chore: prepare 0.8.24 release

CHANGELOG.md

@@ -1,8 +1,18 @@
-## Unreleased
+## 0.8.24
 
 * Fix fresh macOS Flutter test/build dependency scanning while retaining the
   Apple companion ABI and local-override guards.
 
+* Keep repository writer checks independent of generated website output.
+
+* Preserve failure-phase diagnostics in the physical iOS speech test harness.
+
+* Aligned the default WebGPU bridge assets to `v0.1.43` (unchanged from
+  0.8.23), retaining Web/native llama.cpp
+  `v0.4.0@5266f24da75dc449bd56cbed7addb9c8e4a6a73e` parity. Web
+  `@litert-lm/core@0.15.0` and native LiteRT pins are unchanged. Immutable
+  manifest: `111eefc3588842cebfe665b363378edca34924764610263e1eda5280dfcfaa27`.
+
 ## 0.8.23
 
 * Fail Apple builds before native symbol lookup when the resolved llama.cpp

README.md

@@ -55,13 +55,13 @@ For Dart or Flutter apps:
 
 ```yaml
 dependencies:
-  llamadart: ^0.8.23
+  llamadart: ^0.8.24
 ```
 
 Flutter iOS/macOS apps that should link Apple XCFrameworks through Swift
 Package Manager should also add the runtime companion packages they need:
 
-Pair companion `0.0.18` with core `0.8.23` for matching llama.cpp v0.4.0
+Pair companion `0.0.18` with core `0.8.24` for matching llama.cpp v0.4.0
 bindings. Keep core `0.8.22` paired with companion `0.0.17`.
 
 Apple builds verify the resolved companion's SwiftPM runtime pin before native
@@ -71,7 +71,7 @@ overrides fail the build; resolve the matching companion and rerun
 
 ```yaml
 dependencies:
-  llamadart: ^0.8.23
+  llamadart: ^0.8.24
   llamadart_llama_cpp_flutter: ^0.0.18 # GGUF / llama.cpp
   llamadart_litert_lm_flutter: ^0.0.10 # Apple .litertlm / LiteRT-LM targets
 ```

example/chat_app/pubspec.lock

@@ -413,7 +413,7 @@ packages:
       path: "../.."
       relative: true
     source: path
-    version: "0.8.23"
+    version: "0.8.24"
   llamadart_litert_lm_flutter:
     dependency: "direct main"
     description:

packages/llamadart_litert_lm_flutter/README.md

@@ -15,7 +15,7 @@ also request an x86_64 Simulator slice must exclude x86_64 for LiteRT-LM builds.
 
 ```yaml
 dependencies:
-  llamadart: ^0.8.23
+  llamadart: ^0.8.24
   llamadart_litert_lm_flutter: ^0.0.10
 ```
 

packages/llamadart_llama_cpp_flutter/README.md

@@ -7,12 +7,12 @@ Add this package to a Flutter iOS/macOS app when the app should link the
 prebuilt llama.cpp Apple XCFramework through SwiftPM instead of relying on the
 core package's native-assets fallback.
 
-Pair companion `0.0.18` with core `0.8.23` for matching llama.cpp v0.4.0
+Pair companion `0.0.18` with core `0.8.24` for matching llama.cpp v0.4.0
 bindings. Keep core `0.8.22` paired with companion `0.0.17`.
 
 ```yaml
 dependencies:
-  llamadart: ^0.8.23
+  llamadart: ^0.8.24
   llamadart_llama_cpp_flutter: ^0.0.18
 ```
 

pubspec.yaml

@@ -1,6 +1,6 @@
 name: llamadart
 description: Dart and Flutter local LLM inference with llama.cpp GGUF and LiteRT-LM across native platforms and web.
-version: 0.8.23
+version: 0.8.24
 homepage: https://github.com/leehack/llamadart
 repository: https://github.com/leehack/llamadart
 issue_tracker: https://github.com/leehack/llamadart/issues

website/docs/changelog/recent-releases.md

@@ -7,11 +7,21 @@ For canonical full release notes, use:
 
 - [`CHANGELOG.md`](https://github.com/leehack/llamadart/blob/main/CHANGELOG.md)
 
-## Unreleased
+## 0.8.24
 
 - Fix fresh macOS Flutter test/build dependency scanning while retaining the
   Apple companion ABI and local-override guards.
 
+- Keep repository writer checks independent of generated website output.
+
+- Preserve failure-phase diagnostics in the physical iOS speech test harness.
+
+- Aligned default WebGPU bridge assets to `v0.1.43` (unchanged from
+  0.8.23), retaining Web/native llama.cpp
+  `v0.4.0@5266f24da75dc449bd56cbed7addb9c8e4a6a73e` parity. Web
+  `@litert-lm/core@0.15.0` and native LiteRT pins are unchanged. Immutable
+  manifest: `111eefc3588842cebfe665b363378edca34924764610263e1eda5280dfcfaa27`.
+
 ## 0.8.23
 
 - Fail Apple builds before native symbol lookup when the resolved llama.cpp

website/docs/getting-started/installation.md

@@ -27,13 +27,13 @@ In Xcode, set `IPHONEOS_DEPLOYMENT_TARGET = 16.4` or
 
 ```yaml
 dependencies:
-  llamadart: ^0.8.23
+  llamadart: ^0.8.24
 ```
 
 For Flutter iOS/macOS apps that should link Apple XCFrameworks through Swift
 Package Manager, also add the runtime companion packages you need:
 
-Pair companion `0.0.18` with core `0.8.23` for matching llama.cpp v0.4.0
+Pair companion `0.0.18` with core `0.8.24` for matching llama.cpp v0.4.0
 bindings. Keep core `0.8.22` paired with companion `0.0.17`.
 
 Apple builds verify the resolved companion's SwiftPM runtime pin before native
@@ -43,7 +43,7 @@ overrides fail the build; resolve the matching companion and rerun
 
 ```yaml
 dependencies:
-  llamadart: ^0.8.23
+  llamadart: ^0.8.24
   llamadart_llama_cpp_flutter: ^0.0.18 # GGUF / llama.cpp
   llamadart_litert_lm_flutter: ^0.0.10 # Apple .litertlm / LiteRT-LM targets
 ```