native acceleration** wherever it runs: WebGPU in browsers, CUDA / Metal
-  / Vulkan / DirectML on desktop, ANE / Metal / MLX on iOS, NNAPI / QNN
-  Hexagon / GPU delegate on Android.
-- **Multimodal.** Text, image, audio, video — declarative loader for
-  cutting-edge models (Gemma 4, LLaVA, Idefics) without waiting for library
-  updates.
-- **Distributed inference (v3.0+).** Phone too slow? Offload to your laptop
-  on the same Wi-Fi via mDNS pairing — same OpenAI wire, transparent to
-  your code. Internet path via a self-hostable rendezvous server.
-- **DVAI Hub (v3.1+).** A first-party desktop utility that turns any device
-  into a strong-peer for the rest of your fleet. Brand-neutral install via
-  Homebrew / winget / GitHub Releases, OR fork it for your own branded
-  companion. Routes through Ollama / LM Studio / vLLM / llama-server /
-  llamafile if you've already got those running.
-- **Zero user install.** It's a library, not a daemon. `npm install`,
-  `cocoapods`, gradle — your CI already has the muscle for it.
-
----
-
-## Supported platforms
-
-| Stack | Package | Backends |
-| --- | --- | --- |
-| Browser (React, Vue, Svelte, vanilla JS) | `@dvai-bridge/core` + `react` / `vanilla` | WebLLM (WebGPU), Transformers.js (WebGPU / WASM SIMD) |
-| Node / Bun / Electron | `@dvai-bridge/core` | Transformers.js, native llama.cpp |
-| Capacitor hybrid mobile | `@dvai-bridge/capacitor` + backend slice | Native llama.cpp (Metal iOS, Vulkan / CPU Android) |
-| iOS native (Swift) | `DVAIBridge` (SPM / CocoaPods) | llama.cpp (Metal), CoreML / ANE, Apple Foundation Models, MLX |
-| Android native (Kotlin / Java) | `co.deepvoiceai:dvai-bridge` (AAR) | llama.cpp, MediaPipe LLM, LiteRT, NNAPI / QNN |
-| React Native (≥0.77, TurboModule) | `@dvai-bridge/react-native` | All iOS + Android backends (delegates) |
-| Flutter (≥3.39) | `dvai_bridge` (pub.dev) | All iOS + Android backends (Pigeon channels) |
-| .NET 10 LTS (MAUI / Avalonia / WinUI / Catalyst / desktop) | `co.deepvoiceai.dvai-bridge*` (NuGet) | iOS / Android delegate to native; desktop = llama.cpp + ONNX Runtime GenAI + ML.NET |
-
-Full quickstart per platform: [dvai-bridge.deepvoiceai.co/guide/getting-started](https://dvai-bridge.deepvoiceai.co/guide/getting-started)
-
----
-
-## Examples
-
-```ts
-// React
-import { DVAIProvider, useDVAI } from "@dvai-bridge/react";
-<DVAIProvider config={{ backend: "transformers" }}>
-  <Chat />
-</DVAIProvider>;
-function Chat() {
-  const { isReady, baseUrl } = useDVAI();
-  return isReady ? <div>Local AI live at {baseUrl}</div> : <Loading />;
-}
-```
-
-```swift
-// iOS
-let server = try await DVAIBridge.shared.start()
-// server.baseUrl = "http://127.0.0.1:38883/v1"
-```
-
-```kotlin
-// Android
-val server = DVAIBridge.start(context)
-// server.baseUrl = "http://127.0.0.1:38883/v1"
-```
-
-```dart
-// Flutter
-final state = await DVAIBridge.instance.start(
-  backend: BackendKind.auto,
-  modelPath: '/path/to/model.gguf',
-);
-// state.baseUrl = "http://127.0.0.1:38883/v1"
-```
-
-```csharp
-// .NET
-var server = await DVAIBridge.Shared.StartAsync(new StartOptions {
-    Backend = BackendKind.Auto,
-    ModelPath = "/path/to/model.gguf",
-});
-// server.BaseUrl = "http://127.0.0.1:38883/v1"
-```
-
-Multimodal, streaming, embeddings, distributed offload, the Hub —
-everything's at the [docs site](https://dvai-bridge.deepvoiceai.co).
-
----
-
-## What's new in v3.1
-
-- **DVAI Hub** — Tauri desktop utility that's the strong-peer side of v3
-  distributed inference. `brew install deepvoiceai/dvai-hub/dvai-hub` (or
-  `winget install DeepVoiceAI.DVAIHub`) → mobile apps on the same Wi-Fi
-  pair with it and offload heavy inference. [Guide →](https://dvai-bridge.deepvoiceai.co/guide/dvai-hub)
-- **External-engine bridge.** Hub surfaces Ollama / LM Studio / vLLM /
-  llama-server / llamafile as additional backend pools so paired apps
-  serve from whatever's already cached. Opt-in per engine.
-- **Strict substitution policy.** Models with mismatched family / version /
-  size / type are refused by default; quant-only mismatches gated behind a
-  per-pairing `preferBetterQuant` flag. No silent mis-routing.
-- **HMAC-signed identity** on `/v1/chat/completions`. Per-app audit logs
-  surface who served what, with structured `(appId, peerDeviceId,
-  engine, requestedModel, servedModel, outcome)` rows.
-- **Library finalization.** `httpBindHost` (LAN bind), `chatCompletionInterceptor`
-  (extension point), HMAC primitives re-exported, `/v1/dvai/*` routes
-  actually dispatched, TransformersBackend Node-mode device fix.
-  [Migration v3.0 → v3.1 →](https://dvai-bridge.deepvoiceai.co/migration/v3.0-to-v3.1)
-
----
-
-## Robustness
-
-Streaming-correct (SSE passthrough + blank-chunk detection), generation
-timeout, automatic engine-state recovery on fatal errors, port fallback,
-worker offloading, Private Network Access ready, CORS configured. The
-boring substrate so your agent code never has to think about it.
-
----
-
-## Licensing
-
-Dual: **free for development & personal use** on `localhost` (verified at
-runtime). **Commercial use** requires a license key — `info@deepvoiceai.co`.
-
----
-
-## Contributing
-
-PRs welcome.
-
-```bash
-pnpm install
-pnpm build
-bash scripts/build-all.sh   # full matrix (auto-skips per-host)
-```
-
-[`CONTRIBUTING.md`](./CONTRIBUTING.md) for the PR flow. Per-platform
-contributor docs (iOS / Android / RN / Flutter / .NET) under
-[`docs/development/`](./docs/development/).
-
----
-
-© Deep Voice AI Limited. All rights reserved.