Release v1.5.7

What's Changed

• chore(website): docs → flutter_gemma 1.5.6; document VoiceSession streamAudio by @DenisovAV in #420
• fix(core): tag installed STT/TTS/embedding models correctly so getInstalledModels lists them (#391) by @DenisovAV in #422

---

🙏 Credit: the #391 fix was also submitted independently by @o-mid in #421, opened before #422 landed — thank you for the fix and the report.

Full Changelog: v1.5.6...v1.5.7

Release v1.5.6

What's Changed

• fix(agent): require flutter_gemma ^1.5.5 (onMaxToolTurns) by @DenisovAV in #418
• feat(speech): VoiceSession streamAudio (0.4.3) + fix(core): SDK tool-call JSON suppression (1.5.6) by @DenisovAV in #419

Full Changelog: v1.5.5...v1.5.6

Release v1.5.5

What's Changed

• consolidate: AgentLoop delegates its tool loop to core (core 1.5.5 + agent 0.2.2) by @DenisovAV in #417

Full Changelog: v1.5.4...v1.5.5

Release v1.5.4

What's Changed

• feat(agent): stream final-answer tokens in AgentLoop (VoiceSession parity) by @DenisovAV in #415
• 1.5.4: balance committed tool-calls on a mid-stream generation error by @DenisovAV in #416

Full Changelog: v1.5.3...v1.5.4

Native dylibs native-v0.16.0

Native LiteRT-LM prebuilts for flutter_gemma, built from LiteRT-LM 924e79c9 (v0.16.0) with LiteRT 0ff28117.

Consumed automatically by flutter_gemma_litertlm/hook/build.dart (Native Assets) at pub get time; SHA256-verified against the map baked into that hook. Previous release: native-v0.14.0 — there was no native-v0.15.0.

What changed

• Android OpenCL per-turn memory leak is fixed (LiteRT-LM #2699). This is the leak behind #348 and #402: RSS ratcheted ~65–300 MB per inference on the GPU path until the app was OOM-killed.
• Stream-callback ABI moved from a 4-argument callback to a 2-argument opaque chunk, upstream, with no compatibility path. libStreamProxy resolves the shape at runtime, so both old and new hosts work.
• Windows discrete GPU works again. The crash reported as LiteRT-LM #2957 was not an upstream regression: our Windows build passed --define=litert_link_capi_so=true, a name upstream had deleted. Bazel accepts unknown defines silently, so the LiteRt runtime was being linked statically, which conflicts with the separately shipped WebGPU accelerator once Dawn became its own library. Corrected to litert_runtime_link_mode=dynamic + resolve_symbols_in_exec=false. That issue has been retracted.
• Both NPU dispatch stacks are now built from the pin instead of carried forward:
  • Intel — LiteRtDispatch.dll plus a version-matched OpenVino runtime (2026.3.0.dev20260622). The carried-forward pair shipped OpenVino 2026.2.0 against a runtime pinned to 2026.3.0, which is what broke backend=npu.
  • Qualcomm — libLiteRtDispatch_Qualcomm.so rebuilt from the derived LiteRT ref, and the ten QNN runtime libraries refreshed from the same QAIRT 2.44.0.260225. The stale pair failed with Qnn System library version 1.8.0 is mismatched. The minimum supported version is 1.11.0.
• macOS deployment target is pinned. libStreamProxy.dylib had been inheriting the build host's OS since native-v0.14.0 and shipped with minos 26.0; it is now built with -mmacosx-version-min=11.0.

Verification

• Android — Snapdragon 8 Elite (SM8750), Android 16: 23/23 integration tests pass; CPU, GPU (OpenCL) and NPU all reach Engine initialized successfully, NPU engine_create in 498 ms.
• Windows — Intel Arc 140V: GPU 36.1 chunks/s; NPU functional on Lunar Lake.
• Linux — 24/24.
• Apple — all dylibs arm64; install_name_tool rewrite clean on every one (Native Assets re-runs it on each pub get); iOS minos 13.0, macOS 11.0; gpu_registry @executable_path patch present, basename dlopen absent.

Contents

Archive	Files
litertlm-android_arm64.tar.gz	19 — core + Qualcomm QNN NPU stack
litertlm-ios_arm64.tar.gz	4
litertlm-ios_sim_arm64.tar.gz	4
litertlm-macos_arm64.tar.gz	4
litertlm-linux_x86_64.tar.gz	7
litertlm-linux_arm64.tar.gz	7
litertlm-windows_x86_64.tar.gz	28 — core + DXC runtime + Intel NPU stack

SHA256 sums for every archive are in checksums_litertlm.txt.

Release v1.5.3

What's Changed

• refactor(example): standard list-screen model selection for TTS + Voice Loop by @DenisovAV in #411
• feat(example): per-step model selection for the Voice Loop (STT / LLM / TTS) by @DenisovAV in #412
• feat: Voice Loop tool-calling + agent, and Inflect-Nano-v2 fast TTS by @DenisovAV in #414

Full Changelog: v1.5.2...v1.5.3

Release v1.5.2

What's Changed

• example: download progress on model-install screens + device-local LLM staging for the voice gate by @DenisovAV in #403
• feat: Qwen3-TTS — multilingual AR codec-LM as a 2nd on-device TTS family by @DenisovAV in #408

Full Changelog: v1.5.1...v1.5.2

Release v1.5.1

What's Changed

• feat: Whisper + Parakeet-CTC STT, int8 models, install-identity namespacing by @DenisovAV in #406

Full Changelog: v1.5.0...v1.5.1

Release v1.5.0

What's Changed

• feat(genai): genai_primitives parallel input/output path (#181) by @DenisovAV in #363
• feat(core): flutter_gemma 1.5.0 — complete the FlutterGemma facade (API completeness) by @DenisovAV in #396

Full Changelog: v1.4.2...v1.5.0

Release v1.4.2

What's Changed

• docs: fix stale version pins + TTS README/CLAUDE coverage by @DenisovAV in #397
• ci: pin jaspr_cli 0.23.1 (0.23.2 build daemon broken) by @DenisovAV in #399
• feat(speech): robust model-agnostic TTS text frontend + neural G2P (0.3.0) by @DenisovAV in #398
• feat(speech): on-device voice loop (VoiceSession) + model-agnostic TTS robustness — flutter_gemma_speech 0.3.0 by @DenisovAV in #400
• 1.4.2: docs — surface the on-device voice loop on the flutter_gemma README by @DenisovAV in #401

Full Changelog: v1.4.1...v1.4.2