Jake
1d71e8e361
extract_content_tags now generates with grammar=None and parses the response via a manual brace-counting JSON envelope extractor that handles Qwen <think>...</think> prefixes and trailing stop tokens. Five new unit tests. Bumps llama-cpp-2 to 0.1.146. Explicit features=[] on tauri dependency (no-op). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
33 lines
1.2 KiB
TOML
33 lines
1.2 KiB
TOML
[package]
|
|
name = "magnotia-llm"
|
|
version = "0.1.0"
|
|
edition = "2021"
|
|
description = "Local LLM engine for Magnotia (Qwen3.5 / Qwen3.6 via llama-cpp-2): transcript cleanup, task extraction, micro-step decomposition"
|
|
|
|
[features]
|
|
# Default desktop build keeps the existing openmp + vulkan acceleration.
|
|
# Mobile / CPU-only targets can drop one or both via:
|
|
# cargo build -p magnotia-llm --no-default-features
|
|
# These are independent so an Android Vulkan build can opt into vulkan
|
|
# without openmp (the NDK ships OpenMP libs but the toolchain configuration
|
|
# is fragile across NDK versions).
|
|
default = ["gpu-vulkan", "openmp"]
|
|
gpu-vulkan = ["llama-cpp-2/vulkan"]
|
|
openmp = ["llama-cpp-2/openmp"]
|
|
|
|
[dependencies]
|
|
magnotia-core = { path = "../core" }
|
|
encoding_rs = "0.8"
|
|
futures-util = "0.3"
|
|
llama-cpp-2 = { version = "0.1.146", default-features = false }
|
|
reqwest = { version = "0.12", default-features = false, features = ["rustls-tls", "stream"] }
|
|
serde = { version = "1", features = ["derive"] }
|
|
serde_json = "1"
|
|
sha2 = "0.10"
|
|
thiserror = "2"
|
|
tokio = { version = "1", features = ["fs", "io-util", "macros", "net", "rt-multi-thread", "sync", "time"] }
|
|
tracing = "0.1"
|
|
|
|
[dev-dependencies]
|
|
tempfile = "3"
|