feat: bump praisonai to v2.2.76 and praisonaiagents to v0.0.149 with callback refactor

- Added execute_sync_callback call in custom LLM path to match OpenAI behavior
- Fixed issue where Gemini/custom LLM responses were not triggering callbacks
- Prevents duplicate display by relying on LLM class to handle verbose display
- Ensures both paths execute callbacks for consistent behavior

The issue was that custom LLM providers (like Gemini) were not calling
_execute_callback_and_display after guardrail validation, while OpenAI
path was. This caused missing Task/Response display boxes for Gemini.

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <[email protected]>

docker/Dockerfile

@@ -16,7 +16,7 @@ RUN mkdir -p /root/.praison
 # Install Python packages (using latest versions)
 RUN pip install --no-cache-dir \
     flask \
-    "praisonai>=2.2.74" \
+    "praisonai>=2.2.76" \
     "praisonai[api]" \
     gunicorn \
     markdown

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>=2.2.74" \
+    "praisonai>=2.2.76" \
     "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>=2.2.74" \
+    "praisonai>=2.2.76" \
     "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>=2.2.74" \
+    "praisonai>=2.2.76" \
     "praisonai[ui]" \
     "praisonai[crewai]"
 

docker/README.md

@@ -121,7 +121,7 @@ healthcheck:
 ## 📦 Package Versions
 
 All Docker images use consistent, up-to-date versions:
-- PraisonAI: `>=2.2.74`
+- PraisonAI: `>=2.2.76`
 - PraisonAI Agents: `>=0.0.92`
 - Python: `3.11-slim`
 
@@ -218,7 +218,7 @@ docker-compose up -d
 ### Version Pinning
 To use specific versions, update the Dockerfile:
 ```dockerfile
-RUN pip install "praisonai==2.2.74" "praisonaiagents==0.0.92"
+RUN pip install "praisonai==2.2.76" "praisonaiagents==0.0.92"
 ```
 
 ## 🌐 Production Deployment

src/praisonai-agents/praisonaiagents/_logging.py

@@ -59,7 +59,7 @@ def _configure_loggers():
     
     # When DEBUG is set, allow some HTTP logging for API endpoints
     if loglevel == 'DEBUG':
-        allowed_debug_loggers = {"httpx._client", "openai._client"}
+        allowed_debug_loggers = {"httpx", "httpx._client", "openai._client"}
         
         for logger_name in _get_all_noisy_loggers():
             if logger_name not in allowed_debug_loggers:

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

@@ -331,8 +331,15 @@ class Agent:
 
         # Configure logging to suppress unwanted outputs
         logging.getLogger("litellm").setLevel(logging.WARNING)
-        logging.getLogger("httpx").setLevel(logging.WARNING)
-        logging.getLogger("httpcore").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)
+        else:
+            logging.getLogger("httpx").setLevel(logging.WARNING)
+            logging.getLogger("httpcore").setLevel(logging.WARNING)
 
         # If instructions are provided, use them to set role, goal, and backstory
         if instructions:
@@ -1229,14 +1236,14 @@ Your Goal: {self.goal}"""
                 border_style="green",
                 expand=False
             )
-        else:
-            # No content yet: show generating message
-            return Panel(
-                f"[bold cyan]Generating response...[/bold cyan]",
-                title=f"[bold]{self.name}[/bold] - {elapsed:.1f}s",
-                border_style="cyan",
-                expand=False
-            )
+        # else:
+        #     # No content yet: show generating message
+        #     return Panel(
+        #         f"[bold cyan]Generating response...[/bold cyan]",
+        #         title=f"[bold]{self.name}[/bold] - {elapsed:.1f}s",
+        #         border_style="cyan",
+        #         expand=False
+        #     )
 
     def chat(self, prompt, temperature=0.2, tools=None, output_json=None, output_pydantic=None, reasoning_steps=False, stream=None, task_name=None, task_description=None, task_id=None):
         # Reset the final display flag for each new conversation
@@ -1353,6 +1360,8 @@ Your Goal: {self.goal}"""
                     # Apply guardrail validation for custom LLM response
                     try:
                         validated_response = self._apply_guardrail_with_retry(response_text, prompt, temperature, tools, task_name, task_description, task_id)
+                        # Execute callback and display after validation
+                        self._execute_callback_and_display(prompt, validated_response, time.time() - start_time, task_name, task_description, task_id)
                         return validated_response
                     except Exception as e:
                         logging.error(f"Agent {self.name}: Guardrail validation failed for custom LLM: {e}")

src/praisonai-agents/praisonaiagents/llm/OLLAMA_HANDLING.md

@@ -1,25 +0,0 @@
-# Ollama Handling in LLM.py
-
-The `ollama_handled` flag is used in `llm.py` (not in `agent.py`) to track whether special Ollama model handling has been applied for tool results. Here's what I found:
-
-## Where it's used in llm.py:
-- **Line 863**: `ollama_handled = False` - initialized at the beginning of the tool execution loop
-- **Line 864**: Special handling logic via `_handle_ollama_model()` method
-- **Line 907**: `ollama_handled = True` - set when Ollama special handling is applied
-- **Line 928 & 959**: Checks `if not ollama_handled` to avoid duplicate processing
-
-## Why it's needed:
-The flag prevents duplicate processing when Ollama models require special handling. Some Ollama models return only the tool call JSON without processing the results, requiring a follow-up prompt to get the final answer. The `ollama_handled` flag ensures this special handling happens only once.
-
-## Does this contradict the requirement?
-**No, it doesn't.** The issue states:
-
-> "ollama/xxxx model is already handled via llm.py via litellm, so no special condition or handling required for ollama inside agent.py"
-
-✅ **Current implementation is correct:**
-
-- `agent.py` has NO ollama-specific conditions (only one documentation mention as an example)
-- All ollama handling is contained within `llm.py` as intended
-- The `ollama_handled` flag is an internal implementation detail within `llm.py`
-
-The codebase already follows the desired pattern where ollama models are handled through the generic LLM interface via litellm without special conditions in agent.py.

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

@@ -201,7 +201,14 @@ class LLM:
             # These are from external libraries and not useful for debugging user code
             logging.getLogger("litellm.utils").setLevel(logging.WARNING)
             logging.getLogger("litellm.main").setLevel(logging.WARNING)
-            logging.getLogger("litellm.llms.custom_httpx.http_handler").setLevel(logging.WARNING)
+            
+            # Allow httpx logging when LOGLEVEL=debug, otherwise suppress it
+            loglevel = os.environ.get('LOGLEVEL', 'INFO').upper()
+            if loglevel == 'DEBUG':
+                logging.getLogger("litellm.llms.custom_httpx.http_handler").setLevel(logging.INFO)
+            else:
+                logging.getLogger("litellm.llms.custom_httpx.http_handler").setLevel(logging.WARNING)
+            
             logging.getLogger("litellm.litellm_logging").setLevel(logging.WARNING)
             logging.getLogger("litellm.transformation").setLevel(logging.WARNING)
             litellm.suppress_debug_messages = True

src/praisonai-agents/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "praisonaiagents"
-version = "0.0.147"
+version = "0.0.149"
 description = "Praison AI agents for completing complex tasks with Self Reflection Agents"
 requires-python = ">=3.10"
 authors = [

src/praisonai-agents/test_display_boxes.py

@@ -0,0 +1,52 @@
+#!/usr/bin/env python3
+"""Test script to compare display output between OpenAI and Gemini models."""
+
+import os
+from praisonaiagents import Agent
+
+def test_model_display(model_name, api_key_env=None):
+    """Test display output for a specific model."""
+    print(f"\n{'='*60}")
+    print(f"Testing {model_name}")
+    print('='*60)
+    
+    # Set API key if provided
+    if api_key_env:
+        if not os.getenv(api_key_env):
+            print(f"Skipping {model_name} - {api_key_env} not set")
+            return
+    
+    try:
+        # Create agent with the specified model
+        agent = Agent(
+            name=f"{model_name.split('/')[-1]}_agent",
+            role="Math Assistant",
+            goal="Help with simple calculations",
+            backstory="You are a helpful math assistant.",
+            llm=model_name,
+            verbose=True,  # This should trigger display_interaction
+            markdown=True
+        )
+        
+        # Simple test prompt
+        response = agent.chat("What is 5 + 3? Please provide a brief answer.")
+        
+        print(f"\nRaw response: {response}")
+        
+    except Exception as e:
+        print(f"Error with {model_name}: {e}")
+
+# Test with different models
+if __name__ == "__main__":
+    print("Testing display output for different LLM models...")
+    
+    # Test OpenAI
+    test_model_display("gpt-4o-mini", "OPENAI_API_KEY")
+    
+    # Test Gemini
+    test_model_display("gemini/gemini-1.5-flash", "GEMINI_API_KEY")
+    
+    # Test Anthropic (if available)
+    test_model_display("claude-3-haiku-20240307", "ANTHROPIC_API_KEY")
+    
+    print("\n\nTest completed!")

src/praisonai-agents/uv.lock

@@ -2422,7 +2422,7 @@ wheels = [
 
 [[package]]
 name = "praisonaiagents"
-version = "0.0.147"
+version = "0.0.149"
 source = { editable = "." }
 dependencies = [
     { name = "aiohttp" },

src/praisonai/praisonai.rb

@@ -3,8 +3,8 @@ class Praisonai < Formula
   
     desc "AI tools for various AI applications"
     homepage "https://github.com/MervinPraison/PraisonAI"
-    url "https://github.com/MervinPraison/PraisonAI/archive/refs/tags/v2.2.74.tar.gz"
-    sha256 `curl -sL https://github.com/MervinPraison/PraisonAI/archive/refs/tags/v2.2.74.tar.gz | shasum -a 256`.split.first
+    url "https://github.com/MervinPraison/PraisonAI/archive/refs/tags/v2.2.76.tar.gz"
+    sha256 `curl -sL https://github.com/MervinPraison/PraisonAI/archive/refs/tags/v2.2.76.tar.gz | shasum -a 256`.split.first
     license "MIT"
   
     depends_on "[email protected]"

src/praisonai/praisonai/deploy.py

@@ -57,7 +57,7 @@ class CloudDeployer:
             file.write("FROM python:3.11-slim\n")
             file.write("WORKDIR /app\n")
             file.write("COPY . .\n")
-            file.write("RUN pip install flask praisonai==2.2.74 gunicorn markdown\n")
+            file.write("RUN pip install flask praisonai==2.2.76 gunicorn markdown\n")
             file.write("EXPOSE 8080\n")
             file.write('CMD ["gunicorn", "-b", "0.0.0.0:8080", "api:app"]\n')
             

src/praisonai/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "PraisonAI"
-version = "2.2.74"
+version = "2.2.76"
 description = "PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human-agent collaboration."
 readme = "README.md"
 license = ""
@@ -12,7 +12,7 @@ dependencies = [
     "rich>=13.7",
     "markdown>=3.5",
     "pyparsing>=3.0.0",
-    "praisonaiagents>=0.0.147",
+    "praisonaiagents>=0.0.149",
     "python-dotenv>=0.19.0",
     "instructor>=1.3.3",
     "PyYAML>=6.0",
@@ -102,7 +102,7 @@ autogen-v4 = [
 
 [tool.poetry]
 name = "PraisonAI"
-version = "2.2.74"
+version = "2.2.76"
 description = "PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human-agent collaboration."
 authors = ["Mervin Praison"]
 license = ""
@@ -120,7 +120,7 @@ python = ">=3.10,<3.13"
 rich = ">=13.7"
 markdown = ">=3.5"
 pyparsing = ">=3.0.0"
-praisonaiagents = ">=0.0.147"
+praisonaiagents = ">=0.0.149"
 python-dotenv = ">=0.19.0"
 instructor = ">=1.3.3"
 PyYAML = ">=6.0"

src/praisonai/uv.lock

@@ -4031,7 +4031,7 @@ wheels = [
 
 [[package]]
 name = "praisonai"
-version = "2.2.74"
+version = "2.2.76"
 source = { editable = "." }
 dependencies = [
     { name = "instructor" },
@@ -4185,7 +4185,7 @@ requires-dist = [
     { name = "praisonai-tools", marker = "extra == 'autogen'", specifier = ">=0.0.22" },
     { name = "praisonai-tools", marker = "extra == 'autogen-v4'", specifier = ">=0.0.22" },
     { name = "praisonai-tools", marker = "extra == 'crewai'", specifier = ">=0.0.22" },
-    { name = "praisonaiagents", specifier = ">=0.0.147" },
+    { name = "praisonaiagents", specifier = ">=0.0.149" },
     { name = "pyautogen", marker = "extra == 'autogen'", specifier = "==0.2.29" },
     { name = "pydantic", marker = "extra == 'chat'", specifier = "<=2.10.1" },
     { name = "pydantic", marker = "extra == 'code'", specifier = "<=2.10.1" },
@@ -4240,7 +4240,7 @@ wheels = [
 
 [[package]]
 name = "praisonaiagents"
-version = "0.0.147"
+version = "0.0.149"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "aiohttp" },
@@ -4249,9 +4249,9 @@ dependencies = [
     { name = "pydantic" },
     { name = "rich" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/c7/bd/ed4688ef7290faf76f214e30e3fbdf22276d790588b91968ee71aac635f6/praisonaiagents-0.0.147.tar.gz", hash = "sha256:2c5c8d2fe1cb630218c3f0e9f0dc4c22dffd4f36d113df4d9876484603aef82c", size = 270562, upload-time = "2025-07-24T00:52:45.432Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/6e/ec/be31b9a2b40977a993870adfa00dc4cbb54c347e6a689e3f01a9ab4843eb/praisonaiagents-0.0.149.tar.gz", hash = "sha256:2365c1fbc298397713cdb5aafd45fb1f543083274dd9827e589061e89e441b63", size = 270788, upload-time = "2025-07-25T08:39:56.201Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/d5/02/88e446fb1232ca586646722e1db4dd94ddf5afc2cd49e6ef9b6b938309a9/praisonaiagents-0.0.147-py3-none-any.whl", hash = "sha256:9e3177346b611b5d3de0820edb16ed9fc8c1ea811f6b6392a9838cd0ade4282b", size = 288525, upload-time = "2025-07-24T00:52:43.845Z" },
+    { url = "https://files.pythonhosted.org/packages/e0/08/69bdea25d05d9faa98ea2eaefa63007b46e2092c865d1d5d04e40cd97208/praisonaiagents-0.0.149-py3-none-any.whl", hash = "sha256:bef4d2688759ecbcb84e897f3b3bd701f24672987e0f816829a6f1be74be29fa", size = 288759, upload-time = "2025-07-25T08:39:54.598Z" },
 ]
 
 [[package]]