iq >UdZddlmZddlZddlZddlZddlZddlmZm Z m Z ddddddZ ddd d d d d d d d d d d Z e hdZe hdZdZdBdZdCdZdCdZddlmZmZmZmZejeZdDdZdEdZdFdGd#Zdaej Z!ej Z"d$a#d$a$d%a%de&d&<da'de&d'<ej(Z)e)*da+d(e&d)<da,d(e&d*<da-d+e&d,<da.d-Z/dHd.Z0dId0Z1 dJdKd;Z2dLdMd=Z3dEd>Z4dHd?Z5dNdAZ6dS)Ou Process-wide voice recording + TTS API for the TUI gateway. Wraps ``tools.voice_mode`` (recording/transcription) and ``tools.tts_tool`` (text-to-speech) behind idempotent, stateful entry points that the gateway's ``voice.record``, ``voice.toggle``, and ``voice.tts`` JSON-RPC handlers can call from a dedicated thread. The gateway imports this module lazily so that missing optional audio deps (sounddevice, faster-whisper, numpy) surface as an ``ImportError`` at call time, not at startup. Two usage modes are exposed: * **Push-to-talk** (``start_recording`` / ``stop_and_transcribe``) — single manually-bounded capture used when the caller drives the start/stop pair explicitly. * **Continuous (VAD)** (``start_continuous`` / ``stop_continuous``) — mirrors the classic CLI voice mode: recording auto-stops on silence, transcribes, hands the result to a callback, and then auto-restarts for the next turn. Three consecutive no-speech cycles stop the loop and fire ``on_silent_limit`` so the UI can turn the mode off. ) annotationsN)AnyCallableOptionalc-a-)ctrlcontrolaltoptionoptspaceentertabescape backspacedelete) rspcrreturnretrrescrbsrdel>cdlzc-bcfgrrct|tsdS|d}t|tsdS|dS)aShape-safe ``cfg.voice.record_key`` lookup. ``load_config()`` deep-merges raw YAML and preserves scalar overrides, so a hand-edited ``voice: true`` / ``voice: cmd+b`` leaves ``cfg["voice"]`` as a bool/str instead of a dict, and the naive ``.get("voice", {}).get("record_key")`` chain raises AttributeError before voice can even start (Copilot round-11 on #19835). Return ``None`` for malformed shapes so call sites can feed the result straight into the normalizer/formatter and get the documented default. Nvoice record_key) isinstancedictget)rrs 5/home/piyush/.hermes/hermes-agent/hermes_cli/voice.pyvoice_record_key_from_configr%VsU c4 t GGG  E eT " "t 99\ " ""rawstrct|tstS|}|stSd|dD}|stSt |dkrtSt |dkrtS|\}}|dvrtSt|}|stSt |dkrB|dkr|tvrtS|dkr tj dkr|tvrtS||St|}|stS||S) uCoerce ``voice.record_key`` into prompt_toolkit's ``c-x`` / ``a-x`` format. Mirrors the TUI parser contract (``ui-tui/src/lib/platform.ts``) so one config value binds the same shortcut in both runtimes: * non-string / empty / typo'd / bare-char / multi-modifier / reserved ``ctrl+c|d|l`` → documented default ``c-b`` * single-char keys: ``ctrl+o`` → ``c-o`` * named keys: ``ctrl+space`` → ``c-space`` (aliases collapse: ``ctrl+return`` → ``c-enter``) * ``super`` / ``win`` / ``windows`` → ``c-b`` (TUI-only modifiers — prompt_toolkit has no super mod; the CLI binding site is expected to warn when this fallback fires so users see the cross-runtime split, Copilot round-11 on #19835) c^g|]*}||+S)strip).0ps r$ zAnormalize_voice_record_key_for_prompt_toolkit..s- @ @ @1aggii @QWWYY @ @ @r&+>winsuperwindowsrrdarwin)r!r(_DEFAULT_PT_KEYr,lowersplitlen_VOICE_MOD_ALIASESr#_VOICE_RESERVED_CTRL_CHARSsysplatform_VOICE_RESERVED_ALT_CHARS_MAC_VOICE_NAMED_KEYS)r'loweredpartsmodifier_token key_tokennormalized_modnameds r$-normalize_voice_record_key_for_prompt_toolkitrGls{ c3  iikk!!G  @ @ c 2 2 @ @ @E   5zzA~~  5zzQ %NI444'++N;;N  9~~ T ! !i3M&M&M" " d " " ((:::" " -)---  ! !) , ,E  %e % %%r&c t|}|dr d|dd}}nj|dr d|dd}}nHd|vrB|dd\}}|d |ddzdz}nd S|s|dSt |dkr||zS||d z|ddzS) aFRender ``voice.record_key`` for ``/voice status`` in CLI-friendly form. Mirrors the TUI's ``formatVoiceRecordKey``: returns ``Ctrl+B`` / ``Alt+Space`` / ``Ctrl+Enter``. Malformed configs surface as the documented default so status never advertises a shortcut that won't bind (Copilot round-10 on #19835). rzCtrl+r1NrzAlt+r0r2rzCtrl+B)rG startswithr9upperrstripr:)r' normalizedprefixkeymods r$"format_voice_record_key_for_statusrPs?sCCJT"" z!""~   t $ $jn  ##C++SQ#abb')C/x "}}S!!! 3xx1}} ## CFLLNN "SW ,,r&)create_audio_recorderis_whisper_hallucinationplay_audio_filetranscribe_recordingmsgNonectjdddkrdS t d|t jddS#ttf$rYdSwxYw)u^Emit a debug breadcrumb when HERMES_VOICE_DEBUG=1. Goes to stderr so the TUI gateway wraps it as a gateway.stderr event, which createGatewayEventHandler shows as an Activity line — exactly what we need to diagnose "why didn't the loop auto-restart?" in the user's real terminal without shipping a separate debug RPC. Any OSError / BrokenPipeError is swallowed because this fires from background threads (silence callback, TTS daemon, beep) where a broken stderr pipe must not kill the whole gateway — the main command pipe (stdin+stdout) is what actually matters. HERMES_VOICE_DEBUG1Nz[voice] T)fileflush) osenvironr#r,printr=stderrBrokenPipeErrorOSError)rUs r$_debugrcs z~~*B//55773>>  SZt<<<<<< W %     sAA0/A0boolc ddlm}|di}t|tr#t |ddSn#t $rYnwxYwdS)z=CLI parity: voice.beep_enabled in config.yaml (default True).r) load_configr beep_enabledT)hermes_cli.configrfr#r!r"rd Exception)rf voice_cfgs r$_beeps_enabledrks 111111KMM%%gr22 i & & = nd;;<< < =      4sAA A,+A,r2 frequencyintcountctsdS ddlm}|||dS#t$r }t d|d|Yd}~dSd}~wwxYw)uUAudible cue matching cli.py's record/stop beeps. 880 Hz single-beep on start (cli.py:_voice_start_recording line 7532), 660 Hz double-beep on stop (cli.py:_voice_stop_and_transcribe line 7585). Best-effort — sounddevice failures are silently swallowed so the voice loop never breaks because a speaker was unavailable. Nr) play_beeprlrnzbeep z Hz failed: )rktools.voice_moderprirc)rlrnrpes r$ _play_beeprts   2...... IU333333 2220y00Q001111111112s' AA  AFT_continuous_auto_restart_continuous_recorderOptional[Callable[[str], None]]_continuous_on_transcript_continuous_on_statusOptional[Callable[[], None]]_continuous_on_silent_limitct5t$ttddr ddddSt}||addddS#1swxYwYdS)uBegin capturing from the default input device (push-to-talk). Idempotent — calling again while a recording is in progress is a no-op. N is_recordingF)_recorder_lock _recordergetattrrQstart)recs r$start_recordingr5s   WY%N%N $%%  sA%$A%%A),A) Optional[str]cjt5t}dadddn #1swxYwY|dS|}|sdS t|}nz#t$rm}t d|Yd}~ tj |rtj |dSdS#t$rYdSwxYwd}~wwxYw tj |rtj |nZ#t$rYnNwxYw# tj |rtj |ww#t$rYwwxYwxYw| dsdS| dpd }|rt|rdS|S)zStop the active push-to-talk recording, transcribe, return text. Returns ``None`` when no recording is active, when the microphone captured no speech, or when Whisper returned a known hallucination. Nzvoice transcription failed: %ssuccess transcriptrY)rrstoprTriloggerwarningr]pathisfileunlinkr#r,rR)rwav_pathresultrstexts r$stop_and_transcriberDsD   {txxzzH t %h// 7;;;ttt w~~h'' $ (##### $ $    DD    w~~h'' $ (###    D  w~~h'' $ (#### $    D  ::i t JJ| $ $ * 1 1 3 3D +D11t Ks ""AD C  C;D3B77 CCC  D3D DDE3E  E EEEE@ on_transcriptCallable[[str], None] on_statuson_silent_limitsilence_thresholdsilence_durationfloat auto_restartc t5trtd ddddStrtd ddddSda|a|a|a|a|rdatta |t_ |t_ t}dddn #1swxYwYtd|d|d td d  |t nv#t $ri}t"d|tdt'|jd|t5dadddn #1swxYwYd}~wwxYw|r |dn#t $rYnwxYwdS)uStart a VAD-driven continuous recording loop. The loop calls ``on_transcript(text)`` each time speech is detected and transcribed successfully. If ``auto_restart`` is True, it auto-restarts for the next turn and resets the no-speech counter for that loop. If ``auto_restart`` is False, the first silence-triggered transcription ends the loop and reports ``"idle"``; no-speech counts are retained across starts so a push-to-talk caller can still enforce the three-strikes guard. After ``_CONTINUOUS_NO_SPEECH_LIMIT`` consecutive silent cycles (no speech picked up at all) the loop stops itself and calls ``on_silent_limit`` so the UI can reflect "voice off". Returns False if a previous stop is still transcribing/cleaning up; otherwise returns True. Idempotent — calling while already active is a successful no-op. ``on_status`` is called with ``"listening"`` / ``"transcribing"`` / ``"idle"`` so the UI can show a live indicator. u*start_continuous: already active — no-opNTu6start_continuous: stop/transcribe in progress — busyFrz#start_continuous: begin (threshold=z , duration=zs)pr2rqon_silence_stopz(failed to start continuous recording: %sz#start_continuous: rec.start raised : listening)_continuous_lock_continuous_activerc_continuous_stoppingrurxryr{_continuous_no_speech_countrvrQ_silence_threshold_silence_durationrtr_continuous_on_silencerirerrortype__name__)rrrrrrrrss r$start_continuousrqs: ##   ? @ @ @########   K L L L ########"#/ $1! )&5#  ,*+ '  '#8#:#: 2C/1A.")###############, `.?``L\```A&&&& "8 9999  ?CCCLT!WW5ELLLLMMM  ' '!&  ' ' ' ' ' ' ' ' ' ' ' ' ' ' '   Ik " " " "    D  4slBBABB#&B#C.. E!8A EE EE EE EE!' E33 F?Fforce_transcribec t5ts ddddSdat}ttt t }|o| |duadadada sdadddn #1swxYwY|0|rrr dn#t$rYnwxYw | n|#t$ro}t d| | n2#t$r%}t d|Yd}~nd}~wwxYwd Yd}~nd}~wwxYw fd}tj|d dS | n2#t$r%}t d|Yd}~nd}~wwxYwt5dadddn #1swxYwYt#d d r d dS#t$rYdSwxYwdS)u?Stop the active continuous loop and release the microphone. Idempotent — calling while not active is a no-op. If ``force_transcribe`` is True, the recorder stops synchronously, then transcription/cleanup runs on a background thread before reporting ``"idle"``. Otherwise the buffer is discarded. NFr transcribingzfailed to stop recorder: %szfailed to cancel recorder: %scd}d} r t }|dr<|dpd}|rt|s|}tj rt j n9#tj rt j wwxYwn2#t$r%}t d|Yd}~nd}~wwxYw|r? |n2#t$r%}t d|Yd}~nd}~wwxYwrbt5|rda ntdz a ttk}|rda dddn #1swxYwY|rr n#t$rYnwxYwtd d t5dadddn #1swxYwYr d dS#t$rYdSwxYwdS#|r? |n2#t$r%}t d|Yd}~nd}~wwxYwrbt5|rda ntdz a ttk}|rda dddn #1swxYwY|rr n#t$rYnwxYwtd d t5dadddn #1swxYwYr d w#t$rYwwxYwwxYw) NFrrrYz&failed to stop/transcribe recorder: %s!on_transcript callback raised: %srr2r1rqidle)rTr#r,rRr]rrrrirrrr_CONTINUOUS_NO_SPEECH_LIMITrtr) r should_haltrrrsrrrtrack_no_speechrs r$_transcribe_and_cleanupz0stop_continuous.._transcribe_and_cleanupsv,0 # -! 44%9(%C%CF%zz)446(. <(@(@(FB'M'M'O'O#'!60H0N0N!615J!w~~h774 " ( 3 3 3 "w~~h774 " ( 3 3 3 34 PPPNN#KQOOOOOOOOP"SS)M*5555(SSS"NN+NPQRRRRRRRRS'%- D D) D>? ; ; ;q @ ;$?'B%C!,$/!DBC$? D D D D D D D D D D D D D D D'%?%% / 1 1 1 1#,%%% $%A6666)55/4,555555555555555 !!%If-----(!!! DD!!!7"SS)M*5555(SSS"NN+NPQRRRRRRRRS'%- D D) D>? ; ; ;q @ ;$?'B%C!,$/!DBC$? D D D D D D D D D D D D D D D'%?%% / 1 1 1 1#,%%% $%A6666)55/4,555555555555555 !!%If----(!!! D!!saCA B*4C6CCH D"D=HDH D E#EE$FF F F F,+F,GGG$ G11 G?>G?K< HK< IH>9K<>I K<$I?3 K<?J K<J K< JK< J'$K<&J''K<K K<K K<K K< K+*K<+ K85K<7K88K<T)targetdaemonrr1rqr)rrrvryrxr{rurrrirrrcancel threadingThreadrrt) rrrrs cancel_errorrrrrrrs @@@@@r$stop_continuousrsy ,,!  ,,,,,,,,#") 1 5/ *?BBBBBBBB C %%$%%%%%%%%%%%%%%% A&&&&  If         DD s A'8A''A+.A+< B BBB.. D'8D"C)(D") D3DD"DD""D'E33 F"=FF",F;;F?F? G'' G54G5cRt5tcdddS#1swxYwYdS)z5Whether a continuous voice loop is currently running.N)rrr+r&r$is_continuous_activer9so ""!""""""""""""""""""s   cr tdt5tstd ddddSt}t}t }t }dddn #1swxYwY|tddS|r |dn#t$rYnwxYw|}t|dd}td|d |d td d d}|r t|}t| d}| dpd} | d} td|d| d| |r| rt| s| }nY#t$rL} t d| tdt%| jd| Yd} ~ nd} ~ wwxYw t(j|rt)j|nZ#t$rYnNwxYw# t(j|rt)j|ww#t$rYwwxYwxYwt5tstd ddddS|rdan t0dz at0t2k} t0} dddn #1swxYwY|rA|r? ||n2#t$r%} t d| Yd} ~ nd} ~ wwxYw| rtd| dt5dadadddn #1swxYwY|r |n#t$rYnwxYw |n#t$rYnwxYw|r |dn#t$rYnwxYwdSt6std t6d!"ddl}|d#t5tstd$ ddddS dddn #1swxYwYt@rtd%| d td&d  |!tD'n#t$r} t #d(| td)t%| jd| t5dadddn #1swxYwY|r |dn#t$rYnwxYwYd} ~ dSd} ~ wwxYw|r |d*dS#t$rYdSwxYwdStd+t5dadddn #1swxYwY|r |ddS#t$rYdSwxYwdS),u AudioRecorder silence callback — runs in a daemon thread. Stops the current capture, transcribes, delivers the text via ``on_transcript``, and — if the loop is still active — starts the next capture. Three consecutive silent cycles end the loop. z_continuous_on_silence: firedu/_continuous_on_silence: loop inactive — abortNu-_continuous_on_silence: no recorder — abortr _peak_rmsz$_continuous_on_silence: rec.stop -> z (peak_rms=)rr1rqrrrYrz._continuous_on_silence: transcribe -> success=z text=z err=z#continuous transcription failed: %sz*_continuous_on_silence: transcribe raised ru@_continuous_on_silence: stopped during transcribe — no restartrr2rz_continuous_on_silence: u silent cycles — haltingFrz1_continuous_on_silence: waiting for TTS to finish<)timeout333333?z5_continuous_on_silence: stopped while waiting for TTSz3_continuous_on_silence: restarting loop (no_speech=rrz*failed to restart continuous recording: %sz'_continuous_on_silence: restart raised rz9_continuous_on_silence: auto_restart=False, stopping loop)$rcrrrvrxryr{rirrrtrTrdr#r,rRrrrrr]rrrrrr _tts_playingis_setwaittimesleeprurrr)rrrrrpeak_rmsrrrrerrrsr no_speech_times r$rr?sW  *+++ 66!  D E E E 66666666#1 ) 5666666666666666 {>???  In % % % %    D xxzzHsK,,H QxQQhQQQ A&&&& $J )(33F 6::i0011GJJ|,,299;;D**W%%C -----%(--    "4 "(@(F(F "!  Y Y Y NN@! D D D WQ@PWWTUWW X X X X X X X X Y 7>>(++(Ih'''     7>>(++(Ih''''(      0 0!  U V V V  0 0 0 0 0 0 0 0  -*+ ' ' '1 , '15PP /  0 0 0 0 0 0 0 0 0 0 0 0 0 0 0CmC C M* % % % % C C C NN> B B B B B B B B CO)OOOPPP  , ,!& *+ ' , , , , , , , , , , , , , , ,   !!!!      JJLLLL    D     &!!!!        BCCC"%%% C  % NOOO                          QYQQQRRRS****  II& )r output_pathzspeak_text: playing z (z bytes).r2z.oggz*speak_text: TTS tool produced no audio at zVoice TTS playback failed: %szspeak_text raised r)&r,retempfilerrrrvrrrirrrclearrctools.tts_toolrr:sub MULTILINEsetrrrr]makedirsrjoin gettempdirstrftimergetsizerSrrsplitrbrr) rrrrpaused_recordingrsrtts_textmp3_pathogg_paths r$ speak_textrs tzz|| IIIOOOKKK   J J  J$0,neDD1 J$++---#'   J J JEqIIIIIIII J J J J J J J J J J J J J J J J I6F I I IJJJA666666"%d))d"2"24;;66+S(;;662E8DD66/2x8866*E8<<66,x8866*eX6666)R6FF66."hbl6KK66'2x0066)VX66>>##  > %&&&   JJsOOO!  % *>*J,22,B3HIIII$Eq                    A BGLL!4!4!6!6GGRVWWWW7<<    ! !  74==11 7 7 7   N3x==NNHNNOOOx@@@@ 7>>( # # L(A(AA(E(E X(XXbgooh6O6OXXX Y Y Y H % % %  (####??32215>7>>(++(Ih'''     JJJ K K K ===6:::;DGG$4;;;;<<<<<<<<= %&&&   JJsOOO!  % *>*J,22,B3HIIII$Eq                     %&&&   JJsOOO!  % *>*J,22,B3HIIII$Eq                 s`%B.A0/B.0 B:BB.BB..B25B2&D/R8K,/JK K &KKK  KK"K*ER8.A&RR8 R"R8!R""R87W%8 TAT W% TW%W'/VW W!W<WWWWW%AZ7,Z*rsG*#""""" **********             &'Y77!* /// : :####,J&J&J&J&Z---->  8 $ $    *    22222$  !!"9>##!%%%%%  y  =AAAAA9=====<@@@@@    ''''^2648 ! KKKKK\wwwwwt"""" ____Jjjjjjjr&