refactor: SDK Architecture - Centralize Logging and Retry Logic (#1212)

Merges centralized logging (_logging.py, 152 files migrated) and resilience utility (utils/resilience.py). Also fixes CI/CD workflows and test fixtures.

Closes #1131 #1132

Author: MervinPraison

.github/workflows/test-core.yml

@@ -64,9 +64,10 @@ jobs:
           || echo "Some integration tests failed"
 
     - name: Upload coverage to Codecov
+      if: always()
       uses: codecov/codecov-action@v5
       with:
-        token: ${{ secrets.CODECOV_TOKEN }}
-        file: src/praisonai/coverage.xml
+        token: ${{ secrets.CODECOV_TOKEN || '' }}
+        files: src/praisonai/coverage.xml
         flags: core-tests
         fail_ci_if_error: false

.github/workflows/test-optimized.yml

@@ -157,8 +157,8 @@ jobs:
       if: matrix.python-version == '3.11'
       uses: codecov/codecov-action@v5
       with:
-        token: ${{ secrets.CODECOV_TOKEN }}
-        file: src/praisonai/coverage.xml
+        token: ${{ secrets.CODECOV_TOKEN || '' }}
+        files: src/praisonai/coverage.xml
         flags: main-tests
         fail_ci_if_error: false
 
@@ -301,8 +301,10 @@ jobs:
     steps:
     - name: Check if Google key is available
       id: check-key
+      env:
+        GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
       run: |
-        if [ -n "${{ secrets.GOOGLE_API_KEY }}" ]; then
+        if [ -n "$GOOGLE_API_KEY" ]; then
           echo "has_key=true" >> $GITHUB_OUTPUT
         else
           echo "has_key=false" >> $GITHUB_OUTPUT
@@ -356,8 +358,10 @@ jobs:
     steps:
     - name: Check if Groq key is available
       id: check-key
+      env:
+        GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
       run: |
-        if [ -n "${{ secrets.GROQ_API_KEY }}" ]; then
+        if [ -n "$GROQ_API_KEY" ]; then
           echo "has_key=true" >> $GITHUB_OUTPUT
         else
           echo "has_key=false" >> $GITHUB_OUTPUT
@@ -411,8 +415,10 @@ jobs:
     steps:
     - name: Check if xAI key is available
       id: check-key
+      env:
+        XAI_API_KEY: ${{ secrets.XAI_API_KEY }}
       run: |
-        if [ -n "${{ secrets.XAI_API_KEY }}" ]; then
+        if [ -n "$XAI_API_KEY" ]; then
           echo "has_key=true" >> $GITHUB_OUTPUT
         else
           echo "has_key=false" >> $GITHUB_OUTPUT
@@ -466,8 +472,10 @@ jobs:
     steps:
     - name: Check if Cohere key is available
       id: check-key
+      env:
+        COHERE_API_KEY: ${{ secrets.COHERE_API_KEY }}
       run: |
-        if [ -n "${{ secrets.COHERE_API_KEY }}" ]; then
+        if [ -n "$COHERE_API_KEY" ]; then
           echo "has_key=true" >> $GITHUB_OUTPUT
         else
           echo "has_key=false" >> $GITHUB_OUTPUT

docker/Dockerfile.chat

@@ -16,7 +16,7 @@ RUN mkdir -p /root/.praison
 # Install Python packages (using latest versions)
 RUN pip install --no-cache-dir \
     praisonai_tools \
-    "praisonai>=4.5.88" \
+    "praisonai>=4.5.89" \
     "praisonai[chat]" \
     "embedchain[github,youtube]"
 

docker/Dockerfile.dev

@@ -20,7 +20,7 @@ RUN mkdir -p /root/.praison
 # Install Python packages (using latest versions)
 RUN pip install --no-cache-dir \
     praisonai_tools \
-    "praisonai>=4.5.88" \
+    "praisonai>=4.5.89" \
     "praisonai[ui]" \
     "praisonai[chat]" \
     "praisonai[realtime]" \

docker/Dockerfile.ui

@@ -16,7 +16,7 @@ RUN mkdir -p /root/.praison
 # Install Python packages (using latest versions)
 RUN pip install --no-cache-dir \
     praisonai_tools \
-    "praisonai>=4.5.88" \
+    "praisonai>=4.5.89" \
     "praisonai[ui]" \
     "praisonai[crewai]"
 

src/praisonai-agents/praisonaiagents/agent/agent.py

@@ -2,6 +2,7 @@
 import time
 import json
 import logging
+from praisonaiagents._logging import get_logger
 import asyncio
 import contextlib
 import threading
@@ -16,7 +17,7 @@
 from .session_manager import SessionManagerMixin
 
 # Module-level logger for thread safety errors and debugging
-logger = logging.getLogger(__name__)
+logger = get_logger(__name__)
 
 # ============================================================================
 # Performance: Lazy imports for heavy dependencies
@@ -195,7 +196,6 @@ def __init__(self, agent_name: str, total_cost: float, max_budget: float):
             f"${total_cost:.4f} >= ${max_budget:.4f}"
         )
 
-
 class Agent(ToolExecutionMixin, ChatHandlerMixin, SessionManagerMixin):
     # Class-level counter for generating unique display names for nameless agents
     _agent_counter = 0
@@ -255,16 +255,16 @@ def _get_default_model(cls):
     def _configure_logging(cls):
         """Configure logging settings once for all agent instances."""
         # Configure logging to suppress unwanted outputs
-        logging.getLogger("litellm").setLevel(logging.WARNING)
+        get_logger("litellm").setLevel(logging.WARNING)
 
         # Allow httpx logging when LOGLEVEL=debug, otherwise suppress it
         loglevel = os.environ.get('LOGLEVEL', 'INFO').upper()
         if loglevel == 'DEBUG':
-            logging.getLogger("httpx").setLevel(logging.INFO)
-            logging.getLogger("httpcore").setLevel(logging.INFO)
+            get_logger("httpx").setLevel(logging.INFO)
+            get_logger("httpcore").setLevel(logging.INFO)
         else:
-            logging.getLogger("httpx").setLevel(logging.WARNING)
-            logging.getLogger("httpcore").setLevel(logging.WARNING)
+            get_logger("httpx").setLevel(logging.WARNING)
+            get_logger("httpcore").setLevel(logging.WARNING)
 
     @classmethod
     def from_template(
@@ -2771,7 +2771,7 @@ def run_autonomous(
                         "agent_name": getattr(self, 'name', None),
                     })
                 elif self.autonomy_config.get("observe"):
-                    logging.getLogger(__name__).info(
+                    get_logger(__name__).info(
                         f"[autonomy] iteration={iterations} stage={stage} "
                         f"response_len={len(response_str)}"
                     )
@@ -3161,7 +3161,7 @@ async def main():
                         "agent_name": getattr(self, 'name', None),
                     })
                 elif self.autonomy_config.get("observe"):
-                    logging.getLogger(__name__).info(
+                    get_logger(__name__).info(
                         f"[autonomy-async] iteration={iterations} stage={stage} "
                         f"response_len={len(response_str)}"
                     )
@@ -6337,7 +6337,7 @@ def _chat_impl(self, prompt, temperature, tools, output_json, output_pydantic, r
         self._final_display_shown = False
 
         # Log all parameter values when in debug mode
-        if logging.getLogger().getEffectiveLevel() == logging.DEBUG:
+        if get_logger().getEffectiveLevel() == logging.DEBUG:
             param_info = {
                 "prompt": str(prompt)[:100] + "..." if isinstance(prompt, str) and len(str(prompt)) > 100 else str(prompt),
                 "temperature": temperature,
@@ -6503,7 +6503,7 @@ def _chat_impl(self, prompt, temperature, tools, output_json, output_pydantic, r
                     self._persist_message("assistant", response_text)
 
                     # Log completion time if in debug mode
-                    if logging.getLogger().getEffectiveLevel() == logging.DEBUG:
+                    if get_logger().getEffectiveLevel() == logging.DEBUG:
                         total_time = time.time() - start_time
                         logging.debug(f"Agent.chat completed in {total_time:.2f} seconds")
 
@@ -6846,7 +6846,7 @@ async def _achat_impl(self, prompt, temperature, tools, output_json, output_pyda
         self._final_display_shown = False
 
         # Log all parameter values when in debug mode
-        if logging.getLogger().getEffectiveLevel() == logging.DEBUG:
+        if get_logger().getEffectiveLevel() == logging.DEBUG:
             param_info = {
                 "prompt": str(prompt)[:100] + "..." if isinstance(prompt, str) and len(str(prompt)) > 100 else str(prompt),
                 "temperature": temperature,
@@ -6950,7 +6950,7 @@ async def _achat_impl(self, prompt, temperature, tools, output_json, output_pyda
 
                     self.chat_history.append({"role": "assistant", "content": response_text})
 
-                    if logging.getLogger().getEffectiveLevel() == logging.DEBUG:
+                    if get_logger().getEffectiveLevel() == logging.DEBUG:
                         total_time = time.time() - start_time
                         logging.debug(f"Agent.achat completed in {total_time:.2f} seconds")
 
@@ -6969,7 +6969,7 @@ async def _achat_impl(self, prompt, temperature, tools, output_json, output_pyda
                     # Rollback chat history if LLM call fails
                     self.chat_history = self.chat_history[:chat_history_length]
                     _get_display_functions()['display_error'](f"Error in LLM chat: {e}")
-                    if logging.getLogger().getEffectiveLevel() == logging.DEBUG:
+                    if get_logger().getEffectiveLevel() == logging.DEBUG:
                         total_time = time.time() - start_time
                         logging.debug(f"Agent.achat failed in {total_time:.2f} seconds: {str(e)}")
                     return None
@@ -7058,7 +7058,7 @@ async def _achat_impl(self, prompt, temperature, tools, output_json, output_pyda
                             tools=formatted_tools,
                         )
                         result = await self._achat_completion(response, tools)
-                        if logging.getLogger().getEffectiveLevel() == logging.DEBUG:
+                        if get_logger().getEffectiveLevel() == logging.DEBUG:
                             total_time = time.time() - start_time
                             logging.debug(f"Agent.achat completed in {total_time:.2f} seconds")
                         # Execute callback after tool completion
@@ -7072,7 +7072,7 @@ async def _achat_impl(self, prompt, temperature, tools, output_json, output_pyda
                             response_format={"type": "json_object"}
                         )
                         response_text = response.choices[0].message.content
-                        if logging.getLogger().getEffectiveLevel() == logging.DEBUG:
+                        if get_logger().getEffectiveLevel() == logging.DEBUG:
                             total_time = time.time() - start_time
                             logging.debug(f"Agent.achat completed in {total_time:.2f} seconds")
                         # Execute callback after JSON/Pydantic completion
@@ -7114,7 +7114,7 @@ async def _achat_impl(self, prompt, temperature, tools, output_json, output_pyda
                                         # Return the original response without reflection
                                         self.chat_history.append({"role": "user", "content": original_prompt})
                                         self.chat_history.append({"role": "assistant", "content": response_text})
-                                        if logging.getLogger().getEffectiveLevel() == logging.DEBUG:
+                                        if get_logger().getEffectiveLevel() == logging.DEBUG:
                                             total_time = time.time() - start_time
                                             logging.debug(f"Agent.achat completed in {total_time:.2f} seconds")
                                         return await self._atrigger_after_agent_hook(original_prompt, response_text, start_time)
@@ -7166,7 +7166,7 @@ async def _achat_impl(self, prompt, temperature, tools, output_json, output_pyda
                                         break
                                     continue
 
-                        if logging.getLogger().getEffectiveLevel() == logging.DEBUG:
+                        if get_logger().getEffectiveLevel() == logging.DEBUG:
                             total_time = time.time() - start_time
                             logging.debug(f"Agent.achat completed in {total_time:.2f} seconds")
 
@@ -7183,13 +7183,13 @@ async def _achat_impl(self, prompt, temperature, tools, output_json, output_pyda
                             return None
                 except Exception as e:
                     _get_display_functions()['display_error'](f"Error in chat completion: {e}")
-                    if logging.getLogger().getEffectiveLevel() == logging.DEBUG:
+                    if get_logger().getEffectiveLevel() == logging.DEBUG:
                         total_time = time.time() - start_time
                         logging.debug(f"Agent.achat failed in {total_time:.2f} seconds: {str(e)}")
                     return None
         except Exception as e:
             _get_display_functions()['display_error'](f"Error in achat: {e}")
-            if logging.getLogger().getEffectiveLevel() == logging.DEBUG:
+            if get_logger().getEffectiveLevel() == logging.DEBUG:
                 total_time = time.time() - start_time
                 logging.debug(f"Agent.achat failed in {total_time:.2f} seconds: {str(e)}")
             return None
@@ -7271,7 +7271,6 @@ async def _achat_completion(self, response, tools, reasoning_steps=False):
                     _get_display_functions()['display_error'](f"Error executing tool {function_name}: {e}")
                     results.append(None)
 
-
             # If we have results, format them into a response
             if results:
                 formatted_results = "\n".join([str(r) for r in results if r is not None])

src/praisonai-agents/praisonaiagents/agent/audio_agent.py

@@ -9,6 +9,7 @@
 """
 import os
 import logging
+from praisonaiagents._logging import get_logger
 import warnings
 from dataclasses import dataclass, field
 from typing import Optional, Any, Dict, Union, BinaryIO
@@ -17,7 +18,6 @@
 # Filter out Pydantic warning about fields
 warnings.filterwarnings("ignore", "Valid config keys have changed in V2", UserWarning)
 
-
 # ─────────────────────────────────────────────────────────────────────────────
 # AudioConfig - Configuration dataclass following feature_configs.py patterns
 # ─────────────────────────────────────────────────────────────────────────────
@@ -59,7 +59,6 @@ def to_dict(self) -> Dict[str, Any]:
             "api_key": self.api_key,
         }
 
-
 # ─────────────────────────────────────────────────────────────────────────────
 # AudioAgent Class - Agent-centric audio processing
 # ─────────────────────────────────────────────────────────────────────────────
@@ -192,10 +191,10 @@ def litellm(self):
     def _configure_logging(self, verbose: Union[bool, int]) -> None:
         """Configure logging levels."""
         if isinstance(verbose, int) and verbose >= 10:
-            logging.getLogger("litellm").setLevel(logging.DEBUG)
+            get_logger("litellm").setLevel(logging.DEBUG)
         else:
-            logging.getLogger("litellm").setLevel(logging.WARNING)
-            logging.getLogger("httpx").setLevel(logging.WARNING)
+            get_logger("litellm").setLevel(logging.WARNING)
+            get_logger("httpx").setLevel(logging.WARNING)
 
     def _get_model_params(self, model: Optional[str] = None) -> Dict[str, Any]:
         """Build parameters for LiteLLM calls."""

src/praisonai-agents/praisonaiagents/agent/autonomy.py

@@ -35,8 +35,9 @@
 from typing import Optional, Dict, Any, List, Set
 from enum import Enum
 import logging
+from praisonaiagents._logging import get_logger
 
-logger = logging.getLogger(__name__)
+logger = get_logger(__name__)
 
 # ============================================================================
 # Unified Stage Enum (G-DUP-1 fix: single source of truth)
@@ -72,7 +73,6 @@
 # Reverse map for converting autonomy signal strings back to EscalationSignal values
 _AUTONOMY_TO_ESCALATION_SIGNAL = {v: k for k, v in _ESCALATION_TO_AUTONOMY_SIGNAL.items()}
 
-
 # Valid autonomy modes
 VALID_AUTONOMY_MODES = {"caller", "iterative"}
 
@@ -83,7 +83,6 @@
     "full_auto": "iterative",
 }
 
-
 @dataclass
 class AutonomyConfig:
     """Configuration for Agent autonomy features.
@@ -196,7 +195,6 @@ def from_dict(cls, data: Dict[str, Any]) -> "AutonomyConfig":
             default_tools=data.get("default_tools"),
         )
 
-
 class AutonomySignal(str, Enum):
     """Signals detected from prompts for autonomy decisions.
     
@@ -225,7 +223,6 @@ def __init_subclass__(cls, **kwargs):
         )
         super().__init_subclass__(**kwargs)
 
-
 def _warn_autonomy_signal():
     """Emit deprecation warning when AutonomySignal is accessed."""
     from ..utils.deprecation import warn_deprecated_param
@@ -237,7 +234,6 @@ def _warn_autonomy_signal():
         stacklevel=4
     )
 
-
 class AutonomyTrigger:
     """Detects signals from prompts for autonomy decisions.
     
@@ -283,7 +279,6 @@ def recommend_stage(self, signals: Set[str]) -> AutonomyStage:
                 pass
         return self._delegate.recommend_stage(esc_signals)
 
-
 @dataclass
 class AutonomyResult:
     """Result of an autonomous execution.
@@ -318,7 +313,6 @@ def __str__(self) -> str:
         """
         return self.output or ""
 
-
 class DoomLoopTracker:
     """Tracks actions to detect doom loops with graduated recovery.
     
@@ -421,7 +415,6 @@ def reset(self) -> None:
         self._delegate.start_session()
         self._recovery_attempts = 0
 
-
 class AutonomyMixin:
     """Helper-only trait for autonomy utilities.