docs: update changelog and version for v1.11.0rc1

* fix: replace os.system with subprocess.run in unsafe mode pip install

Eliminates shell injection risk (A05) where a malicious library name like
"pkg; rm -rf /" could execute arbitrary host commands. Using list-form
subprocess.run with shell=False ensures the library name is always treated
as a single argument with no shell metacharacter expansion.

Adds two tests: one verifying list-form invocation, one verifying that
shell metacharacters in a library name cannot trigger shell execution.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* fix: use sys.executable -m pip to satisfy S607 linting rule

S607 flags partial executable paths like ["pip", ...]. Using
[sys.executable, "-m", "pip", ...] provides an absolute path and also
ensures installation targets the correct Python environment.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>

.github/workflows/nightly.yml

@@ -0,0 +1,127 @@
+name: Nightly Canary Release
+
+on:
+  schedule:
+    - cron: '0 6 * * *' # daily at 6am UTC
+  workflow_dispatch:
+
+jobs:
+  check:
+    name: Check for new commits
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+    outputs:
+      has_changes: ${{ steps.check.outputs.has_changes }}
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Check for commits in last 24h
+        id: check
+        run: |
+          RECENT=$(git log --since="24 hours ago" --oneline | head -1)
+          if [ -n "$RECENT" ]; then
+            echo "has_changes=true" >> "$GITHUB_OUTPUT"
+          else
+            echo "has_changes=false" >> "$GITHUB_OUTPUT"
+          fi
+
+  build:
+    name: Build nightly packages
+    needs: check
+    if: needs.check.outputs.has_changes == 'true' || github.event_name == 'workflow_dispatch'
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+
+      - name: Stamp nightly versions
+        run: |
+          DATE=$(date +%Y%m%d)
+          for init_file in \
+            lib/crewai/src/crewai/__init__.py \
+            lib/crewai-tools/src/crewai_tools/__init__.py \
+            lib/crewai-files/src/crewai_files/__init__.py; do
+            CURRENT=$(python -c "
+          import re
+          text = open('$init_file').read()
+          print(re.search(r'__version__\s*=\s*\"(.*?)\"\s*$', text, re.MULTILINE).group(1))
+          ")
+            NIGHTLY="${CURRENT}.dev${DATE}"
+            sed -i "s/__version__ = .*/__version__ = \"${NIGHTLY}\"/" "$init_file"
+            echo "$init_file: $CURRENT -> $NIGHTLY"
+          done
+
+          # Update cross-package dependency pins to nightly versions
+          sed -i "s/\"crewai-tools==[^\"]*\"/\"crewai-tools==${NIGHTLY}\"/" lib/crewai/pyproject.toml
+          sed -i "s/\"crewai==[^\"]*\"/\"crewai==${NIGHTLY}\"/" lib/crewai-tools/pyproject.toml
+          echo "Updated cross-package dependency pins to ${NIGHTLY}"
+
+      - name: Build packages
+        run: |
+          uv build --all-packages
+          rm dist/.gitignore
+
+      - name: Upload artifacts
+        uses: actions/upload-artifact@v4
+        with:
+          name: dist
+          path: dist/
+
+  publish:
+    name: Publish nightly to PyPI
+    needs: build
+    runs-on: ubuntu-latest
+    environment:
+      name: pypi
+      url: https://pypi.org/p/crewai
+    permissions:
+      id-token: write
+      contents: read
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v6
+        with:
+          version: "0.8.4"
+          python-version: "3.12"
+          enable-cache: false
+
+      - name: Download artifacts
+        uses: actions/download-artifact@v4
+        with:
+          name: dist
+          path: dist
+
+      - name: Publish to PyPI
+        env:
+          UV_PUBLISH_TOKEN: ${{ secrets.PYPI_API_TOKEN }}
+        run: |
+          failed=0
+          for package in dist/*; do
+            if [[ "$package" == *"crewai_devtools"* ]]; then
+              echo "Skipping private package: $package"
+              continue
+            fi
+            echo "Publishing $package"
+            if ! uv publish "$package"; then
+              echo "Failed to publish $package"
+              failed=1
+            fi
+          done
+          if [ $failed -eq 1 ]; then
+            echo "Some packages failed to publish"
+            exit 1
+          fi

.github/workflows/publish.yml

@@ -59,6 +59,8 @@ jobs:
       contents: read
     steps:
       - uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.release_tag || github.ref }}
 
       - name: Install uv
         uses: astral-sh/setup-uv@v6
@@ -93,3 +95,72 @@ jobs:
             echo "Some packages failed to publish"
             exit 1
           fi
+
+      - name: Build Slack payload
+        if: success()
+        id: slack
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          RELEASE_TAG: ${{ inputs.release_tag }}
+        run: |
+          payload=$(uv run python -c "
+          import json, re, subprocess, sys
+
+          with open('lib/crewai/src/crewai/__init__.py') as f:
+              m = re.search(r\"__version__\s*=\s*[\\\"']([^\\\"']+)\", f.read())
+          version = m.group(1) if m else 'unknown'
+
+          import os
+          tag = os.environ.get('RELEASE_TAG') or version
+
+          try:
+              r = subprocess.run(['gh','release','view',tag,'--json','body','-q','.body'],
+                                 capture_output=True, text=True, check=True)
+              body = r.stdout.strip()
+          except Exception:
+              body = ''
+
+          blocks = [
+              {'type':'section','text':{'type':'mrkdwn',
+                  'text':f':rocket: \`crewai v{version}\` published to PyPI'}},
+              {'type':'section','text':{'type':'mrkdwn',
+                  'text':f'<https://pypi.org/project/crewai/{version}/|View on PyPI> · <https://github.com/crewAIInc/crewAI/releases/tag/{tag}|Release notes>'}},
+              {'type':'divider'},
+          ]
+
+          if body:
+              heading, items = '', []
+              for line in body.split('\n'):
+                  line = line.strip()
+                  if not line: continue
+                  hm = re.match(r'^#{2,3}\s+(.*)', line)
+                  if hm:
+                      if heading and items:
+                          skip = heading in ('What\\'s Changed','') or 'Contributors' in heading
+                          if not skip:
+                              txt = f'*{heading}*\n' + '\n'.join(f'• {i}' for i in items)
+                              blocks.append({'type':'section','text':{'type':'mrkdwn','text':txt}})
+                      heading, items = hm.group(1), []
+                  elif line.startswith('- ') or line.startswith('* '):
+                      items.append(re.sub(r'\*\*([^*]*)\*\*', r'*\1*', line[2:]))
+              if heading and items:
+                  skip = heading in ('What\\'s Changed','') or 'Contributors' in heading
+                  if not skip:
+                      txt = f'*{heading}*\n' + '\n'.join(f'• {i}' for i in items)
+                      blocks.append({'type':'section','text':{'type':'mrkdwn','text':txt}})
+
+          blocks.append({'type':'divider'})
+          blocks.append({'type':'section','text':{'type':'mrkdwn',
+              'text':f'\`\`\`uv add \"crewai[tools]=={version}\"\`\`\`'}})
+
+          print(json.dumps({'blocks':blocks}))
+          ")
+          echo "payload=$payload" >> $GITHUB_OUTPUT
+
+      - name: Notify Slack
+        if: success()
+        uses: slackapi/slack-github-action@v2.1.0
+        with:
+          webhook: ${{ secrets.SLACK_WEBHOOK_URL }}
+          webhook-type: incoming-webhook
+          payload: ${{ steps.slack.outputs.payload }}

conftest.py

@@ -12,6 +12,7 @@ from dotenv import load_dotenv
 import pytest
 from vcr.request import Request  # type: ignore[import-untyped]
 
+
 try:
     import vcr.stubs.httpx_stubs as httpx_stubs  # type: ignore[import-untyped]
 except ModuleNotFoundError:

docs/en/changelog.mdx

@@ -4,6 +4,237 @@ description: "Product updates, improvements, and bug fixes for CrewAI"
 icon: "clock"
 mode: "wide"
 ---
+<Update label="Mar 15, 2026">
+  ## v1.11.0rc1
+
+  [View release on GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.11.0rc1)
+
+  ## What's Changed
+
+  ### Features
+  - Add Plus API token authentication in a2a
+  - Implement plan execute pattern
+
+  ### Bug Fixes
+  - Resolve code interpreter sandbox escape issue
+
+  ### Documentation
+  - Update changelog and version for v1.10.2rc2
+
+  ## Contributors
+
+  @Copilot, @greysonlalonde, @lorenzejay, @theCyberTech
+
+</Update>
+
+<Update label="Mar 14, 2026">
+  ## v1.10.2rc2
+
+  [View release on GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.10.2rc2)
+
+  ## What's Changed
+
+  ### Bug Fixes
+  - Remove exclusive locks from read-only storage operations
+
+  ### Documentation
+  - Update changelog and version for v1.10.2rc1
+
+  ## Contributors
+
+  @greysonlalonde
+
+</Update>
+
+<Update label="Mar 13, 2026">
+  ## v1.10.2rc1
+
+  [View release on GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.10.2rc1)
+
+  ## What's Changed
+
+  ### Features
+  - Add release command and trigger PyPI publish
+
+  ### Bug Fixes
+  - Fix cross-process and thread-safe locking to unprotected I/O
+  - Propagate contextvars across all thread and executor boundaries
+  - Propagate ContextVars into async task threads
+
+  ### Documentation
+  - Update changelog and version for v1.10.2a1
+
+  ## Contributors
+
+  @danglies007, @greysonlalonde
+
+</Update>
+
+<Update label="Mar 11, 2026">
+  ## v1.10.2a1
+
+  [View release on GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.10.2a1)
+
+  ## What's Changed
+
+  ### Features
+  - Add support for tool search, saving tokens, and dynamically injecting appropriate tools during execution for Anthropics.
+  - Introduce more Brave Search tools.
+  - Create action for nightly releases.
+
+  ### Bug Fixes
+  - Fix LockException under concurrent multi-process execution.
+  - Resolve issues with grouping parallel tool results in a single user message.
+  - Address MCP tools resolutions and eliminate all shared mutable connections.
+  - Update LLM parameter handling in the human_feedback function.
+  - Add missing list/dict methods to LockedListProxy and LockedDictProxy.
+  - Propagate contextvars context to parallel tool call threads.
+  - Bump gitpython dependency to >=3.1.41 to resolve CVE path traversal vulnerability.
+
+  ### Refactoring
+  - Refactor memory classes to be serializable.
+
+  ### Documentation
+  - Update changelog and version for v1.10.1.
+
+  ## Contributors
+
+  @akaKuruma, @github-actions[bot], @giulio-leone, @greysonlalonde, @joaomdmoura, @jonathansampson, @lorenzejay, @lucasgomide, @mattatcha
+
+</Update>
+
+<Update label="Mar 04, 2026">
+  ## v1.10.1
+
+  [View release on GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.10.1)
+
+  ## What's Changed
+
+  ### Features
+  - Upgrade Gemini GenAI
+
+  ### Bug Fixes
+  - Adjust executor listener value to avoid recursion
+  - Group parallel function response parts in a single Content object in Gemini
+  - Surface thought output from thinking models in Gemini
+  - Load MCP and platform tools when agent tools are None
+  - Support Jupyter environments with running event loops in A2A
+  - Use anonymous ID for ephemeral traces
+  - Conditionally pass plus header
+  - Skip signal handler registration in non-main threads for telemetry
+  - Inject tool errors as observations and resolve name collisions
+  - Upgrade pypdf from 4.x to 6.7.4 to resolve Dependabot alerts
+  - Resolve critical and high Dependabot security alerts
+
+  ### Documentation
+  - Sync Composio tool documentation across locales
+
+  ## Contributors
+
+  @giulio-leone, @greysonlalonde, @haxzie, @joaomdmoura, @lorenzejay, @mattatcha, @mplachta, @nicoferdi96
+
+</Update>
+
+<Update label="Feb 27, 2026">
+  ## v1.10.1a1
+
+  [View release on GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.10.1a1)
+
+  ## What's Changed
+
+  ### Features
+  - Implement asynchronous invocation support in step callback methods
+  - Implement lazy loading for heavy dependencies in Memory module
+
+  ### Documentation
+  - Update changelog and version for v1.10.0
+
+  ### Refactoring
+  - Refactor step callback methods to support asynchronous invocation
+  - Refactor to implement lazy loading for heavy dependencies in Memory module
+
+  ### Bug Fixes
+  - Fix branch for release notes
+
+  ## Contributors
+
+  @greysonlalonde, @joaomdmoura
+
+</Update>
+
+<Update label="Feb 27, 2026">
+  ## v1.10.1a1
+
+  [View release on GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.10.1a1)
+
+  ## What's Changed
+
+  ### Refactoring
+  - Refactor step callback methods to support asynchronous invocation
+  - Implement lazy loading for heavy dependencies in Memory module
+
+  ### Documentation
+  - Update changelog and version for v1.10.0
+
+  ### Bug Fixes
+  - Make branch for release notes
+
+  ## Contributors
+
+  @greysonlalonde, @joaomdmoura
+
+</Update>
+
+<Update label="Feb 26, 2026">
+  ## v1.10.0
+
+  [View release on GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.10.0)
+
+  ## What's Changed
+
+  ### Features
+  - Enhance MCP tool resolution and related events
+  - Update lancedb version and add lance-namespace packages
+  - Enhance JSON argument parsing and validation in CrewAgentExecutor and BaseTool
+  - Migrate CLI HTTP client from requests to httpx
+  - Add versioned documentation
+  - Add yanked detection for version notes
+  - Implement user input handling in Flows
+  - Enhance HITL self-loop functionality in human feedback integration tests
+  - Add started_event_id and set in eventbus
+  - Auto update tools.specs
+
+  ### Bug Fixes
+  - Validate tool kwargs even when empty to prevent cryptic TypeError
+  - Preserve null types in tool parameter schemas for LLM
+  - Map output_pydantic/output_json to native structured output
+  - Ensure callbacks are ran/awaited if promise
+  - Capture method name in exception context
+  - Preserve enum type in router result; improve types
+  - Fix cyclic flows silently breaking when persistence ID is passed in inputs
+  - Correct CLI flag format from --skip-provider to --skip_provider
+  - Ensure OpenAI tool call stream is finalized
+  - Resolve complex schema $ref pointers in MCP tools
+  - Enforce additionalProperties=false in schemas
+  - Reject reserved script names for crew folders
+  - Resolve race condition in guardrail event emission test
+
+  ### Documentation
+  - Add litellm dependency note for non-native LLM providers
+  - Clarify NL2SQL security model and hardening guidance
+  - Add 96 missing actions across 9 integrations
+
+  ### Refactoring
+  - Refactor crew to provider
+  - Extract HITL to provider pattern
+  - Improve hook typing and registration
+
+  ## Contributors
+
+  @dependabot[bot], @github-actions[bot], @github-code-quality[bot], @greysonlalonde, @heitorado, @hobostay, @joaomdmoura, @johnvan7, @jonathansampson, @lorenzejay, @lucasgomide, @mattatcha, @mplachta, @nicoferdi96, @theCyberTech, @thiagomoretto, @vinibrsl
+
+</Update>
+
 <Update label="Jan 26, 2026">
   ## v1.9.0
 

docs/en/concepts/event-listener.mdx

@@ -219,6 +219,16 @@ CrewAI provides a wide range of events that you can listen for:
 - **ToolExecutionErrorEvent**: Emitted when a tool execution encounters an error
 - **ToolSelectionErrorEvent**: Emitted when there's an error selecting a tool
 
+### MCP Events
+
+- **MCPConnectionStartedEvent**: Emitted when starting to connect to an MCP server. Contains the server name, URL, transport type, connection timeout, and whether it's a reconnection attempt.
+- **MCPConnectionCompletedEvent**: Emitted when successfully connected to an MCP server. Contains the server name, connection duration in milliseconds, and whether it was a reconnection.
+- **MCPConnectionFailedEvent**: Emitted when connection to an MCP server fails. Contains the server name, error message, and error type (`timeout`, `authentication`, `network`, etc.).
+- **MCPToolExecutionStartedEvent**: Emitted when starting to execute an MCP tool. Contains the server name, tool name, and tool arguments.
+- **MCPToolExecutionCompletedEvent**: Emitted when MCP tool execution completes successfully. Contains the server name, tool name, result, and execution duration in milliseconds.
+- **MCPToolExecutionFailedEvent**: Emitted when MCP tool execution fails. Contains the server name, tool name, error message, and error type (`timeout`, `validation`, `server_error`, etc.).
+- **MCPConfigFetchFailedEvent**: Emitted when fetching an MCP server configuration fails (e.g., the MCP is not connected in your account, API error, or connection failure after config was fetched). Contains the slug, error message, and error type (`not_connected`, `api_error`, `connection_failed`).
+
 ### Knowledge Events
 
 - **KnowledgeRetrievalStartedEvent**: Emitted when a knowledge retrieval is started

docs/en/guides/migration/migrating-from-langgraph.mdx

@@ -0,0 +1,518 @@
+---
+title: "Moving from LangGraph to CrewAI: A Practical Guide for Engineers"
+description: If you already have built with LangGraph, learn how to quickly port your projects to CrewAI
+icon: switch
+mode: "wide"
+---
+
+You've built agents with LangGraph. You've wrestled with `StateGraph`, wired up conditional edges, and debugged state dictionaries at 2 AM. It works — but somewhere along the way, you started wondering if there's a better path to production.
+
+There is. **CrewAI Flows** gives you the same power — event-driven orchestration, conditional routing, shared state — with dramatically less boilerplate and a mental model that maps cleanly to how you actually think about multi-step AI workflows.
+
+This article walks through the core concepts side by side, shows real code comparisons, and demonstrates why CrewAI Flows is the framework you'll want to reach for next.
+
+---
+
+## The Mental Model Shift
+
+LangGraph asks you to think in **graphs**: nodes, edges, and state dictionaries. Every workflow is a directed graph where you explicitly wire transitions between computation steps. It's powerful, but the abstraction carries overhead — especially when your workflow is fundamentally sequential with a few decision points.
+
+CrewAI Flows asks you to think in **events**: methods that start things, methods that listen for results, and methods that route execution. The topology of your workflow emerges from decorator annotations rather than explicit graph construction. This isn't just syntactic sugar — it changes how you design, read, and maintain your pipelines.
+
+Here's the core mapping:
+
+| LangGraph Concept | CrewAI Flows Equivalent |
+| --- | --- |
+| `StateGraph` class | `Flow` class |
+| `add_node()` | Methods decorated with `@start`, `@listen` |
+| `add_edge()` / `add_conditional_edges()` | `@listen()` / `@router()` decorators |
+| `TypedDict` state | Pydantic `BaseModel` state |
+| `START` / `END` constants | `@start()` decorator / natural method return |
+| `graph.compile()` | `flow.kickoff()` |
+| Checkpointer / persistence | Built-in memory (LanceDB-backed) |
+
+Let's see what this looks like in practice.
+
+---
+
+## Demo 1: A Simple Sequential Pipeline
+
+Imagine you're building a pipeline that takes a topic, researches it, writes a summary, and formats the output. Here's how each framework handles it.
+
+### LangGraph Approach
+
+```python
+from typing import TypedDict
+from langgraph.graph import StateGraph, START, END
+
+class ResearchState(TypedDict):
+    topic: str
+    raw_research: str
+    summary: str
+    formatted_output: str
+
+def research_topic(state: ResearchState) -> dict:
+    # Call an LLM or search API
+    result = llm.invoke(f"Research the topic: {state['topic']}")
+    return {"raw_research": result}
+
+def write_summary(state: ResearchState) -> dict:
+    result = llm.invoke(
+        f"Summarize this research:\n{state['raw_research']}"
+    )
+    return {"summary": result}
+
+def format_output(state: ResearchState) -> dict:
+    result = llm.invoke(
+        f"Format this summary as a polished article section:\n{state['summary']}"
+    )
+    return {"formatted_output": result}
+
+# Build the graph
+graph = StateGraph(ResearchState)
+graph.add_node("research", research_topic)
+graph.add_node("summarize", write_summary)
+graph.add_node("format", format_output)
+
+graph.add_edge(START, "research")
+graph.add_edge("research", "summarize")
+graph.add_edge("summarize", "format")
+graph.add_edge("format", END)
+
+# Compile and run
+app = graph.compile()
+result = app.invoke({"topic": "quantum computing advances in 2026"})
+print(result["formatted_output"])
+```
+
+You define functions, register them as nodes, and manually wire every transition. For a simple sequence like this, there's a lot of ceremony.
+
+### CrewAI Flows Approach
+
+```python
+from crewai import LLM, Agent, Crew, Process, Task
+from crewai.flow.flow import Flow, listen, start
+from pydantic import BaseModel
+
+llm = LLM(model="openai/gpt-5.2")
+
+class ResearchState(BaseModel):
+    topic: str = ""
+    raw_research: str = ""
+    summary: str = ""
+    formatted_output: str = ""
+
+class ResearchFlow(Flow[ResearchState]):
+    @start()
+    def research_topic(self):
+        # Option 1: Direct LLM call
+        result = llm.call(f"Research the topic: {self.state.topic}")
+        self.state.raw_research = result
+        return result
+
+    @listen(research_topic)
+    def write_summary(self, research_output):
+        # Option 2: A single agent
+        summarizer = Agent(
+            role="Research Summarizer",
+            goal="Produce concise, accurate summaries of research content",
+            backstory="You are an expert at distilling complex research into clear, "
+            "digestible summaries.",
+            llm=llm,
+            verbose=True,
+        )
+        result = summarizer.kickoff(
+            f"Summarize this research:\n{self.state.raw_research}"
+        )
+        self.state.summary = str(result)
+        return self.state.summary
+
+    @listen(write_summary)
+    def format_output(self, summary_output):
+        # Option 3: a complete crew (with one or more agents)
+        formatter = Agent(
+            role="Content Formatter",
+            goal="Transform research summaries into polished, publication-ready article sections",
+            backstory="You are a skilled editor with expertise in structuring and "
+            "presenting technical content for a general audience.",
+            llm=llm,
+            verbose=True,
+        )
+        format_task = Task(
+            description=f"Format this summary as a polished article section:\n{self.state.summary}",
+            expected_output="A well-structured, polished article section ready for publication.",
+            agent=formatter,
+        )
+        crew = Crew(
+            agents=[formatter],
+            tasks=[format_task],
+            process=Process.sequential,
+            verbose=True,
+        )
+        result = crew.kickoff()
+        self.state.formatted_output = str(result)
+        return self.state.formatted_output
+
+# Run the flow
+flow = ResearchFlow()
+flow.state.topic = "quantum computing advances in 2026"
+result = flow.kickoff()
+print(flow.state.formatted_output)
+
+```
+
+Notice what's different: no graph construction, no edge wiring, no compile step. The execution order is declared right where the logic lives. `@start()` marks the entry point, and `@listen(method_name)` chains steps together. The state is a proper Pydantic model with type safety, validation, and IDE auto-completion.
+
+---
+
+## Demo 2: Conditional Routing
+
+This is where things get interesting. Say you're building a content pipeline that routes to different processing paths based on the type of content detected.
+
+### LangGraph Approach
+
+```python
+from typing import TypedDict, Literal
+from langgraph.graph import StateGraph, START, END
+
+class ContentState(TypedDict):
+    input_text: str
+    content_type: str
+    result: str
+
+def classify_content(state: ContentState) -> dict:
+    content_type = llm.invoke(
+        f"Classify this content as 'technical', 'creative', or 'business':\n{state['input_text']}"
+    )
+    return {"content_type": content_type.strip().lower()}
+
+def process_technical(state: ContentState) -> dict:
+    result = llm.invoke(f"Process as technical doc:\n{state['input_text']}")
+    return {"result": result}
+
+def process_creative(state: ContentState) -> dict:
+    result = llm.invoke(f"Process as creative writing:\n{state['input_text']}")
+    return {"result": result}
+
+def process_business(state: ContentState) -> dict:
+    result = llm.invoke(f"Process as business content:\n{state['input_text']}")
+    return {"result": result}
+
+# Routing function
+def route_content(state: ContentState) -> Literal["technical", "creative", "business"]:
+    return state["content_type"]
+
+# Build the graph
+graph = StateGraph(ContentState)
+graph.add_node("classify", classify_content)
+graph.add_node("technical", process_technical)
+graph.add_node("creative", process_creative)
+graph.add_node("business", process_business)
+
+graph.add_edge(START, "classify")
+graph.add_conditional_edges(
+    "classify",
+    route_content,
+    {
+        "technical": "technical",
+        "creative": "creative",
+        "business": "business",
+    }
+)
+graph.add_edge("technical", END)
+graph.add_edge("creative", END)
+graph.add_edge("business", END)
+
+app = graph.compile()
+result = app.invoke({"input_text": "Explain how TCP handshakes work"})
+```
+
+You need a separate routing function, explicit conditional edge mapping, and termination edges for every branch. The routing logic is decoupled from the node that produces the routing decision.
+
+### CrewAI Flows Approach
+
+```python
+from crewai import LLM, Agent
+from crewai.flow.flow import Flow, listen, router, start
+from pydantic import BaseModel
+
+llm = LLM(model="openai/gpt-5.2")
+
+class ContentState(BaseModel):
+    input_text: str = ""
+    content_type: str = ""
+    result: str = ""
+
+class ContentFlow(Flow[ContentState]):
+    @start()
+    def classify_content(self):
+        self.state.content_type = (
+            llm.call(
+                f"Classify this content as 'technical', 'creative', or 'business':\n"
+                f"{self.state.input_text}"
+            )
+            .strip()
+            .lower()
+        )
+        return self.state.content_type
+
+    @router(classify_content)
+    def route_content(self, classification):
+        if classification == "technical":
+            return "process_technical"
+        elif classification == "creative":
+            return "process_creative"
+        else:
+            return "process_business"
+
+    @listen("process_technical")
+    def handle_technical(self):
+        agent = Agent(
+            role="Technical Writer",
+            goal="Produce clear, accurate technical documentation",
+            backstory="You are an expert technical writer who specializes in "
+            "explaining complex technical concepts precisely.",
+            llm=llm,
+            verbose=True,
+        )
+        self.state.result = str(
+            agent.kickoff(f"Process as technical doc:\n{self.state.input_text}")
+        )
+
+    @listen("process_creative")
+    def handle_creative(self):
+        agent = Agent(
+            role="Creative Writer",
+            goal="Craft engaging and imaginative creative content",
+            backstory="You are a talented creative writer with a flair for "
+            "compelling storytelling and vivid expression.",
+            llm=llm,
+            verbose=True,
+        )
+        self.state.result = str(
+            agent.kickoff(f"Process as creative writing:\n{self.state.input_text}")
+        )
+
+    @listen("process_business")
+    def handle_business(self):
+        agent = Agent(
+            role="Business Writer",
+            goal="Produce professional, results-oriented business content",
+            backstory="You are an experienced business writer who communicates "
+            "strategy and value clearly to professional audiences.",
+            llm=llm,
+            verbose=True,
+        )
+        self.state.result = str(
+            agent.kickoff(f"Process as business content:\n{self.state.input_text}")
+        )
+
+flow = ContentFlow()
+flow.state.input_text = "Explain how TCP handshakes work"
+flow.kickoff()
+print(flow.state.result)
+
+```
+
+The `@router()` decorator turns a method into a decision point. It returns a string that matches a listener — no mapping dictionaries, no separate routing functions. The branching logic reads like a Python `if` statement because it *is* one.
+
+---
+
+## Demo 3: Integrating AI Agent Crews into Flows
+
+Here's where CrewAI's real power shines. Flows aren't just for chaining LLM calls — they orchestrate full **Crews** of autonomous agents. This is something LangGraph simply doesn't have a native equivalent for.
+
+```python
+from crewai import Agent, Task, Crew
+from crewai.flow.flow import Flow, listen, start
+from pydantic import BaseModel
+
+class ArticleState(BaseModel):
+    topic: str = ""
+    research: str = ""
+    draft: str = ""
+    final_article: str = ""
+
+class ArticleFlow(Flow[ArticleState]):
+
+    @start()
+    def run_research_crew(self):
+        """A full Crew of agents handles research."""
+        researcher = Agent(
+            role="Senior Research Analyst",
+            goal=f"Produce comprehensive research on: {self.state.topic}",
+            backstory="You're a veteran analyst known for thorough, "
+                       "well-sourced research reports.",
+            llm="gpt-4o"
+        )
+
+        research_task = Task(
+            description=f"Research '{self.state.topic}' thoroughly. "
+                        "Cover key trends, data points, and expert opinions.",
+            expected_output="A detailed research brief with sources.",
+            agent=researcher
+        )
+
+        crew = Crew(agents=[researcher], tasks=[research_task])
+        result = crew.kickoff()
+        self.state.research = result.raw
+        return result.raw
+
+    @listen(run_research_crew)
+    def run_writing_crew(self, research_output):
+        """A different Crew handles writing."""
+        writer = Agent(
+            role="Technical Writer",
+            goal="Write a compelling article based on provided research.",
+            backstory="You turn complex research into engaging, clear prose.",
+            llm="gpt-4o"
+        )
+
+        editor = Agent(
+            role="Senior Editor",
+            goal="Review and polish articles for publication quality.",
+            backstory="20 years of editorial experience at top tech publications.",
+            llm="gpt-4o"
+        )
+
+        write_task = Task(
+            description=f"Write an article based on this research:\n{self.state.research}",
+            expected_output="A well-structured draft article.",
+            agent=writer
+        )
+
+        edit_task = Task(
+            description="Review, fact-check, and polish the draft article.",
+            expected_output="A publication-ready article.",
+            agent=editor
+        )
+
+        crew = Crew(agents=[writer, editor], tasks=[write_task, edit_task])
+        result = crew.kickoff()
+        self.state.final_article = result.raw
+        return result.raw
+
+# Run the full pipeline
+flow = ArticleFlow()
+flow.state.topic = "The Future of Edge AI"
+flow.kickoff()
+print(flow.state.final_article)
+```
+
+This is the key insight: **Flows provide the orchestration layer, and Crews provide the intelligence layer.** Each step in a Flow can spin up a full team of collaborating agents, each with their own roles, goals, and tools. You get structured, predictable control flow *and* autonomous agent collaboration — the best of both worlds.
+
+In LangGraph, achieving something similar means manually implementing agent communication protocols, tool-calling loops, and delegation logic inside your node functions. It's possible, but it's plumbing you're building from scratch every time.
+
+---
+
+## Demo 4: Parallel Execution and Synchronization
+
+Real-world pipelines often need to fan out work and join the results. CrewAI Flows handles this elegantly with `and_` and `or_` operators.
+
+```python
+from crewai import LLM
+from crewai.flow.flow import Flow, and_, listen, start
+from pydantic import BaseModel
+
+llm = LLM(model="openai/gpt-5.2")
+
+class AnalysisState(BaseModel):
+    topic: str = ""
+    market_data: str = ""
+    tech_analysis: str = ""
+    competitor_intel: str = ""
+    final_report: str = ""
+
+class ParallelAnalysisFlow(Flow[AnalysisState]):
+    @start()
+    def start_method(self):
+        pass
+
+    @listen(start_method)
+    def gather_market_data(self):
+        # Your agentic or deterministic code
+        pass
+
+    @listen(start_method)
+    def run_tech_analysis(self):
+        # Your agentic or deterministic code
+        pass
+
+    @listen(start_method)
+    def gather_competitor_intel(self):
+        # Your agentic or deterministic code
+        pass
+
+    @listen(and_(gather_market_data, run_tech_analysis, gather_competitor_intel))
+    def synthesize_report(self):
+        # Your agentic or deterministic code
+        pass
+
+flow = ParallelAnalysisFlow()
+flow.state.topic = "AI-powered developer tools"
+flow.kickoff()
+
+```
+
+Multiple `@start()` decorators fire in parallel. The `and_()` combinator on the `@listen` decorator ensures `synthesize_report` only executes after *all three* upstream methods complete. There's also `or_()` for when you want to proceed as soon as *any* upstream task finishes.
+
+In LangGraph, you'd need to build a fan-out/fan-in pattern with parallel branches, a synchronization node, and careful state merging — all wired explicitly through edges.
+
+---
+
+## Why CrewAI Flows for Production
+
+Beyond cleaner syntax, Flows deliver several production-critical advantages:
+
+**Built-in state persistence.** Flow state is backed by LanceDB, meaning your workflows can survive crashes, be resumed, and accumulate knowledge across runs. LangGraph requires you to configure a separate checkpointer.
+
+**Type-safe state management.** Pydantic models give you validation, serialization, and IDE support out of the box. LangGraph's `TypedDict` states don't validate at runtime.
+
+**First-class agent orchestration.** Crews are a native primitive. You define agents with roles, goals, backstories, and tools — and they collaborate autonomously within the structured envelope of a Flow. No need to reinvent multi-agent coordination.
+
+**Simpler mental model.** Decorators declare intent. `@start` means "begin here." `@listen(x)` means "run after x." `@router(x)` means "decide where to go after x." The code reads like the workflow it describes.
+
+**CLI integration.** Run flows with `crewai run`. No separate compilation step, no graph serialization. Your Flow is a Python class, and it runs like one.
+
+---
+
+## Migration Cheat Sheet
+
+If you're sitting on a LangGraph codebase and want to move to CrewAI Flows, here's a practical conversion guide:
+
+1. **Map your state.** Convert your `TypedDict` to a Pydantic `BaseModel`. Add default values for all fields.
+2. **Convert nodes to methods.** Each `add_node` function becomes a method on your `Flow` subclass. Replace `state["field"]` reads with `self.state.field`.
+3. **Replace edges with decorators.** Your `add_edge(START, "first_node")` becomes `@start()` on the first method. Sequential `add_edge("a", "b")` becomes `@listen(a)` on method `b`.
+4. **Replace conditional edges with `@router`.** Your routing function and `add_conditional_edges()` mapping become a single `@router()` method that returns a route string.
+5. **Replace compile + invoke with kickoff.** Drop `graph.compile()`. Call `flow.kickoff()` instead.
+6. **Consider where Crews fit.** Any node where you have complex multi-step agent logic is a candidate for extraction into a Crew. This is where you'll see the biggest quality improvement.
+
+---
+
+## Getting Started
+
+Install CrewAI and scaffold a new Flow project:
+
+```bash
+pip install crewai
+crewai create flow my_first_flow
+cd my_first_flow
+```
+
+This generates a project structure with a ready-to-edit Flow class, configuration files, and a `pyproject.toml` with `type = "flow"` already set. Run it with:
+
+```bash
+crewai run
+```
+
+From there, add your agents, wire up your listeners, and ship it.
+
+---
+
+## Final Thoughts
+
+LangGraph taught the ecosystem that AI workflows need structure. That was an important lesson. But CrewAI Flows takes that lesson and delivers it in a form that's faster to write, easier to read, and more powerful in production — especially when your workflows involve multiple collaborating agents.
+
+If you're building anything beyond a single-agent chain, give Flows a serious look. The decorator-driven model, native Crew integration, and built-in state management mean you'll spend less time on plumbing and more time on the problems that matter.
+
+Start with `crewai create flow`. You won't look back.

docs/en/mcp/dsl-integration.mdx

@@ -62,22 +62,22 @@ Use the `#` syntax to select specific tools from a server:
 "https://mcp.exa.ai/mcp?api_key=your_key#web_search_exa"
 ```
 
-### CrewAI AMP Marketplace
+### Connected MCP Integrations
 
-Access tools from the CrewAI AMP marketplace:
+Connect MCP servers from the CrewAI catalog or bring your own. Once connected in your account, reference them by slug:
 
 ```python
-# Full service with all tools
-"crewai-amp:financial-data"
+# Connected MCP with all tools
+"snowflake"
 
-# Specific tool from AMP service
-"crewai-amp:research-tools#pubmed_search"
+# Specific tool from a connected MCP
+"stripe#list_invoices"
 
-# Multiple AMP services
+# Multiple connected MCPs
 mcps=[
-    "crewai-amp:weather-insights",
-    "crewai-amp:market-analysis",
-    "crewai-amp:social-media-monitoring"
+    "snowflake",
+    "stripe",
+    "github"
 ]
 ```
 
@@ -99,10 +99,10 @@ multi_source_agent = Agent(
         "https://mcp.exa.ai/mcp?api_key=your_exa_key&profile=research",
         "https://weather.api.com/mcp#get_current_conditions",
 
-        # CrewAI AMP marketplace
-        "crewai-amp:financial-insights",
-        "crewai-amp:academic-research#pubmed_search",
-        "crewai-amp:market-intelligence#competitor_analysis"
+        # Connected MCPs from catalog
+        "snowflake",
+        "stripe#list_invoices",
+        "github#search_repositories"
     ]
 )
 
@@ -147,7 +147,7 @@ agent = Agent(
     mcps=[
         "https://mcp.exa.ai/mcp?api_key=key",      # Tools: mcp_exa_ai_*
         "https://weather.service.com/mcp",         # Tools: weather_service_com_*
-        "crewai-amp:financial-data"                # Tools: financial_data_*
+        "snowflake"                                # Tools: snowflake_*
     ]
 )
 
@@ -170,7 +170,7 @@ agent = Agent(
         "https://primary-server.com/mcp",         # Primary data source
         "https://backup-server.com/mcp",          # Backup if primary fails
         "https://unreachable-server.com/mcp",     # Will be skipped with warning
-        "crewai-amp:reliable-service"             # Reliable AMP service
+        "snowflake"                               # Connected MCP from catalog
     ]
 )
 
@@ -254,7 +254,7 @@ agent = Agent(
     apps=["gmail", "slack"],                       # Platform integrations
     mcps=[                                         # MCP servers
         "https://mcp.exa.ai/mcp?api_key=key",
-        "crewai-amp:research-tools"
+        "snowflake"
     ],
 
     verbose=True,
@@ -298,7 +298,7 @@ agent = Agent(
 mcps=[
     "https://primary-api.com/mcp",       # Primary choice
     "https://backup-api.com/mcp",        # Backup option
-    "crewai-amp:reliable-service"        # AMP fallback
+    "snowflake"                          # Connected MCP fallback
 ]
 ```
 
@@ -311,7 +311,7 @@ agent = Agent(
     backstory="Financial analyst with access to weather data for agricultural market insights",
     mcps=[
         "https://weather.service.com/mcp#get_forecast",
-        "crewai-amp:financial-data#stock_analysis"
+        "stripe#list_invoices"
     ]
 )
 ```

docs/en/mcp/overview.mdx

@@ -17,7 +17,7 @@ Use the `mcps` field directly on agents for seamless MCP tool integration. The D
 
 #### String-Based References (Quick Setup)
 
-Perfect for remote HTTPS servers and CrewAI AMP marketplace:
+Perfect for remote HTTPS servers and connected MCP integrations from the CrewAI catalog:
 
 ```python
 from crewai import Agent
@@ -29,8 +29,8 @@ agent = Agent(
     mcps=[
         "https://mcp.exa.ai/mcp?api_key=your_key",           # External MCP server
         "https://api.weather.com/mcp#get_forecast",          # Specific tool from server
-        "crewai-amp:financial-data",                         # CrewAI AMP marketplace
-        "crewai-amp:research-tools#pubmed_search"            # Specific AMP tool
+        "snowflake",                                         # Connected MCP from catalog
+        "stripe#list_invoices"                               # Specific tool from connected MCP
     ]
 )
 # MCP tools are now automatically available to your agent!
@@ -127,7 +127,7 @@ research_agent = Agent(
     backstory="Expert researcher with access to multiple data sources",
     mcps=[
         "https://mcp.exa.ai/mcp?api_key=your_key&profile=your_profile",
-        "crewai-amp:weather-service#current_conditions"
+        "snowflake#run_query"
     ]
 )
 
@@ -204,19 +204,22 @@ mcps=[
 ]
 ```
 
-#### CrewAI AMP Marketplace
+#### Connected MCP Integrations
+
+Connect MCP servers from the CrewAI catalog or bring your own. Once connected in your account, reference them by slug:
 
 ```python
 mcps=[
-    # Full AMP MCP service - get all available tools
-    "crewai-amp:financial-data",
+    # Connected MCP - get all available tools
+    "snowflake",
 
-    # Specific tool from AMP service using # syntax
-    "crewai-amp:research-tools#pubmed_search",
+    # Specific tool from a connected MCP using # syntax
+    "stripe#list_invoices",
 
-    # Multiple AMP services
-    "crewai-amp:weather-service",
-    "crewai-amp:market-analysis"
+    # Multiple connected MCPs
+    "snowflake",
+    "stripe",
+    "github"
 ]
 ```
 
@@ -299,7 +302,7 @@ from crewai.mcp import MCPServerStdio, MCPServerHTTP
 mcps=[
     # String references
     "https://external-api.com/mcp",              # External server
-    "crewai-amp:financial-insights",             # AMP service
+    "snowflake",                                 # Connected MCP from catalog
 
     # Structured configurations
     MCPServerStdio(
@@ -409,7 +412,7 @@ agent = Agent(
         # String references
         "https://reliable-server.com/mcp",        # Will work
         "https://unreachable-server.com/mcp",     # Will be skipped gracefully
-        "crewai-amp:working-service",             # Will work
+        "snowflake",                              # Connected MCP from catalog
 
         # Structured configs
         MCPServerStdio(

docs/en/tools/automation/composiotool.mdx

@@ -18,77 +18,46 @@ Composio is an integration platform that allows you to connect your AI agents to
 To incorporate Composio tools into your project, follow the instructions below:
 
 ```shell
-pip install composio-crewai
+pip install composio composio-crewai
 pip install crewai
 ```
 
-After the installation is complete, either run `composio login` or export your composio API key as `COMPOSIO_API_KEY`. Get your Composio API key from [here](https://app.composio.dev)
+After the installation is complete, set your Composio API key as `COMPOSIO_API_KEY`. Get your Composio API key from [here](https://platform.composio.dev)
 
 ## Example
 
 The following example demonstrates how to initialize the tool and execute a github action:
 
-1. Initialize Composio toolset
+1. Initialize Composio with CrewAI Provider
 
 ```python Code
-from composio_crewai import ComposioToolSet, App, Action
+from composio_crewai import ComposioProvider
+from composio import Composio
 from crewai import Agent, Task, Crew
 
-toolset = ComposioToolSet()
+composio = Composio(provider=ComposioProvider())
 ```
 
-2. Connect your GitHub account
+2. Create a new Composio Session and retrieve the tools
 <CodeGroup>
-```shell CLI
-composio add github
-```
-```python Code
-request = toolset.initiate_connection(app=App.GITHUB)
-print(f"Open this URL to authenticate: {request.redirectUrl}")
+```python
+session = composio.create(
+    user_id="your-user-id",
+    toolkits=["gmail", "github"] # optional, default is all toolkits
+)
+tools = session.tools()
 ```
+Read more about sessions and user management [here](https://docs.composio.dev/docs/configuring-sessions)
 </CodeGroup>
 
-3. Get Tools
+3. Authenticating users manually
 
-- Retrieving all the tools from an app (not recommended for production):
+Composio automatically authenticates the users during the agent chat session. However, you can also authenticate the user manually by calling the `authorize` method.
 ```python Code
-tools = toolset.get_tools(apps=[App.GITHUB])
+connection_request = session.authorize("github")
+print(f"Open this URL to authenticate: {connection_request.redirect_url}")
 ```
 
-- Filtering tools based on tags:
-```python Code
-tag = "users"
-
-filtered_action_enums = toolset.find_actions_by_tags(
-    App.GITHUB,
-    tags=[tag], 
-)
-
-tools = toolset.get_tools(actions=filtered_action_enums)
-```
-
-- Filtering tools based on use case:
-```python Code
-use_case = "Star a repository on GitHub"
-
-filtered_action_enums = toolset.find_actions_by_use_case(
-    App.GITHUB, use_case=use_case, advanced=False
-)
-
-tools = toolset.get_tools(actions=filtered_action_enums)
-```
-<Tip>Set `advanced` to True to get actions for complex use cases</Tip>
-
-- Using specific tools:
-
-In this demo, we will use the `GITHUB_STAR_A_REPOSITORY_FOR_THE_AUTHENTICATED_USER` action from the GitHub app.
-```python Code
-tools = toolset.get_tools(
-    actions=[Action.GITHUB_STAR_A_REPOSITORY_FOR_THE_AUTHENTICATED_USER]
-)
-```
-Learn more about filtering actions [here](https://docs.composio.dev/patterns/tools/use-tools/use-specific-actions)
-
 4. Define agent
 
 ```python Code
@@ -116,4 +85,4 @@ crew = Crew(agents=[crewai_agent], tasks=[task])
 crew.kickoff()
 ```
 
-* More detailed list of tools can be found [here](https://app.composio.dev)
+* More detailed list of tools can be found [here](https://docs.composio.dev/toolkits)

docs/en/tools/search-research/bravesearchtool.mdx

@@ -1,97 +1,316 @@
 ---
-title: Brave Search
-description: The `BraveSearchTool` is designed to search the internet using the Brave Search API.
+title: Brave Search Tools
+description: A suite of tools for querying the Brave Search API — covering web, news, image, and video search.
 icon: searchengin
 mode: "wide"
 ---
 
-# `BraveSearchTool`
+# Brave Search Tools
 
 ## Description
 
-This tool is designed to perform web searches using the Brave Search API. It allows you to search the internet with a specified query and retrieve relevant results. The tool supports customizable result counts and country-specific searches.
+CrewAI offers a family of Brave Search tools, each targeting a specific [Brave Search API](https://brave.com/search/api/) endpoint.
+Rather than a single catch-all tool, you can pick exactly the tool that matches the kind of results your agent needs:
+
+| Tool | Endpoint | Use case |
+| --- | --- | --- |
+| `BraveWebSearchTool` | Web Search | General web results, snippets, and URLs |
+| `BraveNewsSearchTool` | News Search | Recent news articles and headlines |
+| `BraveImageSearchTool` | Image Search | Image results with dimensions and source URLs |
+| `BraveVideoSearchTool` | Video Search | Video results from across the web |
+| `BraveLocalPOIsTool` | Local POIs | Find points of interest (e.g., restaurants) |
+| `BraveLocalPOIsDescriptionTool` | Local POIs | Retrieve AI-generated location descriptions |
+| `BraveLLMContextTool` | LLM Context | Pre-extracted web content optimized for AI agents, LLM grounding, and RAG pipelines. |
+
+All tools share a common base class (`BraveSearchToolBase`) that provides consistent behavior — rate limiting, automatic retries on `429` responses, header and parameter validation, and optional file saving.
+
+<Note>
+  The older `BraveSearchTool` class is still available for backwards compatibility, but it is considered **legacy** and will not receive the same level of attention going forward. We recommend migrating to the specific tools listed above, which offer richer configuration and a more focused interface.
+</Note>
+
+<Note>
+    While many tools (e.g., _BraveWebSearchTool_, _BraveNewsSearchTool_, _BraveImageSearchTool_, and _BraveVideoSearchTool_) can be used with a free Brave Search API subscription/plan, some parameters (e.g., `enable_snippets`) and tools (e.g., _BraveLocalPOIsTool_ and _BraveLocalPOIsDescriptionTool_) require a paid plan. Consult your subscription plan's capabilities for clarification.
+</Note>
 
 ## Installation
 
-To incorporate this tool into your project, follow the installation instructions below:
-
 ```shell
 pip install 'crewai[tools]'
 ```
 
-## Steps to Get Started
+## Getting Started
 
-To effectively use the `BraveSearchTool`, follow these steps:
+1. **Install the package** — confirm that `crewai[tools]` is installed in your Python environment.
+2. **Get an API key** — sign up at [api-dashboard.search.brave.com/login](https://api-dashboard.search.brave.com/login) to generate a key.
+3. **Set the environment variable** — store your key as `BRAVE_API_KEY`, or pass it directly via the `api_key` parameter.
 
-1. **Package Installation**: Confirm that the `crewai[tools]` package is installed in your Python environment.
-2. **API Key Acquisition**: Acquire a Brave Search API key at https://api.search.brave.com/app/keys (sign in to generate a key).
-3. **Environment Configuration**: Store your obtained API key in an environment variable named `BRAVE_API_KEY` to facilitate its use by the tool.
+## Quick Examples
 
-## Example
-
-The following example demonstrates how to initialize the tool and execute a search with a given query:
+### Web Search
 
 ```python Code
-from crewai_tools import BraveSearchTool
+from crewai_tools import BraveWebSearchTool
 
-# Initialize the tool for internet searching capabilities
-tool = BraveSearchTool()
-
-# Execute a search
-results = tool.run(search_query="CrewAI agent framework")
+tool = BraveWebSearchTool()
+results = tool.run(q="CrewAI agent framework")
 print(results)
 ```
 
-## Parameters
-
-The `BraveSearchTool` accepts the following parameters:
-
-- **search_query**: Mandatory. The search query you want to use to search the internet.
-- **country**: Optional. Specify the country for the search results. Default is empty string.
-- **n_results**: Optional. Number of search results to return. Default is `10`.
-- **save_file**: Optional. Whether to save the search results to a file. Default is `False`.
-
-## Example with Parameters
-
-Here is an example demonstrating how to use the tool with additional parameters:
+### News Search
 
 ```python Code
-from crewai_tools import BraveSearchTool
+from crewai_tools import BraveNewsSearchTool
 
-# Initialize the tool with custom parameters
-tool = BraveSearchTool(
-    country="US",
-    n_results=5,
-    save_file=True
+tool = BraveNewsSearchTool()
+results = tool.run(q="latest AI breakthroughs")
+print(results)
+```
+
+### Image Search
+
+```python Code
+from crewai_tools import BraveImageSearchTool
+
+tool = BraveImageSearchTool()
+results = tool.run(q="northern lights photography")
+print(results)
+```
+
+### Video Search
+
+```python Code
+from crewai_tools import BraveVideoSearchTool
+
+tool = BraveVideoSearchTool()
+results = tool.run(q="how to build AI agents")
+print(results)
+```
+
+### Location POI Descriptions
+
+```python Code
+from crewai_tools import (
+    BraveWebSearchTool,
+    BraveLocalPOIsDescriptionTool,
 )
 
-# Execute a search
-results = tool.run(search_query="Latest AI developments")
-print(results)
+web_search = BraveWebSearchTool(raw=True)
+poi_details = BraveLocalPOIsDescriptionTool()
+
+results = web_search.run(q="italian restaurants in pensacola, florida")
+
+if "locations" in results:
+    location_ids = [ loc["id"] for loc in results["locations"]["results"] ]
+    if location_ids:
+        descriptions = poi_details.run(ids=location_ids)
+        print(descriptions)
+```
+
+## Common Constructor Parameters
+
+Every Brave Search tool accepts the following parameters at initialization:
+
+| Parameter | Type | Default | Description |
+| --- | --- | --- | --- |
+| `api_key` | `str \| None` | `None` | Brave API key. Falls back to the `BRAVE_API_KEY` environment variable. |
+| `headers` | `dict \| None` | `None` | Additional HTTP headers to send with every request (e.g., `api-version`, geolocation headers). |
+| `requests_per_second` | `float` | `1.0` | Maximum request rate. The tool will sleep between calls to stay within this limit. |
+| `save_file` | `bool` | `False` | When `True`, each response is written to a timestamped `.txt` file. |
+| `raw` | `bool` | `False` | When `True`, the full API JSON response is returned without any refinement. |
+| `timeout` | `int` | `30` | HTTP request timeout in seconds. |
+| `country` | `str \| None` | `None` | Legacy shorthand for geo-targeting (e.g., `"US"`). Prefer using the `country` query parameter directly. |
+| `n_results` | `int` | `10` | Legacy shorthand for result count. Prefer using the `count` query parameter directly. |
+
+<Warning>
+  The `country` and `n_results` constructor parameters exist for backwards compatibility. They are applied as defaults when the corresponding query parameters (`country`, `count`) are not provided at call time. For new code, we recommend passing `country` and `count` directly as query parameters instead.
+</Warning>
+
+## Query Parameters
+
+Each tool validates its query parameters against a Pydantic schema before sending the request.
+The parameters vary slightly per endpoint — here is a summary of the most commonly used ones:
+
+### BraveWebSearchTool
+
+| Parameter | Description |
+| --- | --- |
+| `q` | **(required)** Search query string (max 400 chars). |
+| `country` | Two-letter country code for geo-targeting (e.g., `"US"`). |
+| `search_lang` | Two-letter language code for results (e.g., `"en"`). |
+| `count` | Max number of results to return (1–20). |
+| `offset` | Skip the first N pages of results (0–9). |
+| `safesearch` | Content filter: `"off"`, `"moderate"`, or `"strict"`. |
+| `freshness` | Recency filter: `"pd"` (past day), `"pw"` (past week), `"pm"` (past month), `"py"` (past year), or a date range like `"2025-01-01to2025-06-01"`. |
+| `extra_snippets` | Include up to 5 additional text snippets per result. |
+| `goggles` | Brave Goggles URL(s) and/or source for custom re-ranking. |
+
+For the complete parameter and header reference, see the [Brave Web Search API documentation](https://api-dashboard.search.brave.com/api-reference/web/search/get).
+
+### BraveNewsSearchTool
+
+| Parameter | Description |
+| --- | --- |
+| `q` | **(required)** Search query string (max 400 chars). |
+| `country` | Two-letter country code for geo-targeting. |
+| `search_lang` | Two-letter language code for results. |
+| `count` | Max number of results to return (1–50). |
+| `offset` | Skip the first N pages of results (0–9). |
+| `safesearch` | Content filter: `"off"`, `"moderate"`, or `"strict"`. |
+| `freshness` | Recency filter (same options as Web Search). |
+| `goggles` | Brave Goggles URL(s) and/or source for custom re-ranking. |
+
+For the complete parameter and header reference, see the [Brave News Search API documentation](https://api-dashboard.search.brave.com/api-reference/news/news_search/get).
+
+### BraveImageSearchTool
+
+| Parameter | Description |
+| --- | --- |
+| `q` | **(required)** Search query string (max 400 chars). |
+| `country` | Two-letter country code for geo-targeting. |
+| `search_lang` | Two-letter language code for results. |
+| `count` | Max number of results to return (1–200). |
+| `safesearch` | Content filter: `"off"` or `"strict"`. |
+| `spellcheck` | Attempt to correct spelling errors in the query. |
+
+For the complete parameter and header reference, see the [Brave Image Search API documentation](https://api-dashboard.search.brave.com/api-reference/images/image_search).
+
+### BraveVideoSearchTool
+
+| Parameter | Description |
+| --- | --- |
+| `q` | **(required)** Search query string (max 400 chars). |
+| `country` | Two-letter country code for geo-targeting. |
+| `search_lang` | Two-letter language code for results. |
+| `count` | Max number of results to return (1–50). |
+| `offset` | Skip the first N pages of results (0–9). |
+| `safesearch` | Content filter: `"off"`, `"moderate"`, or `"strict"`. |
+| `freshness` | Recency filter (same options as Web Search). |
+
+For the complete parameter and header reference, see the [Brave Video Search API documentation](https://api-dashboard.search.brave.com/api-reference/videos/video_search/get).
+
+### BraveLocalPOIsTool
+
+| Parameter | Description |
+| --- | --- |
+| `ids` | **(required)** A list of unique identifiers for the desired locations. |
+| `search_lang` | Two-letter language code for results. |
+
+For the complete parameter and header reference, see [Brave Local POIs API documentation](https://api-dashboard.search.brave.com/api-reference/web/local_pois).
+
+### BraveLocalPOIsDescriptionTool
+
+| Parameter | Description |
+| --- | --- |
+| `ids` | **(required)** A list of unique identifiers for the desired locations. |
+
+For the complete parameter and header reference, see [Brave POI Descriptions API documentation](https://api-dashboard.search.brave.com/api-reference/web/poi_descriptions).
+
+## Custom Headers
+
+All tools support custom HTTP request headers. The Web Search tool, for example, accepts geolocation headers for location-aware results:
+
+```python Code
+from crewai_tools import BraveWebSearchTool
+
+tool = BraveWebSearchTool(
+    headers={
+        "x-loc-lat": "37.7749",
+        "x-loc-long": "-122.4194",
+        "x-loc-city": "San Francisco",
+        "x-loc-state": "CA",
+        "x-loc-country": "US",
+    }
+)
+
+results = tool.run(q="best coffee shops nearby")
+```
+
+You can also update headers after initialization using the `set_headers()` method:
+
+```python Code
+tool.set_headers({"api-version": "2025-01-01"})
+```
+
+## Raw Mode
+
+By default, each tool refines the API response into a concise list of results. If you need the full, unprocessed API response, enable raw mode:
+
+```python Code
+from crewai_tools import BraveWebSearchTool
+
+tool = BraveWebSearchTool(raw=True)
+full_response = tool.run(q="Brave Search API")
 ```
 
 ## Agent Integration Example
 
-Here's how to integrate the `BraveSearchTool` with a CrewAI agent:
+Here's how to equip a CrewAI agent with multiple Brave Search tools:
 
 ```python Code
 from crewai import Agent
 from crewai.project import agent
-from crewai_tools import BraveSearchTool
+from crewai_tools import BraveWebSearchTool, BraveNewsSearchTool
 
-# Initialize the tool
-brave_search_tool = BraveSearchTool()
+web_search = BraveWebSearchTool()
+news_search = BraveNewsSearchTool()
 
-# Define an agent with the BraveSearchTool
 @agent
 def researcher(self) -> Agent:
     return Agent(
         config=self.agents_config["researcher"],
-        allow_delegation=False,
-        tools=[brave_search_tool]
+        tools=[web_search, news_search],
     )
 ```
 
+## Advanced Example
+
+Combining multiple parameters for a targeted search:
+
+```python Code
+from crewai_tools import BraveWebSearchTool
+
+tool = BraveWebSearchTool(
+    requests_per_second=0.5,  # conservative rate limit
+    save_file=True,
+)
+
+results = tool.run(
+    q="artificial intelligence news",
+    country="US",
+    search_lang="en",
+    count=5,
+    freshness="pm",           # past month only
+    extra_snippets=True,
+)
+print(results)
+```
+
+## Migrating from `BraveSearchTool` (Legacy)
+
+If you are currently using `BraveSearchTool`, switching to the new tools is straightforward:
+
+```python Code
+# Before (legacy)
+from crewai_tools import BraveSearchTool
+
+tool = BraveSearchTool(country="US", n_results=5, save_file=True)
+results = tool.run(search_query="AI agents")
+
+# After (recommended)
+from crewai_tools import BraveWebSearchTool
+
+tool = BraveWebSearchTool(save_file=True)
+results = tool.run(q="AI agents", country="US", count=5)
+```
+
+Key differences:
+- **Import**: Use `BraveWebSearchTool` (or the news/image/video variant) instead of `BraveSearchTool`.
+- **Query parameter**: Use `q` instead of `search_query`. (Both `search_query` and `query` are still accepted for convenience, but `q` is the preferred parameter.)
+- **Result count**: Pass `count` as a query parameter instead of `n_results` at init time.
+- **Country**: Pass `country` as a query parameter instead of at init time.
+- **API key**: Can now be passed directly via `api_key=` in addition to the `BRAVE_API_KEY` environment variable.
+- **Rate limiting**: Configurable via `requests_per_second` with automatic retry on `429` responses.
+
 ## Conclusion
 
-By integrating the `BraveSearchTool` into Python projects, users gain the ability to conduct real-time, relevant searches across the internet directly from their applications. The tool provides a simple interface to the powerful Brave Search API, making it easy to retrieve and process search results programmatically. By adhering to the setup and usage guidelines provided, incorporating this tool into projects is streamlined and straightforward. 
+The Brave Search tool suite gives your CrewAI agents flexible, endpoint-specific access to the Brave Search API. Whether you need web pages, breaking news, images, or videos, there is a dedicated tool with validated parameters and built-in resilience. Pick the tool that fits your use case, and refer to the [Brave Search API documentation](https://brave.com/search/api/) for the full details on available parameters and response formats.

docs/ko/changelog.mdx

@@ -4,6 +4,237 @@ description: "CrewAI의 제품 업데이트, 개선 사항 및 버그 수정"
 icon: "clock"
 mode: "wide"
 ---
+<Update label="2026년 3월 15일">
+  ## v1.11.0rc1
+
+  [GitHub 릴리스 보기](https://github.com/crewAIInc/crewAI/releases/tag/1.11.0rc1)
+
+  ## 변경 사항
+
+  ### 기능
+  - Plus API 토큰 인증 추가
+  - 에서 계획 실행 패턴 구현
+
+  ### 버그 수정
+  - 코드 인터프리터 샌드박스 탈출 문제 해결
+
+  ### 문서
+  - v1.10.2rc2의 변경 로그 및 버전 업데이트
+
+  ## 기여자
+
+  @Copilot, @greysonlalonde, @lorenzejay, @theCyberTech
+
+</Update>
+
+<Update label="2026년 3월 14일">
+  ## v1.10.2rc2
+
+  [GitHub 릴리스 보기](https://github.com/crewAIInc/crewAI/releases/tag/1.10.2rc2)
+
+  ## 변경 사항
+
+  ### 버그 수정
+  - 읽기 전용 스토리지 작업에서 독점 잠금 제거
+
+  ### 문서
+  - v1.10.2rc1에 대한 변경 로그 및 버전 업데이트
+
+  ## 기여자
+
+  @greysonlalonde
+
+</Update>
+
+<Update label="2026년 3월 13일">
+  ## v1.10.2rc1
+
+  [GitHub 릴리스 보기](https://github.com/crewAIInc/crewAI/releases/tag/1.10.2rc1)
+
+  ## 변경 사항
+
+  ### 기능
+  - 릴리스 명령 추가 및 PyPI 게시 트리거
+
+  ### 버그 수정
+  - 보호되지 않은 I/O에 대한 프로세스 간 및 스레드 안전 잠금 수정
+  - 모든 스레드 및 실행기 경계를 넘는 contextvars 전파
+  - async 작업 스레드로 ContextVars 전파
+
+  ### 문서
+  - v1.10.2a1에 대한 변경 로그 및 버전 업데이트
+
+  ## 기여자
+
+  @danglies007, @greysonlalonde
+
+</Update>
+
+<Update label="2026년 3월 11일">
+  ## v1.10.2a1
+
+  [GitHub 릴리스 보기](https://github.com/crewAIInc/crewAI/releases/tag/1.10.2a1)
+
+  ## 변경 사항
+
+  ### 기능
+  - Anthropics에 대한 도구 검색 지원 추가, 토큰 저장, 실행 중 적절한 도구를 동적으로 주입하는 기능 추가.
+  - 더 많은 Brave Search 도구 도입.
+  - 야간 릴리스를 위한 액션 생성.
+
+  ### 버그 수정
+  - 동시 다중 프로세스 실행 중 LockException 수정.
+  - 단일 사용자 메시지에서 병렬 도구 결과 그룹화 문제 해결.
+  - MCP 도구 해상도 문제 해결 및 모든 공유 가변 연결 제거.
+  - human_feedback 함수에서 LLM 매개변수 처리 업데이트.
+  - LockedListProxy 및 LockedDictProxy에 누락된 list/dict 메서드 추가.
+  - 병렬 도구 호출 스레드에 contextvars 컨텍스트 전파.
+  - CVE 경로 탐색 취약점을 해결하기 위해 gitpython 의존성을 >=3.1.41로 업데이트.
+
+  ### 리팩토링
+  - 메모리 클래스를 직렬화 가능하도록 리팩토링.
+
+  ### 문서
+  - v1.10.1에 대한 변경 로그 및 버전 업데이트.
+
+  ## 기여자
+
+  @akaKuruma, @github-actions[bot], @giulio-leone, @greysonlalonde, @joaomdmoura, @jonathansampson, @lorenzejay, @lucasgomide, @mattatcha
+
+</Update>
+
+<Update label="2026년 3월 4일">
+  ## v1.10.1
+
+  [GitHub 릴리스 보기](https://github.com/crewAIInc/crewAI/releases/tag/1.10.1)
+
+  ## 변경 사항
+
+  ### 기능
+  - Gemini GenAI 업그레이드
+
+  ### 버그 수정
+  - 재귀를 피하기 위해 실행기 리스너 값을 조정
+  - Gemini에서 병렬 함수 응답 부분을 단일 Content 객체로 그룹화
+  - Gemini에서 사고 모델의 사고 출력을 표시
+  - 에이전트 도구가 None일 때 MCP 및 플랫폼 도구 로드
+  - A2A에서 실행 이벤트 루프가 있는 Jupyter 환경 지원
+  - 일시적인 추적을 위해 익명 ID 사용
+  - 조건부로 플러스 헤더 전달
+  - 원격 측정을 위해 비주 스레드에서 신호 처리기 등록 건너뛰기
+  - 도구 오류를 관찰로 주입하고 이름 충돌 해결
+  - Dependabot 경고를 해결하기 위해 pypdf를 4.x에서 6.7.4로 업그레이드
+  - 심각 및 높은 Dependabot 보안 경고 해결
+
+  ### 문서
+  - Composio 도구 문서를 지역별로 동기화
+
+  ## 기여자
+
+  @giulio-leone, @greysonlalonde, @haxzie, @joaomdmoura, @lorenzejay, @mattatcha, @mplachta, @nicoferdi96
+
+</Update>
+
+<Update label="2026년 2월 27일">
+  ## v1.10.1a1
+
+  [GitHub 릴리스 보기](https://github.com/crewAIInc/crewAI/releases/tag/1.10.1a1)
+
+  ## 변경 사항
+
+  ### 기능
+  - 단계 콜백 메서드에서 비동기 호출 지원 구현
+  - 메모리 모듈의 무거운 의존성에 대한 지연 로딩 구현
+
+  ### 문서
+  - v1.10.0에 대한 변경 로그 및 버전 업데이트
+
+  ### 리팩토링
+  - 비동기 호출을 지원하기 위해 단계 콜백 메서드 리팩토링
+  - 메모리 모듈의 무거운 의존성에 대한 지연 로딩을 구현하기 위해 리팩토링
+
+  ### 버그 수정
+  - 릴리스 노트의 분기 수정
+
+  ## 기여자
+
+  @greysonlalonde, @joaomdmoura
+
+</Update>
+
+<Update label="2026년 2월 27일">
+  ## v1.10.1a1
+
+  [GitHub 릴리스 보기](https://github.com/crewAIInc/crewAI/releases/tag/1.10.1a1)
+
+  ## 변경 사항
+
+  ### 리팩토링
+  - 비동기 호출을 지원하기 위해 단계 콜백 메서드 리팩토링
+  - 메모리 모듈의 무거운 의존성에 대해 지연 로딩 구현
+
+  ### 문서화
+  - v1.10.0에 대한 변경 로그 및 버전 업데이트
+
+  ### 버그 수정
+  - 릴리스 노트를 위한 브랜치 생성
+
+  ## 기여자
+
+  @greysonlalonde, @joaomdmoura
+
+</Update>
+
+<Update label="2026년 2월 26일">
+  ## v1.10.0
+
+  [GitHub 릴리스 보기](https://github.com/crewAIInc/crewAI/releases/tag/1.10.0)
+
+  ## 변경 사항
+
+  ### 기능
+  - MCP 도구 해상도 및 관련 이벤트 개선
+  - lancedb 버전 업데이트 및 lance-namespace 패키지 추가
+  - CrewAgentExecutor 및 BaseTool에서 JSON 인수 파싱 및 검증 개선
+  - CLI HTTP 클라이언트를 requests에서 httpx로 마이그레이션
+  - 버전화된 문서 추가
+  - 버전 노트에 대한 yanked 감지 추가
+  - Flows에서 사용자 입력 처리 구현
+  - 인간 피드백 통합 테스트에서 HITL 자기 루프 기능 개선
+  - eventbus에 started_event_id 추가 및 설정
+  - tools.specs 자동 업데이트
+
+  ### 버그 수정
+  - 빈 경우에도 도구 kwargs를 검증하여 모호한 TypeError 방지
+  - LLM을 위한 도구 매개변수 스키마에서 null 타입 유지
+  - output_pydantic/output_json을 네이티브 구조화된 출력으로 매핑
+  - 약속이 있는 경우 콜백이 실행/대기되도록 보장
+  - 예외 컨텍스트에서 메서드 이름 캡처
+  - 라우터 결과에서 enum 타입 유지; 타입 개선
+  - 입력으로 지속성 ID가 전달될 때 조용히 깨지는 순환 흐름 수정
+  - CLI 플래그 형식을 --skip-provider에서 --skip_provider로 수정
+  - OpenAI 도구 호출 스트림이 완료되도록 보장
+  - MCP 도구에서 복잡한 스키마 $ref 포인터 해결
+  - 스키마에서 additionalProperties=false 강제 적용
+  - 크루 폴더에 대해 예약된 스크립트 이름 거부
+  - 가드레일 이벤트 방출 테스트에서 경쟁 조건 해결
+
+  ### 문서
+  - 비네이티브 LLM 공급자를 위한 litellm 종속성 노트 추가
+  - NL2SQL 보안 모델 및 강화 지침 명확화
+  - 9개 통합에서 96개의 누락된 작업 추가
+
+  ### 리팩토링
+  - crew를 provider로 리팩토링
+  - HITL을 provider 패턴으로 추출
+  - 훅 타이핑 및 등록 개선
+
+  ## 기여자
+
+  @dependabot[bot], @github-actions[bot], @github-code-quality[bot], @greysonlalonde, @heitorado, @hobostay, @joaomdmoura, @johnvan7, @jonathansampson, @lorenzejay, @lucasgomide, @mattatcha, @mplachta, @nicoferdi96, @theCyberTech, @thiagomoretto, @vinibrsl
+
+</Update>
+
 <Update label="2026년 1월 26일">
   ## v1.9.0
 

docs/ko/guides/migration/migrating-from-langgraph.mdx

@@ -0,0 +1,518 @@
+---
+title: "LangGraph에서 CrewAI로 옮기기: 엔지니어를 위한 실전 가이드"
+description: LangGraph로 이미 구축했다면, 프로젝트를 CrewAI로 빠르게 옮기는 방법을 알아보세요
+icon: switch
+mode: "wide"
+---
+
+LangGraph로 에이전트를 구축해 왔습니다. `StateGraph`와 씨름하고, 조건부 에지를 연결하고, 새벽 2시에 상태 딕셔너리를 디버깅해 본 적도 있죠. 동작은 하지만 — 어느 순간부터 프로덕션으로 가는 더 나은 길이 없을까 고민하게 됩니다.
+
+있습니다. **CrewAI Flows**는 이벤트 기반 오케스트레이션, 조건부 라우팅, 공유 상태라는 동일한 힘을 훨씬 적은 보일러플레이트와 실제로 다단계 AI 워크플로우를 생각하는 방식에 잘 맞는 정신적 모델로 제공합니다.
+
+이 글은 핵심 개념을 나란히 비교하고 실제 코드 비교를 보여주며, 다음으로 손이 갈 프레임워크가 왜 CrewAI Flows인지 설명합니다.
+
+---
+
+## 정신적 모델의 전환
+
+LangGraph는 **그래프**로 생각하라고 요구합니다: 노드, 에지, 그리고 상태 딕셔너리. 모든 워크플로우는 계산 단계 사이의 전이를 명시적으로 연결하는 방향 그래프입니다. 강력하지만, 특히 워크플로우가 몇 개의 결정 지점이 있는 순차적 흐름일 때 이 추상화는 오버헤드를 가져옵니다.
+
+CrewAI Flows는 **이벤트**로 생각하라고 요구합니다: 시작하는 메서드, 결과를 듣는 메서드, 실행을 라우팅하는 메서드. 워크플로우의 토폴로지는 명시적 그래프 구성 대신 데코레이터 어노테이션에서 드러납니다. 이것은 단순한 문법 설탕이 아니라 — 파이프라인을 설계하고 읽고 유지하는 방식을 바꿉니다.
+
+핵심 매핑은 다음과 같습니다:
+
+| LangGraph 개념 | CrewAI Flows 대응 |
+| --- | --- |
+| `StateGraph` class | `Flow` class |
+| `add_node()` | Methods decorated with `@start`, `@listen` |
+| `add_edge()` / `add_conditional_edges()` | `@listen()` / `@router()` decorators |
+| `TypedDict` state | Pydantic `BaseModel` state |
+| `START` / `END` constants | `@start()` decorator / natural method return |
+| `graph.compile()` | `flow.kickoff()` |
+| Checkpointer / persistence | Built-in memory (LanceDB-backed) |
+
+실제로 어떻게 보이는지 살펴보겠습니다.
+
+---
+
+## 데모 1: 간단한 순차 파이프라인
+
+주제를 받아 조사하고, 요약을 작성한 뒤, 결과를 포맷팅하는 파이프라인을 만든다고 해봅시다. 각 프레임워크는 이렇게 처리합니다.
+
+### LangGraph 방식
+
+```python
+from typing import TypedDict
+from langgraph.graph import StateGraph, START, END
+
+class ResearchState(TypedDict):
+    topic: str
+    raw_research: str
+    summary: str
+    formatted_output: str
+
+def research_topic(state: ResearchState) -> dict:
+    # Call an LLM or search API
+    result = llm.invoke(f"Research the topic: {state['topic']}")
+    return {"raw_research": result}
+
+def write_summary(state: ResearchState) -> dict:
+    result = llm.invoke(
+        f"Summarize this research:\n{state['raw_research']}"
+    )
+    return {"summary": result}
+
+def format_output(state: ResearchState) -> dict:
+    result = llm.invoke(
+        f"Format this summary as a polished article section:\n{state['summary']}"
+    )
+    return {"formatted_output": result}
+
+# Build the graph
+graph = StateGraph(ResearchState)
+graph.add_node("research", research_topic)
+graph.add_node("summarize", write_summary)
+graph.add_node("format", format_output)
+
+graph.add_edge(START, "research")
+graph.add_edge("research", "summarize")
+graph.add_edge("summarize", "format")
+graph.add_edge("format", END)
+
+# Compile and run
+app = graph.compile()
+result = app.invoke({"topic": "quantum computing advances in 2026"})
+print(result["formatted_output"])
+```
+
+함수를 정의하고 노드로 등록한 다음, 모든 전이를 수동으로 연결합니다. 이렇게 단순한 순서인데도 의례처럼 해야 할 작업이 많습니다.
+
+### CrewAI Flows 방식
+
+```python
+from crewai import LLM, Agent, Crew, Process, Task
+from crewai.flow.flow import Flow, listen, start
+from pydantic import BaseModel
+
+llm = LLM(model="openai/gpt-5.2")
+
+class ResearchState(BaseModel):
+    topic: str = ""
+    raw_research: str = ""
+    summary: str = ""
+    formatted_output: str = ""
+
+class ResearchFlow(Flow[ResearchState]):
+    @start()
+    def research_topic(self):
+        # Option 1: Direct LLM call
+        result = llm.call(f"Research the topic: {self.state.topic}")
+        self.state.raw_research = result
+        return result
+
+    @listen(research_topic)
+    def write_summary(self, research_output):
+        # Option 2: A single agent
+        summarizer = Agent(
+            role="Research Summarizer",
+            goal="Produce concise, accurate summaries of research content",
+            backstory="You are an expert at distilling complex research into clear, "
+            "digestible summaries.",
+            llm=llm,
+            verbose=True,
+        )
+        result = summarizer.kickoff(
+            f"Summarize this research:\n{self.state.raw_research}"
+        )
+        self.state.summary = str(result)
+        return self.state.summary
+
+    @listen(write_summary)
+    def format_output(self, summary_output):
+        # Option 3: a complete crew (with one or more agents)
+        formatter = Agent(
+            role="Content Formatter",
+            goal="Transform research summaries into polished, publication-ready article sections",
+            backstory="You are a skilled editor with expertise in structuring and "
+            "presenting technical content for a general audience.",
+            llm=llm,
+            verbose=True,
+        )
+        format_task = Task(
+            description=f"Format this summary as a polished article section:\n{self.state.summary}",
+            expected_output="A well-structured, polished article section ready for publication.",
+            agent=formatter,
+        )
+        crew = Crew(
+            agents=[formatter],
+            tasks=[format_task],
+            process=Process.sequential,
+            verbose=True,
+        )
+        result = crew.kickoff()
+        self.state.formatted_output = str(result)
+        return self.state.formatted_output
+
+# Run the flow
+flow = ResearchFlow()
+flow.state.topic = "quantum computing advances in 2026"
+result = flow.kickoff()
+print(flow.state.formatted_output)
+
+```
+
+눈에 띄는 차이점이 있습니다: 그래프 구성 없음, 에지 연결 없음, 컴파일 단계 없음. 실행 순서는 로직이 있는 곳에서 바로 선언됩니다. `@start()`는 진입점을 표시하고, `@listen(method_name)`은 단계들을 연결합니다. 상태는 타입 안전성, 검증, IDE 자동 완성까지 제공하는 제대로 된 Pydantic 모델입니다.
+
+---
+
+## 데모 2: 조건부 라우팅
+
+여기서 흥미로워집니다. 콘텐츠 유형에 따라 서로 다른 처리 경로로 라우팅하는 파이프라인을 만든다고 해봅시다.
+
+### LangGraph 방식
+
+```python
+from typing import TypedDict, Literal
+from langgraph.graph import StateGraph, START, END
+
+class ContentState(TypedDict):
+    input_text: str
+    content_type: str
+    result: str
+
+def classify_content(state: ContentState) -> dict:
+    content_type = llm.invoke(
+        f"Classify this content as 'technical', 'creative', or 'business':\n{state['input_text']}"
+    )
+    return {"content_type": content_type.strip().lower()}
+
+def process_technical(state: ContentState) -> dict:
+    result = llm.invoke(f"Process as technical doc:\n{state['input_text']}")
+    return {"result": result}
+
+def process_creative(state: ContentState) -> dict:
+    result = llm.invoke(f"Process as creative writing:\n{state['input_text']}")
+    return {"result": result}
+
+def process_business(state: ContentState) -> dict:
+    result = llm.invoke(f"Process as business content:\n{state['input_text']}")
+    return {"result": result}
+
+# Routing function
+def route_content(state: ContentState) -> Literal["technical", "creative", "business"]:
+    return state["content_type"]
+
+# Build the graph
+graph = StateGraph(ContentState)
+graph.add_node("classify", classify_content)
+graph.add_node("technical", process_technical)
+graph.add_node("creative", process_creative)
+graph.add_node("business", process_business)
+
+graph.add_edge(START, "classify")
+graph.add_conditional_edges(
+    "classify",
+    route_content,
+    {
+        "technical": "technical",
+        "creative": "creative",
+        "business": "business",
+    }
+)
+graph.add_edge("technical", END)
+graph.add_edge("creative", END)
+graph.add_edge("business", END)
+
+app = graph.compile()
+result = app.invoke({"input_text": "Explain how TCP handshakes work"})
+```
+
+별도의 라우팅 함수, 명시적 조건부 에지 매핑, 그리고 모든 분기에 대한 종료 에지가 필요합니다. 라우팅 결정 로직이 그 결정을 만들어 내는 노드와 분리됩니다.
+
+### CrewAI Flows 방식
+
+```python
+from crewai import LLM, Agent
+from crewai.flow.flow import Flow, listen, router, start
+from pydantic import BaseModel
+
+llm = LLM(model="openai/gpt-5.2")
+
+class ContentState(BaseModel):
+    input_text: str = ""
+    content_type: str = ""
+    result: str = ""
+
+class ContentFlow(Flow[ContentState]):
+    @start()
+    def classify_content(self):
+        self.state.content_type = (
+            llm.call(
+                f"Classify this content as 'technical', 'creative', or 'business':\n"
+                f"{self.state.input_text}"
+            )
+            .strip()
+            .lower()
+        )
+        return self.state.content_type
+
+    @router(classify_content)
+    def route_content(self, classification):
+        if classification == "technical":
+            return "process_technical"
+        elif classification == "creative":
+            return "process_creative"
+        else:
+            return "process_business"
+
+    @listen("process_technical")
+    def handle_technical(self):
+        agent = Agent(
+            role="Technical Writer",
+            goal="Produce clear, accurate technical documentation",
+            backstory="You are an expert technical writer who specializes in "
+            "explaining complex technical concepts precisely.",
+            llm=llm,
+            verbose=True,
+        )
+        self.state.result = str(
+            agent.kickoff(f"Process as technical doc:\n{self.state.input_text}")
+        )
+
+    @listen("process_creative")
+    def handle_creative(self):
+        agent = Agent(
+            role="Creative Writer",
+            goal="Craft engaging and imaginative creative content",
+            backstory="You are a talented creative writer with a flair for "
+            "compelling storytelling and vivid expression.",
+            llm=llm,
+            verbose=True,
+        )
+        self.state.result = str(
+            agent.kickoff(f"Process as creative writing:\n{self.state.input_text}")
+        )
+
+    @listen("process_business")
+    def handle_business(self):
+        agent = Agent(
+            role="Business Writer",
+            goal="Produce professional, results-oriented business content",
+            backstory="You are an experienced business writer who communicates "
+            "strategy and value clearly to professional audiences.",
+            llm=llm,
+            verbose=True,
+        )
+        self.state.result = str(
+            agent.kickoff(f"Process as business content:\n{self.state.input_text}")
+        )
+
+flow = ContentFlow()
+flow.state.input_text = "Explain how TCP handshakes work"
+flow.kickoff()
+print(flow.state.result)
+
+```
+
+`@router()` 데코레이터는 메서드를 결정 지점으로 만듭니다. 리스너와 매칭되는 문자열을 반환하므로, 매핑 딕셔너리도, 별도의 라우팅 함수도 필요 없습니다. 분기 로직이 Python `if` 문처럼 읽히는 이유는, 실제로 `if` 문이기 때문입니다.
+
+---
+
+## 데모 3: AI 에이전트 Crew를 Flow에 통합하기
+
+여기서 CrewAI의 진짜 힘이 드러납니다. Flows는 LLM 호출을 연결하는 것에 그치지 않고 자율적인 에이전트 **Crew** 전체를 오케스트레이션합니다. 이는 LangGraph에 기본으로 대응되는 개념이 없습니다.
+
+```python
+from crewai import Agent, Task, Crew
+from crewai.flow.flow import Flow, listen, start
+from pydantic import BaseModel
+
+class ArticleState(BaseModel):
+    topic: str = ""
+    research: str = ""
+    draft: str = ""
+    final_article: str = ""
+
+class ArticleFlow(Flow[ArticleState]):
+
+    @start()
+    def run_research_crew(self):
+        """A full Crew of agents handles research."""
+        researcher = Agent(
+            role="Senior Research Analyst",
+            goal=f"Produce comprehensive research on: {self.state.topic}",
+            backstory="You're a veteran analyst known for thorough, "
+                       "well-sourced research reports.",
+            llm="gpt-4o"
+        )
+
+        research_task = Task(
+            description=f"Research '{self.state.topic}' thoroughly. "
+                        "Cover key trends, data points, and expert opinions.",
+            expected_output="A detailed research brief with sources.",
+            agent=researcher
+        )
+
+        crew = Crew(agents=[researcher], tasks=[research_task])
+        result = crew.kickoff()
+        self.state.research = result.raw
+        return result.raw
+
+    @listen(run_research_crew)
+    def run_writing_crew(self, research_output):
+        """A different Crew handles writing."""
+        writer = Agent(
+            role="Technical Writer",
+            goal="Write a compelling article based on provided research.",
+            backstory="You turn complex research into engaging, clear prose.",
+            llm="gpt-4o"
+        )
+
+        editor = Agent(
+            role="Senior Editor",
+            goal="Review and polish articles for publication quality.",
+            backstory="20 years of editorial experience at top tech publications.",
+            llm="gpt-4o"
+        )
+
+        write_task = Task(
+            description=f"Write an article based on this research:\n{self.state.research}",
+            expected_output="A well-structured draft article.",
+            agent=writer
+        )
+
+        edit_task = Task(
+            description="Review, fact-check, and polish the draft article.",
+            expected_output="A publication-ready article.",
+            agent=editor
+        )
+
+        crew = Crew(agents=[writer, editor], tasks=[write_task, edit_task])
+        result = crew.kickoff()
+        self.state.final_article = result.raw
+        return result.raw
+
+# Run the full pipeline
+flow = ArticleFlow()
+flow.state.topic = "The Future of Edge AI"
+flow.kickoff()
+print(flow.state.final_article)
+```
+
+핵심 인사이트는 다음과 같습니다: **Flows는 오케스트레이션 레이어를, Crews는 지능 레이어를 제공합니다.** Flow의 각 단계는 각자의 역할, 목표, 도구를 가진 협업 에이전트 팀을 띄울 수 있습니다. 구조화되고 예측 가능한 제어 흐름 *그리고* 자율적 에이전트 협업 — 두 세계의 장점을 모두 얻습니다.
+
+LangGraph에서 비슷한 것을 하려면 노드 함수 안에 에이전트 통신 프로토콜, 도구 호출 루프, 위임 로직을 직접 구현해야 합니다. 가능하긴 하지만, 매번 처음부터 배관을 만드는 셈입니다.
+
+---
+
+## 데모 4: 병렬 실행과 동기화
+
+실제 파이프라인은 종종 작업을 병렬로 분기하고 결과를 합쳐야 합니다. CrewAI Flows는 `and_`와 `or_` 연산자로 이를 우아하게 처리합니다.
+
+```python
+from crewai import LLM
+from crewai.flow.flow import Flow, and_, listen, start
+from pydantic import BaseModel
+
+llm = LLM(model="openai/gpt-5.2")
+
+class AnalysisState(BaseModel):
+    topic: str = ""
+    market_data: str = ""
+    tech_analysis: str = ""
+    competitor_intel: str = ""
+    final_report: str = ""
+
+class ParallelAnalysisFlow(Flow[AnalysisState]):
+    @start()
+    def start_method(self):
+        pass
+
+    @listen(start_method)
+    def gather_market_data(self):
+        # Your agentic or deterministic code
+        pass
+
+    @listen(start_method)
+    def run_tech_analysis(self):
+        # Your agentic or deterministic code
+        pass
+
+    @listen(start_method)
+    def gather_competitor_intel(self):
+        # Your agentic or deterministic code
+        pass
+
+    @listen(and_(gather_market_data, run_tech_analysis, gather_competitor_intel))
+    def synthesize_report(self):
+        # Your agentic or deterministic code
+        pass
+
+flow = ParallelAnalysisFlow()
+flow.state.topic = "AI-powered developer tools"
+flow.kickoff()
+
+```
+
+여러 `@start()` 데코레이터는 병렬로 실행됩니다. `@listen` 데코레이터의 `and_()` 결합자는 `synthesize_report`가 *세 가지* 상위 메서드가 모두 완료된 뒤에만 실행되도록 보장합니다. *어떤* 상위 작업이든 끝나는 즉시 진행하고 싶다면 `or_()`도 사용할 수 있습니다.
+
+LangGraph에서는 병렬 분기, 동기화 노드, 신중한 상태 병합이 포함된 fan-out/fan-in 패턴을 만들어야 하며 — 모든 것을 에지로 명시적으로 연결해야 합니다.
+
+---
+
+## 프로덕션에서 CrewAI Flows를 쓰는 이유
+
+깔끔한 문법을 넘어, Flows는 여러 프로덕션 핵심 이점을 제공합니다:
+
+**내장 상태 지속성.** Flow 상태는 LanceDB에 의해 백업되므로 워크플로우가 크래시에서 살아남고, 재개될 수 있으며, 실행 간에 지식을 축적할 수 있습니다. LangGraph는 별도의 체크포인터를 구성해야 합니다.
+
+**타입 안전한 상태 관리.** Pydantic 모델은 즉시 검증, 직렬화, IDE 지원을 제공합니다. LangGraph의 `TypedDict` 상태는 런타임 검증을 하지 않습니다.
+
+**일급 에이전트 오케스트레이션.** Crews는 기본 프리미티브입니다. 역할, 목표, 배경, 도구를 가진 에이전트를 정의하고, Flow의 구조적 틀 안에서 자율적으로 협업하게 합니다. 다중 에이전트 조율을 다시 만들 필요가 없습니다.
+
+**더 단순한 정신적 모델.** 데코레이터는 의도를 선언합니다. `@start`는 "여기서 시작", `@listen(x)`는 "x 이후 실행", `@router(x)`는 "x 이후 어디로 갈지 결정"을 의미합니다. 코드는 자신이 설명하는 워크플로우처럼 읽힙니다.
+
+**CLI 통합.** `crewai run`으로 Flows를 실행합니다. 별도의 컴파일 단계나 그래프 직렬화가 없습니다. Flow는 Python 클래스이며, 그대로 실행됩니다.
+
+---
+
+## 마이그레이션 치트 시트
+
+LangGraph 코드베이스를 CrewAI Flows로 옮기고 싶다면, 다음의 실전 변환 가이드를 참고하세요:
+
+1. **상태를 매핑하세요.** `TypedDict`를 Pydantic `BaseModel`로 변환하고 모든 필드에 기본값을 추가하세요.
+2. **노드를 메서드로 변환하세요.** 각 `add_node` 함수는 `Flow` 서브클래스의 메서드가 됩니다. `state["field"]` 읽기는 `self.state.field`로 바꾸세요.
+3. **에지를 데코레이터로 교체하세요.** `add_edge(START, "first_node")`는 첫 메서드의 `@start()`가 됩니다. 순차적인 `add_edge("a", "b")`는 `b` 메서드의 `@listen(a)`가 됩니다.
+4. **조건부 에지는 `@router`로 교체하세요.** 라우팅 함수와 `add_conditional_edges()` 매핑은 하나의 `@router()` 메서드로 통합하고, 라우트 문자열을 반환하세요.
+5. **compile + invoke를 kickoff으로 교체하세요.** `graph.compile()`를 제거하고 `flow.kickoff()`를 호출하세요.
+6. **Crew가 들어갈 지점을 고려하세요.** 복잡한 다단계 에이전트 로직이 있는 노드는 Crew로 분리할 후보입니다. 이 부분에서 가장 큰 품질 향상을 체감할 수 있습니다.
+
+---
+
+## 시작하기
+
+CrewAI를 설치하고 새 Flow 프로젝트를 스캐폴딩하세요:
+
+```bash
+pip install crewai
+crewai create flow my_first_flow
+cd my_first_flow
+```
+
+이렇게 하면 바로 편집 가능한 Flow 클래스, 설정 파일, 그리고 `type = "flow"`가 이미 설정된 `pyproject.toml`이 포함된 프로젝트 구조가 생성됩니다. 다음으로 실행하세요:
+
+```bash
+crewai run
+```
+
+그 다음부터는 에이전트를 추가하고 리스너를 연결한 뒤, 배포하면 됩니다.
+
+---
+
+## 마무리
+
+LangGraph는 AI 워크플로우에 구조가 필요하다는 사실을 생태계에 일깨워 주었습니다. 중요한 교훈이었습니다. 하지만 CrewAI Flows는 그 교훈을 더 빠르게 쓰고, 더 쉽게 읽으며, 프로덕션에서 더 강력한 형태로 제공합니다 — 특히 워크플로우에 여러 에이전트의 협업이 포함될 때 그렇습니다.
+
+단일 에이전트 체인을 넘는 무엇인가를 만들고 있다면, Flows를 진지하게 검토해 보세요. 데코레이터 기반 모델, Crews의 네이티브 통합, 내장 상태 관리를 통해 배관 작업에 쓰는 시간을 줄이고, 중요한 문제에 더 많은 시간을 쓸 수 있습니다.
+
+`crewai create flow`로 시작하세요. 후회하지 않을 겁니다.

docs/ko/mcp/dsl-integration.mdx

@@ -62,22 +62,22 @@ agent = Agent(
 "https://mcp.exa.ai/mcp?api_key=your_key#web_search_exa"
 ```
 
-### CrewAI AMP 마켓플레이스
+### 연결된 MCP 통합
 
-CrewAI AMP 마켓플레이스의 도구에 액세스하세요:
+CrewAI 카탈로그에서 MCP 서버를 연결하거나 직접 가져올 수 있습니다. 계정에 연결한 후 슬러그로 참조하세요:
 
 ```python
-# 모든 도구가 포함된 전체 서비스
-"crewai-amp:financial-data"
+# 모든 도구가 포함된 연결된 MCP
+"snowflake"
 
-# AMP 서비스의 특정 도구
-"crewai-amp:research-tools#pubmed_search"
+# 연결된 MCP의 특정 도구
+"stripe#list_invoices"
 
-# 다중 AMP 서비스
+# 여러 연결된 MCP
 mcps=[
-    "crewai-amp:weather-insights",
-    "crewai-amp:market-analysis",
-    "crewai-amp:social-media-monitoring"
+    "snowflake",
+    "stripe",
+    "github"
 ]
 ```
 
@@ -99,10 +99,10 @@ multi_source_agent = Agent(
         "https://mcp.exa.ai/mcp?api_key=your_exa_key&profile=research",
         "https://weather.api.com/mcp#get_current_conditions",
 
-        # CrewAI AMP 마켓플레이스
-        "crewai-amp:financial-insights",
-        "crewai-amp:academic-research#pubmed_search",
-        "crewai-amp:market-intelligence#competitor_analysis"
+        # 카탈로그에서 연결된 MCP
+        "snowflake",
+        "stripe#list_invoices",
+        "github#search_repositories"
     ]
 )
 
@@ -154,7 +154,7 @@ agent = Agent(
         "https://reliable-server.com/mcp",        # 작동할 것
         "https://unreachable-server.com/mcp",     # 우아하게 건너뛸 것
         "https://slow-server.com/mcp",            # 우아하게 타임아웃될 것
-        "crewai-amp:working-service"              # 작동할 것
+        "snowflake"                               # 카탈로그에서 연결된 MCP
     ]
 )
 # 에이전트는 작동하는 서버의 도구를 사용하고 실패한 서버에 대한 경고를 로그에 남깁니다
@@ -229,6 +229,6 @@ agent = Agent(
 mcps=[
     "https://primary-api.com/mcp",       # 주요 선택
     "https://backup-api.com/mcp",        # 백업 옵션
-    "crewai-amp:reliable-service"        # AMP 폴백
+    "snowflake"                          # 연결된 MCP 폴백
 ]
 ```

docs/ko/mcp/overview.mdx

@@ -25,8 +25,8 @@ agent = Agent(
     mcps=[
         "https://mcp.exa.ai/mcp?api_key=your_key",           # 외부 MCP 서버
         "https://api.weather.com/mcp#get_forecast",          # 서버의 특정 도구
-        "crewai-amp:financial-data",                         # CrewAI AMP 마켓플레이스
-        "crewai-amp:research-tools#pubmed_search"            # 특정 AMP 도구
+        "snowflake",                                         # 카탈로그에서 연결된 MCP
+        "stripe#list_invoices"                               # 연결된 MCP의 특정 도구
     ]
 )
 # MCP 도구들이 이제 자동으로 에이전트에서 사용 가능합니다!

docs/ko/tools/automation/composiotool.mdx

@@ -18,77 +18,46 @@ Composio는 AI 에이전트를 250개 이상의 도구와 연결할 수 있는
 Composio 도구를 프로젝트에 통합하려면 아래 지침을 따르세요:
 
 ```shell
-pip install composio-crewai
+pip install composio composio-crewai
 pip install crewai
 ```
 
-설치가 완료된 후, `composio login`을 실행하거나 Composio API 키를 `COMPOSIO_API_KEY`로 export하세요. Composio API 키는 [여기](https://app.composio.dev)에서 받을 수 있습니다.
+설치가 완료되면 Composio API 키를 `COMPOSIO_API_KEY`로 설정하세요. Composio API 키는 [여기](https://platform.composio.dev)에서 받을 수 있습니다.
 
 ## 예시
 
-다음 예시는 도구를 초기화하고 github action을 실행하는 방법을 보여줍니다:
+다음 예시는 도구를 초기화하고 GitHub 액션을 실행하는 방법을 보여줍니다:
 
-1. Composio 도구 세트 초기화
+1. CrewAI Provider와 함께 Composio 초기화
 
 ```python Code
-from composio_crewai import ComposioToolSet, App, Action
+from composio_crewai import ComposioProvider
+from composio import Composio
 from crewai import Agent, Task, Crew
 
-toolset = ComposioToolSet()
+composio = Composio(provider=ComposioProvider())
 ```
 
-2. GitHub 계정 연결
+2. 새 Composio 세션을 만들고 도구 가져오기
 <CodeGroup>
-```shell CLI
-composio add github
-```
-```python Code
-request = toolset.initiate_connection(app=App.GITHUB)
-print(f"Open this URL to authenticate: {request.redirectUrl}")
+```python
+session = composio.create(
+    user_id="your-user-id",
+    toolkits=["gmail", "github"] # optional, default is all toolkits
+)
+tools = session.tools()
 ```
+세션 및 사용자 관리에 대한 자세한 내용은 [여기](https://docs.composio.dev/docs/configuring-sessions)를 참고하세요.
 </CodeGroup>
 
-3. 도구 가져오기
+3. 사용자 수동 인증하기
 
-- 앱에서 모든 도구를 가져오기 (프로덕션 환경에서는 권장하지 않음):
+Composio는 에이전트 채팅 세션 중에 사용자를 자동으로 인증합니다. 하지만 `authorize` 메서드를 호출해 사용자를 수동으로 인증할 수도 있습니다.
 ```python Code
-tools = toolset.get_tools(apps=[App.GITHUB])
+connection_request = session.authorize("github")
+print(f"Open this URL to authenticate: {connection_request.redirect_url}")
 ```
 
-- 태그를 기반으로 도구 필터링:
-```python Code
-tag = "users"
-
-filtered_action_enums = toolset.find_actions_by_tags(
-    App.GITHUB,
-    tags=[tag], 
-)
-
-tools = toolset.get_tools(actions=filtered_action_enums)
-```
-
-- 사용 사례를 기반으로 도구 필터링:
-```python Code
-use_case = "Star a repository on GitHub"
-
-filtered_action_enums = toolset.find_actions_by_use_case(
-    App.GITHUB, use_case=use_case, advanced=False
-)
-
-tools = toolset.get_tools(actions=filtered_action_enums)
-```
-<Tip>`advanced`를 True로 설정하면 복잡한 사용 사례를 위한 액션을 가져올 수 있습니다</Tip>
-
-- 특정 도구 사용하기:
-
-이 데모에서는 GitHub 앱의 `GITHUB_STAR_A_REPOSITORY_FOR_THE_AUTHENTICATED_USER` 액션을 사용합니다.
-```python Code
-tools = toolset.get_tools(
-    actions=[Action.GITHUB_STAR_A_REPOSITORY_FOR_THE_AUTHENTICATED_USER]
-)
-```
-액션 필터링에 대해 더 자세한 내용을 보려면 [여기](https://docs.composio.dev/patterns/tools/use-tools/use-specific-actions)를 참고하세요.
-
 4. 에이전트 정의
 
 ```python Code
@@ -116,4 +85,4 @@ crew = Crew(agents=[crewai_agent], tasks=[task])
 crew.kickoff()
 ```
 
-* 더욱 자세한 도구 리스트는 [여기](https://app.composio.dev)에서 확인하실 수 있습니다.
+* 더욱 자세한 도구 목록은 [여기](https://docs.composio.dev/toolkits)에서 확인할 수 있습니다.

docs/pt-BR/changelog.mdx

@@ -4,6 +4,237 @@ description: "Atualizações de produto, melhorias e correções do CrewAI"
 icon: "clock"
 mode: "wide"
 ---
+<Update label="15 mar 2026">
+  ## v1.11.0rc1
+
+  [Ver release no GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.11.0rc1)
+
+  ## O que Mudou
+
+  ### Funcionalidades
+  - Adicionar autenticação de token da API Plus
+  - Implementar padrão de execução de plano
+
+  ### Correções de Bugs
+  - Resolver problema de escape do sandbox do interpretador de código
+
+  ### Documentação
+  - Atualizar changelog e versão para v1.10.2rc2
+
+  ## Contribuidores
+
+  @Copilot, @greysonlalonde, @lorenzejay, @theCyberTech
+
+</Update>
+
+<Update label="14 mar 2026">
+  ## v1.10.2rc2
+
+  [Ver release no GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.10.2rc2)
+
+  ## O que Mudou
+
+  ### Correções de Bugs
+  - Remover bloqueios exclusivos de operações de armazenamento somente leitura
+
+  ### Documentação
+  - Atualizar changelog e versão para v1.10.2rc1
+
+  ## Contribuidores
+
+  @greysonlalonde
+
+</Update>
+
+<Update label="13 mar 2026">
+  ## v1.10.2rc1
+
+  [Ver release no GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.10.2rc1)
+
+  ## O que Mudou
+
+  ### Funcionalidades
+  - Adicionar comando de lançamento e acionar publicação no PyPI
+
+  ### Correções de Bugs
+  - Corrigir bloqueio seguro entre processos e threads para I/O não protegido
+  - Propagar contextvars através de todos os limites de thread e executor
+  - Propagar ContextVars para threads de tarefas assíncronas
+
+  ### Documentação
+  - Atualizar changelog e versão para v1.10.2a1
+
+  ## Contribuidores
+
+  @danglies007, @greysonlalonde
+
+</Update>
+
+<Update label="11 mar 2026">
+  ## v1.10.2a1
+
+  [Ver release no GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.10.2a1)
+
+  ## O que mudou
+
+  ### Recursos
+  - Adicionar suporte para busca de ferramentas, salvamento de tokens e injeção dinâmica de ferramentas apropriadas durante a execução para Anthropics.
+  - Introduzir mais ferramentas de Busca Brave.
+  - Criar ação para lançamentos noturnos.
+
+  ### Correções de Bugs
+  - Corrigir LockException durante a execução concorrente de múltiplos processos.
+  - Resolver problemas com a agrupação de resultados de ferramentas paralelas em uma única mensagem de usuário.
+  - Abordar resoluções de ferramentas MCP e eliminar todas as conexões mutáveis compartilhadas.
+  - Atualizar o manuseio de parâmetros LLM na função human_feedback.
+  - Adicionar métodos de lista/dicionário ausentes a LockedListProxy e LockedDictProxy.
+  - Propagar o contexto de contextvars para as threads de chamada de ferramentas paralelas.
+  - Atualizar a dependência gitpython para >=3.1.41 para resolver a vulnerabilidade de travessia de diretórios CVE.
+
+  ### Refatoração
+  - Refatorar classes de memória para serem serializáveis.
+
+  ### Documentação
+  - Atualizar o changelog e a versão para v1.10.1.
+
+  ## Contribuidores
+
+  @akaKuruma, @github-actions[bot], @giulio-leone, @greysonlalonde, @joaomdmoura, @jonathansampson, @lorenzejay, @lucasgomide, @mattatcha
+
+</Update>
+
+<Update label="04 mar 2026">
+  ## v1.10.1
+
+  [Ver release no GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.10.1)
+
+  ## O que mudou
+
+  ### Recursos
+  - Atualizar Gemini GenAI
+
+  ### Correções de Bugs
+  - Ajustar o valor do listener do executor para evitar recursão
+  - Agrupar partes da resposta da função paralela em um único objeto Content no Gemini
+  - Exibir a saída de pensamento dos modelos de pensamento no Gemini
+  - Carregar ferramentas MCP e da plataforma quando as ferramentas do agente forem None
+  - Suportar ambientes Jupyter com loops de eventos em A2A
+  - Usar ID anônimo para rastreamentos efêmeros
+  - Passar condicionalmente o cabeçalho plus
+  - Ignorar o registro do manipulador de sinal em threads não principais para telemetria
+  - Injetar erros de ferramentas como observações e resolver colisões de nomes
+  - Atualizar pypdf de 4.x para 6.7.4 para resolver alertas do Dependabot
+  - Resolver alertas de segurança críticos e altos do Dependabot
+
+  ### Documentação
+  - Sincronizar a documentação da ferramenta Composio entre locais
+
+  ## Contribuidores
+
+  @giulio-leone, @greysonlalonde, @haxzie, @joaomdmoura, @lorenzejay, @mattatcha, @mplachta, @nicoferdi96
+
+</Update>
+
+<Update label="27 fev 2026">
+  ## v1.10.1a1
+
+  [Ver release no GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.10.1a1)
+
+  ## O que Mudou
+
+  ### Funcionalidades
+  - Implementar suporte a invocação assíncrona em métodos de callback de etapas
+  - Implementar carregamento sob demanda para dependências pesadas no módulo de Memória
+
+  ### Documentação
+  - Atualizar changelog e versão para v1.10.0
+
+  ### Refatoração
+  - Refatorar métodos de callback de etapas para suportar invocação assíncrona
+  - Refatorar para implementar carregamento sob demanda para dependências pesadas no módulo de Memória
+
+  ### Correções de Bugs
+  - Corrigir branch para notas de lançamento
+
+  ## Contribuidores
+
+  @greysonlalonde, @joaomdmoura
+
+</Update>
+
+<Update label="27 fev 2026">
+  ## v1.10.1a1
+
+  [Ver release no GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.10.1a1)
+
+  ## O que Mudou
+
+  ### Refatoração
+  - Refatorar métodos de callback de etapas para suportar invocação assíncrona
+  - Implementar carregamento sob demanda para dependências pesadas no módulo de Memória
+
+  ### Documentação
+  - Atualizar changelog e versão para v1.10.0
+
+  ### Correções de Bugs
+  - Criar branch para notas de lançamento
+
+  ## Contribuidores
+
+  @greysonlalonde, @joaomdmoura
+
+</Update>
+
+<Update label="26 fev 2026">
+  ## v1.10.0
+
+  [Ver release no GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.10.0)
+
+  ## O que Mudou
+
+  ### Recursos
+  - Aprimorar a resolução da ferramenta MCP e eventos relacionados
+  - Atualizar a versão do lancedb e adicionar pacotes lance-namespace
+  - Aprimorar a análise e validação de argumentos JSON no CrewAgentExecutor e BaseTool
+  - Migrar o cliente HTTP da CLI de requests para httpx
+  - Adicionar documentação versionada
+  - Adicionar detecção de versões removidas para notas de versão
+  - Implementar tratamento de entrada do usuário em Flows
+  - Aprimorar a funcionalidade de auto-loop HITL nos testes de integração de feedback humano
+  - Adicionar started_event_id e definir no eventbus
+  - Atualizar automaticamente tools.specs
+
+  ### Correções de Bugs
+  - Validar kwargs da ferramenta mesmo quando vazios para evitar TypeError crípticos
+  - Preservar tipos nulos nos esquemas de parâmetros da ferramenta para LLM
+  - Mapear output_pydantic/output_json para saída estruturada nativa
+  - Garantir que callbacks sejam executados/aguardados se forem promessas
+  - Capturar o nome do método no contexto da exceção
+  - Preservar tipo enum no resultado do roteador; melhorar tipos
+  - Corrigir fluxos cíclicos que quebram silenciosamente quando o ID de persistência é passado nas entradas
+  - Corrigir o formato da flag da CLI de --skip-provider para --skip_provider
+  - Garantir que o fluxo de chamada da ferramenta OpenAI seja finalizado
+  - Resolver ponteiros $ref de esquema complexos nas ferramentas MCP
+  - Impor additionalProperties=false nos esquemas
+  - Rejeitar nomes de scripts reservados para pastas de equipe
+  - Resolver condição de corrida no teste de emissão de eventos de guardrail
+
+  ### Documentação
+  - Adicionar nota de dependência litellm para provedores de LLM não nativos
+  - Esclarecer o modelo de segurança NL2SQL e orientações de fortalecimento
+  - Adicionar 96 ações ausentes em 9 integrações
+
+  ### Refatoração
+  - Refatorar crew para provider
+  - Extrair HITL para padrão de provider
+  - Melhorar tipagem e registro de hooks
+
+  ## Contribuidores
+
+  @dependabot[bot], @github-actions[bot], @github-code-quality[bot], @greysonlalonde, @heitorado, @hobostay, @joaomdmoura, @johnvan7, @jonathansampson, @lorenzejay, @lucasgomide, @mattatcha, @mplachta, @nicoferdi96, @theCyberTech, @thiagomoretto, @vinibrsl
+
+</Update>
+
 <Update label="26 jan 2026">
   ## v1.9.0
 

docs/pt-BR/guides/migration/migrating-from-langgraph.mdx

@@ -0,0 +1,518 @@
+---
+title: "Migrando do LangGraph para o CrewAI: um guia prático para engenheiros"
+description: Se você já construiu com LangGraph, saiba como portar rapidamente seus projetos para o CrewAI
+icon: switch
+mode: "wide"
+---
+
+Você construiu agentes com LangGraph. Já lutou com o `StateGraph`, ligou arestas condicionais e depurou dicionários de estado às 2 da manhã. Funciona — mas, em algum momento, você começou a se perguntar se existe um caminho melhor para produção.
+
+Existe. **CrewAI Flows** entrega o mesmo poder — orquestração orientada a eventos, roteamento condicional, estado compartilhado — com muito menos boilerplate e um modelo mental que se alinha a como você realmente pensa sobre fluxos de trabalho de IA em múltiplas etapas.
+
+Este artigo apresenta os conceitos principais lado a lado, mostra comparações reais de código e demonstra por que o CrewAI Flows é o framework que você vai querer usar a seguir.
+
+---
+
+## A Mudança de Modelo Mental
+
+LangGraph pede que você pense em **grafos**: nós, arestas e dicionários de estado. Todo workflow é um grafo direcionado em que você conecta explicitamente as transições entre as etapas de computação. É poderoso, mas a abstração traz overhead — especialmente quando o seu fluxo é fundamentalmente sequencial com alguns pontos de decisão.
+
+CrewAI Flows pede que você pense em **eventos**: métodos que iniciam, métodos que escutam resultados e métodos que roteiam a execução. A topologia do workflow emerge de anotações com decorators, em vez de construção explícita do grafo. Isso não é apenas açúcar sintático — muda como você projeta, lê e mantém seus pipelines.
+
+Veja o mapeamento principal:
+
+| Conceito no LangGraph | Equivalente no CrewAI Flows |
+| --- | --- |
+| `StateGraph` class | `Flow` class |
+| `add_node()` | Methods decorated with `@start`, `@listen` |
+| `add_edge()` / `add_conditional_edges()` | `@listen()` / `@router()` decorators |
+| `TypedDict` state | Pydantic `BaseModel` state |
+| `START` / `END` constants | `@start()` decorator / natural method return |
+| `graph.compile()` | `flow.kickoff()` |
+| Checkpointer / persistence | Built-in memory (LanceDB-backed) |
+
+Vamos ver como isso fica na prática.
+
+---
+
+## Demo 1: Um Pipeline Sequencial Simples
+
+Imagine que você está construindo um pipeline que recebe um tema, pesquisa, escreve um resumo e formata a saída. Veja como cada framework lida com isso.
+
+### Abordagem com LangGraph
+
+```python
+from typing import TypedDict
+from langgraph.graph import StateGraph, START, END
+
+class ResearchState(TypedDict):
+    topic: str
+    raw_research: str
+    summary: str
+    formatted_output: str
+
+def research_topic(state: ResearchState) -> dict:
+    # Call an LLM or search API
+    result = llm.invoke(f"Research the topic: {state['topic']}")
+    return {"raw_research": result}
+
+def write_summary(state: ResearchState) -> dict:
+    result = llm.invoke(
+        f"Summarize this research:\n{state['raw_research']}"
+    )
+    return {"summary": result}
+
+def format_output(state: ResearchState) -> dict:
+    result = llm.invoke(
+        f"Format this summary as a polished article section:\n{state['summary']}"
+    )
+    return {"formatted_output": result}
+
+# Build the graph
+graph = StateGraph(ResearchState)
+graph.add_node("research", research_topic)
+graph.add_node("summarize", write_summary)
+graph.add_node("format", format_output)
+
+graph.add_edge(START, "research")
+graph.add_edge("research", "summarize")
+graph.add_edge("summarize", "format")
+graph.add_edge("format", END)
+
+# Compile and run
+app = graph.compile()
+result = app.invoke({"topic": "quantum computing advances in 2026"})
+print(result["formatted_output"])
+```
+
+Você define funções, registra-as como nós e conecta manualmente cada transição. Para uma sequência simples como essa, há muita cerimônia.
+
+### Abordagem com CrewAI Flows
+
+```python
+from crewai import LLM, Agent, Crew, Process, Task
+from crewai.flow.flow import Flow, listen, start
+from pydantic import BaseModel
+
+llm = LLM(model="openai/gpt-5.2")
+
+class ResearchState(BaseModel):
+    topic: str = ""
+    raw_research: str = ""
+    summary: str = ""
+    formatted_output: str = ""
+
+class ResearchFlow(Flow[ResearchState]):
+    @start()
+    def research_topic(self):
+        # Option 1: Direct LLM call
+        result = llm.call(f"Research the topic: {self.state.topic}")
+        self.state.raw_research = result
+        return result
+
+    @listen(research_topic)
+    def write_summary(self, research_output):
+        # Option 2: A single agent
+        summarizer = Agent(
+            role="Research Summarizer",
+            goal="Produce concise, accurate summaries of research content",
+            backstory="You are an expert at distilling complex research into clear, "
+            "digestible summaries.",
+            llm=llm,
+            verbose=True,
+        )
+        result = summarizer.kickoff(
+            f"Summarize this research:\n{self.state.raw_research}"
+        )
+        self.state.summary = str(result)
+        return self.state.summary
+
+    @listen(write_summary)
+    def format_output(self, summary_output):
+        # Option 3: a complete crew (with one or more agents)
+        formatter = Agent(
+            role="Content Formatter",
+            goal="Transform research summaries into polished, publication-ready article sections",
+            backstory="You are a skilled editor with expertise in structuring and "
+            "presenting technical content for a general audience.",
+            llm=llm,
+            verbose=True,
+        )
+        format_task = Task(
+            description=f"Format this summary as a polished article section:\n{self.state.summary}",
+            expected_output="A well-structured, polished article section ready for publication.",
+            agent=formatter,
+        )
+        crew = Crew(
+            agents=[formatter],
+            tasks=[format_task],
+            process=Process.sequential,
+            verbose=True,
+        )
+        result = crew.kickoff()
+        self.state.formatted_output = str(result)
+        return self.state.formatted_output
+
+# Run the flow
+flow = ResearchFlow()
+flow.state.topic = "quantum computing advances in 2026"
+result = flow.kickoff()
+print(flow.state.formatted_output)
+
+```
+
+Repare a diferença: nada de construção de grafo, de ligação de arestas, nem de etapa de compilação. A ordem de execução é declarada exatamente onde a lógica vive. `@start()` marca o ponto de entrada, e `@listen(method_name)` encadeia as etapas. O estado é um modelo Pydantic de verdade, com segurança de tipos, validação e auto-complete na IDE.
+
+---
+
+## Demo 2: Roteamento Condicional
+
+Aqui é que fica interessante. Digamos que você está construindo um pipeline de conteúdo que roteia para diferentes caminhos de processamento com base no tipo de conteúdo detectado.
+
+### Abordagem com LangGraph
+
+```python
+from typing import TypedDict, Literal
+from langgraph.graph import StateGraph, START, END
+
+class ContentState(TypedDict):
+    input_text: str
+    content_type: str
+    result: str
+
+def classify_content(state: ContentState) -> dict:
+    content_type = llm.invoke(
+        f"Classify this content as 'technical', 'creative', or 'business':\n{state['input_text']}"
+    )
+    return {"content_type": content_type.strip().lower()}
+
+def process_technical(state: ContentState) -> dict:
+    result = llm.invoke(f"Process as technical doc:\n{state['input_text']}")
+    return {"result": result}
+
+def process_creative(state: ContentState) -> dict:
+    result = llm.invoke(f"Process as creative writing:\n{state['input_text']}")
+    return {"result": result}
+
+def process_business(state: ContentState) -> dict:
+    result = llm.invoke(f"Process as business content:\n{state['input_text']}")
+    return {"result": result}
+
+# Routing function
+def route_content(state: ContentState) -> Literal["technical", "creative", "business"]:
+    return state["content_type"]
+
+# Build the graph
+graph = StateGraph(ContentState)
+graph.add_node("classify", classify_content)
+graph.add_node("technical", process_technical)
+graph.add_node("creative", process_creative)
+graph.add_node("business", process_business)
+
+graph.add_edge(START, "classify")
+graph.add_conditional_edges(
+    "classify",
+    route_content,
+    {
+        "technical": "technical",
+        "creative": "creative",
+        "business": "business",
+    }
+)
+graph.add_edge("technical", END)
+graph.add_edge("creative", END)
+graph.add_edge("business", END)
+
+app = graph.compile()
+result = app.invoke({"input_text": "Explain how TCP handshakes work"})
+```
+
+Você precisa de uma função de roteamento separada, de um mapeamento explícito de arestas condicionais e de arestas de término para cada ramificação. A lógica de roteamento fica desacoplada do nó que produz a decisão.
+
+### Abordagem com CrewAI Flows
+
+```python
+from crewai import LLM, Agent
+from crewai.flow.flow import Flow, listen, router, start
+from pydantic import BaseModel
+
+llm = LLM(model="openai/gpt-5.2")
+
+class ContentState(BaseModel):
+    input_text: str = ""
+    content_type: str = ""
+    result: str = ""
+
+class ContentFlow(Flow[ContentState]):
+    @start()
+    def classify_content(self):
+        self.state.content_type = (
+            llm.call(
+                f"Classify this content as 'technical', 'creative', or 'business':\n"
+                f"{self.state.input_text}"
+            )
+            .strip()
+            .lower()
+        )
+        return self.state.content_type
+
+    @router(classify_content)
+    def route_content(self, classification):
+        if classification == "technical":
+            return "process_technical"
+        elif classification == "creative":
+            return "process_creative"
+        else:
+            return "process_business"
+
+    @listen("process_technical")
+    def handle_technical(self):
+        agent = Agent(
+            role="Technical Writer",
+            goal="Produce clear, accurate technical documentation",
+            backstory="You are an expert technical writer who specializes in "
+            "explaining complex technical concepts precisely.",
+            llm=llm,
+            verbose=True,
+        )
+        self.state.result = str(
+            agent.kickoff(f"Process as technical doc:\n{self.state.input_text}")
+        )
+
+    @listen("process_creative")
+    def handle_creative(self):
+        agent = Agent(
+            role="Creative Writer",
+            goal="Craft engaging and imaginative creative content",
+            backstory="You are a talented creative writer with a flair for "
+            "compelling storytelling and vivid expression.",
+            llm=llm,
+            verbose=True,
+        )
+        self.state.result = str(
+            agent.kickoff(f"Process as creative writing:\n{self.state.input_text}")
+        )
+
+    @listen("process_business")
+    def handle_business(self):
+        agent = Agent(
+            role="Business Writer",
+            goal="Produce professional, results-oriented business content",
+            backstory="You are an experienced business writer who communicates "
+            "strategy and value clearly to professional audiences.",
+            llm=llm,
+            verbose=True,
+        )
+        self.state.result = str(
+            agent.kickoff(f"Process as business content:\n{self.state.input_text}")
+        )
+
+flow = ContentFlow()
+flow.state.input_text = "Explain how TCP handshakes work"
+flow.kickoff()
+print(flow.state.result)
+
+```
+
+O decorator `@router()` transforma um método em um ponto de decisão. Ele retorna uma string que corresponde a um listener — sem dicionários de mapeamento, sem funções de roteamento separadas. A lógica de ramificação parece um `if` em Python porque *é* um.
+
+---
+
+## Demo 3: Integrando Crews de Agentes de IA em Flows
+
+É aqui que o verdadeiro poder do CrewAI aparece. Flows não servem apenas para encadear chamadas de LLM — elas orquestram **Crews** completas de agentes autônomos. Isso é algo para o qual o LangGraph simplesmente não tem um equivalente nativo.
+
+```python
+from crewai import Agent, Task, Crew
+from crewai.flow.flow import Flow, listen, start
+from pydantic import BaseModel
+
+class ArticleState(BaseModel):
+    topic: str = ""
+    research: str = ""
+    draft: str = ""
+    final_article: str = ""
+
+class ArticleFlow(Flow[ArticleState]):
+
+    @start()
+    def run_research_crew(self):
+        """A full Crew of agents handles research."""
+        researcher = Agent(
+            role="Senior Research Analyst",
+            goal=f"Produce comprehensive research on: {self.state.topic}",
+            backstory="You're a veteran analyst known for thorough, "
+                       "well-sourced research reports.",
+            llm="gpt-4o"
+        )
+
+        research_task = Task(
+            description=f"Research '{self.state.topic}' thoroughly. "
+                        "Cover key trends, data points, and expert opinions.",
+            expected_output="A detailed research brief with sources.",
+            agent=researcher
+        )
+
+        crew = Crew(agents=[researcher], tasks=[research_task])
+        result = crew.kickoff()
+        self.state.research = result.raw
+        return result.raw
+
+    @listen(run_research_crew)
+    def run_writing_crew(self, research_output):
+        """A different Crew handles writing."""
+        writer = Agent(
+            role="Technical Writer",
+            goal="Write a compelling article based on provided research.",
+            backstory="You turn complex research into engaging, clear prose.",
+            llm="gpt-4o"
+        )
+
+        editor = Agent(
+            role="Senior Editor",
+            goal="Review and polish articles for publication quality.",
+            backstory="20 years of editorial experience at top tech publications.",
+            llm="gpt-4o"
+        )
+
+        write_task = Task(
+            description=f"Write an article based on this research:\n{self.state.research}",
+            expected_output="A well-structured draft article.",
+            agent=writer
+        )
+
+        edit_task = Task(
+            description="Review, fact-check, and polish the draft article.",
+            expected_output="A publication-ready article.",
+            agent=editor
+        )
+
+        crew = Crew(agents=[writer, editor], tasks=[write_task, edit_task])
+        result = crew.kickoff()
+        self.state.final_article = result.raw
+        return result.raw
+
+# Run the full pipeline
+flow = ArticleFlow()
+flow.state.topic = "The Future of Edge AI"
+flow.kickoff()
+print(flow.state.final_article)
+```
+
+Este é o insight-chave: **Flows fornecem a camada de orquestração, e Crews fornecem a camada de inteligência.** Cada etapa em um Flow pode subir uma equipe completa de agentes colaborativos, cada um com seus próprios papéis, objetivos e ferramentas. Você obtém fluxo de controle estruturado e previsível *e* colaboração autônoma de agentes — o melhor dos dois mundos.
+
+No LangGraph, alcançar algo similar significa implementar manualmente protocolos de comunicação entre agentes, loops de chamada de ferramentas e lógica de delegação dentro das funções dos nós. É possível, mas é encanamento que você constrói do zero todas as vezes.
+
+---
+
+## Demo 4: Execução Paralela e Sincronização
+
+Pipelines do mundo real frequentemente precisam dividir o trabalho e juntar os resultados. O CrewAI Flows lida com isso de forma elegante com os operadores `and_` e `or_`.
+
+```python
+from crewai import LLM
+from crewai.flow.flow import Flow, and_, listen, start
+from pydantic import BaseModel
+
+llm = LLM(model="openai/gpt-5.2")
+
+class AnalysisState(BaseModel):
+    topic: str = ""
+    market_data: str = ""
+    tech_analysis: str = ""
+    competitor_intel: str = ""
+    final_report: str = ""
+
+class ParallelAnalysisFlow(Flow[AnalysisState]):
+    @start()
+    def start_method(self):
+        pass
+
+    @listen(start_method)
+    def gather_market_data(self):
+        # Your agentic or deterministic code
+        pass
+
+    @listen(start_method)
+    def run_tech_analysis(self):
+        # Your agentic or deterministic code
+        pass
+
+    @listen(start_method)
+    def gather_competitor_intel(self):
+        # Your agentic or deterministic code
+        pass
+
+    @listen(and_(gather_market_data, run_tech_analysis, gather_competitor_intel))
+    def synthesize_report(self):
+        # Your agentic or deterministic code
+        pass
+
+flow = ParallelAnalysisFlow()
+flow.state.topic = "AI-powered developer tools"
+flow.kickoff()
+
+```
+
+Vários decorators `@start()` disparam em paralelo. O combinador `and_()` no decorator `@listen` garante que `synthesize_report` só execute depois que *todos os três* métodos upstream forem concluídos. Também existe `or_()` para quando você quer prosseguir assim que *qualquer* tarefa upstream terminar.
+
+No LangGraph, você precisaria construir um padrão fan-out/fan-in com ramificações paralelas, um nó de sincronização e uma mesclagem de estado cuidadosa — tudo conectado explicitamente por arestas.
+
+---
+
+## Por que CrewAI Flows em Produção
+
+Além de uma sintaxe mais limpa, Flows entrega várias vantagens críticas para produção:
+
+**Persistência de estado integrada.** O estado do Flow é respaldado pelo LanceDB, o que significa que seus workflows podem sobreviver a falhas, ser retomados e acumular conhecimento entre execuções. No LangGraph, você precisa configurar um checkpointer separado.
+
+**Gerenciamento de estado com segurança de tipos.** Modelos Pydantic oferecem validação, serialização e suporte de IDE prontos para uso. Estados `TypedDict` do LangGraph não validam em runtime.
+
+**Orquestração de agentes de primeira classe.** Crews são um primitivo nativo. Você define agentes com papéis, objetivos, histórias e ferramentas — e eles colaboram de forma autônoma dentro do envelope estruturado de um Flow. Não é preciso reinventar a coordenação multiagente.
+
+**Modelo mental mais simples.** Decorators declaram intenção. `@start` significa "comece aqui". `@listen(x)` significa "execute depois de x". `@router(x)` significa "decida para onde ir depois de x". O código lê como o workflow que ele descreve.
+
+**Integração com CLI.** Execute flows com `crewai run`. Sem etapa de compilação separada, sem serialização de grafo. Seu Flow é uma classe Python, e ele roda como tal.
+
+---
+
+## Cheat Sheet de Migração
+
+Se você está com uma base de código LangGraph e quer migrar para o CrewAI Flows, aqui vai um guia prático de conversão:
+
+1. **Mapeie seu estado.** Converta seu `TypedDict` para um `BaseModel` do Pydantic. Adicione valores padrão para todos os campos.
+2. **Converta nós em métodos.** Cada função de `add_node` vira um método na sua subclasse de `Flow`. Substitua leituras `state["field"]` por `self.state.field`.
+3. **Substitua arestas por decorators.** `add_edge(START, "first_node")` vira `@start()` no primeiro método. A sequência `add_edge("a", "b")` vira `@listen(a)` no método `b`.
+4. **Substitua arestas condicionais por `@router`.** A função de roteamento e o mapeamento do `add_conditional_edges()` viram um único método `@router()` que retorna a string de rota.
+5. **Troque compile + invoke por kickoff.** Remova `graph.compile()`. Chame `flow.kickoff()`.
+6. **Considere onde as Crews se encaixam.** Qualquer nó com lógica complexa de agentes em múltiplas etapas é um candidato a extração para uma Crew. É aqui que você verá a maior melhoria de qualidade.
+
+---
+
+## Primeiros Passos
+
+Instale o CrewAI e crie o scaffold de um novo projeto Flow:
+
+```bash
+pip install crewai
+crewai create flow my_first_flow
+cd my_first_flow
+```
+
+Isso gera uma estrutura de projeto com uma classe Flow pronta para edição, arquivos de configuração e um `pyproject.toml` com `type = "flow"` já definido. Execute com:
+
+```bash
+crewai run
+```
+
+A partir daí, adicione seus agentes, conecte seus listeners e publique.
+
+---
+
+## Considerações Finais
+
+O LangGraph ensinou ao ecossistema que workflows de IA precisam de estrutura. Essa foi uma lição importante. Mas o CrewAI Flows pega essa lição e a entrega de um jeito mais rápido de escrever, mais fácil de ler e mais poderoso em produção — especialmente quando seus workflows envolvem múltiplos agentes colaborando.
+
+Se você está construindo algo além de uma cadeia de agente único, dê uma olhada séria no Flows. O modelo baseado em decorators, a integração nativa com Crews e o gerenciamento de estado embutido significam menos tempo com encanamento e mais tempo nos problemas que importam.
+
+Comece com `crewai create flow`. Você não vai olhar para trás.

docs/pt-BR/mcp/dsl-integration.mdx

@@ -62,22 +62,22 @@ Use a sintaxe `#` para selecionar ferramentas específicas de um servidor:
 "https://mcp.exa.ai/mcp?api_key=sua_chave#web_search_exa"
 ```
 
-### Marketplace CrewAI AMP
+### Integrações MCP Conectadas
 
-Acesse ferramentas do marketplace CrewAI AMP:
+Conecte servidores MCP do catálogo CrewAI ou traga os seus próprios. Uma vez conectados em sua conta, referencie-os pelo slug:
 
 ```python
-# Serviço completo com todas as ferramentas
-"crewai-amp:financial-data"
+# MCP conectado com todas as ferramentas
+"snowflake"
 
-# Ferramenta específica do serviço AMP
-"crewai-amp:research-tools#pubmed_search"
+# Ferramenta específica de um MCP conectado
+"stripe#list_invoices"
 
-# Múltiplos serviços AMP
+# Múltiplos MCPs conectados
 mcps=[
-    "crewai-amp:weather-insights",
-    "crewai-amp:market-analysis",
-    "crewai-amp:social-media-monitoring"
+    "snowflake",
+    "stripe",
+    "github"
 ]
 ```
 
@@ -99,10 +99,10 @@ agente_multi_fonte = Agent(
         "https://mcp.exa.ai/mcp?api_key=sua_chave_exa&profile=pesquisa",
         "https://weather.api.com/mcp#get_current_conditions",
 
-        # Marketplace CrewAI AMP
-        "crewai-amp:financial-insights",
-        "crewai-amp:academic-research#pubmed_search",
-        "crewai-amp:market-intelligence#competitor_analysis"
+        # MCPs conectados do catálogo
+        "snowflake",
+        "stripe#list_invoices",
+        "github#search_repositories"
     ]
 )
 
@@ -154,7 +154,7 @@ agente = Agent(
         "https://servidor-confiavel.com/mcp",        # Vai funcionar
         "https://servidor-inalcancavel.com/mcp",     # Será ignorado graciosamente
         "https://servidor-lento.com/mcp",            # Timeout gracioso
-        "crewai-amp:servico-funcionando"             # Vai funcionar
+        "snowflake"                                  # MCP conectado do catálogo
     ]
 )
 # O agente usará ferramentas de servidores funcionais e registrará avisos para os que falharem
@@ -229,6 +229,6 @@ agente = Agent(
 mcps=[
     "https://api-principal.com/mcp",       # Escolha principal
     "https://api-backup.com/mcp",          # Opção de backup
-    "crewai-amp:servico-confiavel"         # Fallback AMP
+    "snowflake"                            # Fallback MCP conectado
 ]
 ```

docs/pt-BR/mcp/overview.mdx

@@ -25,8 +25,8 @@ agent = Agent(
     mcps=[
         "https://mcp.exa.ai/mcp?api_key=sua_chave",           # Servidor MCP externo
         "https://api.weather.com/mcp#get_forecast",           # Ferramenta específica do servidor
-        "crewai-amp:financial-data",                          # Marketplace CrewAI AMP
-        "crewai-amp:research-tools#pubmed_search"             # Ferramenta AMP específica
+        "snowflake",                                          # MCP conectado do catálogo
+        "stripe#list_invoices"                                # Ferramenta específica de MCP conectado
     ]
 )
 # Ferramentas MCP agora estão automaticamente disponíveis para seu agente!

docs/pt-BR/tools/automation/composiotool.mdx

@@ -11,84 +11,53 @@ mode: "wide"
 Composio é uma plataforma de integração que permite conectar seus agentes de IA a mais de 250 ferramentas. Os principais recursos incluem:
 
 - **Autenticação de Nível Empresarial**: Suporte integrado para OAuth, Chaves de API, JWT com atualização automática de token
-- **Observabilidade Completa**: Logs detalhados de uso das ferramentas, registros de execução, e muito mais
+- **Observabilidade Completa**: Logs detalhados de uso das ferramentas, carimbos de data/hora de execução e muito mais
 
 ## Instalação
 
 Para incorporar as ferramentas Composio em seu projeto, siga as instruções abaixo:
 
 ```shell
-pip install composio-crewai
+pip install composio composio-crewai
 pip install crewai
 ```
 
-Após a conclusão da instalação, execute `composio login` ou exporte sua chave de API do composio como `COMPOSIO_API_KEY`. Obtenha sua chave de API Composio [aqui](https://app.composio.dev)
+Após concluir a instalação, defina sua chave de API do Composio como `COMPOSIO_API_KEY`. Obtenha sua chave de API do Composio [aqui](https://platform.composio.dev)
 
 ## Exemplo
 
-O exemplo a seguir demonstra como inicializar a ferramenta e executar uma ação do github:
+O exemplo a seguir demonstra como inicializar a ferramenta e executar uma ação do GitHub:
 
-1. Inicialize o conjunto de ferramentas Composio
+1. Inicialize o Composio com o Provider do CrewAI
 
 ```python Code
-from composio_crewai import ComposioToolSet, App, Action
+from composio_crewai import ComposioProvider
+from composio import Composio
 from crewai import Agent, Task, Crew
 
-toolset = ComposioToolSet()
+composio = Composio(provider=ComposioProvider())
 ```
 
-2. Conecte sua conta do GitHub
+2. Crie uma nova sessão Composio e recupere as ferramentas
 <CodeGroup>
-```shell CLI
-composio add github
-```
-```python Code
-request = toolset.initiate_connection(app=App.GITHUB)
-print(f"Open this URL to authenticate: {request.redirectUrl}")
+```python
+session = composio.create(
+    user_id="your-user-id",
+    toolkits=["gmail", "github"] # optional, default is all toolkits
+)
+tools = session.tools()
 ```
+Leia mais sobre sessões e gerenciamento de usuários [aqui](https://docs.composio.dev/docs/configuring-sessions)
 </CodeGroup>
 
-3. Obtenha ferramentas
+3. Autenticação manual dos usuários
 
-- Recuperando todas as ferramentas de um app (não recomendado em produção):
+O Composio autentica automaticamente os usuários durante a sessão de chat do agente. No entanto, você também pode autenticar o usuário manualmente chamando o método `authorize`.
 ```python Code
-tools = toolset.get_tools(apps=[App.GITHUB])
+connection_request = session.authorize("github")
+print(f"Open this URL to authenticate: {connection_request.redirect_url}")
 ```
 
-- Filtrando ferramentas com base em tags:
-```python Code
-tag = "users"
-
-filtered_action_enums = toolset.find_actions_by_tags(
-    App.GITHUB,
-    tags=[tag], 
-)
-
-tools = toolset.get_tools(actions=filtered_action_enums)
-```
-
-- Filtrando ferramentas com base no caso de uso:
-```python Code
-use_case = "Star a repository on GitHub"
-
-filtered_action_enums = toolset.find_actions_by_use_case(
-    App.GITHUB, use_case=use_case, advanced=False
-)
-
-tools = toolset.get_tools(actions=filtered_action_enums)
-```
-<Tip>Defina `advanced` como True para obter ações para casos de uso complexos</Tip>
-
-- Usando ferramentas específicas:
-
-Neste exemplo, usaremos a ação `GITHUB_STAR_A_REPOSITORY_FOR_THE_AUTHENTICATED_USER` do app GitHub.
-```python Code
-tools = toolset.get_tools(
-    actions=[Action.GITHUB_STAR_A_REPOSITORY_FOR_THE_AUTHENTICATED_USER]
-)
-```
-Saiba mais sobre como filtrar ações [aqui](https://docs.composio.dev/patterns/tools/use-tools/use-specific-actions)
-
 4. Defina o agente
 
 ```python Code
@@ -116,4 +85,4 @@ crew = Crew(agents=[crewai_agent], tasks=[task])
 crew.kickoff()
 ```
 
-* Uma lista mais detalhada de ferramentas pode ser encontrada [aqui](https://app.composio.dev)
+* Uma lista mais detalhada de ferramentas pode ser encontrada [aqui](https://docs.composio.dev/toolkits)

lib/crewai-files/pyproject.toml

@@ -8,8 +8,8 @@ authors = [
 ]
 requires-python = ">=3.10, <3.14"
 dependencies = [
-    "Pillow~=10.4.0",
-    "pypdf~=4.0.0",
+    "Pillow~=12.1.1",
+    "pypdf~=6.7.5",
     "python-magic>=0.4.27",
     "aiocache~=0.12.3",
     "aiofiles~=24.1.0",

lib/crewai-files/src/crewai_files/__init__.py

@@ -152,4 +152,4 @@ __all__ = [
     "wrap_file_source",
 ]
 
-__version__ = "1.10.0"
+__version__ = "1.11.0rc1"

lib/crewai-tools/pyproject.toml

@@ -11,7 +11,7 @@ dependencies = [
     "pytube~=15.0.0",
     "requests~=2.32.5",
     "docker~=7.1.0",
-    "crewai==1.10.0",
+    "crewai==1.11.0rc1",
     "tiktoken~=0.8.0",
     "beautifulsoup4~=4.13.4",
     "python-docx~=1.2.0",
@@ -108,7 +108,7 @@ stagehand = [
     "stagehand>=0.4.1",
 ]
 github = [
-    "gitpython==3.1.38",
+    "gitpython>=3.1.41,<4",
     "PyGithub==1.59.1",
 ]
 rag = [

lib/crewai-tools/src/crewai_tools/__init__.py

@@ -10,7 +10,18 @@ from crewai_tools.aws.s3.writer_tool import S3WriterTool
 from crewai_tools.tools.ai_mind_tool.ai_mind_tool import AIMindTool
 from crewai_tools.tools.apify_actors_tool.apify_actors_tool import ApifyActorsTool
 from crewai_tools.tools.arxiv_paper_tool.arxiv_paper_tool import ArxivPaperTool
+from crewai_tools.tools.brave_search_tool.brave_image_tool import BraveImageSearchTool
+from crewai_tools.tools.brave_search_tool.brave_llm_context_tool import (
+    BraveLLMContextTool,
+)
+from crewai_tools.tools.brave_search_tool.brave_local_pois_tool import (
+    BraveLocalPOIsDescriptionTool,
+    BraveLocalPOIsTool,
+)
+from crewai_tools.tools.brave_search_tool.brave_news_tool import BraveNewsSearchTool
 from crewai_tools.tools.brave_search_tool.brave_search_tool import BraveSearchTool
+from crewai_tools.tools.brave_search_tool.brave_video_tool import BraveVideoSearchTool
+from crewai_tools.tools.brave_search_tool.brave_web_tool import BraveWebSearchTool
 from crewai_tools.tools.brightdata_tool.brightdata_dataset import (
     BrightDataDatasetTool,
 )
@@ -200,7 +211,14 @@ __all__ = [
     "ArxivPaperTool",
     "BedrockInvokeAgentTool",
     "BedrockKBRetrieverTool",
+    "BraveImageSearchTool",
+    "BraveLLMContextTool",
+    "BraveLocalPOIsDescriptionTool",
+    "BraveLocalPOIsTool",
+    "BraveNewsSearchTool",
     "BraveSearchTool",
+    "BraveVideoSearchTool",
+    "BraveWebSearchTool",
     "BrightDataDatasetTool",
     "BrightDataSearchTool",
     "BrightDataWebUnlockerTool",
@@ -291,4 +309,4 @@ __all__ = [
     "ZapierActionTools",
 ]
 
-__version__ = "1.10.0"
+__version__ = "1.11.0rc1"

lib/crewai-tools/src/crewai_tools/adapters/lancedb_adapter.py

@@ -1,7 +1,9 @@
 from collections.abc import Callable
+import os
 from pathlib import Path
 from typing import Any
 
+from crewai.utilities.lock_store import lock as store_lock
 from lancedb import (  # type: ignore[import-untyped]
     DBConnection as LanceDBConnection,
     connect as lancedb_connect,
@@ -33,10 +35,12 @@ class LanceDBAdapter(Adapter):
 
     _db: LanceDBConnection = PrivateAttr()
     _table: LanceDBTable = PrivateAttr()
+    _lock_name: str = PrivateAttr(default="")
 
     def model_post_init(self, __context: Any) -> None:
         self._db = lancedb_connect(self.uri)
         self._table = self._db.open_table(self.table_name)
+        self._lock_name = f"lancedb:{os.path.realpath(str(self.uri))}"
 
         super().model_post_init(__context)
 
@@ -56,4 +60,5 @@ class LanceDBAdapter(Adapter):
         *args: Any,
         **kwargs: Any,
     ) -> None:
-        self._table.add(*args, **kwargs)
+        with store_lock(self._lock_name):
+            self._table.add(*args, **kwargs)

lib/crewai-tools/src/crewai_tools/aws/bedrock/browser/browser_session_manager.py

@@ -1,6 +1,9 @@
 from __future__ import annotations
 
+import asyncio
+import contextvars
 import logging
+import threading
 from typing import TYPE_CHECKING
 
 
@@ -18,6 +21,9 @@ class BrowserSessionManager:
     This class maintains separate browser sessions for different threads,
     enabling concurrent usage of browsers in multi-threaded environments.
     Browsers are created lazily only when needed by tools.
+
+    Uses per-key events to serialize creation for the same thread_id without
+    blocking unrelated callers or wasting resources on duplicate sessions.
     """
 
     def __init__(self, region: str = "us-west-2"):
@@ -27,8 +33,10 @@ class BrowserSessionManager:
             region: AWS region for browser client
         """
         self.region = region
+        self._lock = threading.Lock()
         self._async_sessions: dict[str, tuple[BrowserClient, AsyncBrowser]] = {}
         self._sync_sessions: dict[str, tuple[BrowserClient, SyncBrowser]] = {}
+        self._creating: dict[str, threading.Event] = {}
 
     async def get_async_browser(self, thread_id: str) -> AsyncBrowser:
         """Get or create an async browser for the specified thread.
@@ -39,10 +47,29 @@ class BrowserSessionManager:
         Returns:
             An async browser instance specific to the thread
         """
-        if thread_id in self._async_sessions:
-            return self._async_sessions[thread_id][1]
+        loop = asyncio.get_event_loop()
+        while True:
+            with self._lock:
+                if thread_id in self._async_sessions:
+                    return self._async_sessions[thread_id][1]
+                if thread_id not in self._creating:
+                    self._creating[thread_id] = threading.Event()
+                    break
+                event = self._creating[thread_id]
+            ctx = contextvars.copy_context()
+            await loop.run_in_executor(None, ctx.run, event.wait)
 
-        return await self._create_async_browser_session(thread_id)
+        try:
+            browser_client, browser = await self._create_async_browser_session(
+                thread_id
+            )
+            with self._lock:
+                self._async_sessions[thread_id] = (browser_client, browser)
+            return browser
+        finally:
+            with self._lock:
+                evt = self._creating.pop(thread_id)
+            evt.set()
 
     def get_sync_browser(self, thread_id: str) -> SyncBrowser:
         """Get or create a sync browser for the specified thread.
@@ -53,19 +80,33 @@ class BrowserSessionManager:
         Returns:
             A sync browser instance specific to the thread
         """
-        if thread_id in self._sync_sessions:
-            return self._sync_sessions[thread_id][1]
+        while True:
+            with self._lock:
+                if thread_id in self._sync_sessions:
+                    return self._sync_sessions[thread_id][1]
+                if thread_id not in self._creating:
+                    self._creating[thread_id] = threading.Event()
+                    break
+                event = self._creating[thread_id]
+            event.wait()
 
-        return self._create_sync_browser_session(thread_id)
+        try:
+            return self._create_sync_browser_session(thread_id)
+        finally:
+            with self._lock:
+                evt = self._creating.pop(thread_id)
+            evt.set()
 
-    async def _create_async_browser_session(self, thread_id: str) -> AsyncBrowser:
+    async def _create_async_browser_session(
+        self, thread_id: str
+    ) -> tuple[BrowserClient, AsyncBrowser]:
         """Create a new async browser session for the specified thread.
 
         Args:
             thread_id: Unique identifier for the thread
 
         Returns:
-            The newly created async browser instance
+            Tuple of (BrowserClient, AsyncBrowser).
 
         Raises:
             Exception: If browser session creation fails
@@ -75,10 +116,8 @@ class BrowserSessionManager:
         browser_client = BrowserClient(region=self.region)
 
         try:
-            # Start browser session
             browser_client.start()
 
-            # Get WebSocket connection info
             ws_url, headers = browser_client.generate_ws_headers()
 
             logger.info(
@@ -87,7 +126,6 @@ class BrowserSessionManager:
 
             from playwright.async_api import async_playwright
 
-            # Connect to browser using Playwright
             playwright = await async_playwright().start()
             browser = await playwright.chromium.connect_over_cdp(
                 endpoint_url=ws_url, headers=headers, timeout=30000
@@ -96,17 +134,13 @@ class BrowserSessionManager:
                 f"Successfully connected to async browser for thread {thread_id}"
             )
 
-            # Store session resources
-            self._async_sessions[thread_id] = (browser_client, browser)
-
-            return browser
+            return browser_client, browser
 
         except Exception as e:
             logger.error(
                 f"Failed to create async browser session for thread {thread_id}: {e}"
             )
 
-            # Clean up resources if session creation fails
             if browser_client:
                 try:
                     browser_client.stop()
@@ -132,10 +166,8 @@ class BrowserSessionManager:
         browser_client = BrowserClient(region=self.region)
 
         try:
-            # Start browser session
             browser_client.start()
 
-            # Get WebSocket connection info
             ws_url, headers = browser_client.generate_ws_headers()
 
             logger.info(
@@ -144,7 +176,6 @@ class BrowserSessionManager:
 
             from playwright.sync_api import sync_playwright
 
-            # Connect to browser using Playwright
             playwright = sync_playwright().start()
             browser = playwright.chromium.connect_over_cdp(
                 endpoint_url=ws_url, headers=headers, timeout=30000
@@ -153,8 +184,8 @@ class BrowserSessionManager:
                 f"Successfully connected to sync browser for thread {thread_id}"
             )
 
-            # Store session resources
-            self._sync_sessions[thread_id] = (browser_client, browser)
+            with self._lock:
+                self._sync_sessions[thread_id] = (browser_client, browser)
 
             return browser
 
@@ -163,7 +194,6 @@ class BrowserSessionManager:
                 f"Failed to create sync browser session for thread {thread_id}: {e}"
             )
 
-            # Clean up resources if session creation fails
             if browser_client:
                 try:
                     browser_client.stop()
@@ -178,13 +208,13 @@ class BrowserSessionManager:
         Args:
             thread_id: Unique identifier for the thread
         """
-        if thread_id not in self._async_sessions:
-            logger.warning(f"No async browser session found for thread {thread_id}")
-            return
+        with self._lock:
+            if thread_id not in self._async_sessions:
+                logger.warning(f"No async browser session found for thread {thread_id}")
+                return
 
-        browser_client, browser = self._async_sessions[thread_id]
+            browser_client, browser = self._async_sessions.pop(thread_id)
 
-        # Close browser
         if browser:
             try:
                 await browser.close()
@@ -193,7 +223,6 @@ class BrowserSessionManager:
                     f"Error closing async browser for thread {thread_id}: {e}"
                 )
 
-        # Stop browser client
         if browser_client:
             try:
                 browser_client.stop()
@@ -202,8 +231,6 @@ class BrowserSessionManager:
                     f"Error stopping browser client for thread {thread_id}: {e}"
                 )
 
-        # Remove session from dictionary
-        del self._async_sessions[thread_id]
         logger.info(f"Async browser session cleaned up for thread {thread_id}")
 
     def close_sync_browser(self, thread_id: str) -> None:
@@ -212,13 +239,13 @@ class BrowserSessionManager:
         Args:
             thread_id: Unique identifier for the thread
         """
-        if thread_id not in self._sync_sessions:
-            logger.warning(f"No sync browser session found for thread {thread_id}")
-            return
+        with self._lock:
+            if thread_id not in self._sync_sessions:
+                logger.warning(f"No sync browser session found for thread {thread_id}")
+                return
 
-        browser_client, browser = self._sync_sessions[thread_id]
+            browser_client, browser = self._sync_sessions.pop(thread_id)
 
-        # Close browser
         if browser:
             try:
                 browser.close()
@@ -227,7 +254,6 @@ class BrowserSessionManager:
                     f"Error closing sync browser for thread {thread_id}: {e}"
                 )
 
-        # Stop browser client
         if browser_client:
             try:
                 browser_client.stop()
@@ -236,19 +262,17 @@ class BrowserSessionManager:
                     f"Error stopping browser client for thread {thread_id}: {e}"
                 )
 
-        # Remove session from dictionary
-        del self._sync_sessions[thread_id]
         logger.info(f"Sync browser session cleaned up for thread {thread_id}")
 
     async def close_all_browsers(self) -> None:
         """Close all browser sessions."""
-        # Close all async browsers
-        async_thread_ids = list(self._async_sessions.keys())
+        with self._lock:
+            async_thread_ids = list(self._async_sessions.keys())
+            sync_thread_ids = list(self._sync_sessions.keys())
+
         for thread_id in async_thread_ids:
             await self.close_async_browser(thread_id)
 
-        # Close all sync browsers
-        sync_thread_ids = list(self._sync_sessions.keys())
         for thread_id in sync_thread_ids:
             self.close_sync_browser(thread_id)
 

lib/crewai-tools/src/crewai_tools/rag/core.py

@@ -1,9 +1,11 @@
 import logging
+import os
 from pathlib import Path
 from typing import Any
 from uuid import uuid4
 
 import chromadb
+from crewai.utilities.lock_store import lock as store_lock
 from pydantic import BaseModel, Field, PrivateAttr
 
 from crewai_tools.rag.base_loader import BaseLoader
@@ -38,22 +40,32 @@ class RAG(Adapter):
     _client: Any = PrivateAttr()
     _collection: Any = PrivateAttr()
     _embedding_service: EmbeddingService = PrivateAttr()
+    _lock_name: str = PrivateAttr(default="")
 
     def model_post_init(self, __context: Any) -> None:
         try:
-            if self.persist_directory:
-                self._client = chromadb.PersistentClient(path=self.persist_directory)
-            else:
-                self._client = chromadb.Client()
-
-            self._collection = self._client.get_or_create_collection(
-                name=self.collection_name,
-                metadata={
-                    "hnsw:space": "cosine",
-                    "description": "CrewAI Knowledge Base",
-                },
+            self._lock_name = (
+                f"chromadb:{os.path.realpath(self.persist_directory)}"
+                if self.persist_directory
+                else "chromadb:ephemeral"
             )
 
+            with store_lock(self._lock_name):
+                if self.persist_directory:
+                    self._client = chromadb.PersistentClient(
+                        path=self.persist_directory
+                    )
+                else:
+                    self._client = chromadb.Client()
+
+                self._collection = self._client.get_or_create_collection(
+                    name=self.collection_name,
+                    metadata={
+                        "hnsw:space": "cosine",
+                        "description": "CrewAI Knowledge Base",
+                    },
+                )
+
             self._embedding_service = EmbeddingService(
                 provider=self.embedding_provider,
                 model=self.embedding_model,
@@ -87,29 +99,8 @@ class RAG(Adapter):
         loader_result = loader.load(source_content)
         doc_id = loader_result.doc_id
 
-        existing_doc = self._collection.get(
-            where={"source": source_content.source_ref}, limit=1
-        )
-        existing_doc_id = (
-            existing_doc and existing_doc["metadatas"][0]["doc_id"]
-            if existing_doc["metadatas"]
-            else None
-        )
-
-        if existing_doc_id == doc_id:
-            logger.warning(
-                f"Document with source {loader_result.source} already exists"
-            )
-            return
-
-        # Document with same source ref does exists but the content has changed, deleting the oldest reference
-        if existing_doc_id and existing_doc_id != loader_result.doc_id:
-            logger.warning(f"Deleting old document with doc_id {existing_doc_id}")
-            self._collection.delete(where={"doc_id": existing_doc_id})
-
-        documents = []
-
         chunks = chunker.chunk(loader_result.content)
+        documents = []
         for i, chunk in enumerate(chunks):
             doc_metadata = (metadata or {}).copy()
             doc_metadata["chunk_index"] = i
@@ -136,7 +127,6 @@ class RAG(Adapter):
 
         ids = [doc.id for doc in documents]
         metadatas = []
-
         for doc in documents:
             doc_metadata = doc.metadata.copy()
             doc_metadata.update(
@@ -148,16 +138,36 @@ class RAG(Adapter):
             )
             metadatas.append(doc_metadata)
 
-        try:
-            self._collection.add(
-                ids=ids,
-                embeddings=embeddings,
-                documents=contents,
-                metadatas=metadatas,
+        with store_lock(self._lock_name):
+            existing_doc = self._collection.get(
+                where={"source": source_content.source_ref}, limit=1
             )
-            logger.info(f"Added {len(documents)} documents to knowledge base")
-        except Exception as e:
-            logger.error(f"Failed to add documents to ChromaDB: {e}")
+            existing_doc_id = (
+                existing_doc and existing_doc["metadatas"][0]["doc_id"]
+                if existing_doc["metadatas"]
+                else None
+            )
+
+            if existing_doc_id == doc_id:
+                logger.warning(
+                    f"Document with source {loader_result.source} already exists"
+                )
+                return
+
+            if existing_doc_id and existing_doc_id != loader_result.doc_id:
+                logger.warning(f"Deleting old document with doc_id {existing_doc_id}")
+                self._collection.delete(where={"doc_id": existing_doc_id})
+
+            try:
+                self._collection.add(
+                    ids=ids,
+                    embeddings=embeddings,
+                    documents=contents,
+                    metadatas=metadatas,
+                )
+                logger.info(f"Added {len(documents)} documents to knowledge base")
+            except Exception as e:
+                logger.error(f"Failed to add documents to ChromaDB: {e}")
 
     def query(self, question: str, where: dict[str, Any] | None = None) -> str:  # type: ignore
         try:
@@ -201,7 +211,8 @@ class RAG(Adapter):
 
     def delete_collection(self) -> None:
         try:
-            self._client.delete_collection(self.collection_name)
+            with store_lock(self._lock_name):
+                self._client.delete_collection(self.collection_name)
             logger.info(f"Deleted collection: {self.collection_name}")
         except Exception as e:
             logger.error(f"Failed to delete collection: {e}")

lib/crewai-tools/src/crewai_tools/tools/__init__.py

@@ -1,7 +1,18 @@
 from crewai_tools.tools.ai_mind_tool.ai_mind_tool import AIMindTool
 from crewai_tools.tools.apify_actors_tool.apify_actors_tool import ApifyActorsTool
 from crewai_tools.tools.arxiv_paper_tool.arxiv_paper_tool import ArxivPaperTool
+from crewai_tools.tools.brave_search_tool.brave_image_tool import BraveImageSearchTool
+from crewai_tools.tools.brave_search_tool.brave_llm_context_tool import (
+    BraveLLMContextTool,
+)
+from crewai_tools.tools.brave_search_tool.brave_local_pois_tool import (
+    BraveLocalPOIsDescriptionTool,
+    BraveLocalPOIsTool,
+)
+from crewai_tools.tools.brave_search_tool.brave_news_tool import BraveNewsSearchTool
 from crewai_tools.tools.brave_search_tool.brave_search_tool import BraveSearchTool
+from crewai_tools.tools.brave_search_tool.brave_video_tool import BraveVideoSearchTool
+from crewai_tools.tools.brave_search_tool.brave_web_tool import BraveWebSearchTool
 from crewai_tools.tools.brightdata_tool import (
     BrightDataDatasetTool,
     BrightDataSearchTool,
@@ -185,7 +196,14 @@ __all__ = [
     "AIMindTool",
     "ApifyActorsTool",
     "ArxivPaperTool",
+    "BraveImageSearchTool",
+    "BraveLLMContextTool",
+    "BraveLocalPOIsDescriptionTool",
+    "BraveLocalPOIsTool",
+    "BraveNewsSearchTool",
     "BraveSearchTool",
+    "BraveVideoSearchTool",
+    "BraveWebSearchTool",
     "BrightDataDatasetTool",
     "BrightDataSearchTool",
     "BrightDataWebUnlockerTool",

lib/crewai-tools/src/crewai_tools/tools/brave_search_tool/base.py

@@ -0,0 +1,322 @@
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+from datetime import datetime
+import json
+import logging
+import os
+import threading
+import time
+from typing import Any, ClassVar
+
+from crewai.tools import BaseTool, EnvVar
+from pydantic import BaseModel, Field
+import requests
+
+
+logger = logging.getLogger(__name__)
+
+# Brave API error codes that indicate non-retryable quota/usage exhaustion.
+_QUOTA_CODES = frozenset({"QUOTA_LIMITED", "USAGE_LIMIT_EXCEEDED"})
+
+
+def _save_results_to_file(content: str) -> None:
+    """Saves the search results to a file."""
+    filename = f"search_results_{datetime.now().strftime('%Y-%m-%d_%H-%M-%S')}.txt"
+    with open(filename, "w") as file:
+        file.write(content)
+
+
+def _parse_error_body(resp: requests.Response) -> dict[str, Any] | None:
+    """Extract the structured "error" object from a Brave API error response."""
+    try:
+        body = resp.json()
+        error = body.get("error")
+        return error if isinstance(error, dict) else None
+    except (ValueError, KeyError):
+        return None
+
+
+def _raise_for_error(resp: requests.Response) -> None:
+    """Brave Search API error responses contain helpful JSON payloads"""
+    status = resp.status_code
+    try:
+        body = json.dumps(resp.json())
+    except (ValueError, KeyError):
+        body = resp.text[:500]
+
+    raise RuntimeError(f"Brave Search API error (HTTP {status}): {body}")
+
+
+def _is_retryable(resp: requests.Response) -> bool:
+    """Return True for transient failures that are worth retrying.
+
+    * 429 + RATE_LIMITED — the per-second sliding window is full.
+    * 5xx — transient server-side errors.
+
+    Quota exhaustion (QUOTA_LIMITED, USAGE_LIMIT_EXCEEDED) is
+    explicitly excluded: retrying will never succeed until the billing
+    period resets.
+    """
+    if resp.status_code == 429:
+        error = _parse_error_body(resp) or {}
+        return error.get("code") not in _QUOTA_CODES
+    return 500 <= resp.status_code < 600
+
+
+def _retry_delay(resp: requests.Response, attempt: int) -> float:
+    """Compute wait time before the next retry attempt.
+
+    Prefers the server-supplied Retry-After header when available;
+    falls back to exponential backoff (1s, 2s, 4s, ...).
+    """
+    retry_after = resp.headers.get("Retry-After")
+    if retry_after is not None:
+        try:
+            return max(0.0, float(retry_after))
+        except (ValueError, TypeError):
+            pass
+    return float(2**attempt)
+
+
+class BraveSearchToolBase(BaseTool, ABC):
+    """
+    Base class for Brave Search API interactions.
+
+    Individual tool subclasses must provide the following:
+      - search_url
+      - header_schema (pydantic model)
+      - args_schema (pydantic model)
+      - _refine_payload() -> dict[str, Any]
+    """
+
+    search_url: str
+    raw: bool = False
+    args_schema: type[BaseModel]
+    header_schema: type[BaseModel]
+
+    # Tool options (legacy parameters)
+    country: str | None = None
+    save_file: bool = False
+    n_results: int = 10
+
+    env_vars: list[EnvVar] = Field(
+        default_factory=lambda: [
+            EnvVar(
+                name="BRAVE_API_KEY",
+                description="API key for Brave Search",
+                required=True,
+            ),
+        ]
+    )
+
+    def __init__(
+        self,
+        *,
+        api_key: str | None = None,
+        headers: dict[str, Any] | None = None,
+        requests_per_second: float = 1.0,
+        save_file: bool = False,
+        raw: bool = False,
+        timeout: int = 30,
+        **kwargs: Any,
+    ):
+        super().__init__(**kwargs)
+
+        self._api_key = api_key or os.environ.get("BRAVE_API_KEY")
+        if not self._api_key:
+            raise ValueError("BRAVE_API_KEY environment variable is required")
+
+        self.raw = bool(raw)
+        self._timeout = int(timeout)
+        self.save_file = bool(save_file)
+        self._requests_per_second = float(requests_per_second)
+        self._headers = self._build_and_validate_headers(headers or {})
+        # Per-instance rate limiting: each instance has its own clock and lock.
+        # Total process rate is the sum of limits of instances you create.
+        self._last_request_time: float = 0
+        self._rate_limit_lock = threading.Lock()
+
+    @property
+    def api_key(self) -> str:
+        return self._api_key
+
+    @property
+    def headers(self) -> dict[str, Any]:
+        return self._headers
+
+    def set_headers(self, headers: dict[str, Any]) -> BraveSearchToolBase:
+        merged = {**self._headers, **{k.lower(): v for k, v in headers.items()}}
+        self._headers = self._build_and_validate_headers(merged)
+        return self
+
+    def _build_and_validate_headers(self, headers: dict[str, Any]) -> dict[str, Any]:
+        normalized = {k.lower(): v for k, v in headers.items()}
+        normalized.setdefault("x-subscription-token", self._api_key)
+        normalized.setdefault("accept", "application/json")
+
+        try:
+            self.header_schema(**normalized)
+        except Exception as e:
+            raise ValueError(f"Invalid headers: {e}") from e
+
+        return normalized
+
+    def _rate_limit(self) -> None:
+        """Enforce minimum interval between requests for this instance. Thread-safe."""
+        if self._requests_per_second <= 0:
+            return
+
+        min_interval = 1.0 / self._requests_per_second
+        with self._rate_limit_lock:
+            now = time.time()
+            next_allowed = self._last_request_time + min_interval
+            if now < next_allowed:
+                time.sleep(next_allowed - now)
+                now = time.time()
+            self._last_request_time = now
+
+    def _make_request(
+        self, params: dict[str, Any], *, _max_retries: int = 3
+    ) -> dict[str, Any]:
+        """Execute an HTTP GET against the Brave Search API with retry logic."""
+        last_resp: requests.Response | None = None
+
+        # Retry the request up to _max_retries times
+        for attempt in range(_max_retries):
+            self._rate_limit()
+
+            # Make the request
+            try:
+                resp = requests.get(
+                    self.search_url,
+                    headers=self._headers,
+                    params=params,
+                    timeout=self._timeout,
+                )
+            except requests.ConnectionError as exc:
+                raise RuntimeError(
+                    f"Brave Search API connection failed: {exc}"
+                ) from exc
+            except requests.Timeout as exc:
+                raise RuntimeError(
+                    f"Brave Search API request timed out after {self._timeout}s: {exc}"
+                ) from exc
+
+            # Log the rate limit headers and request details
+            logger.debug(
+                "Brave Search API request: %s %s -> %d",
+                "GET",
+                resp.url,
+                resp.status_code,
+            )
+
+            # Response was OK, return the JSON body
+            if resp.ok:
+                try:
+                    return resp.json()
+                except ValueError as exc:
+                    raise RuntimeError(
+                        f"Brave Search API returned invalid JSON (HTTP {resp.status_code}): {exc}"
+                    ) from exc
+
+            # Response was not OK, but is retryable
+            # (e.g., 429 Too Many Requests, 500 Internal Server Error)
+            if _is_retryable(resp) and attempt < _max_retries - 1:
+                delay = _retry_delay(resp, attempt)
+                logger.warning(
+                    "Brave Search API returned %d. Retrying in %.1fs (attempt %d/%d)",
+                    resp.status_code,
+                    delay,
+                    attempt + 1,
+                    _max_retries,
+                )
+                time.sleep(delay)
+                last_resp = resp
+                continue
+
+            # Response was not OK, nor was it retryable
+            # (e.g., 422 Unprocessable Entity, 400 Bad Request (OPTION_NOT_IN_PLAN))
+            _raise_for_error(resp)
+
+        # All retries exhausted
+        _raise_for_error(last_resp or resp)  # type: ignore[possibly-undefined]
+        return {}  # unreachable (here to satisfy the type checker and linter)
+
+    def _run(self, q: str | None = None, **params: Any) -> Any:
+        # Allow positional usage: tool.run("latest Brave browser features")
+        if q is not None:
+            params["q"] = q
+
+        params = self._common_payload_refinement(params)
+
+        # Validate only schema fields
+        schema_keys = self.args_schema.model_fields
+        payload_in = {k: v for k, v in params.items() if k in schema_keys}
+
+        try:
+            validated = self.args_schema(**payload_in)
+        except Exception as e:
+            raise ValueError(f"Invalid parameters: {e}") from e
+
+        # The subclass may have additional refinements to apply to the payload, such as goggles or other parameters
+        payload = self._refine_request_payload(validated.model_dump(exclude_none=True))
+        response = self._make_request(payload)
+
+        if not self.raw:
+            response = self._refine_response(response)
+
+        if self.save_file:
+            _save_results_to_file(json.dumps(response, indent=2))
+
+        return response
+
+    @abstractmethod
+    def _refine_request_payload(self, params: dict[str, Any]) -> dict[str, Any]:
+        """Subclass must implement: transform validated params dict into API request params."""
+        raise NotImplementedError
+
+    @abstractmethod
+    def _refine_response(self, response: dict[str, Any]) -> Any:
+        """Subclass must implement: transform response dict into a more useful format."""
+        raise NotImplementedError
+
+    _EMPTY_VALUES: ClassVar[tuple[None, str, str, list[Any]]] = (None, "", "null", [])
+
+    def _common_payload_refinement(self, params: dict[str, Any]) -> dict[str, Any]:
+        """Common payload refinement for all tools."""
+        # crewAI's schema pipeline (ensure_all_properties_required in
+        # pydantic_schema_utils.py) marks every property as required so
+        # that OpenAI strict-mode structured outputs work correctly.
+        # The side-effect is that the LLM fills in *every* parameter —
+        # even truly optional ones — using placeholder values such as
+        # None, "", "null", or [].  Only optional fields are affected,
+        # so we limit the check to those.
+        fields = self.args_schema.model_fields
+        params = {
+            k: v
+            for k, v in params.items()
+            # Permit custom and required fields, and fields with non-empty values
+            if k not in fields or fields[k].is_required() or v not in self._EMPTY_VALUES
+        }
+
+        # Make sure params has "q" for query instead of "query" or "search_query"
+        query = params.get("query") or params.get("search_query")
+        if query is not None and "q" not in params:
+            params["q"] = query
+        params.pop("query", None)
+        params.pop("search_query", None)
+
+        # If "count" was not explicitly provided, use n_results
+        # (only when the schema actually supports a "count" field)
+        if "count" in self.args_schema.model_fields:
+            if "count" not in params and self.n_results is not None:
+                params["count"] = self.n_results
+
+        # If "country" was not explicitly provided, but self.country is set, use it
+        # (only when the schema actually supports a "country" field)
+        if "country" in self.args_schema.model_fields:
+            if "country" not in params and self.country is not None:
+                params["country"] = self.country
+
+        return params

lib/crewai-tools/src/crewai_tools/tools/brave_search_tool/brave_image_tool.py

@@ -0,0 +1,42 @@
+from typing import Any
+
+from pydantic import BaseModel
+
+from crewai_tools.tools.brave_search_tool.base import BraveSearchToolBase
+from crewai_tools.tools.brave_search_tool.schemas import (
+    ImageSearchHeaders,
+    ImageSearchParams,
+)
+
+
+class BraveImageSearchTool(BraveSearchToolBase):
+    """A tool that performs image searches using the Brave Search API."""
+
+    name: str = "Brave Image Search"
+    args_schema: type[BaseModel] = ImageSearchParams
+    header_schema: type[BaseModel] = ImageSearchHeaders
+
+    description: str = (
+        "A tool that performs image searches using the Brave Search API. "
+        "Results are returned as structured JSON data."
+    )
+
+    search_url: str = "https://api.search.brave.com/res/v1/images/search"
+
+    def _refine_request_payload(self, params: dict[str, Any]) -> dict[str, Any]:
+        return params
+
+    def _refine_response(self, response: dict[str, Any]) -> list[dict[str, Any]]:
+        # Make the response more concise, and easier to consume
+        results = response.get("results", [])
+        return [
+            {
+                "title": result.get("title"),
+                "url": result.get("properties", {}).get("url"),
+                "dimensions": f"{w}x{h}"
+                if (w := result.get("properties", {}).get("width"))
+                and (h := result.get("properties", {}).get("height"))
+                else None,
+            }
+            for result in results
+        ]

lib/crewai-tools/src/crewai_tools/tools/brave_search_tool/brave_llm_context_tool.py

@@ -0,0 +1,32 @@
+from typing import Any
+
+from pydantic import BaseModel
+
+from crewai_tools.tools.brave_search_tool.base import BraveSearchToolBase
+from crewai_tools.tools.brave_search_tool.response_types import LLMContext
+from crewai_tools.tools.brave_search_tool.schemas import (
+    LLMContextHeaders,
+    LLMContextParams,
+)
+
+
+class BraveLLMContextTool(BraveSearchToolBase):
+    """A tool that retrieves context for LLM usage from the Brave Search API."""
+
+    name: str = "Brave LLM Context"
+    args_schema: type[BaseModel] = LLMContextParams
+    header_schema: type[BaseModel] = LLMContextHeaders
+
+    description: str = (
+        "A tool that retrieves context for LLM usage from the Brave Search API. "
+        "Results are returned as structured JSON data."
+    )
+
+    search_url: str = "https://api.search.brave.com/res/v1/llm/context"
+
+    def _refine_request_payload(self, params: dict[str, Any]) -> dict[str, Any]:
+        return params
+
+    def _refine_response(self, response: LLMContext.Response) -> LLMContext.Response:
+        """The LLM Context response schema is fairly simple. Return as is."""
+        return response

lib/crewai-tools/src/crewai_tools/tools/brave_search_tool/brave_local_pois_tool.py

@@ -0,0 +1,109 @@
+from typing import Any
+
+from pydantic import BaseModel
+
+from crewai_tools.tools.brave_search_tool.base import BraveSearchToolBase
+from crewai_tools.tools.brave_search_tool.response_types import LocalPOIs
+from crewai_tools.tools.brave_search_tool.schemas import (
+    LocalPOIsDescriptionHeaders,
+    LocalPOIsDescriptionParams,
+    LocalPOIsHeaders,
+    LocalPOIsParams,
+)
+
+
+DayOpeningHours = LocalPOIs.DayOpeningHours
+OpeningHours = LocalPOIs.OpeningHours
+LocationResult = LocalPOIs.LocationResult
+LocalPOIsResponse = LocalPOIs.Response
+
+
+def _flatten_slots(slots: list[DayOpeningHours]) -> list[dict[str, str]]:
+    """Convert a list of DayOpeningHours dicts into simplified entries."""
+    return [
+        {
+            "day": slot["full_name"].lower(),
+            "opens": slot["opens"],
+            "closes": slot["closes"],
+        }
+        for slot in slots
+    ]
+
+
+def _simplify_opening_hours(result: LocationResult) -> list[dict[str, str]] | None:
+    """Collapse opening_hours into a flat list of {day, opens, closes} dicts."""
+    hours = result.get("opening_hours")
+    if not hours:
+        return None
+
+    entries: list[dict[str, str]] = []
+
+    current = hours.get("current_day")
+    if current:
+        entries.extend(_flatten_slots(current))
+
+    days = hours.get("days")
+    if days:
+        for day_slots in days:
+            entries.extend(_flatten_slots(day_slots))
+
+    return entries or None
+
+
+class BraveLocalPOIsTool(BraveSearchToolBase):
+    """A tool that retrieves local POIs using the Brave Search API."""
+
+    name: str = "Brave Local POIs"
+    args_schema: type[BaseModel] = LocalPOIsParams
+    header_schema: type[BaseModel] = LocalPOIsHeaders
+    description: str = (
+        "A tool that retrieves local POIs using the Brave Search API. "
+        "Results are returned as structured JSON data."
+    )
+    search_url: str = "https://api.search.brave.com/res/v1/local/pois"
+
+    def _refine_request_payload(self, params: dict[str, Any]) -> dict[str, Any]:
+        return params
+
+    def _refine_response(self, response: LocalPOIsResponse) -> list[dict[str, Any]]:
+        results = response.get("results", [])
+        return [
+            {
+                "title": result.get("title"),
+                "url": result.get("url"),
+                "description": result.get("description"),
+                "address": result.get("postal_address", {}).get("displayAddress"),
+                "contact": result.get("contact", {}).get("telephone")
+                or result.get("contact", {}).get("email")
+                or None,
+                "opening_hours": _simplify_opening_hours(result),
+            }
+            for result in results
+        ]
+
+
+class BraveLocalPOIsDescriptionTool(BraveSearchToolBase):
+    """A tool that retrieves AI-generated descriptions for local POIs using the Brave Search API."""
+
+    name: str = "Brave Local POI Descriptions"
+    args_schema: type[BaseModel] = LocalPOIsDescriptionParams
+    header_schema: type[BaseModel] = LocalPOIsDescriptionHeaders
+    description: str = (
+        "A tool that retrieves AI-generated descriptions for local POIs using the Brave Search API. "
+        "Results are returned as structured JSON data."
+    )
+    search_url: str = "https://api.search.brave.com/res/v1/local/descriptions"
+
+    def _refine_request_payload(self, params: dict[str, Any]) -> dict[str, Any]:
+        return params
+
+    def _refine_response(self, response: LocalPOIsResponse) -> list[dict[str, Any]]:
+        # Make the response more concise, and easier to consume
+        results = response.get("results", [])
+        return [
+            {
+                "id": result.get("id"),
+                "description": result.get("description"),
+            }
+            for result in results
+        ]

lib/crewai-tools/src/crewai_tools/tools/brave_search_tool/brave_news_tool.py

@@ -0,0 +1,39 @@
+from typing import Any
+
+from pydantic import BaseModel
+
+from crewai_tools.tools.brave_search_tool.base import BraveSearchToolBase
+from crewai_tools.tools.brave_search_tool.schemas import (
+    NewsSearchHeaders,
+    NewsSearchParams,
+)
+
+
+class BraveNewsSearchTool(BraveSearchToolBase):
+    """A tool that performs news searches using the Brave Search API."""
+
+    name: str = "Brave News Search"
+    args_schema: type[BaseModel] = NewsSearchParams
+    header_schema: type[BaseModel] = NewsSearchHeaders
+
+    description: str = (
+        "A tool that performs news searches using the Brave Search API. "
+        "Results are returned as structured JSON data."
+    )
+
+    search_url: str = "https://api.search.brave.com/res/v1/news/search"
+
+    def _refine_request_payload(self, params: dict[str, Any]) -> dict[str, Any]:
+        return params
+
+    def _refine_response(self, response: dict[str, Any]) -> list[dict[str, Any]]:
+        # Make the response more concise, and easier to consume
+        results = response.get("results", [])
+        return [
+            {
+                "url": result.get("url"),
+                "title": result.get("title"),
+                "description": result.get("description"),
+            }
+            for result in results
+        ]

lib/crewai-tools/src/crewai_tools/tools/brave_search_tool/brave_search_tool.py

@@ -1,4 +1,3 @@
-from datetime import datetime
 import json
 import os
 import time
@@ -10,16 +9,13 @@ from pydantic import BaseModel, Field
 from pydantic.types import StringConstraints
 import requests
 
+from crewai_tools.tools.brave_search_tool.base import _save_results_to_file
+from crewai_tools.tools.brave_search_tool.schemas import WebSearchParams
+
+
 load_dotenv()
 
 
-def _save_results_to_file(content: str) -> None:
-    """Saves the search results to a file."""
-    filename = f"search_results_{datetime.now().strftime('%Y-%m-%d_%H-%M-%S')}.txt"
-    with open(filename, "w") as file:
-        file.write(content)
-
-
 FreshnessPreset = Literal["pd", "pw", "pm", "py"]
 FreshnessRange = Annotated[
     str, StringConstraints(pattern=r"^\d{4}-\d{2}-\d{2}to\d{4}-\d{2}-\d{2}$")
@@ -28,51 +24,6 @@ Freshness = FreshnessPreset | FreshnessRange
 SafeSearch = Literal["off", "moderate", "strict"]
 
 
-class BraveSearchToolSchema(BaseModel):
-    """Input for BraveSearchTool"""
-
-    query: str = Field(..., description="Search query to perform")
-    country: str | None = Field(
-        default=None,
-        description="Country code for geo-targeting (e.g., 'US', 'BR').",
-    )
-    search_language: str | None = Field(
-        default=None,
-        description="Language code for the search results (e.g., 'en', 'es').",
-    )
-    count: int | None = Field(
-        default=None,
-        description="The maximum number of results to return. Actual number may be less.",
-    )
-    offset: int | None = Field(
-        default=None, description="Skip the first N result sets/pages. Max is 9."
-    )
-    safesearch: SafeSearch | None = Field(
-        default=None,
-        description="Filter out explicit content. Options: off/moderate/strict",
-    )
-    spellcheck: bool | None = Field(
-        default=None,
-        description="Attempt to correct spelling errors in the search query.",
-    )
-    freshness: Freshness | None = Field(
-        default=None,
-        description="Enforce freshness of results. Options: pd/pw/pm/py, or YYYY-MM-DDtoYYYY-MM-DD",
-    )
-    text_decorations: bool | None = Field(
-        default=None,
-        description="Include markup to highlight search terms in the results.",
-    )
-    extra_snippets: bool | None = Field(
-        default=None,
-        description="Include up to 5 text snippets for each page if possible.",
-    )
-    operators: bool | None = Field(
-        default=None,
-        description="Whether to apply search operators (e.g., site:example.com).",
-    )
-
-
 # TODO: Extend support to additional endpoints (e.g., /images, /news, etc.)
 class BraveSearchTool(BaseTool):
     """A tool that performs web searches using the Brave Search API."""
@@ -82,7 +33,7 @@ class BraveSearchTool(BaseTool):
         "A tool that performs web searches using the Brave Search API. "
         "Results are returned as structured JSON data."
     )
-    args_schema: type[BaseModel] = BraveSearchToolSchema
+    args_schema: type[BaseModel] = WebSearchParams
     search_url: str = "https://api.search.brave.com/res/v1/web/search"
     n_results: int = 10
     save_file: bool = False
@@ -119,8 +70,8 @@ class BraveSearchTool(BaseTool):
 
         # Construct and send the request
         try:
-            # Maintain both "search_query" and "query" for backwards compatibility
-            query = kwargs.get("search_query") or kwargs.get("query")
+            # Fallback to "query" or "search_query" for backwards compatibility
+            query = kwargs.get("q") or kwargs.get("query") or kwargs.get("search_query")
             if not query:
                 raise ValueError("Query is required")
 
@@ -129,8 +80,11 @@ class BraveSearchTool(BaseTool):
             if country := kwargs.get("country"):
                 payload["country"] = country
 
-            if search_language := kwargs.get("search_language"):
-                payload["search_language"] = search_language
+            # Fallback to "search_language" for backwards compatibility
+            if search_lang := kwargs.get("search_lang") or kwargs.get(
+                "search_language"
+            ):
+                payload["search_lang"] = search_lang
 
             # Fallback to deprecated n_results parameter if no count is provided
             count = kwargs.get("count")

lib/crewai-tools/src/crewai_tools/tools/brave_search_tool/brave_video_tool.py

@@ -0,0 +1,39 @@
+from typing import Any
+
+from pydantic import BaseModel
+
+from crewai_tools.tools.brave_search_tool.base import BraveSearchToolBase
+from crewai_tools.tools.brave_search_tool.schemas import (
+    VideoSearchHeaders,
+    VideoSearchParams,
+)
+
+
+class BraveVideoSearchTool(BraveSearchToolBase):
+    """A tool that performs video searches using the Brave Search API."""
+
+    name: str = "Brave Video Search"
+    args_schema: type[BaseModel] = VideoSearchParams
+    header_schema: type[BaseModel] = VideoSearchHeaders
+
+    description: str = (
+        "A tool that performs video searches using the Brave Search API. "
+        "Results are returned as structured JSON data."
+    )
+
+    search_url: str = "https://api.search.brave.com/res/v1/videos/search"
+
+    def _refine_request_payload(self, params: dict[str, Any]) -> dict[str, Any]:
+        return params
+
+    def _refine_response(self, response: dict[str, Any]) -> list[dict[str, Any]]:
+        # Make the response more concise, and easier to consume
+        results = response.get("results", [])
+        return [
+            {
+                "url": result.get("url"),
+                "title": result.get("title"),
+                "description": result.get("description"),
+            }
+            for result in results
+        ]

lib/crewai-tools/src/crewai_tools/tools/brave_search_tool/brave_web_tool.py

@@ -0,0 +1,45 @@
+from typing import Any
+
+from pydantic import BaseModel
+
+from crewai_tools.tools.brave_search_tool.base import BraveSearchToolBase
+from crewai_tools.tools.brave_search_tool.schemas import (
+    WebSearchHeaders,
+    WebSearchParams,
+)
+
+
+class BraveWebSearchTool(BraveSearchToolBase):
+    """A tool that performs web searches using the Brave Search API."""
+
+    name: str = "Brave Web Search"
+    args_schema: type[BaseModel] = WebSearchParams
+    header_schema: type[BaseModel] = WebSearchHeaders
+
+    description: str = (
+        "A tool that performs web searches using the Brave Search API. "
+        "Results are returned as structured JSON data."
+    )
+
+    search_url: str = "https://api.search.brave.com/res/v1/web/search"
+
+    def _refine_request_payload(self, params: dict[str, Any]) -> dict[str, Any]:
+        return params
+
+    def _refine_response(self, response: dict[str, Any]) -> list[dict[str, Any]]:
+        results = response.get("web", {}).get("results", [])
+        refined = []
+        for result in results:
+            snippets = result.get("extra_snippets") or []
+            if not snippets:
+                desc = result.get("description")
+                if desc:
+                    snippets = [desc]
+            refined.append(
+                {
+                    "url": result.get("url"),
+                    "title": result.get("title"),
+                    "snippets": snippets,
+                }
+            )
+        return refined

lib/crewai-tools/src/crewai_tools/tools/brave_search_tool/response_types.py

@@ -0,0 +1,67 @@
+from __future__ import annotations
+
+from typing import Literal, TypedDict
+
+
+class LocalPOIs:
+    class PostalAddress(TypedDict, total=False):
+        type: Literal["PostalAddress"]
+        country: str
+        postalCode: str
+        streetAddress: str
+        addressRegion: str
+        addressLocality: str
+        displayAddress: str
+
+    class DayOpeningHours(TypedDict):
+        abbr_name: str
+        full_name: str
+        opens: str
+        closes: str
+
+    class OpeningHours(TypedDict, total=False):
+        current_day: list[LocalPOIs.DayOpeningHours]
+        days: list[list[LocalPOIs.DayOpeningHours]]
+
+    class LocationResult(TypedDict, total=False):
+        provider_url: str
+        title: str
+        url: str
+        id: str | None
+        opening_hours: LocalPOIs.OpeningHours | None
+        postal_address: LocalPOIs.PostalAddress | None
+
+    class Response(TypedDict, total=False):
+        type: Literal["local_pois"]
+        results: list[LocalPOIs.LocationResult]
+
+
+class LLMContext:
+    class LLMContextItem(TypedDict, total=False):
+        snippets: list[str]
+        title: str
+        url: str
+
+    class LLMContextMapItem(TypedDict, total=False):
+        name: str
+        snippets: list[str]
+        title: str
+        url: str
+
+    class LLMContextPOIItem(TypedDict, total=False):
+        name: str
+        snippets: list[str]
+        title: str
+        url: str
+
+    class Grounding(TypedDict, total=False):
+        generic: list[LLMContext.LLMContextItem]
+        poi: LLMContext.LLMContextPOIItem
+        map: list[LLMContext.LLMContextMapItem]
+
+    class Sources(TypedDict, total=False):
+        pass
+
+    class Response(TypedDict, total=False):
+        grounding: LLMContext.Grounding
+        sources: LLMContext.Sources

lib/crewai-tools/src/crewai_tools/tools/brave_search_tool/schemas.py

@@ -0,0 +1,525 @@
+from typing import Annotated, Literal
+
+from pydantic import BaseModel, Field
+from pydantic.types import StringConstraints
+
+
+# Common types
+Units = Literal["metric", "imperial"]
+SafeSearch = Literal["off", "moderate", "strict"]
+Freshness = (
+    Literal["pd", "pw", "pm", "py"]
+    | Annotated[
+        str, StringConstraints(pattern=r"^\d{4}-\d{2}-\d{2}to\d{4}-\d{2}-\d{2}$")
+    ]
+)
+ResultFilter = list[
+    Literal[
+        "discussions",
+        "faq",
+        "infobox",
+        "news",
+        "query",
+        "summarizer",
+        "videos",
+        "web",
+        "locations",
+    ]
+]
+
+
+class LLMContextParams(BaseModel):
+    """Parameters for Brave LLM Context endpoint."""
+
+    q: str = Field(
+        description="Search query to perform",
+        min_length=1,
+        max_length=400,
+    )
+    country: str | None = Field(
+        default=None,
+        description="Country code for geo-targeting (e.g., 'US', 'BR').",
+        pattern=r"^[A-Z]{2}$",
+    )
+    search_lang: str | None = Field(
+        default=None,
+        description="Language code for the search results (e.g., 'en', 'es').",
+        pattern=r"^[a-z]{2}$",
+    )
+    count: int | None = Field(
+        default=None,
+        description="The maximum number of results to return. Actual number may be less.",
+        ge=1,
+        le=50,
+    )
+    maximum_number_of_urls: int | None = Field(
+        default=None,
+        description="The maximum number of URLs to include in the context.",
+        ge=1,
+        le=50,
+    )
+    maximum_number_of_tokens: int | None = Field(
+        default=None,
+        description="The approximate maximum number of tokens to include in the context.",
+        ge=1,
+        le=32768,
+    )
+    maximum_number_of_snippets: int | None = Field(
+        default=None,
+        description="The maximum number of different snippets to include in the context.",
+        ge=1,
+        le=100,
+    )
+    context_threshold_mode: (
+        Literal["disabled", "strict", "lenient", "balanced"] | None
+    ) = Field(
+        default=None,
+        description="The mode to use for the context thresholding.",
+    )
+    maximum_number_of_tokens_per_url: int | None = Field(
+        default=None,
+        description="The maximum number of tokens to include for each URL in the context.",
+        ge=1,
+        le=8192,
+    )
+    maximum_number_of_snippets_per_url: int | None = Field(
+        default=None,
+        description="The maximum number of snippets to include per URL.",
+        ge=1,
+        le=100,
+    )
+    goggles: str | list[str] | None = Field(
+        default=None,
+        description="Goggles act as a custom re-ranking mechanism. Goggle source or URLs.",
+    )
+    enable_local: bool | None = Field(
+        default=None,
+        description="Whether to enable local recall. Not setting this value means auto-detect and uses local recall if any of the localization headers are provided.",
+    )
+
+
+class WebSearchParams(BaseModel):
+    """Parameters for Brave Web Search endpoint."""
+
+    q: str = Field(
+        description="Search query to perform",
+        min_length=1,
+        max_length=400,
+    )
+    country: str | None = Field(
+        default=None,
+        description="Country code for geo-targeting (e.g., 'US', 'BR').",
+        pattern=r"^[A-Z]{2}$",
+    )
+    search_lang: str | None = Field(
+        default=None,
+        description="Language code for the search results (e.g., 'en', 'es').",
+        pattern=r"^[a-z]{2}$",
+    )
+    ui_lang: str | None = Field(
+        default=None,
+        description="Language code for the user interface (e.g., 'en-US', 'es-AR').",
+        pattern=r"^[a-z]{2}-[A-Z]{2}$",
+    )
+    count: int | None = Field(
+        default=None,
+        description="The maximum number of results to return. Actual number may be less.",
+        ge=1,
+        le=20,
+    )
+    offset: int | None = Field(
+        default=None,
+        description="Skip the first N result sets/pages. Max is 9.",
+        ge=0,
+        le=9,
+    )
+    safesearch: Literal["off", "moderate", "strict"] | None = Field(
+        default=None,
+        description="Filter out explicit content. Options: off/moderate/strict",
+    )
+    spellcheck: bool | None = Field(
+        default=None,
+        description="Attempt to correct spelling errors in the search query.",
+    )
+    freshness: Freshness | None = Field(
+        default=None,
+        description="Enforce freshness of results. Options: pd/pw/pm/py, or YYYY-MM-DDtoYYYY-MM-DD",
+    )
+    text_decorations: bool | None = Field(
+        default=None,
+        description="Include markup to highlight search terms in the results.",
+    )
+    extra_snippets: bool | None = Field(
+        default=None,
+        description="Include up to 5 text snippets for each page if possible.",
+    )
+    result_filter: ResultFilter | None = Field(
+        default=None,
+        description="Filter the results by type. Options: discussions/faq/infobox/news/query/summarizer/videos/web/locations. Note: The `count` parameter is applied only to the `web` results.",
+    )
+    units: Units | None = Field(
+        default=None,
+        description="The units to use for the results. Options: metric/imperial",
+    )
+    goggles: str | list[str] | None = Field(
+        default=None,
+        description="Goggles act as a custom re-ranking mechanism. Goggle source or URLs.",
+    )
+    summary: bool | None = Field(
+        default=None,
+        description="Whether to generate a summarizer ID for the results.",
+    )
+    enable_rich_callback: bool | None = Field(
+        default=None,
+        description="Whether to enable rich callbacks for the results. Requires Pro level subscription.",
+    )
+    include_fetch_metadata: bool | None = Field(
+        default=None,
+        description="Whether to include fetch metadata (e.g., last fetch time) in the results.",
+    )
+    operators: bool | None = Field(
+        default=None,
+        description="Whether to apply search operators (e.g., site:example.com).",
+    )
+
+
+class LocalPOIsParams(BaseModel):
+    """Parameters for Brave Local POIs endpoint."""
+
+    ids: list[str] = Field(
+        description="List of POI IDs to retrieve. Maximum of 20. IDs are valid for 8 hours.",
+        min_length=1,
+        max_length=20,
+    )
+    search_lang: str | None = Field(
+        default=None,
+        description="Language code for the search results (e.g., 'en', 'es').",
+        pattern=r"^[a-z]{2}$",
+    )
+    ui_lang: str | None = Field(
+        default=None,
+        description="Language code for the user interface (e.g., 'en-US', 'es-AR').",
+        pattern=r"^[a-z]{2}-[A-Z]{2}$",
+    )
+    units: Units | None = Field(
+        default=None,
+        description="The units to use for the results. Options: metric/imperial",
+    )
+
+
+class LocalPOIsDescriptionParams(BaseModel):
+    """Parameters for Brave Local POI Descriptions endpoint."""
+
+    ids: list[str] = Field(
+        description="List of POI IDs to retrieve. Maximum of 20. IDs are valid for 8 hours.",
+        min_length=1,
+        max_length=20,
+    )
+
+
+class ImageSearchParams(BaseModel):
+    """Parameters for Brave Image Search endpoint."""
+
+    q: str = Field(
+        description="Search query to perform",
+        min_length=1,
+        max_length=400,
+    )
+    search_lang: str | None = Field(
+        default=None,
+        description="Language code for the search results (e.g., 'en', 'es').",
+        pattern=r"^[a-z]{2}$",
+    )
+    country: str | None = Field(
+        default=None,
+        description="Country code for geo-targeting (e.g., 'US', 'BR').",
+        pattern=r"^[A-Z]{2}$",
+    )
+    safesearch: Literal["off", "strict"] | None = Field(
+        default=None,
+        description="Filter out explicit content. Default is strict.",
+    )
+    count: int | None = Field(
+        default=None,
+        description="The maximum number of results to return.",
+        ge=1,
+        le=200,
+    )
+    spellcheck: bool | None = Field(
+        default=None,
+        description="Attempt to correct spelling errors in the search query.",
+    )
+
+
+class VideoSearchParams(BaseModel):
+    """Parameters for Brave Video Search endpoint."""
+
+    q: str = Field(
+        description="Search query to perform",
+        min_length=1,
+        max_length=400,
+    )
+    search_lang: str | None = Field(
+        default=None,
+        description="Language code for the search results (e.g., 'en', 'es').",
+        pattern=r"^[a-z]{2}$",
+    )
+    ui_lang: str | None = Field(
+        default=None,
+        description="Language code for the user interface (e.g., 'en-US', 'es-AR').",
+        pattern=r"^[a-z]{2}-[A-Z]{2}$",
+    )
+    country: str | None = Field(
+        default=None,
+        description="Country code for geo-targeting (e.g., 'US', 'BR').",
+        pattern=r"^[A-Z]{2}$",
+    )
+    safesearch: SafeSearch | None = Field(
+        default=None,
+        description="Filter out explicit content. Options: off/moderate/strict",
+    )
+    count: int | None = Field(
+        default=None,
+        description="The maximum number of results to return.",
+        ge=1,
+        le=50,
+    )
+    offset: int | None = Field(
+        default=None,
+        description="Skip the first N result sets/pages. Max is 9.",
+        ge=0,
+        le=9,
+    )
+    spellcheck: bool | None = Field(
+        default=None,
+        description="Attempt to correct spelling errors in the search query.",
+    )
+    freshness: Freshness | None = Field(
+        default=None,
+        description="Enforce freshness of results. Options: pd/pw/pm/py, or YYYY-MM-DDtoYYYY-MM-DD",
+    )
+    include_fetch_metadata: bool | None = Field(
+        default=None,
+        description="Whether to include fetch metadata (e.g., last fetch time) in the results.",
+    )
+    operators: bool | None = Field(
+        default=None,
+        description="Whether to apply search operators (e.g., site:example.com).",
+    )
+
+
+class NewsSearchParams(BaseModel):
+    """Parameters for Brave News Search endpoint."""
+
+    q: str = Field(
+        description="Search query to perform",
+        min_length=1,
+        max_length=400,
+    )
+    search_lang: str | None = Field(
+        default=None,
+        description="Language code for the search results (e.g., 'en', 'es').",
+        pattern=r"^[a-z]{2}$",
+    )
+    ui_lang: str | None = Field(
+        default=None,
+        description="Language code for the user interface (e.g., 'en-US', 'es-AR').",
+        pattern=r"^[a-z]{2}-[A-Z]{2}$",
+    )
+    country: str | None = Field(
+        default=None,
+        description="Country code for geo-targeting (e.g., 'US', 'BR').",
+        pattern=r"^[A-Z]{2}$",
+    )
+    safesearch: Literal["off", "moderate", "strict"] | None = Field(
+        default=None,
+        description="Filter out explicit content. Options: off/moderate/strict",
+    )
+    count: int | None = Field(
+        default=None,
+        description="The maximum number of results to return.",
+        ge=1,
+        le=50,
+    )
+    offset: int | None = Field(
+        default=None,
+        description="Skip the first N result sets/pages. Max is 9.",
+        ge=0,
+        le=9,
+    )
+    spellcheck: bool | None = Field(
+        default=None,
+        description="Attempt to correct spelling errors in the search query.",
+    )
+    freshness: Freshness | None = Field(
+        default=None,
+        description="Enforce freshness of results. Options: pd/pw/pm/py, or YYYY-MM-DDtoYYYY-MM-DD",
+    )
+    extra_snippets: bool | None = Field(
+        default=None,
+        description="Include up to 5 text snippets for each page if possible.",
+    )
+    goggles: str | list[str] | None = Field(
+        default=None,
+        description="Goggles act as a custom re-ranking mechanism. Goggle source or URLs.",
+    )
+    include_fetch_metadata: bool | None = Field(
+        default=None,
+        description="Whether to include fetch metadata in the results.",
+    )
+    operators: bool | None = Field(
+        default=None,
+        description="Whether to apply search operators (e.g., site:example.com).",
+    )
+
+
+class BaseSearchHeaders(BaseModel):
+    """Common headers for Brave Search endpoints."""
+
+    x_subscription_token: str = Field(
+        alias="x-subscription-token",
+        description="API key for Brave Search",
+    )
+    api_version: str | None = Field(
+        alias="api-version",
+        default=None,
+        description="API version to use. Default is latest available.",
+        pattern=r"^\d{4}-\d{2}-\d{2}$",  # YYYY-MM-DD
+    )
+    accept: Literal["application/json"] | Literal["*/*"] | None = Field(
+        default=None,
+        description="Accept header for the request.",
+    )
+    cache_control: Literal["no-cache"] | None = Field(
+        alias="cache-control",
+        default=None,
+        description="Cache control header for the request.",
+    )
+    user_agent: str | None = Field(
+        alias="user-agent",
+        default=None,
+        description="User agent for the request.",
+    )
+
+
+class LLMContextHeaders(BaseSearchHeaders):
+    """Headers for Brave LLM Context endpoint."""
+
+    x_loc_lat: float | None = Field(
+        alias="x-loc-lat",
+        default=None,
+        description="Latitude of the user's location.",
+        ge=-90.0,
+        le=90.0,
+    )
+    x_loc_long: float | None = Field(
+        alias="x-loc-long",
+        default=None,
+        description="Longitude of the user's location.",
+        ge=-180.0,
+        le=180.0,
+    )
+    x_loc_city: str | None = Field(
+        alias="x-loc-city",
+        default=None,
+        description="City of the user's location.",
+    )
+    x_loc_state: str | None = Field(
+        alias="x-loc-state",
+        default=None,
+        description="State of the user's location.",
+    )
+    x_loc_state_name: str | None = Field(
+        alias="x-loc-state-name",
+        default=None,
+        description="Name of the state of the user's location.",
+    )
+    x_loc_country: str | None = Field(
+        alias="x-loc-country",
+        default=None,
+        description="The ISO 3166-1 alpha-2 country code of the user's location.",
+    )
+
+
+class LocalPOIsHeaders(BaseSearchHeaders):
+    """Headers for Brave Local POIs endpoint."""
+
+    x_loc_lat: float | None = Field(
+        alias="x-loc-lat",
+        default=None,
+        description="Latitude of the user's location.",
+        ge=-90.0,
+        le=90.0,
+    )
+    x_loc_long: float | None = Field(
+        alias="x-loc-long",
+        default=None,
+        description="Longitude of the user's location.",
+        ge=-180.0,
+        le=180.0,
+    )
+
+
+class LocalPOIsDescriptionHeaders(BaseSearchHeaders):
+    """Headers for Brave Local POI Descriptions endpoint."""
+
+
+class VideoSearchHeaders(BaseSearchHeaders):
+    """Headers for Brave Video Search endpoint."""
+
+
+class ImageSearchHeaders(BaseSearchHeaders):
+    """Headers for Brave Image Search endpoint."""
+
+
+class NewsSearchHeaders(BaseSearchHeaders):
+    """Headers for Brave News Search endpoint."""
+
+
+class WebSearchHeaders(BaseSearchHeaders):
+    """Headers for Brave Web Search endpoint."""
+
+    x_loc_lat: float | None = Field(
+        alias="x-loc-lat",
+        default=None,
+        description="Latitude of the user's location.",
+        ge=-90.0,
+        le=90.0,
+    )
+    x_loc_long: float | None = Field(
+        alias="x-loc-long",
+        default=None,
+        description="Longitude of the user's location.",
+        ge=-180.0,
+        le=180.0,
+    )
+    x_loc_timezone: str | None = Field(
+        alias="x-loc-timezone",
+        default=None,
+        description="Timezone of the user's location.",
+    )
+    x_loc_city: str | None = Field(
+        alias="x-loc-city",
+        default=None,
+        description="City of the user's location.",
+    )
+    x_loc_state: str | None = Field(
+        alias="x-loc-state",
+        default=None,
+        description="State of the user's location.",
+    )
+    x_loc_state_name: str | None = Field(
+        alias="x-loc-state-name",
+        default=None,
+        description="Name of the state of the user's location.",
+    )
+    x_loc_country: str | None = Field(
+        alias="x-loc-country",
+        default=None,
+        description="The ISO 3166-1 alpha-2 country code of the user's location.",
+    )
+    x_loc_postal_code: str | None = Field(
+        alias="x-loc-postal-code",
+        default=None,
+        description="The postal code of the user's location.",
+    )

lib/crewai-tools/src/crewai_tools/tools/code_interpreter_tool/README.md

@@ -1,13 +1,27 @@
 # CodeInterpreterTool
 
 ## Description
-This tool is used to give the Agent the ability to run code (Python3) from the code generated by the Agent itself. The code is executed in a sandboxed environment, so it is safe to run any code.
+This tool is used to give the Agent the ability to run code (Python3) from the code generated by the Agent itself. The code is executed in a Docker container for secure isolation.
 
-It is incredible useful since it allows the Agent to generate code, run it in the same environment, get the result and use it to make decisions.
+It is incredibly useful since it allows the Agent to generate code, run it in an isolated environment, get the result and use it to make decisions.
+
+## ⚠️ Security Requirements
+
+**Docker is REQUIRED** for safe code execution. The tool will refuse to execute code without Docker to prevent security vulnerabilities.
+
+### Why Docker is Required
+
+Previous versions included a "restricted sandbox" fallback when Docker was unavailable. This has been **removed** due to critical security vulnerabilities:
+
+- The Python-based sandbox could be escaped via object introspection
+- Attackers could recover the original `__import__` function and access any module
+- This allowed arbitrary command execution on the host system
+
+**Docker provides real process isolation** and is the only secure way to execute untrusted code.
 
 ## Requirements
 
-- Docker
+- **Docker (REQUIRED)** - Install from [docker.com](https://docs.docker.com/get-docker/)
 
 ## Installation
 Install the crewai_tools package
@@ -17,7 +31,9 @@ pip install 'crewai[tools]'
 
 ## Example
 
-Remember that when using this tool, the code must be generated by the Agent itself. The code must be a Python3 code. And it will take some time for the first time to run because it needs to build the Docker image.
+Remember that when using this tool, the code must be generated by the Agent itself. The code must be Python3 code. It will take some time the first time to run because it needs to build the Docker image.
+
+### Basic Usage (Docker Container - Recommended)
 
 ```python
 from crewai_tools import CodeInterpreterTool
@@ -28,7 +44,9 @@ Agent(
 )
 ```
 
-Or if you need to pass your own Dockerfile just do this
+### Custom Dockerfile
+
+If you need to pass your own Dockerfile:
 
 ```python
 from crewai_tools import CodeInterpreterTool
@@ -39,15 +57,39 @@ Agent(
 )
 ```
 
-If it is difficult to connect to docker daemon automatically (especially for macOS users), you can do this to setup docker host manually
+### Manual Docker Host Configuration
+
+If it is difficult to connect to the Docker daemon automatically (especially for macOS users), you can set up the Docker host manually:
 
 ```python 
 from crewai_tools import CodeInterpreterTool
 
 Agent(
     ...
-    tools=[CodeInterpreterTool(user_docker_base_url="<Docker Host Base Url>",
-        user_dockerfile_path="<Dockerfile_path>")],
+    tools=[CodeInterpreterTool(
+        user_docker_base_url="<Docker Host Base Url>",
+        user_dockerfile_path="<Dockerfile_path>"
+    )],
 )
-
 ```
+
+### Unsafe Mode (NOT RECOMMENDED)
+
+If you absolutely cannot use Docker and **fully trust the code source**, you can use unsafe mode:
+
+```python
+from crewai_tools import CodeInterpreterTool
+
+# WARNING: Only use with fully trusted code!
+Agent(
+    ...
+    tools=[CodeInterpreterTool(unsafe_mode=True)],
+)
+```
+
+**⚠️ SECURITY WARNING:** `unsafe_mode=True` executes code directly on the host without any isolation. Only use this if:
+- You completely trust the code being executed
+- You understand the security risks
+- You cannot install Docker in your environment
+
+For production use, **always use Docker** (the default mode).

lib/crewai-tools/src/crewai_tools/tools/code_interpreter_tool/code_interpreter_tool.py

@@ -8,6 +8,7 @@ potentially unsafe operations and importing restricted modules.
 import importlib.util
 import os
 import subprocess
+import sys
 from types import ModuleType
 from typing import Any, ClassVar, TypedDict
 
@@ -50,11 +51,16 @@ class CodeInterpreterSchema(BaseModel):
 
 
 class SandboxPython:
-    """A restricted Python execution environment for running code safely.
+    """INSECURE: A restricted Python execution environment with known vulnerabilities.
 
-    This class provides methods to safely execute Python code by restricting access to
-    potentially dangerous modules and built-in functions. It creates a sandboxed
-    environment where harmful operations are blocked.
+    WARNING: This class does NOT provide real security isolation and is vulnerable to
+    sandbox escape attacks via Python object introspection. Attackers can recover the
+    original __import__ function and bypass all restrictions.
+
+    DO NOT USE for untrusted code execution. Use Docker containers instead.
+
+    This class attempts to restrict access to dangerous modules and built-in functions
+    but provides no real security boundary against a motivated attacker.
     """
 
     BLOCKED_MODULES: ClassVar[set[str]] = {
@@ -299,8 +305,8 @@ class CodeInterpreterTool(BaseTool):
     def run_code_safety(self, code: str, libraries_used: list[str]) -> str:
         """Runs code in the safest available environment.
 
-        Attempts to run code in Docker if available, falls back to a restricted
-        sandbox if Docker is not available.
+        Requires Docker to be available for secure code execution. Fails closed
+        if Docker is not available to prevent sandbox escape vulnerabilities.
 
         Args:
             code: The Python code to execute as a string.
@@ -308,10 +314,24 @@ class CodeInterpreterTool(BaseTool):
 
         Returns:
             The output of the executed code as a string.
+
+        Raises:
+            RuntimeError: If Docker is not available, as the restricted sandbox
+                         is vulnerable to escape attacks and should not be used
+                         for untrusted code execution.
         """
         if self._check_docker_available():
             return self.run_code_in_docker(code, libraries_used)
-        return self.run_code_in_restricted_sandbox(code)
+
+        error_msg = (
+            "Docker is required for safe code execution but is not available. "
+            "The restricted sandbox fallback has been removed due to security vulnerabilities "
+            "that allow sandbox escape via Python object introspection. "
+            "Please install Docker (https://docs.docker.com/get-docker/) or use unsafe_mode=True "
+            "if you trust the code source and understand the security risks."
+        )
+        Printer.print(error_msg, color="bold_red")
+        raise RuntimeError(error_msg)
 
     def run_code_in_docker(self, code: str, libraries_used: list[str]) -> str:
         """Runs Python code in a Docker container for safe isolation.
@@ -342,10 +362,19 @@ class CodeInterpreterTool(BaseTool):
 
     @staticmethod
     def run_code_in_restricted_sandbox(code: str) -> str:
-        """Runs Python code in a restricted sandbox environment.
+        """DEPRECATED AND INSECURE: Runs Python code in a restricted sandbox environment.
 
-        Executes the code with restricted access to potentially dangerous modules and
-        built-in functions for basic safety when Docker is not available.
+        WARNING: This method is vulnerable to sandbox escape attacks via Python object
+        introspection and should NOT be used for untrusted code execution. It has been
+        deprecated and is only kept for backward compatibility with trusted code.
+
+        The "restricted" environment can be bypassed by attackers who can:
+        - Use object graph introspection to recover the original __import__ function
+        - Access any Python module including os, subprocess, sys, etc.
+        - Execute arbitrary commands on the host system
+
+        Use run_code_in_docker() for secure code execution, or run_code_unsafe()
+        if you explicitly acknowledge the security risks.
 
         Args:
             code: The Python code to execute as a string.
@@ -354,7 +383,10 @@ class CodeInterpreterTool(BaseTool):
             The value of the 'result' variable from the executed code,
             or an error message if execution failed.
         """
-        Printer.print("Running code in restricted sandbox", color="yellow")
+        Printer.print(
+            "WARNING: Running code in INSECURE restricted sandbox (vulnerable to escape attacks)",
+            color="bold_red"
+        )
         exec_locals: dict[str, Any] = {}
         try:
             SandboxPython.exec(code=code, locals_=exec_locals)
@@ -380,7 +412,7 @@ class CodeInterpreterTool(BaseTool):
         Printer.print("WARNING: Running code in unsafe mode", color="bold_magenta")
         # Install libraries on the host machine
         for library in libraries_used:
-            os.system(f"pip install {library}")  # noqa: S605
+            subprocess.run([sys.executable, "-m", "pip", "install", library], check=False)  # noqa: S603
 
         # Execute the code
         try:

lib/crewai-tools/src/crewai_tools/tools/file_writer_tool/file_writer_tool.py

@@ -30,9 +30,8 @@ class FileWriterTool(BaseTool):
 
     def _run(self, **kwargs: Any) -> str:
         try:
-            # Create the directory if it doesn't exist
-            if kwargs.get("directory") and not os.path.exists(kwargs["directory"]):
-                os.makedirs(kwargs["directory"])
+            if kwargs.get("directory"):
+                os.makedirs(kwargs["directory"], exist_ok=True)
 
             # Construct the full path
             filepath = os.path.join(kwargs.get("directory") or "", kwargs["filename"])

lib/crewai-tools/src/crewai_tools/tools/files_compressor_tool/files_compressor_tool.py

@@ -99,8 +99,8 @@ class FileCompressorTool(BaseTool):
     def _prepare_output(output_path: str, overwrite: bool) -> bool:
         """Ensures output path is ready for writing."""
         output_dir = os.path.dirname(output_path)
-        if output_dir and not os.path.exists(output_dir):
-            os.makedirs(output_dir)
+        if output_dir:
+            os.makedirs(output_dir, exist_ok=True)
         if os.path.exists(output_path) and not overwrite:
             return False
         return True

lib/crewai-tools/src/crewai_tools/tools/merge_agent_handler_tool/merge_agent_handler_tool.py

@@ -18,7 +18,6 @@ class MergeAgentHandlerToolError(Exception):
     """Base exception for Merge Agent Handler tool errors."""
 
 
-
 class MergeAgentHandlerTool(BaseTool):
     """
     Wrapper for Merge Agent Handler tools.
@@ -174,7 +173,7 @@ class MergeAgentHandlerTool(BaseTool):
             >>> tool = MergeAgentHandlerTool.from_tool_name(
             ...     tool_name="linear__create_issue",
             ...     tool_pack_id="134e0111-0f67-44f6-98f0-597000290bb3",
-            ...     registered_user_id="91b2b905-e866-40c8-8be2-efe53827a0aa"
+            ...     registered_user_id="91b2b905-e866-40c8-8be2-efe53827a0aa",
             ... )
         """
         # Create an empty args schema model (proper BaseModel subclass)
@@ -210,7 +209,10 @@ class MergeAgentHandlerTool(BaseTool):
                     if "parameters" in tool_schema:
                         try:
                             params = tool_schema["parameters"]
-                            if params.get("type") == "object" and "properties" in params:
+                            if (
+                                params.get("type") == "object"
+                                and "properties" in params
+                            ):
                                 # Build field definitions for Pydantic
                                 fields = {}
                                 properties = params["properties"]
@@ -298,7 +300,7 @@ class MergeAgentHandlerTool(BaseTool):
             >>> tools = MergeAgentHandlerTool.from_tool_pack(
             ...     tool_pack_id="134e0111-0f67-44f6-98f0-597000290bb3",
             ...     registered_user_id="91b2b905-e866-40c8-8be2-efe53827a0aa",
-            ...     tool_names=["linear__create_issue", "linear__get_issues"]
+            ...     tool_names=["linear__create_issue", "linear__get_issues"],
             ... )
         """
         # Create a temporary instance to fetch the tool list

lib/crewai-tools/src/crewai_tools/tools/multion_tool/example.py

@@ -1,7 +1,7 @@
 import os
 
 from crewai import Agent, Crew, Task
-from multion_tool import MultiOnTool # type: ignore[import-not-found]
+from multion_tool import MultiOnTool  # type: ignore[import-not-found]
 
 
 os.environ["OPENAI_API_KEY"] = "Your Key"

lib/crewai-tools/src/crewai_tools/tools/qdrant_vector_search_tool/qdrant_search_tool.py

@@ -110,11 +110,13 @@ class QdrantVectorSearchTool(BaseTool):
             self.custom_embedding_fn(query)
             if self.custom_embedding_fn
             else (
-                lambda: __import__("openai")
-                .Client(api_key=os.getenv("OPENAI_API_KEY"))
-                .embeddings.create(input=[query], model="text-embedding-3-large")
-                .data[0]
-                .embedding
+                lambda: (
+                    __import__("openai")
+                    .Client(api_key=os.getenv("OPENAI_API_KEY"))
+                    .embeddings.create(input=[query], model="text-embedding-3-large")
+                    .data[0]
+                    .embedding
+                )
             )()
         )
         results = self.client.query_points(

lib/crewai-tools/src/crewai_tools/tools/snowflake_search_tool/snowflake_search_tool.py

@@ -3,6 +3,7 @@ from __future__ import annotations
 import asyncio
 from concurrent.futures import ThreadPoolExecutor
 import logging
+import threading
 from typing import TYPE_CHECKING, Any
 
 from crewai.tools.base_tool import BaseTool
@@ -33,6 +34,7 @@ logger = logging.getLogger(__name__)
 
 # Cache for query results
 _query_cache: dict[str, list[dict[str, Any]]] = {}
+_cache_lock = threading.Lock()
 
 
 class SnowflakeConfig(BaseModel):
@@ -102,7 +104,7 @@ class SnowflakeSearchTool(BaseTool):
     )
 
     _connection_pool: list[SnowflakeConnection] | None = None
-    _pool_lock: asyncio.Lock | None = None
+    _pool_lock: threading.Lock | None = None
     _thread_pool: ThreadPoolExecutor | None = None
     _model_rebuilt: bool = False
     package_dependencies: list[str] = Field(
@@ -122,7 +124,7 @@ class SnowflakeSearchTool(BaseTool):
         try:
             if SNOWFLAKE_AVAILABLE:
                 self._connection_pool = []
-                self._pool_lock = asyncio.Lock()
+                self._pool_lock = threading.Lock()
                 self._thread_pool = ThreadPoolExecutor(max_workers=self.pool_size)
             else:
                 raise ImportError
@@ -147,7 +149,7 @@ class SnowflakeSearchTool(BaseTool):
                     )
 
                     self._connection_pool = []
-                    self._pool_lock = asyncio.Lock()
+                    self._pool_lock = threading.Lock()
                     self._thread_pool = ThreadPoolExecutor(max_workers=self.pool_size)
                 except subprocess.CalledProcessError as e:
                     raise ImportError("Failed to install Snowflake dependencies") from e
@@ -163,13 +165,12 @@ class SnowflakeSearchTool(BaseTool):
             raise RuntimeError("Pool lock not initialized")
         if self._connection_pool is None:
             raise RuntimeError("Connection pool not initialized")
-        async with self._pool_lock:
-            if not self._connection_pool:
-                conn = await asyncio.get_event_loop().run_in_executor(
-                    self._thread_pool, self._create_connection
-                )
-                self._connection_pool.append(conn)
-            return self._connection_pool.pop()
+        with self._pool_lock:
+            if self._connection_pool:
+                return self._connection_pool.pop()
+        return await asyncio.get_event_loop().run_in_executor(
+            self._thread_pool, self._create_connection
+        )
 
     def _create_connection(self) -> SnowflakeConnection:
         """Create a new Snowflake connection."""
@@ -204,9 +205,10 @@ class SnowflakeSearchTool(BaseTool):
         """Execute a query with retries and return results."""
         if self.enable_caching:
             cache_key = self._get_cache_key(query, timeout)
-            if cache_key in _query_cache:
-                logger.info("Returning cached result")
-                return _query_cache[cache_key]
+            with _cache_lock:
+                if cache_key in _query_cache:
+                    logger.info("Returning cached result")
+                    return _query_cache[cache_key]
 
         for attempt in range(self.max_retries):
             try:
@@ -225,7 +227,8 @@ class SnowflakeSearchTool(BaseTool):
                     ]
 
                     if self.enable_caching:
-                        _query_cache[self._get_cache_key(query, timeout)] = results
+                        with _cache_lock:
+                            _query_cache[self._get_cache_key(query, timeout)] = results
 
                     return results
                 finally:
@@ -234,7 +237,7 @@ class SnowflakeSearchTool(BaseTool):
                         self._pool_lock is not None
                         and self._connection_pool is not None
                     ):
-                        async with self._pool_lock:
+                        with self._pool_lock:
                             self._connection_pool.append(conn)
             except (DatabaseError, OperationalError) as e:  # noqa: PERF203
                 if attempt == self.max_retries - 1:

lib/crewai-tools/src/crewai_tools/tools/stagehand_tool/example.py

@@ -17,11 +17,11 @@ Usage:
 
 import os
 
+from crewai import Agent, Crew, Process, Task
 from crewai.utilities.printer import Printer
 from dotenv import load_dotenv
 from stagehand.schemas import AvailableModel  # type: ignore[import-untyped]
 
-from crewai import Agent, Crew, Process, Task
 from crewai_tools import StagehandTool
 
 

lib/crewai-tools/src/crewai_tools/tools/stagehand_tool/stagehand_tool.py

@@ -1,4 +1,5 @@
 import asyncio
+import contextvars
 import json
 import os
 import re
@@ -137,7 +138,9 @@ class StagehandTool(BaseTool):
     - 'observe': For finding elements in a specific area
     """
     args_schema: type[BaseModel] = StagehandToolSchema
-    package_dependencies: list[str] = Field(default_factory=lambda: ["stagehand<=0.5.9"])
+    package_dependencies: list[str] = Field(
+        default_factory=lambda: ["stagehand<=0.5.9"]
+    )
     env_vars: list[EnvVar] = Field(
         default_factory=lambda: [
             EnvVar(
@@ -620,9 +623,12 @@ class StagehandTool(BaseTool):
                 # We're in an existing event loop, use it
                 import concurrent.futures
 
+                ctx = contextvars.copy_context()
                 with concurrent.futures.ThreadPoolExecutor() as executor:
                     future = executor.submit(
-                        asyncio.run, self._async_run(instruction, url, command_type)
+                        ctx.run,
+                        asyncio.run,
+                        self._async_run(instruction, url, command_type),
                     )
                     result = future.result()
             else:
@@ -706,11 +712,12 @@ class StagehandTool(BaseTool):
                             if loop.is_running():
                                 import concurrent.futures
 
+                                ctx = contextvars.copy_context()
                                 with (
                                     concurrent.futures.ThreadPoolExecutor() as executor
                                 ):
                                     future = executor.submit(
-                                        asyncio.run, self._async_close()
+                                        ctx.run, asyncio.run, self._async_close()
                                     )
                                     future.result()
                             else:

lib/crewai-tools/tests/tools/brave_search_tool_test.py

@@ -1,80 +1,777 @@
-import json
-from unittest.mock import patch
+import os
+from unittest.mock import MagicMock, patch
 
 import pytest
+import requests as requests_lib
 
-from crewai_tools.tools.brave_search_tool.brave_search_tool import BraveSearchTool
+from crewai_tools.tools.brave_search_tool.base import BraveSearchToolBase
+from crewai_tools.tools.brave_search_tool.brave_web_tool import BraveWebSearchTool
+from crewai_tools.tools.brave_search_tool.brave_image_tool import BraveImageSearchTool
+from crewai_tools.tools.brave_search_tool.brave_news_tool import BraveNewsSearchTool
+from crewai_tools.tools.brave_search_tool.brave_video_tool import BraveVideoSearchTool
+from crewai_tools.tools.brave_search_tool.brave_llm_context_tool import (
+    BraveLLMContextTool,
+)
+from crewai_tools.tools.brave_search_tool.brave_local_pois_tool import (
+    BraveLocalPOIsTool,
+    BraveLocalPOIsDescriptionTool,
+)
+from crewai_tools.tools.brave_search_tool.schemas import (
+    WebSearchParams,
+    WebSearchHeaders,
+    ImageSearchParams,
+    ImageSearchHeaders,
+    NewsSearchParams,
+    NewsSearchHeaders,
+    VideoSearchParams,
+    VideoSearchHeaders,
+    LLMContextParams,
+    LLMContextHeaders,
+    LocalPOIsParams,
+    LocalPOIsHeaders,
+    LocalPOIsDescriptionParams,
+    LocalPOIsDescriptionHeaders,
+)
+
+
+def _mock_response(
+    status_code: int = 200,
+    json_data: dict | None = None,
+    headers: dict | None = None,
+    text: str = "",
+) -> MagicMock:
+    """Build a ``requests.Response``-like mock with the attributes used by ``_make_request``."""
+    resp = MagicMock(spec=requests_lib.Response)
+    resp.status_code = status_code
+    resp.ok = 200 <= status_code < 400
+    resp.url = "https://api.search.brave.com/res/v1/web/search?q=test"
+    resp.text = text or (str(json_data) if json_data else "")
+    resp.headers = headers or {}
+    resp.json.return_value = json_data if json_data is not None else {}
+    return resp
+
+
+# Fixtures
+
+
+@pytest.fixture(autouse=True)
+def _brave_env_and_rate_limit():
+    """Set BRAVE_API_KEY for every test. Rate limiting is per-instance (each tool starts with a fresh clock)."""
+    with patch.dict(os.environ, {"BRAVE_API_KEY": "test-api-key"}):
+        yield
 
 
 @pytest.fixture
-def brave_tool():
-    return BraveSearchTool(n_results=2)
+def web_tool():
+    return BraveWebSearchTool()
 
 
-def test_brave_tool_initialization():
-    tool = BraveSearchTool()
-    assert tool.n_results == 10
+@pytest.fixture
+def image_tool():
+    return BraveImageSearchTool()
+
+
+@pytest.fixture
+def news_tool():
+    return BraveNewsSearchTool()
+
+
+@pytest.fixture
+def video_tool():
+    return BraveVideoSearchTool()
+
+
+# Initialization
+
+ALL_TOOL_CLASSES = [
+    BraveWebSearchTool,
+    BraveImageSearchTool,
+    BraveNewsSearchTool,
+    BraveVideoSearchTool,
+    BraveLLMContextTool,
+    BraveLocalPOIsTool,
+    BraveLocalPOIsDescriptionTool,
+]
+
+
+@pytest.mark.parametrize("tool_cls", ALL_TOOL_CLASSES)
+def test_instantiation_with_env_var(tool_cls):
+    """Each tool can be created when BRAVE_API_KEY is in the environment."""
+    tool = tool_cls()
+    assert tool.api_key == "test-api-key"
+
+
+@pytest.mark.parametrize("tool_cls", ALL_TOOL_CLASSES)
+def test_instantiation_with_explicit_key(tool_cls):
+    """An explicit api_key takes precedence over the environment."""
+    tool = tool_cls(api_key="explicit-key")
+    assert tool.api_key == "explicit-key"
+
+
+def test_missing_api_key_raises():
+    with patch.dict(os.environ, {}, clear=True):
+        with pytest.raises(ValueError, match="BRAVE_API_KEY"):
+            BraveWebSearchTool()
+
+
+def test_default_attributes():
+    tool = BraveWebSearchTool()
     assert tool.save_file is False
+    assert tool.n_results == 10
+    assert tool._timeout == 30
+    assert tool._requests_per_second == 1.0
+    assert tool.raw is False
 
 
-@patch("requests.get")
-def test_brave_tool_search(mock_get, brave_tool):
-    mock_response = {
+def test_custom_constructor_args():
+    tool = BraveWebSearchTool(
+        save_file=True,
+        timeout=60,
+        n_results=5,
+        requests_per_second=0.5,
+        raw=True,
+    )
+    assert tool.save_file is True
+    assert tool._timeout == 60
+    assert tool.n_results == 5
+    assert tool._requests_per_second == 0.5
+    assert tool.raw is True
+
+
+# Headers
+
+
+def test_default_headers():
+    tool = BraveWebSearchTool()
+    assert tool.headers["x-subscription-token"] == "test-api-key"
+    assert tool.headers["accept"] == "application/json"
+
+
+def test_set_headers_merges_and_normalizes():
+    tool = BraveWebSearchTool()
+    tool.set_headers({"Cache-Control": "no-cache"})
+    assert tool.headers["cache-control"] == "no-cache"
+    assert tool.headers["x-subscription-token"] == "test-api-key"
+
+
+def test_set_headers_returns_self_for_chaining():
+    tool = BraveWebSearchTool()
+    assert tool.set_headers({"Cache-Control": "no-cache"}) is tool
+
+
+def test_invalid_header_value_raises():
+    tool = BraveImageSearchTool()
+    with pytest.raises(ValueError, match="Invalid headers"):
+        tool.set_headers({"Accept": "text/xml"})
+
+
+# Endpoint & Schema Wiring
+
+
+@pytest.mark.parametrize(
+    "tool_cls, expected_url, expected_params, expected_headers",
+    [
+        (
+            BraveWebSearchTool,
+            "https://api.search.brave.com/res/v1/web/search",
+            WebSearchParams,
+            WebSearchHeaders,
+        ),
+        (
+            BraveImageSearchTool,
+            "https://api.search.brave.com/res/v1/images/search",
+            ImageSearchParams,
+            ImageSearchHeaders,
+        ),
+        (
+            BraveNewsSearchTool,
+            "https://api.search.brave.com/res/v1/news/search",
+            NewsSearchParams,
+            NewsSearchHeaders,
+        ),
+        (
+            BraveVideoSearchTool,
+            "https://api.search.brave.com/res/v1/videos/search",
+            VideoSearchParams,
+            VideoSearchHeaders,
+        ),
+        (
+            BraveLLMContextTool,
+            "https://api.search.brave.com/res/v1/llm/context",
+            LLMContextParams,
+            LLMContextHeaders,
+        ),
+        (
+            BraveLocalPOIsTool,
+            "https://api.search.brave.com/res/v1/local/pois",
+            LocalPOIsParams,
+            LocalPOIsHeaders,
+        ),
+        (
+            BraveLocalPOIsDescriptionTool,
+            "https://api.search.brave.com/res/v1/local/descriptions",
+            LocalPOIsDescriptionParams,
+            LocalPOIsDescriptionHeaders,
+        ),
+    ],
+)
+def test_tool_wiring(tool_cls, expected_url, expected_params, expected_headers):
+    tool = tool_cls()
+    assert tool.search_url == expected_url
+    assert tool.args_schema is expected_params
+    assert tool.header_schema is expected_headers
+
+
+# Payload Refinement  (e.g., `query` -> `q`, `count` fallback, param pass-through)
+
+
+def test_web_refine_request_payload_passes_all_params(web_tool):
+    params = web_tool._common_payload_refinement(
+        {
+            "query": "test",
+            "country": "US",
+            "search_lang": "en",
+            "count": 5,
+            "offset": 2,
+            "safesearch": "moderate",
+            "freshness": "pw",
+        }
+    )
+    refined_params = web_tool._refine_request_payload(params)
+
+    assert refined_params["q"] == "test"
+    assert "query" not in refined_params
+    assert refined_params["count"] == 5
+    assert refined_params["country"] == "US"
+    assert refined_params["search_lang"] == "en"
+    assert refined_params["offset"] == 2
+    assert refined_params["safesearch"] == "moderate"
+    assert refined_params["freshness"] == "pw"
+
+
+def test_image_refine_request_payload_passes_all_params(image_tool):
+    params = image_tool._common_payload_refinement(
+        {
+            "query": "cat photos",
+            "country": "US",
+            "search_lang": "en",
+            "safesearch": "strict",
+            "count": 50,
+            "spellcheck": True,
+        }
+    )
+    refined_params = image_tool._refine_request_payload(params)
+
+    assert refined_params["q"] == "cat photos"
+    assert "query" not in refined_params
+    assert refined_params["country"] == "US"
+    assert refined_params["safesearch"] == "strict"
+    assert refined_params["count"] == 50
+    assert refined_params["spellcheck"] is True
+
+
+def test_news_refine_request_payload_passes_all_params(news_tool):
+    params = news_tool._common_payload_refinement(
+        {
+            "query": "breaking news",
+            "country": "US",
+            "count": 10,
+            "offset": 1,
+            "freshness": "pd",
+            "extra_snippets": True,
+        }
+    )
+    refined_params = news_tool._refine_request_payload(params)
+
+    assert refined_params["q"] == "breaking news"
+    assert "query" not in refined_params
+    assert refined_params["country"] == "US"
+    assert refined_params["offset"] == 1
+    assert refined_params["freshness"] == "pd"
+    assert refined_params["extra_snippets"] is True
+
+
+def test_video_refine_request_payload_passes_all_params(video_tool):
+    params = video_tool._common_payload_refinement(
+        {
+            "query": "tutorial",
+            "country": "US",
+            "count": 25,
+            "offset": 0,
+            "safesearch": "strict",
+            "freshness": "pm",
+        }
+    )
+    refined_params = video_tool._refine_request_payload(params)
+
+    assert refined_params["q"] == "tutorial"
+    assert "query" not in refined_params
+    assert refined_params["country"] == "US"
+    assert refined_params["offset"] == 0
+    assert refined_params["freshness"] == "pm"
+
+
+def test_legacy_constructor_params_flow_into_query_params():
+    """The legacy n_results and country constructor params are applied as defaults
+    when count/country are not explicitly provided at call time."""
+    tool = BraveWebSearchTool(n_results=3, country="BR")
+    params = tool._common_payload_refinement({"query": "test"})
+
+    assert params["count"] == 3
+    assert params["country"] == "BR"
+
+
+def test_legacy_constructor_params_do_not_override_explicit_query_params():
+    """Explicit query-time count/country take precedence over constructor defaults."""
+    tool = BraveWebSearchTool(n_results=3, country="BR")
+    params = tool._common_payload_refinement(
+        {"query": "test", "count": 10, "country": "US"}
+    )
+
+    assert params["count"] == 10
+    assert params["country"] == "US"
+
+
+def test_refine_request_payload_passes_multiple_goggles_as_multiple_params(web_tool):
+    result = web_tool._refine_request_payload(
+        {
+            "query": "test",
+            "goggles": ["goggle1", "goggle2"],
+        }
+    )
+    assert result["goggles"] == ["goggle1", "goggle2"]
+
+
+# Null-like / empty value stripping
+#
+# crewAI's ensure_all_properties_required (pydantic_schema_utils.py) marks
+# every schema property as required for OpenAI strict-mode compatibility.
+# Because optional Brave API parameters look required to the LLM, it fills
+# them with placeholder junk — None, "", "null", or [].  The test below
+# verifies that _common_payload_refinement strips these from optional fields.
+
+
+def test_common_refinement_strips_null_like_values(web_tool):
+    """_common_payload_refinement drops optional keys with None / '' / 'null' / []."""
+    params = web_tool._common_payload_refinement(
+        {
+            "query": "test",
+            "country": "US",
+            "search_lang": "",
+            "freshness": "null",
+            "count": 5,
+            "goggles": [],
+        }
+    )
+    assert params["q"] == "test"
+    assert params["country"] == "US"
+    assert params["count"] == 5
+    assert "search_lang" not in params
+    assert "freshness" not in params
+    assert "goggles" not in params
+
+
+# End-to-End _run() with Mocked HTTP Response
+
+
+@patch("crewai_tools.tools.brave_search_tool.base.requests.get")
+def test_web_search_end_to_end(mock_get, web_tool):
+    web_tool.raw = True
+    data = {"web": {"results": [{"title": "R", "url": "http://r.co"}]}}
+    mock_get.return_value = _mock_response(json_data=data)
+
+    result = web_tool._run(query="test")
+
+    mock_get.assert_called_once()
+    call_args = mock_get.call_args.kwargs
+    assert call_args["params"]["q"] == "test"
+    assert call_args["headers"]["x-subscription-token"] == "test-api-key"
+    assert result == data
+
+
+@patch("crewai_tools.tools.brave_search_tool.base.requests.get")
+def test_image_search_end_to_end(mock_get, image_tool):
+    image_tool.raw = True
+    data = {"results": [{"url": "http://img.co/a.jpg"}]}
+    mock_get.return_value = _mock_response(json_data=data)
+
+    assert image_tool._run(query="cats") == data
+
+
+@patch("crewai_tools.tools.brave_search_tool.base.requests.get")
+def test_news_search_end_to_end(mock_get, news_tool):
+    news_tool.raw = True
+    data = {"results": [{"title": "News", "url": "http://n.co"}]}
+    mock_get.return_value = _mock_response(json_data=data)
+
+    assert news_tool._run(query="headlines") == data
+
+
+@patch("crewai_tools.tools.brave_search_tool.base.requests.get")
+def test_video_search_end_to_end(mock_get, video_tool):
+    video_tool.raw = True
+    data = {"results": [{"title": "Vid", "url": "http://v.co"}]}
+    mock_get.return_value = _mock_response(json_data=data)
+
+    assert video_tool._run(query="python tutorial") == data
+
+
+@patch("crewai_tools.tools.brave_search_tool.base.requests.get")
+def test_raw_false_calls_refine_response(mock_get, web_tool):
+    """With raw=False (the default), _refine_response transforms the API response."""
+    api_response = {
         "web": {
             "results": [
                 {
-                    "title": "Test Title",
-                    "url": "http://test.com",
-                    "description": "Test Description",
+                    "title": "CrewAI",
+                    "url": "https://crewai.com",
+                    "description": "AI agent framework",
                 }
             ]
         }
     }
-    mock_get.return_value.json.return_value = mock_response
+    mock_get.return_value = _mock_response(json_data=api_response)
 
-    result = brave_tool.run(query="test")
-    data = json.loads(result)
-    assert isinstance(data, list)
-    assert len(data) >= 1
-    assert data[0]["title"] == "Test Title"
-    assert data[0]["url"] == "http://test.com"
+    assert web_tool.raw is False
+    result = web_tool._run(query="crewai")
+
+    # The web tool's _refine_response extracts and reshapes results.
+    # The key assertion: we should NOT get back the raw API envelope.
+    assert result != api_response
 
 
-@patch("requests.get")
-def test_brave_tool(mock_get):
-    mock_response = {
-        "web": {
-            "results": [
-                {
-                    "title": "Brave Browser",
-                    "url": "https://brave.com",
-                    "description": "Brave Browser description",
-                }
-            ]
-        }
-    }
-    mock_get.return_value.json.return_value = mock_response
-
-    tool = BraveSearchTool(n_results=2)
-    result = tool.run(query="Brave Browser")
-    assert result is not None
-
-    # Parse JSON so we can examine the structure
-    data = json.loads(result)
-    assert isinstance(data, list)
-    assert len(data) >= 1
-
-    # First item should have expected fields: title, url, and description
-    first = data[0]
-    assert "title" in first
-    assert first["title"] == "Brave Browser"
-    assert "url" in first
-    assert first["url"] == "https://brave.com"
-    assert "description" in first
-    assert first["description"] == "Brave Browser description"
+# Backward Compatibility & Legacy Parameter Support
 
 
-if __name__ == "__main__":
-    test_brave_tool()
-    test_brave_tool_initialization()
-    # test_brave_tool_search(brave_tool)
+@patch("crewai_tools.tools.brave_search_tool.base.requests.get")
+def test_positional_query_argument(mock_get, web_tool):
+    """tool.run('my query') works as a positional argument."""
+    mock_get.return_value = _mock_response(json_data={})
+
+    web_tool._run("positional test")
+
+    assert mock_get.call_args.kwargs["params"]["q"] == "positional test"
+
+
+@patch("crewai_tools.tools.brave_search_tool.base.requests.get")
+def test_search_query_backward_compat(mock_get, web_tool):
+    """The legacy 'search_query' param is mapped to 'query'."""
+    mock_get.return_value = _mock_response(json_data={})
+
+    web_tool._run(search_query="legacy test")
+
+    assert mock_get.call_args.kwargs["params"]["q"] == "legacy test"
+
+
+@patch("crewai_tools.tools.brave_search_tool.base.requests.get")
+@patch("crewai_tools.tools.brave_search_tool.base._save_results_to_file")
+def test_save_file_called_when_enabled(mock_save, mock_get):
+    mock_get.return_value = _mock_response(json_data={"results": []})
+
+    tool = BraveWebSearchTool(save_file=True)
+    tool._run(query="test")
+
+    mock_save.assert_called_once()
+
+
+# Error Handling
+
+
+@patch("crewai_tools.tools.brave_search_tool.base.requests.get")
+def test_connection_error_raises_runtime_error(mock_get, web_tool):
+    mock_get.side_effect = requests_lib.exceptions.ConnectionError("refused")
+    with pytest.raises(RuntimeError, match="Brave Search API connection failed"):
+        web_tool._run(query="test")
+
+
+@patch("crewai_tools.tools.brave_search_tool.base.requests.get")
+def test_timeout_raises_runtime_error(mock_get, web_tool):
+    mock_get.side_effect = requests_lib.exceptions.Timeout("timed out")
+    with pytest.raises(RuntimeError, match="timed out"):
+        web_tool._run(query="test")
+
+
+@patch("crewai_tools.tools.brave_search_tool.base.requests.get")
+def test_invalid_params_raises_value_error(mock_get, web_tool):
+    """count=999 exceeds WebSearchParams.count le=20."""
+    with pytest.raises(ValueError, match="Invalid parameters"):
+        web_tool._run(query="test", count=999)
+
+
+@patch("crewai_tools.tools.brave_search_tool.base.requests.get")
+def test_4xx_error_raises_with_api_detail(mock_get, web_tool):
+    """A 422 with a structured error body includes code and detail in the message."""
+    mock_get.return_value = _mock_response(
+        status_code=422,
+        json_data={
+            "error": {
+                "id": "abc-123",
+                "status": 422,
+                "code": "OPTION_NOT_IN_PLAN",
+                "detail": "extra_snippets requires a Pro plan",
+            }
+        },
+    )
+    with pytest.raises(RuntimeError, match="OPTION_NOT_IN_PLAN") as exc_info:
+        web_tool._run(query="test")
+    assert "extra_snippets requires a Pro plan" in str(exc_info.value)
+    assert "HTTP 422" in str(exc_info.value)
+
+
+@patch("crewai_tools.tools.brave_search_tool.base.requests.get")
+def test_auth_error_raises_immediately(mock_get, web_tool):
+    """A 401 with SUBSCRIPTION_TOKEN_INVALID is not retried."""
+    mock_get.return_value = _mock_response(
+        status_code=401,
+        json_data={
+            "error": {
+                "id": "xyz",
+                "status": 401,
+                "code": "SUBSCRIPTION_TOKEN_INVALID",
+                "detail": "The subscription token is invalid",
+            }
+        },
+    )
+    with pytest.raises(RuntimeError, match="SUBSCRIPTION_TOKEN_INVALID"):
+        web_tool._run(query="test")
+    # Should NOT have retried — only one call.
+    assert mock_get.call_count == 1
+
+
+@patch("crewai_tools.tools.brave_search_tool.base.requests.get")
+def test_quota_limited_429_raises_immediately(mock_get, web_tool):
+    """A 429 with QUOTA_LIMITED is NOT retried — quota exhaustion is terminal."""
+    mock_get.return_value = _mock_response(
+        status_code=429,
+        json_data={
+            "error": {
+                "id": "ql-1",
+                "status": 429,
+                "code": "QUOTA_LIMITED",
+                "detail": "Monthly quota exceeded",
+            }
+        },
+    )
+    with pytest.raises(RuntimeError, match="QUOTA_LIMITED") as exc_info:
+        web_tool._run(query="test")
+    assert "Monthly quota exceeded" in str(exc_info.value)
+    # Terminal — only one HTTP call, no retries.
+    assert mock_get.call_count == 1
+
+
+@patch("crewai_tools.tools.brave_search_tool.base.requests.get")
+def test_usage_limit_exceeded_429_raises_immediately(mock_get, web_tool):
+    """USAGE_LIMIT_EXCEEDED is also non-retryable, just like QUOTA_LIMITED."""
+    mock_get.return_value = _mock_response(
+        status_code=429,
+        json_data={
+            "error": {
+                "id": "ule-1",
+                "status": 429,
+                "code": "USAGE_LIMIT_EXCEEDED",
+            }
+        },
+        text="usage limit exceeded",
+    )
+    with pytest.raises(RuntimeError, match="USAGE_LIMIT_EXCEEDED"):
+        web_tool._run(query="test")
+    assert mock_get.call_count == 1
+
+
+@patch("crewai_tools.tools.brave_search_tool.base.requests.get")
+def test_error_body_is_fully_included_in_message(mock_get, web_tool):
+    """The full JSON error body is included in the RuntimeError message."""
+    mock_get.return_value = _mock_response(
+        status_code=429,
+        json_data={
+            "error": {
+                "id": "x",
+                "status": 429,
+                "code": "QUOTA_LIMITED",
+                "detail": "Exceeded",
+                "meta": {"plan": "free", "limit": 1000},
+            }
+        },
+    )
+    with pytest.raises(RuntimeError) as exc_info:
+        web_tool._run(query="test")
+    msg = str(exc_info.value)
+    assert "HTTP 429" in msg
+    assert "QUOTA_LIMITED" in msg
+    assert "free" in msg
+    assert "1000" in msg
+
+
+@patch("crewai_tools.tools.brave_search_tool.base.requests.get")
+def test_error_without_json_body_falls_back_to_text(mock_get, web_tool):
+    """When the error response isn't valid JSON, resp.text is used as the detail."""
+    resp = _mock_response(status_code=500, text="Internal Server Error")
+    resp.json.side_effect = ValueError("No JSON")
+    mock_get.return_value = resp
+
+    with pytest.raises(RuntimeError, match="Internal Server Error"):
+        web_tool._run(query="test")
+
+
+@patch("crewai_tools.tools.brave_search_tool.base.requests.get")
+def test_invalid_json_on_success_raises_runtime_error(mock_get, web_tool):
+    """A 200 OK with a non-JSON body raises RuntimeError."""
+    resp = _mock_response(status_code=200)
+    resp.json.side_effect = ValueError("Expecting value")
+    mock_get.return_value = resp
+
+    with pytest.raises(RuntimeError, match="invalid JSON"):
+        web_tool._run(query="test")
+
+
+# Rate Limiting
+
+
+@patch("crewai_tools.tools.brave_search_tool.base.requests.get")
+@patch("crewai_tools.tools.brave_search_tool.base.time")
+def test_rate_limit_sleeps_when_too_fast(mock_time, mock_get, web_tool):
+    """Back-to-back calls within the interval trigger a sleep."""
+    mock_get.return_value = _mock_response(json_data={})
+
+    # Simulate: last request was at t=100, "now" is t=100.2 (only 0.2s elapsed).
+    # With default 1 req/s the min interval is 1.0s, so it should sleep ~0.8s.
+    mock_time.time.return_value = 100.2
+    web_tool._last_request_time = 100.0
+
+    web_tool._run(query="test")
+
+    mock_time.sleep.assert_called_once()
+    sleep_duration = mock_time.sleep.call_args[0][0]
+    assert 0.7 < sleep_duration < 0.9  # approximately 0.8s
+
+
+@patch("crewai_tools.tools.brave_search_tool.base.requests.get")
+@patch("crewai_tools.tools.brave_search_tool.base.time")
+def test_rate_limit_skips_sleep_when_enough_time_passed(mock_time, mock_get, web_tool):
+    """No sleep when the elapsed time already exceeds the interval."""
+    mock_get.return_value = _mock_response(json_data={})
+
+    # Last request was at t=100, "now" is t=102 (2s elapsed > 1s interval).
+    mock_time.time.return_value = 102.0
+    web_tool._last_request_time = 100.0
+
+    web_tool._run(query="test")
+
+    mock_time.sleep.assert_not_called()
+
+
+@patch("crewai_tools.tools.brave_search_tool.base.requests.get")
+@patch("crewai_tools.tools.brave_search_tool.base.time")
+def test_rate_limit_disabled_when_zero(mock_time, mock_get, web_tool):
+    """requests_per_second=0 disables rate limiting entirely."""
+    mock_get.return_value = _mock_response(json_data={})
+
+    web_tool._last_request_time = 100.0
+    mock_time.time.return_value = 100.0  # same instant
+
+    web_tool._run(query="test")
+
+    mock_time.sleep.assert_not_called()
+
+
+@patch("crewai_tools.tools.brave_search_tool.base.requests.get")
+@patch("crewai_tools.tools.brave_search_tool.base.time")
+def test_rate_limit_per_instance_independent(mock_time, mock_get, web_tool, image_tool):
+    """Each instance has its own rate-limit clock; a request on one does not delay the other."""
+    mock_get.return_value = _mock_response(json_data={})
+
+    # Web tool fires at t=100 (its clock goes 0 -> 100).
+    mock_time.time.return_value = 100.0
+    web_tool._run(query="test")
+
+    # Image tool fires at t=100.3. Its clock is still 0 (separate instance), so
+    # next_allowed = 1.0 and 100.3 > 1.0 — no sleep. Total process rate can be sum of instance limits.
+    mock_time.time.return_value = 100.3
+    image_tool._run(query="cats")
+
+    mock_time.sleep.assert_not_called()
+
+
+# Retry Behavior
+
+
+@patch("crewai_tools.tools.brave_search_tool.base.requests.get")
+@patch("crewai_tools.tools.brave_search_tool.base.time")
+def test_429_rate_limited_retries_then_succeeds(mock_time, mock_get, web_tool):
+    """A transient RATE_LIMITED 429 is retried; success on the second attempt."""
+    mock_time.time.return_value = 200.0
+
+    resp_429 = _mock_response(
+        status_code=429,
+        json_data={"error": {"id": "r", "status": 429, "code": "RATE_LIMITED"}},
+        headers={"Retry-After": "2"},
+    )
+    resp_200 = _mock_response(status_code=200, json_data={"web": {"results": []}})
+    mock_get.side_effect = [resp_429, resp_200]
+
+    web_tool.raw = True
+    result = web_tool._run(query="test")
+
+    assert result == {"web": {"results": []}}
+    assert mock_get.call_count == 2
+    # Slept for the Retry-After value.
+    retry_sleeps = [c for c in mock_time.sleep.call_args_list if c[0][0] == 2.0]
+    assert len(retry_sleeps) == 1
+
+
+@patch("crewai_tools.tools.brave_search_tool.base.requests.get")
+@patch("crewai_tools.tools.brave_search_tool.base.time")
+def test_5xx_is_retried(mock_time, mock_get, web_tool):
+    """A 502 server error is retried; success on the second attempt."""
+    mock_time.time.return_value = 200.0
+
+    resp_502 = _mock_response(status_code=502, text="Bad Gateway")
+    resp_502.json.side_effect = ValueError("no json")
+    resp_200 = _mock_response(status_code=200, json_data={"web": {"results": []}})
+    mock_get.side_effect = [resp_502, resp_200]
+
+    web_tool.raw = True
+    result = web_tool._run(query="test")
+
+    assert result == {"web": {"results": []}}
+    assert mock_get.call_count == 2
+
+
+@patch("crewai_tools.tools.brave_search_tool.base.requests.get")
+@patch("crewai_tools.tools.brave_search_tool.base.time")
+def test_429_rate_limited_exhausts_retries(mock_time, mock_get, web_tool):
+    """Persistent RATE_LIMITED 429s exhaust retries and raise RuntimeError."""
+    mock_time.time.return_value = 200.0
+
+    resp_429 = _mock_response(
+        status_code=429,
+        json_data={"error": {"id": "r", "status": 429, "code": "RATE_LIMITED"}},
+    )
+    mock_get.return_value = resp_429
+
+    with pytest.raises(RuntimeError, match="RATE_LIMITED"):
+        web_tool._run(query="test")
+    # 3 attempts (default _max_retries).
+    assert mock_get.call_count == 3
+
+
+@patch("crewai_tools.tools.brave_search_tool.base.requests.get")
+@patch("crewai_tools.tools.brave_search_tool.base.time")
+def test_retry_uses_exponential_backoff_when_no_retry_after(
+    mock_time, mock_get, web_tool
+):
+    """Without Retry-After, backoff is 2^attempt (1s, 2s, ...)."""
+    mock_time.time.return_value = 200.0
+
+    resp_503 = _mock_response(status_code=503, text="Service Unavailable")
+    resp_503.json.side_effect = ValueError("no json")
+    resp_200 = _mock_response(status_code=200, json_data={"ok": True})
+    mock_get.side_effect = [resp_503, resp_503, resp_200]
+
+    web_tool.raw = True
+    web_tool._run(query="test")
+
+    # Two retries: attempt 0 → sleep(1.0), attempt 1 → sleep(2.0).
+    retry_sleeps = [c[0][0] for c in mock_time.sleep.call_args_list]
+    assert 1.0 in retry_sleeps
+    assert 2.0 in retry_sleeps

lib/crewai-tools/tests/tools/test_code_interpreter_tool.py

@@ -1,3 +1,4 @@
+import sys
 from unittest.mock import patch
 
 from crewai_tools.tools.code_interpreter_tool.code_interpreter_tool import (
@@ -76,24 +77,22 @@ print("This is line 2")"""
     )
 
 
-def test_restricted_sandbox_basic_code_execution(printer_mock, docker_unavailable_mock):
-    """Test basic code execution."""
+def test_docker_unavailable_raises_error(printer_mock, docker_unavailable_mock):
+    """Test that execution fails when Docker is unavailable in safe mode."""
     tool = CodeInterpreterTool()
     code = """
 result = 2 + 2
 print(result)
 """
-    result = tool.run(code=code, libraries_used=[])
-    printer_mock.assert_called_with(
-        "Running code in restricted sandbox", color="yellow"
-    )
-    assert result == 4
+    with pytest.raises(RuntimeError) as exc_info:
+        tool.run(code=code, libraries_used=[])
+    
+    assert "Docker is required for safe code execution" in str(exc_info.value)
+    assert "sandbox escape" in str(exc_info.value)
 
 
-def test_restricted_sandbox_running_with_blocked_modules(
-    printer_mock, docker_unavailable_mock
-):
-    """Test that restricted modules cannot be imported."""
+def test_restricted_sandbox_running_with_blocked_modules():
+    """Test that restricted modules cannot be imported when using the deprecated sandbox directly."""
     tool = CodeInterpreterTool()
     restricted_modules = SandboxPython.BLOCKED_MODULES
 
@@ -102,18 +101,15 @@ def test_restricted_sandbox_running_with_blocked_modules(
 import {module}
 result = "Import succeeded"
 """
-        result = tool.run(code=code, libraries_used=[])
-        printer_mock.assert_called_with(
-            "Running code in restricted sandbox", color="yellow"
-        )
-
+        # Note: run_code_in_restricted_sandbox is deprecated and insecure
+        # This test verifies the old behavior but should not be used in production
+        result = tool.run_code_in_restricted_sandbox(code)
+        
         assert f"An error occurred: Importing '{module}' is not allowed" in result
 
 
-def test_restricted_sandbox_running_with_blocked_builtins(
-    printer_mock, docker_unavailable_mock
-):
-    """Test that restricted builtins are not available."""
+def test_restricted_sandbox_running_with_blocked_builtins():
+    """Test that restricted builtins are not available when using the deprecated sandbox directly."""
     tool = CodeInterpreterTool()
     restricted_builtins = SandboxPython.UNSAFE_BUILTINS
 
@@ -122,25 +118,23 @@ def test_restricted_sandbox_running_with_blocked_builtins(
 {builtin}("test")
 result = "Builtin available"
 """
-        result = tool.run(code=code, libraries_used=[])
-        printer_mock.assert_called_with(
-            "Running code in restricted sandbox", color="yellow"
-        )
+        # Note: run_code_in_restricted_sandbox is deprecated and insecure
+        # This test verifies the old behavior but should not be used in production
+        result = tool.run_code_in_restricted_sandbox(code)
         assert f"An error occurred: name '{builtin}' is not defined" in result
 
 
 def test_restricted_sandbox_running_with_no_result_variable(
     printer_mock, docker_unavailable_mock
 ):
-    """Test behavior when no result variable is set."""
+    """Test behavior when no result variable is set in deprecated sandbox."""
     tool = CodeInterpreterTool()
     code = """
 x = 10
 """
-    result = tool.run(code=code, libraries_used=[])
-    printer_mock.assert_called_with(
-        "Running code in restricted sandbox", color="yellow"
-    )
+    # Note: run_code_in_restricted_sandbox is deprecated and insecure
+    # This test verifies the old behavior but should not be used in production
+    result = tool.run_code_in_restricted_sandbox(code)
     assert result == "No result variable found."
 
 
@@ -159,6 +153,44 @@ x = 10
     assert result == "No result variable found."
 
 
+@patch("crewai_tools.tools.code_interpreter_tool.code_interpreter_tool.subprocess.run")
+def test_unsafe_mode_installs_libraries_without_shell(
+    subprocess_run_mock, printer_mock, docker_unavailable_mock
+):
+    """Test that library installation uses subprocess.run with shell=False, not os.system."""
+    tool = CodeInterpreterTool(unsafe_mode=True)
+    code = "result = 1"
+    libraries_used = ["numpy", "pandas"]
+
+    tool.run(code=code, libraries_used=libraries_used)
+
+    assert subprocess_run_mock.call_count == 2
+    for call, library in zip(subprocess_run_mock.call_args_list, libraries_used):
+        args, kwargs = call
+        # Must be list form (no shell expansion possible)
+        assert args[0] == [sys.executable, "-m", "pip", "install", library]
+        # shell= must not be True (defaults to False)
+        assert kwargs.get("shell", False) is False
+
+
+@patch("crewai_tools.tools.code_interpreter_tool.code_interpreter_tool.subprocess.run")
+def test_unsafe_mode_library_name_with_shell_metacharacters_does_not_invoke_shell(
+    subprocess_run_mock, printer_mock, docker_unavailable_mock
+):
+    """Test that a malicious library name cannot inject shell commands."""
+    tool = CodeInterpreterTool(unsafe_mode=True)
+    code = "result = 1"
+    malicious_library = "numpy; rm -rf /"
+
+    tool.run(code=code, libraries_used=[malicious_library])
+
+    subprocess_run_mock.assert_called_once()
+    args, kwargs = subprocess_run_mock.call_args
+    # The entire malicious string is passed as a single argument — no shell parsing
+    assert args[0] == [sys.executable, "-m", "pip", "install", malicious_library]
+    assert kwargs.get("shell", False) is False
+
+
 def test_unsafe_mode_running_unsafe_code(printer_mock, docker_unavailable_mock):
     """Test behavior when no result variable is set."""
     tool = CodeInterpreterTool(unsafe_mode=True)
@@ -172,3 +204,50 @@ result = eval("5/1")
         "WARNING: Running code in unsafe mode", color="bold_magenta"
     )
     assert 5.0 == result
+
+
+@pytest.mark.xfail(
+    reason=(
+        "run_code_in_restricted_sandbox is known to be vulnerable to sandbox "
+        "escape via object introspection. This test encodes the desired secure "
+        "behavior (no escape possible) and will start passing once the "
+        "vulnerability is fixed or the function is removed."
+    )
+)
+def test_sandbox_escape_vulnerability_demonstration(printer_mock):
+    """Demonstrate that the restricted sandbox is vulnerable to escape attacks.
+    
+    This test shows that an attacker can use Python object introspection to bypass
+    the restricted sandbox and access blocked modules like 'os'. This is why the
+    sandbox should never be used for untrusted code execution.
+    
+    NOTE: This test uses the deprecated run_code_in_restricted_sandbox directly
+    to demonstrate the vulnerability. In production, Docker is now required.
+    """
+    tool = CodeInterpreterTool()
+    
+    # Classic Python sandbox escape via object introspection
+    escape_code = """
+# Recover the real __import__ function via object introspection
+for cls in ().__class__.__bases__[0].__subclasses__():
+    if cls.__name__ == 'catch_warnings':
+        # Get the real builtins module
+        real_builtins = cls()._module.__builtins__
+        real_import = real_builtins['__import__']
+        # Now we can import os and execute commands
+        os = real_import('os')
+        # Demonstrate we have escaped the sandbox
+        result = "SANDBOX_ESCAPED" if hasattr(os, 'system') else "FAILED"
+        break
+"""
+    
+    # The deprecated sandbox is vulnerable to this attack
+    result = tool.run_code_in_restricted_sandbox(escape_code)
+    
+    # Desired behavior: the restricted sandbox should prevent this escape.
+    # If this assertion fails, run_code_in_restricted_sandbox remains vulnerable.
+    assert result != "SANDBOX_ESCAPED", (
+        "The restricted sandbox was bypassed via object introspection. "
+        "This indicates run_code_in_restricted_sandbox is still vulnerable and "
+        "is why Docker is now required for safe code execution."
+    )

lib/crewai/pyproject.toml

@@ -21,7 +21,7 @@ dependencies = [
     "opentelemetry-exporter-otlp-proto-http~=1.34.0",
     # Data Handling
     "chromadb~=1.1.0",
-    "tokenizers~=0.20.3",
+    "tokenizers>=0.21,<1",
     "openpyxl~=3.1.5",
     # Authentication and Security
     "python-dotenv~=1.1.1",
@@ -53,7 +53,7 @@ Repository = "https://github.com/crewAIInc/crewAI"
 
 [project.optional-dependencies]
 tools = [
-    "crewai-tools==1.10.0",
+    "crewai-tools==1.11.0rc1",
 ]
 embeddings = [
     "tiktoken~=0.8.0"
@@ -66,7 +66,7 @@ openpyxl = [
 ]
 mem0 = ["mem0ai~=0.1.94"]
 docling = [
-    "docling~=2.63.0",
+    "docling~=2.75.0",
 ]
 qdrant = [
     "qdrant-client[fastembed]~=1.14.3",
@@ -88,7 +88,7 @@ bedrock = [
     "boto3~=1.40.45",
 ]
 google-genai = [
-    "google-genai~=1.49.0",
+    "google-genai~=1.65.0",
 ]
 azure-ai-inference = [
     "azure-ai-inference~=1.0.0b9",

lib/crewai/src/crewai/__init__.py

@@ -1,16 +1,17 @@
+import contextvars
 import threading
 from typing import Any
 import urllib.request
 import warnings
 
 from crewai.agent.core import Agent
+from crewai.agent.planning_config import PlanningConfig
 from crewai.crew import Crew
 from crewai.crews.crew_output import CrewOutput
 from crewai.flow.flow import Flow
 from crewai.knowledge.knowledge import Knowledge
 from crewai.llm import LLM
 from crewai.llms.base_llm import BaseLLM
-from crewai.memory.unified_memory import Memory
 from crewai.process import Process
 from crewai.task import Task
 from crewai.tasks.llm_guardrail import LLMGuardrail
@@ -41,7 +42,7 @@ def _suppress_pydantic_deprecation_warnings() -> None:
 
 _suppress_pydantic_deprecation_warnings()
 
-__version__ = "1.10.0"
+__version__ = "1.11.0rc1"
 _telemetry_submitted = False
 
 
@@ -67,11 +68,31 @@ def _track_install() -> None:
 def _track_install_async() -> None:
     """Track installation in background thread to avoid blocking imports."""
     if not Telemetry._is_telemetry_disabled():
-        thread = threading.Thread(target=_track_install, daemon=True)
+        ctx = contextvars.copy_context()
+        thread = threading.Thread(target=ctx.run, args=(_track_install,), daemon=True)
         thread.start()
 
 
 _track_install_async()
+
+_LAZY_IMPORTS: dict[str, tuple[str, str]] = {
+    "Memory": ("crewai.memory.unified_memory", "Memory"),
+}
+
+
+def __getattr__(name: str) -> Any:
+    """Lazily import heavy modules (e.g. Memory → lancedb) on first access."""
+    if name in _LAZY_IMPORTS:
+        module_path, attr = _LAZY_IMPORTS[name]
+        import importlib
+
+        mod = importlib.import_module(module_path)
+        val = getattr(mod, attr)
+        globals()[name] = val
+        return val
+    raise AttributeError(f"module 'crewai' has no attribute {name!r}")
+
+
 __all__ = [
     "LLM",
     "Agent",
@@ -82,6 +103,7 @@ __all__ = [
     "Knowledge",
     "LLMGuardrail",
     "Memory",
+    "PlanningConfig",
     "Process",
     "Task",
     "TaskOutput",

lib/crewai/src/crewai/a2a/auth/__init__.py

@@ -13,6 +13,7 @@ from crewai.a2a.auth.client_schemes import (
 )
 from crewai.a2a.auth.server_schemes import (
     AuthenticatedUser,
+    EnterpriseTokenAuth,
     OIDCAuth,
     ServerAuthScheme,
     SimpleTokenAuth,
@@ -25,6 +26,7 @@ __all__ = [
     "AuthenticatedUser",
     "BearerTokenAuth",
     "ClientAuthScheme",
+    "EnterpriseTokenAuth",
     "HTTPBasicAuth",
     "HTTPDigestAuth",
     "OAuth2AuthorizationCode",

lib/crewai/src/crewai/a2a/auth/server_schemes.py

@@ -4,6 +4,7 @@ These schemes validate incoming requests to A2A server endpoints.
 
 Supported authentication methods:
 - Simple token validation with static bearer tokens
+- Enterprise token validation (via PlusAPI)
 - OpenID Connect with JWT validation using JWKS
 - OAuth2 with JWT validation or token introspection
 """
@@ -16,6 +17,7 @@ import logging
 import os
 from typing import TYPE_CHECKING, Annotated, Any, ClassVar, Literal
 
+import httpx
 import jwt
 from jwt import PyJWKClient
 from pydantic import (
@@ -33,6 +35,7 @@ from typing_extensions import Self
 
 if TYPE_CHECKING:
     from a2a.types import OAuth2SecurityScheme
+    from jwt.types import Options
 
 
 logger = logging.getLogger(__name__)
@@ -183,6 +186,24 @@ class SimpleTokenAuth(ServerAuthScheme):
         )
 
 
+class EnterpriseTokenAuth(ServerAuthScheme):
+    """Enterprise token authentication.
+
+    Validates tokens via the PlusAPI enterprise verification endpoint.
+    """
+
+    async def authenticate(self, token: str) -> AuthenticatedUser:
+        """Authenticate using enterprise token verification.
+
+        Args:
+            token: The bearer token to authenticate.
+
+        Raises:
+            NotImplementedError
+        """
+        raise NotImplementedError
+
+
 class OIDCAuth(ServerAuthScheme):
     """OpenID Connect authentication.
 
@@ -475,7 +496,7 @@ class OAuth2ServerAuth(ServerAuthScheme):
         try:
             signing_key = self._jwk_client.get_signing_key_from_jwt(token)
 
-            decode_options: dict[str, Any] = {
+            decode_options: Options = {
                 "require": self.required_claims,
             }
 
@@ -556,7 +577,6 @@ class OAuth2ServerAuth(ServerAuthScheme):
 
     async def _authenticate_introspection(self, token: str) -> AuthenticatedUser:
         """Authenticate using OAuth2 token introspection (RFC 7662)."""
-        import httpx
 
         if not self.introspection_url:
             raise HTTPException(

lib/crewai/src/crewai/a2a/config.py

@@ -633,6 +633,10 @@ class A2AServerConfig(BaseModel):
         default=False,
         description="Whether agent provides extended card to authenticated users",
     )
+    extended_skills: list[AgentSkill] = Field(
+        default_factory=list,
+        description="Additional skills visible only to authenticated users in the extended card",
+    )
     url: Url | None = Field(
         default=None,
         description="Preferred endpoint URL for the agent. Set at runtime if not provided.",

lib/crewai/src/crewai/a2a/errors.py

@@ -63,6 +63,9 @@ class A2AErrorCode(IntEnum):
     INVALID_AGENT_RESPONSE = -32006
     """The agent produced an invalid response."""
 
+    AUTHENTICATED_EXTENDED_CARD_NOT_CONFIGURED = -32007
+    """Authenticated extended card feature is not configured."""
+
     # CrewAI Custom Extensions (-32768 to -32100)
     UNSUPPORTED_VERSION = -32009
     """The requested A2A protocol version is not supported."""
@@ -108,6 +111,7 @@ ERROR_MESSAGES: dict[int, str] = {
     A2AErrorCode.UNSUPPORTED_OPERATION: "This operation is not supported",
     A2AErrorCode.CONTENT_TYPE_NOT_SUPPORTED: "Incompatible content types",
     A2AErrorCode.INVALID_AGENT_RESPONSE: "Invalid agent response",
+    A2AErrorCode.AUTHENTICATED_EXTENDED_CARD_NOT_CONFIGURED: "Authenticated Extended Card is not configured",
     A2AErrorCode.UNSUPPORTED_VERSION: "Unsupported A2A version",
     A2AErrorCode.UNSUPPORTED_EXTENSION: "Client does not support required extensions",
     A2AErrorCode.AUTHENTICATION_REQUIRED: "Authentication required",
@@ -284,6 +288,15 @@ class InvalidAgentResponseError(A2AError):
     code: int = field(default=A2AErrorCode.INVALID_AGENT_RESPONSE, init=False)
 
 
+@dataclass
+class AuthenticatedExtendedCardNotConfiguredError(A2AError):
+    """Authenticated extended card is not configured."""
+
+    code: int = field(
+        default=A2AErrorCode.AUTHENTICATED_EXTENDED_CARD_NOT_CONFIGURED, init=False
+    )
+
+
 @dataclass
 class UnsupportedVersionError(A2AError):
     """The requested A2A version is not supported."""

lib/crewai/src/crewai/a2a/utils/agent_card.py

@@ -4,6 +4,8 @@ from __future__ import annotations
 
 import asyncio
 from collections.abc import MutableMapping
+import concurrent.futures
+import contextvars
 from functools import lru_cache
 import ssl
 import time
@@ -138,14 +140,18 @@ def fetch_agent_card(
         ttl_hash = int(time.time() // cache_ttl)
         return _fetch_agent_card_cached(endpoint, auth_hash, timeout, ttl_hash)
 
-    loop = asyncio.new_event_loop()
-    asyncio.set_event_loop(loop)
+    coro = afetch_agent_card(endpoint=endpoint, auth=auth, timeout=timeout)
     try:
-        return loop.run_until_complete(
-            afetch_agent_card(endpoint=endpoint, auth=auth, timeout=timeout)
-        )
-    finally:
-        loop.close()
+        asyncio.get_running_loop()
+        has_running_loop = True
+    except RuntimeError:
+        has_running_loop = False
+
+    if has_running_loop:
+        ctx = contextvars.copy_context()
+        with concurrent.futures.ThreadPoolExecutor(max_workers=1) as pool:
+            return pool.submit(ctx.run, asyncio.run, coro).result()
+    return asyncio.run(coro)
 
 
 async def afetch_agent_card(
@@ -203,14 +209,18 @@ def _fetch_agent_card_cached(
     """Cached sync version of fetch_agent_card."""
     auth = _auth_store.get(auth_hash)
 
-    loop = asyncio.new_event_loop()
-    asyncio.set_event_loop(loop)
+    coro = _afetch_agent_card_impl(endpoint=endpoint, auth=auth, timeout=timeout)
     try:
-        return loop.run_until_complete(
-            _afetch_agent_card_impl(endpoint=endpoint, auth=auth, timeout=timeout)
-        )
-    finally:
-        loop.close()
+        asyncio.get_running_loop()
+        has_running_loop = True
+    except RuntimeError:
+        has_running_loop = False
+
+    if has_running_loop:
+        ctx = contextvars.copy_context()
+        with concurrent.futures.ThreadPoolExecutor(max_workers=1) as pool:
+            return pool.submit(ctx.run, asyncio.run, coro).result()
+    return asyncio.run(coro)
 
 
 @cached(ttl=300, serializer=PickleSerializer())  # type: ignore[untyped-decorator]

lib/crewai/src/crewai/a2a/utils/delegation.py

@@ -5,7 +5,9 @@ from __future__ import annotations
 import asyncio
 import base64
 from collections.abc import AsyncIterator, Callable, MutableMapping
+import concurrent.futures
 from contextlib import asynccontextmanager
+import contextvars
 import logging
 from typing import TYPE_CHECKING, Any, Final, Literal
 import uuid
@@ -194,56 +196,44 @@ def execute_a2a_delegation(
 
     Returns:
         TaskStateResult with status, result/error, history, and agent_card.
-
-    Raises:
-        RuntimeError: If called from an async context with a running event loop.
     """
+    coro = aexecute_a2a_delegation(
+        endpoint=endpoint,
+        auth=auth,
+        timeout=timeout,
+        task_description=task_description,
+        context=context,
+        context_id=context_id,
+        task_id=task_id,
+        reference_task_ids=reference_task_ids,
+        metadata=metadata,
+        extensions=extensions,
+        conversation_history=conversation_history,
+        agent_id=agent_id,
+        agent_role=agent_role,
+        agent_branch=agent_branch,
+        response_model=response_model,
+        turn_number=turn_number,
+        updates=updates,
+        from_task=from_task,
+        from_agent=from_agent,
+        skill_id=skill_id,
+        client_extensions=client_extensions,
+        transport=transport,
+        accepted_output_modes=accepted_output_modes,
+        input_files=input_files,
+    )
     try:
         asyncio.get_running_loop()
-        raise RuntimeError(
-            "execute_a2a_delegation() cannot be called from an async context. "
-            "Use 'await aexecute_a2a_delegation()' instead."
-        )
-    except RuntimeError as e:
-        if "no running event loop" not in str(e).lower():
-            raise
+        has_running_loop = True
+    except RuntimeError:
+        has_running_loop = False
 
-    loop = asyncio.new_event_loop()
-    asyncio.set_event_loop(loop)
-    try:
-        return loop.run_until_complete(
-            aexecute_a2a_delegation(
-                endpoint=endpoint,
-                auth=auth,
-                timeout=timeout,
-                task_description=task_description,
-                context=context,
-                context_id=context_id,
-                task_id=task_id,
-                reference_task_ids=reference_task_ids,
-                metadata=metadata,
-                extensions=extensions,
-                conversation_history=conversation_history,
-                agent_id=agent_id,
-                agent_role=agent_role,
-                agent_branch=agent_branch,
-                response_model=response_model,
-                turn_number=turn_number,
-                updates=updates,
-                from_task=from_task,
-                from_agent=from_agent,
-                skill_id=skill_id,
-                client_extensions=client_extensions,
-                transport=transport,
-                accepted_output_modes=accepted_output_modes,
-                input_files=input_files,
-            )
-        )
-    finally:
-        try:
-            loop.run_until_complete(loop.shutdown_asyncgens())
-        finally:
-            loop.close()
+    if has_running_loop:
+        ctx = contextvars.copy_context()
+        with concurrent.futures.ThreadPoolExecutor(max_workers=1) as pool:
+            return pool.submit(ctx.run, asyncio.run, coro).result()
+    return asyncio.run(coro)
 
 
 async def aexecute_a2a_delegation(

lib/crewai/src/crewai/a2a/wrapper.py

@@ -8,6 +8,7 @@ from __future__ import annotations
 import asyncio
 from collections.abc import Callable, Coroutine, Mapping
 from concurrent.futures import ThreadPoolExecutor, as_completed
+import contextvars
 from functools import wraps
 import json
 from types import MethodType
@@ -278,7 +279,9 @@ def _fetch_agent_cards_concurrently(
     max_workers = min(len(a2a_agents), 10)
     with ThreadPoolExecutor(max_workers=max_workers) as executor:
         futures = {
-            executor.submit(_fetch_card_from_config, config): config
+            executor.submit(
+                contextvars.copy_context().run, _fetch_card_from_config, config
+            ): config
             for config in a2a_agents
         }
         for future in as_completed(futures):

lib/crewai/src/crewai/agent/core.py

@@ -2,6 +2,7 @@ from __future__ import annotations
 
 import asyncio
 from collections.abc import Callable, Coroutine, Sequence
+import contextvars
 import shutil
 import subprocess
 import time
@@ -22,6 +23,7 @@ from pydantic import (
 )
 from typing_extensions import Self
 
+from crewai.agent.planning_config import PlanningConfig
 from crewai.agent.utils import (
     ahandle_knowledge_retrieval,
     apply_training_data,
@@ -191,13 +193,23 @@ class Agent(BaseAgent):
         default="safe",
         description="Mode for code execution: 'safe' (using Docker) or 'unsafe' (direct execution).",
     )
-    reasoning: bool = Field(
+    planning_config: PlanningConfig | None = Field(
+        default=None,
+        description="Configuration for agent planning before task execution.",
+    )
+    planning: bool = Field(
         default=False,
         description="Whether the agent should reflect and create a plan before executing a task.",
     )
+    reasoning: bool = Field(
+        default=False,
+        description="[DEPRECATED: Use planning_config instead] Whether the agent should reflect and create a plan before executing a task.",
+        deprecated=True,
+    )
     max_reasoning_attempts: int | None = Field(
         default=None,
-        description="Maximum number of reasoning attempts before executing the task. If None, will try until ready.",
+        description="[DEPRECATED: Use planning_config.max_attempts instead] Maximum number of reasoning attempts before executing the task. If None, will try until ready.",
+        deprecated=True,
     )
     embedder: EmbedderConfig | None = Field(
         default=None,
@@ -264,8 +276,26 @@ class Agent(BaseAgent):
         if self.allow_code_execution:
             self._validate_docker_installation()
 
+        # Handle backward compatibility: convert reasoning=True to planning_config
+        if self.reasoning and self.planning_config is None:
+            import warnings
+
+            warnings.warn(
+                "The 'reasoning' parameter is deprecated. Use 'planning_config=PlanningConfig()' instead.",
+                DeprecationWarning,
+                stacklevel=2,
+            )
+            self.planning_config = PlanningConfig(
+                max_attempts=self.max_reasoning_attempts,
+            )
+
         return self
 
+    @property
+    def planning_enabled(self) -> bool:
+        """Check if planning is enabled for this agent."""
+        return self.planning_config is not None or self.planning
+
     def _setup_agent_executor(self) -> None:
         if not self.cache_handler:
             self.cache_handler = CacheHandler()
@@ -334,7 +364,11 @@ class Agent(BaseAgent):
             ValueError: If the max execution time is not a positive integer.
             RuntimeError: If the agent execution fails for other reasons.
         """
-        handle_reasoning(self, task)
+        # Only call handle_reasoning for legacy CrewAgentExecutor
+        # For AgentExecutor, planning is handled in AgentExecutor.generate_plan()
+        if self.executor_class is not AgentExecutor:
+            handle_reasoning(self, task)
+
         self._inject_date_to_task(task)
 
         if self.tools_handler:
@@ -513,9 +547,13 @@ class Agent(BaseAgent):
         """
         import concurrent.futures
 
+        ctx = contextvars.copy_context()
         with concurrent.futures.ThreadPoolExecutor() as executor:
             future = executor.submit(
-                self._execute_without_timeout, task_prompt=task_prompt, task=task
+                ctx.run,
+                self._execute_without_timeout,
+                task_prompt=task_prompt,
+                task=task,
             )
 
             try:
@@ -572,7 +610,10 @@ class Agent(BaseAgent):
             ValueError: If the max execution time is not a positive integer.
             RuntimeError: If the agent execution fails for other reasons.
         """
-        handle_reasoning(self, task)
+        if self.executor_class is not AgentExecutor:
+            handle_reasoning(
+                self, task
+            )  # we need this till CrewAgentExecutor migrates to AgentExecutor
         self._inject_date_to_task(task)
 
         if self.tools_handler:
@@ -1156,11 +1197,15 @@ class Agent(BaseAgent):
         # Process platform apps and MCP tools
         if self.apps:
             platform_tools = self.get_platform_tools(self.apps)
-            if platform_tools and self.tools is not None:
+            if platform_tools:
+                if self.tools is None:
+                    self.tools = []
                 self.tools.extend(platform_tools)
         if self.mcps:
             mcps = self.get_mcp_tools(self.mcps)
-            if mcps and self.tools is not None:
+            if mcps:
+                if self.tools is None:
+                    self.tools = []
                 self.tools.extend(mcps)
 
         # Prepare tools
@@ -1264,7 +1309,7 @@ class Agent(BaseAgent):
                     ),
                 )
                 start_time = time.time()
-                matches = agent_memory.recall(formatted_messages, limit=5)
+                matches = agent_memory.recall(formatted_messages, limit=20)
                 memory_block = ""
                 if matches:
                     memory_block = "Relevant memories:\n" + "\n".join(
@@ -1414,17 +1459,19 @@ class Agent(BaseAgent):
         except Exception as e:
             self._logger.log("error", f"Failed to save kickoff result to memory: {e}")
 
-    def _execute_and_build_output(
+    def _build_output_from_result(
         self,
+        result: dict[str, Any],
         executor: AgentExecutor,
-        inputs: dict[str, str],
         response_format: type[Any] | None = None,
     ) -> LiteAgentOutput:
-        """Execute the agent and build the output object.
+        """Build a LiteAgentOutput from an executor result dict.
+
+        Shared logic used by both sync and async execution paths.
 
         Args:
+            result: The result dictionary from executor.invoke / invoke_async.
             executor: The executor instance.
-            inputs: Input dictionary for execution.
             response_format: Optional response format.
 
         Returns:
@@ -1432,8 +1479,6 @@ class Agent(BaseAgent):
         """
         import json
 
-        # Execute the agent (this is called from sync path, so invoke returns dict)
-        result = cast(dict[str, Any], executor.invoke(inputs))
         output = result.get("output", "")
 
         # Handle response format conversion
@@ -1481,91 +1526,39 @@ class Agent(BaseAgent):
             else str(raw_output)
         )
 
+        todo_results = LiteAgentOutput.from_todo_items(executor.state.todos.items)
+
         return LiteAgentOutput(
             raw=raw_str,
             pydantic=formatted_result,
             agent_role=self.role,
             usage_metrics=usage_metrics.model_dump() if usage_metrics else None,
-            messages=executor.messages,
+            messages=list(executor.state.messages),
+            plan=executor.state.plan,
+            todos=todo_results,
+            replan_count=executor.state.replan_count,
+            last_replan_reason=executor.state.last_replan_reason,
         )
 
+    def _execute_and_build_output(
+        self,
+        executor: AgentExecutor,
+        inputs: dict[str, str],
+        response_format: type[Any] | None = None,
+    ) -> LiteAgentOutput:
+        """Execute the agent synchronously and build the output object."""
+        result = cast(dict[str, Any], executor.invoke(inputs))
+        return self._build_output_from_result(result, executor, response_format)
+
     async def _execute_and_build_output_async(
         self,
         executor: AgentExecutor,
         inputs: dict[str, str],
         response_format: type[Any] | None = None,
     ) -> LiteAgentOutput:
-        """Execute the agent asynchronously and build the output object.
-
-        This is the async version of _execute_and_build_output that uses
-        invoke_async() for native async execution within event loops.
-
-        Args:
-            executor: The executor instance.
-            inputs: Input dictionary for execution.
-            response_format: Optional response format.
-
-        Returns:
-            LiteAgentOutput with raw output, formatted result, and metrics.
-        """
-        import json
-
-        # Execute the agent asynchronously
+        """Execute the agent asynchronously and build the output object."""
         result = await executor.invoke_async(inputs)
-        output = result.get("output", "")
-
-        # Handle response format conversion
-        formatted_result: BaseModel | None = None
-        raw_output: str
-
-        if isinstance(output, BaseModel):
-            formatted_result = output
-            raw_output = output.model_dump_json()
-        elif response_format:
-            raw_output = str(output) if not isinstance(output, str) else output
-            try:
-                model_schema = generate_model_description(response_format)
-                schema = json.dumps(model_schema, indent=2)
-                instructions = self.i18n.slice("formatted_task_instructions").format(
-                    output_format=schema
-                )
-
-                converter = Converter(
-                    llm=self.llm,
-                    text=raw_output,
-                    model=response_format,
-                    instructions=instructions,
-                )
-
-                conversion_result = converter.to_pydantic()
-                if isinstance(conversion_result, BaseModel):
-                    formatted_result = conversion_result
-            except ConverterError:
-                pass  # Keep raw output if conversion fails
-        else:
-            raw_output = str(output) if not isinstance(output, str) else output
-
-        # Get token usage metrics
-        if isinstance(self.llm, BaseLLM):
-            usage_metrics = self.llm.get_token_usage_summary()
-        else:
-            usage_metrics = self._token_process.get_summary()
-
-        raw_str = (
-            raw_output
-            if isinstance(raw_output, str)
-            else raw_output.model_dump_json()
-            if isinstance(raw_output, BaseModel)
-            else str(raw_output)
-        )
-
-        return LiteAgentOutput(
-            raw=raw_str,
-            pydantic=formatted_result,
-            agent_role=self.role,
-            usage_metrics=usage_metrics.model_dump() if usage_metrics else None,
-            messages=executor.messages,
-        )
+        return self._build_output_from_result(result, executor, response_format)
 
     def _process_kickoff_guardrail(
         self,

lib/crewai/src/crewai/agent/planning_config.py

@@ -0,0 +1,138 @@
+from __future__ import annotations
+
+from typing import Literal
+
+from pydantic import BaseModel, Field
+
+from crewai.llms.base_llm import BaseLLM
+
+
+class PlanningConfig(BaseModel):
+    """Configuration for agent planning/reasoning before task execution.
+
+    This allows users to customize the planning behavior including prompts,
+    iteration limits, the LLM used for planning, and the reasoning effort
+    level that controls post-step observation and replanning behavior.
+
+    Note: To disable planning, don't pass a planning_config or set planning=False
+    on the Agent. The presence of a PlanningConfig enables planning.
+
+    Attributes:
+        reasoning_effort: Controls observation and replanning after each step.
+            - "low": Observe each step (validates success), but skip the
+              decide/replan/refine pipeline. Steps are marked complete and
+              execution continues linearly. Fastest option.
+            - "medium": Observe each step. On failure, trigger replanning.
+              On success, skip refinement and continue. Balanced option.
+            - "high": Full observation pipeline — observe every step, then
+              route through decide_next_action which can trigger early goal
+              achievement, full replanning, or lightweight refinement.
+              Most adaptive but adds latency per step.
+        max_attempts: Maximum number of planning refinement attempts.
+            If None, will continue until the agent indicates readiness.
+        max_steps: Maximum number of steps in the generated plan.
+        system_prompt: Custom system prompt for planning. Uses default if None.
+        plan_prompt: Custom prompt for creating the initial plan.
+        refine_prompt: Custom prompt for refining the plan.
+        llm: LLM to use for planning. Uses agent's LLM if None.
+
+    Example:
+        ```python
+        from crewai import Agent
+        from crewai.agent.planning_config import PlanningConfig
+
+        # Simple usage — fast, linear execution (default)
+        agent = Agent(
+            role="Researcher",
+            goal="Research topics",
+            backstory="Expert researcher",
+            planning_config=PlanningConfig(),
+        )
+
+        # Balanced — replan only when steps fail
+        agent = Agent(
+            role="Researcher",
+            goal="Research topics",
+            backstory="Expert researcher",
+            planning_config=PlanningConfig(
+                reasoning_effort="medium",
+            ),
+        )
+
+        # Full adaptive planning with refinement and replanning
+        agent = Agent(
+            role="Researcher",
+            goal="Research topics",
+            backstory="Expert researcher",
+            planning_config=PlanningConfig(
+                reasoning_effort="high",
+                max_attempts=3,
+                max_steps=10,
+                plan_prompt="Create a focused plan for: {description}",
+                llm="gpt-4o-mini",  # Use cheaper model for planning
+            ),
+        )
+        ```
+    """
+
+    reasoning_effort: Literal["low", "medium", "high"] = Field(
+        default="medium",
+        description=(
+            "Controls post-step observation and replanning behavior. "
+            "'low' observes steps but skips replanning/refinement (fastest). "
+            "'medium' observes and replans only on step failure (balanced). "
+            "'high' runs full observation pipeline with replanning, refinement, "
+            "and early goal detection (most adaptive, highest latency)."
+        ),
+    )
+    max_attempts: int | None = Field(
+        default=None,
+        description=(
+            "Maximum number of planning refinement attempts. "
+            "If None, will continue until the agent indicates readiness."
+        ),
+    )
+    max_steps: int = Field(
+        default=20,
+        description="Maximum number of steps in the generated plan.",
+        ge=1,
+    )
+    system_prompt: str | None = Field(
+        default=None,
+        description="Custom system prompt for planning. Uses default if None.",
+    )
+    plan_prompt: str | None = Field(
+        default=None,
+        description="Custom prompt for creating the initial plan.",
+    )
+    refine_prompt: str | None = Field(
+        default=None,
+        description="Custom prompt for refining the plan.",
+    )
+    max_replans: int = Field(
+        default=3,
+        description="Maximum number of full replanning attempts before finalizing.",
+        ge=0,
+    )
+    max_step_iterations: int = Field(
+        default=15,
+        description=(
+            "Maximum LLM iterations per step in the StepExecutor multi-turn loop. "
+            "Lower values make steps faster but less thorough."
+        ),
+        ge=1,
+    )
+    step_timeout: int | None = Field(
+        default=None,
+        description=(
+            "Maximum wall-clock seconds for a single step execution. "
+            "If exceeded, the step is marked as failed and observation decides "
+            "whether to continue or replan. None means no per-step timeout."
+        ),
+    )
+    llm: str | BaseLLM | None = Field(
+        default=None,
+        description="LLM to use for planning. Uses agent's LLM if None.",
+    )
+
+    model_config = {"arbitrary_types_allowed": True}

lib/crewai/src/crewai/agent/utils.py

@@ -28,13 +28,20 @@ if TYPE_CHECKING:
 
 
 def handle_reasoning(agent: Agent, task: Task) -> None:
-    """Handle the reasoning process for an agent before task execution.
+    """Handle the reasoning/planning process for an agent before task execution.
+
+    This function checks if planning is enabled for the agent and, if so,
+    creates a plan that gets appended to the task description.
+
+    Note: This function is used by CrewAgentExecutor (legacy path).
+    For AgentExecutor, planning is handled in AgentExecutor.generate_plan().
 
     Args:
         agent: The agent performing the task.
         task: The task to execute.
     """
-    if not agent.reasoning:
+    # Check if planning is enabled using the planning_enabled property
+    if not getattr(agent, "planning_enabled", False):
         return
 
     try:
@@ -43,13 +50,13 @@ def handle_reasoning(agent: Agent, task: Task) -> None:
             AgentReasoningOutput,
         )
 
-        reasoning_handler = AgentReasoning(task=task, agent=agent)
-        reasoning_output: AgentReasoningOutput = (
-            reasoning_handler.handle_agent_reasoning()
+        planning_handler = AgentReasoning(agent=agent, task=task)
+        planning_output: AgentReasoningOutput = (
+            planning_handler.handle_agent_reasoning()
         )
-        task.description += f"\n\nReasoning Plan:\n{reasoning_output.plan.plan}"
+        task.description += f"\n\nPlanning:\n{planning_output.plan.plan}"
     except Exception as e:
-        agent._logger.log("error", f"Error during reasoning process: {e!s}")
+        agent._logger.log("error", f"Error during planning: {e!s}")
 
 
 def build_task_prompt_with_schema(task: Task, task_prompt: str, i18n: I18N) -> str:

lib/crewai/src/crewai/agents/agent_builder/base_agent.py

@@ -38,7 +38,7 @@ from crewai.utilities.string_utils import interpolate_only
 
 
 _SLUG_RE: Final[re.Pattern[str]] = re.compile(
-    r"^(?:crewai-amp:)?[a-zA-Z0-9][a-zA-Z0-9_-]*(?:#\w+)?$"
+    r"^(?:crewai-amp:)?[a-zA-Z0-9][a-zA-Z0-9_-]*(?:#[\w-]+)?$"
 )
 
 

lib/crewai/src/crewai/agents/agent_builder/base_agent_executor_mixin.py

@@ -30,12 +30,9 @@ class CrewAgentExecutorMixin:
         memory = getattr(self.agent, "memory", None) or (
             getattr(self.crew, "_memory", None) if self.crew else None
         )
-        if memory is None or not self.task or getattr(memory, "_read_only", False):
+        if memory is None or not self.task or memory.read_only:
             return
-        if (
-            f"Action: {sanitize_tool_name('Delegate work to coworker')}"
-            in output.text
-        ):
+        if f"Action: {sanitize_tool_name('Delegate work to coworker')}" in output.text:
             return
         try:
             raw = (
@@ -48,6 +45,4 @@ class CrewAgentExecutorMixin:
             if extracted:
                 memory.remember_many(extracted, agent_role=self.agent.role)
         except Exception as e:
-            self.agent._logger.log(
-                "error", f"Failed to save to memory: {e}"
-            )
+            self.agent._logger.log("error", f"Failed to save to memory: {e}")

lib/crewai/src/crewai/agents/cache/__init__.py

@@ -1,5 +1,4 @@
 from crewai.agents.cache.cache_handler import CacheHandler
 
 
-
 __all__ = ["CacheHandler"]

lib/crewai/src/crewai/agents/crew_agent_executor.py

@@ -9,6 +9,7 @@ from __future__ import annotations
 import asyncio
 from collections.abc import Callable
 from concurrent.futures import ThreadPoolExecutor, as_completed
+import contextvars
 import inspect
 import logging
 from typing import TYPE_CHECKING, Any, Literal, cast
@@ -487,8 +488,8 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
             # No tools available, fall back to simple LLM call
             return self._invoke_loop_native_no_tools()
 
-        openai_tools, available_functions = convert_tools_to_openai_schema(
-            self.original_tools
+        openai_tools, available_functions, self._tool_name_mapping = (
+            convert_tools_to_openai_schema(self.original_tools)
         )
 
         while True:
@@ -700,9 +701,7 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
         if not parsed_calls:
             return None
 
-        original_tools_by_name: dict[str, Any] = {}
-        for tool in self.original_tools or []:
-            original_tools_by_name[sanitize_tool_name(tool.name)] = tool
+        original_tools_by_name: dict[str, Any] = dict(self._tool_name_mapping)
 
         if len(parsed_calls) > 1:
             has_result_as_answer_in_batch = any(
@@ -757,6 +756,7 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
                 with ThreadPoolExecutor(max_workers=max_workers) as pool:
                     futures = {
                         pool.submit(
+                            contextvars.copy_context().run,
                             self._execute_single_native_tool_call,
                             call_id=call_id,
                             func_name=func_name,
@@ -895,7 +895,9 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
             ToolUsageStartedEvent,
         )
 
-        args_dict, parse_error = parse_tool_call_args(func_args, func_name, call_id, original_tool)
+        args_dict, parse_error = parse_tool_call_args(
+            func_args, func_name, call_id, original_tool
+        )
         if parse_error is not None:
             return parse_error
 
@@ -949,10 +951,16 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
         track_delegation_if_needed(func_name, args_dict, self.task)
 
         structured_tool: CrewStructuredTool | None = None
-        for structured in self.tools or []:
-            if sanitize_tool_name(structured.name) == func_name:
-                structured_tool = structured
-                break
+        if original_tool is not None:
+            for structured in self.tools or []:
+                if getattr(structured, "_original_tool", None) is original_tool:
+                    structured_tool = structured
+                    break
+        if structured_tool is None:
+            for structured in self.tools or []:
+                if sanitize_tool_name(structured.name) == func_name:
+                    structured_tool = structured
+                    break
 
         hook_blocked = False
         before_hook_context = ToolCallHookContext(
@@ -1259,7 +1267,7 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
                         formatted_answer, tool_result
                     )
 
-                self._invoke_step_callback(formatted_answer)  # type: ignore[arg-type]
+                await self._ainvoke_step_callback(formatted_answer)  # type: ignore[arg-type]
                 self._append_message(formatted_answer.text)  # type: ignore[union-attr]
 
             except OutputParserError as e:
@@ -1312,8 +1320,8 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
         if not self.original_tools:
             return await self._ainvoke_loop_native_no_tools()
 
-        openai_tools, available_functions = convert_tools_to_openai_schema(
-            self.original_tools
+        openai_tools, available_functions, self._tool_name_mapping = (
+            convert_tools_to_openai_schema(self.original_tools)
         )
 
         while True:
@@ -1374,7 +1382,7 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
                         output=answer,
                         text=answer,
                     )
-                    self._invoke_step_callback(formatted_answer)
+                    await self._ainvoke_step_callback(formatted_answer)
                     self._append_message(answer)  # Save final answer to messages
                     self._show_logs(formatted_answer)
                     return formatted_answer
@@ -1386,7 +1394,7 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
                         output=answer,
                         text=output_json,
                     )
-                    self._invoke_step_callback(formatted_answer)
+                    await self._ainvoke_step_callback(formatted_answer)
                     self._append_message(output_json)
                     self._show_logs(formatted_answer)
                     return formatted_answer
@@ -1397,7 +1405,7 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
                     output=str(answer),
                     text=str(answer),
                 )
-                self._invoke_step_callback(formatted_answer)
+                await self._ainvoke_step_callback(formatted_answer)
                 self._append_message(str(answer))  # Save final answer to messages
                 self._show_logs(formatted_answer)
                 return formatted_answer
@@ -1491,7 +1499,7 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
     def _invoke_step_callback(
         self, formatted_answer: AgentAction | AgentFinish
     ) -> None:
-        """Invoke step callback.
+        """Invoke step callback (sync context).
 
         Args:
             formatted_answer: Current agent response.
@@ -1501,6 +1509,19 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
             if inspect.iscoroutine(cb_result):
                 asyncio.run(cb_result)
 
+    async def _ainvoke_step_callback(
+        self, formatted_answer: AgentAction | AgentFinish
+    ) -> None:
+        """Invoke step callback (async context).
+
+        Args:
+            formatted_answer: Current agent response.
+        """
+        if self.step_callback:
+            cb_result = self.step_callback(formatted_answer)
+            if inspect.iscoroutine(cb_result):
+                await cb_result
+
     def _append_message(
         self, text: str, role: Literal["user", "assistant", "system"] = "assistant"
     ) -> None:

lib/crewai/src/crewai/agents/planner_observer.py

@@ -0,0 +1,345 @@
+"""PlannerObserver: Observation phase after each step execution.
+
+Implements the "Observe" phase. After every step execution, the Planner
+analyzes what happened, what new information was learned, and whether the
+remaining plan is still valid.
+
+This is NOT an error detector — it runs on every step, including successes,
+to incorporate runtime observations into the remaining plan.
+
+Refinements are structured (StepRefinement objects) and applied directly
+from the observation result — no second LLM call required.
+"""
+
+from __future__ import annotations
+
+import logging
+from typing import TYPE_CHECKING, Any
+
+from crewai.events.event_bus import crewai_event_bus
+from crewai.events.types.observation_events import (
+    StepObservationCompletedEvent,
+    StepObservationFailedEvent,
+    StepObservationStartedEvent,
+)
+from crewai.utilities.agent_utils import extract_task_section
+from crewai.utilities.i18n import I18N, get_i18n
+from crewai.utilities.llm_utils import create_llm
+from crewai.utilities.planning_types import StepObservation, TodoItem
+from crewai.utilities.types import LLMMessage
+
+
+if TYPE_CHECKING:
+    from crewai.agent import Agent
+    from crewai.task import Task
+
+logger = logging.getLogger(__name__)
+
+
+class PlannerObserver:
+    """Observes step execution results and decides on plan continuation.
+
+    After EVERY step execution, this class:
+    1. Analyzes what the step accomplished
+    2. Identifies new information learned
+    3. Decides if the remaining plan is still valid
+    4. Suggests lightweight refinements or triggers full replanning
+
+    LLM resolution (magical fallback):
+    - If ``agent.planning_config.llm`` is explicitly set → use that
+    - Otherwise → fall back to ``agent.llm`` (same LLM for everything)
+
+    Args:
+        agent: The agent instance (for LLM resolution and config).
+        task: Optional task context (for description and expected output).
+    """
+
+    def __init__(
+        self,
+        agent: Agent,
+        task: Task | None = None,
+        kickoff_input: str = "",
+    ) -> None:
+        self.agent = agent
+        self.task = task
+        self.kickoff_input = kickoff_input
+        self.llm = self._resolve_llm()
+        self._i18n: I18N = get_i18n()
+
+    def _resolve_llm(self) -> Any:
+        """Resolve which LLM to use for observation/planning.
+
+        Mirrors AgentReasoning._resolve_llm(): uses planning_config.llm
+        if explicitly set, otherwise falls back to agent.llm.
+
+        Returns:
+            The resolved LLM instance.
+        """
+        from crewai.llm import LLM
+
+        config = getattr(self.agent, "planning_config", None)
+        if config is not None and config.llm is not None:
+            if isinstance(config.llm, LLM):
+                return config.llm
+            return create_llm(config.llm)
+        return self.agent.llm
+
+    # ------------------------------------------------------------------
+    # Public API
+    # ------------------------------------------------------------------
+
+    def observe(
+        self,
+        completed_step: TodoItem,
+        result: str,
+        all_completed: list[TodoItem],
+        remaining_todos: list[TodoItem],
+    ) -> StepObservation:
+        """Observe a step's result and decide on plan continuation.
+
+        This runs after EVERY step execution — not just failures.
+
+        Args:
+            completed_step: The todo item that was just executed.
+            result: The final result string from the step.
+            all_completed: All previously completed todos (for context).
+            remaining_todos: The pending todos still in the plan.
+
+        Returns:
+            StepObservation with the Planner's analysis. Any suggested
+            refinements are structured StepRefinement objects ready for
+            direct application — no second LLM call needed.
+        """
+        agent_role = self.agent.role
+
+        crewai_event_bus.emit(
+            self.agent,
+            event=StepObservationStartedEvent(
+                agent_role=agent_role,
+                step_number=completed_step.step_number,
+                step_description=completed_step.description,
+                from_task=self.task,
+                from_agent=self.agent,
+            ),
+        )
+
+        messages = self._build_observation_messages(
+            completed_step, result, all_completed, remaining_todos
+        )
+
+        try:
+            response = self.llm.call(
+                messages,
+                response_model=StepObservation,
+                from_task=self.task,
+                from_agent=self.agent,
+            )
+
+            observation = self._parse_observation_response(response)
+
+            refinement_summaries = (
+                [
+                    f"Step {r.step_number}: {r.new_description}"
+                    for r in observation.suggested_refinements
+                ]
+                if observation.suggested_refinements
+                else None
+            )
+
+            crewai_event_bus.emit(
+                self.agent,
+                event=StepObservationCompletedEvent(
+                    agent_role=agent_role,
+                    step_number=completed_step.step_number,
+                    step_description=completed_step.description,
+                    step_completed_successfully=observation.step_completed_successfully,
+                    key_information_learned=observation.key_information_learned,
+                    remaining_plan_still_valid=observation.remaining_plan_still_valid,
+                    needs_full_replan=observation.needs_full_replan,
+                    replan_reason=observation.replan_reason,
+                    goal_already_achieved=observation.goal_already_achieved,
+                    suggested_refinements=refinement_summaries,
+                    from_task=self.task,
+                    from_agent=self.agent,
+                ),
+            )
+
+            return observation
+
+        except Exception as e:
+            logger.warning(
+                f"Observation LLM call failed: {e}. Defaulting to conservative replan."
+            )
+
+            crewai_event_bus.emit(
+                self.agent,
+                event=StepObservationFailedEvent(
+                    agent_role=agent_role,
+                    step_number=completed_step.step_number,
+                    step_description=completed_step.description,
+                    error=str(e),
+                    from_task=self.task,
+                    from_agent=self.agent,
+                ),
+            )
+
+            # Don't force a full replan — the step may have succeeded even if the
+            # observer LLM failed to parse the result. Defaulting to "continue" is
+            # far less disruptive than wiping the entire plan on every observer error.
+            return StepObservation(
+                step_completed_successfully=True,
+                key_information_learned="",
+                remaining_plan_still_valid=True,
+                needs_full_replan=False,
+            )
+
+    def apply_refinements(
+        self,
+        observation: StepObservation,
+        remaining_todos: list[TodoItem],
+    ) -> list[TodoItem]:
+        """Apply structured refinements from the observation directly to todo descriptions.
+
+        No LLM call needed — refinements are already structured StepRefinement
+        objects produced by the observation call. This is a pure in-memory update.
+
+        Args:
+            observation: The observation containing structured refinements.
+            remaining_todos: The pending todos to update in-place.
+
+        Returns:
+            The same todo list with updated descriptions where refinements applied.
+        """
+        if not observation.suggested_refinements:
+            return remaining_todos
+
+        todo_by_step: dict[int, TodoItem] = {t.step_number: t for t in remaining_todos}
+        for refinement in observation.suggested_refinements:
+            if refinement.step_number in todo_by_step and refinement.new_description:
+                todo_by_step[
+                    refinement.step_number
+                ].description = refinement.new_description
+
+        return remaining_todos
+
+    # ------------------------------------------------------------------
+    # Internal: Message building
+    # ------------------------------------------------------------------
+
+    def _build_observation_messages(
+        self,
+        completed_step: TodoItem,
+        result: str,
+        all_completed: list[TodoItem],
+        remaining_todos: list[TodoItem],
+    ) -> list[LLMMessage]:
+        """Build messages for the observation LLM call."""
+        task_desc = ""
+        task_goal = ""
+        if self.task:
+            task_desc = self.task.description or ""
+            task_goal = self.task.expected_output or ""
+        elif self.kickoff_input:
+            # Standalone kickoff path — no Task object, but we have the raw input.
+            # Extract just the ## Task section so the observer sees the actual goal,
+            # not the full enriched instruction with env/tools/verification noise.
+            task_desc = extract_task_section(self.kickoff_input)
+            task_goal = "Complete the task successfully"
+
+        system_prompt = self._i18n.retrieve("planning", "observation_system_prompt")
+
+        # Build context of what's been done
+        completed_summary = ""
+        if all_completed:
+            completed_lines = []
+            for todo in all_completed:
+                result_preview = (todo.result or "")[:200]
+                completed_lines.append(
+                    f"  Step {todo.step_number}: {todo.description}\n"
+                    f"    Result: {result_preview}"
+                )
+            completed_summary = "\n## Previously completed steps:\n" + "\n".join(
+                completed_lines
+            )
+
+        # Build remaining plan
+        remaining_summary = ""
+        if remaining_todos:
+            remaining_lines = [
+                f"  Step {todo.step_number}: {todo.description}"
+                for todo in remaining_todos
+            ]
+            remaining_summary = "\n## Remaining plan steps:\n" + "\n".join(
+                remaining_lines
+            )
+
+        user_prompt = self._i18n.retrieve("planning", "observation_user_prompt").format(
+            task_description=task_desc,
+            task_goal=task_goal,
+            completed_summary=completed_summary,
+            step_number=completed_step.step_number,
+            step_description=completed_step.description,
+            step_result=result,
+            remaining_summary=remaining_summary,
+        )
+
+        return [
+            {"role": "system", "content": system_prompt},
+            {"role": "user", "content": user_prompt},
+        ]
+
+    @staticmethod
+    def _parse_observation_response(response: Any) -> StepObservation:
+        """Parse the LLM response into a StepObservation.
+
+        The LLM may return:
+        - A StepObservation instance directly (streaming + litellm path)
+        - A JSON string (non-streaming path serialises model_dump_json())
+        - A dict (some provider paths)
+        - Something else (unexpected)
+
+        We handle all cases to avoid silently falling back to a
+        hardcoded success default.
+        """
+
+        if isinstance(response, StepObservation):
+            return response
+
+        # JSON string path — most common miss before this fix
+        if isinstance(response, str):
+            text = response.strip()
+            try:
+                return StepObservation.model_validate_json(text)
+            except Exception:  # noqa: S110
+                pass
+            # Some LLMs wrap the JSON in markdown fences
+            if text.startswith("```"):
+                lines = text.split("\n")
+                # Strip first and last lines (``` markers)
+                inner = "\n".join(
+                    lines[1:-1] if lines[-1].strip() == "```" else lines[1:]
+                )
+                try:
+                    return StepObservation.model_validate_json(inner.strip())
+                except Exception:  # noqa: S110
+                    pass
+
+        # Dict path
+        if isinstance(response, dict):
+            try:
+                return StepObservation.model_validate(response)
+            except Exception:  # noqa: S110
+                pass
+
+        # Last resort — log what we got so it's diagnosable
+        logger.warning(
+            "Could not parse observation response (type=%s). "
+            "Falling back to default failure observation. Preview: %.200s",
+            type(response).__name__,
+            str(response),
+        )
+        return StepObservation(
+            step_completed_successfully=False,
+            key_information_learned=str(response) if response else "",
+            remaining_plan_still_valid=False,
+        )

lib/crewai/src/crewai/agents/step_executor.py

@@ -0,0 +1,629 @@
+"""StepExecutor: Isolated executor for a single plan step.
+
+Implements the direct-action execution pattern from Plan-and-Act
+(arxiv 2503.09572): the Executor receives one step description,
+makes a single LLM call, executes any tool call returned, and
+returns the result immediately.
+
+There is no inner loop. Recovery from failure (retry, replan) is
+the responsibility of PlannerObserver and AgentExecutor — keeping
+this class single-purpose and fast.
+"""
+
+from __future__ import annotations
+
+from collections.abc import Callable
+from datetime import datetime
+import json
+import time
+from typing import TYPE_CHECKING, Any, cast
+
+from pydantic import BaseModel
+
+from crewai.agents.parser import AgentAction, AgentFinish
+from crewai.events.event_bus import crewai_event_bus
+from crewai.events.types.tool_usage_events import (
+    ToolUsageErrorEvent,
+    ToolUsageFinishedEvent,
+    ToolUsageStartedEvent,
+)
+from crewai.utilities.agent_utils import (
+    build_tool_calls_assistant_message,
+    check_native_tool_support,
+    enforce_rpm_limit,
+    execute_single_native_tool_call,
+    extract_task_section,
+    format_message_for_llm,
+    is_tool_call_list,
+    process_llm_response,
+    setup_native_tools,
+)
+from crewai.utilities.i18n import I18N, get_i18n
+from crewai.utilities.planning_types import TodoItem
+from crewai.utilities.printer import Printer
+from crewai.utilities.step_execution_context import StepExecutionContext, StepResult
+from crewai.utilities.string_utils import sanitize_tool_name
+from crewai.utilities.tool_utils import execute_tool_and_check_finality
+from crewai.utilities.types import LLMMessage
+
+
+if TYPE_CHECKING:
+    from crewai.agent import Agent
+    from crewai.agents.tools_handler import ToolsHandler
+    from crewai.crew import Crew
+    from crewai.llms.base_llm import BaseLLM
+    from crewai.task import Task
+    from crewai.tools.base_tool import BaseTool
+    from crewai.tools.structured_tool import CrewStructuredTool
+
+
+class StepExecutor:
+    """Executes a SINGLE todo item using direct-action execution.
+
+    The StepExecutor owns its own message list per invocation. It never reads
+    or writes the AgentExecutor's state. Results flow back via StepResult.
+
+    Execution pattern (per Plan-and-Act, arxiv 2503.09572):
+        1. Build messages from todo + context
+        2. Call LLM once (with or without native tools)
+        3. If tool call → execute it → return tool result
+        4. If text answer → return it directly
+        No inner loop — recovery is PlannerObserver's responsibility.
+
+    Args:
+        llm: The language model to use for execution.
+        tools: Structured tools available to the executor.
+        agent: The agent instance (for role/goal/verbose/config).
+        original_tools: Original BaseTool instances (needed for native tool schema).
+        tools_handler: Optional tools handler for caching and delegation tracking.
+        task: Optional task context.
+        crew: Optional crew context.
+        function_calling_llm: Optional separate LLM for function calling.
+        request_within_rpm_limit: Optional RPM limit function.
+        callbacks: Optional list of callbacks.
+        i18n: Optional i18n instance.
+    """
+
+    def __init__(
+        self,
+        llm: BaseLLM,
+        tools: list[CrewStructuredTool],
+        agent: Agent,
+        original_tools: list[BaseTool] | None = None,
+        tools_handler: ToolsHandler | None = None,
+        task: Task | None = None,
+        crew: Crew | None = None,
+        function_calling_llm: BaseLLM | None = None,
+        request_within_rpm_limit: Callable[[], bool] | None = None,
+        callbacks: list[Any] | None = None,
+        i18n: I18N | None = None,
+    ) -> None:
+        self.llm = llm
+        self.tools = tools
+        self.agent = agent
+        self.original_tools = original_tools or []
+        self.tools_handler = tools_handler
+        self.task = task
+        self.crew = crew
+        self.function_calling_llm = function_calling_llm
+        self.request_within_rpm_limit = request_within_rpm_limit
+        self.callbacks = callbacks or []
+        self._i18n: I18N = i18n or get_i18n()
+        self._printer: Printer = Printer()
+
+        # Native tool support — set up once
+        self._use_native_tools = check_native_tool_support(
+            self.llm, self.original_tools
+        )
+        self._openai_tools: list[dict[str, Any]] = []
+        self._available_functions: dict[str, Callable[..., Any]] = {}
+        if self._use_native_tools and self.original_tools:
+            (
+                self._openai_tools,
+                self._available_functions,
+                _,
+            ) = setup_native_tools(self.original_tools)
+
+    # ------------------------------------------------------------------
+    # Public API
+    # ------------------------------------------------------------------
+
+    def execute(
+        self,
+        todo: TodoItem,
+        context: StepExecutionContext,
+        max_step_iterations: int = 15,
+        step_timeout: int | None = None,
+    ) -> StepResult:
+        """Execute a single todo item using a multi-turn action loop.
+
+        Enforces the RPM limit, builds a fresh message list, then iterates
+        LLM call → tool execution → observation until the LLM signals it is
+        done (text answer) or max_step_iterations is reached.  Never touches
+        external AgentExecutor state.
+
+        Args:
+            todo: The todo item to execute.
+            context: Immutable context with task info and dependency results.
+            max_step_iterations: Maximum LLM iterations in the multi-turn loop.
+            step_timeout: Maximum wall-clock seconds for this step. None = no limit.
+
+        Returns:
+            StepResult with the outcome.
+        """
+        start_time = time.monotonic()
+        tool_calls_made: list[str] = []
+
+        try:
+            enforce_rpm_limit(self.request_within_rpm_limit)
+            messages = self._build_isolated_messages(todo, context)
+
+            if self._use_native_tools:
+                result_text = self._execute_native(
+                    messages,
+                    tool_calls_made,
+                    max_step_iterations=max_step_iterations,
+                    step_timeout=step_timeout,
+                    start_time=start_time,
+                )
+            else:
+                result_text = self._execute_text_parsed(
+                    messages,
+                    tool_calls_made,
+                    max_step_iterations=max_step_iterations,
+                    step_timeout=step_timeout,
+                    start_time=start_time,
+                )
+            self._validate_expected_tool_usage(todo, tool_calls_made)
+
+            elapsed = time.monotonic() - start_time
+            return StepResult(
+                success=True,
+                result=result_text,
+                tool_calls_made=tool_calls_made,
+                execution_time=elapsed,
+            )
+        except Exception as e:
+            elapsed = time.monotonic() - start_time
+            return StepResult(
+                success=False,
+                result="",
+                error=str(e),
+                tool_calls_made=tool_calls_made,
+                execution_time=elapsed,
+            )
+
+    # ------------------------------------------------------------------
+    # Internal: Message building
+    # ------------------------------------------------------------------
+
+    def _build_isolated_messages(
+        self, todo: TodoItem, context: StepExecutionContext
+    ) -> list[LLMMessage]:
+        """Build a fresh message list for this step's execution.
+
+        System prompt tells the LLM it is an Executor focused on one step.
+        User prompt provides the step description, dependencies, and tools.
+        """
+        system_prompt = self._build_system_prompt()
+        user_prompt = self._build_user_prompt(todo, context)
+
+        return [
+            format_message_for_llm(system_prompt, role="system"),
+            format_message_for_llm(user_prompt, role="user"),
+        ]
+
+    def _build_system_prompt(self) -> str:
+        """Build the Executor's system prompt."""
+        role = self.agent.role if self.agent else "Assistant"
+        goal = self.agent.goal if self.agent else "Complete tasks efficiently"
+        backstory = getattr(self.agent, "backstory", "") or ""
+
+        tools_section = ""
+        if self.tools and not self._use_native_tools:
+            tool_names = ", ".join(sanitize_tool_name(t.name) for t in self.tools)
+            tools_section = self._i18n.retrieve(
+                "planning", "step_executor_tools_section"
+            ).format(tool_names=tool_names)
+        elif self.tools:
+            tool_names = ", ".join(sanitize_tool_name(t.name) for t in self.tools)
+            tools_section = f"\n\nAvailable tools: {tool_names}"
+
+        return self._i18n.retrieve("planning", "step_executor_system_prompt").format(
+            role=role,
+            backstory=backstory,
+            goal=goal,
+            tools_section=tools_section,
+        )
+
+    def _build_user_prompt(self, todo: TodoItem, context: StepExecutionContext) -> str:
+        """Build the user prompt for this specific step."""
+        parts: list[str] = []
+
+        # Include overall task context so the executor knows the full goal and
+        # required output format/location — critical for knowing WHAT to produce.
+        # We extract only the task body (not tool instructions or verification
+        # sections) to avoid duplicating directives already in the system prompt.
+        if context.task_description:
+            task_section = extract_task_section(context.task_description)
+            if task_section:
+                parts.append(
+                    self._i18n.retrieve(
+                        "planning", "step_executor_task_context"
+                    ).format(
+                        task_context=task_section,
+                    )
+                )
+
+        parts.append(
+            self._i18n.retrieve("planning", "step_executor_user_prompt").format(
+                step_description=todo.description,
+            )
+        )
+
+        if todo.tool_to_use:
+            parts.append(
+                self._i18n.retrieve("planning", "step_executor_suggested_tool").format(
+                    tool_to_use=todo.tool_to_use,
+                )
+            )
+
+        # Include dependency results (final results only, no traces)
+        if context.dependency_results:
+            parts.append(
+                self._i18n.retrieve("planning", "step_executor_context_header")
+            )
+            for step_num, result in sorted(context.dependency_results.items()):
+                parts.append(
+                    self._i18n.retrieve(
+                        "planning", "step_executor_context_entry"
+                    ).format(step_number=step_num, result=result)
+                )
+
+        parts.append(self._i18n.retrieve("planning", "step_executor_complete_step"))
+
+        return "\n".join(parts)
+
+    # ------------------------------------------------------------------
+    # Internal: Multi-turn execution loop
+    # ------------------------------------------------------------------
+
+    def _execute_text_parsed(
+        self,
+        messages: list[LLMMessage],
+        tool_calls_made: list[str],
+        max_step_iterations: int = 15,
+        step_timeout: int | None = None,
+        start_time: float | None = None,
+    ) -> str:
+        """Execute step using text-parsed tool calling with a multi-turn loop.
+
+        Iterates LLM call → tool execution → observation until the LLM
+        produces a Final Answer or max_step_iterations is reached.
+        This allows the agent to: run a command, see the output, adjust its
+        approach, and run another command — all within a single plan step.
+        """
+        use_stop_words = self.llm.supports_stop_words() if self.llm else False
+        last_tool_result = ""
+
+        for _ in range(max_step_iterations):
+            # Check step timeout
+            if step_timeout and start_time:
+                elapsed = time.monotonic() - start_time
+                if elapsed >= step_timeout:
+                    return last_tool_result or f"Step timed out after {elapsed:.0f}s"
+            answer = self.llm.call(
+                messages,
+                callbacks=self.callbacks,
+                from_task=self.task,
+                from_agent=self.agent,
+            )
+
+            if not answer:
+                raise ValueError("Empty response from LLM")
+
+            answer_str = str(answer)
+            formatted = process_llm_response(answer_str, use_stop_words)
+
+            if isinstance(formatted, AgentFinish):
+                return str(formatted.output)
+
+            if isinstance(formatted, AgentAction):
+                tool_calls_made.append(formatted.tool)
+                tool_result = self._execute_text_tool_with_events(formatted)
+                last_tool_result = tool_result
+                # Append the assistant's reasoning + action, then the observation.
+                # _build_observation_message handles vision sentinels so the LLM
+                # receives an image content block instead of raw base64 text.
+                messages.append({"role": "assistant", "content": answer_str})
+                messages.append(self._build_observation_message(tool_result))
+                continue
+
+            # Raw text response with no Final Answer marker — treat as done
+            return answer_str
+
+        # Max iterations reached — return the last tool result we accumulated
+        return last_tool_result
+
+    def _execute_text_tool_with_events(self, formatted: AgentAction) -> str:
+        """Execute text-parsed tool calls with tool usage events."""
+        args_dict = self._parse_tool_args(formatted.tool_input)
+        agent_key = getattr(self.agent, "key", "unknown") if self.agent else "unknown"
+        started_at = datetime.now()
+        crewai_event_bus.emit(
+            self,
+            event=ToolUsageStartedEvent(
+                tool_name=formatted.tool,
+                tool_args=args_dict,
+                from_agent=self.agent,
+                from_task=self.task,
+                agent_key=agent_key,
+            ),
+        )
+
+        try:
+            fingerprint_context = {}
+            if (
+                self.agent
+                and hasattr(self.agent, "security_config")
+                and hasattr(self.agent.security_config, "fingerprint")
+            ):
+                fingerprint_context = {
+                    "agent_fingerprint": str(self.agent.security_config.fingerprint)
+                }
+
+            tool_result = execute_tool_and_check_finality(
+                agent_action=formatted,
+                fingerprint_context=fingerprint_context,
+                tools=self.tools,
+                i18n=self._i18n,
+                agent_key=self.agent.key if self.agent else None,
+                agent_role=self.agent.role if self.agent else None,
+                tools_handler=self.tools_handler,
+                task=self.task,
+                agent=self.agent,
+                function_calling_llm=self.function_calling_llm,
+                crew=self.crew,
+            )
+        except Exception as e:
+            crewai_event_bus.emit(
+                self,
+                event=ToolUsageErrorEvent(
+                    tool_name=formatted.tool,
+                    tool_args=args_dict,
+                    from_agent=self.agent,
+                    from_task=self.task,
+                    agent_key=agent_key,
+                    error=e,
+                ),
+            )
+            raise
+
+        crewai_event_bus.emit(
+            self,
+            event=ToolUsageFinishedEvent(
+                output=str(tool_result.result),
+                tool_name=formatted.tool,
+                tool_args=args_dict,
+                from_agent=self.agent,
+                from_task=self.task,
+                agent_key=agent_key,
+                started_at=started_at,
+                finished_at=datetime.now(),
+            ),
+        )
+        return str(tool_result.result)
+
+    def _parse_tool_args(self, tool_input: Any) -> dict[str, Any]:
+        """Parse tool args from the parser output into a dict payload for events."""
+        if isinstance(tool_input, dict):
+            return tool_input
+        if isinstance(tool_input, str):
+            stripped_input = tool_input.strip()
+            if not stripped_input:
+                return {}
+            try:
+                parsed = json.loads(stripped_input)
+                if isinstance(parsed, dict):
+                    return parsed
+                return {"input": parsed}
+            except json.JSONDecodeError:
+                return {"input": stripped_input}
+        return {"input": str(tool_input)}
+
+    # ------------------------------------------------------------------
+    # Internal: Vision support
+    # ------------------------------------------------------------------
+
+    @staticmethod
+    def _parse_vision_sentinel(raw: str) -> tuple[str, str] | None:
+        """Parse a VISION_IMAGE sentinel into (media_type, base64_data), or None."""
+        prefix = "VISION_IMAGE:"
+        if not raw.startswith(prefix):
+            return None
+        rest = raw[len(prefix) :]
+        sep = rest.find(":")
+        if sep <= 0:
+            return None
+        return rest[:sep], rest[sep + 1 :]
+
+    @staticmethod
+    def _build_observation_message(tool_result: str) -> LLMMessage:
+        """Build an observation message, converting vision sentinels to image blocks.
+
+        When a tool returns a VISION_IMAGE sentinel (e.g. from read_image),
+        we build a multimodal content block so the LLM can actually *see*
+        the image rather than receiving a wall of base64 text.
+
+        Uses the standard image_url / data-URI format so each LLM provider's
+        SDK (OpenAI, LiteLLM, etc.) handles the provider-specific conversion.
+
+        Format: ``VISION_IMAGE:<media_type>:<base64_data>``
+        """
+        parsed = StepExecutor._parse_vision_sentinel(tool_result)
+        if parsed:
+            media_type, b64_data = parsed
+            return {
+                "role": "user",
+                "content": [
+                    {"type": "text", "text": "Observation: Here is the image:"},
+                    {
+                        "type": "image_url",
+                        "image_url": {
+                            "url": f"data:{media_type};base64,{b64_data}",
+                        },
+                    },
+                ],
+            }
+        return {"role": "user", "content": f"Observation: {tool_result}"}
+
+    def _validate_expected_tool_usage(
+        self,
+        todo: TodoItem,
+        tool_calls_made: list[str],
+    ) -> None:
+        """Fail step execution when a required tool is configured but not called."""
+        expected_tool = getattr(todo, "tool_to_use", None)
+        if not expected_tool:
+            return
+        expected_tool_name = sanitize_tool_name(expected_tool)
+        available_tool_names = {
+            sanitize_tool_name(tool.name)
+            for tool in self.tools
+            if getattr(tool, "name", "")
+        } | set(self._available_functions.keys())
+        if expected_tool_name not in available_tool_names:
+            return
+        called_names = {sanitize_tool_name(name) for name in tool_calls_made}
+        if expected_tool_name not in called_names:
+            raise ValueError(
+                f"Expected tool '{expected_tool_name}' was not called "
+                f"for step {todo.step_number}."
+            )
+
+    def _execute_native(
+        self,
+        messages: list[LLMMessage],
+        tool_calls_made: list[str],
+        max_step_iterations: int = 15,
+        step_timeout: int | None = None,
+        start_time: float | None = None,
+    ) -> str:
+        """Execute step using native function calling with a multi-turn loop.
+
+        Iterates LLM call → tool execution → appended results until the LLM
+        returns a text answer (no more tool calls) or max_step_iterations is
+        reached.  This lets the agent run a shell command, observe the output,
+        correct mistakes, and issue follow-up commands — all within one step.
+        """
+        accumulated_results: list[str] = []
+
+        for _ in range(max_step_iterations):
+            # Check step timeout
+            if step_timeout and start_time:
+                elapsed = time.monotonic() - start_time
+                if elapsed >= step_timeout:
+                    return (
+                        "\n\n".join(accumulated_results)
+                        if accumulated_results
+                        else f"Step timed out after {elapsed:.0f}s"
+                    )
+            answer = self.llm.call(
+                messages,
+                tools=self._openai_tools,
+                callbacks=self.callbacks,
+                from_task=self.task,
+                from_agent=self.agent,
+            )
+
+            if not answer:
+                raise ValueError("Empty response from LLM")
+
+            if isinstance(answer, BaseModel):
+                return answer.model_dump_json()
+
+            if isinstance(answer, list) and answer and is_tool_call_list(answer):
+                # _execute_native_tool_calls appends assistant + tool messages
+                # to `messages` as a side-effect, so the next LLM call will
+                # see the full conversation history including tool outputs.
+                result = self._execute_native_tool_calls(
+                    answer, messages, tool_calls_made
+                )
+                accumulated_results.append(result)
+                continue
+
+            # Text answer → LLM decided the step is done
+            return str(answer)
+
+        # Max iterations reached — return everything we accumulated
+        return "\n".join(filter(None, accumulated_results))
+
+    def _execute_native_tool_calls(
+        self,
+        tool_calls: list[Any],
+        messages: list[LLMMessage],
+        tool_calls_made: list[str],
+    ) -> str:
+        """Execute a batch of native tool calls and return their results.
+
+        Returns the result of the first tool marked result_as_answer if any,
+        otherwise returns all tool results concatenated.
+        """
+        assistant_message, _reports = build_tool_calls_assistant_message(tool_calls)
+        if assistant_message:
+            messages.append(assistant_message)
+
+        tool_results: list[str] = []
+        for tool_call in tool_calls:
+            call_result = execute_single_native_tool_call(
+                tool_call,
+                available_functions=self._available_functions,
+                original_tools=self.original_tools,
+                structured_tools=self.tools,
+                tools_handler=self.tools_handler,
+                agent=self.agent,
+                task=self.task,
+                crew=self.crew,
+                event_source=self,
+                printer=self._printer,
+                verbose=bool(self.agent and self.agent.verbose),
+            )
+
+            if call_result.func_name:
+                tool_calls_made.append(call_result.func_name)
+
+            if call_result.result_as_answer:
+                return str(call_result.result)
+
+            if call_result.tool_message:
+                raw_content = call_result.tool_message.get("content", "")
+                if isinstance(raw_content, str):
+                    parsed = self._parse_vision_sentinel(raw_content)
+                    if parsed:
+                        media_type, b64_data = parsed
+                        # Replace the sentinel with a standard image_url content block.
+                        # Each provider's _format_messages handles conversion to
+                        # its native format (e.g. Anthropic image blocks).
+                        modified: LLMMessage = cast(
+                            LLMMessage, dict(call_result.tool_message)
+                        )
+                        modified["content"] = [
+                            {
+                                "type": "image_url",
+                                "image_url": {
+                                    "url": f"data:{media_type};base64,{b64_data}",
+                                },
+                            }
+                        ]
+                        messages.append(modified)
+                        tool_results.append("[image]")
+                    else:
+                        messages.append(call_result.tool_message)
+                        if raw_content:
+                            tool_results.append(raw_content)
+                else:
+                    messages.append(call_result.tool_message)
+                    if raw_content:
+                        tool_results.append(str(raw_content))
+
+        return "\n".join(tool_results) if tool_results else ""

lib/crewai/src/crewai/cli/authentication/__init__.py

@@ -1,5 +1,4 @@
 from crewai.cli.authentication.main import AuthenticationCommand
 
 
-
 __all__ = ["AuthenticationCommand"]

lib/crewai/src/crewai/cli/cli.py

@@ -182,15 +182,24 @@ def log_tasks_outputs() -> None:
 @crewai.command()
 @click.option("-m", "--memory", is_flag=True, help="Reset MEMORY")
 @click.option(
-    "-l", "--long", is_flag=True, hidden=True,
+    "-l",
+    "--long",
+    is_flag=True,
+    hidden=True,
     help="[Deprecated: use --memory] Reset memory",
 )
 @click.option(
-    "-s", "--short", is_flag=True, hidden=True,
+    "-s",
+    "--short",
+    is_flag=True,
+    hidden=True,
     help="[Deprecated: use --memory] Reset memory",
 )
 @click.option(
-    "-e", "--entities", is_flag=True, hidden=True,
+    "-e",
+    "--entities",
+    is_flag=True,
+    hidden=True,
     help="[Deprecated: use --memory] Reset memory",
 )
 @click.option("-kn", "--knowledge", is_flag=True, help="Reset KNOWLEDGE storage")
@@ -218,7 +227,13 @@ def reset_memories(
         # Treat legacy flags as --memory with a deprecation warning
         if long or short or entities:
             legacy_used = [
-                f for f, v in [("--long", long), ("--short", short), ("--entities", entities)] if v
+                f
+                for f, v in [
+                    ("--long", long),
+                    ("--short", short),
+                    ("--entities", entities),
+                ]
+                if v
             ]
             click.echo(
                 f"Warning: {', '.join(legacy_used)} {'is' if len(legacy_used) == 1 else 'are'} "
@@ -238,9 +253,7 @@ def reset_memories(
                 "Please specify at least one memory type to reset using the appropriate flags."
             )
             return
-        reset_memories_command(
-            memory, knowledge, agent_knowledge, kickoff_outputs, all
-        )
+        reset_memories_command(memory, knowledge, agent_knowledge, kickoff_outputs, all)
     except Exception as e:
         click.echo(f"An error occurred while resetting memories: {e}", err=True)
 
@@ -669,18 +682,11 @@ def traces_enable():
     from rich.console import Console
     from rich.panel import Panel
 
-    from crewai.events.listeners.tracing.utils import (
-        _load_user_data,
-        _save_user_data,
-    )
+    from crewai.events.listeners.tracing.utils import update_user_data
 
     console = Console()
 
-    # Update user data to enable traces
-    user_data = _load_user_data()
-    user_data["trace_consent"] = True
-    user_data["first_execution_done"] = True
-    _save_user_data(user_data)
+    update_user_data({"trace_consent": True, "first_execution_done": True})
 
     panel = Panel(
         "✅ Trace collection has been enabled!\n\n"
@@ -699,18 +705,11 @@ def traces_disable():
     from rich.console import Console
     from rich.panel import Panel
 
-    from crewai.events.listeners.tracing.utils import (
-        _load_user_data,
-        _save_user_data,
-    )
+    from crewai.events.listeners.tracing.utils import update_user_data
 
     console = Console()
 
-    # Update user data to disable traces
-    user_data = _load_user_data()
-    user_data["trace_consent"] = False
-    user_data["first_execution_done"] = True
-    _save_user_data(user_data)
+    update_user_data({"trace_consent": False, "first_execution_done": True})
 
     panel = Panel(
         "❌ Trace collection has been disabled!\n\n"

lib/crewai/src/crewai/cli/create_crew.py

@@ -143,7 +143,7 @@ def create_folder_structure(
         (folder_path / "src" / folder_name).mkdir(parents=True)
         (folder_path / "src" / folder_name / "tools").mkdir(parents=True)
         (folder_path / "src" / folder_name / "config").mkdir(parents=True)
-        
+
         # Copy AGENTS.md to project root (top-level projects only)
         package_dir = Path(__file__).parent
         agents_md_src = package_dir / "templates" / "AGENTS.md"

lib/crewai/src/crewai/cli/create_flow.py

@@ -1,5 +1,5 @@
-import shutil
 from pathlib import Path
+import shutil
 
 import click
 

lib/crewai/src/crewai/cli/crew_chat.py

@@ -1,3 +1,4 @@
+import contextvars
 import json
 from pathlib import Path
 import platform
@@ -80,7 +81,10 @@ def run_chat() -> None:
 
     # Start loading indicator
     loading_complete = threading.Event()
-    loading_thread = threading.Thread(target=show_loading, args=(loading_complete,))
+    ctx = contextvars.copy_context()
+    loading_thread = threading.Thread(
+        target=ctx.run, args=(show_loading, loading_complete)
+    )
     loading_thread.start()
 
     try:

lib/crewai/src/crewai/cli/memory_tui.py

@@ -125,13 +125,19 @@ class MemoryTUI(App[None]):
             from crewai.memory.storage.lancedb_storage import LanceDBStorage
             from crewai.memory.unified_memory import Memory
 
-            storage = LanceDBStorage(path=storage_path) if storage_path else LanceDBStorage()
+            storage = (
+                LanceDBStorage(path=storage_path) if storage_path else LanceDBStorage()
+            )
             embedder = None
             if embedder_config is not None:
                 from crewai.rag.embeddings.factory import build_embedder
 
                 embedder = build_embedder(embedder_config)
-            self._memory = Memory(storage=storage, embedder=embedder) if embedder else Memory(storage=storage)
+            self._memory = (
+                Memory(storage=storage, embedder=embedder)
+                if embedder
+                else Memory(storage=storage)
+            )
         except Exception as e:
             self._init_error = str(e)
 
@@ -200,11 +206,7 @@ class MemoryTUI(App[None]):
                 if len(record.content) > 80
                 else record.content
             )
-            label = (
-                f"{date_str}  "
-                f"[bold]{record.importance:.1f}[/]  "
-                f"{preview}"
-            )
+            label = f"{date_str}  [bold]{record.importance:.1f}[/]  {preview}"
             option_list.add_option(label)
 
     def _populate_recall_list(self) -> None:
@@ -220,9 +222,7 @@ class MemoryTUI(App[None]):
                 else m.record.content
             )
             label = (
-                f"[bold]\\[{m.score:.2f}][/]  "
-                f"{preview}  "
-                f"[dim]scope={m.record.scope}[/]"
+                f"[bold]\\[{m.score:.2f}][/]  {preview}  [dim]scope={m.record.scope}[/]"
             )
             option_list.add_option(label)
 
@@ -251,8 +251,7 @@ class MemoryTUI(App[None]):
         lines.append(f"[dim]Scope:[/]          [bold]{record.scope}[/]")
         lines.append(f"[dim]Importance:[/]      [bold]{record.importance:.2f}[/]")
         lines.append(
-            f"[dim]Created:[/]        "
-            f"{record.created_at.strftime('%Y-%m-%d %H:%M:%S')}"
+            f"[dim]Created:[/]        {record.created_at.strftime('%Y-%m-%d %H:%M:%S')}"
         )
         lines.append(
             f"[dim]Last accessed:[/]  "
@@ -362,17 +361,11 @@ class MemoryTUI(App[None]):
         panel = self.query_one("#info-panel", Static)
         panel.loading = True
         try:
-            scope = (
-                self._selected_scope
-                if self._selected_scope != "/"
-                else None
-            )
+            scope = self._selected_scope if self._selected_scope != "/" else None
             loop = asyncio.get_event_loop()
             matches = await loop.run_in_executor(
                 None,
-                lambda: self._memory.recall(
-                    query, scope=scope, limit=10, depth="deep"
-                ),
+                lambda: self._memory.recall(query, scope=scope, limit=10, depth="deep"),
             )
             self._recall_matches = matches or []
             self._view_mode = "recall"

lib/crewai/src/crewai/cli/plus_api.py

@@ -22,14 +22,15 @@ class PlusAPI:
     EPHEMERAL_TRACING_RESOURCE = "/crewai_plus/api/v1/tracing/ephemeral"
     INTEGRATIONS_RESOURCE = "/crewai_plus/api/v1/integrations"
 
-    def __init__(self, api_key: str) -> None:
+    def __init__(self, api_key: str | None = None) -> None:
         self.api_key = api_key
         self.headers = {
-            "Authorization": f"Bearer {api_key}",
             "Content-Type": "application/json",
             "User-Agent": f"CrewAI-CLI/{get_crewai_version()}",
             "X-Crewai-Version": get_crewai_version(),
         }
+        if api_key:
+            self.headers["Authorization"] = f"Bearer {api_key}"
         settings = Settings()
         if settings.org_uuid:
             self.headers["X-Crewai-Organization-Id"] = settings.org_uuid
@@ -48,8 +49,13 @@ class PlusAPI:
         with httpx.Client(trust_env=False, verify=verify) as client:
             return client.request(method, url, headers=self.headers, **kwargs)
 
-    def login_to_tool_repository(self) -> httpx.Response:
-        return self._make_request("POST", f"{self.TOOLS_RESOURCE}/login")
+    def login_to_tool_repository(
+        self, user_identifier: str | None = None
+    ) -> httpx.Response:
+        payload = {}
+        if user_identifier:
+            payload["user_identifier"] = user_identifier
+        return self._make_request("POST", f"{self.TOOLS_RESOURCE}/login", json=payload)
 
     def get_tool(self, handle: str) -> httpx.Response:
         return self._make_request("GET", f"{self.TOOLS_RESOURCE}/{handle}")

lib/crewai/src/crewai/cli/reset_memories_command.py

@@ -95,9 +95,7 @@ def reset_memories_command(
                 continue
             if memory:
                 _reset_flow_memory(flow)
-                click.echo(
-                    f"[Flow ({flow_name})] Memory has been reset."
-                )
+                click.echo(f"[Flow ({flow_name})] Memory has been reset.")
 
     except subprocess.CalledProcessError as e:
         click.echo(f"An error occurred while resetting the memories: {e}", err=True)

lib/crewai/src/crewai/cli/templates/crew/pyproject.toml

@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
 authors = [{ name = "Your Name", email = "you@example.com" }]
 requires-python = ">=3.10,<3.14"
 dependencies = [
-    "crewai[tools]==1.10.0"
+    "crewai[tools]==1.11.0rc1"
 ]
 
 [project.scripts]

lib/crewai/src/crewai/cli/templates/flow/pyproject.toml

@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
 authors = [{ name = "Your Name", email = "you@example.com" }]
 requires-python = ">=3.10,<3.14"
 dependencies = [
-    "crewai[tools]==1.10.0"
+    "crewai[tools]==1.11.0rc1"
 ]
 
 [project.scripts]

lib/crewai/src/crewai/cli/templates/tool/pyproject.toml

@@ -5,7 +5,7 @@ description = "Power up your crews with {{folder_name}}"
 readme = "README.md"
 requires-python = ">=3.10,<3.14"
 dependencies = [
-    "crewai[tools]==1.10.0"
+    "crewai[tools]==1.11.0rc1"
 ]
 
 [tool.crewai]

lib/crewai/src/crewai/cli/tools/main.py

@@ -23,6 +23,7 @@ from crewai.cli.utils import (
     tree_copy,
     tree_find_and_replace,
 )
+from crewai.events.listeners.tracing.utils import get_user_id
 
 
 console = Console()
@@ -169,7 +170,9 @@ class ToolCommand(BaseCommand, PlusAPIMixin):
         console.print(f"Successfully installed {handle}", style="bold green")
 
     def login(self) -> None:
-        login_response = self.plus_api_client.login_to_tool_repository()
+        login_response = self.plus_api_client.login_to_tool_repository(
+            user_identifier=get_user_id()
+        )
 
         if login_response.status_code != 200:
             console.print(

lib/crewai/src/crewai/cli/utils.py

@@ -442,9 +442,7 @@ def get_flows(flow_path: str = "main.py") -> list[Flow]:
         for search_path in search_paths:
             for root, dirs, files in os.walk(search_path):
                 dirs[:] = [
-                    d
-                    for d in dirs
-                    if d not in _SKIP_DIRS and not d.startswith(".")
+                    d for d in dirs if d not in _SKIP_DIRS and not d.startswith(".")
                 ]
                 if flow_path in files and "cli/templates" not in root:
                     file_os_path = os.path.join(root, flow_path)
@@ -464,9 +462,7 @@ def get_flows(flow_path: str = "main.py") -> list[Flow]:
                             for attr_name in dir(module):
                                 module_attr = getattr(module, attr_name)
                                 try:
-                                    if flow_instance := get_flow_instance(
-                                        module_attr
-                                    ):
+                                    if flow_instance := get_flow_instance(module_attr):
                                         flow_instances.append(flow_instance)
                                 except Exception:  # noqa: S112
                                     continue

lib/crewai/src/crewai/crew.py

@@ -1410,9 +1410,7 @@ class Crew(FlowTrackable, BaseModel):
             return self._merge_tools(tools, cast(list[BaseTool], code_tools))
         return tools
 
-    def _add_memory_tools(
-        self, tools: list[BaseTool], memory: Any
-    ) -> list[BaseTool]:
+    def _add_memory_tools(self, tools: list[BaseTool], memory: Any) -> list[BaseTool]:
         """Add recall and remember tools when memory is available.
 
         Args:

lib/crewai/src/crewai/crews/__init__.py

@@ -1,5 +1,4 @@
 from crewai.crews.crew_output import CrewOutput
 
 
-
 __all__ = ["CrewOutput"]

lib/crewai/src/crewai/events/base_event_listener.py

@@ -23,4 +23,3 @@ class BaseEventListener(ABC):
         Args:
             crewai_event_bus: The event bus to register listeners on.
         """
-        pass

lib/crewai/src/crewai/events/event_listener.py

@@ -75,6 +75,14 @@ from crewai.events.types.mcp_events import (
     MCPToolExecutionFailedEvent,
     MCPToolExecutionStartedEvent,
 )
+from crewai.events.types.observation_events import (
+    GoalAchievedEarlyEvent,
+    PlanRefinementEvent,
+    PlanReplanTriggeredEvent,
+    StepObservationCompletedEvent,
+    StepObservationFailedEvent,
+    StepObservationStartedEvent,
+)
 from crewai.events.types.reasoning_events import (
     AgentReasoningCompletedEvent,
     AgentReasoningFailedEvent,
@@ -535,6 +543,64 @@ class EventListener(BaseEventListener):
                 event.error,
             )
 
+        # ----------- OBSERVATION EVENTS (Plan-and-Execute) -----------
+
+        @crewai_event_bus.on(StepObservationStartedEvent)
+        def on_step_observation_started(
+            _: Any, event: StepObservationStartedEvent
+        ) -> None:
+            self.formatter.handle_observation_started(
+                event.agent_role,
+                event.step_number,
+                event.step_description,
+            )
+
+        @crewai_event_bus.on(StepObservationCompletedEvent)
+        def on_step_observation_completed(
+            _: Any, event: StepObservationCompletedEvent
+        ) -> None:
+            self.formatter.handle_observation_completed(
+                event.agent_role,
+                event.step_number,
+                event.step_completed_successfully,
+                event.remaining_plan_still_valid,
+                event.key_information_learned,
+                event.needs_full_replan,
+                event.goal_already_achieved,
+            )
+
+        @crewai_event_bus.on(StepObservationFailedEvent)
+        def on_step_observation_failed(
+            _: Any, event: StepObservationFailedEvent
+        ) -> None:
+            self.formatter.handle_observation_failed(
+                event.step_number,
+                event.error,
+            )
+
+        @crewai_event_bus.on(PlanRefinementEvent)
+        def on_plan_refinement(_: Any, event: PlanRefinementEvent) -> None:
+            self.formatter.handle_plan_refinement(
+                event.step_number,
+                event.refined_step_count,
+                event.refinements,
+            )
+
+        @crewai_event_bus.on(PlanReplanTriggeredEvent)
+        def on_plan_replan_triggered(_: Any, event: PlanReplanTriggeredEvent) -> None:
+            self.formatter.handle_plan_replan(
+                event.replan_reason,
+                event.replan_count,
+                event.completed_steps_preserved,
+            )
+
+        @crewai_event_bus.on(GoalAchievedEarlyEvent)
+        def on_goal_achieved_early(_: Any, event: GoalAchievedEarlyEvent) -> None:
+            self.formatter.handle_goal_achieved_early(
+                event.steps_completed,
+                event.steps_remaining,
+            )
+
         # ----------- AGENT LOGGING EVENTS -----------
 
         @crewai_event_bus.on(AgentLogsStartedEvent)

lib/crewai/src/crewai/events/listeners/tracing/trace_batch_manager.py

@@ -15,6 +15,7 @@ from crewai.cli.plus_api import PlusAPI
 from crewai.cli.version import get_crewai_version
 from crewai.events.listeners.tracing.types import TraceEvent
 from crewai.events.listeners.tracing.utils import (
+    get_user_id,
     is_tracing_enabled_in_context,
     should_auto_collect_first_time_traces,
 )
@@ -67,7 +68,7 @@ class TraceBatchManager:
                 api_key=get_auth_token(),
             )
         except AuthError:
-            self.plus_api = PlusAPI(api_key="")
+            self.plus_api = PlusAPI()
         self.ephemeral_trace_url = None
 
     def initialize_batch(
@@ -120,7 +121,6 @@ class TraceBatchManager:
             payload = {
                 "trace_id": self.current_batch.batch_id,
                 "execution_type": execution_metadata.get("execution_type", "crew"),
-                "user_identifier": execution_metadata.get("user_context", None),
                 "execution_context": {
                     "crew_fingerprint": execution_metadata.get("crew_fingerprint"),
                     "crew_name": execution_metadata.get("crew_name", None),
@@ -140,6 +140,7 @@ class TraceBatchManager:
             }
             if use_ephemeral:
                 payload["ephemeral_trace_id"] = self.current_batch.batch_id
+                payload["user_identifier"] = get_user_id()
 
             response = (
                 self.plus_api.initialize_ephemeral_trace_batch(payload)

lib/crewai/src/crewai/events/listeners/tracing/trace_listener.py

@@ -93,6 +93,14 @@ from crewai.events.types.memory_events import (
     MemorySaveFailedEvent,
     MemorySaveStartedEvent,
 )
+from crewai.events.types.observation_events import (
+    GoalAchievedEarlyEvent,
+    PlanRefinementEvent,
+    PlanReplanTriggeredEvent,
+    StepObservationCompletedEvent,
+    StepObservationFailedEvent,
+    StepObservationStartedEvent,
+)
 from crewai.events.types.reasoning_events import (
     AgentReasoningCompletedEvent,
     AgentReasoningFailedEvent,
@@ -437,6 +445,39 @@ class TraceCollectionListener(BaseEventListener):
         ) -> None:
             self._handle_action_event("agent_reasoning_failed", source, event)
 
+        # Observation events (Plan-and-Execute)
+        @event_bus.on(StepObservationStartedEvent)
+        def on_step_observation_started(
+            source: Any, event: StepObservationStartedEvent
+        ) -> None:
+            self._handle_action_event("step_observation_started", source, event)
+
+        @event_bus.on(StepObservationCompletedEvent)
+        def on_step_observation_completed(
+            source: Any, event: StepObservationCompletedEvent
+        ) -> None:
+            self._handle_action_event("step_observation_completed", source, event)
+
+        @event_bus.on(StepObservationFailedEvent)
+        def on_step_observation_failed(
+            source: Any, event: StepObservationFailedEvent
+        ) -> None:
+            self._handle_action_event("step_observation_failed", source, event)
+
+        @event_bus.on(PlanRefinementEvent)
+        def on_plan_refinement(source: Any, event: PlanRefinementEvent) -> None:
+            self._handle_action_event("plan_refinement", source, event)
+
+        @event_bus.on(PlanReplanTriggeredEvent)
+        def on_plan_replan_triggered(
+            source: Any, event: PlanReplanTriggeredEvent
+        ) -> None:
+            self._handle_action_event("plan_replan_triggered", source, event)
+
+        @event_bus.on(GoalAchievedEarlyEvent)
+        def on_goal_achieved_early(source: Any, event: GoalAchievedEarlyEvent) -> None:
+            self._handle_action_event("goal_achieved_early", source, event)
+
         @event_bus.on(KnowledgeRetrievalStartedEvent)
         def on_knowledge_retrieval_started(
             source: Any, event: KnowledgeRetrievalStartedEvent

lib/crewai/src/crewai/events/listeners/tracing/utils.py

@@ -1,4 +1,5 @@
 from collections.abc import Callable
+import contextvars
 from contextvars import ContextVar, Token
 from datetime import datetime
 import getpass
@@ -18,6 +19,7 @@ from rich.console import Console
 from rich.panel import Panel
 from rich.text import Text
 
+from crewai.utilities.lock_store import lock as store_lock
 from crewai.utilities.paths import db_storage_path
 from crewai.utilities.serialization import to_serializable
 
@@ -137,12 +139,25 @@ def _load_user_data() -> dict[str, Any]:
     return {}
 
 
-def _save_user_data(data: dict[str, Any]) -> None:
+def _user_data_lock_name() -> str:
+    """Return a stable lock name for the user data file."""
+    return f"file:{os.path.realpath(_user_data_file())}"
+
+
+def update_user_data(updates: dict[str, Any]) -> None:
+    """Atomically read-modify-write the user data file.
+
+    Args:
+        updates: Key-value pairs to merge into the existing user data.
+    """
     try:
-        p = _user_data_file()
-        p.write_text(json.dumps(data, indent=2))
+        with store_lock(_user_data_lock_name()):
+            data = _load_user_data()
+            data.update(updates)
+            p = _user_data_file()
+            p.write_text(json.dumps(data, indent=2))
     except (OSError, PermissionError) as e:
-        logger.warning(f"Failed to save user data: {e}")
+        logger.warning(f"Failed to update user data: {e}")
 
 
 def has_user_declined_tracing() -> bool:
@@ -357,24 +372,30 @@ def _get_generic_system_id() -> str | None:
     return None
 
 
-def get_user_id() -> str:
-    """Stable, anonymized user identifier with caching."""
-    data = _load_user_data()
-
-    if "user_id" in data:
-        return cast(str, data["user_id"])
-
+def _generate_user_id() -> str:
+    """Compute an anonymized user identifier from username and machine ID."""
     try:
         username = getpass.getuser()
     except Exception:
         username = "unknown"
 
     seed = f"{username}|{_get_machine_id()}"
-    uid = hashlib.sha256(seed.encode()).hexdigest()
+    return hashlib.sha256(seed.encode()).hexdigest()
 
-    data["user_id"] = uid
-    _save_user_data(data)
-    return uid
+
+def get_user_id() -> str:
+    """Stable, anonymized user identifier with caching."""
+    with store_lock(_user_data_lock_name()):
+        data = _load_user_data()
+
+        if "user_id" in data:
+            return cast(str, data["user_id"])
+
+        uid = _generate_user_id()
+        data["user_id"] = uid
+        p = _user_data_file()
+        p.write_text(json.dumps(data, indent=2))
+        return uid
 
 
 def is_first_execution() -> bool:
@@ -389,20 +410,23 @@ def mark_first_execution_done(user_consented: bool = False) -> None:
     Args:
         user_consented: Whether the user consented to trace collection.
     """
-    data = _load_user_data()
-    if data.get("first_execution_done", False):
-        return
+    with store_lock(_user_data_lock_name()):
+        data = _load_user_data()
+        if data.get("first_execution_done", False):
+            return
 
-    data.update(
-        {
-            "first_execution_done": True,
-            "first_execution_at": datetime.now().timestamp(),
-            "user_id": get_user_id(),
-            "machine_id": _get_machine_id(),
-            "trace_consent": user_consented,
-        }
-    )
-    _save_user_data(data)
+        uid = data.get("user_id") or _generate_user_id()
+        data.update(
+            {
+                "first_execution_done": True,
+                "first_execution_at": datetime.now().timestamp(),
+                "user_id": uid,
+                "machine_id": _get_machine_id(),
+                "trace_consent": user_consented,
+            }
+        )
+        p = _user_data_file()
+        p.write_text(json.dumps(data, indent=2))
 
 
 def safe_serialize_to_dict(obj: Any, exclude: set[str] | None = None) -> dict[str, Any]:
@@ -509,7 +533,8 @@ def prompt_user_for_trace_viewing(timeout_seconds: int = 20) -> bool:
                 # Handle all input-related errors silently
                 result[0] = False
 
-        input_thread = threading.Thread(target=get_input, daemon=True)
+        ctx = contextvars.copy_context()
+        input_thread = threading.Thread(target=ctx.run, args=(get_input,), daemon=True)
         input_thread.start()
         input_thread.join(timeout=timeout_seconds)
 

lib/crewai/src/crewai/events/types/llm_events.py

@@ -86,3 +86,11 @@ class LLMStreamChunkEvent(LLMEventBase):
     tool_call: ToolCall | None = None
     call_type: LLMCallType | None = None
     response_id: str | None = None
+
+
+class LLMThinkingChunkEvent(LLMEventBase):
+    """Event emitted when a thinking/reasoning chunk is received from a thinking model"""
+
+    type: str = "llm_thinking_chunk"
+    chunk: str
+    response_id: str | None = None

lib/crewai/src/crewai/events/types/observation_events.py

@@ -0,0 +1,99 @@
+"""Observation events for the Plan-and-Execute architecture.
+
+Emitted during the Observation phase (PLAN-AND-ACT Section 3.3) when the
+PlannerObserver analyzes step execution results and decides on plan
+continuation, refinement, or replanning.
+"""
+
+from typing import Any
+
+from crewai.events.base_events import BaseEvent
+
+
+class ObservationEvent(BaseEvent):
+    """Base event for observation phase events."""
+
+    type: str
+    agent_role: str
+    step_number: int
+    step_description: str = ""
+    from_task: Any | None = None
+    from_agent: Any | None = None
+
+    def __init__(self, **data: Any) -> None:
+        super().__init__(**data)
+        self._set_task_params(data)
+        self._set_agent_params(data)
+
+
+class StepObservationStartedEvent(ObservationEvent):
+    """Emitted when the Planner begins observing a step's result.
+
+    Fires after every step execution, before the observation LLM call.
+    """
+
+    type: str = "step_observation_started"
+
+
+class StepObservationCompletedEvent(ObservationEvent):
+    """Emitted when the Planner finishes observing a step's result.
+
+    Contains the full observation analysis: what was learned, whether
+    the plan is still valid, and what action to take next.
+    """
+
+    type: str = "step_observation_completed"
+    step_completed_successfully: bool = True
+    key_information_learned: str = ""
+    remaining_plan_still_valid: bool = True
+    needs_full_replan: bool = False
+    replan_reason: str | None = None
+    goal_already_achieved: bool = False
+    suggested_refinements: list[str] | None = None
+
+
+class StepObservationFailedEvent(ObservationEvent):
+    """Emitted when the observation LLM call itself fails.
+
+    The system defaults to continuing the plan when this happens,
+    but the event allows monitoring/alerting on observation failures.
+    """
+
+    type: str = "step_observation_failed"
+    error: str = ""
+
+
+class PlanRefinementEvent(ObservationEvent):
+    """Emitted when the Planner refines upcoming step descriptions.
+
+    This is the lightweight refinement path — no full replan, just
+    sharpening pending todo descriptions based on new information.
+    """
+
+    type: str = "plan_refinement"
+    refined_step_count: int = 0
+    refinements: list[str] | None = None
+
+
+class PlanReplanTriggeredEvent(ObservationEvent):
+    """Emitted when the Planner triggers a full replan.
+
+    The remaining plan was deemed fundamentally wrong and will be
+    regenerated from scratch, preserving completed step results.
+    """
+
+    type: str = "plan_replan_triggered"
+    replan_reason: str = ""
+    replan_count: int = 0
+    completed_steps_preserved: int = 0
+
+
+class GoalAchievedEarlyEvent(ObservationEvent):
+    """Emitted when the Planner detects the goal was achieved early.
+
+    Remaining steps will be skipped and execution will finalize.
+    """
+
+    type: str = "goal_achieved_early"
+    steps_remaining: int = 0
+    steps_completed: int = 0

lib/crewai/src/crewai/events/types/reasoning_events.py

@@ -9,7 +9,7 @@ class ReasoningEvent(BaseEvent):
     type: str
     attempt: int = 1
     agent_role: str
-    task_id: str
+    task_id: str | None = None
     task_name: str | None = None
     from_task: Any | None = None
     agent_id: str | None = None

lib/crewai/src/crewai/events/utils/console_formatter.py

@@ -43,6 +43,7 @@ def should_suppress_console_output() -> bool:
 
 class ConsoleFormatter:
     tool_usage_counts: ClassVar[dict[str, int]] = {}
+    _tool_counts_lock: ClassVar[threading.Lock] = threading.Lock()
 
     current_a2a_turn_count: int = 0
     _pending_a2a_message: str | None = None
@@ -445,9 +446,11 @@ To enable tracing, do any one of these:
         if not self.verbose:
             return
 
-        # Update tool usage count
-        self.tool_usage_counts[tool_name] = self.tool_usage_counts.get(tool_name, 0) + 1
-        iteration = self.tool_usage_counts[tool_name]
+        with self._tool_counts_lock:
+            self.tool_usage_counts[tool_name] = (
+                self.tool_usage_counts.get(tool_name, 0) + 1
+            )
+            iteration = self.tool_usage_counts[tool_name]
 
         content = Text()
         content.append("Tool: ", style="white")
@@ -474,7 +477,8 @@ To enable tracing, do any one of these:
         if not self.verbose:
             return
 
-        iteration = self.tool_usage_counts.get(tool_name, 1)
+        with self._tool_counts_lock:
+            iteration = self.tool_usage_counts.get(tool_name, 1)
 
         content = Text()
         content.append("Tool Completed\n", style="green bold")
@@ -500,7 +504,8 @@ To enable tracing, do any one of these:
         if not self.verbose:
             return
 
-        iteration = self.tool_usage_counts.get(tool_name, 1)
+        with self._tool_counts_lock:
+            iteration = self.tool_usage_counts.get(tool_name, 1)
 
         content = Text()
         content.append("Tool Failed\n", style="red bold")
@@ -936,6 +941,152 @@ To enable tracing, do any one of these:
         )
         self.print_panel(error_content, "❌ Reasoning Error", "red")
 
+    # ----------- OBSERVATION EVENTS (Plan-and-Execute) -----------
+
+    def handle_observation_started(
+        self,
+        agent_role: str,
+        step_number: int,
+        step_description: str,
+    ) -> None:
+        """Handle step observation started event."""
+        if not self.verbose:
+            return
+
+        content = Text()
+        content.append("Observation Started\n", style="cyan bold")
+        content.append("Agent: ", style="white")
+        content.append(f"{agent_role}\n", style="cyan")
+        content.append("Step: ", style="white")
+        content.append(f"{step_number}\n", style="cyan")
+        if step_description:
+            desc_preview = step_description[:80] + (
+                "..." if len(step_description) > 80 else ""
+            )
+            content.append("Description: ", style="white")
+            content.append(f"{desc_preview}\n", style="cyan")
+
+        self.print_panel(content, "🔍 Observing Step Result", "cyan")
+
+    def handle_observation_completed(
+        self,
+        agent_role: str,
+        step_number: int,
+        step_completed: bool,
+        plan_valid: bool,
+        key_info: str,
+        needs_replan: bool,
+        goal_achieved: bool,
+    ) -> None:
+        """Handle step observation completed event."""
+        if not self.verbose:
+            return
+
+        if goal_achieved:
+            style = "green"
+            status = "Goal Achieved Early"
+        elif needs_replan:
+            style = "yellow"
+            status = "Replan Needed"
+        elif plan_valid:
+            style = "green"
+            status = "Plan Valid — Continue"
+        else:
+            style = "red"
+            status = "Step Failed"
+
+        content = Text()
+        content.append("Observation Complete\n", style=f"{style} bold")
+        content.append("Step: ", style="white")
+        content.append(f"{step_number}\n", style=style)
+        content.append("Status: ", style="white")
+        content.append(f"{status}\n", style=style)
+        if key_info:
+            info_preview = key_info[:120] + ("..." if len(key_info) > 120 else "")
+            content.append("Learned: ", style="white")
+            content.append(f"{info_preview}\n", style=style)
+
+        self.print_panel(content, "🔍 Observation Result", style)
+
+    def handle_observation_failed(
+        self,
+        step_number: int,
+        error: str,
+    ) -> None:
+        """Handle step observation failure event."""
+        if not self.verbose:
+            return
+
+        error_content = self.create_status_content(
+            "Observation Failed",
+            "Error",
+            "red",
+            Step=str(step_number),
+            Error=error,
+        )
+        self.print_panel(error_content, "❌ Observation Error", "red")
+
+    def handle_plan_refinement(
+        self,
+        step_number: int,
+        refined_count: int,
+        refinements: list[str] | None,
+    ) -> None:
+        """Handle plan refinement event."""
+        if not self.verbose:
+            return
+
+        content = Text()
+        content.append("Plan Refined\n", style="cyan bold")
+        content.append("After Step: ", style="white")
+        content.append(f"{step_number}\n", style="cyan")
+        content.append("Steps Updated: ", style="white")
+        content.append(f"{refined_count}\n", style="cyan")
+        if refinements:
+            for r in refinements[:3]:
+                content.append(f"  • {r[:80]}\n", style="white")
+
+        self.print_panel(content, "✏️ Plan Refinement", "cyan")
+
+    def handle_plan_replan(
+        self,
+        reason: str,
+        replan_count: int,
+        preserved_count: int,
+    ) -> None:
+        """Handle plan replan triggered event."""
+        if not self.verbose:
+            return
+
+        content = Text()
+        content.append("Full Replan Triggered\n", style="yellow bold")
+        content.append("Reason: ", style="white")
+        content.append(f"{reason}\n", style="yellow")
+        content.append("Replan #: ", style="white")
+        content.append(f"{replan_count}\n", style="yellow")
+        content.append("Preserved Steps: ", style="white")
+        content.append(f"{preserved_count}\n", style="yellow")
+
+        self.print_panel(content, "🔄 Dynamic Replan", "yellow")
+
+    def handle_goal_achieved_early(
+        self,
+        steps_completed: int,
+        steps_remaining: int,
+    ) -> None:
+        """Handle goal achieved early event."""
+        if not self.verbose:
+            return
+
+        content = Text()
+        content.append("Goal Achieved Early!\n", style="green bold")
+        content.append("Completed: ", style="white")
+        content.append(f"{steps_completed} steps\n", style="green")
+        content.append("Skipped: ", style="white")
+        content.append(f"{steps_remaining} remaining steps\n", style="green")
+
+        self.print_panel(content, "🎯 Early Goal Achievement", "green")
+
     # ----------- AGENT LOGGING EVENTS -----------
 
     def handle_agent_logs_started(

lib/crewai/src/crewai/flow/async_feedback/providers.py

@@ -34,6 +34,7 @@ class ConsoleProvider:
         ```python
         from crewai.flow.async_feedback import ConsoleProvider
 
+
         @human_feedback(
             message="Review this:",
             provider=ConsoleProvider(),
@@ -46,6 +47,7 @@ class ConsoleProvider:
         ```python
         from crewai.flow import Flow, start
 
+
         class MyFlow(Flow):
             @start()
             def gather_info(self):

lib/crewai/src/crewai/flow/flow.py

@@ -16,7 +16,8 @@ from collections.abc import (
     Sequence,
     ValuesView,
 )
-from concurrent.futures import Future
+from concurrent.futures import Future, ThreadPoolExecutor
+import contextvars
 import copy
 import enum
 import inspect
@@ -497,6 +498,52 @@ class LockedListProxy(list, Generic[T]):  # type: ignore[type-arg]
     def __bool__(self) -> bool:
         return bool(self._list)
 
+    def index(
+        self, value: T, start: SupportsIndex = 0, stop: SupportsIndex | None = None
+    ) -> int:  # type: ignore[override]
+        if stop is None:
+            return self._list.index(value, start)
+        return self._list.index(value, start, stop)
+
+    def count(self, value: T) -> int:
+        return self._list.count(value)
+
+    def sort(self, *, key: Any = None, reverse: bool = False) -> None:
+        with self._lock:
+            self._list.sort(key=key, reverse=reverse)
+
+    def reverse(self) -> None:
+        with self._lock:
+            self._list.reverse()
+
+    def copy(self) -> list[T]:
+        return self._list.copy()
+
+    def __add__(self, other: list[T]) -> list[T]:
+        return self._list + other
+
+    def __radd__(self, other: list[T]) -> list[T]:
+        return other + self._list
+
+    def __iadd__(self, other: Iterable[T]) -> LockedListProxy[T]:
+        with self._lock:
+            self._list += list(other)
+        return self
+
+    def __mul__(self, n: SupportsIndex) -> list[T]:
+        return self._list * n
+
+    def __rmul__(self, n: SupportsIndex) -> list[T]:
+        return self._list * n
+
+    def __imul__(self, n: SupportsIndex) -> LockedListProxy[T]:
+        with self._lock:
+            self._list *= n
+        return self
+
+    def __reversed__(self) -> Iterator[T]:
+        return reversed(self._list)
+
     def __eq__(self, other: object) -> bool:
         """Compare based on the underlying list contents."""
         if isinstance(other, LockedListProxy):
@@ -579,6 +626,23 @@ class LockedDictProxy(dict, Generic[T]):  # type: ignore[type-arg]
     def __bool__(self) -> bool:
         return bool(self._dict)
 
+    def copy(self) -> dict[str, T]:
+        return self._dict.copy()
+
+    def __or__(self, other: dict[str, T]) -> dict[str, T]:
+        return self._dict | other
+
+    def __ror__(self, other: dict[str, T]) -> dict[str, T]:
+        return other | self._dict
+
+    def __ior__(self, other: dict[str, T]) -> LockedDictProxy[T]:
+        with self._lock:
+            self._dict |= other
+        return self
+
+    def __reversed__(self) -> Iterator[str]:
+        return reversed(self._dict)
+
     def __eq__(self, other: object) -> bool:
         """Compare based on the underlying dict contents."""
         if isinstance(other, LockedDictProxy):
@@ -620,6 +684,10 @@ class StateProxy(Generic[T]):
         if name in ("_proxy_state", "_proxy_lock"):
             object.__setattr__(self, name, value)
         else:
+            if isinstance(value, LockedListProxy):
+                value = value._list
+            elif isinstance(value, LockedDictProxy):
+                value = value._dict
             with object.__getattribute__(self, "_proxy_lock"):
                 setattr(object.__getattribute__(self, "_proxy_state"), name, value)
 
@@ -692,6 +760,7 @@ class FlowMeta(type):
                     condition_type = getattr(
                         attr_value, "__condition_type__", OR_CONDITION
                     )
+
                     if (
                         hasattr(attr_value, "__trigger_condition__")
                         and attr_value.__trigger_condition__ is not None
@@ -769,6 +838,7 @@ class Flow(Generic[T], metaclass=FlowMeta):
         persistence: FlowPersistence | None = None,
         tracing: bool | None = None,
         suppress_flow_events: bool = False,
+        max_method_calls: int = 100,
         **kwargs: Any,
     ) -> None:
         """Initialize a new Flow instance.
@@ -777,6 +847,7 @@ class Flow(Generic[T], metaclass=FlowMeta):
             persistence: Optional persistence backend for storing flow states
             tracing: Whether to enable tracing. True=always enable, False=always disable, None=check environment/user settings
             suppress_flow_events: Whether to suppress flow event emissions (internal use)
+            max_method_calls: Maximum times a single method can be called per execution before raising RecursionError
             **kwargs: Additional state values to initialize or override
         """
         # Initialize basic instance attributes
@@ -792,6 +863,8 @@ class Flow(Generic[T], metaclass=FlowMeta):
         self._completed_methods: set[FlowMethodName] = (
             set()
         )  # Track completed methods for reload
+        self._method_call_counts: dict[FlowMethodName, int] = {}
+        self._max_method_calls = max_method_calls
         self._persistence: FlowPersistence | None = persistence
         self._is_execution_resuming: bool = False
         self._event_futures: list[Future[None]] = []
@@ -1739,7 +1812,13 @@ class Flow(Generic[T], metaclass=FlowMeta):
         async def _run_flow() -> Any:
             return await self.kickoff_async(inputs, input_files)
 
-        return asyncio.run(_run_flow())
+        try:
+            asyncio.get_running_loop()
+            ctx = contextvars.copy_context()
+            with ThreadPoolExecutor(max_workers=1) as pool:
+                return pool.submit(ctx.run, asyncio.run, _run_flow()).result()
+        except RuntimeError:
+            return asyncio.run(_run_flow())
 
     async def kickoff_async(
         self,
@@ -1823,6 +1902,7 @@ class Flow(Generic[T], metaclass=FlowMeta):
                 self._method_outputs.clear()
                 self._pending_and_listeners.clear()
                 self._clear_or_listeners()
+                self._method_call_counts.clear()
             else:
                 # Only enter resumption mode if there are completed methods to
                 # replay.  When _completed_methods is empty (e.g. a pure
@@ -2160,8 +2240,6 @@ class Flow(Generic[T], metaclass=FlowMeta):
                 else:
                     # Run sync methods in thread pool for isolation
                     # This allows Agent.kickoff() to work synchronously inside Flow methods
-                    import contextvars
-
                     ctx = contextvars.copy_context()
                     result = await asyncio.to_thread(ctx.run, method, *args, **kwargs)
             finally:
@@ -2564,6 +2642,16 @@ class Flow(Generic[T], metaclass=FlowMeta):
             - Skips execution if method was already completed (e.g., after reload)
             - Catches and logs any exceptions during execution, preventing individual listener failures from breaking the entire flow
         """
+        count = self._method_call_counts.get(listener_name, 0) + 1
+        if count > self._max_method_calls:
+            raise RecursionError(
+                f"Method '{listener_name}' has been called {self._max_method_calls} times in "
+                f"this flow execution, which indicates an infinite loop. "
+                f"This commonly happens when a @listen label matches the "
+                f"method's own name."
+            )
+        self._method_call_counts[listener_name] = count
+
         if listener_name in self._completed_methods:
             if self._is_execution_resuming:
                 # During resumption, skip execution but continue listeners
@@ -2628,7 +2716,9 @@ class Flow(Generic[T], metaclass=FlowMeta):
             from crewai.flow.async_feedback.types import HumanFeedbackPending
 
             if not isinstance(e, HumanFeedbackPending):
-                logger.error(f"Error executing listener {listener_name}: {e}")
+                if not getattr(e, "_flow_listener_logged", False):
+                    logger.error(f"Error executing listener {listener_name}: {e}")
+                    e._flow_listener_logged = True  # type: ignore[attr-defined]
             raise
 
     # ── User Input (self.ask) ────────────────────────────────────────
@@ -2770,8 +2860,9 @@ class Flow(Generic[T], metaclass=FlowMeta):
                 # Manual executor management to avoid shutdown(wait=True)
                 # deadlock when the provider call outlives the timeout.
                 executor = ThreadPoolExecutor(max_workers=1)
+                ctx = contextvars.copy_context()
                 future = executor.submit(
-                    provider.request_input, message, self, metadata
+                    ctx.run, provider.request_input, message, self, metadata
                 )
                 try:
                     raw = future.result(timeout=timeout)

lib/crewai/src/crewai/flow/human_feedback.py

@@ -188,7 +188,7 @@ def human_feedback(
     metadata: dict[str, Any] | None = None,
     provider: HumanFeedbackProvider | None = None,
     learn: bool = False,
-    learn_source: str = "hitl"
+    learn_source: str = "hitl",
 ) -> Callable[[F], F]:
     """Decorator for Flow methods that require human feedback.
 
@@ -328,9 +328,7 @@ def human_feedback(
             """Recall past HITL lessons and use LLM to pre-review the output."""
             try:
                 query = f"human feedback lessons for {func.__name__}: {method_output!s}"
-                matches = flow_instance.memory.recall(
-                    query, source=learn_source
-                )
+                matches = flow_instance.memory.recall(query, source=learn_source)
                 if not matches:
                     return method_output
 
@@ -341,7 +339,10 @@ def human_feedback(
                     lessons=lessons,
                 )
                 messages = [
-                    {"role": "system", "content": _get_hitl_prompt("hitl_pre_review_system")},
+                    {
+                        "role": "system",
+                        "content": _get_hitl_prompt("hitl_pre_review_system"),
+                    },
                     {"role": "user", "content": prompt},
                 ]
                 if getattr(llm_inst, "supports_function_calling", lambda: False)():
@@ -366,7 +367,10 @@ def human_feedback(
                     feedback=raw_feedback,
                 )
                 messages = [
-                    {"role": "system", "content": _get_hitl_prompt("hitl_distill_system")},
+                    {
+                        "role": "system",
+                        "content": _get_hitl_prompt("hitl_distill_system"),
+                    },
                     {"role": "user", "content": prompt},
                 ]
 
@@ -408,7 +412,7 @@ def human_feedback(
                 emit=list(emit) if emit else None,
                 default_outcome=default_outcome,
                 metadata=metadata or {},
-                llm=llm if isinstance(llm, str) else None,
+                llm=llm if isinstance(llm, str) else getattr(llm, "model", None),
             )
 
             # Determine effective provider:
@@ -487,7 +491,11 @@ def human_feedback(
                 result = _process_feedback(self, method_output, raw_feedback)
 
                 # Distill: extract lessons from output + feedback, store in memory
-                if learn and getattr(self, "memory", None) is not None and raw_feedback.strip():
+                if (
+                    learn
+                    and getattr(self, "memory", None) is not None
+                    and raw_feedback.strip()
+                ):
                     _distill_and_store_lessons(self, method_output, raw_feedback)
 
                 return result
@@ -507,7 +515,11 @@ def human_feedback(
                 result = _process_feedback(self, method_output, raw_feedback)
 
                 # Distill: extract lessons from output + feedback, store in memory
-                if learn and getattr(self, "memory", None) is not None and raw_feedback.strip():
+                if (
+                    learn
+                    and getattr(self, "memory", None) is not None
+                    and raw_feedback.strip()
+                ):
                     _distill_and_store_lessons(self, method_output, raw_feedback)
 
                 return result
@@ -534,7 +546,7 @@ def human_feedback(
             metadata=metadata,
             provider=provider,
             learn=learn,
-            learn_source=learn_source
+            learn_source=learn_source,
         )
         wrapper.__is_flow_method__ = True
 

lib/crewai/src/crewai/flow/persistence/sqlite.py

@@ -1,11 +1,10 @@
-"""
-SQLite-based implementation of flow state persistence.
-"""
+"""SQLite-based implementation of flow state persistence."""
 
 from __future__ import annotations
 
 from datetime import datetime, timezone
 import json
+import os
 from pathlib import Path
 import sqlite3
 from typing import TYPE_CHECKING, Any
@@ -13,6 +12,7 @@ from typing import TYPE_CHECKING, Any
 from pydantic import BaseModel
 
 from crewai.flow.persistence.base import FlowPersistence
+from crewai.utilities.lock_store import lock as store_lock
 from crewai.utilities.paths import db_storage_path
 
 
@@ -68,11 +68,16 @@ class SQLiteFlowPersistence(FlowPersistence):
             raise ValueError("Database path must be provided")
 
         self.db_path = path  # Now mypy knows this is str
+        self._lock_name = f"sqlite:{os.path.realpath(self.db_path)}"
         self.init_db()
 
     def init_db(self) -> None:
         """Create the necessary tables if they don't exist."""
-        with sqlite3.connect(self.db_path) as conn:
+        with (
+            store_lock(self._lock_name),
+            sqlite3.connect(self.db_path, timeout=30) as conn,
+        ):
+            conn.execute("PRAGMA journal_mode=WAL")
             # Main state table
             conn.execute(
                 """
@@ -113,6 +118,49 @@ class SQLiteFlowPersistence(FlowPersistence):
             """
             )
 
+    def _save_state_sql(
+        self,
+        conn: sqlite3.Connection,
+        flow_uuid: str,
+        method_name: str,
+        state_dict: dict[str, Any],
+    ) -> None:
+        """Execute the save-state INSERT without acquiring the lock.
+
+        Args:
+            conn: An open SQLite connection.
+            flow_uuid: Unique identifier for the flow instance.
+            method_name: Name of the method that just completed.
+            state_dict: State data as a plain dict.
+        """
+        conn.execute(
+            """
+            INSERT INTO flow_states (
+                flow_uuid,
+                method_name,
+                timestamp,
+                state_json
+            ) VALUES (?, ?, ?, ?)
+            """,
+            (
+                flow_uuid,
+                method_name,
+                datetime.now(timezone.utc).isoformat(),
+                json.dumps(state_dict),
+            ),
+        )
+
+    @staticmethod
+    def _to_state_dict(state_data: dict[str, Any] | BaseModel) -> dict[str, Any]:
+        """Convert state_data to a plain dict."""
+        if isinstance(state_data, BaseModel):
+            return state_data.model_dump()
+        if isinstance(state_data, dict):
+            return state_data
+        raise ValueError(
+            f"state_data must be either a Pydantic BaseModel or dict, got {type(state_data)}"
+        )
+
     def save_state(
         self,
         flow_uuid: str,
@@ -126,33 +174,13 @@ class SQLiteFlowPersistence(FlowPersistence):
             method_name: Name of the method that just completed
             state_data: Current state data (either dict or Pydantic model)
         """
-        # Convert state_data to dict, handling both Pydantic and dict cases
-        if isinstance(state_data, BaseModel):
-            state_dict = state_data.model_dump()
-        elif isinstance(state_data, dict):
-            state_dict = state_data
-        else:
-            raise ValueError(
-                f"state_data must be either a Pydantic BaseModel or dict, got {type(state_data)}"
-            )
+        state_dict = self._to_state_dict(state_data)
 
-        with sqlite3.connect(self.db_path) as conn:
-            conn.execute(
-                """
-            INSERT INTO flow_states (
-                flow_uuid,
-                method_name,
-                timestamp,
-                state_json
-            ) VALUES (?, ?, ?, ?)
-            """,
-                (
-                    flow_uuid,
-                    method_name,
-                    datetime.now(timezone.utc).isoformat(),
-                    json.dumps(state_dict),
-                ),
-            )
+        with (
+            store_lock(self._lock_name),
+            sqlite3.connect(self.db_path, timeout=30) as conn,
+        ):
+            self._save_state_sql(conn, flow_uuid, method_name, state_dict)
 
     def load_state(self, flow_uuid: str) -> dict[str, Any] | None:
         """Load the most recent state for a given flow UUID.
@@ -163,7 +191,7 @@ class SQLiteFlowPersistence(FlowPersistence):
         Returns:
             The most recent state as a dictionary, or None if no state exists
         """
-        with sqlite3.connect(self.db_path) as conn:
+        with sqlite3.connect(self.db_path, timeout=30) as conn:
             cursor = conn.execute(
                 """
             SELECT state_json
@@ -197,24 +225,14 @@ class SQLiteFlowPersistence(FlowPersistence):
             context: The pending feedback context with all resume information
             state_data: Current state data
         """
-        # Import here to avoid circular imports
+        state_dict = self._to_state_dict(state_data)
 
-        # Convert state_data to dict
-        if isinstance(state_data, BaseModel):
-            state_dict = state_data.model_dump()
-        elif isinstance(state_data, dict):
-            state_dict = state_data
-        else:
-            raise ValueError(
-                f"state_data must be either a Pydantic BaseModel or dict, got {type(state_data)}"
-            )
+        with (
+            store_lock(self._lock_name),
+            sqlite3.connect(self.db_path, timeout=30) as conn,
+        ):
+            self._save_state_sql(conn, flow_uuid, context.method_name, state_dict)
 
-        # Also save to regular state table for consistency
-        self.save_state(flow_uuid, context.method_name, state_data)
-
-        # Save pending feedback context
-        with sqlite3.connect(self.db_path) as conn:
-            # Use INSERT OR REPLACE to handle re-triggering feedback on same flow
             conn.execute(
                 """
             INSERT OR REPLACE INTO pending_feedback (
@@ -248,7 +266,7 @@ class SQLiteFlowPersistence(FlowPersistence):
         # Import here to avoid circular imports
         from crewai.flow.async_feedback.types import PendingFeedbackContext
 
-        with sqlite3.connect(self.db_path) as conn:
+        with sqlite3.connect(self.db_path, timeout=30) as conn:
             cursor = conn.execute(
                 """
             SELECT state_json, context_json
@@ -272,7 +290,10 @@ class SQLiteFlowPersistence(FlowPersistence):
         Args:
             flow_uuid: Unique identifier for the flow instance
         """
-        with sqlite3.connect(self.db_path) as conn:
+        with (
+            store_lock(self._lock_name),
+            sqlite3.connect(self.db_path, timeout=30) as conn,
+        ):
             conn.execute(
                 """
             DELETE FROM pending_feedback

lib/crewai/src/crewai/lite_agent.py

@@ -600,7 +600,7 @@ class LiteAgent(FlowTrackable, BaseModel):
 
     def _save_to_memory(self, output_text: str) -> None:
         """Extract discrete memories from the run and remember each. No-op if _memory is None or read-only."""
-        if self._memory is None or getattr(self._memory, "_read_only", False):
+        if self._memory is None or self._memory.read_only:
             return
         input_str = self._get_last_user_content() or "User request"
         try: