docs(leap-sdk): bump SDK page version pins + exhaustive MessageResponse switches

Two related changes across the remaining SDK pages:

1. Version pins bumped 0.10.7 → 0.10.8 — every `ai.liquid.leap:*` Gradle
   coordinate, SPM `from: "0.10.7"`, `nativelibs` plugin version, the
   `gradle/libs.versions.toml` snippet, Maven `<version>` block,
   XCFramework binary-target URLs, and `*-natives@zip` classifier
   coordinates. Quick-start's XCFramework SHA-256 values were replaced
   with `<copy from the v0.10.8 release page>` placeholders since the
   v0.10.8 GitHub release wasn't live when these were drafted; a
   follow-up pass needs to drop in the real checksums.

2. Every Kotlin `when (response)` over `MessageResponse` and every Swift
   `switch onEnum(of: response)` that previously used an `else -> {}` /
   `else -> Unit` / `default: break` fallback was expanded into explicit
   arms covering all six `MessageResponse` subtypes (`Chunk`,
   `ReasoningChunk`, `FunctionCalls`, `AudioSample`, `Complete`, and the
   new `Error` case from v0.10.8). Rationale: the example code is what
   readers copy into their apps; under v0.10.8 a fallback-based pattern
   silently swallows the new `Error` arm on Kotlin (statement-`when`
   compiles with a warning, expression-`when` won't) and on Swift the
   compiler enforces exhaustiveness, so call sites stop compiling.
   Showing the explicit `.error` arm in every example puts the
   migration path right next to the surrounding code.

Per-file detail:

- `quick-start.mdx` — bump every dependency pin; XCFramework
  binary-target SHA-256s replaced with placeholders; iOS Swift
  streaming example gains `case .error(let err)` arm; Android Kotlin
  `when` gains `is MessageResponse.Error -> _errorMessage.value = ...`
  arm; Kotlin/Native quick-start `when` expanded from 2-arm + `else`
  to 6 explicit arms with `Error → System.err.println(...)`.
- `ai-agent-usage-guide.mdx` — first handler example: Swift `switch
  onEnum(of:)` gains `case .error(let err): log(...)`; Kotlin `when`
  gains `is MessageResponse.Error -> Log.e(...)`. ChatViewModel example:
  same treatment, Kotlin path writes to `_errorMessage` so SwiftUI /
  Compose can surface it. Agent-loop example: Swift `default: break`
  replaced with `case .reasoningChunk, .audioSample: break` +
  `case .error(let err): throw NSError(...)`; Kotlin `else -> {}`
  replaced with explicit no-op arms plus
  `is MessageResponse.Error -> throw response.throwable`.
- `function-calling.mdx` — Swift exhaustive case-list gains `.error`
  arm; Kotlin `when` expanded with explicit `ReasoningChunk` /
  `AudioSample` no-ops plus `Error → Log.e(...)`.
- `cloud-ai-comparison.mdx` — Swift case-list gains `.error` arm
  surfacing via `print(...)`; Kotlin `when` expanded to 6 arms.
- `voice-assistant.mdx` — bump SPM `from:` and Gradle pins; bump
  "stable release notes through v0.10.7" → "through v0.10.8"; Swift
  audio-streaming `switch` gains `case .error(let err): throw
  NSError(...)` so the surrounding `VoiceConversation` machinery
  surfaces the failure; Kotlin `when` expanded with explicit no-op
  arms plus `Error → throw response.throwable` matching the Swift
  shape.
- `desktop-platforms.mdx` — bump every dependency pin, plugin
  version, Maven `<version>`, natives-zip coords, and the XCFramework
  binary-target URL; Kotlin K/N quick-start `when` expanded to 6
  arms.
- `model-loading.mdx` — rewrite the "Sideloaded
  `LiquidInferenceEngineOptions` (URL-based load)" callout from "does
  NOT ship a Swift convenience init in v0.10.7" to "...through v0.10.8"
  so the version stays accurate — v0.10.8's SKIE-on-openai-client
  change didn't touch `LiquidInferenceEngineOptions`, so the all-12-
  fields situation is unchanged.

Author: iamstuffed

deployment/on-device/sdk/ai-agent-usage-guide.mdx

@@ -58,6 +58,8 @@ Every agent has the same shape: send a `ChatMessage`, iterate the response strea
             if let stats = completion.stats {
                 log("Done: \(stats.totalTokens) tokens at \(stats.tokenPerSecond) tok/s")
             }
+        case .error(let err):
+            log("Generation failed: \(err.message)")
         }
     }
     ```
@@ -76,6 +78,7 @@ Every agent has the same shape: send a `ChatMessage`, iterate the response strea
                 _text.value = ""
                 Log.d(TAG, "Done: ${response.stats?.totalTokens} tokens at ${response.stats?.tokenPerSecond} tok/s")
             }
+            is MessageResponse.Error -> Log.e(TAG, "Generation failed: ${response.message}", response.throwable)
         }
     }
     ```
@@ -103,8 +106,10 @@ The defining feature of an agent: the model emits `FunctionCalls`, you execute t
                     toolCalls.append(contentsOf: payload.functionCalls)
                 case .complete:
                     break
-                default:
+                case .reasoningChunk, .audioSample:
                     break
+                case .error(let err):
+                    throw NSError(domain: "AgentLoop", code: 1, userInfo: [NSLocalizedDescriptionKey: err.message])
                 }
             }
 
@@ -139,7 +144,10 @@ The defining feature of an agent: the model emits `FunctionCalls`, you execute t
                 when (response) {
                     is MessageResponse.Chunk -> appendUI(response.text)
                     is MessageResponse.FunctionCalls -> toolCalls.addAll(response.functionCalls)
-                    else -> {}
+                    is MessageResponse.ReasoningChunk -> {}
+                    is MessageResponse.AudioSample -> {}
+                    is MessageResponse.Complete -> {}
+                    is MessageResponse.Error -> throw response.throwable
                 }
             }
 
@@ -317,6 +325,8 @@ A `ChatViewModel` that loads the model, registers a tool, drives generation, and
                 if let stats = c.stats {
                     print("\nFinished — \(stats.totalTokens) tokens at \(stats.tokenPerSecond) tok/s")
                 }
+            case .error(let err):
+                errorMessage = "Generation failed: \(err.message)"
             }
         }
     }
@@ -408,6 +418,7 @@ A `ChatViewModel` that loads the model, registers a tool, drives generation, and
                 is MessageResponse.FunctionCalls -> response.functionCalls.forEach { dispatch(it) }
                 is MessageResponse.AudioSample -> audioRenderer.enqueue(response.samples, response.sampleRate)
                 is MessageResponse.Complete -> Log.d(TAG, "Done: ${response.stats?.totalTokens} tokens")
+                is MessageResponse.Error -> _errorMessage.value = "Generation failed: ${response.message}"
             }
         }
 

deployment/on-device/sdk/cloud-ai-comparison.mdx

@@ -127,6 +127,8 @@ Cloud APIs deliver deltas; you concatenate them. LEAP delivers `MessageResponse`
             print("\nDone! Tokens: \(completion.stats?.totalTokens ?? 0)")
         case .reasoningChunk, .audioSample, .functionCalls:
             break
+        case .error(let err):
+            print("\nGeneration failed: \(err.message)")
         }
     }
     ```
@@ -137,7 +139,10 @@ Cloud APIs deliver deltas; you concatenate them. LEAP delivers `MessageResponse`
         when (response) {
             is MessageResponse.Chunk -> print(response.text)
             is MessageResponse.Complete -> println("\nDone! Tokens: ${response.stats?.totalTokens}")
-            else -> {}
+            is MessageResponse.ReasoningChunk -> {}
+            is MessageResponse.FunctionCalls -> {}
+            is MessageResponse.AudioSample -> {}
+            is MessageResponse.Error -> println("\nGeneration failed: ${response.message}")
         }
     }.collect()
     ```

deployment/on-device/sdk/desktop-platforms.mdx

@@ -49,13 +49,13 @@ The JVM target supports Kotlin and Java projects on macOS (Apple Silicon), Linux
     }
 
     dependencies {
-        implementation("ai.liquid.leap:leap-sdk:0.10.7")
+        implementation("ai.liquid.leap:leap-sdk:0.10.8")
 
         // Optional: OpenAI-compatible cloud chat client (JVM support added in v0.10.7)
-        // implementation("ai.liquid.leap:leap-openai-client:0.10.7")
+        // implementation("ai.liquid.leap:leap-openai-client:0.10.8")
 
         // Optional: Compose Multiplatform voice widget (also runs on JVM)
-        // implementation("ai.liquid.leap:leap-ui:0.10.7")
+        // implementation("ai.liquid.leap:leap-ui:0.10.8")
     }
 
     application {
@@ -75,7 +75,7 @@ The JVM target supports Kotlin and Java projects on macOS (Apple Silicon), Linux
     }
 
     dependencies {
-        implementation 'ai.liquid.leap:leap-sdk:0.10.7'
+        implementation 'ai.liquid.leap:leap-sdk:0.10.8'
     }
 
     application {
@@ -89,7 +89,7 @@ The JVM target supports Kotlin and Java projects on macOS (Apple Silicon), Linux
       <dependency>
         <groupId>ai.liquid.leap</groupId>
         <artifactId>leap-sdk-jvm</artifactId>
-        <version>0.10.7</version>
+        <version>0.10.8</version>
       </dependency>
     </dependencies>
     ```
@@ -137,7 +137,10 @@ fun main() = runBlocking {
         when (response) {
             is MessageResponse.Chunk -> print(response.text)
             is MessageResponse.Complete -> println("\n[${response.stats?.totalTokens} tokens]")
-            else -> {}
+            is MessageResponse.ReasoningChunk -> {}
+            is MessageResponse.FunctionCalls -> {}
+            is MessageResponse.AudioSample -> {}
+            is MessageResponse.Error -> System.err.println("\n[error] ${response.message}")
         }
     }
 
@@ -194,11 +197,11 @@ dependencyResolutionManagement {
 // build.gradle.kts
 plugins {
     kotlin("multiplatform") version "2.3.20"
-    id("ai.liquid.leap.nativelibs") version "0.10.7"
+    id("ai.liquid.leap.nativelibs") version "0.10.8"
 }
 
 dependencies {
-    implementation("ai.liquid.leap:leap-sdk:0.10.7")
+    implementation("ai.liquid.leap:leap-sdk:0.10.8")
 }
 
 kotlin {
@@ -227,7 +230,7 @@ plugins {
 }
 
 dependencies {
-    implementation("ai.liquid.leap:leap-sdk:0.10.7")
+    implementation("ai.liquid.leap:leap-sdk:0.10.8")
 }
 
 val nativesDir = layout.buildDirectory.dir("bin/linuxX64/releaseExecutable")
@@ -241,7 +244,7 @@ kotlin {
 
 val leapSdkNatives by configurations.creating
 dependencies {
-    leapSdkNatives("ai.liquid.leap:leap-sdk-linuxx64:0.10.7:natives@zip")
+    leapSdkNatives("ai.liquid.leap:leap-sdk-linuxx64:0.10.8:natives@zip")
 }
 
 val installLeapNatives by tasks.registering(Copy::class) {
@@ -259,8 +262,8 @@ tasks.named("linkReleaseExecutableLinuxX64") { dependsOn(installLeapNatives) }
 
 The Maven coordinates for the `-natives.zip` artifacts:
 
-- `ai.liquid.leap:leap-sdk-linuxx64:0.10.7:natives@zip`
-- `ai.liquid.leap:leap-sdk-linuxarm64:0.10.7:natives@zip`
+- `ai.liquid.leap:leap-sdk-linuxx64:0.10.8:natives@zip`
+- `ai.liquid.leap:leap-sdk-linuxarm64:0.10.8:natives@zip`
 
 ## Windows native (MinGW x64)
 
@@ -269,11 +272,11 @@ The same Kotlin/Native flow works for Windows x86_64 via the MinGW-w64 toolchain
 ```kotlin
 plugins {
     kotlin("multiplatform") version "2.3.20"
-    id("ai.liquid.leap.nativelibs") version "0.10.7"
+    id("ai.liquid.leap.nativelibs") version "0.10.8"
 }
 
 dependencies {
-    implementation("ai.liquid.leap:leap-sdk:0.10.7")
+    implementation("ai.liquid.leap:leap-sdk:0.10.8")
 }
 
 kotlin {
@@ -291,7 +294,7 @@ The plugin installs `inference_engine.dll`, `libinference_engine_llamacpp_backen
 
 The Maven coordinates for the `-natives.zip` artifact:
 
-- `ai.liquid.leap:leap-sdk-mingwx64:0.10.7:natives@zip`
+- `ai.liquid.leap:leap-sdk-mingwx64:0.10.8:natives@zip`
 
 <Info>
 **Building from macOS or Linux for Windows?** Kotlin/Native does not support cross-compiling to MinGW from a non-Windows host as of 2.3.20 — the build must run on Windows (native or in CI). GitHub Actions `windows-latest` works without extra setup.
@@ -316,7 +319,7 @@ Identical Swift API to iOS — same `ModelDownloader`, `Conversation`, `ChatMess
 ```swift
 .binaryTarget(
   name: "LeapSDK",
-  url: "https://github.com/Liquid4All/leap-sdk/releases/download/v0.10.7/LeapSDK.xcframework.zip",
+  url: "https://github.com/Liquid4All/leap-sdk/releases/download/v0.10.8/LeapSDK.xcframework.zip",
   checksum: "6f2721aa45d7555646f78cbcaedb57aba3d869f56b24d681ad332846e131ae3d"
 )
 ```
@@ -329,8 +332,8 @@ If you're targeting macOS as a JVM host — for example with Compose Multiplatfo
 
 ```kotlin
 dependencies {
-    implementation("ai.liquid.leap:leap-sdk:0.10.7")
-    implementation("ai.liquid.leap:leap-ui:0.10.7") // Compose voice widget runs on JVM too
+    implementation("ai.liquid.leap:leap-sdk:0.10.8")
+    implementation("ai.liquid.leap:leap-ui:0.10.8") // Compose voice widget runs on JVM too
 }
 ```
 

deployment/on-device/sdk/function-calling.mdx

@@ -108,6 +108,8 @@ Function calls arrive as the `MessageResponse.FunctionCalls` variant on both pla
             }
         case .chunk, .reasoningChunk, .audioSample, .complete:
             break
+        case .error(let err):
+            print("Generation failed: \(err.message)")
         }
     }
     ```
@@ -134,7 +136,9 @@ Function calls arrive as the `MessageResponse.FunctionCalls` variant on both pla
                 // Tool calls are also surfaced on the assembled assistant message:
                 response.fullMessage.functionCalls?.forEach { /* ... */ }
             }
-            else -> {}
+            is MessageResponse.ReasoningChunk -> {}
+            is MessageResponse.AudioSample -> {}
+            is MessageResponse.Error -> Log.e(TAG, "Generation failed: ${response.message}", response.throwable)
         }
     }.collect()
     ```

deployment/on-device/sdk/model-loading.mdx

@@ -527,7 +527,7 @@ Per-load runtime overrides. Default values come from the model bundle's manifest
         .with(cacheOptions: .enabled(path: cacheDir.path))
     ```
 
-    **Sideloaded `LiquidInferenceEngineOptions` (URL-based load).** The non-manifest variant does NOT ship a Swift convenience init in v0.10.7 — the K/N-generated designated init takes all 12 fields. Either build it fully (verbose) or use `loadSimpleModel(model: ModelSource(...))` on `ModelDownloader` (preferred for new code; see the Sideloaded files section). The builder `.with(...)` overloads exist but they create a new instance internally via the same 12-arg init, so you still need a fully-built starting instance — there is no `LiquidInferenceEngineOptions(bundlePath: …)` 1-arg form today.
+    **Sideloaded `LiquidInferenceEngineOptions` (URL-based load).** The non-manifest variant does NOT ship a Swift convenience init through v0.10.8 — the K/N-generated designated init takes all 12 fields. Either build it fully (verbose) or use `loadSimpleModel(model: ModelSource(...))` on `ModelDownloader` (preferred for new code; see the Sideloaded files section). The builder `.with(...)` overloads exist but they create a new instance internally via the same 12-arg init, so you still need a fully-built starting instance — there is no `LiquidInferenceEngineOptions(bundlePath: …)` 1-arg form today.
   </Tab>
   <Tab title="Kotlin (all platforms)">
     ```kotlin

deployment/on-device/sdk/quick-start.mdx

@@ -3,7 +3,7 @@ title: "Quick Start"
 description: "Install the LEAP SDK on iOS, macOS, Android, JVM, Linux, or Windows — same API everywhere."
 ---
 
-Latest version: `v0.10.7`
+Latest version: `v0.10.8`
 
 The Leap SDK is a Kotlin Multiplatform library: the same `ModelRunner` / `Conversation` / `MessageResponse` API runs on every supported target. The code differs only in **language** (Swift vs. Kotlin) and **packaging** (SPM, Gradle, or Kotlin/Native plugin) — the call shapes are identical. For background on what the SDK is and what first-class LFM support means in practice, see the [Overview](/deployment/on-device/sdk/overview).
 
@@ -68,7 +68,7 @@ The Leap SDK is a Kotlin Multiplatform library: the same `ModelRunner` / `Conver
 
     1. In Xcode choose **File → Add Package Dependencies**.
     2. Enter `https://github.com/Liquid4All/leap-sdk.git`.
-    3. Select the `0.10.7` release (or newer).
+    3. Select the `0.10.8` release (or newer).
     4. Add the products you need to your app target.
 
     The package vends five products. Most apps only need one or two:
@@ -94,7 +94,7 @@ The Leap SDK is a Kotlin Multiplatform library: the same `ModelRunner` / `Conver
     </Info>
 
     <Accordion title="Pin to explicit binary XCFrameworks">
-      For explicit pinning, declare each framework as a `.binaryTarget` in your `Package.swift`. The XCFramework assets live on the `Liquid4All/leap-sdk` v0.10.7 release page — copy the SHA-256 values from there.
+      For explicit pinning, declare each framework as a `.binaryTarget` in your `Package.swift`. The XCFramework assets live on the `Liquid4All/leap-sdk` v0.10.8 release page — copy the SHA-256 values from there.
 
       <Warning>
       The constrained-generation macros (`@Generatable`, `@Guide`) are Swift macros, not XCFrameworks — they ship as the `LeapSDKMacros` source target inside the SPM package and **cannot be installed as a `.binaryTarget`**. If you need them, use the standard SPM package URL above (or add the `LeapSDKMacros` source target separately on top of your binary targets).
@@ -103,23 +103,23 @@ The Leap SDK is a Kotlin Multiplatform library: the same `ModelRunner` / `Conver
       ```swift
       .binaryTarget(
         name: "LeapSDK",
-        url: "https://github.com/Liquid4All/leap-sdk/releases/download/v0.10.7/LeapSDK.xcframework.zip",
-        checksum: "6f2721aa45d7555646f78cbcaedb57aba3d869f56b24d681ad332846e131ae3d"
+        url: "https://github.com/Liquid4All/leap-sdk/releases/download/v0.10.8/LeapSDK.xcframework.zip",
+        checksum: "<copy from the v0.10.8 release page>"
       ),
       .binaryTarget(
         name: "LeapModelDownloader",
-        url: "https://github.com/Liquid4All/leap-sdk/releases/download/v0.10.7/LeapModelDownloader.xcframework.zip",
-        checksum: "f649aa6c1aa3e87bbeb1073d5aeeb7224879359a24b18eeccc665d24abc725d8"
+        url: "https://github.com/Liquid4All/leap-sdk/releases/download/v0.10.8/LeapModelDownloader.xcframework.zip",
+        checksum: "<copy from the v0.10.8 release page>"
       ),
       .binaryTarget(
         name: "LeapOpenAIClient",
-        url: "https://github.com/Liquid4All/leap-sdk/releases/download/v0.10.7/LeapOpenAIClient.xcframework.zip",
-        checksum: "79bc5443a1cce6fcd4c49c91eeb85727034aaca10d3ef69582c061989c3d9b70"
+        url: "https://github.com/Liquid4All/leap-sdk/releases/download/v0.10.8/LeapOpenAIClient.xcframework.zip",
+        checksum: "<copy from the v0.10.8 release page>"
       ),
       .binaryTarget(
         name: "LeapUi",
-        url: "https://github.com/Liquid4All/leap-sdk/releases/download/v0.10.7/LeapUi.xcframework.zip",
-        checksum: "f1b198cef88c2a37eaf6dc1f36395d6aed024b0c6c2b43724d942e25b60d22e0"
+        url: "https://github.com/Liquid4All/leap-sdk/releases/download/v0.10.8/LeapUi.xcframework.zip",
+        checksum: "<copy from the v0.10.8 release page>"
       ),
       ```
 
@@ -131,14 +131,14 @@ The Leap SDK is a Kotlin Multiplatform library: the same `ModelRunner` / `Conver
 
     ```kotlin
     dependencies {
-      implementation("ai.liquid.leap:leap-sdk:0.10.7")
-      implementation("ai.liquid.leap:leap-model-downloader:0.10.7") // Android background downloads
+      implementation("ai.liquid.leap:leap-sdk:0.10.8")
+      implementation("ai.liquid.leap:leap-model-downloader:0.10.8") // Android background downloads
 
       // Optional: OpenAI-compatible cloud chat client
-      // implementation("ai.liquid.leap:leap-openai-client:0.10.7")
+      // implementation("ai.liquid.leap:leap-openai-client:0.10.8")
 
       // Optional: Voice assistant widget (Compose Multiplatform)
-      // implementation("ai.liquid.leap:leap-ui:0.10.7")
+      // implementation("ai.liquid.leap:leap-ui:0.10.8")
     }
     ```
 
@@ -147,7 +147,7 @@ The Leap SDK is a Kotlin Multiplatform library: the same `ModelRunner` / `Conver
 
       ```toml
       [versions]
-      leapSdk = "0.10.7"
+      leapSdk = "0.10.8"
 
       [libraries]
       leap-sdk = { module = "ai.liquid.leap:leap-sdk", version.ref = "leapSdk" }
@@ -191,11 +191,11 @@ The Leap SDK is a Kotlin Multiplatform library: the same `ModelRunner` / `Conver
     }
 
     dependencies {
-        implementation("ai.liquid.leap:leap-sdk:0.10.7")
+        implementation("ai.liquid.leap:leap-sdk:0.10.8")
 
         // Optional:
-        // implementation("ai.liquid.leap:leap-openai-client:0.10.7")
-        // implementation("ai.liquid.leap:leap-ui:0.10.7") // Compose for Desktop voice widget
+        // implementation("ai.liquid.leap:leap-openai-client:0.10.8")
+        // implementation("ai.liquid.leap:leap-ui:0.10.8") // Compose for Desktop voice widget
     }
     ```
 
@@ -222,11 +222,11 @@ The Leap SDK is a Kotlin Multiplatform library: the same `ModelRunner` / `Conver
     // build.gradle.kts
     plugins {
         kotlin("multiplatform") version "2.3.20"
-        id("ai.liquid.leap.nativelibs") version "0.10.7"
+        id("ai.liquid.leap.nativelibs") version "0.10.8"
     }
 
     dependencies {
-        implementation("ai.liquid.leap:leap-sdk:0.10.7")
+        implementation("ai.liquid.leap:leap-sdk:0.10.8")
     }
 
     kotlin {
@@ -378,7 +378,10 @@ The recommended path is **manifest-based** loading. On every platform, the platf
             when (resp) {
                 is MessageResponse.Chunk -> print(resp.text)
                 is MessageResponse.Complete -> println("\n[done]")
-                else -> {}
+                is MessageResponse.ReasoningChunk -> {}
+                is MessageResponse.FunctionCalls -> {}
+                is MessageResponse.AudioSample -> {}
+                is MessageResponse.Error -> System.err.println("\n[error] ${resp.message}")
             }
         }
 
@@ -473,6 +476,10 @@ Both platforms expose the same streaming shape: an async sequence of `MessageRes
                 return nil
             }.joined()
             print("Final:", text)
+        case .error(let err):
+            // In-band failure (v0.10.8+) — SKIE bridges `Flow` with `Failure = Never`,
+            // so generation failures arrive here instead of on the `catch` block above.
+            print("Generation failed:", err.message)
         }
     }
     ```
@@ -489,6 +496,7 @@ Both platforms expose the same streaming shape: an async sequence of `MessageRes
                         is MessageResponse.FunctionCalls -> handleFunctionCalls(response.functionCalls)
                         is MessageResponse.AudioSample -> audioRenderer.enqueue(response.samples, response.sampleRate)
                         is MessageResponse.Complete -> Log.d(TAG, "Done. Stats: ${response.stats}")
+                        is MessageResponse.Error -> _errorMessage.value = "Generation failed: ${response.message}"
                     }
                 }
                 ?.onCompletion { _isGenerating.value = false }