supervoxtral 0.1.4__py3-none-any.whl → 0.1.5__py3-none-any.whl

{supervoxtral-0.1.4.dist-info → supervoxtral-0.1.5.dist-info}/METADATA

@@ -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.dist-info → supervoxtral-0.1.5.dist-info}/RECORD

@@ -4,15 +4,15 @@ 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=e2tTGjjPcUYFctB28Ha90G-W44mF_0eWey1zpSyZkBo,16095
-svx/core/pipeline.py,sha256=nqvCgK5Pbyx18mfACrN_mIDt546Bh7fKA6MF4XG1hxM,10637
-svx/core/prompt.py,sha256=yO8UbpFg7n1IT7wFjSQ7NUTbrqxuwPhdnxkTH4Iu7XU,5967
+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=6LOMeMjkMmYylu6H_prDRmPDsL0s4PVMZqfbflByCMs,18808
-supervoxtral-0.1.4.dist-info/METADATA,sha256=0w_i5geOKu8F9x7eviNboDNt-PTy6FS3WHe3cCx4eHg,753
-supervoxtral-0.1.4.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-supervoxtral-0.1.4.dist-info/entry_points.txt,sha256=phJhRy3VkYHC6AR_tUB5CypHzG0ePRR9sB13HWE1vEg,36
-supervoxtral-0.1.4.dist-info/licenses/LICENSE,sha256=fCEBKmC4i-1WZAwoKjKWegfDd8qNsG8ECB7JyqoswyQ,1064
-supervoxtral-0.1.4.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/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

@@ -12,6 +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:

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")