v0.2.86

- Add Gemma 4 E2B instruction-tuned models in `q4f16_1` and `q4f32_1`, with text and audio input. The FP32 variant does not require `shader-f16`.
- Update the bundled TVM runtime to `@mlc-ai/web-runtime@0.28.0-dev0` and switch the prebuilt catalog to `v0_2_86/base`.
- Rebuild 224 WebGPU libraries: 112 each in `base` and `sg32`. The release includes compiler revisions, configuration snapshots, checksums, validation results, and a rebuild script.
- Use 4K-prefill Phi-3.5 vision libraries so default square images fit. The previous 2K variants remain in the binary folder.
- Include manifest-based audio and image loading, crash-resumable generation, and fixes for interrupted conversations, cancelled streams, model locks, token counts, and audio cleanup. Manifest loading remains optional; existing records retain the legacy path.

Artifacts:
- [Gemma 4 E2B q4f16_1](https://huggingface.co/mlc-ai/gemma-4-E2B-it-q4f16_1-MLC)
- [Gemma 4 E2B q4f32_1](https://huggingface.co/mlc-ai/gemma-4-E2B-it-q4f32_1-MLC)
- [v0_2_86 model libraries and build provenance](https://github.com/mlc-ai/binary-mlc-llm-libs/tree/main/web-llm-models/v0_2_86)

Compiler sources: [TVM be03dc94b0](https://github.com/akaashrp/tvm/commit/be03dc94b001269b88ae010d2ac352256be55579), based on Apache main `27576ce2d1` with a WebGPU FP32 prefill fix; [MLC-LLM 42fa855891](https://github.com/akaashrp/mlc-llm/commit/42fa855891fcb5825bf0911047d7c91e8234abd1), based on main `8978ea9aec` with compatibility updates for current TVM APIs.