chore: update PraisonAI version to 2.2.47 in Dockerfiles, README, and related files

Merge pull request #781 from MervinPraison/claude/issue-754-20250709_155906
refactor: eliminate sync/async duplication in llm.py
2026-11-08 17:31:00 -10:00 · 2025-07-10 23:30:27 +01:00 · 2025-07-10 23:21:04 +01:00 · 2025-07-10 23:20:50 +01:00 · 2025-07-10 23:20:48 +01:00 · 2025-07-10 23:20:17 +01:00
19 changed files with 730 additions and 559 deletions
@@ -16,7 +16,7 @@ RUN mkdir -p /root/.praison
 # Install Python packages (using latest versions)
 RUN pip install --no-cache-dir \
    flask \
-    "praisonai>=2.2.44" \
+    "praisonai>=2.2.47" \
    "praisonai[api]" \
    gunicorn \
    markdown
@@ -16,7 +16,7 @@ RUN mkdir -p /root/.praison
 # Install Python packages (using latest versions)
 RUN pip install --no-cache-dir \
    praisonai_tools \
-    "praisonai>=2.2.44" \
+    "praisonai>=2.2.47" \
    "praisonai[chat]" \
    "embedchain[github,youtube]"

@@ -20,7 +20,7 @@ RUN mkdir -p /root/.praison
 # Install Python packages (using latest versions)
 RUN pip install --no-cache-dir \
    praisonai_tools \
-    "praisonai>=2.2.44" \
+    "praisonai>=2.2.47" \
    "praisonai[ui]" \
    "praisonai[chat]" \
    "praisonai[realtime]" \
@@ -16,7 +16,7 @@ RUN mkdir -p /root/.praison
 # Install Python packages (using latest versions)
 RUN pip install --no-cache-dir \
    praisonai_tools \
-    "praisonai>=2.2.44" \
+    "praisonai>=2.2.47" \
    "praisonai[ui]" \
    "praisonai[crewai]"

@@ -121,7 +121,7 @@ healthcheck:
 ## 📦 Package Versions

 All Docker images use consistent, up-to-date versions:
- PraisonAI: `>=2.2.44`
+- PraisonAI: `>=2.2.47`
 - 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==2.2.44" "praisonaiagents==0.0.92"
+RUN pip install "praisonai==2.2.47" "praisonaiagents==0.0.92"
 ```

 ## 🌐 Production Deployment
@@ -0,0 +1,57 @@
+from praisonaiagents import AutoAgents
+from praisonaiagents.tools import duckduckgo
+
+# Create AutoAgents instance
+agents = AutoAgents(
+    instructions="Search for information about AI Agents",
+    tools=[duckduckgo],
+    process="sequential",
+    verbose=True,
+    max_agents=3  # Maximum number of agents to create
+)
+
+# Start the agents
+result = agents.start()
+print(result)
+
+##or
+
+from praisonaiagents import AutoAgents
+from praisonaiagents.tools import (
+    evaluate, solve_equation, convert_units,
+    calculate_statistics, calculate_financial
+)
+
+
+def get_stock_price(company_name: str) -> str:
+    """
+    Get the stock price of a company
+    
+    Args:
+        company_name (str): The name of the company
+        
+    Returns:
+        str: The stock price of the company
+    """
+
+    if company_name.lower() == "apple" or company_name.lower() == "aapl":
+        return f"The stock price of {company_name} is 100"
+    elif company_name.lower() == "google" or company_name.lower() == "googl":
+        return f"The stock price of {company_name} is 200"
+    else:
+        return f"The stock price of {company_name} is 50"
+
+# Create AutoAgents instance  
+agents = AutoAgents(
+    instructions="Get the stock price of google and compare it to the stock price of apple",
+    tools=[evaluate, get_stock_price],
+    process="sequential",
+    llm="gemini/gemini-2.5-flash-lite-preview-06-17",
+    self_reflect=False,
+    verbose=False,
+    max_agents=3  # Maximum number of agents to create
+)
+
+# Start the agents
+result = agents.start()
+print(result)
@@ -0,0 +1,6 @@
+from praisonaiagents import Agent, Agents, Tools
+
+research_agent = Agent(name="Research", instructions="You are a research agent to search internet about AI 2024", tools=[Tools.internet_search])
+summarise_agent = Agent(name="Summarise", instructions="You are a summarize agent to summarise in points")
+agents = Agents(agents=[research_agent, summarise_agent])
+agents.launch(path="/agents", port=3030)
@@ -0,0 +1,8 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a helpful assistant",
+    llm="ollama/qwen3"
+)
+
+agent.start("Why sky is Blue?")
@@ -1233,7 +1233,8 @@ Your Goal: {self.goal}
                        # Add to chat history and return raw response
                        self.chat_history.append({"role": "user", "content": original_prompt})
                        self.chat_history.append({"role": "assistant", "content": response_text})
-                        if self.verbose:
+                        # Only display interaction if not using custom LLM (to avoid double output) and verbose is True
+                        if self.verbose and not self._using_custom_llm:
                            display_interaction(original_prompt, response_text, markdown=self.markdown, 
                                             generation_time=time.time() - start_time, console=self.console)
                        return response_text
@@ -1243,7 +1244,9 @@ Your Goal: {self.goal}
                        self.chat_history.append({"role": "assistant", "content": response_text})
                        if self.verbose:
                            logging.debug(f"Agent {self.name} final response: {response_text}")
-                        display_interaction(original_prompt, response_text, markdown=self.markdown, generation_time=time.time() - start_time, console=self.console)
+                        # Only display interaction if not using custom LLM (to avoid double output) and verbose is True
+                        if self.verbose and not self._using_custom_llm:
+                            display_interaction(original_prompt, response_text, markdown=self.markdown, generation_time=time.time() - start_time, console=self.console)
                        # Return only reasoning content if reasoning_steps is True
                        if reasoning_steps and hasattr(response.choices[0].message, 'reasoning_content'):
                            # Apply guardrail to reasoning content
@@ -1279,7 +1282,9 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
                            # Return the original response without reflection
                            self.chat_history.append({"role": "user", "content": prompt})
                            self.chat_history.append({"role": "assistant", "content": response_text})
-                            display_interaction(prompt, response_text, markdown=self.markdown, generation_time=time.time() - start_time, console=self.console)
+                            # Only display interaction if not using custom LLM (to avoid double output) and verbose is True
+                            if self.verbose and not self._using_custom_llm:
+                                display_interaction(prompt, response_text, markdown=self.markdown, generation_time=time.time() - start_time, console=self.console)
                            return response_text
                        
                        reflection_response = self._openai_client.sync_client.beta.chat.completions.parse(
@@ -1302,7 +1307,9 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
                                display_self_reflection("Agent marked the response as satisfactory after meeting minimum reflections", console=self.console)
                            self.chat_history.append({"role": "user", "content": prompt})
                            self.chat_history.append({"role": "assistant", "content": response_text})
-                            display_interaction(prompt, response_text, markdown=self.markdown, generation_time=time.time() - start_time, console=self.console)
+                            # Only display interaction if not using custom LLM (to avoid double output) and verbose is True
+                            if self.verbose and not self._using_custom_llm:
+                                display_interaction(prompt, response_text, markdown=self.markdown, generation_time=time.time() - start_time, console=self.console)
                            # Apply guardrail validation after satisfactory reflection
                            try:
                                validated_response = self._apply_guardrail_with_retry(response_text, prompt, temperature, tools)
@@ -1317,7 +1324,9 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
                                display_self_reflection("Maximum reflection count reached, returning current response", console=self.console)
                            self.chat_history.append({"role": "user", "content": prompt})
                            self.chat_history.append({"role": "assistant", "content": response_text})
-                            display_interaction(prompt, response_text, markdown=self.markdown, generation_time=time.time() - start_time, console=self.console)
+                            # Only display interaction if not using custom LLM (to avoid double output) and verbose is True
+                            if self.verbose and not self._using_custom_llm:
+                                display_interaction(prompt, response_text, markdown=self.markdown, generation_time=time.time() - start_time, console=self.console)
                            # Apply guardrail validation after max reflections
                            try:
                                validated_response = self._apply_guardrail_with_retry(response_text, prompt, temperature, tools)
@@ -13,7 +13,8 @@ import logging
 import os
 from pydantic import BaseModel, ConfigDict
 from ..main import display_instruction, display_tool_call, display_interaction
-from ..llm import get_openai_client
+from ..llm import get_openai_client, LLM, OpenAIClient
+import json

 # Define Pydantic models for structured output
 class TaskConfig(BaseModel):
@@ -108,6 +109,8 @@ class AutoAgents(PraisonAIAgents):
        self.max_execution_time = max_execution_time
        self.max_iter = max_iter
        self.reflect_llm = reflect_llm
+        self.base_url = base_url
+        self.api_key = api_key
        
        # Display initial instruction
        if self.verbose:
@@ -238,33 +241,77 @@ Return the configuration in a structured JSON format matching the AutoAgentsConf
 """
        
        try:
-            # Get OpenAI client
+            # Try to use OpenAI's structured output if available
+            use_openai_structured = False
+            client = None
+            
            try:
-                client = get_openai_client()
-            except ValueError as e:
-                # AutoAgents requires OpenAI for structured output generation
-                raise ValueError(
-                    "AutoAgents requires OpenAI API for automatic agent generation. "
-                    "Please set OPENAI_API_KEY environment variable or use PraisonAIAgents class directly "
-                    "with manually configured agents for non-OpenAI providers."
-                ) from e
+                # Check if we have OpenAI API and the model supports structured output
+                if self.llm and (self.llm.startswith('gpt-') or self.llm.startswith('o1-') or self.llm.startswith('o3-')):
+                    # Create a new client instance if custom parameters are provided
+                    if self.api_key or self.base_url:
+                        client = OpenAIClient(api_key=self.api_key, base_url=self.base_url)
+                    else:
+                        client = get_openai_client()
+                    use_openai_structured = True
+            except:
+                # If OpenAI client is not available, we'll use the LLM class
+                pass
+            
+            if use_openai_structured and client:
+                # Use OpenAI's structured output for OpenAI models (backward compatibility)
+                config = client.parse_structured_output(
+                    messages=[
+                        {"role": "system", "content": "You are a helpful assistant designed to generate AI agent configurations."},
+                        {"role": "user", "content": prompt}
+                    ],
+                    response_format=AutoAgentsConfig,
+                    model=self.llm
+                )
+            else:
+                # Use LLM class for all other providers (Gemini, Anthropic, etc.)
+                llm_instance = LLM(
+                    model=self.llm,
+                    base_url=self.base_url,
+                    api_key=self.api_key
+                )
                
-            response = client.beta.chat.completions.parse(
-                model=self.llm,
-                response_format=AutoAgentsConfig,
-                messages=[
-                    {"role": "system", "content": "You are a helpful assistant designed to generate AI agent configurations."},
-                    {"role": "user", "content": prompt}
-                ]
-            )
+                response_text = llm_instance.response(
+                    prompt=prompt,
+                    system_prompt="You are a helpful assistant designed to generate AI agent configurations.",
+                    output_pydantic=AutoAgentsConfig,
+                    temperature=0.7,
+                    stream=False,
+                    verbose=False
+                )
+                
+                # Parse the JSON response
+                try:
+                    # First try to parse as is
+                    config_dict = json.loads(response_text)
+                    config = AutoAgentsConfig(**config_dict)
+                except json.JSONDecodeError:
+                    # If that fails, try to extract JSON from the response
+                    # Handle cases where the model might wrap JSON in markdown blocks
+                    cleaned_response = response_text.strip()
+                    if cleaned_response.startswith("```json"):
+                        cleaned_response = cleaned_response[7:]
+                    if cleaned_response.startswith("```"):
+                        cleaned_response = cleaned_response[3:]
+                    if cleaned_response.endswith("```"):
+                        cleaned_response = cleaned_response[:-3]
+                    cleaned_response = cleaned_response.strip()
+                    
+                    config_dict = json.loads(cleaned_response)
+                    config = AutoAgentsConfig(**config_dict)
            
            # Ensure we have exactly max_agents number of agents
-            if len(response.choices[0].message.parsed.agents) > self.max_agents:
-                response.choices[0].message.parsed.agents = response.choices[0].message.parsed.agents[:self.max_agents]
-            elif len(response.choices[0].message.parsed.agents) < self.max_agents:
-                logging.warning(f"Generated {len(response.choices[0].message.parsed.agents)} agents, expected {self.max_agents}")
+            if len(config.agents) > self.max_agents:
+                config.agents = config.agents[:self.max_agents]
+            elif len(config.agents) < self.max_agents:
+                logging.warning(f"Generated {len(config.agents)} agents, expected {self.max_agents}")
            
-            return response.choices[0].message.parsed
+            return config
        except Exception as e:
            logging.error(f"Error generating configuration: {e}")
            raise
@@ -308,7 +355,9 @@ Return the configuration in a structured JSON format matching the AutoAgentsConf
                max_rpm=self.max_rpm,
                max_execution_time=self.max_execution_time,
                max_iter=self.max_iter,
-                reflect_llm=self.reflect_llm
+                reflect_llm=self.reflect_llm,
+                base_url=self.base_url,
+                api_key=self.api_key
            )
            agents.append(agent)
            
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"

 [project]
 name = "praisonaiagents"
-version = "0.0.117"
+version = "0.0.121"
 description = "Praison AI agents for completing complex tasks with Self Reflection Agents"
 requires-python = ">=3.10"
 authors = [
@@ -0,0 +1,8 @@
+from praisonaiagents import Agent, MCP
+
+search_agent = Agent(
+    instructions="""You are a Tweet.""",
+    llm="openai/gpt-4o-mini",
+    tools=MCP("http://localhost:8080/sse")
+)
+search_agent.launch(path="/tweet", port=3030)
@@ -0,0 +1,4 @@
+from praisonaiagents import Agent
+
+agent = Agent(instructions="Create a Tweet")
+agent.launch(port=8080, protocol="mcp")
@@ -2375,7 +2375,7 @@ wheels = [

 [[package]]
 name = "praisonaiagents"
-version = "0.0.117"
+version = "0.0.121"
 source = { editable = "." }
 dependencies = [
    { name = "mcp" },
@@ -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/v2.2.44.tar.gz"
-    sha256 `curl -sL https://github.com/MervinPraison/PraisonAI/archive/refs/tags/v2.2.44.tar.gz | shasum -a 256`.split.first
+    url "https://github.com/MervinPraison/PraisonAI/archive/refs/tags/v2.2.47.tar.gz"
+    sha256 `curl -sL https://github.com/MervinPraison/PraisonAI/archive/refs/tags/v2.2.47.tar.gz | shasum -a 256`.split.first
    license "MIT"
  
    depends_on "[email protected]"
@@ -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==2.2.44 gunicorn markdown\n")
+            file.write("RUN pip install flask praisonai==2.2.47 gunicorn markdown\n")
            file.write("EXPOSE 8080\n")
            file.write('CMD ["gunicorn", "-b", "0.0.0.0:8080", "api:app"]\n')
            
@@ -1,6 +1,6 @@
 [project]
 name = "PraisonAI"
-version = "2.2.44"
+version = "2.2.47"
 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>=0.0.117",
+    "praisonaiagents>=0.0.121",
    "python-dotenv>=0.19.0",
    "instructor>=1.3.3",
    "PyYAML>=6.0",
@@ -95,7 +95,7 @@ autogen = ["pyautogen>=0.2.19", "praisonai-tools>=0.0.15", "crewai"]

 [tool.poetry]
 name = "PraisonAI"
-version = "2.2.44"
+version = "2.2.47"
 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 = ""
@@ -113,7 +113,7 @@ python = ">=3.10,<3.13"
 rich = ">=13.7"
 markdown = ">=3.5"
 pyparsing = ">=3.0.0"
-praisonaiagents = ">=0.0.117"
+praisonaiagents = ">=0.0.121"
 python-dotenv = ">=0.19.0"
 instructor = ">=1.3.3"
 PyYAML = ">=6.0"
@@ -3931,7 +3931,7 @@ wheels = [

 [[package]]
 name = "praisonai"
-version = "2.2.44"
+version = "2.2.47"
 source = { editable = "." }
 dependencies = [
    { name = "instructor" },
@@ -4073,7 +4073,7 @@ requires-dist = [
    { name = "plotly", marker = "extra == 'realtime'", specifier = ">=5.24.0" },
    { name = "praisonai-tools", marker = "extra == 'autogen'", specifier = ">=0.0.15" },
    { name = "praisonai-tools", marker = "extra == 'crewai'", specifier = ">=0.0.15" },
-    { name = "praisonaiagents", specifier = ">=0.0.117" },
+    { name = "praisonaiagents", specifier = ">=0.0.121" },
    { name = "pyautogen", marker = "extra == 'autogen'", specifier = ">=0.2.19" },
    { name = "pydantic", marker = "extra == 'chat'", specifier = "<=2.10.1" },
    { name = "pydantic", marker = "extra == 'code'", specifier = "<=2.10.1" },
@@ -4130,7 +4130,7 @@ wheels = [

 [[package]]
 name = "praisonaiagents"
-version = "0.0.117"
+version = "0.0.121"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
    { name = "mcp" },
@@ -4139,9 +4139,9 @@ dependencies = [
    { name = "pydantic" },
    { name = "rich" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/3e/0e/663cdeecbc32af35b8f7ee662079d75c7d743a7d6507fe9742fe5e3edf9e/praisonaiagents-0.0.117.tar.gz", hash = "sha256:b28605506863689433d7825bda72272b04254b5fe95be2a9899d8e96a89467aa", size = 173294 }
+sdist = { url = "https://files.pythonhosted.org/packages/a6/3f/249dc75d8d66c692a2f487286907358afc5f92a9d52ffb2fbee140213be8/praisonaiagents-0.0.121.tar.gz", hash = "sha256:ca121d455f78b30afe5c41ae785ff4b4273b4dfd058b43d326f0255471a828c2", size = 172455 }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/9d/7b/cd590e238196f9539db7302118a2fad2eec4a319566025ae7c2768bbec6f/praisonaiagents-0.0.117-py3-none-any.whl", hash = "sha256:42014556f65da3a27aa30f6446e4408df7e9cc3f2e9cf428e43e44c3244d4857", size = 193878 },
+    { url = "https://files.pythonhosted.org/packages/c2/52/2fad476c91c5ff848d844773c045a8302a9336860e6fdc5cf10636ed79f1/praisonaiagents-0.0.121-py3-none-any.whl", hash = "sha256:4ad623a2ece1ecc5dd1c02e3bba3e79847fe6129bcbafafb380670b383abf299", size = 193136 },
 ]

 [[package]]
Author	SHA1	Message	Date
Mervin Praison	0213dea12b	chore: update PraisonAI version to 2.2.47 in Dockerfiles, README, and related files	2025-07-10 23:30:27 +01:00
Mervin Praison	c0d495fd48	Merge pull request #781 from MervinPraison/claude/issue-754-20250709_155906 refactor: eliminate sync/async duplication in llm.py	2025-07-10 23:21:04 +01:00
Mervin Praison	0e51ed0d6c	Merge branch 'main' of https://github.com/MervinPraison/PraisonAI	2025-07-10 23:20:50 +01:00
Mervin Praison	32dce14f96	chore: update version to 0.0.120 in pyproject.toml and uv.lock	2025-07-10 23:20:48 +01:00
Mervin Praison	27aaac80c6	Merge branch 'main' into claude/issue-754-20250709_155906	2025-07-10 23:20:17 +01:00
Mervin Praison	5a0a3983e4	Merge pull request #794 from MervinPraison/claude/pr-791-20250710_214815 PR #791: Changes from Claude	2025-07-10 23:19:03 +01:00
claude[bot]andMervin Praison	400a4c934e	fix: properly pass base_url and api_key parameters to OpenAI client and agents - Create new OpenAIClient instance when custom base_url or api_key are provided - Pass base_url and api_key to Agent instances for consistency - Maintain backward compatibility by falling back to singleton client when no custom parameters Co-authored-by: Mervin Praison <[email protected]>	2025-07-10 22:13:29 +00:00
Mervin Praison	e88b0fd47b	Merge pull request #793 from MervinPraison/claude/issue-754-20250709_155933 refactor: extract debug logging into centralized method	2025-07-10 23:11:57 +01:00
claude[bot]andMervin Praison	e6c1c0679f	fix: address review comments for debug logging refactor - Restore backward compatibility for verbose parameter (verbose >= 10 now works) - Fix condition ordering bug (check "parameters" before "_async") - Fix API key masking for empty strings - Add type check for system_prompt truncation - Add iterable check for tools parameter - Restore original prompt logging behavior for non-string prompts Co-authored-by: Mervin Praison <[email protected]>	2025-07-10 22:03:01 +00:00
claude[bot]andMervin Praison	108aee0a54	fix: remove duplicate _handle_ollama_model method and fix double tool call processing - Remove duplicate _handle_ollama_model method definition - Fix bug where tool calls were processed twice in verbose streaming - Keep the method with better type hints (Union[str, List[Dict]]) - Remove redundant _process_tool_calls_from_stream calls after _process_stream_delta Co-authored-by: Mervin Praison <[email protected]>	2025-07-10 22:02:58 +00:00
Mervin Praison	cb017aad70	Merge branch 'main' into claude/issue-754-20250709_155906	2025-07-10 22:53:33 +01:00
claude[bot]andMervin Praison	ea29d3181b	fix: properly handle OpenAI client API and store base_url/api_key - Use OpenAIClient's parse_structured_output method instead of accessing client.beta directly - Store base_url and api_key as instance variables to support custom endpoints - This fixes the AttributeError when using AutoAgents with non-OpenAI providers Co-authored-by: Mervin Praison <[email protected]>	2025-07-10 21:50:39 +00:00
claude[bot]andMervin Praison	7f0f265671	refactor: eliminate sync/async duplication in llm.py - Extract common logic into shared helper methods - Fix variable reference errors for ollama_params - Reduce code duplication between get_response/get_response_async - Reduce code duplication between response/aresponse - Maintain 100% backward compatibility - No API changes or breaking changes Fixes #754 Co-authored-by: Mervin Praison <[email protected]>	2025-07-10 21:42:47 +00:00
Mervin Praison	bc1c508419	Merge pull request #789 from MervinPraison/claude/issue-787-20250710_205703 fix: prevent double output when using litellm models	2025-07-10 22:37:16 +01:00
Mervin Praison	bd108ba3e7	Merge pull request #791 from MervinPraison/claude/issue-788-20250710_210226 fix: add multi-provider support for AutoAgents	2025-07-10 22:34:58 +01:00
claude[bot]andMervin Praison	ac5f2649df	refactor: resolve merge conflicts with main branch - Renamed _prepare_ollama_followup to _handle_ollama_model to match main branch - Updated method signature to (response_text, tool_results, messages, original_prompt) - Modified return value to dict with follow_up_messages and original_prompt - Updated all call sites to use the new interface - Maintained backward compatibility and refactoring benefits Co-authored-by: Mervin Praison <[email protected]>	2025-07-10 21:34:28 +00:00
claude[bot]andMervin Praison	1b64762d54	fix: add verbose checks to all display_interaction calls for consistency - Applied consistent pattern to all 4 display_interaction calls - Now all checks follow pattern: if self.verbose and not self._using_custom_llm - Ensures display is only shown when verbose mode is enabled AND not using custom LLM - Maintains backward compatibility while fixing the inconsistency Co-authored-by: Mervin Praison <[email protected]>	2025-07-10 21:29:45 +00:00
claude[bot]andMervin Praison	df402bcfdb	fix: correct indentation error in aresponse method Fixed incorrect indentation in the async Ollama follow-up handling code that was causing a syntax error at line 1364. Co-authored-by: Mervin Praison <[email protected]>	2025-07-10 21:20:39 +00:00
claude[bot]andMervin Praison	061c8d58b4	fix: add multi-provider support for AutoAgents - Replace OpenAI-specific beta.chat.completions.parse() with cross-provider LLM class - Maintain backward compatibility by using structured output for OpenAI models - Add support for all LiteLLM providers (Gemini, Anthropic, etc.) - Include robust JSON parsing to handle markdown-wrapped responses - Fixes #788: AttributeError when using AutoAgent with Gemini provider Co-authored-by: Mervin Praison <[email protected]>	2025-07-10 21:18:52 +00:00
Mervin Praison	117c02cf30	chore: update PraisonAI and related package versions to 2.2.46 and 0.0.119 - Updated PraisonAI version in Dockerfiles and README to 2.2.46 - Updated version in pyproject.toml and uv.lock for PraisonAI and PraisonAI agents to 0.0.119 - Adjusted deployment script to reflect the new PraisonAI version	2025-07-10 22:16:47 +01:00
claude[bot]andMervin Praison	82c9ff80a7	fix: correct indentation error in get_response method Fixed incorrect indentation in lines 779-804 of the get_response method that was causing IndentationError. The code block for Ollama follow-up handling is now properly nested within the if follow_up_prompt block. Co-authored-by: Mervin Praison <[email protected]>	2025-07-10 21:15:53 +00:00
Mervin Praison	f44b15d73b	Merge pull request #782 from MervinPraison/claude/issue-754-20250709_155935 refactor: extract streaming chunk processor to eliminate code duplication	2025-07-10 22:13:29 +01:00
claude[bot]andMervin Praison	f2c89c2012	fix: prevent double output when using litellm models - Check for self._using_custom_llm before calling display_interaction - Custom LLM already handles display in its get_response method - Fixes issue #787 where task/response printed twice with litellm Co-authored-by: Mervin Praison <[email protected]>	2025-07-10 21:12:41 +00:00
Mervin Praison	fd2569e642	chore: update PraisonAI and related package versions to 2.2.45 and 0.0.118 - Updated PraisonAI version in Dockerfiles and README to 2.2.45 - Updated version in pyproject.toml and uv.lock for PraisonAI and PraisonAI agents to 0.0.118 - Adjusted deployment script to reflect the new PraisonAI version	2025-07-10 22:08:47 +01:00
Mervin Praison	58efb4b4cd	Merge pull request #783 from MervinPraison/claude/issue-754-20250709_155947 refactor: extract Ollama handler to eliminate code duplication	2025-07-10 22:04:05 +01:00
claude[bot]andMervin Praison	f3f5f63b22	refactor: eliminate sync/async duplication in llm.py - Extract common logic into shared helper methods - Reduce code duplication between get_response/get_response_async - Reduce code duplication between response/aresponse - Maintain 100% backward compatibility - No API changes or breaking changes Addresses issue #754 Co-authored-by: Mervin Praison <[email protected]>	2025-07-09 16:07:51 +00:00
claude[bot]andMervin Praison	ccf9470f41	refactor: extract debug logging into centralized _log_llm_config method - Created private _log_llm_config method to handle all debug logging - Eliminated ~116 lines of duplicated debug logging code - Maintains 100% backward compatibility (no API changes) - Centralizes security measures (API key masking) - Consistent formatting across all logging calls - No functional changes, only code organization Addresses code duplication issue #754 Co-authored-by: Mervin Praison <[email protected]>	2025-07-09 16:05:59 +00:00
claude[bot]andMervin Praison	75cf937581	refactor: extract Ollama handler to eliminate code duplication - Created shared _handle_ollama_model method to consolidate logic - Updated both sync and async methods to use the shared handler - Eliminated ~185 lines of duplicated code - Maintained 100% backward compatibility Co-authored-by: Mervin Praison <[email protected]>	2025-07-09 16:04:38 +00:00
claude[bot]andMervin Praison	d228a742b7	refactor: extract streaming chunk processor to eliminate code duplication - Add _process_stream_delta() helper method to consolidate duplicate logic - Refactor 4 duplicated streaming sections (sync/async, verbose/non-verbose) - Eliminates ~50 lines of duplicated code - Maintains 100% backward compatibility with no API changes - Addresses original issue #754 about streaming code duplication Co-authored-by: Mervin Praison <[email protected]>	2025-07-09 16:03:24 +00:00