fix(examples): phase-4 API alignment for 40 validation failures on v4.6.52 (#1865)

Co-authored-by: Dhivya-Bharathy <[email protected]>

examples/approval/agent_approval.py

@@ -12,10 +12,15 @@ from praisonaiagents import Agent
 from praisonaiagents.approval import AgentApproval
 from praisonaiagents.tools.shell_tools import execute_command
 
-reviewer = AgentApproval(
+reviewer_agent = Agent(
+    name="CommandReviewer",
     instructions="Only approve read-only commands like 'ls' or 'cat'. Deny destructive commands.",
 )
 
+reviewer = AgentApproval(
+    approver_agent=reviewer_agent,
+)
+
 agent = Agent(
     name="DevOps",
     instructions="You are a DevOps assistant. Use shell tools when asked.",

examples/benchmark/benchmark_example.py

@@ -35,7 +35,7 @@ def run_quick_comparison():
         prompt="What is 2+2?",
         iterations=2,
         paths=["openai_sdk", "praisonai_agent"],
-        output="verbose"
+        verbose=True
     )
     
     # Print comparison table
@@ -56,7 +56,7 @@ def run_full_benchmark():
     report = handler.run_full_benchmark(
         prompt="Hi",
         iterations=3,
-        output="verbose"
+        verbose=True
     )
     
     # Print full report
@@ -78,7 +78,7 @@ def run_agent_benchmark():
         prompt="Explain Python in one sentence",
         iterations=3,
         paths=["openai_sdk", "praisonai_agent"],
-        output="verbose"
+        verbose=True
     )
     
     # Show timeline diagrams

examples/compare/cli_compare_advanced.py

@@ -22,7 +22,7 @@ custom_modes = {
 }
 
 # Create handler with verbose output
-handler = CompareHandler(output="verbose")
+handler = CompareHandler(verbose=True)
 
 # Example: Manually create comparison results for analysis
 # (useful for testing without API calls)

examples/compare/cli_compare_basic.py

@@ -22,7 +22,7 @@ modes = parse_modes("basic,tools,planning")
 print(f"\nParsed modes: {modes}")
 
 # Create compare handler
-handler = CompareHandler(output="verbose")
+handler = CompareHandler(verbose=True)
 
 # Compare modes (this will run actual agent calls)
 # Uncomment to run:

examples/consolidated_params/advanced_memory.py

@@ -15,7 +15,7 @@ agent = Agent(
 # With array [preset, overrides]
 agent_override = Agent(
     instructions="You are a helpful assistant.",
-    memory=["redis", {"user_id": "custom_user"}],
+    memory=MemoryConfig(backend="redis", user_id="custom_user"),
 )
 
 if __name__ == "__main__":

examples/consolidated_params/advanced_workflow_full_features.py

@@ -2,7 +2,7 @@
 from praisonaiagents import Agent
 from praisonaiagents import AgentFlow, Task
 from praisonaiagents.workflows.workflow_configs import (
-    WorkflowOutputConfig, WorkflowPlanningConfig, WorkflowMemoryConfig,
+    WorkflowPlanningConfig, WorkflowMemoryConfig, WorkflowOutputConfig,
 )
 
 # Full-featured workflow with all consolidated params
@@ -32,7 +32,7 @@ workflow = AgentFlow(
         ),
     ],
     # Workflow-level consolidated params
-    output=WorkflowOutputConfig(output="verbose", stream=True),
+    output=WorkflowOutputConfig(verbose=True, stream=True),
     planning=WorkflowPlanningConfig(enabled=True, reasoning=True),
     memory=WorkflowMemoryConfig(backend="file"),
     # Agent-like params

examples/consolidated_params/basic_web.py

@@ -10,7 +10,7 @@ from praisonaiagents import Agent
 # Basic: Enable web search with preset
 agent = Agent(
     instructions="You are a research assistant with web access.",
-    web="duckduckgo",  # Presets: duckduckgo, tavily, google, bing, serper
+    web="search_only",  # Compatible across models without web_fetch
 )
 
 if __name__ == "__main__":

examples/consolidated_params/basic_workflow.py

@@ -15,8 +15,20 @@ workflow = AgentFlow(
     ],
     output="verbose",
     planning=True,
+    variables={"topic": "AI agents"},
 )
 
 if __name__ == "__main__":
-    result = workflow.run(variables={"topic": "AI agents"})
+    import os
+    import sys
+
+    if not os.environ.get("OPENAI_API_KEY"):
+        print("Set OPENAI_API_KEY to run this example.")
+        sys.exit(0)
+    if sys.platform == "win32":
+        try:
+            sys.stdout.reconfigure(encoding="utf-8")
+        except Exception:
+            pass
+    result = workflow.run()
     print(result)

examples/eval/accuracy_example.py

@@ -24,7 +24,7 @@ if has_api_key:
         input_text="What is 2 + 2?",
         expected_output="4",
         num_iterations=3,  # Run 3 times for statistical significance
-        output="verbose"
+        verbose=True
     )
 
     # Run evaluation
@@ -42,7 +42,7 @@ else:
         input_text="What is 2 + 2?",
         expected_output="4",
         num_iterations=1,
-        output="verbose"
+        verbose=True
     )
     
     # Test with mock output

examples/eval/criteria_example.py

@@ -27,7 +27,7 @@ if has_api_key:
         scoring_type="numeric",  # Score 1-10
         threshold=7.0,           # Pass if score >= 7
         num_iterations=2,
-        output="verbose"
+        verbose=True
     )
 
     # Run evaluation
@@ -45,7 +45,7 @@ if has_api_key:
         agent=agent,
         input_text="Tell me a joke",
         scoring_type="binary",  # Pass or Fail
-        output="verbose"
+        verbose=True
     )
 
     binary_result = binary_evaluator.run(print_summary=True)

examples/eval/performance_example.py

@@ -26,7 +26,7 @@ if has_api_key:
         num_iterations=10,  # Run 10 benchmark iterations
         warmup_runs=2,      # 2 warmup runs before measurement
         track_memory=True,  # Track memory usage
-        output="verbose"
+        verbose=True
     )
 
     # Run evaluation

examples/eval/reliability_example.py

@@ -48,7 +48,7 @@ if has_api_key:
         input_text="Search for the weather in Paris and calculate 25 * 4",
         expected_tools=["search_web", "calculate"],  # Tools that should be called
         forbidden_tools=["delete_file"],  # Tools that should NOT be called
-        output="verbose"
+        verbose=True
     )
 
     # Run evaluation
@@ -70,7 +70,7 @@ evaluator = ReliabilityEvaluator(
     agent=mock_agent,
     expected_tools=["search_web", "calculate"],  # Tools that should be called
     forbidden_tools=["delete_file"],  # Tools that should NOT be called
-    output="verbose"
+    verbose=True
 )
 
 result2 = evaluator.evaluate_tool_calls(

examples/knowledge/compression_demo.py

@@ -184,7 +184,7 @@ Answer questions based ONLY on the provided knowledge context.
 When asked about codes, provide the EXACT code from the documents.
 Be concise but accurate.""",
             knowledge=[temp_dir],
-            user_id="compression_demo_user",
+            memory={"user_id": "compression_demo_user"},
             output="verbose",
         )
         

examples/knowledge/context_required_example.py

@@ -80,7 +80,7 @@ Be precise and quote exact values when asked about codes or numbers.""",
         print(f"\nAnswer: {response}\n")
         
         # Verify the answer contains the unique code
-        if "ZEBRA-71" in response.upper():
+        if "ZEBRA-71" in str(response or "").upper():
             print("✅ VERIFIED: Agent correctly retrieved the unique code from context!\n")
         else:
             print("❌ WARNING: Agent did not find the code - check retrieval\n")
@@ -104,7 +104,7 @@ Be precise and quote exact values when asked about codes or numbers.""",
         response = agent.chat("What is the security incident code?")
         print(f"\nAnswer: {response}\n")
         
-        if "HAWK-88" in response.upper():
+        if "HAWK-88" in str(response or "").upper():
             print("✅ VERIFIED: Agent correctly retrieved the security code!\n")
         else:
             print("❌ WARNING: Agent did not find the code - check retrieval\n")

examples/knowledge/hierarchical_summaries_demo.py

@@ -164,7 +164,7 @@ Answer questions based ONLY on the provided knowledge context.
 When asked about department codes, provide the EXACT code from the documents.
 Be specific about which department you're referring to.""",
             knowledge=[temp_dir],
-            user_id="hierarchy_demo_user",
+            memory={"user_id": "hierarchy_demo_user"},
             output="verbose",
         )
         

examples/knowledge/large_corpus_strategy_demo.py

@@ -124,7 +124,7 @@ def main():
             # Show strategy selection for different corpus sizes
             print(f"\nStrategy selection by corpus size:")
             for size in [100, 1000, 10000, 50000, 100000]:
-                strategy = select_strategy(corpus_tokens=size)
+                strategy = select_strategy(CorpusStats(file_count=max(1, size // 1000), total_tokens=size))
                 print(f"  {size:>6} tokens -> {strategy.value}")
                 
         except ImportError as e:
@@ -142,7 +142,7 @@ Answer questions based ONLY on the provided knowledge context.
 When asked about verification codes, provide the EXACT code from the documents.
 If information is not in the context, say 'Information not found in documents.'""",
             knowledge=[temp_dir],
-            user_id="strategy_demo_user",
+            memory={"user_id": "strategy_demo_user"},
             output="verbose",  # Use new consolidated param
         )
         

examples/knowledge/mem0_backend_example.py

@@ -65,7 +65,7 @@ def main():
             name="PolicyExpert",
             instructions="You are a company policy expert. Answer questions based ONLY on the provided knowledge. Quote exact values when asked about codes or numbers.",
             knowledge=[temp_dir],  # Add directory with documents
-            user_id="example_user",  # Required for mem0 backend
+            memory={"user_id": "example_user"},
         )
         
         print("\n1. Testing Agent.chat() with context-required question:")

examples/knowledge/scope_identifiers_example.py

@@ -50,7 +50,7 @@ def main():
             name="HR_Assistant_User1",
             instructions="You are an HR assistant.",
             knowledge=[temp_dir],
-            user_id="user_alice",  # Knowledge scoped to Alice
+            memory={"user_id": "user_alice"},
         )
         
         response = user1_agent.chat("What is the policy on remote work?")
@@ -80,7 +80,7 @@ def main():
             name="Personal_HR_Bot",
             instructions="You are a personal HR assistant.",
             knowledge=[temp_dir],
-            user_id="user_bob",
+            memory={"user_id": "user_bob"},
             agent_id="hr_bot_v2",
         )
         

examples/knowledge/scope_isolation_example.py

@@ -49,7 +49,7 @@ Only authorized personnel with code WRENCH-992 may access this project.
             name="AgentA_Ingester",
             instructions="You ingest and store knowledge.",
             knowledge=[temp_dir],
-            user_id="user_alice",  # Scoped to Alice
+            memory={"user_id": "user_alice"},
             output="silent",
         )
         
@@ -103,7 +103,7 @@ Only authorized personnel with code WRENCH-992 may access this project.
             name="AgentB_Querier",
             instructions="Answer questions based on the provided knowledge. If you don't have the information, say so.",
             knowledge=[temp_dir],
-            user_id="user_alice",  # Same scope as Agent A
+            memory={"user_id": "user_alice"},
             output="silent",
         )
         

examples/managed-agents/persistence/cockroachdb_managed.py

@@ -17,8 +17,10 @@ from praisonaiagents import Agent
 agent = Agent(
     name="CockroachDB Agent",
     instructions="You are a helpful assistant.",
-    db={"database_url": os.getenv("COCKROACHDB_URL")},
-    session_id="crdb-demo-session",
+    memory={
+        "session_id": "crdb-demo-session",
+        "db": {"database_url": os.getenv("COCKROACHDB_URL")},
+    },
 )
 
 result = agent.start("What is distributed SQL? Explain in 2 sentences.")

examples/managed-agents/persistence/neon_managed.py

@@ -18,8 +18,10 @@ from praisonaiagents import Agent
 agent = Agent(
     name="Neon Agent",
     instructions="You are a helpful assistant.",
-    db={"database_url": os.getenv("NEON_DATABASE_URL")},
-    session_id="neon-demo-session",
+    memory={
+        "session_id": "neon-demo-session",
+        "db": {"database_url": os.getenv("NEON_DATABASE_URL")},
+    },
 )
 
 # Option 2: Direct URL

examples/managed-agents/persistence/supabase_direct_managed.py

@@ -20,8 +20,10 @@ from praisonaiagents import Agent
 agent = Agent(
     name="Supabase Agent",
     instructions="You are a helpful assistant.",
-    db={"database_url": os.getenv("SUPABASE_DATABASE_URL")},
-    session_id="supabase-demo-session",
+    memory={
+        "session_id": "supabase-demo-session",
+        "db": {"database_url": os.getenv("SUPABASE_DATABASE_URL")},
+    },
 )
 
 result = agent.start("What is Supabase? Explain in 2 sentences.")

examples/managed-agents/persistence/turso_managed.py

@@ -18,11 +18,13 @@ from praisonaiagents import Agent
 agent = Agent(
     name="Turso Agent",
     instructions="You are a helpful assistant.",
-    db={
-        "database_url": os.getenv("TURSO_DATABASE_URL"),
-        "auth_token": os.getenv("TURSO_AUTH_TOKEN"),
+    memory={
+        "session_id": "turso-demo-session",
+        "db": {
+            "database_url": os.getenv("TURSO_DATABASE_URL"),
+            "auth_token": os.getenv("TURSO_AUTH_TOKEN"),
+        },
     },
-    session_id="turso-demo-session",
 )
 
 result = agent.start("What is edge computing? Explain in 2 sentences.")

examples/middleware/configurable_model.py

@@ -10,8 +10,7 @@ from praisonaiagents import Agent
 agent = Agent(
     name="FlexBot",
     instructions="You are a helpful assistant.",
-    llm="gpt-4o-mini",
-    llm_config={"configurable": True}
+    llm={"model": "gpt-4o-mini", "configurable": True},
 )
 
 if __name__ == "__main__":

examples/middleware/injected_state.py

@@ -21,7 +21,7 @@ agent = Agent(
     name="ContextBot",
     instructions="You help show context information.",
     tools=[show_context],
-    session_id="my-session-123"
+    memory={"session_id": "my-session-123"},
 )
 
 if __name__ == "__main__":

examples/observability/multi_agent_tracing.py

@@ -19,6 +19,16 @@ from praisonaiagents import Agent, AgentTeam
 # Initialize observability
 obs.init()
 
+
+def set_span_attr(span, key, value):
+    """Set span attribute safely across observability implementations."""
+    if hasattr(span, "set_attribute"):
+        span.set_attribute(key, value)
+        return
+    attrs = getattr(span, "attributes", None)
+    if attrs is not None:
+        attrs[key] = value
+
 # Create agents
 researcher = Agent(
     name="Researcher",
@@ -37,13 +47,13 @@ with obs.trace("content-creation", metadata={"workflow": "research-write"}):
     
     # Research phase
     with obs.span("research-phase", kind=SpanKind.AGENT) as research_span:
-        research_span.attributes["agent"] = "Researcher"
+        set_span_attr(research_span, "agent", "Researcher")
         research_result = researcher.chat("Research the benefits of AI in healthcare")
     
     # Writing phase  
     with obs.span("writing-phase", kind=SpanKind.AGENT) as write_span:
-        write_span.attributes["agent"] = "Writer"
-        write_span.attributes["input_length"] = len(str(research_result))
+        set_span_attr(write_span, "agent", "Writer")
+        set_span_attr(write_span, "input_length", len(str(research_result)))
         final_content = writer.chat(f"Write a blog post based on: {research_result}")
 
 print("Final Content:")

examples/persistence/knowledge_qdrant.py

@@ -50,10 +50,12 @@ print("=== Qdrant Knowledge Store Demo (Agent-First) ===")
 agent = Agent(
     name="KnowledgeAssistant",
     instructions="You are a helpful assistant with access to technical documentation.",
-    knowledge=[doc_path],
     knowledge={
-        "vector_store": "qdrant",
-        "url": "http://localhost:6333"
+        "sources": [doc_path],
+        "vector_store": {
+            "provider": "qdrant",
+            "url": "http://localhost:6333",
+        },
     }
 )
 

examples/persistence/minimal_agent_db.py

@@ -13,7 +13,8 @@ Expected output:
     - Session can be resumed later with same session_id
 """
 
-from praisonaiagents import Agent, db
+from praisonaiagents import Agent
+from praisonaiagents.db import db
 
 # Create database connection (PostgreSQL + Redis)
 my_db = db(
@@ -25,10 +26,12 @@ my_db = db(
 agent = Agent(
     name="Assistant",
     instructions="You are a helpful assistant. Be concise.",
-    db=my_db,
-    # session_id is optional - defaults to per-hour ID (YYYYMMDDHH-hash)
-    # Set explicitly for session continuity across runs:
-    session_id="my-persistent-session"
+    memory={
+        "db": my_db,
+        # session_id is optional - defaults to per-hour ID (YYYYMMDDHH-hash)
+        # Set explicitly for session continuity across runs:
+        "session_id": "my-persistent-session",
+    },
 )
 
 # Chat - messages are automatically persisted

examples/persistence/postgres_runs_traces.py

@@ -12,7 +12,8 @@ Expected output:
     - Export shows full session data
 """
 
-from praisonaiagents import Agent, db
+from praisonaiagents import Agent
+from praisonaiagents.db import db
 
 def get_weather(city: str) -> str:
     """Get weather for a city."""
@@ -29,8 +30,10 @@ agent = Agent(
     name="WeatherBot",
     instructions="You help with weather. Use the get_weather tool when asked.",
     tools=[get_weather],
-    db=my_db,
-    session_id="weather-session-001"
+    memory={
+        "db": my_db,
+        "session_id": "weather-session-001",
+    },
 )
 
 # First chat - triggers run tracking

examples/persistence/redis_state.py

@@ -13,7 +13,8 @@ Expected output:
     Agent responds with state persisted to Redis
 """
 
-from praisonaiagents import Agent, db
+from praisonaiagents import Agent
+from praisonaiagents.db import db
 
 print("=== Redis State Store (Agent-First) ===")
 
@@ -26,8 +27,10 @@ my_db = db(
 agent = Agent(
     name="Assistant",
     instructions="You are a helpful assistant.",
-    db=my_db,
-    session_id="redis-state-session"
+    memory={
+        "db": my_db,
+        "session_id": "redis-state-session",
+    },
 )
 
 # Chat - state is automatically managed via Redis

examples/persistence/session_resume.py

@@ -11,7 +11,8 @@ Expected output:
     - Second run: Resumes with history
 """
 
-from praisonaiagents import Agent, db
+from praisonaiagents import Agent
+from praisonaiagents.db import db
 
 # Create database
 my_db = db(
@@ -25,8 +26,10 @@ SESSION_ID = "resume-demo-session"
 agent = Agent(
     name="MemoryBot",
     instructions="You remember our conversation. Be helpful and concise.",
-    db=my_db,
-    session_id=SESSION_ID
+    memory={
+        "db": my_db,
+        "session_id": SESSION_ID,
+    },
 )
 
 # Check if this is a new or resumed session

examples/persistence/simple_db_agent.py

@@ -26,7 +26,8 @@ Expected Output:
     Messages persisted: 2
 """
 
-from praisonaiagents import Agent, db
+from praisonaiagents import Agent
+from praisonaiagents.db import db
 
 # Create database adapter (simplified import)
 db_instance = db(
@@ -37,8 +38,10 @@ db_instance = db(
 agent = Agent(
     name="Assistant",
     instructions="You are a helpful assistant. Keep responses brief.",
-    db=db_instance,
-    session_id="demo-session-001",  # Same session_id = resume conversation
+    memory={
+        "db": db_instance,
+        "session_id": "demo-session-001",  # Same session_id = resume conversation
+    },
     output="silent"
 )
 

examples/persistence/sqlite_local.py

@@ -11,7 +11,8 @@ Expected output:
     - Data persisted to local SQLite file
 """
 
-from praisonaiagents import Agent, db
+from praisonaiagents import Agent
+from praisonaiagents.db import db
 import tempfile
 import os
 
@@ -25,8 +26,10 @@ print(f"Database: {db_path}")
 agent = Agent(
     name="LocalBot",
     instructions="You are a helpful assistant.",
-    db=my_db,
-    session_id="local-session"
+    memory={
+        "db": my_db,
+        "session_id": "local-session",
+    },
 )
 
 # Chat

examples/policy/basic_policy.py

@@ -57,8 +57,8 @@ def main():
     agent = Agent(
         name="SecureAgent",
         instructions="You are a file management assistant.",
-        policy=engine
     )
+    agent.policy = engine
     
     print("\n--- Agent with Policy Enforcement Created ---")
     print(f"Agent: {agent.name}")

examples/python/agents/autoagents-hierarchical-generation.py

@@ -63,6 +63,6 @@ agents_system = AgentTeam(
 print("Starting hierarchical agent generation...")
 result = agents_system.start()
 
-print(f"\nHierarchical Result: {result[:200]}...")
+print(f"\nHierarchical Result: {str(result)[:200]}...")
 print("\n✅ AutoAgents hierarchical generation complete!")
 print("Demonstrated coordinated hierarchical workflow between manager and specialist agents.")

examples/python/api/simple-mcp-server.py

@@ -1,4 +1,5 @@
 from praisonaiagents import Agent
 
-agent = Agent(name="TweetAgent", instructions="Create a Tweet based on the topic provided")
-agent.launch(port=8080, protocol="mcp")
+if __name__ == "__main__":
+    agent = Agent(name="TweetAgent", instructions="Create a Tweet based on the topic provided")
+    agent.launch(port=8080, protocol="mcp", path="/")

examples/python/camera/camera-basic.py

@@ -90,9 +90,18 @@ def main():
     
     if result:
         print("\n🔍 Analysis Results:")
-        for task_id, task_result in result["task_results"].items():
+        task_results = result.get("task_results") if isinstance(result, dict) else result
+        if isinstance(task_results, dict):
+            iterable = task_results.items()
+        elif isinstance(task_results, list):
+            iterable = enumerate(task_results)
+        else:
+            iterable = [("result", task_results)]
+
+        for task_id, task_result in iterable:
             print(f"\nTask {task_id}:")
-            print(task_result.raw)
+            raw_value = getattr(task_result, "raw", None)
+            print(raw_value if raw_value is not None else str(task_result))
     else:
         print("❌ Failed to capture and analyze camera feed")
 

examples/python/camera/camera-continuous.py

@@ -75,7 +75,7 @@ class ContinuousCameraMonitor:
             agents=[self.vision_agent],
             tasks=[task],
             process="sequential",
-            verbose=0  # Reduced verbosity for continuous monitoring
+            output="silent",  # Reduced verbosity for continuous monitoring
         )
         
         return agents.start()

examples/python/camera/camera-multi-agent.py

@@ -148,10 +148,19 @@ def main():
             "scene_analysis": "🌍 SCENE ANALYSIS"
         }
         
-        for task_id, task_result in result["task_results"].items():
+        task_results = result.get("task_results") if isinstance(result, dict) else result
+        if isinstance(task_results, dict):
+            iterable = task_results.items()
+        elif isinstance(task_results, list):
+            iterable = enumerate(task_results)
+        else:
+            iterable = [("result", task_results)]
+
+        for task_id, task_result in iterable:
             print(f"\n{agent_names.get(task_id, f'Task {task_id}')}:")
             print("-" * 40)
-            print(task_result.raw)
+            raw_value = getattr(task_result, "raw", None)
+            print(raw_value if raw_value is not None else str(task_result))
             
         print("\n" + "="*60)
         print("✅ Multi-agent analysis complete!")

examples/python/cli/autonomy_modes_example.py

@@ -34,5 +34,5 @@ print(f"\nChanged to: {handler.get_mode()}")
 print("File edits now auto-approved, shell commands still require approval")
 
 # Get statistics
-stats = handler.get_stats()
+stats = manager.get_stats()
 print(f"\nStats: {stats}")

examples/python/cli/cost_tracking_example.py

@@ -31,4 +31,4 @@ print(f"Total cost: ${summary['total_cost']:.4f}")
 print(f"Avg cost/request: ${summary['avg_cost_per_request']:.4f}")
 
 # Display formatted (uses Rich if available)
-handler.display_summary()
+handler.print_summary()

examples/python/cli/git_integration_example.py

@@ -8,7 +8,7 @@ Docs: https://docs.praison.ai/cli/git-integration
 from praisonai.cli.features import GitIntegrationHandler
 
 # Initialize
-handler = GitIntegrationHandler(output="verbose")
+handler = GitIntegrationHandler(verbose=True)
 git = handler.initialize(repo_path=".")
 
 # Check if it's a git repo

examples/python/cli/repo_map_example.py

@@ -8,7 +8,7 @@ Docs: https://docs.praison.ai/cli/repo-map
 from praisonai.cli.features import RepoMapHandler
 
 # Initialize with current directory
-handler = RepoMapHandler(output="verbose")
+handler = RepoMapHandler(verbose=True)
 repo_map = handler.initialize(root=".")
 
 # Get the repository map

examples/python/cli/sandbox_execution_example.py

@@ -9,7 +9,7 @@ from praisonai.cli.features import SandboxExecutorHandler
 from praisonai.cli.features.sandbox_executor import SandboxMode
 
 # Initialize with basic sandbox
-handler = SandboxExecutorHandler(output="verbose")
+handler = SandboxExecutorHandler(verbose=True)
 sandbox = handler.initialize(mode="basic")
 
 print(f"Sandbox mode: {handler.get_mode()}")

examples/python/cli/slash_commands_example.py

@@ -41,9 +41,9 @@ def my_custom_handler(args, context):
 custom_cmd = SlashCommand(
     name="mycommand",
     description="My custom command",
-    handler=my_custom_handler,
-    kind=CommandKind.ACTION,
-    aliases=["mc"]
+    action=my_custom_handler,
+    kind=CommandKind.CUSTOM,
+    alt_names=["mc"]
 )
 
 handler.register(custom_cmd)

examples/python/concepts/chat-with-pdf.py

@@ -25,8 +25,7 @@ pdf_agent = Agent(
     goal="Help users understand and extract information from PDF documents",
     backstory="You are an expert at reading, analyzing, and answering questions about PDF documents. You provide accurate, detailed answers based on the document content.",
     instructions="Read the provided PDF document and answer questions about its content. Be specific and cite relevant sections when possible.",
-    knowledge=["document.pdf"],  # Replace with your PDF file path
-    knowledge=config,
+    knowledge={**config, "sources": ["document.pdf"]},  # Replace with your PDF path
     reflection=True,
     
     

examples/python/concepts/knowledge-agents-task.py

@@ -1,6 +1,9 @@
+from pathlib import Path
+
 from praisonaiagents import Agent, Task, AgentTeam
 import logging
 import os
+import sys
 
 # Configure logging
 logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
@@ -17,14 +20,16 @@ config = {
     }
 }
 
+_sample_path = Path(__file__).with_name("sample_knowledge.txt")
+
 # Create an agent with knowledge capabilities
 knowledge_agent = Agent(
     name="KnowledgeAgent",
     role="Information Specialist",
     goal="Store and retrieve knowledge efficiently",
     backstory="Expert in managing and utilizing stored knowledge",
-    knowledge=["sample.pdf"],
-    knowledge=config)
+    knowledge={**config, "sources": [str(_sample_path)]},
+)
 
 # Define a task for the agent
 knowledge_task = Task(
@@ -39,8 +44,20 @@ agents = AgentTeam(
     agents=[knowledge_agent],
     tasks=[knowledge_task],
     process="sequential",
-    user_id="user1"
 )
 
-# Start execution
-result = agents.start()
+if __name__ == "__main__":
+    # Create sample file for this run only
+    if not _sample_path.exists():
+        _sample_path.write_text("Mervin Praison is the creator of PraisonAI.\n", encoding="utf-8")
+    
+    if not os.environ.get("OPENAI_API_KEY"):
+        print("Set OPENAI_API_KEY to run this example.")
+        sys.exit(0)
+    if sys.platform == "win32":
+        try:
+            sys.stdout.reconfigure(encoding="utf-8")
+        except Exception:
+            pass
+    result = agents.start()
+    print(result)

examples/python/concepts/knowledge-reranker-example.py

@@ -138,8 +138,7 @@ def main():
     agent = Agent(
         name="AI Research Assistant",
         instructions="You are an AI research assistant. Use your knowledge base to answer questions about artificial intelligence topics.",
-        knowledge=sample_documents,  # Will use default knowledge config
-        knowledge=rerank_config,  # Use reranking config
+        knowledge={**rerank_config, "sources": sample_documents},
         llm="gpt-4o-mini"
     )
     

examples/python/concepts/rag-agents.py

@@ -32,8 +32,12 @@ rag_task = Task(
 agents = AgentTeam(
     agents=[rag_agent],
     tasks=[rag_task],
-    user_id="user1"
 )
 
-# Start Agents
-agents.start()
+if __name__ == "__main__":
+    import os
+    import sys
+    if not os.environ.get("OPENAI_API_KEY"):
+        print("Set OPENAI_API_KEY to run this example.")
+        sys.exit(0)
+    agents.start()

examples/python/concepts/repetitive-agents.py

@@ -16,7 +16,7 @@ agents = AgentTeam(
     agents=[agent],
     tasks=[task],
     process="workflow",
-    max_iter=30
+    execution={"max_iter": 30},
 )
 
 agents.start()

examples/python/concepts/self-reflection-optimization-patterns.py

@@ -34,8 +34,14 @@ reflection_task = Task(
 
 # Run with self-reflection optimization
 print("Starting self-reflection optimization demonstration...")
-result = reflection_agent.execute_task(reflection_task)
+agents = AgentTeam(
+    agents=[reflection_agent],
+    tasks=[reflection_task],
+    process="sequential",
+    output="verbose",
+)
+result = agents.start()
 
-print(f"\nSelf-Reflection Result: {result[:200]}...")
+print(f"\nSelf-Reflection Result: {str(result)[:200]}...")
 print("\n✅ Self-reflection optimization complete!")
 print("Agent demonstrated iterative improvement through built-in self-reflection capabilities.")

examples/python/custom_tools/example_latency_tracking.py

@@ -61,7 +61,6 @@ def example_with_wrappers():
         role="Data Analyst",
         goal="Analyze data and provide insights",
         llm="gpt-4o-mini",
-        request_id="request_2"  # Unique request ID
     )
     
     # Operations are automatically tracked

examples/python/data/cot-agents.py

@@ -132,7 +132,8 @@ agents = AgentTeam(
     agents=[qa_generator, total_questions_evaluator, cot_generator, upload_to_huggingface],
     tasks=[generate_task, evaluate_total_questions_task, generate_cot_task, upload_to_huggingface_task],
     process="workflow",
-    max_iter=30, output="minimal"
+    execution={"max_iter": 30},
+    output="minimal",
 )
 
 agents.start()

examples/python/failover_example.py

@@ -18,7 +18,7 @@ openai_profile = AuthProfile(
     provider="openai",
     api_key=os.environ.get("OPENAI_API_KEY", "sk-..."),
     priority=1,  # Highest priority
-    rate_limit=100,
+    rate_limit_rpm=100,
 )
 
 anthropic_profile = AuthProfile(
@@ -26,7 +26,7 @@ anthropic_profile = AuthProfile(
     provider="anthropic",
     api_key=os.environ.get("ANTHROPIC_API_KEY", "sk-ant-..."),
     priority=2,  # Second priority
-    rate_limit=50,
+    rate_limit_rpm=50,
 )
 
 groq_profile = AuthProfile(
@@ -34,7 +34,7 @@ groq_profile = AuthProfile(
     provider="groq",
     api_key=os.environ.get("GROQ_API_KEY", "gsk-..."),
     priority=3,  # Third priority (fast but limited)
-    rate_limit=30,
+    rate_limit_rpm=30,
 )
 
 # Configure failover behavior

examples/python/general/memory_example.py

@@ -5,7 +5,7 @@ import os
 def main():
     # Initialize memory config
     memory_config = {
-        "provider": "rag",
+        "backend": "sqlite",
         "use_embedding": True,
         "storage": {
             "type": "sqlite",
@@ -105,13 +105,13 @@ def main():
         agents=[researcher, retriever],
         tasks=[store_task, verify_task, query_task, query_both_task],  # Use same verbose level as memory
         memory={
-            "provider": "rag",
             "embedder": {
                 "provider": "openai",
                 "config": {
                     "model": "text-embedding-3-small"
                 }
-            }
+            },
+            "config": {"provider": "sqlite"},
         }
     )
 

examples/python/general/multimodal.py

@@ -53,6 +53,15 @@ agents = AgentTeam(
 result = agents.start()
 
 # Print results
-for task_id, task_result in result["task_results"].items():
+task_results = result.get("task_results") if isinstance(result, dict) else result
+if isinstance(task_results, dict):
+    iterable = task_results.items()
+elif isinstance(task_results, list):
+    iterable = enumerate(task_results)
+else:
+    iterable = [("result", task_results)]
+
+for task_id, task_result in iterable:
     print(f"\nTask {task_id} Result:")
-    print(task_result.raw)
+    raw_value = getattr(task_result, "raw", None)
+    print(raw_value if raw_value is not None else str(task_result))

examples/python/guardrails/production-guardrails-patterns.py

@@ -6,6 +6,7 @@ built-in validation and safety mechanisms for secure agent operations.
 """
 
 from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents.config.feature_configs import GuardrailConfig
 from praisonaiagents.tools import internet_search
 
 print("=== Production Guardrails Patterns Example ===\n")
@@ -38,8 +39,8 @@ production_agent = Agent(
     goal="Generate safe, compliant content for production use",
     backstory="Production-ready agent with built-in safety and compliance checks",
     tools=[internet_search],
-    guardrails=content_guardrail,
-    max_retries=3)
+    guardrails=GuardrailConfig(validator=content_guardrail, max_retries=3),
+)
 
 # Create secure task with validation
 secure_task = Task(

examples/python/linear_agent_example.py

@@ -40,7 +40,7 @@ agent = Agent(
         "execute_command"
     ],
     memory=True,
-    web_search=True,
+    web=True,
     auto_approve_tools=True,
 )
 

examples/python/managed-agents/19_manage_environments.py

@@ -14,30 +14,33 @@ agent = Agent(name="env-mgmt", backend=managed)
 # First call creates agent + environment + session
 agent.start("Say hello briefly")
 
-# Access the underlying Anthropic client for environment management
-client = managed._get_client()
-env_id = managed.environment_id
-print(f"Environment ID: {env_id}")
+if hasattr(managed, "_get_client"):
+    # Access the underlying Anthropic client for environment management
+    client = managed._get_client()
+    env_id = managed.environment_id
+    print(f"Environment ID: {env_id}")
 
-# List all environments
-environments = client.beta.environments.list()
-print(f"\nTotal environments: {len(environments.data)}")
-for env in environments.data[:5]:
-    print(f"  {env.id} | {env.name} | {getattr(env, 'status', 'active')}")
+    # List all environments
+    environments = client.beta.environments.list()
+    print(f"\nTotal environments: {len(environments.data)}")
+    for env in environments.data[:5]:
+        print(f"  {env.id} | {env.name} | {getattr(env, 'status', 'active')}")
 
-# Retrieve a specific environment
-env = client.beta.environments.retrieve(env_id)
-print(f"\nRetrieved: {env.id} | {env.name}")
+    # Retrieve a specific environment
+    env = client.beta.environments.retrieve(env_id)
+    print(f"\nRetrieved: {env.id} | {env.name}")
 
-# Archive (read-only, existing sessions continue)
-archived = client.beta.environments.archive(env_id)
-print(f"Archived: {archived.id} | status: {getattr(archived, 'status', 'archived')}")
+    # Archive (read-only, existing sessions continue)
+    archived = client.beta.environments.archive(env_id)
+    print(f"Archived: {archived.id} | status: {getattr(archived, 'status', 'archived')}")
 
-# Delete (only if no sessions reference it — may fail if sessions exist)
-try:
-    client.beta.environments.delete(env_id)
-    print(f"Deleted: {env_id}")
-except Exception as e:
-    print(f"Delete skipped (expected if sessions exist): {e}")
+    # Delete (only if no sessions reference it — may fail if sessions exist)
+    try:
+        client.beta.environments.delete(env_id)
+        print(f"Deleted: {env_id}")
+    except Exception as e:
+        print(f"Delete skipped (expected if sessions exist): {e}")
+else:
+    print("Environment management demo skipped: backend does not expose _get_client().")
 
 print("\nEnvironment management complete.")

examples/python/mcp/mcp-resumability.py

@@ -15,13 +15,6 @@ Protocol: MCP 2025-11-25
 
 from praisonaiagents import Agent, MCP
 
-# Agent with resumability support (automatic)
-agent = Agent(
-    name="Resumable Assistant",
-    instructions="You are a helpful assistant with resumable connections.",
-    tools=MCP("https://api.example.com/mcp")
-)
-
 # Resumability is automatic - the MCP client:
 # 1. Tracks event IDs from SSE streams (id: field)
 # 2. Stores last event ID per stream
@@ -29,6 +22,12 @@ agent = Agent(
 # 4. Respects retry delay from server (retry: field)
 
 if __name__ == "__main__":
+    agent = Agent(
+        name="Resumable Assistant",
+        instructions="You are a helpful assistant with resumable connections.",
+        tools=MCP("https://api.example.com/mcp"),
+    )
+
     print("MCP Resumability Example")
     print("=" * 40)
     print()

examples/python/mcp/mcp-session-management.py

@@ -15,13 +15,6 @@ Protocol: MCP 2025-11-25
 
 from praisonaiagents import Agent, MCP
 
-# Basic agent with automatic session management
-agent = Agent(
-    name="Session Assistant",
-    instructions="You are a helpful assistant with session support.",
-    tools=MCP("https://api.example.com/mcp")
-)
-
 # Session management is automatic - the MCP client:
 # 1. Receives Mcp-Session-Id from server during initialization
 # 2. Includes session ID in all subsequent requests
@@ -29,6 +22,12 @@ agent = Agent(
 # 4. Can terminate session explicitly when done
 
 if __name__ == "__main__":
+    agent = Agent(
+        name="Session Assistant",
+        instructions="You are a helpful assistant with session support.",
+        tools=MCP("https://api.example.com/mcp"),
+    )
+
     print("MCP Session Management Example")
     print("=" * 40)
     print()

examples/python/mcp/streamable-http-mcp.py

@@ -16,34 +16,31 @@ Protocol: MCP 2025-11-25
 
 from praisonaiagents import Agent, MCP
 
-# Basic Streamable HTTP connection
-agent = Agent(
-    name="HTTP Stream Assistant",
-    instructions="You are a helpful assistant connected via Streamable HTTP.",
-    tools=MCP("https://api.example.com/mcp")
-)
-
-# With authentication headers
-agent_auth = Agent(
-    name="Authenticated Assistant",
-    instructions="You are a helpful assistant with authenticated connection.",
-    tools=MCP(
-        "https://api.example.com/mcp",
-        headers={"Authorization": "Bearer your-token"}
-    )
-)
-
-# With timeout and debug
-agent_debug = Agent(
-    name="Debug Assistant",
-    tools=MCP(
-        "https://api.example.com/mcp",
-        timeout=120,
-        debug=True
-    )
-)
-
 if __name__ == "__main__":
+    agent = Agent(
+        name="HTTP Stream Assistant",
+        instructions="You are a helpful assistant connected via Streamable HTTP.",
+        tools=MCP("https://api.example.com/mcp"),
+    )
+
+    agent_auth = Agent(
+        name="Authenticated Assistant",
+        instructions="You are a helpful assistant with authenticated connection.",
+        tools=MCP(
+            "https://api.example.com/mcp",
+            headers={"Authorization": "Bearer your-token"},
+        ),
+    )
+
+    agent_debug = Agent(
+        name="Debug Assistant",
+        tools=MCP(
+            "https://api.example.com/mcp",
+            timeout=120,
+            debug=True,
+        ),
+    )
+
     print("Streamable HTTP MCP Transport Example")
     print("=" * 40)
     print("This example requires a Streamable HTTP MCP server running.")

examples/python/mcp/websocket-mcp.py

@@ -16,36 +16,33 @@ Protocol: SEP-1288 (WebSocket Transport)
 
 from praisonaiagents import Agent, MCP
 
-# Basic WebSocket connection
-agent = Agent(
-    name="WebSocket Assistant",
-    instructions="You are a helpful assistant connected via WebSocket.",
-    tools=MCP("ws://localhost:8080/mcp")
-)
-
-# Secure WebSocket with authentication
-agent_secure = Agent(
-    name="Secure WebSocket Assistant",
-    instructions="You are a helpful assistant with secure WebSocket connection.",
-    tools=MCP(
-        "wss://api.example.com/mcp",
-        auth_token="Bearer your-secret-token",
-        timeout=60
-    )
-)
-
-# WebSocket with custom options
-agent_custom = Agent(
-    name="Custom WebSocket Assistant",
-    tools=MCP(
-        "wss://api.example.com/mcp",
-        auth_token="your-token",
-        timeout=120,
-        debug=True
-    )
-)
-
 if __name__ == "__main__":
+    agent = Agent(
+        name="WebSocket Assistant",
+        instructions="You are a helpful assistant connected via WebSocket.",
+        tools=MCP("ws://localhost:8080/mcp"),
+    )
+
+    agent_secure = Agent(
+        name="Secure WebSocket Assistant",
+        instructions="You are a helpful assistant with secure WebSocket connection.",
+        tools=MCP(
+            "wss://api.example.com/mcp",
+            auth_token="Bearer your-secret-token",
+            timeout=60,
+        ),
+    )
+
+    agent_custom = Agent(
+        name="Custom WebSocket Assistant",
+        tools=MCP(
+            "wss://api.example.com/mcp",
+            auth_token="your-token",
+            timeout=120,
+            debug=True,
+        ),
+    )
+
     # Note: Requires a running WebSocket MCP server
     # Example server: https://github.com/modelcontextprotocol/servers
     

examples/python/memory/advanced-graph-memory-integration.py

@@ -12,8 +12,8 @@ print("=== Advanced Graph Memory Integration Example ===\n")
 
 # Configure simple graph memory
 memory_config = {
-    "provider": "mem0",
     "config": {
+        "provider": "mem0",
         "vector_store": {
             "provider": "chroma",
             "config": {
@@ -60,8 +60,8 @@ query_task = Task(
 agents_system = AgentTeam(
     agents=[knowledge_agent],
     tasks=[build_task, query_task],
-    memory=True,
-    memory=memory_config, output="verbose"
+    memory=memory_config,
+    output="verbose",
 )
 
 print("Starting graph memory demonstration...")

examples/python/memory/advanced-memory-search-optimization.py

@@ -12,8 +12,8 @@ print("=== Advanced Memory Search and Optimization Example ===\n")
 
 # Configure optimized memory settings
 memory_config = {
-    "provider": "mem0",
     "config": {
+        "provider": "mem0",
         "vector_store": {
             "provider": "chroma",
             "config": {
@@ -61,8 +61,8 @@ search_task = Task(
 agents_system = AgentTeam(
     agents=[research_agent],
     tasks=[build_memory_task, search_task],
-    memory=True,
-    memory=memory_config, output="verbose"
+    memory=memory_config,
+    output="verbose",
 )
 
 print("Starting memory search optimization demonstration...")

examples/python/memory/gemini-embedding-example.py

@@ -86,13 +86,13 @@ def main():
         agents=[researcher, retriever],
         tasks=[store_task, retrieve_task],
         memory={
-            "provider": "rag",
             "embedder": {
                 "provider": "gemini",
                 "config": {
                     "model": "text-embedding-004",
                 }
-            }
+            },
+            "config": {"provider": "sqlite"},
         }
     )
     

examples/python/memory/graph-memory-agent.py

@@ -152,8 +152,7 @@ def main():
     agents_system = AgentTeam(
         agents=[researcher],
         tasks=[build_knowledge_task, query_knowledge_task, expand_knowledge_task],
-        memory=True,
-        memory=memory_config
+        memory=memory_config,
     )
     
     print("\n🚀 Starting graph memory demonstration...")

examples/python/memory_with_tracing_example.py

@@ -30,7 +30,7 @@ def main():
     try:
         # Create memory instance
         memory = Memory(config={
-            "provider": "rag",
+            "backend": "sqlite",
             "use_embedding": False,
             "agent_name": "demo_agent",  # Used in trace events
         })

examples/python/models/deepseek/deepseek-rag-agents-streamlit.py

@@ -32,9 +32,8 @@ def init_agent():
     return Agent(
         name="Knowledge Agent",
         instructions="You answer questions based on the provided knowledge.",
-        knowledge=["kag-research-paper.pdf"],
-        knowledge=config,
-        user_id="user1",
+        knowledge={**config, "sources": ["kag-research-paper.pdf"]},
+        memory={"user_id": "user1"},
         llm="deepseek-r1"
     )
 

examples/python/models/deepseek/deepseek-rag-agents.py

@@ -30,9 +30,12 @@ config = {
 agent = Agent(
     name="Knowledge Agent",
     instructions="You answer questions based on the provided knowledge.",
-    knowledge=["kag-research-paper.pdf"], # Indexing
-    knowledge=config,
-    user_id="user1",
+    knowledge={
+        "sources": ["kag-research-paper.pdf"],
+        "vector_store": config["vector_store"],
+        "embedder": config["embedder"],
+    },
+    memory={"user_id": "user1"},
     llm="deepseek-r1"
 )
 

examples/python/models/googlegemini/any-llm-agents-advanced.py

@@ -31,10 +31,9 @@ llm_config = {
 agent = Agent(
     instructions="You are a helpful Assistant specialized in scientific explanations. "
                 "Provide clear, accurate, and engaging responses.",
-    llm=llm_config,                  # Pass the detailed configuration
-    # Enable detailed output
-    markdown=True,                   # Format responses in markdown
-    reflection=True               # Enable self-reflection
+    llm=llm_config,
+    output={"markdown": True},
+    reflection=True,
 )
 
 # Test the agent

examples/python/mongodb/mongodb_comprehensive_example.py

@@ -189,8 +189,8 @@ def main():
     business_system = AgentTeam(
         agents=[data_manager, knowledge_curator, business_analyst, customer_service],
         tasks=business_tasks,
-        memory=True,
-        memory=mongodb_memory_config, output="verbose"
+        memory=mongodb_memory_config,
+        output="verbose",
     )
     
     # Execute the comprehensive business pipeline

examples/python/mongodb/mongodb_knowledge_example.py

@@ -55,8 +55,10 @@ def main():
         retrieve information from a comprehensive MongoDB knowledge base. You excel 
         at finding relevant information, synthesizing knowledge from multiple sources, 
         and providing accurate, context-aware responses.""",
-        knowledge=mongodb_knowledge_config,
-        knowledge=[os.path.join(os.path.dirname(__file__), "llms.md")],
+        knowledge={
+            **mongodb_knowledge_config,
+            "sources": [os.path.join(os.path.dirname(__file__), "llms.md")],
+        },
         memory=True,
         llm="gpt-4o-mini"
     )

examples/python/mongodb/mongodb_memory_example.py

@@ -28,8 +28,8 @@ if not os.environ.get("OPENAI_API_KEY"):
 def main():
     # MongoDB memory configuration
     mongodb_memory_config = {
-        "provider": "mongodb",
         "config": {
+            "provider": "mongodb",
             "connection_string": "mongodb://localhost:27017/",  # Replace with your MongoDB connection string
             "database": "praisonai_memory",
             "use_vector_search": True,  # Enable Atlas Vector Search (requires MongoDB Atlas)
@@ -93,8 +93,8 @@ def main():
     research_system = AgentTeam(
         agents=[research_agent],
         tasks=research_tasks,
-        memory=True,
-        memory=mongodb_memory_config, output="verbose"
+        memory=mongodb_memory_config,
+        output="verbose",
     )
     
     # Execute the research pipeline

examples/python/rag/agent_vs_auto_rag.py

@@ -50,7 +50,7 @@ agent = Agent(
     name="TechSupport",
     instructions="You are a technical support assistant.",
     knowledge=[sample_doc],
-    user_id="comparison_user",
+    memory={"user_id": "comparison_user"},
     llm="openai/gpt-4o-mini",
     output="minimal",
 )

examples/python/rag/auto_rag_agent_basic.py

@@ -20,8 +20,10 @@ if not os.environ.get("OPENAI_API_KEY"):
     exit(1)
 
 # Create a sample document for testing
-sample_doc = "/tmp/sample_doc.txt"
-with open(sample_doc, "w") as f:
+import tempfile
+from pathlib import Path
+sample_doc = str(Path(tempfile.gettempdir()) / "sample_doc.txt")
+with open(sample_doc, "w", encoding="utf-8") as f:
     f.write("""
 PraisonAI Framework Documentation
 
@@ -44,7 +46,7 @@ agent = Agent(
     name="DocBot",
     instructions="You are a helpful documentation assistant. Answer questions based on the provided context.",
     knowledge=[sample_doc],
-    user_id="example_user",  # Required for RAG retrieval
+    memory={"user_id": "example_user"},
     llm="openai/gpt-4o-mini",
     output="minimal",
 )

examples/python/rag/auto_rag_agent_policy.py

@@ -38,7 +38,7 @@ agent = Agent(
     name="PolicyBot",
     instructions="You are a customer service assistant.",
     knowledge=[sample_doc],
-    user_id="policy_user",
+    memory={"user_id": "policy_user"},
     llm="openai/gpt-4o-mini",
     output="minimal",
 )

examples/python/rag/rag_basic.py

@@ -44,7 +44,7 @@ agent = Agent(
     name="MLExpert",
     instructions="You are a machine learning expert. Answer questions based on the provided context.",
     knowledge=[sample_doc],
-    user_id="rag_user",
+    memory={"user_id": "rag_user"},
     llm="openai/gpt-4o-mini",
     output="minimal",
 )

examples/python/rag/rag_hybrid.py

@@ -59,7 +59,7 @@ agent = Agent(
     name="APIDocBot",
     instructions="You are an API documentation assistant.",
     knowledge=[sample_doc],
-    user_id="hybrid_user",
+    memory={"user_id": "hybrid_user"},
     llm="openai/gpt-4o-mini",
     output="minimal",
 )

examples/python/rag/rag_with_citations.py

@@ -44,7 +44,7 @@ agent = Agent(
     name="ResearchBot",
     instructions="You are a research assistant. Always cite your sources.",
     knowledge=[doc1, doc2],
-    user_id="citation_user",
+    memory={"user_id": "citation_user"},
     llm="openai/gpt-4o-mini",
     output="minimal",
 )

examples/python/save_output/03_workflow_output_file.py

@@ -4,7 +4,7 @@ Example 3: Save Agent Output Using Workflow output_file
 Workflow step output is automatically saved with variable substitution.
 """
 
-from praisonaiagents import AgentFlow
+from praisonaiagents import Agent, AgentFlow, Task
 
 # Define workflow with output_file
 workflow_config = {
@@ -33,9 +33,30 @@ workflow_config = {
     ]
 }
 
-# Run workflow
-workflow = AgentFlow(config=workflow_config)
-result = workflow.run()
+# Build agent and workflow from config dict
+writer_cfg = workflow_config["agents"]["writer"]
+writer = Agent(
+    name="writer",
+    role=writer_cfg["role"],
+    goal=writer_cfg["goal"],
+    llm=writer_cfg["llm"],
+)
+
+step_cfg = workflow_config["steps"][0]
+workflow = AgentFlow(
+    name=workflow_config["metadata"]["name"],
+    variables=workflow_config["variables"],
+    steps=[
+        Task(
+            name="write_tutorial",
+            description=step_cfg["action"],
+            expected_output=step_cfg["expected_output"],
+            output_file=step_cfg["output_file"],
+            agent=writer,
+        )
+    ],
+)
+result = workflow.start()
 
 print("✅ Workflow completed!")
 print("Output saved to: generated/tutorial.md")

examples/python/session/session_persistence_example.py

@@ -28,7 +28,7 @@ def example_basic_persistence():
     agent = Agent(
         name="Assistant",
         instructions="You are a helpful assistant. Be very brief.",
-        session_id=session_id,
+        memory={"session_id": session_id},
         output="minimal",
     )
     
@@ -59,7 +59,7 @@ def example_session_restoration():
     agent1 = Agent(
         name="MemoryBot",
         instructions="You are a helpful assistant. Be very brief.",
-        session_id=session_id,
+        memory={"session_id": session_id},
         output="minimal",
     )
     
@@ -72,7 +72,7 @@ def example_session_restoration():
     agent2 = Agent(
         name="MemoryBot",
         instructions="You are a helpful assistant. Be very brief.",
-        session_id=session_id,
+        memory={"session_id": session_id},
         output="minimal",
     )
     

examples/python/sessions/comprehensive-session-management.py

@@ -172,7 +172,7 @@ print("="*70)
 # Create sessions for different users working on the same project
 reviewer_session = Session(
     session_id="peer_review_001",
-    user_id="user_reviewer_01",  # Different user
+    user_id="user_reviewer_01",
     storage_path=session_dir
 )
 

examples/python/stateful/advanced-state-management-patterns.py

@@ -72,6 +72,6 @@ agents_system = AgentTeam(
 print("Starting state management demonstration...")
 result = agents_system.start()
 
-print(f"\nState Management Result: {result[:200]}...")
+print(f"\nState Management Result: {str(result)[:200]}...")
 print("\n✅ State management patterns complete!")
 print("Agent demonstrated persistent state tracking across multiple tasks.")

examples/python/stateful/memory-quality-example.py

@@ -14,13 +14,12 @@ def main():
     
     # Initialize memory with quality-based configuration
     memory_config = {
-        "provider": "rag",
-        "use_embedding": True,
-        "rag_db_path": "quality_memory_db"
+        "backend": "sqlite",
+        "user_id": "quality_demo_user",
     }
     
     memory = Memory(config=memory_config, verbose=5)
-    print(f"📦 Initialized memory system with provider: {memory_config['provider']}")
+    print(f"📦 Initialized memory system with backend: {memory_config['backend']}")
     
     # Create agent with memory
     agent = Agent(
@@ -28,7 +27,6 @@ def main():
         role="Information Quality Specialist",
         instructions="Store and retrieve information with quality assessment",
         memory=memory,
-        user_id="quality_demo_user"
     )
     
     print(f"🤖 Created agent: {agent.name}")

examples/python/stateful/session-example.py

@@ -15,7 +15,7 @@ def main():
     # Create a session with persistent storage
     session = Session(
         session_id="demo_chat_001",
-        user_id="demo_user"
+        user_id="demo_user",
     )
     
     print(f"📝 Created session: {session}")

examples/python/stateful/workflow-state-example.py

@@ -88,9 +88,8 @@ def main():
     workflow = AgentTeam(
         agents=[researcher, analyzer, writer],
         tasks=[research_task, analysis_task, report_task],
-        memory=True,
+        memory={"user_id": "research_project_001"},
         process="workflow",
-        user_id="research_project_001",
     )
     
     print(f"🤖 Created workflow with {len(workflow.agents)} agents and {len(workflow.tasks)} tasks")

examples/python/telemetry/production-telemetry-example.py

@@ -1,284 +1,55 @@
 """
 Production Telemetry Example
 
-This example demonstrates comprehensive telemetry and monitoring setup for
-production AI agent systems, including metrics collection, performance tracking,
-and observability.
-
-Features demonstrated:
-- OpenTelemetry integration for distributed tracing
-- Custom metrics collection and monitoring
-- Performance tracking and analytics
-- Error tracking and alerting
-- Usage analytics and reporting
+Demonstrates compatible telemetry setup with `enable_telemetry()` and
+`TelemetryCollector` patterns.
 """
 
+from contextlib import nullcontext
 from praisonaiagents import Agent, Task, AgentTeam
 from praisonaiagents.tools import duckduckgo
-from praisonaiagents.telemetry import enable_telemetry
-import time
-import random
-from datetime import datetime
+from praisonaiagents.telemetry import enable_telemetry, TelemetryCollector
 
-# Initialize telemetry for production monitoring
-print("="*80)
-print("PRODUCTION TELEMETRY SETUP")
-print("="*80)
 
-# Configure telemetry (in production, you'd use actual telemetry backends)
-telemetry = enable_telemetry(
-    backend="opentelemetry",
-    config={
-        "service_name": "praisonai_production_agents",
-        "service_version": "1.0.0",
-        "environment": "production",
-        "export_console": True,  # For demo purposes
-        "export_file": True,     # Export to file for analysis
-        "sample_rate": 1.0,      # 100% sampling for demo
-        "attributes": {
-            "deployment": "cloud",
-            "region": "us-east-1",
-            "cluster": "main"
-        }
-    }
-)
+def main() -> None:
+    print("=" * 80)
+    print("PRODUCTION TELEMETRY SETUP")
+    print("=" * 80)
 
-# Create agents for production workflow with telemetry
-customer_service_agent = Agent(
-    name="CustomerServiceAgent",
-    role="Customer Service Representative", 
-    goal="Provide excellent customer service with fast response times",
-    backstory="You are a customer service representative focused on resolving customer issues quickly and effectively.",
-    tools=[duckduckgo],
-    instructions="Provide helpful, accurate customer service responses. Research solutions when needed."
-)
+    # New API: no args
+    enable_telemetry()
+    collector = TelemetryCollector()
 
-technical_support_agent = Agent(
-    name="TechnicalSupportAgent",
-    role="Technical Support Specialist",
-    goal="Resolve technical issues with detailed solutions",
-    backstory="You are a technical support specialist who provides detailed technical solutions and troubleshooting.",
-    instructions="Provide detailed technical solutions with step-by-step instructions."
-)
+    customer_service_agent = Agent(
+        name="CustomerServiceAgent",
+        role="Customer Service Representative",
+        goal="Provide excellent customer service with fast response times",
+        backstory="Customer service expert focused on quick issue resolution.",
+        tools=[duckduckgo],
+        instructions="Provide accurate customer-service responses.",
+    )
 
-quality_assurance_agent = Agent(
-    name="QualityAssuranceAgent", 
-    role="Quality Assurance Specialist",
-    goal="Ensure all customer interactions meet quality standards",
-    backstory="You review and assess the quality of customer service interactions to ensure high standards.",
-    instructions="Review customer service interactions and provide quality scores with detailed feedback."
-)
-
-# Production workflow simulation with telemetry tracking
-def simulate_customer_requests():
-    """Simulate various customer requests for telemetry demonstration"""
-    
-    customer_requests = [
-        {
-            "type": "billing_inquiry",
-            "complexity": "low",
-            "description": "Customer asking about their monthly bill charges",
-            "expected_duration": 30
-        },
-        {
-            "type": "technical_issue", 
-            "complexity": "high",
-            "description": "Customer experiencing connectivity issues with the service",
-            "expected_duration": 120
-        },
-        {
-            "type": "account_setup",
-            "complexity": "medium", 
-            "description": "New customer needs help setting up their account",
-            "expected_duration": 60
-        },
-        {
-            "type": "feature_question",
-            "complexity": "low",
-            "description": "Customer asking about product features and capabilities",
-            "expected_duration": 45
-        }
+    requests = [
+        "Customer asking about monthly bill charges",
+        "Customer experiencing connectivity issues",
     ]
-    
-    return customer_requests
 
-# Execute production workflow with comprehensive telemetry
-print("Starting production workflow with telemetry tracking...")
+    for idx, description in enumerate(requests, start=1):
+        trace_ctx = getattr(collector, "trace", None)
+        trace_cm = trace_ctx(f"customer_request_{idx}") if callable(trace_ctx) else nullcontext()
+        with trace_cm:
+            task = Task(
+                name=f"customer_request_{idx}",
+                description=description,
+                expected_output="Professional customer service response with solution",
+                agent=customer_service_agent,
+            )
+            agents = AgentTeam(agents=[customer_service_agent], tasks=[task], output="minimal")
+            result = agents.start()
+            print(f"✅ Request {idx} completed, response length={len(str(result))}")
 
-customer_requests = simulate_customer_requests()
+    print("\nTelemetry demonstration completed.")
 
-for i, request in enumerate(customer_requests):
-    print(f"\n{'='*60}")
-    print(f"PROCESSING CUSTOMER REQUEST {i+1}: {request['type'].upper()}")
-    print(f"Complexity: {request['complexity']} | Expected Duration: {request['expected_duration']}s")
-    print(f"{'='*60}")
-    
-    # Start telemetry trace for this customer interaction
-    with telemetry.trace_operation(f"customer_request_{request['type']}") as trace:
-        
-        # Add custom attributes to the trace
-        trace.set_attributes({
-            "request.type": request['type'],
-            "request.complexity": request['complexity'],
-            "request.expected_duration": request['expected_duration'],
-            "customer.id": f"customer_{random.randint(1000, 9999)}",
-            "agent.assigned": "CustomerServiceAgent"
-        })
-        
-        start_time = time.time()
-        
-        # Create customer service task with telemetry
-        customer_task = Task(
-            name=f"customer_request_{i+1}",
-            description=request['description'],
-            expected_output="Professional customer service response with solution",
-            agent=customer_service_agent
-        )
-        
-        # Execute with telemetry tracking
-        try:
-            # Customer service response
-            with telemetry.trace_agent_execution("CustomerServiceAgent") as agent_trace:
-                agents = AgentTeam(
-                    agents=[customer_service_agent],
-                    tasks=[customer_task],
-                    output="minimal"  # Reduce verbosity for telemetry demo
-                )
-                
-                cs_result = agents.start()
-                agent_trace.set_attributes({
-                    "agent.response_length": len(str(cs_result)),
-                    "agent.tools_used": len(customer_service_agent.tools) if customer_service_agent.tools else 0
-                })
-            
-            # Technical support (if needed for high complexity)
-            if request['complexity'] == 'high':
-                with telemetry.trace_agent_execution("TechnicalSupportAgent") as tech_trace:
-                    tech_task = Task(
-                        name=f"technical_support_{i+1}",
-                        description=f"Provide detailed technical support for: {request['description']}",
-                        expected_output="Detailed technical solution with troubleshooting steps",
-                        agent=technical_support_agent,
-                        context=[customer_task]
-                    )
-                    
-                    tech_agents = AgentTeam(
-                        agents=[technical_support_agent],
-                        tasks=[tech_task], output="minimal"
-                    )
-                    
-                    tech_result = tech_agents.start()
-                    tech_trace.set_attributes({
-                        "agent.response_length": len(str(tech_result)),
-                        "agent.escalation": True
-                    })
-            
-            # Quality assurance check
-            with telemetry.trace_agent_execution("QualityAssuranceAgent") as qa_trace:
-                qa_task = Task(
-                    name=f"quality_check_{i+1}",
-                    description=f"Review the quality of customer service provided for: {request['description']}",
-                    expected_output="Quality assessment score and feedback",
-                    agent=quality_assurance_agent
-                )
-                
-                qa_agents = AgentTeam(
-                    agents=[quality_assurance_agent],
-                    tasks=[qa_task], output="minimal"
-                )
-                
-                qa_result = qa_agents.start()
-                
-                # Extract quality score (simulated)
-                quality_score = random.uniform(0.8, 1.0)  # Simulated score
-                qa_trace.set_attributes({
-                    "qa.score": quality_score,
-                    "qa.passed": quality_score >= 0.85
-                })
-            
-            # Calculate performance metrics
-            end_time = time.time()
-            duration = end_time - start_time
-            
-            # Record custom metrics
-            telemetry.record_metric("request_duration", duration, {
-                "request_type": request['type'],
-                "complexity": request['complexity']
-            })
-            
-            telemetry.record_metric("request_success", 1, {
-                "request_type": request['type']
-            })
-            
-            # Set final trace attributes
-            trace.set_attributes({
-                "request.duration_seconds": duration,
-                "request.status": "completed",
-                "request.quality_score": quality_score,
-                "request.escalated": request['complexity'] == 'high'
-            })
-            
-            print(f"✅ Request completed successfully in {duration:.2f}s (Quality: {quality_score:.2f})")
-            
-        except Exception as e:
-            # Record error metrics
-            telemetry.record_metric("request_error", 1, {
-                "request_type": request['type'],
-                "error_type": type(e).__name__
-            })
-            
-            trace.set_attributes({
-                "request.status": "error",
-                "request.error": str(e)
-            })
-            
-            print(f"❌ Request failed: {str(e)}")
-    
-    # Add some delay between requests
-    time.sleep(2)
 
-# Generate telemetry summary
-print(f"\n{'='*80}")
-print("TELEMETRY SUMMARY AND ANALYTICS")
-print(f"{'='*80}")
-
-# Simulated telemetry analytics (in production, this would come from your telemetry backend)
-print("📊 Performance Metrics:")
-print("- Total Requests Processed: 4")
-print("- Average Response Time: 3.2s")
-print("- Success Rate: 100%")
-print("- Quality Score Average: 0.91")
-print("- High Complexity Requests: 25%")
-
-print("\n📈 Usage Analytics:")
-print("- Most Common Request Type: technical_issue")
-print("- Peak Performance Window: All requests within SLA")
-print("- Agent Utilization: CustomerService (100%), TechnicalSupport (25%), QA (100%)")
-
-print("\n🔍 Observability Features Demonstrated:")
-print("- Distributed tracing across agent interactions")
-print("- Custom metrics for business KPIs")
-print("- Performance monitoring and SLA tracking")
-print("- Error tracking and alerting")
-print("- Quality assurance metrics")
-print("- User journey tracking")
-print("- Resource utilization monitoring")
-
-print("\n⚙️ Production Monitoring Setup:")
-print("- OpenTelemetry integration for standardized observability")
-print("- Custom metrics for business-specific KPIs") 
-print("- Trace correlation across multi-agent workflows")
-print("- Performance benchmarking against expected durations")
-print("- Quality scoring and automated validation")
-print("- Error categorization and alerting")
-
-print(f"\n{'='*80}")
-print("TELEMETRY DEMONSTRATION COMPLETED")
-print(f"{'='*80}")
-print("This example demonstrated comprehensive production telemetry including:")
-print("- Request tracing and performance monitoring")
-print("- Custom business metrics collection")
-print("- Quality assurance tracking")
-print("- Error handling and alerting")
-print("- Multi-agent workflow observability")
-print("- Production-ready monitoring patterns")
+if __name__ == "__main__":
+    main()

examples/python/token-metrics/01_basic_token_tracking.py

@@ -14,7 +14,7 @@ def main():
         goal="Find information about a topic",
         backstory="You are an expert researcher who finds comprehensive information.",
         llm="gpt-4o-mini",  # Use a cost-effective model for examples
-        metrics=True  # 🎯 SIMPLIFIED: Just add this parameter!
+        output={"metrics": True}  # Token metrics via consolidated output config
     )
     
     # Create a simple task

examples/python/token-metrics/02_session_metrics.py

@@ -14,7 +14,7 @@ def main():
         goal="Analyze data and provide insights",
         backstory="You are an experienced data analyst with expertise in market research.",
         llm="gpt-4o-mini",
-        metrics=True  # 🎯 Enable metrics tracking
+        output={"metrics": True}
     )
     
     writer_agent = Agent(
@@ -23,7 +23,7 @@ def main():
         goal="Create well-structured content",
         backstory="You are a skilled technical writer who creates clear, engaging content.",
         llm="gpt-4o-mini",
-        metrics=True  # 🎯 Enable metrics tracking
+        output={"metrics": True}
     )
     
     # Create multiple tasks

examples/python/token-metrics/03_cost_estimation.py

@@ -14,7 +14,7 @@ def main():
         goal="Conduct comprehensive market research",
         backstory="You are a seasoned market researcher with 10+ years of experience.",
         llm="gpt-4o-mini",
-        metrics=True  # 🎯 Enable automatic metrics tracking
+        output={"metrics": True}
     )
     
     strategy_agent = Agent(
@@ -23,7 +23,7 @@ def main():
         goal="Develop actionable business strategies",
         backstory="You are a strategic consultant who translates research into business plans.",
         llm="gpt-4o-mini",
-        metrics=True  # 🎯 Enable automatic metrics tracking
+        output={"metrics": True}
     )
     
     # Create tasks that will generate substantial token usage

examples/python/tools/exa-tool/rag_examples/agentic_rag/rag_agent.py

@@ -22,7 +22,8 @@ rag_agent = Agent(
     
     You can use the internet_search function to search the web when needed.""",
     llm="gpt-4o",
-    markdown=True)
+    output={"markdown": True},
+)
 
 if __name__ == "__main__":
     print("🤖 Thai Recipe RAG Agent is ready!")

examples/python/tools/langchain/google-serper-search.py

@@ -5,11 +5,17 @@ from dotenv import load_dotenv
 
 load_dotenv()
 
-os.environ['SERPER_API_KEY'] = os.getenv('SERPER_API_KEY')
+serper_api_key = os.getenv("SERPER_API_KEY")
+if serper_api_key is not None:
+    os.environ["SERPER_API_KEY"] = serper_api_key
 
-search = GoogleSerperAPIWrapper()
 
-data_agent = Agent(instructions="Suggest me top 5 most visited websites for Dosa Recipe", tools=[search])
-editor_agent = Agent(instructions="List out the websites with their url and a short description")
-agents = AgentTeam(agents=[data_agent, editor_agent])
-agents.start()
+if __name__ == "__main__":
+    if not serper_api_key:
+        print("SERPER_API_KEY is not set. Skipping Google Serper example.")
+    else:
+        search = GoogleSerperAPIWrapper()
+        data_agent = Agent(instructions="Suggest me top 5 most visited websites for Dosa Recipe", tools=[search])
+        editor_agent = Agent(instructions="List out the websites with their url and a short description")
+        agents = AgentTeam(agents=[data_agent, editor_agent])
+        agents.start()

examples/python/ui/ollama-rag-agents-streamlit.py

@@ -32,9 +32,8 @@ def init_agent():
     return Agent(
         name="Knowledge Agent",
         instructions="You answer questions based on the provided knowledge.",
-        knowledge=["kag-research-paper.pdf"],
-        knowledge=config,
-        user_id="user1",
+        knowledge={**config, "sources": ["kag-research-paper.pdf"]},
+        memory={"user_id": "user1"},
         llm="deepseek-r1"
     )
 

examples/python/usecases/analysis/code-analysis-agents.py

@@ -2,6 +2,7 @@ from praisonaiagents import Agent, Task, AgentTeam
 from pydantic import BaseModel
 from typing import List, Dict
 from gitingest import ingest
+import sys
 
 class CodeMetrics(BaseModel):
     category: str
@@ -60,7 +61,10 @@ def analyze_code(code_source: str) -> CodeAnalysisReport:
     Analyze code from directory path or GitHub URL
     """
     # Ingest code content
-    summary, tree, content = ingest(code_source)
+    try:
+        summary, tree, content = ingest(code_source)
+    except Exception as exc:
+        raise RuntimeError(f"Failed to ingest code source: {exc}") from exc
     
     # Concatenate context into structured format
     context_text = f"""
@@ -86,10 +90,22 @@ def analyze_code(code_source: str) -> CodeAnalysisReport:
         tasks=[code_analysis_task]
     )
     
-    return agents.start(context_text)
+    result = agents.start(context_text)
+    if result is None:
+        raise RuntimeError("No analysis result returned by AgentTeam.start()")
+    return result
 
-if __name__ == "__main__":
+
+def main() -> None:
     # Example usage
     code_source = "https://github.com/openai/openai-python/tree/main/src/openai/cli/_api/chat"  # GitHub URL or local directory
-    result = analyze_code(code_source)
-    print(result) 
+    try:
+        result = analyze_code(code_source)
+    except RuntimeError as exc:
+        print(f"Code analysis failed: {exc}")
+        sys.exit(1)
+    print(result) 
+
+
+if __name__ == "__main__":
+    main()

examples/python/usecases/analysis/cv-analysis.py

@@ -77,25 +77,44 @@ agents = AgentTeam(
     process="sequential", output="verbose"
 )
 
+
+def _extract_pydantic_result(result_obj):
+    """Extract pydantic payload from AgentTeam.start() output shapes."""
+    if hasattr(result_obj, "pydantic"):
+        return result_obj.pydantic
+    if isinstance(result_obj, dict):
+        task_results = result_obj.get("task_results")
+        if isinstance(task_results, dict):
+            values = list(task_results.values())
+            if values and hasattr(values[-1], "pydantic"):
+                return values[-1].pydantic
+        if isinstance(task_results, list) and task_results and hasattr(task_results[-1], "pydantic"):
+            return task_results[-1].pydantic
+    return None
+
+
 # Start the analysis
 result = agents.start()
+pydantic_result = _extract_pydantic_result(result)
+if pydantic_result is None:
+    raise ValueError("Could not extract structured CVAnalysisReport from workflow result")
 
 # Access the structured results
 print("\nCV Analysis Results:")
-print(f"\nOverall Score: {result.pydantic.overall_score}/100")
+print(f"\nOverall Score: {pydantic_result.overall_score}/100")
 print("\nKey Strengths:")
-for strength in result.pydantic.key_strengths:
+for strength in pydantic_result.key_strengths:
     print(f"- {strength}")
 
 print("\nSkill Analysis:")
 print("\nTechnical Skills:")
-for skill in result.pydantic.skill_analysis.technical_skills:
+for skill in pydantic_result.skill_analysis.technical_skills:
     print(f"- {skill}")
 
 print("\nExperience Highlights:")
-for achievement in result.pydantic.experience_analysis.key_achievements:
+for achievement in pydantic_result.experience_analysis.key_achievements:
     print(f"- {achievement}")
 
 print("\nRecommendations:")
-for recommendation in result.pydantic.recommendations:
+for recommendation in pydantic_result.recommendations:
     print(f"- {recommendation}")

examples/python/usecases/analysis/hackathon-judge-agent.py

@@ -100,6 +100,8 @@ def evaluate_project(video_path: str) -> ProjectEvaluation:
             evaluation_data = response
             
         print(f"Debug - Parsed evaluation_data: {evaluation_data}")
+        if not evaluation_data or not isinstance(evaluation_data, dict):
+            raise ValueError("No structured evaluation data returned by agent")
         
         # Create and return ProjectEvaluation instance
         return ProjectEvaluation(

examples/python/usecases/domain-context-solution.py

@@ -264,13 +264,12 @@ agents = AgentTeam(
     tasks=[tool_query_task, pentester_analysis_task, ciso_review_task],
     process="hierarchical",
     manager_llm="gpt-4o-mini",
-    memory=True,  # Enable shared memory for domain context
     memory={
-        "provider": "rag",
+        "backend": "sqlite",
         "config": {
             "collection_name": f"{domain.replace('.', '_')}_security_analysis"
-        }
-    }
+        },
+    },
 )
 
 # Main Execution Workflow

examples/python/video/video_azure.py

@@ -1,5 +1,11 @@
 from praisonaiagents import VideoAgent
+import os
 
-agent = VideoAgent(llm="azure/sora-2")
-video = agent.generate("Mountain landscape")
-print(video.id)
+
+if __name__ == "__main__":
+    if not os.getenv("AZURE_API_BASE"):
+        print("AZURE_API_BASE is not configured. Skipping Azure video example.")
+    else:
+        agent = VideoAgent(llm="azure/sora-2")
+        video = agent.generate("Mountain landscape")
+        print(video.id)

examples/python/workflows/task_callbacks.py

@@ -6,6 +6,7 @@ with Agents for workflow monitoring and logging.
 """
 
 from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents.config.feature_configs import MultiAgentHooksConfig
 
 # Create an agent
 researcher = Agent(
@@ -47,8 +48,10 @@ if __name__ == "__main__":
         agents=[researcher],
         tasks=[task1, task2],
         process="workflow",
-        on_task_start=on_start,
-        on_task_complete=on_complete,
+        hooks=MultiAgentHooksConfig(
+            on_task_start=on_start,
+            on_task_complete=on_complete,
+        ),
         variables={"global_var": "shared_value"}  # Global variables
     )