build(deps): bump flutter_gemma from 0.3.1 to 0.14.1

[dependabot]

Bumps flutter_gemma from 0.3.1 to 0.14.1.

Release notes

Sourced from flutter_gemma's releases.

Release v0.14.1

What's Changed

• Trim 600+ KB of junk from the pub publish archive by @​DenisovAV in DenisovAV/flutter_gemma#241
• docs: revise README for 0.14.0 — factual fixes + extract Legacy API by @​DenisovAV in DenisovAV/flutter_gemma#242
• 0.14.1: App Store fix (#245), Web FFI fix (#244), Gemma 4 native function calling by @​DenisovAV in DenisovAV/flutter_gemma#246

Full Changelog: DenisovAV/flutter_gemma@v0.14.0...v0.14.1

Release v0.14.0

What's Changed

• Release 0.13.3: fix macOS SIGSEGV, iOS pod install, Windows >2GB, iOS simulator build by @​DenisovAV in DenisovAV/flutter_gemma#221
• Fix iOS compile error and arm64 simulator build (#222, #216) by @​DenisovAV in DenisovAV/flutter_gemma#223
• Fix Qwen3 thinking mode (#224) by @​DenisovAV in DenisovAV/flutter_gemma#225
• Add CI workflow to build libLiteRtLm for Linux + Windows by @​DenisovAV in DenisovAV/flutter_gemma#234
• Fix Windows CI: clear ANDROID_NDK_HOME by @​DenisovAV in DenisovAV/flutter_gemma#235
• feat: make maxFunctionBufferLength configurable in createChat() by @​using-system in DenisovAV/flutter_gemma#230
• Release 0.13.6: ModelType.qwen3, Windows paths, removeDocument (#224, #233, #232) by @​DenisovAV in DenisovAV/flutter_gemma#231
• 0.14.0: Desktop FFI rewrite + iOS Metal GPU + sampler params fix by @​DenisovAV in DenisovAV/flutter_gemma#239

New Contributors

• @​using-system made their first contribution in DenisovAV/flutter_gemma#230

Full Changelog: DenisovAV/flutter_gemma@v0.13.3...v0.14.0

Native Libraries v0.10.2

LiteRT-LM native libraries built from source v0.10.2.

Platforms included (CI-built):

• Linux x86_64
• Linux arm64
• Windows x86_64

macOS/iOS/Android archives are uploaded separately after local builds.

Release v0.13.3

0.13.3

• Fix macOS SIGSEGV (#219): Per-conversation mutex in gRPC server prevents conversation.close() racing with sendMessageAsync on a native thread → use-after-free in C++ fixed
• Fix macOS desktop Metal accelerator: setup_desktop.sh now downloads libLiteRtMetalAccelerator.dylib from GitHub Release so GPU inference uses the Metal delegate instead of falling back to static C API
• Fix iOS pod install hanging (#220): Replaced TensorFlowLiteSwift (source pod — cloned entire TensorFlow repo) with direct TensorFlowLiteC C API in EmbeddingModel.swift
• Fix Windows >2 GB model error (#212): Clear error message when model file exceeds 2 GB on Windows (known upstream 32-bit stat() overflow in litertlm_jni.dll, google-ai-edge/LiteRT-LM#1494)
• Fix iOS arm64 simulator build (#216): Excluded arm64 from simulator archs to fix build on Apple Silicon Macs

Release v0.13.1

Changes

• LiteRT-LM 0.10.0: Updated Android and JVM SDK from 0.9.0 to 0.10.0
• Gemma 4 Thinking Mode: isThinking: true now works with Gemma 4 E2B/E4B models via extraContext and streaming thought channels
• Fix cancel download: Cancel download now works correctly (#196)

... (truncated)

Changelog

Sourced from flutter_gemma's changelog.

0.14.1

• Web build fix (#244): 0.14.0 broke web compilation by statically importing core/ffi/litert_lm_client.dart (which imports dart:ffi) through the flutter_gemma_interface.dart → mobile/flutter_gemma_mobile.dart chain. JS/Wasm targets cannot compile dart:ffi. Added conditional imports in mobile/flutter_gemma_mobile.dart that swap litert_lm_client.dart and ffi_inference_model.dart for *_stub.dart shims on dart.library.js_interop. The web plugin (FlutterGemmaWeb) registers itself as FlutterGemmaPlugin.instance before any FFI code path runs, so the stubs' constructors (which throw UnsupportedError) are never actually invoked on web.
• App Store fix (#245, ITMS-90432): 0.14.0 dropped lib*.dylib symlinks alongside the bundled .framework/ accelerators in Runner.app/Frameworks/ so LiteRT-LM's gpu_registry could dlopen them by basename — App Store Connect rejected those builds with "Unexpected file found in Frameworks". 0.14.1 patches the upstream LiteRT-LM source (runtime/components/sampler_factory.cc and litert/runtime/accelerators/gpu_registry.cc) to load Apple platform accelerators via @executable_path/../Frameworks/<X>.framework/<X> (macOS) / @executable_path/Frameworks/<X>.framework/<X> (iOS) instead of libX.dylib. Native Assets bundles the framework bundles correctly out of the box; no host-side Podfile symlinks needed. Patch applied during local Bazel rebuild — see native/litert_lm/patch_c_api.sh section 10.
• Gemma 4 native function calling: New ModelType.gemma4 routes tool definitions to LiteRT-LM SDK via litert_lm_conversation_config_set_tools (OpenAI Chat Completions JSON). SDK applies chat_template.jinja through minja, renders native <|tool>declaration:...<tool|> tokens, and parses the model's <|tool_call>...<tool_call|> response back into structured tool_calls JSON. flutter_gemma reads the result via SdkResponseParser.extractToolCalls (handles parallel calls and the multimodal content[] path) and returns FunctionCallResponse to the app — no Dart-side prompt engineering needed.
• Escape token cleanup: Strips leftover <|"|> Gemma 4 escape tokens from string arguments (recursively, including nested maps/lists).
• example/lib/models/model.dart: Gemma 4 E2B / E4B entries switched to modelType: ModelType.gemma4.

0.14.0

• Desktop FFI rewrite: macOS, Linux, Windows now run LiteRT-LM directly via dart:ffi against the C API. Removed Kotlin/JVM gRPC server, Azul Zulu JRE 24 download, and litertlm-server.jar bundling. Engine creation ~2 s (was ~10–15 s incl. JVM cold-start)
• iOS GPU acceleration: Metal delegate for .litertlm models on iPhone (Gemma 3 1B, Gemma 3n E2B, Gemma 4 E2B). Multimodal vision + audio work on device
• Linux + Windows GPU: WebGPU/Vulkan on Linux, WebGPU/DX12 on Windows; DXC runtime (dxil.dll + dxcompiler.dll v1.9.2602) bundled in the Windows native archive — no manual install required
• Android: drop Kotlin LiteRtLm dependency — .litertlm models on Android now go through the same Dart FFI path as desktop/iOS (was com.google.ai.edge.litertlm:litertlm-android AAR before). MediaPipe stays for .task/.bin models
• iOS Simulator: CPU-only — Metal sim has 256 MB single-allocation cap, LLM weight tensors exceed it
• Unified FFI client: All five platforms (Android, iOS, macOS, Linux, Windows) share LiteRtLmFfiClient (lib/core/ffi/)
• Native log capture: stream_proxy_redirect_stderr exposes glog/abseil output on iOS/Android via temp file; helps diagnose engine init failures
• Native prebuilts: Fetched at build time via hook/build.dart from GitHub release native-v0.10.2; SHA256-verified, bundled via Native Assets
• macOS / iOS setup: requires a small post_install block in your Podfile to symlink lib*.dylib next to the bundled .frameworks — gpu_registry calls dlopen by basename. See the macOS Setup section in README for the exact snippet (iOS works via the same pattern in example/ios/Podfile)

0.13.6

• ModelType.qwen3: New model type for Qwen3 models with thinking support
• Disable Qwen3 thinking at model level: /no_think appended automatically when isThinking: false — faster TTFT
• Configurable maxFunctionBufferLength (#229): createChat(maxFunctionBufferLength: 2048) for long function call args
• Fix Windows path parsing (#233): FileSource now handles backslash paths correctly
• removeDocument (#232): VectorStoreRepository.removeDocument(id:) to delete documents from vector store

0.13.5

• Fix Qwen3 thinking mode (#224): Qwen3 <think> tags now stripped automatically

0.13.4

• Fix iOS compile error (#222): XNNPack delegate type mismatch in EmbeddingModel.swift
• Fix iOS arm64 simulator (#216): Removed TensorFlowLiteSelectTfOps — simulator builds work on Apple Silicon

0.13.3

• Fix macOS SIGSEGV (#219): Per-conversation mutex in gRPC server prevents conversation.close() racing with sendMessageAsync on a native thread → use-after-free in C++ fixed
• Fix macOS desktop Metal accelerator: setup_desktop.sh now downloads libLiteRtMetalAccelerator.dylib from GitHub Release so GPU inference uses the Metal delegate instead of falling back to static C API
• Fix iOS pod install hanging (#220): Replaced TensorFlowLiteSwift (source pod — cloned entire TensorFlow repo) with direct TensorFlowLiteC C API in EmbeddingModel.swift
• Fix Windows >2 GB model error (#212): Clear error message when model file exceeds 2 GB on Windows (known upstream 32-bit stat() overflow in litertlm_jni.dll, google-ai-edge/LiteRT-LM#1494)
• Fix iOS arm64 simulator build (#216): Excluded arm64 from simulator archs to fix build on Apple Silicon Macs

0.13.2

• FileSource absolute paths: Accept both Unix (/path) and Windows (C:\path) absolute paths in FileSource validation
• Package metadata: Updated pubspec description to reflect current feature set (desktop, vision, audio, function calling, embeddings, on-device RAG)
• Desktop CI: Added Linux smoke tests for gRPC server integration

0.13.1

• LiteRT-LM 0.10.0: Updated Android and JVM SDK from 0.9.0 to 0.10.0
• Gemma 4 Thinking Mode: isThinking: true now works with Gemma 4 E2B/E4B models (Android, iOS, Desktop; not Web)
• Fix cancel download: Cancel download now works correctly (#196)
• Fix large_file_handler platform support: Conditional imports for pub.dev platform analysis compatibility

... (truncated)

Commits

• See full diff in compare view

[dependabot]

Superseded by #58.