APEX/BrowserUse_and_ComputerUse_skills
5
0
Fork 0
Code Issues 6 Pull requests 1 Projects 1 Releases Packages Wiki Activity Actions

fix: address voice mode PR review (streaming TTS, prompt cache, _vprint)

Browse source 
Bug A: Replace stale _HAS_ELEVENLABS/_HAS_AUDIO boolean imports with
lazy import function calls (_import_elevenlabs, _import_sounddevice).
The old constants no longer exist in tts_tool -- the try/except
silently swallowed the ImportError, leaving streaming TTS dead.

Bug B: Use user message prefix instead of modifying system prompt for
voice mode instruction. Changing ephemeral_system_prompt mid-session
invalidates the prompt cache. Now the concise-response hint is
prepended to the user_message passed to run_conversation while
conversation_history keeps the original text.

Minor: Add force parameter to _vprint so critical error messages
(max retries, non-retryable errors, API failures) are always shown
even during streaming TTS playback.

Tests: 15 new tests in test_voice_cli_integration.py covering all
three fixes -- lazy import activation, message prefix behavior,
history cleanliness, system prompt stability, and AST verification
that all critical _vprint calls use force=True.
This commit is contained in:
0xbyt4 2026-03-10 03:43:03 +03:00
parent fc893f98f4
commit a78249230c
3 changed files with 361 additions and 29 deletions
Download patch file Download diff file Expand all files Collapse all files

28
run_agent.py
View file

@ -816,9 +816,13 @@ class AIAgent:
else:
print(f"📊 Context limit: {self.context_compressor.context_length:,} tokens (auto-compression disabled)")
def _vprint(self, *args, **kwargs):
"""Verbose print — suppressed when streaming TTS is active."""
if getattr(self, "_stream_callback", None) is not None:
def _vprint(self, *args, force: bool = False, **kwargs):
"""Verbose print — suppressed when streaming TTS is active.
Pass ``force=True`` for error/warning messages that should always be
shown even during streaming TTS playback.
"""
if not force and getattr(self, "_stream_callback", None) is not None:
return
print(*args, **kwargs)
@ -4641,7 +4645,7 @@ class AIAgent:
}
else:
# First message was truncated - mark as failed
self._vprint(f"{self.log_prefix}❌ First response truncated - cannot recover")
self._vprint(f"{self.log_prefix}❌ First response truncated - cannot recover", force=True)
self._persist_session(messages, conversation_history)
return {
"final_response": None,
@ -4783,9 +4787,9 @@ class AIAgent:
error_type = type(api_error).__name__
error_msg = str(api_error).lower()
self._vprint(f"{self.log_prefix}⚠️ API call failed (attempt {retry_count}/{max_retries}): {error_type}")
self._vprint(f"{self.log_prefix}⚠️ API call failed (attempt {retry_count}/{max_retries}): {error_type}", force=True)
self._vprint(f"{self.log_prefix} ⏱️ Time elapsed before failure: {elapsed_time:.2f}s")
self._vprint(f"{self.log_prefix} 📝 Error: {str(api_error)[:200]}")
self._vprint(f"{self.log_prefix} 📝 Error: {str(api_error)[:200]}", force=True)
self._vprint(f"{self.log_prefix} 📊 Request context: {len(api_messages)} messages, ~{approx_tokens:,} tokens, {len(self.tools) if self.tools else 0} tools")
# Check for interrupt before deciding to retry
@ -4839,7 +4843,7 @@ class AIAgent:
restart_with_compressed_messages = True
break
else:
self._vprint(f"{self.log_prefix}❌ Payload too large and cannot compress further.")
self._vprint(f"{self.log_prefix}❌ Payload too large and cannot compress further.", force=True)
logging.error(f"{self.log_prefix}413 payload too large. Cannot compress further.")
self._persist_session(messages, conversation_history)
return {
@ -4948,8 +4952,8 @@ class AIAgent:
self._dump_api_request_debug(
api_kwargs, reason="non_retryable_client_error", error=api_error,
)
self._vprint(f"{self.log_prefix}❌ Non-retryable client error detected. Aborting immediately.")
self._vprint(f"{self.log_prefix} 💡 This type of error won't be fixed by retrying.")
self._vprint(f"{self.log_prefix}❌ Non-retryable client error detected. Aborting immediately.", force=True)
self._vprint(f"{self.log_prefix} 💡 This type of error won't be fixed by retrying.", force=True)
logging.error(f"{self.log_prefix}Non-retryable client error: {api_error}")
self._persist_session(messages, conversation_history)
return {
@ -5081,7 +5085,7 @@ class AIAgent:
continue
else:
# Max retries - discard this turn and save as partial
self._vprint(f"{self.log_prefix}❌ Max retries (2) for incomplete scratchpad. Saving as partial.")
self._vprint(f"{self.log_prefix}❌ Max retries (2) for incomplete scratchpad. Saving as partial.", force=True)
self._incomplete_scratchpad_retries = 0
rolled_back_messages = self._get_messages_up_to_last_assistant(messages)
@ -5176,7 +5180,7 @@ class AIAgent:
self._vprint(f"{self.log_prefix}⚠️ Unknown tool '{invalid_preview}' — sending error to model for self-correction ({self._invalid_tool_retries}/3)")
if self._invalid_tool_retries >= 3:
self._vprint(f"{self.log_prefix}❌ Max retries (3) for invalid tool calls exceeded. Stopping as partial.")
self._vprint(f"{self.log_prefix}❌ Max retries (3) for invalid tool calls exceeded. Stopping as partial.", force=True)
self._invalid_tool_retries = 0
self._persist_session(messages, conversation_history)
return {
@ -5350,7 +5354,7 @@ class AIAgent:
self._vprint(f"{self.log_prefix}🔄 Retrying API call ({self._empty_content_retries}/3)...")
continue
else:
self._vprint(f"{self.log_prefix}❌ Max retries (3) for empty content exceeded.")
self._vprint(f"{self.log_prefix}❌ Max retries (3) for empty content exceeded.", force=True)
self._empty_content_retries = 0
# If a prior tool_calls turn had real content, salvage it: