supervoxtral 0.1.4__tar.gz → 0.1.5__tar.gz

{supervoxtral-0.1.4 → supervoxtral-0.1.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: supervoxtral
-Version: 0.1.4
+Version: 0.1.5
 Summary: CLI/GUI audio recorder and transcription client using Mistral Voxtral (chat with audio and transcription).
 License: MIT
 License-File: LICENSE

{supervoxtral-0.1.4 → supervoxtral-0.1.5}/README.md

@@ -4,7 +4,7 @@
 
 SuperVoxtral is a lightweight Python CLI/GUI utility for recording microphone audio and integrate with Mistral's Voxtral APIs for transcription or audio-enabled chat.
 
-Voxtral models, such as `voxtral-mini-latest` and `voxtral-small-latest`, deliver fast inference times, high transcription accuracy across languages and accents, and minimal API costs. In contrast to OpenAI's Whisper, which performs only standalone transcription, Voxtral supports two modes: pure transcription via a dedicated endpoint (no prompts needed) or chat mode, where audio input combines with text prompts for refined outputs—like error correction or contextual summarization—without invoking a separate LLM.
+Voxtral models, such as `voxtral-mini-latest` and `voxtral-small-latest`, deliver fast inference times, high transcription accuracy across languages and accents, and minimal API costs. Voxtral supports two modes: pure transcription via a dedicated endpoint (no prompts needed) or chat mode, where audio input combines with text prompts for refined outputs—like error correction or contextual summarization—without invoking a separate LLM.
 
 For instance, use a prompt like: "_Transcribe this audio precisely and remove all minor speech hesitations: "um", "uh", "er", "euh", "ben", etc._"
 
@@ -26,6 +26,7 @@ The package is available on PyPI. We recommend using `uv` (a fast Python package
 - For GUI support (includes PySide6):
   ```
   uv tool install "supervoxtral[gui]"
+  # to update: uv tool update "supervoxtral[gui]"
   ```
 
 - For core CLI only functionality:
@@ -233,6 +234,7 @@ By default in CLI, uses the 'default' prompt from config.toml [prompt.default].
 
 ## Changelog
 
+- 0.1.5: Fix bug on prompt selecting
 - 0.1.4: Support for multiple prompts in config.toml with dynamic GUI buttons for each prompt key
 - 0.1.3: Minor style update
 - 0.1.2: Interactive mode in GUI (choose transcribe / prompt / cancel while recording)

{supervoxtral-0.1.4 → supervoxtral-0.1.5}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "supervoxtral"
-version = "0.1.4"
+version = "0.1.5"
 description = "CLI/GUI audio recorder and transcription client using Mistral Voxtral (chat with audio and transcription)."
 requires-python = ">=3.11"
 license = { text = "MIT" }

{supervoxtral-0.1.4 → supervoxtral-0.1.5}/svx/core/pipeline.py

@@ -180,6 +180,8 @@ class RecordingPipeline:
         else:
             self._status("Transcribe mode activated: no prompt used.")
 
+        logging.debug(f"Applied prompt: {final_user_prompt or 'None (transcribe mode)'}")
+
         paths: dict[str, Path | None] = {"wav": wav_path}
 
         # Convert if needed

{supervoxtral-0.1.4 → supervoxtral-0.1.5}/svx/core/prompt.py

@@ -12,6 +12,7 @@ Intended to be small and dependency-light so it can be imported broadly.
 from __future__ import annotations
 
 import logging
+from collections.abc import Callable
 from pathlib import Path
 
 from .config import USER_PROMPT_DIR, Config, PromptEntry
@@ -121,22 +122,45 @@ def resolve_user_prompt(
         return ""
 
     key = key or "default"
-    suppliers = [
-        lambda: _strip(inline),
-        lambda: _read(file),
-        lambda: _from_user_cfg(key),
-        _from_user_prompt_dir,
+
+    # Suppliers annotated with a name for tracing which one returned the prompt.
+    named_suppliers: list[tuple[str, Callable[[], str]]] = [
+        ("inline", lambda: _strip(inline)),
+        ("file", lambda: _read(file)),
+        (f"prompt_config[{key}]", lambda: _from_user_cfg(key)),
+        ("user_prompt_dir/user.md", _from_user_prompt_dir),
     ]
 
-    for supplier in suppliers:
+    for name, supplier in named_suppliers:
         try:
             val = supplier()
             if val:
+                # Log which supplier provided the prompt and a short snippet for debugging.
+                try:
+                    if len(val) > 200:
+                        snippet = val[:200] + "..."
+                    else:
+                        snippet = val
+                    logging.info(
+                        "resolve_user_prompt: supplier '%s' provided prompt snippet: %s",
+                        name,
+                        snippet,
+                    )
+                except Exception:
+                    # Ensure logging failures do not change behavior.
+                    logging.info(
+                        "resolve_user_prompt: supplier '%s' provided a prompt "
+                        "(snippet unavailable)",
+                        name,
+                    )
                 return val
         except Exception as e:
-            logging.debug("Prompt supplier failed: %s", e)
+            logging.debug("Prompt supplier '%s' failed: %s", name, e)
 
-    return "What's in this audio?"
+    # Final fallback
+    fallback = "What's in this audio?"
+    logging.info("resolve_user_prompt: no supplier provided a prompt, using fallback: %s", fallback)
+    return fallback
 
 
 def init_user_prompt_file(force: bool = False) -> Path:

{supervoxtral-0.1.4 → supervoxtral-0.1.5}/svx/ui/qt_app.py

@@ -273,10 +273,39 @@ class RecorderWorker(QObject):
                 self.canceled.emit()
                 return
             self.status.emit("Processing in progress...")
+            # Wait for user to select mode in the GUI
             while self.mode is None:
                 time.sleep(0.05)
+
+            # Log the selected mode/key for debugging prompt application
+            try:
+                logging.info("RecorderWorker: selected mode/key: %s", self.mode)
+            except Exception:
+                # ensure failures in logging don't break the worker
+                pass
+
             transcribe_mode = self.mode == "transcribe"
-            user_prompt = None if transcribe_mode else self._resolve_user_prompt(self.mode)
+            if transcribe_mode:
+                user_prompt = None
+            else:
+                # Resolve the user prompt for the selected key and log a short snippet
+                user_prompt = self._resolve_user_prompt(self.mode)
+                try:
+                    if user_prompt:
+                        snippet = (
+                            user_prompt[:200] + "..." if len(user_prompt) > 200 else user_prompt
+                        )
+                    else:
+                        snippet = "<EMPTY>"
+                    logging.info(
+                        "RecorderWorker: resolved prompt snippet for key '%s': %s",
+                        self.mode,
+                        snippet,
+                    )
+                except Exception:
+                    # avoid breaking the flow on logging errors
+                    pass
+
             result = pipeline.process(wav_path, duration, transcribe_mode, user_prompt)
             keep_audio = self.save_all or self.cfg.defaults.keep_audio_files
             pipeline.clean(wav_path, result["paths"], keep_audio)
@@ -383,13 +412,15 @@ class RecorderWindow(QWidget):
         button_layout.addStretch()
         self._transcribe_btn = QPushButton("Transcribe")
         self._transcribe_btn.setToolTip("Stop and transcribe without prompt")
-        self._transcribe_btn.clicked.connect(lambda: self._on_mode_selected("transcribe"))
+        self._transcribe_btn.clicked.connect(
+            lambda checked=False, m="transcribe": self._on_mode_selected(m)
+        )
         button_layout.addWidget(self._transcribe_btn)
         self._prompt_buttons: dict[str, QPushButton] = {}
         for key in self.prompt_keys:
             btn = QPushButton(key.capitalize())
             btn.setToolTip(f"Stop and transcribe with '{key}' prompt")
-            btn.clicked.connect(lambda k=key: self._on_mode_selected(k))
+            btn.clicked.connect(lambda checked=False, k=key: self._on_mode_selected(k))
             self._prompt_buttons[key] = btn
             button_layout.addWidget(btn)
         self._cancel_btn = QPushButton("Cancel")