chore(deps): bump flutter_gemma from 0.12.0 to 0.12.8

[dependabot]

Bumps flutter_gemma from 0.12.0 to 0.12.8.

Release notes

Sourced from flutter_gemma's releases.

v0.12.7

No release notes provided.

Release v0.12.6

v0.12.6

• LiteRT-LM 0.9.0-beta: Updated from 0.9.0-alpha02 on Android and Desktop (JVM)
• Cancel Generation: Implemented on Android, Desktop, and Web
  • Android LiteRT-LM: Conversation.cancelProcess()
  • Desktop: gRPC CancelGeneration RPC
  • Web: LlmInference.cancelProcessing() (MediaPipe 0.10.26)
• MediaPipe Web 0.10.26: Pinned CDN version
• E2E Integration Tests: Full inference test suite with multimodal support

Release v0.12.5

Pre-converted tokenizer.json files for iOS embedding models (avoids SentencePiece/TFLite protobuf conflict).

Release v0.12.3

JAR for desktop support

Changelog

Sourced from flutter_gemma's changelog.

0.12.8

• ToolChoice enum: auto / required / none parameter in createChat() to control tool calling behavior
• Parallel Tool Calls: ParallelFunctionCallResponse for multiple function calls in one response
• Strategy Pattern Parser: Per-model FunctionCallFormat implementations (Gemma, Qwen, DeepSeek, Llama, Phi, FunctionGemma)
• <tool_call> Format: Qwen/Mistral-style function call parsing
• ModelType.phi: Dedicated model type for Phi-4 with <|tool_calls|> format support
• NPU Fix: Pass nativeLibraryDir to LiteRT-LM Backend.NPU()
• Embeddings: Models return L2-normalized vectors (dot product = cosine similarity)
• Windows/Linux Embeddings Fix: TFLite C library now correctly copied to build output (#200)

0.12.7

• Dual-Prefix Embeddings (TaskType): Improved RAG retrieval quality with query/document prefixes
  • TaskType.retrievalQuery (default) — for search queries
  • TaskType.retrievalDocument — for document indexing
  • Follows Google RAG SDK convention (EmbedData.TaskType)
  • All platforms: Android, iOS, Web, Desktop
  • addDocument() automatically uses document prefix
• Desktop Embeddings: Run .tflite embedding models (EmbeddingGemma, Gecko) on macOS, Windows, Linux
  • LiteRT C API via dart:ffi — no gRPC, no JVM overhead
  • Pure Dart tokenizer via dart_sentencepiece_tokenizer (BPE + Unigram, auto-detect format)
  • LiteRT C library built from google-ai-edge/LiteRT v2.1.3
  • XNNPACK delegate with default options (QS8/QU8 quantization support)
  • Desktop scores match Android/Python exactly (cosine similarity 0.708)
  • CI workflow for building LiteRT C library on all 4 platform/arch combinations
• Unified VectorStore: Single Dart implementation using sqlite3 dart:ffi replacing platform-specific code
• Test Migration: Removed patrol dependency, migrated all integration tests to standard integration_test

0.12.6

• LiteRT-LM 0.9.0-beta: Updated from 0.9.0-alpha02 on Android and Desktop (JVM)
  • Breaking API change: Backend enum to Backend factory constructors
• Cancel Generation: Implemented on Android, Desktop, and Web
  • Android LiteRT-LM: Conversation.cancelProcess()
  • Desktop: gRPC CancelGeneration RPC
  • Web: LlmInference.cancelProcessing() (MediaPipe 0.10.26)
• MediaPipe Web 0.10.26: Pinned CDN version (was @​latest)
• E2E Integration Tests: Full inference test suite
  • Parameterized tests for both MediaPipe and LiteRT-LM engines
  • Multimodal tests: vision (Android, iOS, Web, Desktop) + audio (Android, Desktop)
  • Cancel, lifecycle, dual-engine tests

0.12.5

• iOS Tokenizer Rewrite: Replaced SentencePiece C++ with pure Swift tokenizers (BPE + Unigram)
  • Eliminates protobuf symbol conflict between SentencePiece and TensorFlow Lite (#184)
  • Auto-detects tokenizer type from model.type field in tokenizer.json
  • Supports both EmbeddingGemma (BPE) and Gecko (Unigram) models
• HNSW Vector Search: O(log n) approximate nearest neighbor search for VectorStore
  • Cross-platform: Android (Kotlin), iOS (Swift), Web (JavaScript)
  • Configurable M and efConstruction parameters
  • Falls back to brute-force for small datasets
• iOS Embeddings: iosPath parameter for platform-aware tokenizer downloads

... (truncated)

Commits

• See full diff in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

---

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

• @dependabot rebase will rebase this PR
• @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
• @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
• @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)

[dependabot]

Superseded by #23.