J.A.R.V.I.S-rust/crates/jarvis-app/src
Bossiara13 e5aaa7e064 feat(app): wire LlmClient into voice loop with trigger-prefix fallback
new module crates/jarvis-app/src/llm_fallback.rs holds an optional
LlmClient + ConversationHistory built once at startup. if GROQ_TOKEN is
unset the module logs a warning and stays disabled — voice commands keep
working as before.

both the wake-word voice path (recognize_command in app.rs) and the
gui-side text command path (process_text_command) now check whether the
recognized phrase starts with one of the configured trigger phrases
(ru: 'скажи' / 'ответь' / 'произнеси'). when it does, the remainder of
the phrase is sent to Groq and the reply is published as a new
IpcEvent::LlmReply { text } so the gui can speak it.

on api error the trailing user turn is popped from history, the russian
fallback line is sent over ipc and a 'error' voice cue plays. the loop
itself never panics.
2026-04-23 02:16:02 +03:00
..
tray AI models shared registry + Code cleanup + Better async handling + Some fixes, etc 2026-02-18 21:08:48 +05:00
_app.rs VAD fixes + some calibrations 2026-01-08 00:35:21 +05:00
_main.rs project restructure with Rust workspaces 2026-01-04 05:19:47 +05:00
app.rs feat(app): wire LlmClient into voice loop with trigger-prefix fallback 2026-04-23 02:16:02 +03:00
llm_fallback.rs feat(app): wire LlmClient into voice loop with trigger-prefix fallback 2026-04-23 02:16:02 +03:00
log.rs project restructure with Rust workspaces 2026-01-04 05:19:47 +05:00
main.rs feat(app): wire LlmClient into voice loop with trigger-prefix fallback 2026-04-23 02:16:02 +03:00
tray.rs AI models shared registry + Code cleanup + Better async handling + Some fixes, etc 2026-02-18 21:08:48 +05:00