supervoxtral 0.1.3__py3-none-any.whl → 0.1.5__py3-none-any.whl

{supervoxtral-0.1.3.dist-info → supervoxtral-0.1.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: supervoxtral
-Version: 0.1.3
+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-0.1.3.dist-info → supervoxtral-0.1.5.dist-info}/RECORD

@@ -1,18 +1,18 @@
 svx/__init__.py,sha256=qPEe5u3PT8yOQN4MiOLj_Bd18HqcRb6fxnPDfdMUP7w,742
-svx/cli.py,sha256=FMDdOSwTncgMxBj_H2BAYcuCtDNX9wEelbqm4ddo0O0,9132
+svx/cli.py,sha256=3AirsBynuq2rcz-4C8hbZ69JztkgA7LTMGmL6ym7nyY,9167
 svx/core/__init__.py,sha256=mhzXuIXo3kUzjWme0Bxhe4TQZQELlyEiG_89LUAPC7M,2856
 svx/core/audio.py,sha256=r0m5T1uzdsJ1j9YXgQ5clv15dvMwZBp_bk2aLpjnrkc,7684
 svx/core/clipboard.py,sha256=IFtiN2SnYKQIu0WXx0hCK8syvDXanBpm1Jr2a8X7y9s,3692
-svx/core/config.py,sha256=irODbQBOosIdWANaj1Mju4NfdvPiqTkV0gWmoTNjZRM,14569
-svx/core/pipeline.py,sha256=nqvCgK5Pbyx18mfACrN_mIDt546Bh7fKA6MF4XG1hxM,10637
-svx/core/prompt.py,sha256=z-TFVQjHr4mWYXWYLRjCIChg4dMvG4GGJYcIy5QQwJY,5099
+svx/core/config.py,sha256=e2tTGjjPcUYFctB28Ha90G-W44mF_0eWey1zpSyZkBo,16095
+svx/core/pipeline.py,sha256=AjNTzx8eFyWjI4VQYgKGELdo4soWUJZCn3861yIE5i0,10728
+svx/core/prompt.py,sha256=VAHBSL0UESrkbalT6s7SaMc9IQ0OJFKBFO1bEmXnRrI,7172
 svx/core/storage.py,sha256=5_xKYEpvDhaixRxmSTBlyX_jt8ssjHwHzX9VodcrtJw,3213
 svx/providers/__init__.py,sha256=SzlSWpZSUIptbSrAnGfi0d0NX4hYTpT0ObWpYyskDdA,2634
 svx/providers/base.py,sha256=YoiI8KWVRGISh7dx9XXPr1Q1a7ZDu8vfeJFlPbcKr20,2695
 svx/providers/mistral.py,sha256=vrBatNZg0zGNkJ5Qfnfz6ZwP6QtBgIt9sT_w59zkSO0,6636
-svx/ui/qt_app.py,sha256=0XoAk-6vCJguYq1ZVZA5zm-00442HOds_ibDHoDz-J0,18466
-supervoxtral-0.1.3.dist-info/METADATA,sha256=SpB9BeL_dbolMTM6UydjskMHHy_gnA4QJ1RfZI-Q3kE,753
-supervoxtral-0.1.3.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-supervoxtral-0.1.3.dist-info/entry_points.txt,sha256=phJhRy3VkYHC6AR_tUB5CypHzG0ePRR9sB13HWE1vEg,36
-supervoxtral-0.1.3.dist-info/licenses/LICENSE,sha256=fCEBKmC4i-1WZAwoKjKWegfDd8qNsG8ECB7JyqoswyQ,1064
-supervoxtral-0.1.3.dist-info/RECORD,,
+svx/ui/qt_app.py,sha256=yww_sH0zFI2HEQTRFcR1LW0N4duFqlW-HDo6SWelkWo,19975
+supervoxtral-0.1.5.dist-info/METADATA,sha256=Nq09MVEhqC5mjfVQCNaL2LL4HSgaQB-aQdJTp0-7Gk4,753
+supervoxtral-0.1.5.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+supervoxtral-0.1.5.dist-info/entry_points.txt,sha256=phJhRy3VkYHC6AR_tUB5CypHzG0ePRR9sB13HWE1vEg,36
+supervoxtral-0.1.5.dist-info/licenses/LICENSE,sha256=fCEBKmC4i-1WZAwoKjKWegfDd8qNsG8ECB7JyqoswyQ,1064
+supervoxtral-0.1.5.dist-info/RECORD,,

svx/cli.py

@@ -72,7 +72,7 @@ def config_show() -> None:
     user_prompt_file = cfg.user_prompt_dir / "user.md"
 
     defaults_section = asdict(cfg.defaults)
-    prompt_section = asdict(cfg.prompt)
+    prompt_section = {k: asdict(e) for k, e in cfg.prompt.prompts.items()}
 
     # Resolve prompt source (same logic as record command, but read-only)
     resolved_prompt = cfg.resolve_prompt(None, None)

svx/core/config.py

@@ -242,13 +242,15 @@ def init_user_config(force: bool = False, prompt_file: Path | None = None) -> Pa
         "copy = true\n\n"
         '# Log level: "DEBUG" | "INFO" | "WARNING" | "ERROR"\n'
         'log_level = "INFO"\n\n'
-        "[prompt]\n"
+        "[prompt.default]\n"
         "# Default user prompt source:\n"
         "# - Option 1: Use a file (recommended)\n"
         f'file = "{str(prompt_file)}"\n'
         "#\n"
         "# - Option 2: Inline prompt (less recommended for long text)\n"
         '# text = "Please transcribe the audio and provide a concise summary in French."\n'
+        "#\n"
+        "# For multiple prompts in future, add [prompt.other] sections.\n"
     )
 
     if not USER_CONFIG_FILE.exists() or force:
@@ -282,11 +284,16 @@ class DefaultsConfig:
 
 
 @dataclass
-class PromptConfig:
+class PromptEntry:
     text: str | None = None
     file: str | None = None
 
 
+@dataclass
+class PromptConfig:
+    prompts: dict[str, PromptEntry] = field(default_factory=lambda: {"default": PromptEntry()})
+
+
 @dataclass
 class Config:
     providers: dict[str, ProviderConfig] = field(default_factory=dict)
@@ -356,11 +363,39 @@ class Config:
                 providers_data[name] = ProviderConfig(api_key=api_key)
         # Prompt
         prompt_raw = user_config.get("prompt", {})
-        prompt_data = {
-            "text": prompt_raw.get("text") if isinstance(prompt_raw.get("text"), str) else None,
-            "file": prompt_raw.get("file") if isinstance(prompt_raw.get("file"), str) else None,
-        }
-        prompt = PromptConfig(**prompt_data)
+        prompts_data: dict[str, PromptEntry] = {}
+        if isinstance(prompt_raw, dict):
+            if any(k in prompt_raw for k in ["text", "file"]):  # old flat style
+                logging.warning(
+                    "Old [prompt] format detected in %s; "
+                    "please migrate to [prompt.default] manually.",
+                    USER_CONFIG_FILE,
+                )
+                entry = PromptEntry(
+                    text=prompt_raw.get("text")
+                    if isinstance(prompt_raw.get("text"), str)
+                    else None,
+                    file=prompt_raw.get("file")
+                    if isinstance(prompt_raw.get("file"), str)
+                    else None,
+                )
+                prompts_data["default"] = entry
+            else:  # new nested style
+                for key, entry_raw in prompt_raw.items():
+                    if isinstance(entry_raw, dict):
+                        entry = PromptEntry(
+                            text=entry_raw.get("text")
+                            if isinstance(entry_raw.get("text"), str)
+                            else None,
+                            file=entry_raw.get("file")
+                            if isinstance(entry_raw.get("file"), str)
+                            else None,
+                        )
+                        prompts_data[key] = entry
+        # Ensure "default" always exists
+        if "default" not in prompts_data:
+            prompts_data["default"] = PromptEntry()
+        prompt = PromptConfig(prompts=prompts_data)
         data = {
             "defaults": defaults,
             "providers": providers_data,
@@ -376,7 +411,7 @@ class Config:
     def resolve_prompt(self, inline: str | None = None, file_path: Path | None = None) -> str:
         from svx.core.prompt import resolve_user_prompt
 
-        return resolve_user_prompt(self, inline, file_path, self.user_prompt_dir)
+        return resolve_user_prompt(self, inline, file_path, self.user_prompt_dir, key="default")
 
     def get_provider_config(self, name: str) -> dict[str, Any]:
         return asdict(self.providers.get(name, ProviderConfig()))

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

svx/core/prompt.py

@@ -12,9 +12,10 @@ 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
+from .config import USER_PROMPT_DIR, Config, PromptEntry
 
 __all__ = [
     "read_text_file",
@@ -68,16 +69,16 @@ def resolve_user_prompt(
     inline: str | None = None,
     file: Path | None = None,
     user_prompt_dir: Path | None = None,
+    key: str | None = None,
 ) -> str:
     """
     Resolve the effective user prompt from multiple sources, by priority:
 
     1) inline text (CLI --user-prompt)
     2) explicit file (CLI --user-prompt-file)
-    3) user config inline text (cfg.prompt.text)
-    4) user config file path (cfg.prompt.file)
-    5) user prompt dir file (user_prompt_dir / 'user.md')
-    6) literal fallback: "What's in this audio?"
+    3) user config prompt for key (cfg.prompt.prompts[key or "default"])
+    4) user prompt dir file (user_prompt_dir / 'user.md')
+    5) literal fallback: "What's in this audio?"
 
     Returns the first non-empty string after stripping.
     """
@@ -94,17 +95,18 @@ def resolve_user_prompt(
             logging.warning("Failed to read user prompt file: %s", p)
             return ""
 
-    def _from_user_cfg() -> str:
+    def _from_user_cfg(key: str) -> str:
         try:
-            cfg_prompt = cfg.prompt
-            cfg_text = cfg_prompt.text
-            if isinstance(cfg_text, str) and cfg_text.strip():
-                return cfg_text.strip()
-            cfg_file = cfg_prompt.file
-            if isinstance(cfg_file, str) and cfg_file.strip():
-                return read_text_file(Path(cfg_file).expanduser()).strip()
+            entry = cfg.prompt.prompts.get(key, PromptEntry())
+            if entry.text and entry.text.strip():
+                return entry.text.strip()
+            if entry.file:
+                file_path = Path(entry.file).expanduser()
+                if not file_path.is_absolute():
+                    file_path = (user_prompt_dir or cfg.user_prompt_dir) / entry.file
+                return read_text_file(file_path).strip()
         except Exception:
-            logging.debug("User config prompt processing failed.", exc_info=True)
+            logging.debug("User config prompt processing failed for key '%s'.", key, exc_info=True)
         return ""
 
     def _from_user_prompt_dir() -> str:
@@ -119,22 +121,46 @@ def resolve_user_prompt(
             )
         return ""
 
-    suppliers = [
-        lambda: _strip(inline),
-        lambda: _read(file),
-        _from_user_cfg,
-        _from_user_prompt_dir,
+    key = key or "default"
+
+    # 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:
@@ -150,7 +176,7 @@ def init_user_prompt_file(force: bool = False) -> Path:
     path = USER_PROMPT_DIR / "user.md"
     if not path.exists() or force:
         example_prompt = """
-- Transcribe the input audio file.
+- Transcribe the input audio file. If the audio if empty, just respond "no audio detected".
 - Do not respond to any question in the audio. Just transcribe.
 - DO NOT TRANSLATE.
 - Responde only with the transcription. Do not provide explanations or notes.
@@ -163,3 +189,23 @@ def init_user_prompt_file(force: bool = False) -> Path:
         except Exception as e:
             logging.debug("Could not initialize user prompt file %s: %s", path, e)
     return path
+
+
+def resolve_prompt_entry(entry: PromptEntry, user_prompt_dir: Path) -> str:
+    """
+    Resolve the prompt from a single PromptEntry (text or file).
+
+    - Prioritizes text if present and non-empty.
+    - Falls back to reading the file (expands ~ and resolves relative to user_prompt_dir).
+    - Returns empty string if neither is valid.
+    """
+    if entry.text and entry.text.strip():
+        return entry.text.strip()
+
+    if entry.file:
+        file_path = Path(entry.file).expanduser()
+        if not file_path.is_absolute():
+            file_path = user_prompt_dir / entry.file
+        return read_text_file(file_path).strip()
+
+    return ""

svx/ui/qt_app.py

@@ -37,6 +37,7 @@ from PySide6.QtWidgets import (
 import svx.core.config as config
 from svx.core.config import Config
 from svx.core.pipeline import RecordingPipeline
+from svx.core.prompt import resolve_user_prompt
 
 __all__ = ["RecorderWindow", "run_gui"]
 
@@ -239,11 +240,11 @@ class RecorderWorker(QObject):
         self.cancel_requested = True
         self._stop_event.set()
 
-    def _resolve_user_prompt(self) -> str:
+    def _resolve_user_prompt(self, key: str) -> str:
         """
-        Determine the final user prompt using the shared resolver.
+        Determine the final user prompt using the shared resolver for the given key.
         """
-        return self.cfg.resolve_prompt(self.user_prompt, self.user_prompt_file)
+        return resolve_user_prompt(self.cfg, None, None, self.cfg.user_prompt_dir, key=key)
 
     def run(self) -> None:
         """
@@ -272,10 +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()
+            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)
@@ -310,6 +340,7 @@ class RecorderWindow(QWidget):
         self.user_prompt_file = user_prompt_file
         self.save_all = save_all
         self.outfile_prefix = outfile_prefix
+        self.prompt_keys = sorted(self.cfg.prompt.prompts.keys())
 
         # Background worker (create early for signal connections)
         self._worker = RecorderWorker(
@@ -381,12 +412,17 @@ 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_button_clicked("transcribe"))
+        self._transcribe_btn.clicked.connect(
+            lambda checked=False, m="transcribe": self._on_mode_selected(m)
+        )
         button_layout.addWidget(self._transcribe_btn)
-        self._prompt_btn = QPushButton("Prompt")
-        self._prompt_btn.setToolTip("Stop and transcribe with prompt")
-        self._prompt_btn.clicked.connect(lambda: self._on_button_clicked("prompt"))
-        button_layout.addWidget(self._prompt_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 checked=False, k=key: self._on_mode_selected(k))
+            self._prompt_buttons[key] = btn
+            button_layout.addWidget(btn)
         self._cancel_btn = QPushButton("Cancel")
         self._cancel_btn.setObjectName("cancel_btn")
         self._cancel_btn.setToolTip("Stop recording and quit without processing")
@@ -397,6 +433,8 @@ class RecorderWindow(QWidget):
         button_widget.setLayout(button_layout)
         layout.addWidget(button_widget, 0, Qt.AlignmentFlag.AlignCenter)
 
+        self._action_buttons = [self._transcribe_btn] + list(self._prompt_buttons.values())
+
         # Keyboard shortcut: Esc to stop
         stop_action = QAction(self)
         stop_action.setShortcut(QKeySequence.StandardKey.Cancel)  # Esc
@@ -456,17 +494,17 @@ class RecorderWindow(QWidget):
         self._worker.cancel()
         super().closeEvent(event)
 
-    def _on_button_clicked(self, mode: str) -> None:
-        self._transcribe_btn.setEnabled(False)
-        self._prompt_btn.setEnabled(False)
+    def _on_mode_selected(self, mode: str) -> None:
+        for btn in self._action_buttons:
+            btn.setEnabled(False)
         self._cancel_btn.setEnabled(False)
         self._status_label.setText("Stopping and processing...")
         self._worker.set_mode(mode)
         self._worker.stop()
 
     def _on_cancel_clicked(self) -> None:
-        self._transcribe_btn.setEnabled(False)
-        self._prompt_btn.setEnabled(False)
+        for btn in self._action_buttons:
+            btn.setEnabled(False)
         self._cancel_btn.setEnabled(False)
         self._status_label.setText("Canceling...")
         self._worker.cancel()