mirror of
https://github.com/tinyhumansai/openhuman.git
synced 2026-07-27 21:08:00 +00:00
Steven EnamakelandGitHub
3851d1ef67
* fix(dictation): update hotkey default value and documentation - Changed the default global hotkey for dictation from "CmdOrCtrl+Shift+D" to "Fn" in both the configuration schema and the associated documentation. - Updated the hotkey parsing function to recognize "Fn" as a valid key, enhancing the flexibility of hotkey configurations. - Added a test case to ensure the "Fn" key can be parsed correctly, improving the robustness of the hotkey handling functionality. * fix(voice): update default activation mode and hotkey in configuration - Changed the default activation mode for voice and dictation from "tap" to "push" in the respective configuration schemas. - Updated the default hotkey for voice commands from "ctrl+shift+space" to "Fn" across various modules and documentation. - Adjusted related tests to reflect the new defaults, ensuring consistency in behavior and expectations. * feat(voice): integrate embedded global voice server startup - Added a new asynchronous function `start_if_enabled` to the voice server module, which initializes the embedded voice server based on configuration settings. - Updated the server run logic to check if the voice server should auto-start, enhancing the startup process for the core application. - Integrated the new server startup function into the main server run logic, ensuring the voice server is launched if enabled in the configuration. * feat(voice): add VoicePanel for managing voice server settings - Introduced a new `VoicePanel` component to handle voice server configurations, including startup options, hotkeys, and runtime controls. - Updated routing in the settings page to include the new voice settings section. - Enhanced the `useSettingsNavigation` hook to support navigation to the voice settings. - Added tests for the `VoicePanel` to ensure functionality and reliability of the voice server management features. * refactor(dictation): update documentation and improve component initialization - Revised comments in `DictationHotkeyManager` to clarify the component's mounting process within the app tree. - Removed unused imports and unnecessary state management from `ServiceBlockingGate`, streamlining the component's logic. - Updated tests for `ServiceBlockingGate` to reflect changes in behavior, ensuring accurate rendering of child components based on service status. - Enhanced the `Cargo.lock` file by updating dependencies to their latest versions for improved stability and security. * fix(voice): update default skip_cleanup setting and enhance VoicePanel options - Changed the default value of `skip_cleanup` in the voice server configuration from `false` to `true` to improve transcription handling. - Reordered options in the `VoicePanel` component to ensure "Natural cleanup" is displayed alongside "Verbatim transcription" for better user clarity. - Updated tests to reflect the new default settings and ensure proper functionality of the VoicePanel component. * feat(window): add window management commands for Tauri application - Introduced a new module `window.ts` containing functions for managing window visibility and state in a Tauri application. - Implemented commands to show, hide, toggle visibility, minimize, maximize, close, and set the title of the main window. - Added checks to ensure commands are only executed in a Tauri environment, enhancing compatibility with web contexts. * feat(tauriCommands): add comprehensive Tauri command modules - Introduced multiple new modules for Tauri commands, including `accessibility`, `autocomplete`, `config`, `conscious`, `core`, `cron`, `hardware`, `localAi`, and `window`. - Each module contains functions for managing specific functionalities such as accessibility permissions, autocomplete suggestions, configuration settings, and hardware interactions. - Implemented checks to ensure commands are executed only in a Tauri environment, enhancing compatibility and reliability. - This addition significantly expands the command capabilities of the Tauri application, providing a robust framework for future development. * feat(voice): enhance audio transcription with initial prompt support - Added functionality to transcribe audio with an optional initial prompt, allowing for vocabulary bias and improved conversational continuity. - Updated the `transcribe_pcm_f32` and `transcribe_wav_file` functions to accept an `initial_prompt` parameter, enhancing recognition of specific vocabulary. - Implemented peak RMS energy tracking during audio recording for silence detection, ensuring recordings below a defined threshold are skipped. - Enhanced the voice server configuration to include a silence threshold and custom dictionary for better transcription context. - Introduced methods to build and manage recent transcripts for improved continuity across consecutive recordings. - Updated tests to validate new features and ensure proper functionality of the transcription process. * feat(voice): enhance VoiceServerConfig with silence detection and custom dictionary - Added `silence_threshold` to the `VoiceServerConfig` for improved silence detection, allowing recordings with low RMS energy to be skipped. - Introduced `custom_dictionary` to bias transcription towards specific vocabulary, enhancing recognition of names and technical terms. - Updated the `voice_transcribe` and `voice_transcribe_bytes` functions to utilize the new `initial_prompt` parameter for better context during transcription. - Adjusted the `transcribe_pcm_i16` function to accept additional parameters for improved flexibility in handling audio input. * feat(voice): add silence threshold and custom dictionary features to VoicePanel - Implemented a new input for setting the silence threshold, allowing recordings with low RMS energy to be skipped. - Added functionality for a custom dictionary, enabling users to add specific vocabulary words to improve transcription accuracy. - Updated the VoiceServerSettings interface and related functions to support the new features, ensuring seamless integration with existing settings. - Enhanced the UI in the VoicePanel to facilitate user interaction with the new settings. * feat(voice): propagate silence threshold and custom dictionary to voice server command - Added `silence_threshold` and `custom_dictionary` parameters to the `run_voice_server_command` function, ensuring these settings are utilized during voice server operations. - Enhanced integration with the existing voice server configuration to support improved transcription accuracy and silence detection. * fix(tauriCommands): update import paths for coreRpcClient - Adjusted import paths for `callCoreRpc` in multiple Tauri command modules to ensure correct referencing from the updated directory structure. - This change enhances module organization and maintains consistency across the codebase. * feat(dependencies): update Cargo.lock and Cargo.toml for new packages and versions - Added new dependencies including `arboard`, `fax`, `fax_derive`, `gethostname`, `half`, `quick-error`, `tiff`, and `x11rb` to enhance functionality and support for clipboard operations, transcription improvements, and system interactions. - Updated existing dependencies to their latest versions for better performance and compatibility. - Modified `VoicePanel` to utilize the updated settings and ensure proper handling of voice server configurations. - Enhanced the text input mechanism to use clipboard-paste for improved reliability in text insertion. * fix(voice): update skip_cleanup default value and enhance logging - Changed the default value of `skip_cleanup` in `VoiceServerConfig` from `true` to `false` to align with expected behavior and improve transcription handling. - Added detailed logging in the transcription cleanup process to provide better insights into the LLM state and cleanup decisions. - Removed unused functions related to unreliable key releases in hotkey handling to simplify the codebase. - Updated tests to reflect the new default settings for `skip_cleanup` and ensure proper functionality across components. * style: apply linter formatting fixes * fix(voice): remove unused warn import in hotkey module * test(voice): add silence threshold and custom dictionary to VoicePanel tests - Updated tests for the VoicePanel component to include new parameters: `silence_threshold` and `custom_dictionary`. - Ensured that the tests reflect the latest configuration settings for improved transcription accuracy and functionality.
147 lines
5.7 KiB
TOML
147 lines
5.7 KiB
TOML
[package]
|
|
name = "openhuman"
|
|
version = "0.49.17"
|
|
edition = "2021"
|
|
description = "OpenHuman core business logic and RPC server"
|
|
autobins = false
|
|
|
|
[[bin]]
|
|
name = "openhuman-core"
|
|
path = "src/main.rs"
|
|
|
|
[lib]
|
|
name = "openhuman_core"
|
|
crate-type = ["rlib"]
|
|
|
|
[dependencies]
|
|
rquickjs = { version = "0.9", features = ["futures", "parallel"] }
|
|
serde = { version = "1", features = ["derive"] }
|
|
serde_json = "1"
|
|
reqwest = { version = "0.12", default-features = false, features = ["json", "blocking", "rustls-tls", "native-tls", "stream", "http2", "multipart", "socks"] }
|
|
tokio = { version = "1", features = ["full", "sync"] }
|
|
once_cell = "1.19"
|
|
parking_lot = "0.12"
|
|
log = "0.4"
|
|
nu-ansi-term = "0.46"
|
|
env_logger = "0.11"
|
|
base64 = "0.22"
|
|
aes-gcm = "0.10"
|
|
argon2 = "0.5"
|
|
rand = "0.9"
|
|
dirs = "5"
|
|
sha2 = "0.10"
|
|
hmac = "0.12"
|
|
uuid = { version = "1", features = ["v4"] }
|
|
anyhow = "1.0"
|
|
async-trait = "0.1"
|
|
chacha20poly1305 = "0.10"
|
|
hex = "0.4"
|
|
fastembed = { version = "5.13", default-features = false, features = ["hf-hub-native-tls", "ort-load-dynamic"] }
|
|
ort = { version = "=2.0.0-rc.11", default-features = false, features = ["std", "ndarray", "load-dynamic"] }
|
|
tokio-util = { version = "0.7", features = ["rt"] }
|
|
tokio-tungstenite = { version = "0.24", features = ["rustls-tls-webpki-roots"] }
|
|
futures = "0.3"
|
|
rusqlite = { version = "0.37", features = ["bundled"] }
|
|
chrono = { version = "0.4", features = ["serde"] }
|
|
cron = "0.12"
|
|
futures-util = "0.3"
|
|
directories = "6"
|
|
toml = "1.0"
|
|
shellexpand = "3.1"
|
|
schemars = "1.2"
|
|
tracing = { version = "0.1", default-features = false }
|
|
tracing-log = "0.2"
|
|
tracing-subscriber = { version = "0.3", default-features = false, features = ["fmt", "ansi", "env-filter"] }
|
|
prometheus = { version = "0.14", default-features = false }
|
|
urlencoding = "2.1"
|
|
thiserror = "2.0"
|
|
ring = "0.17"
|
|
prost = { version = "0.14", default-features = false }
|
|
postgres = { version = "0.19", features = ["with-chrono-0_4"] }
|
|
chrono-tz = "0.10"
|
|
dialoguer = { version = "0.12", features = ["fuzzy-select"] }
|
|
console = "0.16"
|
|
glob = "0.3"
|
|
regex = "1.10"
|
|
ndarray = "0.17.2"
|
|
tokenizers = "0.21.0"
|
|
hostname = "0.4.2"
|
|
rustyline = { version = "15", features = ["with-file-history"] }
|
|
rustls = { version = "0.23", features = ["ring"] }
|
|
rustls-pki-types = "1.14.0"
|
|
tokio-rustls = "0.26.4"
|
|
webpki-roots = "1.0.6"
|
|
sysinfo = { version = "0.33", default-features = false, features = ["system"] }
|
|
clap = { version = "4.5", features = ["derive"] }
|
|
clap_complete = "4.5"
|
|
lettre = { version = "0.11.19", default-features = false, features = ["builder", "smtp-transport", "rustls-tls"] }
|
|
mail-parser = "0.11.2"
|
|
async-imap = { version = "0.11", features = ["runtime-tokio"], default-features = false }
|
|
axum = { version = "0.8", default-features = false, features = ["http1", "json", "tokio", "query", "ws", "macros"] }
|
|
tower = { version = "0.5", default-features = false }
|
|
opentelemetry = { version = "0.31", default-features = false, features = ["trace", "metrics"] }
|
|
opentelemetry_sdk = { version = "0.31", default-features = false, features = ["trace", "metrics"] }
|
|
opentelemetry-otlp = { version = "0.31", default-features = false, features = ["trace", "metrics", "http-proto", "reqwest-client", "reqwest-rustls-webpki-roots"] }
|
|
sentry = { version = "0.47.0", default-features = false, features = ["backtrace", "contexts", "panic", "tracing", "reqwest", "rustls"] }
|
|
tokio-stream = { version = "0.1.18", features = ["full"] }
|
|
url = "2"
|
|
socketioxide = { version = "0.15", features = ["extensions"] }
|
|
whisper-rs = "0.16"
|
|
image = { version = "0.25", default-features = false, features = ["png", "jpeg"] }
|
|
tempfile = "3"
|
|
cpal = "0.15"
|
|
hound = "3.5"
|
|
enigo = "0.3"
|
|
arboard = "3"
|
|
rdev = "0.5"
|
|
|
|
matrix-sdk = { version = "0.16", optional = true, default-features = false, features = ["e2e-encryption", "rustls-tls", "markdown"] }
|
|
fantoccini = { version = "0.22.0", optional = true, default-features = false, features = ["rustls-tls"] }
|
|
serde-big-array = { version = "0.5", optional = true }
|
|
nusb = { version = "0.2", default-features = false, optional = true }
|
|
tokio-serial = { version = "5", default-features = false, optional = true }
|
|
probe-rs = { version = "0.30", optional = true }
|
|
pdf-extract = { version = "0.10", optional = true }
|
|
wa-rs = { version = "0.2", optional = true, default-features = false }
|
|
wa-rs-core = { version = "0.2", optional = true, default-features = false }
|
|
wa-rs-binary = { version = "0.2", optional = true, default-features = false }
|
|
wa-rs-proto = { version = "0.2", optional = true, default-features = false }
|
|
wa-rs-ureq-http = { version = "0.2", optional = true }
|
|
wa-rs-tokio-transport = { version = "0.2", optional = true, default-features = false }
|
|
|
|
[target.'cfg(target_os = "linux")'.dependencies]
|
|
landlock = { version = "0.4", optional = true }
|
|
rppal = { version = "0.22", optional = true }
|
|
|
|
[dev-dependencies]
|
|
|
|
[features]
|
|
sandbox-landlock = ["dep:landlock"]
|
|
sandbox-bubblewrap = []
|
|
hardware = ["dep:nusb", "dep:tokio-serial"]
|
|
channel-matrix = ["dep:matrix-sdk"]
|
|
peripheral-rpi = ["dep:rppal"]
|
|
browser-native = ["dep:fantoccini"]
|
|
fantoccini = ["browser-native"]
|
|
landlock = ["sandbox-landlock"]
|
|
probe = ["dep:probe-rs"]
|
|
rag-pdf = ["dep:pdf-extract"]
|
|
whatsapp-web = ["dep:wa-rs", "dep:wa-rs-core", "dep:wa-rs-binary", "dep:wa-rs-proto", "dep:wa-rs-ureq-http", "dep:wa-rs-tokio-transport", "serde-big-array"]
|
|
|
|
# Fix whisper-rs-sys CRT mismatch on Windows MSVC (LNK2038).
|
|
# Upstream cmake build defaults to /MD but Rust uses /MT.
|
|
# This fork adds config.static_crt(true) to the build script.
|
|
# See: https://github.com/tinyhumansai/openhuman/issues/273
|
|
[patch.crates-io]
|
|
whisper-rs-sys = { git = "https://github.com/tinyhumansai/whisper-rs-sys.git", branch = "main" }
|
|
|
|
# Fast CI builds: trade runtime perf for compile speed
|
|
[profile.ci]
|
|
inherits = "release"
|
|
opt-level = 1
|
|
codegen-units = 16
|
|
lto = false
|
|
incremental = false
|
|
strip = true
|
|
debug = false
|