Merge branch 'main' into claude/issue-958-20250716-2304

Author: MervinPraison

README.md

@@ -120,6 +120,10 @@ agent.start('Write a movie script about a robot in Mars');
 
 ![PraisonAI CLI Demo](docs/demo/praisonai-cli-demo.gif)
 
+## Star History
+
+[![Star History Chart](https://api.star-history.com/svg?repos=MervinPraison/PraisonAI&type=Date)](https://docs.praison.ai)
+
 ## AI Agents Flow
 
 ```mermaid
@@ -557,10 +561,6 @@ uv pip install -r pyproject.toml --extra "crewai,autogen"
 - 🖼️ Vision Language Model (VLM) Support
 - 🎙️ Real-time Voice Interaction
 
-## Star History
-
-[![Star History Chart](https://api.star-history.com/svg?repos=MervinPraison/PraisonAI&type=Date)](https://docs.praison.ai)
-
 ## Video Tutorials
 
 | Topic | Video |

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>=2.2.67" \
+    "praisonai>=2.2.69" \
     "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>=2.2.67" \
+    "praisonai>=2.2.69" \
     "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>=2.2.67" \
+    "praisonai>=2.2.69" \
     "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>=2.2.67" \
+    "praisonai>=2.2.69" \
     "praisonai[ui]" \
     "praisonai[crewai]"
 

docker/README.md

@@ -121,7 +121,7 @@ healthcheck:
 ## 📦 Package Versions
 
 All Docker images use consistent, up-to-date versions:
-- PraisonAI: `>=2.2.67`
+- PraisonAI: `>=2.2.69`
 - 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==2.2.67" "praisonaiagents==0.0.92"
+RUN pip install "praisonai==2.2.69" "praisonaiagents==0.0.92"
 ```
 
 ## 🌐 Production Deployment

src/praisonai-agents/agentic_parallelisation.py

@@ -94,12 +94,17 @@ async def main():
         process="workflow",
         verbose=True
     )
-    results = await workflow.astart()
+    results = await workflow.astart(dict_output=True)
 
     print("\nParallel Processing Results:")
-    for task_id, result in results["task_results"].items():
-        if result:
-            print(f"Task {task_id}: {result.raw}")
+    
+    # Handle both string and dictionary return types
+    if isinstance(results, dict) and "task_results" in results:
+        for task_id, result in results["task_results"].items():
+            if result:
+                print(f"Task {task_id}: {result.raw}")
+    else:
+        print("Final result:", results)
 
 if __name__ == "__main__":
     asyncio.run(main())

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

@@ -362,14 +362,20 @@ def _get_multimodal_message(text_prompt, images):
                 _get_multimodal_message(task_prompt, task.images),
                 tools=tools,
                 output_json=task.output_json,
-                output_pydantic=task.output_pydantic
+                output_pydantic=task.output_pydantic,
+                task_name=task.name,
+                task_description=task.description,
+                task_id=task.id
             )
         else:
             agent_output = await executor_agent.achat(
                 task_prompt,
                 tools=tools,
                 output_json=task.output_json,
-                output_pydantic=task.output_pydantic
+                output_pydantic=task.output_pydantic,
+                task_name=task.name,
+                task_description=task.description,
+                task_id=task.id
             )
 
         if agent_output:
@@ -1138,7 +1144,7 @@ async def handle_query(request: Request, query_data: Optional[AgentQuery] = None
                         try:
                             # Use async version if available, otherwise use sync version
                             if asyncio.iscoroutinefunction(agent_instance.chat):
-                                response = await agent_instance.achat(current_input)
+                                response = await agent_instance.achat(current_input, task_name=None, task_description=None, task_id=None)
                             else:
                                 # Run sync function in a thread to avoid blocking
                                 loop = asyncio.get_running_loop()
@@ -1294,7 +1300,7 @@ async def execute_workflow_tool(query: str) -> str: # Renamed for clarity
                     try:
                         logging.debug(f"Processing with agent: {agent_instance.name}")
                         if hasattr(agent_instance, 'achat') and asyncio.iscoroutinefunction(agent_instance.achat):
-                            response = await agent_instance.achat(current_input, tools=agent_instance.tools)
+                            response = await agent_instance.achat(current_input, tools=agent_instance.tools, task_name=None, task_description=None, task_id=None)
                         elif hasattr(agent_instance, 'chat'): # Fallback to sync chat if achat not suitable
                             loop = asyncio.get_running_loop()
                             response = await loop.run_in_executor(None, lambda ci=current_input: agent_instance.chat(ci, tools=agent_instance.tools))

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

@@ -477,6 +477,49 @@ def _validate_and_filter_ollama_arguments(self, function_name: str, arguments: D
             logging.debug(f"[OLLAMA_FIX] Error validating arguments for {function_name}: {e}")
             return arguments
 
+    def _handle_ollama_sequential_logic(self, iteration_count: int, accumulated_tool_results: List[Any], 
+                                      response_text: str, messages: List[Dict]) -> tuple:
+        """
+        Handle Ollama sequential tool execution logic to prevent premature tool summary generation.
+        
+        This method implements the two-step process:
+        1. After reaching threshold with tool results, add explicit final answer prompt
+        2. Only generate tool summary if LLM still doesn't respond after explicit prompt
+        
+        Args:
+            iteration_count: Current iteration count
+            accumulated_tool_results: List of tool results from all iterations
+            response_text: Current LLM response text
+            messages: Message history list to potentially modify
+            
+        Returns:
+            tuple: (should_break, final_response_text, iteration_count)
+                - should_break: Whether to break the iteration loop
+                - final_response_text: Text to use as final response (None if continuing)
+                - iteration_count: Updated iteration count
+        """
+        if not (self._is_ollama_provider() and iteration_count >= self.OLLAMA_SUMMARY_ITERATION_THRESHOLD):
+            return False, None, iteration_count
+            
+        # For Ollama: if we have meaningful tool results but empty responses,
+        # give LLM one final chance with explicit prompt for final answer
+        if accumulated_tool_results and iteration_count == self.OLLAMA_SUMMARY_ITERATION_THRESHOLD:
+            # Add explicit prompt asking for final answer
+            messages.append({
+                "role": "user", 
+                "content": self.OLLAMA_FINAL_ANSWER_PROMPT
+            })
+            # Continue to next iteration to get the final response
+            iteration_count += 1
+            return False, None, iteration_count
+        else:
+            # If still no response after final answer prompt, generate summary
+            tool_summary = self._generate_ollama_tool_summary(accumulated_tool_results, response_text)
+            if tool_summary:
+                return True, tool_summary, iteration_count
+                
+        return False, None, iteration_count
+
     def _needs_system_message_skip(self) -> bool:
         """Check if this model requires skipping system messages"""
         if not self.model:
@@ -1132,11 +1175,15 @@ def get_response(
 
                         # Special handling for Ollama to prevent infinite loops
                         # Only generate summary after multiple iterations to allow sequential execution
-                        if iteration_count >= self.OLLAMA_SUMMARY_ITERATION_THRESHOLD:
-                            tool_summary = self._generate_ollama_tool_summary(accumulated_tool_results, response_text)
-                            if tool_summary:
-                                final_response_text = tool_summary
-                                break
+                        should_break, tool_summary_text, iteration_count = self._handle_ollama_sequential_logic(
+                            iteration_count, accumulated_tool_results, response_text, messages
+                        )
+                        if should_break:
+                            final_response_text = tool_summary_text
+                            break
+                        elif tool_summary_text is None and iteration_count > self.OLLAMA_SUMMARY_ITERATION_THRESHOLD:
+                            # Continue iteration after adding final answer prompt
+                            continue
 
                         # Safety check: prevent infinite loops for any provider
                         if iteration_count >= 5:
@@ -1911,11 +1958,15 @@ async def get_response_async(
 
                     # Special handling for Ollama to prevent infinite loops
                     # Only generate summary after multiple iterations to allow sequential execution
-                    if iteration_count >= self.OLLAMA_SUMMARY_ITERATION_THRESHOLD:
-                        tool_summary = self._generate_ollama_tool_summary(accumulated_tool_results, response_text)
-                        if tool_summary:
-                            final_response_text = tool_summary
-                            break
+                    should_break, tool_summary_text, iteration_count = self._handle_ollama_sequential_logic(
+                        iteration_count, accumulated_tool_results, response_text, messages
+                    )
+                    if should_break:
+                        final_response_text = tool_summary_text
+                        break
+                    elif tool_summary_text is None and iteration_count > self.OLLAMA_SUMMARY_ITERATION_THRESHOLD:
+                        # Continue iteration after adding final answer prompt
+                        continue
 
                     # Safety check: prevent infinite loops for any provider
                     if iteration_count >= 5:
@@ -2417,18 +2468,14 @@ def response(
             )
 
             if stream:
-                if verbose:
-                    with Live(display_generating("", start_time), console=console or self.console, refresh_per_second=4) as live:
-                        for chunk in litellm.completion(**completion_params):
-                            content = self._process_streaming_chunk(chunk)
-                            if content:
-                                response_text += content
-                                live.update(display_generating(response_text, start_time))
-                else:
+                with Live(display_generating("", start_time), console=console or self.console, refresh_per_second=4) as live:
                     for chunk in litellm.completion(**completion_params):
                         content = self._process_streaming_chunk(chunk)
                         if content:
                             response_text += content
+                            live.update(display_generating(response_text, start_time))
+                        if content:
+                            response_text += content
             else:
                 response = litellm.completion(**completion_params)
                 response_text = response.choices[0].message.content.strip() if response.choices[0].message.content else ""
@@ -2517,18 +2564,14 @@ async def aresponse(
             )
 
             if stream:
-                if verbose:
-                    with Live(display_generating("", start_time), console=console or self.console, refresh_per_second=4) as live:
-                        async for chunk in await litellm.acompletion(**completion_params):
-                            content = self._process_streaming_chunk(chunk)
-                            if content:
-                                response_text += content
-                                live.update(display_generating(response_text, start_time))
-                else:
+                with Live(display_generating("", start_time), console=console or self.console, refresh_per_second=4) as live:
                     async for chunk in await litellm.acompletion(**completion_params):
                         content = self._process_streaming_chunk(chunk)
                         if content:
                             response_text += content
+                            live.update(display_generating(response_text, start_time))
+                        if content:
+                            response_text += content
             else:
                 response = await litellm.acompletion(**completion_params)
                 response_text = response.choices[0].message.content.strip() if response.choices[0].message.content else ""