pygpt-net 2.5.89__py3-none-any.whl → 2.5.91__py3-none-any.whl

pygpt_net/CHANGELOG.txt

@@ -1,3 +1,14 @@
+2.5.91 (2025-08-08)
+
+- Added GPT-5.
+- Added audio cache - #118.
+
+2.5.90 (2025-08-07)
+
+- Fix: Initialize context summary if a conversation starts with a tool call.
+- Fix: Store splitter positions even if the object is deleted from memory.
+- Update: CSS improvements.
+
 2.5.89 (2025-08-07)
 
 - Added audio output device selection in Config -> Audio - issue #117

pygpt_net/__init__.py

@@ -6,15 +6,15 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2025.08.06 00:00:00                  #
+# Updated Date: 2025.08.08 00:00:00                  #
 # ================================================== #
 
 __author__ = "Marcin Szczygliński"
 __copyright__ = "Copyright 2025, Marcin Szczygliński"
 __credits__ = ["Marcin Szczygliński"]
 __license__ = "MIT"
-__version__ = "2.5.89"
-__build__ = "2025-08-07"
+__version__ = "2.5.91"
+__build__ = "2025-08-08"
 __maintainer__ = "Marcin Szczygliński"
 __github__ = "https://github.com/szczyglis-dev/py-gpt"
 __report__ = "https://github.com/szczyglis-dev/py-gpt/issues"

pygpt_net/controller/access/voice.py

@@ -6,7 +6,7 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2025.08.07 03:00:00                  #
+# Updated Date: 2025.08.07 22:00:00                  #
 # ================================================== #
 
 from typing import Optional, List, Dict, Any
@@ -231,8 +231,7 @@ class Voice(QObject):
             self.switch_btn_stop()
 
             # stop audio output if playing
-            if self.window.controller.audio.is_playing():
-                self.window.controller.audio.stop_output()
+            self.window.controller.audio.stop_output()
 
             # set audio volume bar
             self.window.core.audio.capture.set_bar(

pygpt_net/controller/audio/audio.py

@@ -6,7 +6,7 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2025.01.17 13:00:00                  #
+# Updated Date: 2025.08.07 22:00:00                  #
 # ================================================== #
 
 import os
@@ -291,7 +291,7 @@ class Audio:
 
         if use_cache:
             lang = self.window.core.config.get("lang")
-            cache_dir = os.path.join(self.window.core.config.get_user_path(), "cache", "audio", lang)
+            cache_dir = os.path.join(self.window.core.audio.get_cache_dir(), lang)
             if not os.path.exists(cache_dir):
                 os.makedirs(cache_dir, exist_ok=True)
             cache_file = os.path.join(str(cache_dir), event.name + ".wav")
@@ -318,7 +318,7 @@ class Audio:
             )
             return
 
-        cache_dir = os.path.join(self.window.core.config.get_user_path(), "cache", "audio")
+        cache_dir = self.window.core.audio.get_cache_dir()
         if os.path.exists(cache_dir):
             import shutil
             shutil.rmtree(cache_dir)
@@ -352,7 +352,10 @@ class Audio:
 
         :param text: text to play
         """
-        self.window.update_status(trans("status.audio.start"))
+        if text:
+            self.window.update_status(trans("status.audio.start"))
+        else:
+            self.window.update_status("")
         QApplication.processEvents()  # process events to update UI
 
     def on_play(self, event: str):

pygpt_net/controller/chat/output.py

@@ -226,7 +226,7 @@ class Output:
                 self.window.controller.chat.common.unlock_input()  # unlock input
 
         # handle ctx name (generate title from summary if not initialized)
-        if not reply and not internal:  # don't call if reply or internal mode
+        if not ctx.meta or not ctx.meta.initialized:  # don't call if reply or internal mode
             if self.window.core.config.get('ctx.auto_summary'):
                 self.log("Calling for prepare context name...")
                 self.window.controller.ctx.prepare_name(ctx)  # async
@@ -295,7 +295,7 @@ class Output:
             self.window.dispatch(event)  # reload chat window
 
         # self.window.core.debug.mem("END")  # debug memory usage
-        gc.collect()
+        # gc.collect()
 
     def log(self, data: Any):
         """

pygpt_net/controller/ctx/extra.py

@@ -6,7 +6,7 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2025.07.14 18:00:00                  #
+# Updated Date: 2025.08.07 22:00:00                  #
 # ================================================== #
 
 from PySide6.QtWidgets import QApplication
@@ -220,12 +220,7 @@ class Extra:
                 self.window.controller.audio.read_text(item.output)
                 self.audio_play_id = item_id
             elif self.audio_play_id == item_id:
-                if not self.window.controller.audio.is_playing():
-                    self.window.controller.audio.read_text(item.output)
-                else:
-                    self.window.controller.audio.stop_output()
-                    self.window.controller.audio.on_stop()
-                    self.audio_play_id = None
+                self.window.controller.audio.read_text(item.output)
 
     def join_item(
             self,

pygpt_net/controller/kernel/kernel.py

@@ -52,6 +52,7 @@ class Kernel(QObject):
             KernelEvent.APPEND_DATA, 
             KernelEvent.INPUT_USER,
             KernelEvent.FORCE_CALL,
+            KernelEvent.STATUS,
         ]
 
     def init(self):

pygpt_net/controller/layout/layout.py

@@ -112,8 +112,11 @@ class Layout:
             # do not save main splitter state if notepad was not opened yet
             if splitter == "calendar" and not self.window.controller.notepad.opened_once:
                 continue
-            if splitter in self.window.ui.splitters:
-                data[splitter] = self.window.ui.splitters[splitter].sizes()
+            try:
+                if splitter in self.window.ui.splitters:
+                    data[splitter] = self.window.ui.splitters[splitter].sizes()
+            except Exception as e:
+                pass
         self.window.core.config.set('layout.splitters', data)
 
     def splitters_restore(self):
@@ -151,8 +154,11 @@ class Layout:
 
         # notepads
         for id in self.window.ui.notepad:
-            scroll_id = "notepad." + str(id)
-            data[scroll_id] = self.window.ui.notepad[id].textarea.verticalScrollBar().value()
+            try:
+                scroll_id = "notepad." + str(id)
+                data[scroll_id] = self.window.ui.notepad[id].textarea.verticalScrollBar().value()
+            except Exception as e:
+                pass
         self.window.core.config.set('layout.scroll', data)
 
     def scroll_restore(self):

pygpt_net/controller/ui/tabs.py

@@ -6,10 +6,10 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2025.07.20 23:00:00                  #
+# Updated Date: 2025.08.07 18:00:00                  #
 # ================================================== #
 
-from typing import Any, Optional
+from typing import Any, Optional, Tuple
 
 from PySide6.QtCore import QTimer
 
@@ -178,6 +178,7 @@ class Tabs:
 
         prev_tab = self.current
         prev_column = self.column_idx
+
         self.current = idx
         self.column_idx = column_idx
         self.window.controller.ui.mode.update()
@@ -287,6 +288,38 @@ class Tabs:
         """
         return self.window.core.tabs.get_min_idx_by_type(type, self.column_idx)
 
+    def get_prev_idx_from(self, idx: int) -> Tuple[int, bool]:
+        """
+        Get previous tab index from given index
+
+        :param idx: tab index
+        :return: tuple of previous index and boolean indicating if it exists
+        """
+        return self.window.core.tabs.get_prev_idx_from(idx, self.column_idx)
+
+    def get_next_idx_from(self, idx: int) -> Tuple[int, bool]:
+        """
+        Get next tab index from given index
+
+        :param idx: tab index
+        :return: tuple of next index and boolean indicating if it exists
+        """
+        return self.window.core.tabs.get_next_idx_from(idx, self.column_idx)
+
+    def get_after_close_idx(self, idx: int) -> int:
+        """
+        Get tab index after closing the given index
+
+        :param idx: tab index
+        :return: previous tab index if exists, otherwise None
+        """
+        prev_idx, exists = self.get_prev_idx_from(idx)
+        if exists:
+            return prev_idx
+        next_idx, exists = self.get_next_idx_from(idx)
+        if exists:
+            return next_idx
+
     def on_column_changed(self):
         """Column changed event"""
         if self.locked:
@@ -381,7 +414,21 @@ class Tabs:
         """
         if self.locked:
             return
+
+        previous_current = self.current
+        idx_after = None  # <--- next tab index after close to switch to
+        if previous_current != idx and self.column_idx == column_idx:
+            idx_after = previous_current
+            if idx_after > idx:
+                idx_after -= 1  # if current is after closed tab, idx will be shifted
+
+        if idx_after is None:
+            idx_after = self.get_after_close_idx(idx)  # find next tab index after close
+
         self.window.core.tabs.remove_tab_by_idx(idx, column_idx)
+        if idx_after is not None:
+            self.switch_tab_by_idx(idx_after, column_idx)
+
         self.on_changed()
         self.update_current()
         self.debug()
@@ -639,7 +686,10 @@ class Tabs:
 
         :param column_idx: column index
         """
-        idx = self.get_current_idx(column_idx)
+        # append at the end of column
+        idx = self.window.core.tabs.get_max_idx_by_column(column_idx)
+        if idx == -1:
+            idx = 0
         self.append(
             type=Tab.TAB_CHAT,
             tool_id=None,

pygpt_net/controller/ui/ui.py

@@ -42,6 +42,8 @@ class UI:
             7: {'label': 'label.color.violet', 'color': QColor(238, 130, 238), 'font': QColor(255, 255, 255)},
         }
         self.stop_action = None
+        self.splitter_output_size_input = None
+        self.splitter_output_size_files = None
 
     def setup(self):
         """Setup UI"""

pygpt_net/core/audio/audio.py

@@ -6,9 +6,11 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2025.08.07 03:00:00                  #
+# Updated Date: 2025.08.07 22:00:00                  #
 # ================================================== #
 
+import hashlib
+import os
 import re
 from typing import Union, Optional, Tuple, List
 
@@ -21,6 +23,9 @@ from .whisper import Whisper
 
 
 class Audio:
+
+    CACHE_FORMAT = "mp3"  # default cache format
+
     def __init__(self, window=None):
         """
         Audio input/output core
@@ -173,3 +178,63 @@ class Audio:
         :return: Error
         """
         return self.last_error
+
+    def prepare_cache_path(self, content: str) -> Tuple[Union[str, None], bool]:
+        """
+        Prepare unique cache file name for given content
+
+        :param content: text content to generate cache file name
+        :return: cache file path or None if content is empty
+        """
+        exists = False
+        if not content:
+            return None, exists
+        sha1sum = hashlib.sha1(content.encode('utf-8')).hexdigest()
+        filename = f"{sha1sum}." + self.CACHE_FORMAT
+        tmp_dir = self.get_cache_dir()
+        path = os.path.join(tmp_dir, filename)
+        if os.path.exists(path):
+            exists = True
+        return str(path), exists
+
+    def get_cache_dir(self) -> str:
+        """
+        Get cache directory for audio files
+
+        :return: audio cache directory path
+        """
+        dir = self.window.core.config.get_user_dir("tmp")
+        tmp_dir = os.path.join(dir, "audio_cache")
+        if not os.path.exists(tmp_dir):
+            os.makedirs(tmp_dir, exist_ok=True)
+        return tmp_dir
+
+    def mp3_to_wav(
+            self,
+            src_file: str,
+            dst_file: Optional[str] = None
+    ) -> Union[str, None]:
+        """
+        Convert MP3 file to WAV format
+
+        :param src_file: Path to the source MP3 file
+        :param dst_file: Optional path for the destination WAV file.
+        :return: Path to the converted WAV file or None if conversion fails.
+        """
+        from pydub import AudioSegment
+        try:
+            mp3_audio = AudioSegment.from_mp3(src_file)
+        except Exception as e:
+            print(f"Error loading mp3 file: {e}")
+            print("Please install ffmpeg to handle mp3 files: https://ffmpeg.org/")
+            return
+        if dst_file is None:
+            dir = os.path.dirname(src_file)
+            filename = os.path.splitext(os.path.basename(src_file))[0] + ".wav"
+            dst_file = os.path.join(dir, filename)
+        try:
+            mp3_audio.export(dst_file, format="wav")
+            return str(dst_file)
+        except Exception as e:
+            print(f"Error exporting wav file: {e}")
+            return

pygpt_net/core/audio/backend/native.py

@@ -6,18 +6,21 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2025.08.07 03:00:00                  #
+# Updated Date: 2025.08.07 22:00:00                  #
 # ================================================== #
 
+import os
 import time
 from typing import List, Tuple
 
 from PySide6.QtCore import QTimer, QObject
+from pydub import AudioSegment
 
 
 class NativeBackend(QObject):
 
     MIN_FRAMES = 25  # minimum frames to start transcription
+    AUTO_CONVERT_TO_WAV = False  # automatically convert to WAV format
 
     def __init__(self, window=None):
         """
@@ -42,7 +45,10 @@ class NativeBackend(QObject):
         self.stop_callback = None
         self.player = None
         self.playback_timer = None
+        self.volume_timer = None
         self.audio_output = None
+        self.envelope = []
+        self.chunk_ms = 10
 
         # Get configuration values (use defaults if unavailable)
         if self.window is not None and hasattr(self.window, "core"):
@@ -457,8 +463,6 @@ class NativeBackend(QObject):
         :param signals: Signals to emit on playback
         :return: True if started
         """
-        import os
-        from pydub import AudioSegment
         from PySide6.QtMultimedia import QMediaPlayer, QAudioOutput, QMediaDevices
         from PySide6.QtCore import QUrl, QTimer
         if signals is not None:
@@ -476,42 +480,57 @@ class NativeBackend(QObject):
             selected_device = devices[num_device] if num_device < len(devices) else devices[0]
             self.audio_output.setDevice(selected_device)
 
-        self.player = QMediaPlayer()
-        self.player.setAudioOutput(self.audio_output)
-
-        if audio_file.lower().endswith('.mp3'):
-            try:
-                mp3_audio = AudioSegment.from_mp3(audio_file)
-            except Exception as e:
-                print(f"Error loading mp3 file: {e}")
-                return
-
-            base_dir = self.window.core.config.get_user_path()
-            base_name = os.path.splitext(os.path.basename(audio_file))[0]
-            wav_file = os.path.join(base_dir, "_" + base_name + ".wav")
-            try:
-                mp3_audio.export(wav_file, format="wav")
-            except Exception as e:
-                print(f"Error exporting wav file: {e}")
-                return
-
-            self.player.setSource(QUrl.fromLocalFile(wav_file))
-        else:
-            self.player.setSource(QUrl.fromLocalFile(audio_file))
-
-        self.player.play()
-        self.playback_timer = QTimer()
-        self.playback_timer.setInterval(100)
+        if self.AUTO_CONVERT_TO_WAV:
+            if audio_file.lower().endswith('.mp3'):
+                tmp_dir = self.window.core.audio.get_cache_dir()
+                base_name = os.path.splitext(os.path.basename(audio_file))[0]
+                dst_file = os.path.join(tmp_dir, "_" + base_name + ".wav")
+                wav_file = self.window.core.audio.mp3_to_wav(audio_file, dst_file)
+                if wav_file:
+                    audio_file = wav_file
 
         def check_stop():
             if stopped():
                 self.player.stop()
-                self.playback_timer.stop()
+                self.stop_timers()
+                signals.volume_changed.emit(0)
+            else:
+                if self.player:
+                    if self.player.playbackState() == QMediaPlayer.StoppedState:
+                        self.player.stop()
+                        self.stop_timers()
+                        signals.volume_changed.emit(0)
 
+        self.envelope = self.calculate_envelope(audio_file, self.chunk_ms)
+        self.player = QMediaPlayer()
+        self.player.setAudioOutput(self.audio_output)
+        self.player.setSource(QUrl.fromLocalFile(audio_file))
+        self.player.play()
+
+        self.playback_timer = QTimer()
+        self.playback_timer.setInterval(100)
         self.playback_timer.timeout.connect(check_stop)
+        self.volume_timer = QTimer(self)
+        self.volume_timer.setInterval(10)  # every 100 ms
+        self.volume_timer.timeout.connect(
+            lambda: self.update_volume(signals)
+        )
+
         self.playback_timer.start()
+        self.volume_timer.start()
         signals.volume_changed.emit(0)
 
+    def stop_timers(self):
+        """
+        Stop playback timers.
+        """
+        if self.playback_timer is not None:
+            self.playback_timer.stop()
+            self.playback_timer = None
+        if self.volume_timer is not None:
+            self.volume_timer.stop()
+            self.volume_timer = None
+
     def play(
             self,
             audio_file: str,
@@ -543,6 +562,49 @@ class NativeBackend(QObject):
                 self.playback_timer.stop()
         return False
 
+    def calculate_envelope(
+            self,
+            audio_file: str,
+            chunk_ms: int = 100
+    ) -> list:
+        """
+        Calculate the volume envelope of an audio file.
+
+        :param audio_file: Path to the audio file
+        :param chunk_ms: Size of each chunk in milliseconds
+        """
+        import numpy as np
+        audio = AudioSegment.from_file(audio_file)
+        max_amplitude = 32767
+        envelope = []
+
+        for ms in range(0, len(audio), chunk_ms):
+            chunk = audio[ms:ms + chunk_ms]
+            rms = chunk.rms
+            if rms > 0:
+                db = 20 * np.log10(rms / max_amplitude)
+            else:
+                db = -60
+            db = max(-60, min(0, db))
+            volume = ((db + 60) / 60) * 100
+            envelope.append(volume)
+
+        return envelope
+
+    def update_volume(self, signals=None):
+        """
+        Update the volume based on the current position in the audio file.
+
+        :param signals: Signals object to emit volume changed event.
+        """
+        pos = self.player.position()
+        index = int(pos / self.chunk_ms)
+        if index < len(self.envelope):
+            volume = self.envelope[index]
+        else:
+            volume = 0
+        signals.volume_changed.emit(volume)
+
     def get_input_devices(self) -> List[Tuple[int, str]]:
         """
         Get input devices

pygpt_net/core/tabs/tabs.py

@@ -6,7 +6,7 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2025.08.05 21:00:00                  #
+# Updated Date: 2025.08.07 18:00:00                  #
 # ================================================== #
 
 import uuid
@@ -447,6 +447,66 @@ class Tabs:
                 column_idx = tab.column_idx
         return min, column_idx, exists
 
+    def get_prev_idx_from(self, idx: int, column_idx: int = 0) -> Tuple[int, bool]:
+        """
+        Get previous index from the specified index
+
+        :param idx: Tab index
+        :param column_idx: Column index
+        :return: Previous index and exists flag
+        """
+        tabs = self.window.ui.layout.get_tabs_by_idx(column_idx)
+        if idx < 1:
+            return -1, False
+        prev_idx = idx - 1
+        if prev_idx < 0 or prev_idx >= tabs.count():
+            return -1, False
+        tab = self.get_tab_by_index(prev_idx, column_idx)
+        if tab is None:
+            return -1, False
+        if tab.column_idx != column_idx:
+            return -1, False
+        return prev_idx, True
+
+    def get_next_idx_from(self, idx: int, column_idx: int = 0) -> Tuple[int, bool]:
+        """
+        Get next index from the specified index
+
+        :param idx: Tab index
+        :param column_idx: Column index
+        :return: Next index and exists flag
+        """
+        tabs = self.window.ui.layout.get_tabs_by_idx(column_idx)
+        if idx < 0 or idx >= tabs.count():
+            return -1, False
+        next_idx = idx + 1
+        if next_idx < 0 or next_idx >= tabs.count():
+            return -1, False
+        tab = self.get_tab_by_index(next_idx, column_idx)
+        if tab is None:
+            return -1, False
+        if tab.column_idx != column_idx:
+            return -1, False
+        return next_idx, True
+
+    def get_max_idx_by_column(self, column_idx: int = 0) -> int:
+        """
+        Get max index in column
+
+        :param column_idx: Column index
+        :return: Max index
+        """
+        tabs = self.window.ui.layout.get_tabs_by_idx(column_idx)
+        if tabs.count() == 0:
+            return -1
+        max_idx = -1
+        for idx in range(tabs.count()):
+            tab = self.get_tab_by_index(idx, column_idx)
+            if tab is not None and tab.column_idx == column_idx:
+                if tab.idx > max_idx:
+                    max_idx = tab.idx
+        return max_idx
+
     def update(self):
         """Update tabs data (pids) from UI (all columns)"""
         for n in range(0, self.NUM_COLS):

pygpt_net/data/config/config.json

@@ -1,8 +1,8 @@
 {
   "__meta__": {
-    "version": "2.5.89",
-    "app.version": "2.5.89",
-    "updated_at": "2025-08-07T00:00:00"
+    "version": "2.5.91",
+    "app.version": "2.5.91",
+    "updated_at": "2025-08-08T00:00:00"
   },
   "access.audio.event.speech": false,
   "access.audio.event.speech.disabled": [],
@@ -94,6 +94,7 @@
   "attachments_auto_index": true,
   "attachments_send_clear": true,
   "attachments_capture_clear": true,
+  "audio.cache.enabled": true,
   "audio.input.backend": "native",
   "audio.input.channels": 1,
   "audio.input.continuous": false,