[feat][grep-tool][add grep search tool to autonomous

  loop][improvement][autonomous-loop][fix execution prompt written once per
  subtask][bugf][streaming-thinking][prevent thinking panel corruption inside live
  context][improvement][arun-stream][use get_running_loop and propagate
  exceptions][bugf][final-summary][thread streaming callback through generate final
  summary][improvement][think-tool][exclude think tool when thinking tokens
  enabled][bugf][license][correct license from MIT to
  Apache-2.0][improvement][sensor-assembly][remove deprecated senator assembly module]

Author: kyegomez

README.md

@@ -366,8 +366,7 @@ The `SwarmRouter` simplifies building complex workflows by providing a single in
 This makes your code cleaner and more flexible, allowing you to switch between different multi-agent strategies with ease. Here's a complete example that shows how to define agents and then use `SwarmRouter` to execute the same task using different collaborative strategies.
 
 ```python
-from swarms import Agent
-from swarms.structs.swarm_router import SwarmRouter, SwarmType
+from swarms import Agent, SwarmRouter, SwarmType
 
 # Define a few generic agents
 writer = Agent(agent_name="Writer", system_prompt="You are a creative writer.", model_name="gpt-5.4")
@@ -421,7 +420,7 @@ The `SwarmRouter` is a powerful tool for simplifying multi-agent orchestration.
 The `AutoSwarmBuilder` automatically generates specialized agents and their workflows based on your task description. Simply describe what you need, and it will create a complete multi-agent system with detailed prompts and optimal agent configurations. [Learn more about AutoSwarmBuilder](https://docs.swarms.world/en/latest/swarms/structs/auto_swarm_builder/)
 
 ```python
-from swarms.structs.auto_swarm_builder import AutoSwarmBuilder
+from swarms import AutoSwarmBuilder
 import json
 
 # Initialize the AutoSwarmBuilder
@@ -692,8 +691,7 @@ Perfect for implementing complex multi-agent workflows, collaborative problem-so
 The **Agent Orchestration Protocol (AOP)** is a powerful framework for deploying and managing agents as distributed services. AOP enables agents to be discovered, managed, and executed through a standardized protocol, making it perfect for building scalable multi-agent systems. [Learn more about AOP](https://docs.swarms.world/en/latest/swarms/structs/aop/)
 
 ```python
-from swarms import Agent
-from swarms.structs.aop import AOP
+from swarms import Agent, AOP
 
 # Create specialized agents
 research_agent = Agent(

docs/mkdocs.yml

@@ -347,162 +347,6 @@ nav:
         - AOP Server Setup: "swarms/examples/aop_server_example.md"
         - AOP Cluster Example: "swarms/examples/aop_cluster_example.md"
 
-    
-  - Examples:
-    - Overview: "examples/index.md"
-    - CookBook Index: "examples/cookbook_index.md"
-    - Paper Implementations: "examples/paper_implementations.md"
-    - Templates & Applications: "examples/templates.md"
-    - Community Resources: "examples/community_resources.md"
-
-    - CLI Guides:
-      - Overview: "examples/cli_guides_overview.md"
-      - CLI Quickstart: "swarms/cli/cli_quickstart.md"
-      - Creating Agents from CLI: "swarms/cli/cli_agent_guide.md"
-      - YAML Configuration: "swarms/cli/cli_yaml_guide.md"
-      - LLM Council CLI: "swarms/cli/cli_llm_council_guide.md"
-      - Heavy Swarm CLI: "swarms/cli/cli_heavy_swarm_guide.md"
-      - CLI Multi-Agent Commands: "examples/cli_multi_agent_quickstart.md"
-      - CLI Examples: "swarms/cli/cli_examples.md"
-      - Chat Command Usage: "examples/chat_command_usage.md"
-
-    - Agent Examples:
-      - Overview: "examples/basic_examples_overview.md"
-      - Basic Agent: "swarms/examples/basic_agent.md"
-      - ReAct Agent Tutorial: "swarms/examples/react_agent_tutorial.md"
-      - Agent Skills: "swarms/examples/agent_skills_overview.md"
-      - Autonomous Agent: "swarms/examples/autonomous_agent_tutorial.md"
-      - Agent Handoff: "swarms/examples/agent_handoff_tutorial.md"
-      - Sub-Agent Delegation: "swarms/examples/sub_agent_tutorial.md"
-      - Autosave: "swarms/examples/autosave_tutorial.md"
-      - Tool Usage:
-        - Agents with Vision and Tool Usage: "swarms/examples/vision_tools.md"
-        - Callable Tools: "swarms/examples/agent_with_tools.md"
-        - Structured Outputs: "swarms/examples/agent_structured_outputs.md"
-        - Pydantic Structured Outputs Tutorial: "swarms/examples/pydantic_structured_outputs_tutorial.md"
-        - Message Transforms for Context Management: "swarms/structs/transforms.md"
-        - Selecting PreConfigured Tools: "examples/autonomous_looper_tools.md"
-      - Vision:
-        - Agents with Vision: "swarms/examples/vision_processing.md"
-        - Base64 Image Handling: "swarms/examples/base64_image.md"
-        - Agent with Multiple Images: "swarms/examples/multiple_images.md"
-      - Utils:
-        - Agent with Streaming: "examples/agent_stream.md"
-        - Agent Output Types: "swarms/examples/agent_output_types.md"
-        - Gradio Chat Interface: "swarms/ui/main.md"
-      - LLM Providers:
-        - Language Models:
-          - Overview: "swarms/examples/model_providers.md"
-          - LiteLLM: "swarms/examples/litellm.md"
-          - OpenAI: "swarms/examples/openai_example.md"
-          - Anthropic: "swarms/examples/claude.md"
-          - Groq: "swarms/examples/groq.md"
-          - Cohere: "swarms/examples/cohere.md"
-          - DeepSeek: "swarms/examples/deepseek.md"
-          - Ollama: "swarms/examples/ollama.md"
-          - OpenRouter: "swarms/examples/openrouter.md"
-          - XAI: "swarms/examples/xai.md"
-          - Azure OpenAI: "swarms/examples/azure.md"
-          - Llama4: "swarms/examples/llama4.md"
-          - Custom Base URL & API Keys: "swarms/examples/custom_base_url_example.md"
-          - vLLM Custom Wrapper: "swarms/examples/vllm_custom_wrapper.md"
-
-    - Multi-Agent Examples:
-      - Overview: "examples/multi_agent_architectures_overview.md"
-      - Guide to Choosing Multi-Agent Architectures: "swarms/concept/how_to_choose_swarms.md"
-
-      - Hierarchical & Orchestration:
-        - HierarchicalSwarm: "swarms/examples/hierarchical_swarm_example.md"
-        - PlannerWorkerSwarm: "swarms/examples/planner_worker_swarm_example.md"
-        - Hybrid Hierarchical-Cluster Swarm: "swarms/examples/hhcs_examples.md"
-        - AutoSwarmBuilder: "swarms/examples/auto_swarm_builder_example.md"
-        - SwarmRouter: "swarms/examples/swarm_router.md"
-        - MultiAgentRouter: "swarms/examples/multi_agent_router_minimal.md"
-        - ModelRouter: "swarms/examples/model_router_example.md"
-        - AgentRearrange: "swarms/examples/agent_rearrange_example.md"
-        - SwarmRearrange: "swarms/examples/swarm_rearrange_example.md"
-        - SkillOrchestra: "swarms/examples/skill_orchestra_example.md"
-
-      - Voting & Consensus:
-        - MajorityVoting: "swarms/examples/majority_voting_example.md"
-        - CouncilAsAJudge: "swarms/examples/council_as_judge_example.md"
-        - LLM Council: "swarms/examples/llm_council_examples.md"
-        - DebateWithJudge Quickstart: "examples/debate_quickstart.md"
-        - Mixture of Agents: "swarms/examples/moa_example.md"
-        - SelfMoASeq: "swarms/examples/self_moa_seq_example.md"
-
-      - Workflow Patterns:
-        - Sequential Workflow: "swarms/examples/sequential_example.md"
-        - Concurrent Workflow: "swarms/examples/concurrent_workflow.md"
-        - GraphWorkflow: "swarms/examples/graphworkflow_example.md"
-        - BatchedGridWorkflow: "swarms/examples/batched_grid_simple_example.md"
-
-      - Group Communication:
-        - GroupChat: "swarms/examples/groupchat_comprehensive_examples.md"
-        - RoundRobinSwarm: "swarms/examples/roundrobin_example.md"
-        - SocialAlgorithms: "swarms/examples/social_algorithms_example.md"
-
-      - Communication Patterns:
-        - Circular Swarm: "swarms/examples/circular_swarm_example.md"
-        - Grid Swarm: "swarms/examples/grid_swarm_example.md"
-        - Star Swarm: "swarms/examples/star_swarm_example.md"
-        - Mesh Swarm: "swarms/examples/mesh_swarm_example.md"
-        - Pyramid Swarm: "swarms/examples/pyramid_swarm_example.md"
-        - One-to-One Communication: "swarms/examples/one_to_one_example.md"
-        - Broadcast Communication: "swarms/examples/broadcast_example.md"
-
-      - Utilities:
-        - Unique Swarms: "swarms/examples/unique_swarms.md"
-        - Agents as Tools: "swarms/examples/agents_as_tools.md"
-        - Aggregate Responses: "swarms/examples/aggregate.md"
-        - SpreadSheetSwarm: "swarms/examples/spreadsheet_swarm_example.md"
-    
-    - Applications:
-      - Overview: "examples/applications_overview.md"
-      - Swarms of Browser Agents: "swarms/examples/swarms_of_browser_agents.md"
-      - Hiearchical Marketing Team: "examples/marketing_team.md"
-      - Gold ETF Research with HeavySwarm: "examples/gold_etf_research.md"
-      - Hiring Swarm: "examples/hiring_swarm.md"
-      - Advanced Research: "examples/av.md"
-      - Real Estate Swarm: "examples/realestate_swarm.md"
-      - Job Finding Swarm: "examples/job_finding.md"
-      - Mergers & Aquisition (M&A) Advisory Swarm: "examples/ma_swarm.md"
-    
-    - Voice Agents:
-      - Overview: "swarms/examples/voice_agents_overview.md"
-      - Single Speech Agent: "swarms/examples/single_agent_speech.md"
-      - Multi-Agent Speech Debate: "swarms/examples/multi_agent_speech_debate.md"
-      - Hierarchical Speech Swarm: "swarms/examples/hierarchical_speech_swarm.md"
-    
-    - Tools & Integrations:
-      - Overview: "examples/tools_integrations_overview.md"
-      - Web Search with Exa: "examples/exa_search.md"
-      - Browser Use: "examples/browser_use.md"
-      - Yahoo Finance: "swarms/examples/yahoo_finance.md"
-      - Firecrawl: "developer_guides/firecrawl.md"
-    
-      - MCP: 
-        - Multi-MCP Agent Integration: "swarms/examples/multi_mcp_agent.md"
-
-    - RAG:
-      - Overview: "examples/rag_examples_overview.md"
-      - RAG with Qdrant: "swarms/RAG/qdrant_rag.md"
-
-    - Apps:
-      - Overview: "examples/apps_examples_overview.md"
-      - Web Scraper Agents: "developer_guides/web_scraper.md"
-      - Smart Database: "examples/smart_database.md"
-      
-    - AOP:
-      - Overview: "examples/aop_examples_overview.md"
-      - Medical AOP Example: "examples/aop_medical.md"
-
-    - X402:
-      - x402 Quickstart Example: "examples/x402_payment_integration.md"
-      - X402 Discovery Query Agent: "examples/x402_discovery_query.md"
-      - X402 Tools Agent: "swarms/examples/x402_tools_agent.md"
-
-
   - Swarms Rust:
     - Overview: "swarms_rs/overview.md"
     - Agents: "swarms_rs/agents.md"

example.py

@@ -2,18 +2,21 @@
 
 # Initialize the agent
 agent = Agent(
-    agent_name="Quantitative-Trading-Agent",
+    agent_name="Quantitative-Trading-Agent--new",
     agent_description="Advanced quantitative trading and algorithmic analysis agent",
     system_prompt="You are a helpful assistant that can answer questions and help with tasks and your name is Quantitative-Trading-Agent",
-    model_name="gpt-5.4",
+    model_name="claude-sonnet-4-6",
     dynamic_temperature_enabled=True,
     max_loops=1,
     dynamic_context_window=True,
     top_p=None,
+    thinking_tokens=1024,
+    reasoning_effort="high",
+    streaming_on=True,
 )
 
 out = agent.run(
-    task="What are the top five best energy stocks across nuclear, solar, gas, and other energy sources?",
+    task="Do a deep dive into just one of your choices",
 )
 
 print(out)

example_streaming_tools.py

@@ -0,0 +1,139 @@
+import json
+
+from swarms import Agent
+
+
+# ---------------------------------------------------------------------------
+# Tools
+# ---------------------------------------------------------------------------
+
+
+def get_stock_price(ticker: str) -> str:
+    """Return a mock current price for a stock ticker."""
+    prices = {
+        "AAPL": 213.45,
+        "MSFT": 415.20,
+        "NVDA": 875.30,
+        "CEG": 192.60,
+    }
+    price = prices.get(ticker.upper(), 100.00)
+    return json.dumps(
+        {"ticker": ticker.upper(), "price": price, "currency": "USD"}
+    )
+
+
+def get_market_news(topic: str) -> str:
+    """Return mock market headlines for a topic."""
+    headlines = {
+        "energy": "Nuclear power demand surges as data-center operators sign long-term PPAs.",
+        "semiconductors": "NVDA posts record revenue driven by AI accelerator shipments.",
+    }
+    text = headlines.get(
+        topic.lower(), f"Markets steady; awaiting data on {topic}."
+    )
+    return json.dumps({"topic": topic, "headline": text})
+
+
+def calculate_pe_ratio(price: float, eps: float) -> str:
+    """Calculate price-to-earnings ratio."""
+    if eps <= 0:
+        return json.dumps({"error": "EPS must be positive"})
+    return json.dumps(
+        {
+            "price": price,
+            "eps": eps,
+            "pe_ratio": round(price / eps, 2),
+        }
+    )
+
+
+TASK = (
+    "Analyse Constellation Energy (CEG): fetch the current price, "
+    "check the latest energy market news, and compute the P/E ratio assuming "
+    "EPS of $8.40. Give me a buy / hold / sell recommendation."
+)
+
+
+def make_agent() -> Agent:
+    return Agent(
+        agent_name="Streaming-Trading-Agent",
+        agent_description="Quantitative trading analyst",
+        system_prompt=(
+            "You are a quantitative trading analyst. "
+            "Use the available tools to fetch live data before forming your view."
+        ),
+        model_name="claude-sonnet-4-6",
+        max_loops="auto",
+        thinking_tokens=2048,
+        tools=[get_stock_price, get_market_news, calculate_pe_ratio],
+        top_p=None,
+        streaming_on=True,
+        reasoning_effort="high",
+        temperature=1,
+    )
+
+
+# ---------------------------------------------------------------------------
+# 1. Sync generator — run_stream()
+# ---------------------------------------------------------------------------
+
+
+def demo_sync():
+    print("\n" + "=" * 60)
+    print("SYNC STREAMING  (run_stream)")
+    print("=" * 60 + "\n")
+
+    agent = make_agent()
+
+    out = agent.run(TASK)
+    print(out)
+
+
+# ---------------------------------------------------------------------------
+# 2. Async generator — arun_stream()
+# ---------------------------------------------------------------------------
+
+
+async def demo_async():
+    print("\n" + "=" * 60)
+    print("ASYNC STREAMING  (arun_stream)")
+    print("=" * 60 + "\n")
+
+    agent = make_agent()
+
+    async for token in agent.arun_stream(TASK):
+        print(token, end="", flush=True)
+
+    print("\n")
+
+
+# ---------------------------------------------------------------------------
+# 3. Original blocking call — run()  (for comparison)
+# ---------------------------------------------------------------------------
+
+
+def demo_blocking():
+    print("\n" + "=" * 60)
+    print("BLOCKING  (run)")
+    print("=" * 60 + "\n")
+
+    agent = make_agent()
+    agent.print_on = True  # let the agent render its own panels
+
+    result = agent.run(TASK)
+    print(result)
+
+
+# ---------------------------------------------------------------------------
+# Entry point
+# ---------------------------------------------------------------------------
+
+if __name__ == "__main__":
+    mode = "async"
+
+    # if mode == "async":
+    #     asyncio.run(demo_async())
+    # elif mode == "blocking":
+    #     demo_blocking()
+    # else:
+    demo_sync()