refactor: standardize developer text and identifiers in English

speech_to_speech/LLM/chat_completions_language_model.py

@@ -196,7 +196,7 @@ class ChatCompletionsApiModelHandler(BaseOpenAICompatibleHandler):
         if self.stream:
             create_kwargs["stream_options"] = {"include_usage": True}
         
-        # Svuota i parametri dei tool per evitare il blocco 400 di NVIDIA NIM
+        # Remove tool parameters to avoid NVIDIA NIM's HTTP 400 response.
         create_kwargs.pop("tools", None)
         create_kwargs.pop("tool_choice", None)
         

speech_to_speech/LLM/lm_output_processor.py

@@ -4,7 +4,7 @@ LLM Output Processor
 Intercepts LLM output to:
 1. Extract tool calls and send them via text_output_queue
 2. Forward clean text to TTS pipeline
-3. 2026-09-25: SANITIZE APIPILOT internal markers before clients / TTS (anti-leak tecnico)
+3. Sanitize ApiPilot internal markers before sending output to clients or TTS
 """
 
 from __future__ import annotations
@@ -17,16 +17,15 @@ from queue import Queue
 from speech_to_speech.baseHandler import BaseHandler
 from speech_to_speech.pipeline.events import AssistantTextEvent, ResponseFailedEvent, TokenUsageEvent
 
-# 2026-09-25 SANITIZE APIPILOT CALL/RESULT markers in LLM output BEFORE:
-#   (a) AssistantTextEvent viene mandato ai client WS (e loggato come <<< TEXT:/ASSISTANT:)
-#   (b) TTSInput viene mandato a Qwen3-TTS (che lo pronuncerebbe ad alta voce).
-# Formati osservati reali oggi (upstream Vocero start_pipeline_rag):
-#   1) <<<APIPILOT_CALL:NAME=tool,ARGUMENTS=json>>>   standard 3x
+# Sanitize ApiPilot CALL/RESULT markers before emitting AssistantTextEvent
+# to WebSocket clients or TTSInput to Qwen3-TTS, which would speak the markers.
+# Observed formats from upstream Vocero start_pipeline_rag:
+#   1) <<<APIPILOT_CALL:NAME=tool,ARGUMENTS=json>>>   standard triple brackets
 #   2) <APIPILOT_CALL:NAME=get_user_briefing,ARGUMENTS={"format":"voice"}
-#                                 singolo '<' '>' + args inventati da AI (format=voice)
-#   3) <<<APIPILOT_CALL:...}>  \n>>                      spezzato multi-riga
-#   4) >>>APIPILOT_CALL:...<<<                            invertito (errore sintassi AI)
-#   5) <<<APIPILOT_RESULT:PASS2>>> + blocco result.
+#                                 single brackets and model-generated arguments
+#   3) <<<APIPILOT_CALL:...}>  \n>>                      split across lines
+#   4) >>>APIPILOT_CALL:...<<<                            inverted brackets
+#   5) <<<APIPILOT_RESULT:PASS2>>> followed by a result block
 _APIPILOT_CALL_NORM = re.compile(
     r"[<]{1,3}\s*APIPILOT_CALL:NAME=([A-Za-z0-9_.-]+),ARGUMENTS=(.*?)[>]{1,3}",
     re.IGNORECASE | re.DOTALL,
@@ -64,7 +63,7 @@ def _sanitize_apipilot_before_client_and_tts(text: str) -> tuple[str, bool, str]
     if _APIPILOT_RESULT.search(new_text):
         new_text = _APIPILOT_RESULT.sub(" ", new_text)
         found_result = True
-    # safety catchall frammenti marker senza wrapper (se marker troncato mid-stream)
+    # Catch marker fragments without a wrapper, including mid-stream truncation.
     low = new_text.lower()
     if "apipilot" in low and ("call" in low or "result" in low or "name=" in low or "arguments=" in low):
         new_text = re.sub(r"(?i)\bAPIPILOT(?:_CALL|_RESULT)?\b", " ", new_text)
@@ -184,8 +183,8 @@ class LMOutputProcessor(BaseHandler[LLMOut, TTSIn]):
 
         logger.debug(f"LM processor: text='{lm_output.text}', tools={lm_output.tools}")
 
-        # 2026-09-25 SANITIZE SINGOLO PUNTO CENTRALE: PRIMA di AssistantTextEvent (client/log)
-        #    E PRIMA di TTSInput (Qwen3-TTS che pronuncerebbe marker APIPILOT CALL).
+        # Sanitize centrally before AssistantTextEvent and TTSInput so neither
+        # clients nor Qwen3-TTS receive internal ApiPilot markers.
         clean_text = lm_output.text
         any_sanitized = False
         sanitize_tag = ""
@@ -193,14 +192,14 @@ class LMOutputProcessor(BaseHandler[LLMOut, TTSIn]):
             clean_text, any_sanitized, sanitize_tag = _sanitize_apipilot_before_client_and_tts(clean_text)
             if any_sanitized:
                 logger.warning(
-                    "[LM-OUTPUT-APIPILOT-SANITIZE] %s — tool=%s rawLen=%d cleanLen=%d (rimosso / sostituito con placeholder spagnolo PRIMA di client + TTS).",
+                    "[LM-OUTPUT-APIPILOT-SANITIZE] %s — tool=%s rawLen=%d cleanLen=%d (removed or replaced with the Spanish placeholder before client/TTS output).",
                     sanitize_tag or "-",
                     (sanitize_tag if sanitize_tag else "marker"),
                     len(lm_output.text or ""),
                     len(clean_text or ""),
                 )
-                # evita che lo stesso chunk (marker solo) arrivi a TTS come "" → Hello.
-                # Se dopo sanitize testo vuoto MA avevamo trovato marker → placeholder.
+                # Use the placeholder when sanitization removes the entire chunk,
+                # avoiding empty text that would trigger the TTS greeting fallback.
                 if not clean_text.strip():
                     clean_text = _APIPILOT_SPANISH_PLACEHOLDER