David Perov a69b993694 feat(local): bundled talkis-llm runtime (llama.cpp) for local summary ... - talkis-llm.rs: a raw-HTTP sidecar like talkis-stt, backed by llama.cpp via llama-cpp-2, serving /health, /v1/models and an OpenAI-compatible /v1/chat/completions (Qwen2.5 ChatML). Args: -m/--host/--port/-c. - Cargo: add llama-cpp-2 (Metal acceleration on macOS) - prepare-stt-sidecar.mjs + tauri.conf externalBin + check.yml placeholders: build and bundle talkis-llm alongside the STT sidecars - commit the macOS arm64 binary (built locally), like the other sidecars The engine for the local "Текстовая" model: the GGUF model already downloads; the runtime is now bundled and signed with the app, so no talkis.ru hosting and no Gatekeeper issue.		2026-06-24 15:09:51 +03:00
..
before-tauri-build.mjs	ci: optimize macOS release workflow	2026-05-12 09:11:31 +03:00
build-release-macos.sh	Prepare v0.1.16 multi-platform release	2026-05-12 16:43:21 +03:00
build-release.mjs	Prepare v0.1.16 multi-platform release	2026-05-12 16:43:21 +03:00
check-version-sync.sh	review	2026-04-01 23:15:53 +03:00
create-updater-latest-json.sh	Prepare v0.1.16 multi-platform release	2026-05-12 16:43:21 +03:00
postprocess-macos-release.sh	Release v0.1.11	2026-04-27 04:22:56 +03:00
prepare-ffmpeg-sidecar.mjs	Release v0.1.19	2026-05-15 00:49:49 +03:00
prepare-stt-sidecar.mjs	feat(local): bundled talkis-llm runtime (llama.cpp) for local summary	2026-06-24 15:09:51 +03:00