docs: update changelog and version for v1.10.2rc2

* fix: remove exclusive locks from read-only storage operations to eliminate lock contention

read operations like search, list_scopes, get_scope_info, count across
LanceDB, ChromaDB, and RAG adapters were holding exclusive locks unnecessarily.
under multi-process prefork workers this caused RedisLock contention triggering
a portalocker bug where AlreadyLocked is raised with the exceptions module as its arg.

- remove store_lock from 7 LanceDB read methods since MVCC handles concurrent reads
- remove store_lock from ChromaDB search/asearch which are thread-safe since v0.4
- remove store_lock from RAG core query and LanceDB adapter query
- wrap lock_store BaseLockException with actionable error message
- add exception handling in encoding_flow/recall_flow ThreadPoolExecutor calls
- fix flow.py double-logging of ancestor listener errors

* fix: remove dead conditional in filter_and_chunk fallback

both branches of the if/else and the except all produced the same
candidates = [scope_prefix] result, making the get_scope_info call
and conditional pointless

* fix: separate lock acquisition from caller body in lock_store

the try/except wrapped the yield inside the contextmanager, which meant
any BaseLockException raised by the caller's code inside the with block
would be caught and re-raised with a misleading "Failed to acquire lock"
message. split into acquire-then-yield so only actual acquisition
failures get the actionable error message.

.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 +4,114 @@ description: "Product updates, improvements, and bug fixes for CrewAI"
 icon: "clock"
 mode: "wide"
 ---
+<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
 

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/tools/search-research/bravesearchtool.mdx

@@ -1,97 +1,316 @@
 ---
-title: Brave Search
+title: Brave Search Tools
-description: The `BraveSearchTool` is designed to search the internet using the Brave Search API.
+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.
+## Quick Examples
-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.
 
-## Example
+### Web Search
-
-The following example demonstrates how to initialize the tool and execute a search with a given query:
 
 ```python Code
-from crewai_tools import BraveSearchTool
+from crewai_tools import BraveWebSearchTool
 
-# Initialize the tool for internet searching capabilities
+tool = BraveWebSearchTool()
-tool = BraveSearchTool()
+results = tool.run(q="CrewAI agent framework")
-
-# Execute a search
-results = tool.run(search_query="CrewAI agent framework")
 print(results)
 ```
 
-## Parameters
+### News Search
-
-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:
 
 ```python Code
-from crewai_tools import BraveSearchTool
+from crewai_tools import BraveNewsSearchTool
 
-# Initialize the tool with custom parameters
+tool = BraveNewsSearchTool()
-tool = BraveSearchTool(
+results = tool.run(q="latest AI breakthroughs")
-    country="US",
+print(results)
-    n_results=5,
+```
-    save_file=True
+
+### 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
+web_search = BraveWebSearchTool(raw=True)
-results = tool.run(search_query="Latest AI developments")
+poi_details = BraveLocalPOIsDescriptionTool()
-print(results)
+
+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
+web_search = BraveWebSearchTool()
-brave_search_tool = BraveSearchTool()
+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=[web_search, news_search],
-        tools=[brave_search_tool]
     )
 ```
 
+## 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 +4,114 @@ description: "CrewAI의 제품 업데이트, 개선 사항 및 버그 수정"
 icon: "clock"
 mode: "wide"
 ---
+<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
 

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/pt-BR/changelog.mdx

@@ -4,6 +4,114 @@ description: "Atualizações de produto, melhorias e correções do CrewAI"
 icon: "clock"
 mode: "wide"
 ---
+<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
 

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.

lib/crewai-files/pyproject.toml

@@ -9,7 +9,7 @@ authors = [
 requires-python = ">=3.10, <3.14"
 dependencies = [
     "Pillow~=12.1.1",
-    "pypdf~=6.7.4",
+    "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__ = "1.10.1a1"
+__version__ = "1.10.2rc2"

lib/crewai-tools/pyproject.toml

@@ -11,7 +11,7 @@ dependencies = [
     "pytube~=15.0.0",
     "requests~=2.32.5",
     "docker~=7.1.0",
-    "crewai==1.10.1a1",
+    "crewai==1.10.2rc2",
     "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__ = "1.10.1a1"
+__version__ = "1.10.2rc2"

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:
+        loop = asyncio.get_event_loop()
-            return self._async_sessions[thread_id][1]
+        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:
+        while True:
-            return self._sync_sessions[thread_id][1]
+            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
+            return browser_client, browser
-            self._async_sessions[thread_id] = (browser_client, browser)
-
-            return 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
+            with self._lock:
-            self._sync_sessions[thread_id] = (browser_client, browser)
+                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:
+        with self._lock:
-            logger.warning(f"No async browser session found for thread {thread_id}")
+            if thread_id not in self._async_sessions:
-            return
+                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:
+        with self._lock:
-            logger.warning(f"No sync browser session found for thread {thread_id}")
+            if thread_id not in self._sync_sessions:
-            return
+                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
+        with self._lock:
-        async_thread_ids = list(self._async_sessions.keys())
+            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._lock_name = (
-                self._client = chromadb.PersistentClient(path=self.persist_directory)
+                f"chromadb:{os.path.realpath(self.persist_directory)}"
-            else:
+                if self.persist_directory
-                self._client = chromadb.Client()
+                else "chromadb:ephemeral"
-
-            self._collection = self._client.get_or_create_collection(
-                name=self.collection_name,
-                metadata={
-                    "hnsw:space": "cosine",
-                    "description": "CrewAI Knowledge Base",
-                },
             )
 
+            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:
+        with store_lock(self._lock_name):
-            self._collection.add(
+            existing_doc = self._collection.get(
-                ids=ids,
+                where={"source": source_content.source_ref}, limit=1
-                embeddings=embeddings,
-                documents=contents,
-                metadatas=metadatas,
             )
-            logger.info(f"Added {len(documents)} documents to knowledge base")
+            existing_doc_id = (
-        except Exception as e:
+                existing_doc and existing_doc["metadatas"][0]["doc_id"]
-            logger.error(f"Failed to add documents to ChromaDB: {e}")
+                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
+            # Fallback to "query" or "search_query" for backwards compatibility
-            query = kwargs.get("search_query") or kwargs.get("query")
+            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"):
+            # Fallback to "search_language" for backwards compatibility
-                payload["search_language"] = search_language
+            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/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"):
-            if kwargs.get("directory") and not os.path.exists(kwargs["directory"]):
+                os.makedirs(kwargs["directory"], exist_ok=True)
-                os.makedirs(kwargs["directory"])
 
             # 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):
+        if output_dir:
-            os.makedirs(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")
+                lambda: (
-                .Client(api_key=os.getenv("OPENAI_API_KEY"))
+                    __import__("openai")
-                .embeddings.create(input=[query], model="text-embedding-3-large")
+                    .Client(api_key=os.getenv("OPENAI_API_KEY"))
-                .data[0]
+                    .embeddings.create(input=[query], model="text-embedding-3-large")
-                .embedding
+                    .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:
+        with self._pool_lock:
-            if not self._connection_pool:
+            if self._connection_pool:
-                conn = await asyncio.get_event_loop().run_in_executor(
+                return self._connection_pool.pop()
-                    self._thread_pool, self._create_connection
+        return await asyncio.get_event_loop().run_in_executor(
-                )
+            self._thread_pool, self._create_connection
-                self._connection_pool.append(conn)
+        )
-            return self._connection_pool.pop()
 
     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:
+            with _cache_lock:
-                logger.info("Returning cached result")
+                if cache_key in _query_cache:
-                return _query_cache[cache_key]
+                    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
+import os
-from unittest.mock import patch
+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():
+def web_tool():
-    return BraveSearchTool(n_results=2)
+    return BraveWebSearchTool()
 
 
-def test_brave_tool_initialization():
+@pytest.fixture
-    tool = BraveSearchTool()
+def image_tool():
-    assert tool.n_results == 10
+    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_custom_constructor_args():
-def test_brave_tool_search(mock_get, brave_tool):
+    tool = BraveWebSearchTool(
-    mock_response = {
+        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",
+                    "title": "CrewAI",
-                    "url": "http://test.com",
+                    "url": "https://crewai.com",
-                    "description": "Test Description",
+                    "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")
+    assert web_tool.raw is False
-    data = json.loads(result)
+    result = web_tool._run(query="crewai")
-    assert isinstance(data, list)
+
-    assert len(data) >= 1
+    # The web tool's _refine_response extracts and reshapes results.
-    assert data[0]["title"] == "Test Title"
+    # The key assertion: we should NOT get back the raw API envelope.
-    assert data[0]["url"] == "http://test.com"
+    assert result != api_response
 
 
-@patch("requests.get")
+# Backward Compatibility & Legacy Parameter Support
-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"
 
 
-if __name__ == "__main__":
+@patch("crewai_tools.tools.brave_search_tool.base.requests.get")
-    test_brave_tool()
+def test_positional_query_argument(mock_get, web_tool):
-    test_brave_tool_initialization()
+    """tool.run('my query') works as a positional argument."""
-    # test_brave_tool_search(brave_tool)
+    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/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==1.10.1a1",
+    "crewai-tools==1.10.2rc2",
 ]
 embeddings = [
     "tiktoken~=0.8.0"
@@ -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

@@ -1,3 +1,4 @@
+import contextvars
 import threading
 from typing import Any
 import urllib.request
@@ -40,7 +41,7 @@ def _suppress_pydantic_deprecation_warnings() -> None:
 
 _suppress_pydantic_deprecation_warnings()
 
-__version__ = "1.10.1a1"
+__version__ = "1.10.2rc2"
 _telemetry_submitted = False
 
 
@@ -66,7 +67,8 @@ 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()
 
 

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()
+    coro = afetch_agent_card(endpoint=endpoint, auth=auth, timeout=timeout)
-    asyncio.set_event_loop(loop)
     try:
-        return loop.run_until_complete(
+        asyncio.get_running_loop()
-            afetch_agent_card(endpoint=endpoint, auth=auth, timeout=timeout)
+        has_running_loop = True
-        )
+    except RuntimeError:
-    finally:
+        has_running_loop = False
-        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 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()
+    coro = _afetch_agent_card_impl(endpoint=endpoint, auth=auth, timeout=timeout)
-    asyncio.set_event_loop(loop)
     try:
-        return loop.run_until_complete(
+        asyncio.get_running_loop()
-            _afetch_agent_card_impl(endpoint=endpoint, auth=auth, timeout=timeout)
+        has_running_loop = True
-        )
+    except RuntimeError:
-    finally:
+        has_running_loop = False
-        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)
 
 
 @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(
+        has_running_loop = True
-            "execute_a2a_delegation() cannot be called from an async context. "
+    except RuntimeError:
-            "Use 'await aexecute_a2a_delegation()' instead."
+        has_running_loop = False
-        )
-    except RuntimeError as e:
-        if "no running event loop" not in str(e).lower():
-            raise
 
-    loop = asyncio.new_event_loop()
+    if has_running_loop:
-    asyncio.set_event_loop(loop)
+        ctx = contextvars.copy_context()
-    try:
+        with concurrent.futures.ThreadPoolExecutor(max_workers=1) as pool:
-        return loop.run_until_complete(
+            return pool.submit(ctx.run, asyncio.run, coro).result()
-            aexecute_a2a_delegation(
+    return asyncio.run(coro)
-                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()
 
 
 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
@@ -513,9 +514,13 @@ 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:
@@ -1156,11 +1161,15 @@ 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 +1273,7 @@ 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(

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 (
+        if f"Action: {sanitize_tool_name('Delegate work to coworker')}" in output.text:
-            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(
+            self.agent._logger.log("error", f"Failed to save to memory: {e}")
-                "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
@@ -755,6 +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,
@@ -893,7 +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
 

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(
+        reset_memories_command(memory, knowledge, agent_knowledge, kickoff_outputs, all)
-            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 (
+    from crewai.events.listeners.tracing.utils import update_user_data
-        _load_user_data,
-        _save_user_data,
-    )
 
     console = Console()
 
-    # Update user data to enable traces
+    update_user_data({"trace_consent": True, "first_execution_done": True})
-    user_data = _load_user_data()
-    user_data["trace_consent"] = True
-    user_data["first_execution_done"] = True
-    _save_user_data(user_data)
 
     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 (
+    from crewai.events.listeners.tracing.utils import update_user_data
-        _load_user_data,
-        _save_user_data,
-    )
 
     console = Console()
 
-    # Update user data to disable traces
+    update_user_data({"trace_consent": False, "first_execution_done": True})
-    user_data = _load_user_data()
-    user_data["trace_consent"] = False
-    user_data["first_execution_done"] = True
-    _save_user_data(user_data)
 
     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 = (
+            label = f"{date_str}  [bold]{record.importance:.1f}[/]  {preview}"
-                f"{date_str}  "
-                f"[bold]{record.importance:.1f}[/]  "
-                f"{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"[bold]\\[{m.score:.2f}][/]  {preview}  [dim]scope={m.record.scope}[/]"
-                f"{preview}  "
-                f"[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"[dim]Created:[/]        {record.created_at.strftime('%Y-%m-%d %H:%M:%S')}"
-            f"{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 = (
+            scope = self._selected_scope if self._selected_scope != "/" else None
-                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(
+                lambda: self._memory.recall(query, scope=scope, limit=10, depth="deep"),
-                    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:
+    def login_to_tool_repository(
-        return self._make_request("POST", f"{self.TOOLS_RESOURCE}/login")
+        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(
+                click.echo(f"[Flow ({flow_name})] Memory has been reset.")
-                    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]==1.10.1a1"
+    "crewai[tools]==1.10.2rc2"
 ]
 
 [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]==1.10.1a1"
+    "crewai[tools]==1.10.2rc2"
 ]
 
 [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]==1.10.1a1"
+    "crewai[tools]==1.10.2rc2"
 ]
 
 [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
+                    d for d in dirs if d not in _SKIP_DIRS and not d.startswith(".")
-                    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(
+                                    if flow_instance := get_flow_instance(module_attr):
-                                        module_attr
-                                    ):
                                         flow_instances.append(flow_instance)
                                 except Exception:  # noqa: S112
                                     continue

lib/crewai/src/crewai/crew.py

@@ -438,18 +438,6 @@ class Crew(FlowTrackable, BaseModel):
                     agent.set_rpm_controller(self._rpm_controller)
         return self
 
-    @model_validator(mode="after")
-    def stamp_execution_order(self) -> Self:
-        """Lock task execution order by stamping each task with its insertion index.
-
-        This guarantees deterministic, stable ordering for all tasks regardless
-        of any other attribute.  Tasks are always dispatched in the order they
-        appear in ``self.tasks`` (i.e. insertion order).
-        """
-        for idx, task in enumerate(self.tasks):
-            task._execution_index = idx
-        return self
-
     @model_validator(mode="after")
     def validate_tasks(self) -> Self:
         if self.process == Process.sequential:
@@ -996,18 +984,13 @@ class Crew(FlowTrackable, BaseModel):
     ) -> CrewOutput:
         """Executes tasks using native async and returns the final output.
 
-        **Ordering contract**: tasks are dispatched in the exact order they
-        appear in *tasks* (i.e. their insertion / list order).  Each task
-        carries an ``_execution_index`` stamped at crew-construction time
-        that locks this order deterministically.
-
         Args:
-            tasks: List of tasks to execute (preserves insertion order).
+            tasks: List of tasks to execute
-            start_index: Index to start execution from (for replay).
+            start_index: Index to start execution from (for replay)
-            was_replayed: Whether this is a replayed execution.
+            was_replayed: Whether this is a replayed execution
 
         Returns:
-            CrewOutput: Final output of the crew.
+            CrewOutput: Final output of the crew
         """
         task_outputs: list[TaskOutput] = []
         pending_tasks: list[tuple[Task, asyncio.Task[TaskOutput], int]] = []
@@ -1200,18 +1183,13 @@ class Crew(FlowTrackable, BaseModel):
     ) -> CrewOutput:
         """Executes tasks sequentially and returns the final output.
 
-        **Ordering contract**: tasks are dispatched in the exact order they
-        appear in *tasks* (i.e. their insertion / list order).  Each task
-        carries an ``_execution_index`` stamped at crew-construction time
-        that locks this order deterministically.
-
         Args:
-            tasks: List of tasks to execute (preserves insertion order).
+            tasks (List[Task]): List of tasks to execute
-            start_index: Index to resume execution from (for replay).
+            manager (Optional[BaseAgent], optional): Manager agent to use for
-            was_replayed: Whether this is a replayed execution.
+                delegation. Defaults to None.
 
         Returns:
-            CrewOutput: Final output of the crew.
+            CrewOutput: Final output of the crew
         """
         custom_start = self._get_execution_start_index(tasks)
         if custom_start is not None:
@@ -1432,9 +1410,7 @@ class Crew(FlowTrackable, BaseModel):
             return self._merge_tools(tools, cast(list[BaseTool], code_tools))
         return tools
 
-    def _add_memory_tools(
+    def _add_memory_tools(self, tools: list[BaseTool], memory: Any) -> list[BaseTool]:
-        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/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/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()
+        with store_lock(_user_data_lock_name()):
-        p.write_text(json.dumps(data, indent=2))
+            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:
+def _generate_user_id() -> str:
-    """Stable, anonymized user identifier with caching."""
+    """Compute an anonymized user identifier from username and machine ID."""
-    data = _load_user_data()
-
-    if "user_id" in data:
-        return cast(str, data["user_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)
+def get_user_id() -> str:
-    return uid
+    """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()
+    with store_lock(_user_data_lock_name()):
-    if data.get("first_execution_done", False):
+        data = _load_user_data()
-        return
+        if data.get("first_execution_done", False):
+            return
 
-    data.update(
+        uid = data.get("user_id") or _generate_user_id()
-        {
+        data.update(
-            "first_execution_done": True,
+            {
-            "first_execution_at": datetime.now().timestamp(),
+                "first_execution_done": True,
-            "user_id": get_user_id(),
+                "first_execution_at": datetime.now().timestamp(),
-            "machine_id": _get_machine_id(),
+                "user_id": uid,
-            "trace_consent": user_consented,
+                "machine_id": _get_machine_id(),
-        }
+                "trace_consent": user_consented,
-    )
+            }
-    _save_user_data(data)
+        )
+        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/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
+        with self._tool_counts_lock:
-        self.tool_usage_counts[tool_name] = self.tool_usage_counts.get(tool_name, 0) + 1
+            self.tool_usage_counts[tool_name] = (
-        iteration = 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")

lib/crewai/src/crewai/experimental/agent_executor.py

@@ -3,6 +3,7 @@ from __future__ import annotations
 import asyncio
 from collections.abc import Callable, Coroutine
 from concurrent.futures import ThreadPoolExecutor, as_completed
+import contextvars
 from datetime import datetime
 import inspect
 import json
@@ -302,6 +303,7 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
             super().__init__(
                 suppress_flow_events=True,
                 tracing=current_tracing if current_tracing else None,
+                max_method_calls=self.max_iter * 10,
             )
             self._flow_initialized = True
 
@@ -403,7 +405,7 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
                 self._setup_native_tools()
         return "initialized"
 
-    @listen("force_final_answer")
+    @listen("max_iterations_exceeded")
     def force_final_answer(self) -> Literal["agent_finished"]:
         """Force agent to provide final answer when max iterations exceeded."""
         formatted_answer = handle_max_iterations_exceeded(
@@ -655,11 +657,11 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
             return "tool_result_is_final"
 
         reasoning_prompt = self._i18n.slice("post_tool_reasoning")
-        reasoning_message: LLMMessage = {
+        reasoning_message_post: LLMMessage = {
             "role": "user",
             "content": reasoning_prompt,
         }
-        self.state.messages.append(reasoning_message)
+        self.state.messages.append(reasoning_message_post)
 
         return "tool_completed"
 
@@ -727,7 +729,11 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
             max_workers = min(8, len(runnable_tool_calls))
             with ThreadPoolExecutor(max_workers=max_workers) as pool:
                 future_to_idx = {
-                    pool.submit(self._execute_single_native_tool_call, tool_call): idx
+                    pool.submit(
+                        contextvars.copy_context().run,
+                        self._execute_single_native_tool_call,
+                        tool_call,
+                    ): idx
                     for idx, tool_call in enumerate(runnable_tool_calls)
                 }
                 ordered_results: list[dict[str, Any] | None] = [None] * len(
@@ -886,9 +892,10 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
         call_id, func_name, func_args = info
 
         # Parse arguments
-        args_dict, parse_error = parse_tool_call_args(func_args, func_name, call_id)
+        parsed_args, parse_error = parse_tool_call_args(func_args, func_name, call_id)
         if parse_error is not None:
             return parse_error
+        args_dict: dict[str, Any] = parsed_args or {}
 
         # Get agent_key for event tracking
         agent_key = getattr(self.agent, "key", "unknown") if self.agent else "unknown"
@@ -1107,11 +1114,11 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
     def check_max_iterations(
         self,
     ) -> Literal[
-        "force_final_answer", "continue_reasoning", "continue_reasoning_native"
+        "max_iterations_exceeded", "continue_reasoning", "continue_reasoning_native"
     ]:
         """Check if max iterations reached before proceeding with reasoning."""
         if has_reached_max_iterations(self.state.iterations, self.max_iter):
-            return "force_final_answer"
+            return "max_iterations_exceeded"
         if self.state.use_native_tools:
             return "continue_reasoning_native"
         return "continue_reasoning"

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

@@ -17,6 +17,7 @@ from collections.abc import (
     ValuesView,
 )
 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]] = []
@@ -1741,8 +1814,9 @@ class Flow(Generic[T], metaclass=FlowMeta):
 
         try:
             asyncio.get_running_loop()
+            ctx = contextvars.copy_context()
             with ThreadPoolExecutor(max_workers=1) as pool:
-                return pool.submit(asyncio.run, _run_flow()).result()
+                return pool.submit(ctx.run, asyncio.run, _run_flow()).result()
         except RuntimeError:
             return asyncio.run(_run_flow())
 
@@ -1828,6 +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
@@ -2165,8 +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:
@@ -2569,6 +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
@@ -2633,7 +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) ────────────────────────────────────────
@@ -2775,8 +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(
+                matches = flow_instance.memory.recall(query, source=learn_source)
-                    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
+        state_dict = self._to_state_dict(state_data)
-        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 sqlite3.connect(self.db_path) as conn:
+        with (
-            conn.execute(
+            store_lock(self._lock_name),
-                """
+            sqlite3.connect(self.db_path, timeout=30) as conn,
-            INSERT INTO flow_states (
+        ):
-                flow_uuid,
+            self._save_state_sql(conn, flow_uuid, method_name, state_dict)
-                method_name,
-                timestamp,
-                state_json
-            ) VALUES (?, ?, ?, ?)
-            """,
-                (
-                    flow_uuid,
-                    method_name,
-                    datetime.now(timezone.utc).isoformat(),
-                    json.dumps(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
+        with (
-        if isinstance(state_data, BaseModel):
+            store_lock(self._lock_name),
-            state_dict = state_data.model_dump()
+            sqlite3.connect(self.db_path, timeout=30) as conn,
-        elif isinstance(state_data, dict):
+        ):
-            state_dict = state_data
+            self._save_state_sql(conn, flow_uuid, context.method_name, state_dict)
-        else:
-            raise ValueError(
-                f"state_data must be either a Pydantic BaseModel or dict, got {type(state_data)}"
-            )
 
-        # 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:

lib/crewai/src/crewai/llms/base_llm.py

@@ -26,6 +26,7 @@ from crewai.events.types.llm_events import (
     LLMCallStartedEvent,
     LLMCallType,
     LLMStreamChunkEvent,
+    LLMThinkingChunkEvent,
 )
 from crewai.events.types.tool_usage_events import (
     ToolUsageErrorEvent,
@@ -368,9 +369,6 @@ class BaseLLM(ABC):
         """Emit LLM call started event."""
         from crewai.utilities.serialization import to_serializable
 
-        if not hasattr(crewai_event_bus, "emit"):
-            raise ValueError("crewai_event_bus does not have an emit method") from None
-
         crewai_event_bus.emit(
             self,
             event=LLMCallStartedEvent(
@@ -416,9 +414,6 @@ class BaseLLM(ABC):
         from_agent: Agent | None = None,
     ) -> None:
         """Emit LLM call failed event."""
-        if not hasattr(crewai_event_bus, "emit"):
-            raise ValueError("crewai_event_bus does not have an emit method") from None
-
         crewai_event_bus.emit(
             self,
             event=LLMCallFailedEvent(
@@ -449,9 +444,6 @@ class BaseLLM(ABC):
             call_type: The type of LLM call (LLM_CALL or TOOL_CALL).
             response_id: Unique ID for a particular LLM response, chunks have same response_id.
         """
-        if not hasattr(crewai_event_bus, "emit"):
-            raise ValueError("crewai_event_bus does not have an emit method") from None
-
         crewai_event_bus.emit(
             self,
             event=LLMStreamChunkEvent(
@@ -465,6 +457,32 @@ class BaseLLM(ABC):
             ),
         )
 
+    def _emit_thinking_chunk_event(
+        self,
+        chunk: str,
+        from_task: Task | None = None,
+        from_agent: Agent | None = None,
+        response_id: str | None = None,
+    ) -> None:
+        """Emit thinking/reasoning chunk event from a thinking model.
+
+        Args:
+            chunk: The thinking text content.
+            from_task: The task that initiated the call.
+            from_agent: The agent that initiated the call.
+            response_id: Unique ID for a particular LLM response.
+        """
+        crewai_event_bus.emit(
+            self,
+            event=LLMThinkingChunkEvent(
+                chunk=chunk,
+                from_task=from_task,
+                from_agent=from_agent,
+                response_id=response_id,
+                call_id=get_current_call_id(),
+            ),
+        )
+
     def _handle_tool_execution(
         self,
         function_name: str,

lib/crewai/src/crewai/llms/providers/anthropic/completion.py

@@ -22,7 +22,12 @@ if TYPE_CHECKING:
 
 try:
     from anthropic import Anthropic, AsyncAnthropic, transform_schema
-    from anthropic.types import Message, TextBlock, ThinkingBlock, ToolUseBlock
+    from anthropic.types import (
+        Message,
+        TextBlock,
+        ThinkingBlock,
+        ToolUseBlock,
+    )
     from anthropic.types.beta import BetaMessage, BetaTextBlock, BetaToolUseBlock
     import httpx
 except ImportError:
@@ -31,6 +36,11 @@ except ImportError:
     ) from None
 
 
+TOOL_SEARCH_TOOL_TYPES: Final[tuple[str, ...]] = (
+    "tool_search_tool_regex_20251119",
+    "tool_search_tool_bm25_20251119",
+)
+
 ANTHROPIC_FILES_API_BETA: Final = "files-api-2025-04-14"
 ANTHROPIC_STRUCTURED_OUTPUTS_BETA: Final = "structured-outputs-2025-11-13"
 
@@ -117,6 +127,22 @@ class AnthropicThinkingConfig(BaseModel):
     budget_tokens: int | None = None
 
 
+class AnthropicToolSearchConfig(BaseModel):
+    """Configuration for Anthropic's server-side tool search.
+
+    When enabled, tools marked with defer_loading=True are not loaded into
+    context immediately. Instead, Claude uses the tool search tool to
+    dynamically discover and load relevant tools on-demand.
+
+    Attributes:
+        type: The tool search variant to use.
+            - "regex": Claude constructs regex patterns to search tool names/descriptions.
+            - "bm25": Claude uses natural language queries to search tools.
+    """
+
+    type: Literal["regex", "bm25"] = "bm25"
+
+
 class AnthropicCompletion(BaseLLM):
     """Anthropic native completion implementation.
 
@@ -140,6 +166,7 @@ class AnthropicCompletion(BaseLLM):
         interceptor: BaseInterceptor[httpx.Request, httpx.Response] | None = None,
         thinking: AnthropicThinkingConfig | None = None,
         response_format: type[BaseModel] | None = None,
+        tool_search: AnthropicToolSearchConfig | bool | None = None,
         **kwargs: Any,
     ):
         """Initialize Anthropic chat completion client.
@@ -159,6 +186,10 @@ class AnthropicCompletion(BaseLLM):
             interceptor: HTTP interceptor for modifying requests/responses at transport level.
             response_format: Pydantic model for structured output. When provided, responses
                 will be validated against this model schema.
+            tool_search: Enable Anthropic's server-side tool search. When True, uses "bm25"
+                variant by default. Pass an AnthropicToolSearchConfig to choose "regex" or
+                "bm25". When enabled, tools are automatically marked with defer_loading=True
+                and a tool search tool is injected into the tools list.
             **kwargs: Additional parameters
         """
         super().__init__(
@@ -190,6 +221,13 @@ class AnthropicCompletion(BaseLLM):
         self.thinking = thinking
         self.previous_thinking_blocks: list[ThinkingBlock] = []
         self.response_format = response_format
+        # Tool search config
+        if tool_search is True:
+            self.tool_search = AnthropicToolSearchConfig()
+        elif isinstance(tool_search, AnthropicToolSearchConfig):
+            self.tool_search = tool_search
+        else:
+            self.tool_search = None
         # Model-specific settings
         self.is_claude_3 = "claude-3" in model.lower()
         self.supports_tools = True
@@ -432,10 +470,23 @@ class AnthropicCompletion(BaseLLM):
         # Handle tools for Claude 3+
         if tools and self.supports_tools:
             converted_tools = self._convert_tools_for_interference(tools)
+
+            # When tool_search is enabled and there are 2+ regular tools,
+            # inject the search tool and mark regular tools with defer_loading.
+            # With only 1 tool there's nothing to search — skip tool search
+            # entirely so the normal forced tool_choice optimisation still works.
+            regular_tools = [
+                t
+                for t in converted_tools
+                if t.get("type", "") not in TOOL_SEARCH_TOOL_TYPES
+            ]
+            if self.tool_search is not None and len(regular_tools) >= 2:
+                converted_tools = self._apply_tool_search(converted_tools)
+
             params["tools"] = converted_tools
 
-            if available_functions and len(converted_tools) == 1:
+            if available_functions and len(regular_tools) == 1:
-                tool_name = converted_tools[0].get("name")
+                tool_name = regular_tools[0].get("name")
                 if tool_name and tool_name in available_functions:
                     params["tool_choice"] = {"type": "tool", "name": tool_name}
 
@@ -454,6 +505,12 @@ class AnthropicCompletion(BaseLLM):
         anthropic_tools = []
 
         for tool in tools:
+            # Pass through tool search tool definitions unchanged
+            tool_type = tool.get("type", "")
+            if tool_type in TOOL_SEARCH_TOOL_TYPES:
+                anthropic_tools.append(tool)
+                continue
+
             if "input_schema" in tool and "name" in tool and "description" in tool:
                 anthropic_tools.append(tool)
                 continue
@@ -466,15 +523,15 @@ class AnthropicCompletion(BaseLLM):
                 logging.error(f"Error converting tool to Anthropic format: {e}")
                 raise e
 
-            anthropic_tool = {
+            anthropic_tool: dict[str, Any] = {
                 "name": name,
                 "description": description,
             }
 
             if parameters and isinstance(parameters, dict):
-                anthropic_tool["input_schema"] = parameters  # type: ignore[assignment]
+                anthropic_tool["input_schema"] = parameters
             else:
-                anthropic_tool["input_schema"] = {  # type: ignore[assignment]
+                anthropic_tool["input_schema"] = {
                     "type": "object",
                     "properties": {},
                     "required": [],
@@ -484,6 +541,55 @@ class AnthropicCompletion(BaseLLM):
 
         return anthropic_tools
 
+    def _apply_tool_search(self, tools: list[dict[str, Any]]) -> list[dict[str, Any]]:
+        """Inject tool search tool and mark regular tools with defer_loading.
+
+        When tool_search is enabled, this method:
+        1. Adds the appropriate tool search tool definition (regex or bm25)
+        2. Marks all regular tools with defer_loading=True so they are only
+           loaded when Claude discovers them via search
+
+        Args:
+            tools: Converted tool definitions in Anthropic format.
+
+        Returns:
+            Updated tools list with tool search tool prepended and
+            regular tools marked as deferred.
+        """
+        if self.tool_search is None:
+            return tools
+
+        # Check if a tool search tool is already present (user passed one manually)
+        has_search_tool = any(
+            t.get("type", "") in TOOL_SEARCH_TOOL_TYPES for t in tools
+        )
+
+        result: list[dict[str, Any]] = []
+
+        if not has_search_tool:
+            # Map config type to API type identifier
+            type_map = {
+                "regex": "tool_search_tool_regex_20251119",
+                "bm25": "tool_search_tool_bm25_20251119",
+            }
+            tool_type = type_map[self.tool_search.type]
+            # Tool search tool names follow the convention: tool_search_tool_{variant}
+            tool_name = f"tool_search_tool_{self.tool_search.type}"
+            result.append({"type": tool_type, "name": tool_name})
+
+        for tool in tools:
+            # Don't modify tool search tools
+            if tool.get("type", "") in TOOL_SEARCH_TOOL_TYPES:
+                result.append(tool)
+                continue
+
+            # Mark regular tools as deferred if not already set
+            if "defer_loading" not in tool:
+                tool = {**tool, "defer_loading": True}
+            result.append(tool)
+
+        return result
+
     def _extract_thinking_block(
         self, content_block: Any
     ) -> ThinkingBlock | dict[str, Any] | None:

lib/crewai/src/crewai/llms/providers/bedrock/completion.py

@@ -1781,6 +1781,7 @@ class BedrockCompletion(BaseLLM):
 
         converse_messages: list[LLMMessage] = []
         system_message: str | None = None
+        pending_tool_results: list[dict[str, Any]] = []
 
         for message in formatted_messages:
             role = message.get("role")
@@ -1794,53 +1795,56 @@ class BedrockCompletion(BaseLLM):
                     system_message += f"\n\n{content}"
                 else:
                     system_message = cast(str, content)
-            elif role == "assistant" and tool_calls:
-                # Convert OpenAI-style tool_calls to Bedrock toolUse format
-                bedrock_content = []
-                for tc in tool_calls:
-                    func = tc.get("function", {})
-                    tool_use_block = {
-                        "toolUse": {
-                            "toolUseId": tc.get("id", f"call_{id(tc)}"),
-                            "name": func.get("name", ""),
-                            "input": func.get("arguments", {})
-                            if isinstance(func.get("arguments"), dict)
-                            else json.loads(func.get("arguments", "{}") or "{}"),
-                        }
-                    }
-                    bedrock_content.append(tool_use_block)
-                converse_messages.append(
-                    {"role": "assistant", "content": bedrock_content}
-                )
             elif role == "tool":
                 if not tool_call_id:
                     raise ValueError("Tool message missing required tool_call_id")
-                converse_messages.append(
+                pending_tool_results.append(
                     {
-                        "role": "user",
+                        "toolResult": {
-                        "content": [
+                            "toolUseId": tool_call_id,
-                            {
+                            "content": [{"text": str(content) if content else ""}],
-                                "toolResult": {
+                        }
-                                    "toolUseId": tool_call_id,
-                                    "content": [
-                                        {"text": str(content) if content else ""}
-                                    ],
-                                }
-                            }
-                        ],
                     }
                 )
             else:
-                # Convert to Converse API format with proper content structure
+                if pending_tool_results:
-                if isinstance(content, list):
-                    # Already formatted as multimodal content blocks
-                    converse_messages.append({"role": role, "content": content})
-                else:
-                    # String content - wrap in text block
-                    text_content = content if content else ""
                     converse_messages.append(
-                        {"role": role, "content": [{"text": text_content}]}
+                        {"role": "user", "content": pending_tool_results}
                     )
+                    pending_tool_results = []
+
+                if role == "assistant" and tool_calls:
+                    # Convert OpenAI-style tool_calls to Bedrock toolUse format
+                    bedrock_content = []
+                    for tc in tool_calls:
+                        func = tc.get("function", {})
+                        tool_use_block = {
+                            "toolUse": {
+                                "toolUseId": tc.get("id", f"call_{id(tc)}"),
+                                "name": func.get("name", ""),
+                                "input": func.get("arguments", {})
+                                if isinstance(func.get("arguments"), dict)
+                                else json.loads(func.get("arguments", "{}") or "{}"),
+                            }
+                        }
+                        bedrock_content.append(tool_use_block)
+                    converse_messages.append(
+                        {"role": "assistant", "content": bedrock_content}
+                    )
+                else:
+                    # Convert to Converse API format with proper content structure
+                    if isinstance(content, list):
+                        # Already formatted as multimodal content blocks
+                        converse_messages.append({"role": role, "content": content})
+                    else:
+                        # String content - wrap in text block
+                        text_content = content if content else ""
+                        converse_messages.append(
+                            {"role": role, "content": [{"text": text_content}]}
+                        )
+
+        if pending_tool_results:
+            converse_messages.append({"role": "user", "content": pending_tool_results})
 
         # CRITICAL: Handle model-specific conversation requirements
         # Cohere and some other models require conversation to end with user message

lib/crewai/src/crewai/llms/providers/gemini/completion.py

@@ -61,6 +61,7 @@ class GeminiCompletion(BaseLLM):
         interceptor: BaseInterceptor[Any, Any] | None = None,
         use_vertexai: bool | None = None,
         response_format: type[BaseModel] | None = None,
+        thinking_config: types.ThinkingConfig | None = None,
         **kwargs: Any,
     ):
         """Initialize Google Gemini chat completion client.
@@ -93,6 +94,10 @@ class GeminiCompletion(BaseLLM):
                          api_version="v1" is automatically configured.
             response_format: Pydantic model for structured output. Used as default when
                            response_model is not passed to call()/acall() methods.
+            thinking_config: ThinkingConfig for thinking models (gemini-2.5+, gemini-3+).
+                           Controls thought output via include_thoughts, thinking_budget,
+                           and thinking_level. When None, thinking models automatically
+                           get include_thoughts=True so thought content is surfaced.
             **kwargs: Additional parameters
         """
         if interceptor is not None:
@@ -139,6 +144,14 @@ class GeminiCompletion(BaseLLM):
             version_match and float(version_match.group(1)) >= 2.0
         )
 
+        self.thinking_config = thinking_config
+        if (
+            self.thinking_config is None
+            and version_match
+            and float(version_match.group(1)) >= 2.5
+        ):
+            self.thinking_config = types.ThinkingConfig(include_thoughts=True)
+
     @property
     def stop(self) -> list[str]:
         """Get stop sequences sent to the API."""
@@ -520,6 +533,9 @@ class GeminiCompletion(BaseLLM):
         if self.safety_settings:
             config_params["safety_settings"] = self.safety_settings
 
+        if self.thinking_config is not None:
+            config_params["thinking_config"] = self.thinking_config
+
         return types.GenerateContentConfig(**config_params)
 
     def _convert_tools_for_interference(  # type: ignore[override]
@@ -618,9 +634,17 @@ class GeminiCompletion(BaseLLM):
                 function_response_part = types.Part.from_function_response(
                     name=tool_name, response=response_data
                 )
-                contents.append(
+                if (
-                    types.Content(role="user", parts=[function_response_part])
+                    contents
-                )
+                    and contents[-1].role == "user"
+                    and contents[-1].parts
+                    and contents[-1].parts[-1].function_response is not None
+                ):
+                    contents[-1].parts.append(function_response_part)
+                else:
+                    contents.append(
+                        types.Content(role="user", parts=[function_response_part])
+                    )
             elif role == "assistant" and message.get("tool_calls"):
                 raw_parts: list[Any] | None = message.get("raw_tool_call_parts")
                 if raw_parts and all(isinstance(p, types.Part) for p in raw_parts):
@@ -931,15 +955,6 @@ class GeminiCompletion(BaseLLM):
         if chunk.usage_metadata:
             usage_data = self._extract_token_usage(chunk)
 
-        if chunk.text:
-            full_response += chunk.text
-            self._emit_stream_chunk_event(
-                chunk=chunk.text,
-                from_task=from_task,
-                from_agent=from_agent,
-                response_id=response_id,
-            )
-
         if chunk.candidates:
             candidate = chunk.candidates[0]
             if candidate.content and candidate.content.parts:
@@ -976,6 +991,21 @@ class GeminiCompletion(BaseLLM):
                             call_type=LLMCallType.TOOL_CALL,
                             response_id=response_id,
                         )
+                    elif part.thought and part.text:
+                        self._emit_thinking_chunk_event(
+                            chunk=part.text,
+                            from_task=from_task,
+                            from_agent=from_agent,
+                            response_id=response_id,
+                        )
+                    elif part.text:
+                        full_response += part.text
+                        self._emit_stream_chunk_event(
+                            chunk=part.text,
+                            from_task=from_task,
+                            from_agent=from_agent,
+                            response_id=response_id,
+                        )
 
         return full_response, function_calls, usage_data
 
@@ -1329,7 +1359,7 @@ class GeminiCompletion(BaseLLM):
         text_parts = [
             part.text
             for part in candidate.content.parts
-            if hasattr(part, "text") and part.text
+            if part.text and not part.thought
         ]
 
         return "".join(text_parts)

lib/crewai/src/crewai/mcp/tool_resolver.py

@@ -11,6 +11,7 @@ into a standalone MCPToolResolver. It handles three flavours of MCP reference:
 from __future__ import annotations
 
 import asyncio
+import contextvars
 import time
 from typing import TYPE_CHECKING, Any, Final, cast
 from urllib.parse import urlparse
@@ -25,6 +26,7 @@ from crewai.mcp.config import (
 from crewai.mcp.transports.http import HTTPTransport
 from crewai.mcp.transports.sse import SSETransport
 from crewai.mcp.transports.stdio import StdioTransport
+from crewai.utilities.string_utils import sanitize_tool_name
 
 
 if TYPE_CHECKING:
@@ -74,10 +76,9 @@ class MCPToolResolver:
             elif isinstance(mcp_config, str):
                 amp_refs.append(self._parse_amp_ref(mcp_config))
             else:
-                tools, client = self._resolve_native(mcp_config)
+                tools, clients = self._resolve_native(mcp_config)
                 all_tools.extend(tools)
-                if client:
+                self._clients.extend(clients)
-                    self._clients.append(client)
 
         if amp_refs:
             tools, clients = self._resolve_amp(amp_refs)
@@ -131,7 +132,7 @@ class MCPToolResolver:
         all_tools: list[BaseTool] = []
         all_clients: list[Any] = []
 
-        resolved_cache: dict[str, tuple[list[BaseTool], Any | None]] = {}
+        resolved_cache: dict[str, tuple[list[BaseTool], list[Any]]] = {}
 
         for slug in unique_slugs:
             config_dict = amp_configs_map.get(slug)
@@ -149,10 +150,9 @@ class MCPToolResolver:
             mcp_server_config = self._build_mcp_config_from_dict(config_dict)
 
             try:
-                tools, client = self._resolve_native(mcp_server_config)
+                tools, clients = self._resolve_native(mcp_server_config)
-                resolved_cache[slug] = (tools, client)
+                resolved_cache[slug] = (tools, clients)
-                if client:
+                all_clients.extend(clients)
-                    all_clients.append(client)
             except Exception as e:
                 crewai_event_bus.emit(
                     self,
@@ -170,8 +170,9 @@ class MCPToolResolver:
 
             slug_tools, _ = cached
             if specific_tool:
+                sanitized = sanitize_tool_name(specific_tool)
                 all_tools.extend(
-                    t for t in slug_tools if t.name.endswith(f"_{specific_tool}")
+                    t for t in slug_tools if t.name.endswith(f"_{sanitized}")
                 )
             else:
                 all_tools.extend(slug_tools)
@@ -198,7 +199,6 @@ class MCPToolResolver:
 
             plus_api = PlusAPI(api_key=get_platform_integration_token())
             response = plus_api.get_mcp_configs(slugs)
-
             if response.status_code == 200:
                 configs: dict[str, dict[str, Any]] = response.json().get("configs", {})
                 return configs
@@ -218,6 +218,7 @@ class MCPToolResolver:
 
     def _resolve_external(self, mcp_ref: str) -> list[BaseTool]:
         """Resolve an HTTPS MCP server URL into tools."""
+        from crewai.tools.base_tool import BaseTool
         from crewai.tools.mcp_tool_wrapper import MCPToolWrapper
 
         if "#" in mcp_ref:
@@ -227,6 +228,9 @@ class MCPToolResolver:
 
         server_params = {"url": server_url}
         server_name = self._extract_server_name(server_url)
+        sanitized_specific_tool = (
+            sanitize_tool_name(specific_tool) if specific_tool else None
+        )
 
         try:
             tool_schemas = self._get_mcp_tool_schemas(server_params)
@@ -239,7 +243,7 @@ class MCPToolResolver:
 
             tools = []
             for tool_name, schema in tool_schemas.items():
-                if specific_tool and tool_name != specific_tool:
+                if sanitized_specific_tool and tool_name != sanitized_specific_tool:
                     continue
 
                 try:
@@ -271,14 +275,16 @@ class MCPToolResolver:
             )
             return []
 
-    def _resolve_native(
+    @staticmethod
-        self, mcp_config: MCPServerConfig
+    def _create_transport(
-    ) -> tuple[list[BaseTool], Any | None]:
+        mcp_config: MCPServerConfig,
-        """Resolve an ``MCPServerConfig`` into tools, returning the client for cleanup."""
+    ) -> tuple[StdioTransport | HTTPTransport | SSETransport, str]:
-        from crewai.tools.base_tool import BaseTool
+        """Create a fresh transport instance from an MCP server config.
-        from crewai.tools.mcp_native_tool import MCPNativeTool
 
-        transport: StdioTransport | HTTPTransport | SSETransport
+        Returns a ``(transport, server_name)`` tuple. Each call produces an
+        independent transport so that parallel tool executions never share
+        state.
+        """
         if isinstance(mcp_config, MCPServerStdio):
             transport = StdioTransport(
                 command=mcp_config.command,
@@ -292,38 +298,54 @@ class MCPToolResolver:
                 headers=mcp_config.headers,
                 streamable=mcp_config.streamable,
             )
-            server_name = self._extract_server_name(mcp_config.url)
+            server_name = MCPToolResolver._extract_server_name(mcp_config.url)
         elif isinstance(mcp_config, MCPServerSSE):
             transport = SSETransport(
                 url=mcp_config.url,
                 headers=mcp_config.headers,
             )
-            server_name = self._extract_server_name(mcp_config.url)
+            server_name = MCPToolResolver._extract_server_name(mcp_config.url)
         else:
             raise ValueError(f"Unsupported MCP server config type: {type(mcp_config)}")
+        return transport, server_name
 
-        client = MCPClient(
+    def _resolve_native(
-            transport=transport,
+        self, mcp_config: MCPServerConfig
+    ) -> tuple[list[BaseTool], list[Any]]:
+        """Resolve an ``MCPServerConfig`` into tools.
+
+        Returns ``(tools, clients)`` where *clients* is always empty for
+        native tools (clients are now created on-demand per invocation).
+        A ``client_factory`` closure is passed to each ``MCPNativeTool`` so
+        every call -- even concurrent calls to the *same* tool -- gets its
+        own ``MCPClient`` + transport with no shared mutable state.
+        """
+        from crewai.tools.base_tool import BaseTool
+        from crewai.tools.mcp_native_tool import MCPNativeTool
+
+        discovery_transport, server_name = self._create_transport(mcp_config)
+        discovery_client = MCPClient(
+            transport=discovery_transport,
             cache_tools_list=mcp_config.cache_tools_list,
         )
 
         async def _setup_client_and_list_tools() -> list[dict[str, Any]]:
             try:
-                if not client.connected:
+                if not discovery_client.connected:
-                    await client.connect()
+                    await discovery_client.connect()
 
-                tools_list = await client.list_tools()
+                tools_list = await discovery_client.list_tools()
 
                 try:
-                    await client.disconnect()
+                    await discovery_client.disconnect()
                     await asyncio.sleep(0.1)
                 except Exception as e:
                     self._logger.log("error", f"Error during disconnect: {e}")
 
                 return tools_list
             except Exception as e:
-                if client.connected:
+                if discovery_client.connected:
-                    await client.disconnect()
+                    await discovery_client.disconnect()
                     await asyncio.sleep(0.1)
                 raise RuntimeError(
                     f"Error during setup client and list tools: {e}"
@@ -334,9 +356,10 @@ class MCPToolResolver:
                 asyncio.get_running_loop()
                 import concurrent.futures
 
+                ctx = contextvars.copy_context()
                 with concurrent.futures.ThreadPoolExecutor() as executor:
                     future = executor.submit(
-                        asyncio.run, _setup_client_and_list_tools()
+                        ctx.run, asyncio.run, _setup_client_and_list_tools()
                     )
                     tools_list = future.result()
             except RuntimeError:
@@ -376,6 +399,13 @@ class MCPToolResolver:
                         filtered_tools.append(tool)
                 tools_list = filtered_tools
 
+            def _client_factory() -> MCPClient:
+                transport, _ = self._create_transport(mcp_config)
+                return MCPClient(
+                    transport=transport,
+                    cache_tools_list=mcp_config.cache_tools_list,
+                )
+
             tools = []
             for tool_def in tools_list:
                 tool_name = tool_def.get("name", "")
@@ -396,7 +426,7 @@ class MCPToolResolver:
 
                 try:
                     native_tool = MCPNativeTool(
-                        mcp_client=client,
+                        client_factory=_client_factory,
                         tool_name=tool_name,
                         tool_schema=tool_schema,
                         server_name=server_name,
@@ -407,10 +437,10 @@ class MCPToolResolver:
                     self._logger.log("error", f"Failed to create native MCP tool: {e}")
                     continue
 
-            return cast(list[BaseTool], tools), client
+            return cast(list[BaseTool], tools), []
         except Exception as e:
-            if client.connected:
+            if discovery_client.connected:
-                asyncio.run(client.disconnect())
+                asyncio.run(discovery_client.disconnect())
 
             raise RuntimeError(f"Failed to get native MCP tools: {e}") from e
 

lib/crewai/src/crewai/memory/__init__.py

@@ -19,6 +19,7 @@ from crewai.memory.types import (
     embed_texts,
 )
 
+
 _LAZY_IMPORTS: dict[str, tuple[str, str]] = {
     "Memory": ("crewai.memory.unified_memory", "Memory"),
     "EncodingFlow": ("crewai.memory.encoding_flow", "EncodingFlow"),

lib/crewai/src/crewai/memory/analyze.py

@@ -308,7 +308,9 @@ def analyze_for_save(
         return MemoryAnalysis.model_validate(response)
     except Exception as e:
         _logger.warning(
-            "Memory save analysis failed, using defaults: %s", e, exc_info=False,
+            "Memory save analysis failed, using defaults: %s",
+            e,
+            exc_info=False,
         )
         return _SAVE_DEFAULTS
 
@@ -366,6 +368,8 @@ def analyze_for_consolidation(
         return ConsolidationPlan.model_validate(response)
     except Exception as e:
         _logger.warning(
-            "Consolidation analysis failed, defaulting to insert: %s", e, exc_info=False,
+            "Consolidation analysis failed, defaulting to insert: %s",
+            e,
+            exc_info=False,
         )
         return _CONSOLIDATION_DEFAULT

lib/crewai/src/crewai/memory/encoding_flow.py

@@ -11,7 +11,9 @@ Orchestrates the encoding side of memory in a single Flow with 5 steps:
 from __future__ import annotations
 
 from concurrent.futures import Future, ThreadPoolExecutor
+import contextvars
 from datetime import datetime
+import logging
 import math
 from typing import Any
 from uuid import uuid4
@@ -28,6 +30,8 @@ from crewai.memory.analyze import (
 from crewai.memory.types import MemoryConfig, MemoryRecord, embed_texts
 
 
+logger = logging.getLogger(__name__)
+
 # ---------------------------------------------------------------------------
 # State models
 # ---------------------------------------------------------------------------
@@ -164,14 +168,20 @@ class EncodingFlow(Flow[EncodingState]):
     def parallel_find_similar(self) -> None:
         """Search storage for similar records, concurrently for all active items."""
         items = list(self.state.items)
-        active = [(i, item) for i, item in enumerate(items) if not item.dropped and item.embedding]
+        active = [
+            (i, item)
+            for i, item in enumerate(items)
+            if not item.dropped and item.embedding
+        ]
 
         if not active:
             return
 
-        def _search_one(item: ItemState) -> list[tuple[MemoryRecord, float]]:
+        def _search_one(
+            item: ItemState,
+        ) -> list[tuple[MemoryRecord, float]]:
             scope_prefix = item.scope if item.scope and item.scope.strip("/") else None
-            return self._storage.search(
+            return self._storage.search(  # type: ignore[no-any-return]
                 item.embedding,
                 scope_prefix=scope_prefix,
                 categories=None,
@@ -181,14 +191,37 @@ class EncodingFlow(Flow[EncodingState]):
 
         if len(active) == 1:
             _, item = active[0]
-            raw = _search_one(item)
+            try:
+                raw = _search_one(item)
+            except Exception:
+                logger.warning(
+                    "Storage search failed in parallel_find_similar, "
+                    "treating item as new",
+                    exc_info=True,
+                )
+                raw = []
             item.similar_records = [r for r, _ in raw]
             item.top_similarity = float(raw[0][1]) if raw else 0.0
         else:
             with ThreadPoolExecutor(max_workers=min(len(active), 8)) as pool:
-                futures = [(i, item, pool.submit(_search_one, item)) for i, item in active]
+                futures = [
+                    (
+                        i,
+                        item,
+                        pool.submit(contextvars.copy_context().run, _search_one, item),
+                    )
+                    for i, item in active
+                ]
                 for _, item, future in futures:
-                    raw = future.result()
+                    try:
+                        raw = future.result()
+                    except Exception:
+                        logger.warning(
+                            "Storage search failed in parallel_find_similar, "
+                            "treating item as new",
+                            exc_info=True,
+                        )
+                        raw = []
                     item.similar_records = [r for r, _ in raw]
                     item.top_similarity = float(raw[0][1]) if raw else 0.0
 
@@ -250,24 +283,38 @@ class EncodingFlow(Flow[EncodingState]):
                     # Group B: consolidation only
                     self._apply_defaults(item)
                     consol_futures[i] = pool.submit(
+                        contextvars.copy_context().run,
                         analyze_for_consolidation,
-                        item.content, list(item.similar_records), self._llm,
+                        item.content,
+                        list(item.similar_records),
+                        self._llm,
                     )
                 elif not fields_provided and not has_similar:
                     # Group C: field resolution only
                     save_futures[i] = pool.submit(
+                        contextvars.copy_context().run,
                         analyze_for_save,
-                        item.content, existing_scopes, existing_categories, self._llm,
+                        item.content,
+                        existing_scopes,
+                        existing_categories,
+                        self._llm,
                     )
                 else:
                     # Group D: both in parallel
                     save_futures[i] = pool.submit(
+                        contextvars.copy_context().run,
                         analyze_for_save,
-                        item.content, existing_scopes, existing_categories, self._llm,
+                        item.content,
+                        existing_scopes,
+                        existing_categories,
+                        self._llm,
                     )
                     consol_futures[i] = pool.submit(
+                        contextvars.copy_context().run,
                         analyze_for_consolidation,
-                        item.content, list(item.similar_records), self._llm,
+                        item.content,
+                        list(item.similar_records),
+                        self._llm,
                     )
 
             # Collect field-resolution results
@@ -300,8 +347,8 @@ class EncodingFlow(Flow[EncodingState]):
                     item.plan = ConsolidationPlan(actions=[], insert_new=True)
 
             # Collect consolidation results
-            for i, future in consol_futures.items():
+            for i, consol_future in consol_futures.items():
-                items[i].plan = future.result()
+                items[i].plan = consol_future.result()
         finally:
             pool.shutdown(wait=False)
 
@@ -339,7 +386,9 @@ class EncodingFlow(Flow[EncodingState]):
         # similar_records overlap). Collect one action per record_id, first wins.
         # Also build a map from record_id to the original MemoryRecord for updates.
         dedup_deletes: set[str] = set()  # record_ids to delete
-        dedup_updates: dict[str, tuple[int, str]] = {}  # record_id -> (item_idx, new_content)
+        dedup_updates: dict[
+            str, tuple[int, str]
+        ] = {}  # record_id -> (item_idx, new_content)
         all_similar: dict[str, MemoryRecord] = {}  # record_id -> MemoryRecord
 
         for i, item in enumerate(items):
@@ -350,13 +399,24 @@ class EncodingFlow(Flow[EncodingState]):
                     all_similar[r.id] = r
             for action in item.plan.actions:
                 rid = action.record_id
-                if action.action == "delete" and rid not in dedup_deletes and rid not in dedup_updates:
+                if (
+                    action.action == "delete"
+                    and rid not in dedup_deletes
+                    and rid not in dedup_updates
+                ):
                     dedup_deletes.add(rid)
-                elif action.action == "update" and action.new_content and rid not in dedup_deletes and rid not in dedup_updates:
+                elif (
+                    action.action == "update"
+                    and action.new_content
+                    and rid not in dedup_deletes
+                    and rid not in dedup_updates
+                ):
                     dedup_updates[rid] = (i, action.new_content)
 
         # --- Batch re-embed all update contents in ONE call ---
-        update_list = list(dedup_updates.items())  # [(record_id, (item_idx, new_content)), ...]
+        update_list = list(
+            dedup_updates.items()
+        )  # [(record_id, (item_idx, new_content)), ...]
         update_embeddings: list[list[float]] = []
         if update_list:
             update_contents = [content for _, (_, content) in update_list]
@@ -377,51 +437,52 @@ class EncodingFlow(Flow[EncodingState]):
             if item.dropped or item.plan is None:
                 continue
             if item.plan.insert_new:
-                to_insert.append((i, MemoryRecord(
+                to_insert.append(
-                    content=item.content,
+                    (
-                    scope=item.resolved_scope,
+                        i,
-                    categories=item.resolved_categories,
+                        MemoryRecord(
-                    metadata=item.resolved_metadata,
+                            content=item.content,
-                    importance=item.resolved_importance,
+                            scope=item.resolved_scope,
-                    embedding=item.embedding if item.embedding else None,
+                            categories=item.resolved_categories,
-                    source=item.resolved_source,
+                            metadata=item.resolved_metadata,
-                    private=item.resolved_private,
+                            importance=item.resolved_importance,
-                )))
+                            embedding=item.embedding if item.embedding else None,
-
+                            source=item.resolved_source,
-        # All storage mutations under one lock so no other pipeline can
+                            private=item.resolved_private,
-        # interleave and cause version conflicts. The lock is reentrant
+                        ),
-        # (RLock) so the individual storage methods re-acquire it safely.
-        updated_records: dict[str, MemoryRecord] = {}
-        with self._storage.write_lock:
-            if dedup_deletes:
-                self._storage.delete(record_ids=list(dedup_deletes))
-                self.state.records_deleted += len(dedup_deletes)
-
-            for rid, (_item_idx, new_content) in dedup_updates.items():
-                existing = all_similar.get(rid)
-                if existing is not None:
-                    new_emb = update_emb_map.get(rid, [])
-                    updated = MemoryRecord(
-                        id=existing.id,
-                        content=new_content,
-                        scope=existing.scope,
-                        categories=existing.categories,
-                        metadata=existing.metadata,
-                        importance=existing.importance,
-                        created_at=existing.created_at,
-                        last_accessed=now,
-                        embedding=new_emb if new_emb else existing.embedding,
                     )
-                    self._storage.update(updated)
+                )
-                    self.state.records_updated += 1
-                    updated_records[rid] = updated
 
-            if to_insert:
+        updated_records: dict[str, MemoryRecord] = {}
-                records = [r for _, r in to_insert]
+        if dedup_deletes:
-                self._storage.save(records)
+            self._storage.delete(record_ids=list(dedup_deletes))
-                self.state.records_inserted += len(records)
+            self.state.records_deleted += len(dedup_deletes)
-                for idx, record in to_insert:
+
-                    items[idx].result_record = record
+        for rid, (_item_idx, new_content) in dedup_updates.items():
+            existing = all_similar.get(rid)
+            if existing is not None:
+                new_emb = update_emb_map.get(rid, [])
+                updated = MemoryRecord(
+                    id=existing.id,
+                    content=new_content,
+                    scope=existing.scope,
+                    categories=existing.categories,
+                    metadata=existing.metadata,
+                    importance=existing.importance,
+                    created_at=existing.created_at,
+                    last_accessed=now,
+                    embedding=new_emb if new_emb else existing.embedding,
+                )
+                self._storage.update(updated)
+                self.state.records_updated += 1
+                updated_records[rid] = updated
+
+        if to_insert:
+            records = [r for _, r in to_insert]
+            self._storage.save(records)
+            self.state.records_inserted += len(records)
+            for idx, record in to_insert:
+                items[idx].result_record = record
 
         # Set result_record for non-insert items (after lock, using updated_records)
         for _i, item in enumerate(items):

lib/crewai/src/crewai/memory/memory_scope.py

@@ -3,11 +3,9 @@
 from __future__ import annotations
 
 from datetime import datetime
-from typing import TYPE_CHECKING, Any
+from typing import Any, Literal
 
-
+from pydantic import BaseModel, ConfigDict, Field, PrivateAttr, model_validator
-if TYPE_CHECKING:
-    from crewai.memory.unified_memory import Memory
 
 from crewai.memory.types import (
     _RECALL_OVERSAMPLE_FACTOR,
@@ -15,22 +13,38 @@ from crewai.memory.types import (
     MemoryRecord,
     ScopeInfo,
 )
+from crewai.memory.unified_memory import Memory
 
 
-class MemoryScope:
+class MemoryScope(BaseModel):
     """View of Memory restricted to a root path. All operations are scoped under that path."""
 
-    def __init__(self, memory: Memory, root_path: str) -> None:
+    model_config = ConfigDict(arbitrary_types_allowed=True)
-        """Initialize scope.
 
-        Args:
+    root_path: str = Field(default="/")
-            memory: The underlying Memory instance.
+
-            root_path: Root path for this scope (e.g. /agent/1).
+    _memory: Memory = PrivateAttr()
-        """
+    _root: str = PrivateAttr()
-        self._memory = memory
+
-        self._root = root_path.rstrip("/") or ""
+    @model_validator(mode="wrap")
-        if self._root and not self._root.startswith("/"):
+    @classmethod
-            self._root = "/" + self._root
+    def _accept_memory(cls, data: Any, handler: Any) -> MemoryScope:
+        """Extract memory dependency and normalize root path before validation."""
+        if isinstance(data, MemoryScope):
+            return data
+        memory = data.pop("memory")
+        instance: MemoryScope = handler(data)
+        instance._memory = memory
+        root = instance.root_path.rstrip("/") or ""
+        if root and not root.startswith("/"):
+            root = "/" + root
+        instance._root = root
+        return instance
+
+    @property
+    def read_only(self) -> bool:
+        """Whether the underlying memory is read-only."""
+        return self._memory.read_only
 
     def _scope_path(self, scope: str | None) -> str:
         if not scope or scope == "/":
@@ -52,7 +66,7 @@ class MemoryScope:
         importance: float | None = None,
         source: str | None = None,
         private: bool = False,
-    ) -> MemoryRecord:
+    ) -> MemoryRecord | None:
         """Remember content; scope is relative to this scope's root."""
         path = self._scope_path(scope)
         return self._memory.remember(
@@ -71,7 +85,7 @@ class MemoryScope:
         scope: str | None = None,
         categories: list[str] | None = None,
         limit: int = 10,
-        depth: str = "deep",
+        depth: Literal["shallow", "deep"] = "deep",
         source: str | None = None,
         include_private: bool = False,
     ) -> list[MemoryMatch]:
@@ -138,34 +152,34 @@ class MemoryScope:
         """Return a narrower scope under this scope."""
         child = path.strip("/")
         if not child:
-            return MemoryScope(self._memory, self._root or "/")
+            return MemoryScope(memory=self._memory, root_path=self._root or "/")
         base = self._root.rstrip("/") or ""
         new_root = f"{base}/{child}" if base else f"/{child}"
-        return MemoryScope(self._memory, new_root)
+        return MemoryScope(memory=self._memory, root_path=new_root)
 
 
-class MemorySlice:
+class MemorySlice(BaseModel):
     """View over multiple scopes: recall searches all, remember is a no-op when read_only."""
 
-    def __init__(
+    model_config = ConfigDict(arbitrary_types_allowed=True)
-        self,
-        memory: Memory,
-        scopes: list[str],
-        categories: list[str] | None = None,
-        read_only: bool = True,
-    ) -> None:
-        """Initialize slice.
 
-        Args:
+    scopes: list[str] = Field(default_factory=list)
-            memory: The underlying Memory instance.
+    categories: list[str] | None = Field(default=None)
-            scopes: List of scope paths to include.
+    read_only: bool = Field(default=True)
-            categories: Optional category filter for recall.
+
-            read_only: If True, remember() is a silent no-op.
+    _memory: Memory = PrivateAttr()
-        """
+
-        self._memory = memory
+    @model_validator(mode="wrap")
-        self._scopes = [s.rstrip("/") or "/" for s in scopes]
+    @classmethod
-        self._categories = categories
+    def _accept_memory(cls, data: Any, handler: Any) -> MemorySlice:
-        self._read_only = read_only
+        """Extract memory dependency and normalize scopes before validation."""
+        if isinstance(data, MemorySlice):
+            return data
+        memory = data.pop("memory")
+        data["scopes"] = [s.rstrip("/") or "/" for s in data.get("scopes", [])]
+        instance: MemorySlice = handler(data)
+        instance._memory = memory
+        return instance
 
     def remember(
         self,
@@ -178,7 +192,7 @@ class MemorySlice:
         private: bool = False,
     ) -> MemoryRecord | None:
         """Remember into an explicit scope. No-op when read_only=True."""
-        if self._read_only:
+        if self.read_only:
             return None
         return self._memory.remember(
             content,
@@ -196,14 +210,14 @@ class MemorySlice:
         scope: str | None = None,
         categories: list[str] | None = None,
         limit: int = 10,
-        depth: str = "deep",
+        depth: Literal["shallow", "deep"] = "deep",
         source: str | None = None,
         include_private: bool = False,
     ) -> list[MemoryMatch]:
         """Recall across all slice scopes; results merged and re-ranked."""
-        cats = categories or self._categories
+        cats = categories or self.categories
         all_matches: list[MemoryMatch] = []
-        for sc in self._scopes:
+        for sc in self.scopes:
             matches = self._memory.recall(
                 query,
                 scope=sc,
@@ -231,7 +245,7 @@ class MemorySlice:
     def list_scopes(self, path: str = "/") -> list[str]:
         """List scopes across all slice roots."""
         out: list[str] = []
-        for sc in self._scopes:
+        for sc in self.scopes:
             full = f"{sc.rstrip('/')}{path}" if sc != "/" else path
             out.extend(self._memory.list_scopes(full))
         return sorted(set(out))
@@ -243,15 +257,23 @@ class MemorySlice:
         oldest: datetime | None = None
         newest: datetime | None = None
         children: list[str] = []
-        for sc in self._scopes:
+        for sc in self.scopes:
             full = f"{sc.rstrip('/')}{path}" if sc != "/" else path
             inf = self._memory.info(full)
             total_records += inf.record_count
             all_categories.update(inf.categories)
             if inf.oldest_record:
-                oldest = inf.oldest_record if oldest is None else min(oldest, inf.oldest_record)
+                oldest = (
+                    inf.oldest_record
+                    if oldest is None
+                    else min(oldest, inf.oldest_record)
+                )
             if inf.newest_record:
-                newest = inf.newest_record if newest is None else max(newest, inf.newest_record)
+                newest = (
+                    inf.newest_record
+                    if newest is None
+                    else max(newest, inf.newest_record)
+                )
             children.extend(inf.child_scopes)
         return ScopeInfo(
             path=path,
@@ -265,7 +287,7 @@ class MemorySlice:
     def list_categories(self, path: str | None = None) -> dict[str, int]:
         """Categories and counts across slice scopes."""
         counts: dict[str, int] = {}
-        for sc in self._scopes:
+        for sc in self.scopes:
             full = (f"{sc.rstrip('/')}{path}" if sc != "/" else path) if path else sc
             for k, v in self._memory.list_categories(full).items():
                 counts[k] = counts.get(k, 0) + v

lib/crewai/src/crewai/memory/recall_flow.py

@@ -2,7 +2,6 @@
 
 Implements adaptive-depth retrieval with:
 - LLM query distillation into targeted sub-queries
-- Keyword-driven category filtering
 - Time-based filtering from temporal hints
 - Parallel multi-query, multi-scope search
 - Confidence-based routing with iterative deepening (budget loop)
@@ -12,7 +11,9 @@ Implements adaptive-depth retrieval with:
 from __future__ import annotations
 
 from concurrent.futures import ThreadPoolExecutor, as_completed
+import contextvars
 from datetime import datetime
+import logging
 from typing import Any
 from uuid import uuid4
 
@@ -30,6 +31,9 @@ from crewai.memory.types import (
 )
 
 
+logger = logging.getLogger(__name__)
+
+
 class RecallState(BaseModel):
     """State for the recall flow."""
 
@@ -37,7 +41,6 @@ class RecallState(BaseModel):
     query: str = ""
     scope: str | None = None
     categories: list[str] | None = None
-    inferred_categories: list[str] = Field(default_factory=list)
     time_cutoff: datetime | None = None
     source: str | None = None
     include_private: bool = False
@@ -82,11 +85,8 @@ class RecallFlow(Flow[RecallState]):
     # ------------------------------------------------------------------
 
     def _merged_categories(self) -> list[str] | None:
-        """Merge caller-supplied and LLM-inferred categories."""
+        """Return caller-supplied categories, or None if empty."""
-        merged = list(
+        return self.state.categories or None
-            set((self.state.categories or []) + self.state.inferred_categories)
-        )
-        return merged or None
 
     def _do_search(self) -> list[dict[str, Any]]:
         """Run parallel search across (embeddings x scopes) with filters.
@@ -108,13 +108,12 @@ class RecallFlow(Flow[RecallState]):
             )
             # Post-filter by time cutoff
             if self.state.time_cutoff and raw:
-                raw = [
+                raw = [(r, s) for r, s in raw if r.created_at >= self.state.time_cutoff]
-                    (r, s) for r, s in raw if r.created_at >= self.state.time_cutoff
-                ]
             # Privacy filter
             if not self.state.include_private and raw:
                 raw = [
-                    (r, s) for r, s in raw
+                    (r, s)
+                    for r, s in raw
                     if not r.private or r.source == self.state.source
                 ]
             return scope, raw
@@ -130,38 +129,57 @@ class RecallFlow(Flow[RecallState]):
 
         if len(tasks) <= 1:
             for emb, sc in tasks:
-                scope, results = _search_one(emb, sc)
+                try:
+                    scope, results = _search_one(emb, sc)
+                except Exception:
+                    logger.warning(
+                        "Storage search failed in recall flow, skipping scope",
+                        exc_info=True,
+                    )
+                    continue
                 if results:
                     top_composite, _ = compute_composite_score(
                         results[0][0], results[0][1], self._config
                     )
-                    findings.append({
+                    findings.append(
-                        "scope": scope,
+                        {
-                        "results": results,
+                            "scope": scope,
-                        "top_score": top_composite,
+                            "results": results,
-                    })
+                            "top_score": top_composite,
+                        }
+                    )
         else:
             with ThreadPoolExecutor(max_workers=min(len(tasks), 4)) as pool:
                 futures = {
-                    pool.submit(_search_one, emb, sc): (emb, sc)
+                    pool.submit(contextvars.copy_context().run, _search_one, emb, sc): (
+                        emb,
+                        sc,
+                    )
                     for emb, sc in tasks
                 }
                 for future in as_completed(futures):
-                    scope, results = future.result()
+                    try:
+                        scope, results = future.result()
+                    except Exception:
+                        logger.warning(
+                            "Storage search failed in recall flow, skipping scope",
+                            exc_info=True,
+                        )
+                        continue
                     if results:
                         top_composite, _ = compute_composite_score(
                             results[0][0], results[0][1], self._config
                         )
-                        findings.append({
+                        findings.append(
-                            "scope": scope,
+                            {
-                            "results": results,
+                                "scope": scope,
-                            "top_score": top_composite,
+                                "results": results,
-                        })
+                                "top_score": top_composite,
+                            }
+                        )
 
         self.state.chunk_findings = findings
-        self.state.confidence = max(
+        self.state.confidence = max((f["top_score"] for f in findings), default=0.0)
-            (f["top_score"] for f in findings), default=0.0
-        )
         return findings
 
     # ------------------------------------------------------------------
@@ -212,19 +230,19 @@ class RecallFlow(Flow[RecallState]):
             )
             self.state.query_analysis = analysis
 
-            # Wire keywords -> category filter
-            if analysis.keywords:
-                self.state.inferred_categories = analysis.keywords
-
             # Parse time_filter into a datetime cutoff
             if analysis.time_filter:
                 try:
-                    self.state.time_cutoff = datetime.fromisoformat(analysis.time_filter)
+                    self.state.time_cutoff = datetime.fromisoformat(
+                        analysis.time_filter
+                    )
                 except ValueError:
                     pass
 
         # Batch-embed all sub-queries in ONE call
-        queries = analysis.recall_queries if analysis.recall_queries else [self.state.query]
+        queries = (
+            analysis.recall_queries if analysis.recall_queries else [self.state.query]
+        )
         queries = queries[:3]
         embeddings = embed_texts(self._embedder, queries)
         pairs: list[tuple[str, list[float]]] = [
@@ -246,13 +264,17 @@ class RecallFlow(Flow[RecallState]):
         if analysis and analysis.suggested_scopes:
             candidates = [s for s in analysis.suggested_scopes if s]
         else:
-            candidates = self._storage.list_scopes(scope_prefix)
+            try:
+                candidates = self._storage.list_scopes(scope_prefix)
+            except Exception:
+                logger.warning(
+                    "Storage list_scopes failed in filter_and_chunk, "
+                    "falling back to scope prefix",
+                    exc_info=True,
+                )
+                candidates = []
         if not candidates:
-            info = self._storage.get_scope_info(scope_prefix)
+            candidates = [scope_prefix]
-            if info.record_count > 0:
-                candidates = [scope_prefix]
-            else:
-                candidates = [scope_prefix]
         self.state.candidate_scopes = candidates[:20]
         return self.state.candidate_scopes
 
@@ -305,17 +327,21 @@ class RecallFlow(Flow[RecallState]):
                 response = self._llm.call([{"role": "user", "content": prompt}])
                 if isinstance(response, str) and "missing" in response.lower():
                     self.state.evidence_gaps.append(response[:200])
-                enhanced.append({
+                enhanced.append(
-                    "scope": finding["scope"],
+                    {
-                    "extraction": response,
+                        "scope": finding["scope"],
-                    "results": finding["results"],
+                        "extraction": response,
-                })
+                        "results": finding["results"],
+                    }
+                )
             except Exception:
-                enhanced.append({
+                enhanced.append(
-                    "scope": finding["scope"],
+                    {
-                    "extraction": "",
+                        "scope": finding["scope"],
-                    "results": finding["results"],
+                        "extraction": "",
-                })
+                        "results": finding["results"],
+                    }
+                )
         self.state.chunk_findings = enhanced
         return enhanced
 
@@ -327,7 +353,7 @@ class RecallFlow(Flow[RecallState]):
     @router(re_search)
     def re_decide_depth(self) -> str:
         """Re-evaluate depth after re-search. Same logic as decide_depth."""
-        return self.decide_depth()
+        return self.decide_depth()  # type: ignore[call-arg]
 
     @listen("synthesize")
     def synthesize_results(self) -> list[MemoryMatch]:

lib/crewai/src/crewai/memory/storage/kickoff_task_outputs_storage.py

@@ -1,5 +1,6 @@
 import json
 import logging
+import os
 from pathlib import Path
 import sqlite3
 from typing import Any
@@ -8,6 +9,7 @@ from crewai.task import Task
 from crewai.utilities import Printer
 from crewai.utilities.crew_json_encoder import CrewJSONEncoder
 from crewai.utilities.errors import DatabaseError, DatabaseOperationError
+from crewai.utilities.lock_store import lock as store_lock
 from crewai.utilities.paths import db_storage_path
 
 
@@ -24,6 +26,7 @@ class KickoffTaskOutputsSQLiteStorage:
             # Get the parent directory of the default db path and create our db file there
             db_path = str(Path(db_storage_path()) / "latest_kickoff_task_outputs.db")
         self.db_path = db_path
+        self._lock_name = f"sqlite:{os.path.realpath(self.db_path)}"
         self._printer: Printer = Printer()
         self._initialize_db()
 
@@ -38,23 +41,25 @@ class KickoffTaskOutputsSQLiteStorage:
             DatabaseOperationError: If database initialization fails due to SQLite errors.
         """
         try:
-            with sqlite3.connect(self.db_path) as conn:
+            with store_lock(self._lock_name):
-                cursor = conn.cursor()
+                with sqlite3.connect(self.db_path, timeout=30) as conn:
-                cursor.execute(
+                    conn.execute("PRAGMA journal_mode=WAL")
+                    cursor = conn.cursor()
+                    cursor.execute(
+                        """
+                        CREATE TABLE IF NOT EXISTS latest_kickoff_task_outputs (
+                            task_id TEXT PRIMARY KEY,
+                            expected_output TEXT,
+                            output JSON,
+                            task_index INTEGER,
+                            inputs JSON,
+                            was_replayed BOOLEAN,
+                            timestamp DATETIME DEFAULT CURRENT_TIMESTAMP
+                        )
                     """
-                    CREATE TABLE IF NOT EXISTS latest_kickoff_task_outputs (
-                        task_id TEXT PRIMARY KEY,
-                        expected_output TEXT,
-                        output JSON,
-                        task_index INTEGER,
-                        inputs JSON,
-                        was_replayed BOOLEAN,
-                        timestamp DATETIME DEFAULT CURRENT_TIMESTAMP
                     )
-                """
-                )
 
-                conn.commit()
+                    conn.commit()
         except sqlite3.Error as e:
             error_msg = DatabaseError.format_error(DatabaseError.INIT_ERROR, e)
             logger.error(error_msg)
@@ -82,25 +87,26 @@ class KickoffTaskOutputsSQLiteStorage:
         """
         inputs = inputs or {}
         try:
-            with sqlite3.connect(self.db_path) as conn:
+            with store_lock(self._lock_name):
-                conn.execute("BEGIN TRANSACTION")
+                with sqlite3.connect(self.db_path, timeout=30) as conn:
-                cursor = conn.cursor()
+                    conn.execute("BEGIN TRANSACTION")
-                cursor.execute(
+                    cursor = conn.cursor()
-                    """
+                    cursor.execute(
-                INSERT OR REPLACE INTO latest_kickoff_task_outputs
+                        """
-                (task_id, expected_output, output, task_index, inputs, was_replayed)
+                    INSERT OR REPLACE INTO latest_kickoff_task_outputs
-                VALUES (?, ?, ?, ?, ?, ?)
+                    (task_id, expected_output, output, task_index, inputs, was_replayed)
-            """,
+                    VALUES (?, ?, ?, ?, ?, ?)
-                    (
+                """,
-                        str(task.id),
+                        (
-                        task.expected_output,
+                            str(task.id),
-                        json.dumps(output, cls=CrewJSONEncoder),
+                            task.expected_output,
-                        task_index,
+                            json.dumps(output, cls=CrewJSONEncoder),
-                        json.dumps(inputs, cls=CrewJSONEncoder),
+                            task_index,
-                        was_replayed,
+                            json.dumps(inputs, cls=CrewJSONEncoder),
-                    ),
+                            was_replayed,
-                )
+                        ),
-                conn.commit()
+                    )
+                    conn.commit()
         except sqlite3.Error as e:
             error_msg = DatabaseError.format_error(DatabaseError.SAVE_ERROR, e)
             logger.error(error_msg)
@@ -125,30 +131,31 @@ class KickoffTaskOutputsSQLiteStorage:
             DatabaseOperationError: If updating the task output fails due to SQLite errors.
         """
         try:
-            with sqlite3.connect(self.db_path) as conn:
+            with store_lock(self._lock_name):
-                conn.execute("BEGIN TRANSACTION")
+                with sqlite3.connect(self.db_path, timeout=30) as conn:
-                cursor = conn.cursor()
+                    conn.execute("BEGIN TRANSACTION")
+                    cursor = conn.cursor()
 
-                fields = []
+                    fields = []
-                values = []
+                    values = []
-                for key, value in kwargs.items():
+                    for key, value in kwargs.items():
-                    fields.append(f"{key} = ?")
+                        fields.append(f"{key} = ?")
-                    values.append(
+                        values.append(
-                        json.dumps(value, cls=CrewJSONEncoder)
+                            json.dumps(value, cls=CrewJSONEncoder)
-                        if isinstance(value, dict)
+                            if isinstance(value, dict)
-                        else value
+                            else value
-                    )
+                        )
 
-                query = f"UPDATE latest_kickoff_task_outputs SET {', '.join(fields)} WHERE task_index = ?"  # nosec # noqa: S608
+                    query = f"UPDATE latest_kickoff_task_outputs SET {', '.join(fields)} WHERE task_index = ?"  # nosec # noqa: S608
-                values.append(task_index)
+                    values.append(task_index)
 
-                cursor.execute(query, tuple(values))
+                    cursor.execute(query, tuple(values))
-                conn.commit()
+                    conn.commit()
 
-                if cursor.rowcount == 0:
+                    if cursor.rowcount == 0:
-                    logger.warning(
+                        logger.warning(
-                        f"No row found with task_index {task_index}. No update performed."
+                            f"No row found with task_index {task_index}. No update performed."
-                    )
+                        )
         except sqlite3.Error as e:
             error_msg = DatabaseError.format_error(DatabaseError.UPDATE_ERROR, e)
             logger.error(error_msg)
@@ -166,7 +173,7 @@ class KickoffTaskOutputsSQLiteStorage:
             DatabaseOperationError: If loading task outputs fails due to SQLite errors.
         """
         try:
-            with sqlite3.connect(self.db_path) as conn:
+            with sqlite3.connect(self.db_path, timeout=30) as conn:
                 cursor = conn.cursor()
                 cursor.execute("""
                 SELECT *
@@ -205,11 +212,12 @@ class KickoffTaskOutputsSQLiteStorage:
             DatabaseOperationError: If deleting task outputs fails due to SQLite errors.
         """
         try:
-            with sqlite3.connect(self.db_path) as conn:
+            with store_lock(self._lock_name):
-                conn.execute("BEGIN TRANSACTION")
+                with sqlite3.connect(self.db_path, timeout=30) as conn:
-                cursor = conn.cursor()
+                    conn.execute("BEGIN TRANSACTION")
-                cursor.execute("DELETE FROM latest_kickoff_task_outputs")
+                    cursor = conn.cursor()
-                conn.commit()
+                    cursor.execute("DELETE FROM latest_kickoff_task_outputs")
+                    conn.commit()
         except sqlite3.Error as e:
             error_msg = DatabaseError.format_error(DatabaseError.DELETE_ERROR, e)
             logger.error(error_msg)

lib/crewai/src/crewai/memory/storage/lancedb_storage.py

@@ -2,6 +2,7 @@
 
 from __future__ import annotations
 
+import contextvars
 from datetime import datetime
 import json
 import logging
@@ -9,11 +10,12 @@ import os
 from pathlib import Path
 import threading
 import time
-from typing import Any, ClassVar
+from typing import Any
 
-import lancedb
+import lancedb  # type: ignore[import-untyped]
 
 from crewai.memory.types import MemoryRecord, ScopeInfo
+from crewai.utilities.lock_store import lock as store_lock
 
 
 _logger = logging.getLogger(__name__)
@@ -39,15 +41,6 @@ _RETRY_BASE_DELAY = 0.2  # seconds; doubles on each retry
 class LanceDBStorage:
     """LanceDB-backed storage for the unified memory system."""
 
-    # Class-level registry: maps resolved database path -> shared write lock.
-    # When multiple Memory instances (e.g. agent + crew) independently create
-    # LanceDBStorage pointing at the same directory, they share one lock so
-    # their writes don't conflict.
-    # Uses RLock (reentrant) so callers can hold the lock for a batch of
-    # operations while the individual methods re-acquire it without deadlocking.
-    _path_locks: ClassVar[dict[str, threading.RLock]] = {}
-    _path_locks_guard: ClassVar[threading.Lock] = threading.Lock()
-
     def __init__(
         self,
         path: str | Path | None = None,
@@ -83,13 +76,9 @@ class LanceDBStorage:
         self._table_name = table_name
         self._db = lancedb.connect(str(self._path))
 
-        # On macOS and Linux the default per-process open-file limit is 256.
-        # A LanceDB table stores one file per fragment (one fragment per save()
-        # call by default).  With hundreds of fragments, a single full-table
-        # scan opens all of them simultaneously, exhausting the limit.
-        # Raise it proactively so scans on large tables never hit OS error 24.
         try:
             import resource
+
             soft, hard = resource.getrlimit(resource.RLIMIT_NOFILE)
             if soft < 4096:
                 resource.setrlimit(resource.RLIMIT_NOFILE, (min(hard, 4096), hard))
@@ -99,68 +88,46 @@ class LanceDBStorage:
         self._compact_every = compact_every
         self._save_count = 0
 
-        # Get or create a shared write lock for this database path.
+        self._lock_name = f"lancedb:{self._path.resolve()}"
-        resolved = str(self._path.resolve())
-        with LanceDBStorage._path_locks_guard:
-            if resolved not in LanceDBStorage._path_locks:
-                LanceDBStorage._path_locks[resolved] = threading.RLock()
-            self._write_lock = LanceDBStorage._path_locks[resolved]
 
         # Try to open an existing table and infer dimension from its schema.
         # If no table exists yet, defer creation until the first save so the
         # dimension can be auto-detected from the embedder's actual output.
         try:
-            self._table: lancedb.table.Table | None = self._db.open_table(self._table_name)
+            self._table: Any = self._db.open_table(self._table_name)
             self._vector_dim: int = self._infer_dim_from_table(self._table)
-            # Best-effort: create the scope index if it doesn't exist yet.
+            with store_lock(self._lock_name):
-            self._ensure_scope_index()
+                self._ensure_scope_index()
-            # Compact in the background if the table has accumulated many
-            # fragments from previous runs (each save() creates one).
             self._compact_if_needed()
         except Exception:
+            _logger.debug(
+                "Failed to open existing LanceDB table %r", table_name, exc_info=True
+            )
             self._table = None
             self._vector_dim = vector_dim or 0  # 0 = not yet known
 
         # Explicit dim provided: create the table immediately if it doesn't exist.
         if self._table is None and vector_dim is not None:
             self._vector_dim = vector_dim
-            self._table = self._create_table(vector_dim)
+            with store_lock(self._lock_name):
-
+                self._table = self._create_table(vector_dim)
-    @property
-    def write_lock(self) -> threading.RLock:
-        """The shared reentrant write lock for this database path.
-
-        Callers can acquire this to hold the lock across multiple storage
-        operations (e.g. delete + update + save as one atomic batch).
-        Individual methods also acquire it internally, but since it's
-        reentrant (RLock), the same thread won't deadlock.
-        """
-        return self._write_lock
 
     @staticmethod
-    def _infer_dim_from_table(table: lancedb.table.Table) -> int:
+    def _infer_dim_from_table(table: Any) -> int:
         """Read vector dimension from an existing table's schema."""
         schema = table.schema
         for field in schema:
             if field.name == "vector":
                 try:
-                    return field.type.list_size
+                    return int(field.type.list_size)
                 except Exception:
                     break
         return DEFAULT_VECTOR_DIM
 
-    def _retry_write(self, op: str, *args: Any, **kwargs: Any) -> Any:
+    def _do_write(self, op: str, *args: Any, **kwargs: Any) -> Any:
-        """Execute a table operation with retry on LanceDB commit conflicts.
+        """Execute a single table write with retry on commit conflicts.
 
-        Args:
+        Caller must already hold ``store_lock(self._lock_name)``.
-            op: Method name on the table object (e.g. "add", "delete").
-            *args, **kwargs: Passed to the table method.
-
-        LanceDB uses optimistic concurrency: if two transactions overlap,
-        the second to commit fails with an ``OSError`` containing
-        "Commit conflict". This helper retries with exponential backoff,
-        refreshing the table reference before each retry so the retried
-        call uses the latest committed version (not a stale reference).
         """
         delay = _RETRY_BASE_DELAY
         for attempt in range(_MAX_RETRIES + 1):
@@ -171,20 +138,24 @@ class LanceDBStorage:
                     raise
                 _logger.debug(
                     "LanceDB commit conflict on %s (attempt %d/%d), retrying in %.1fs",
-                    op, attempt + 1, _MAX_RETRIES, delay,
+                    op,
+                    attempt + 1,
+                    _MAX_RETRIES,
+                    delay,
                 )
-                # Refresh table to pick up the latest version before retrying.
-                # The next getattr(self._table, op) will use the fresh table.
                 try:
                     self._table = self._db.open_table(self._table_name)
-                except Exception:  # noqa: S110
+                except Exception:
-                    pass  # table refresh is best-effort
+                    _logger.debug("Failed to re-open table during retry", exc_info=True)
                 time.sleep(delay)
                 delay *= 2
         return None  # unreachable, but satisfies type checker
 
-    def _create_table(self, vector_dim: int) -> lancedb.table.Table:
+    def _create_table(self, vector_dim: int) -> Any:
-        """Create a new table with the given vector dimension."""
+        """Create a new table with the given vector dimension.
+
+        Caller must already hold ``store_lock(self._lock_name)``.
+        """
         placeholder = [
             {
                 "id": "__schema_placeholder__",
@@ -200,8 +171,12 @@ class LanceDBStorage:
                 "vector": [0.0] * vector_dim,
             }
         ]
-        table = self._db.create_table(self._table_name, placeholder)
+        try:
-        table.delete("id = '__schema_placeholder__'")
+            table = self._db.create_table(self._table_name, placeholder)
+        except ValueError:
+            table = self._db.open_table(self._table_name)
+        else:
+            table.delete("id = '__schema_placeholder__'")
         return table
 
     def _ensure_scope_index(self) -> None:
@@ -217,8 +192,10 @@ class LanceDBStorage:
             return
         try:
             self._table.create_scalar_index("scope", index_type="BTREE", replace=False)
-        except Exception:  # noqa: S110
+        except Exception:
-            pass  # index already exists, table empty, or unsupported version
+            _logger.debug(
+                "Scope index creation skipped (may already exist)", exc_info=True
+            )
 
     # ------------------------------------------------------------------
     # Automatic background compaction
@@ -238,8 +215,10 @@ class LanceDBStorage:
 
     def _compact_async(self) -> None:
         """Fire-and-forget: compact the table in a daemon background thread."""
+        ctx = contextvars.copy_context()
         threading.Thread(
-            target=self._compact_safe,
+            target=ctx.run,
+            args=(self._compact_safe,),
             daemon=True,
             name="lancedb-compact",
         ).start()
@@ -248,13 +227,13 @@ class LanceDBStorage:
         """Run ``table.optimize()`` in a background thread, absorbing errors."""
         try:
             if self._table is not None:
-                self._table.optimize()
+                with store_lock(self._lock_name):
-                # Refresh the scope index so new fragments are covered.
+                    self._table.optimize()
-                self._ensure_scope_index()
+                    self._ensure_scope_index()
         except Exception:
             _logger.debug("LanceDB background compaction failed", exc_info=True)
 
-    def _ensure_table(self, vector_dim: int | None = None) -> lancedb.table.Table:
+    def _ensure_table(self, vector_dim: int | None = None) -> Any:
         """Return the table, creating it lazily if needed.
 
         Args:
@@ -280,7 +259,9 @@ class LanceDBStorage:
             "last_accessed": record.last_accessed.isoformat(),
             "source": record.source or "",
             "private": record.private,
-            "vector": record.embedding if record.embedding else [0.0] * self._vector_dim,
+            "vector": record.embedding
+            if record.embedding
+            else [0.0] * self._vector_dim,
         }
 
     def _row_to_record(self, row: dict[str, Any]) -> MemoryRecord:
@@ -296,7 +277,9 @@ class LanceDBStorage:
             id=str(row["id"]),
             content=str(row["content"]),
             scope=str(row["scope"]),
-            categories=json.loads(row["categories_str"]) if row.get("categories_str") else [],
+            categories=json.loads(row["categories_str"])
+            if row.get("categories_str")
+            else [],
             metadata=json.loads(row["metadata_str"]) if row.get("metadata_str") else {},
             importance=float(row.get("importance", 0.5)),
             created_at=_parse_dt(row.get("created_at")),
@@ -316,16 +299,15 @@ class LanceDBStorage:
                 dim = len(r.embedding)
                 break
         is_new_table = self._table is None
-        with self._write_lock:
+        with store_lock(self._lock_name):
             self._ensure_table(vector_dim=dim)
-            rows = [self._record_to_row(r) for r in records]
+            rows = [self._record_to_row(rec) for rec in records]
-            for r in rows:
+            for row in rows:
-                if r["vector"] is None or len(r["vector"]) != self._vector_dim:
+                if row["vector"] is None or len(row["vector"]) != self._vector_dim:
-                    r["vector"] = [0.0] * self._vector_dim
+                    row["vector"] = [0.0] * self._vector_dim
-            self._retry_write("add", rows)
+            self._do_write("add", rows)
-        # Create the scope index on the first save so it covers the initial dataset.
+            if is_new_table:
-        if is_new_table:
+                self._ensure_scope_index()
-            self._ensure_scope_index()
         # Auto-compact every N saves so fragment files don't pile up.
         self._save_count += 1
         if self._compact_every > 0 and self._save_count % self._compact_every == 0:
@@ -333,14 +315,14 @@ class LanceDBStorage:
 
     def update(self, record: MemoryRecord) -> None:
         """Update a record by ID. Preserves created_at, updates last_accessed."""
-        with self._write_lock:
+        with store_lock(self._lock_name):
             self._ensure_table()
             safe_id = str(record.id).replace("'", "''")
-            self._retry_write("delete", f"id = '{safe_id}'")
+            self._do_write("delete", f"id = '{safe_id}'")
             row = self._record_to_row(record)
             if row["vector"] is None or len(row["vector"]) != self._vector_dim:
                 row["vector"] = [0.0] * self._vector_dim
-            self._retry_write("add", [row])
+            self._do_write("add", [row])
 
     def touch_records(self, record_ids: list[str]) -> None:
         """Update last_accessed to now for the given record IDs.
@@ -354,11 +336,11 @@ class LanceDBStorage:
         """
         if not record_ids or self._table is None:
             return
-        with self._write_lock:
+        with store_lock(self._lock_name):
             now = datetime.utcnow().isoformat()
             safe_ids = [str(rid).replace("'", "''") for rid in record_ids]
             ids_expr = ", ".join(f"'{rid}'" for rid in safe_ids)
-            self._retry_write(
+            self._do_write(
                 "update",
                 where=f"id IN ({ids_expr})",
                 values={"last_accessed": now},
@@ -390,13 +372,17 @@ class LanceDBStorage:
             prefix = scope_prefix.rstrip("/")
             like_val = prefix + "%"
             query = query.where(f"scope LIKE '{like_val}'")
-        results = query.limit(limit * 3 if (categories or metadata_filter) else limit).to_list()
+        results = query.limit(
+            limit * 3 if (categories or metadata_filter) else limit
+        ).to_list()
         out: list[tuple[MemoryRecord, float]] = []
         for row in results:
             record = self._row_to_record(row)
             if categories and not any(c in record.categories for c in categories):
                 continue
-            if metadata_filter and not all(record.metadata.get(k) == v for k, v in metadata_filter.items()):
+            if metadata_filter and not all(
+                record.metadata.get(k) == v for k, v in metadata_filter.items()
+            ):
                 continue
             distance = row.get("_distance", 0.0)
             score = 1.0 / (1.0 + float(distance)) if distance is not None else 1.0
@@ -416,30 +402,34 @@ class LanceDBStorage:
     ) -> int:
         if self._table is None:
             return 0
-        with self._write_lock:
+        with store_lock(self._lock_name):
             if record_ids and not (categories or metadata_filter):
-                before = self._table.count_rows()
+                before = int(self._table.count_rows())
                 ids_expr = ", ".join(f"'{rid}'" for rid in record_ids)
-                self._retry_write("delete", f"id IN ({ids_expr})")
+                self._do_write("delete", f"id IN ({ids_expr})")
-                return before - self._table.count_rows()
+                return before - int(self._table.count_rows())
             if categories or metadata_filter:
                 rows = self._scan_rows(scope_prefix)
                 to_delete: list[str] = []
                 for row in rows:
                     record = self._row_to_record(row)
-                    if categories and not any(c in record.categories for c in categories):
+                    if categories and not any(
+                        c in record.categories for c in categories
+                    ):
                         continue
-                    if metadata_filter and not all(record.metadata.get(k) == v for k, v in metadata_filter.items()):
+                    if metadata_filter and not all(
+                        record.metadata.get(k) == v for k, v in metadata_filter.items()
+                    ):
                         continue
                     if older_than and record.created_at >= older_than:
                         continue
                     to_delete.append(record.id)
                 if not to_delete:
                     return 0
-                before = self._table.count_rows()
+                before = int(self._table.count_rows())
                 ids_expr = ", ".join(f"'{rid}'" for rid in to_delete)
-                self._retry_write("delete", f"id IN ({ids_expr})")
+                self._do_write("delete", f"id IN ({ids_expr})")
-                return before - self._table.count_rows()
+                return before - int(self._table.count_rows())
             conditions = []
             if scope_prefix is not None and scope_prefix.strip("/"):
                 prefix = scope_prefix.rstrip("/")
@@ -449,13 +439,13 @@ class LanceDBStorage:
             if older_than is not None:
                 conditions.append(f"created_at < '{older_than.isoformat()}'")
             if not conditions:
-                before = self._table.count_rows()
+                before = int(self._table.count_rows())
-                self._retry_write("delete", "id != ''")
+                self._do_write("delete", "id != ''")
-                return before - self._table.count_rows()
+                return before - int(self._table.count_rows())
             where_expr = " AND ".join(conditions)
-            before = self._table.count_rows()
+            before = int(self._table.count_rows())
-            self._retry_write("delete", where_expr)
+            self._do_write("delete", where_expr)
-            return before - self._table.count_rows()
+            return before - int(self._table.count_rows())
 
     def _scan_rows(
         self,
@@ -482,7 +472,8 @@ class LanceDBStorage:
             q = q.where(f"scope LIKE '{scope_prefix.rstrip('/')}%'")
         if columns is not None:
             q = q.select(columns)
-        return q.limit(limit).to_list()
+        result: list[dict[str, Any]] = q.limit(limit).to_list()
+        return result
 
     def list_records(
         self, scope_prefix: str | None = None, limit: int = 200, offset: int = 0
@@ -528,7 +519,7 @@ class LanceDBStorage:
         for row in rows:
             sc = str(row.get("scope", ""))
             if child_prefix and sc.startswith(child_prefix):
-                rest = sc[len(child_prefix):]
+                rest = sc[len(child_prefix) :]
                 first_component = rest.split("/", 1)[0]
                 if first_component:
                     children.add(child_prefix + first_component)
@@ -539,7 +530,11 @@ class LanceDBStorage:
                 pass
             created = row.get("created_at")
             if created:
-                dt = datetime.fromisoformat(str(created).replace("Z", "+00:00")) if isinstance(created, str) else created
+                dt = (
+                    datetime.fromisoformat(str(created).replace("Z", "+00:00"))
+                    if isinstance(created, str)
+                    else created
+                )
                 if isinstance(dt, datetime):
                     if oldest is None or dt < oldest:
                         oldest = dt
@@ -562,7 +557,7 @@ class LanceDBStorage:
         for row in rows:
             sc = str(row.get("scope", ""))
             if sc.startswith(prefix) and sc != (prefix.rstrip("/") or "/"):
-                rest = sc[len(prefix):]
+                rest = sc[len(prefix) :]
                 first_component = rest.split("/", 1)[0]
                 if first_component:
                     children.add(prefix + first_component)
@@ -585,22 +580,24 @@ class LanceDBStorage:
         if self._table is None:
             return 0
         if scope_prefix is None or scope_prefix.strip("/") == "":
-            return self._table.count_rows()
+            return int(self._table.count_rows())
         info = self.get_scope_info(scope_prefix)
         return info.record_count
 
     def reset(self, scope_prefix: str | None = None) -> None:
-        if scope_prefix is None or scope_prefix.strip("/") == "":
+        with store_lock(self._lock_name):
-            if self._table is not None:
+            if scope_prefix is None or scope_prefix.strip("/") == "":
-                self._db.drop_table(self._table_name)
+                if self._table is not None:
-            self._table = None
+                    self._db.drop_table(self._table_name)
-            # Dimension is preserved; table will be recreated on next save.
+                self._table = None
-            return
+                return
-        if self._table is None:
+            if self._table is None:
-            return
+                return
-        prefix = scope_prefix.rstrip("/")
+            prefix = scope_prefix.rstrip("/")
-        if prefix:
+            if prefix:
-            self._table.delete(f"scope >= '{prefix}' AND scope < '{prefix}/\uFFFF'")
+                self._do_write(
+                    "delete", f"scope >= '{prefix}' AND scope < '{prefix}/\uffff'"
+                )
 
     def optimize(self) -> None:
         """Compact the table synchronously and refresh the scope index.
@@ -614,8 +611,9 @@ class LanceDBStorage:
         """
         if self._table is None:
             return
-        self._table.optimize()
+        with store_lock(self._lock_name):
-        self._ensure_scope_index()
+            self._table.optimize()
+            self._ensure_scope_index()
 
     async def asave(self, records: list[MemoryRecord]) -> None:
         self.save(records)

lib/crewai/src/crewai/memory/unified_memory.py

@@ -3,10 +3,13 @@
 from __future__ import annotations
 
 from concurrent.futures import Future, ThreadPoolExecutor
+import contextvars
 from datetime import datetime
 import threading
 import time
-from typing import TYPE_CHECKING, Any, Literal
+from typing import TYPE_CHECKING, Annotated, Any, Literal
+
+from pydantic import BaseModel, ConfigDict, Field, PlainValidator, PrivateAttr
 
 from crewai.events.event_bus import crewai_event_bus
 from crewai.events.types.memory_events import (
@@ -39,13 +42,18 @@ if TYPE_CHECKING:
     )
 
 
+def _passthrough(v: Any) -> Any:
+    """PlainValidator that accepts any value, bypassing strict union discrimination."""
+    return v
+
+
 def _default_embedder() -> OpenAIEmbeddingFunction:
     """Build default OpenAI embedder for memory."""
     spec: OpenAIProviderSpec = {"provider": "openai", "config": {}}
     return build_embedder(spec)
 
 
-class Memory:
+class Memory(BaseModel):
     """Unified memory: standalone, LLM-analyzed, with intelligent recall flow.
 
     Works without agent/crew. Uses LLM to infer scope, categories, importance on save.
@@ -53,116 +61,119 @@ class Memory:
     pluggable storage (LanceDB default).
     """
 
-    def __init__(
+    model_config = ConfigDict(arbitrary_types_allowed=True)
-        self,
-        llm: BaseLLM | str = "gpt-4o-mini",
-        storage: StorageBackend | str = "lancedb",
-        embedder: Any = None,
-        # -- Scoring weights --
-        # These three weights control how recall results are ranked.
-        # The composite score is: semantic_weight * similarity + recency_weight * decay + importance_weight * importance.
-        # They should sum to ~1.0 for intuitive scoring.
-        recency_weight: float = 0.3,
-        semantic_weight: float = 0.5,
-        importance_weight: float = 0.2,
-        # How quickly old memories lose relevance. The recency score halves every
-        # N days (exponential decay). Lower = faster forgetting; higher = longer relevance.
-        recency_half_life_days: int = 30,
-        # -- Consolidation --
-        # When remembering new content, if an existing record has similarity >= this
-        # threshold, the LLM is asked to merge/update/delete. Set to 1.0 to disable.
-        consolidation_threshold: float = 0.85,
-        # Max existing records to compare against when checking for consolidation.
-        consolidation_limit: int = 5,
-        # -- Save defaults --
-        # Importance assigned to new memories when no explicit value is given and
-        # the LLM analysis path is skipped (all fields provided by the caller).
-        default_importance: float = 0.5,
-        # -- Recall depth control --
-        # These thresholds govern the RecallFlow router that decides between
-        # returning results immediately ("synthesize") vs. doing an extra
-        # LLM-driven exploration round ("explore_deeper").
-        #   confidence >= confidence_threshold_high  => always synthesize
-        #   confidence <  confidence_threshold_low   => explore deeper (if budget > 0)
-        #   complex query + confidence < complex_query_threshold => explore deeper
-        confidence_threshold_high: float = 0.8,
-        confidence_threshold_low: float = 0.5,
-        complex_query_threshold: float = 0.7,
-        # How many LLM-driven exploration rounds the RecallFlow is allowed to run.
-        # 0 = always shallow (vector search only); higher = more thorough but slower.
-        exploration_budget: int = 1,
-        # Queries shorter than this skip LLM analysis (saving ~1-3s).
-        # Longer queries (full task descriptions) benefit from LLM distillation.
-        query_analysis_threshold: int = 200,
-        # When True, all write operations (remember, remember_many) are silently
-        # skipped. Useful for sharing a read-only view of memory across agents
-        # without any of them persisting new memories.
-        read_only: bool = False,
-    ) -> None:
-        """Initialize Memory.
 
-        Args:
+    llm: Annotated[BaseLLM | str, PlainValidator(_passthrough)] = Field(
-            llm: LLM for analysis (model name or BaseLLM instance).
+        default="gpt-4o-mini",
-            storage: Backend: "lancedb" or a StorageBackend instance.
+        description="LLM for analysis (model name or BaseLLM instance).",
-            embedder: Embedding callable, provider config dict, or None (default OpenAI).
+    )
-            recency_weight: Weight for recency in the composite relevance score.
+    storage: Annotated[StorageBackend | str, PlainValidator(_passthrough)] = Field(
-            semantic_weight: Weight for semantic similarity in the composite relevance score.
+        default="lancedb",
-            importance_weight: Weight for importance in the composite relevance score.
+        description="Storage backend instance or path string.",
-            recency_half_life_days: Recency score halves every N days (exponential decay).
+    )
-            consolidation_threshold: Similarity above which consolidation is triggered on save.
+    embedder: Any = Field(
-            consolidation_limit: Max existing records to compare during consolidation.
+        default=None,
-            default_importance: Default importance when not provided or inferred.
+        description="Embedding callable, provider config dict, or None for default OpenAI.",
-            confidence_threshold_high: Recall confidence above which results are returned directly.
+    )
-            confidence_threshold_low: Recall confidence below which deeper exploration is triggered.
+    recency_weight: float = Field(
-            complex_query_threshold: For complex queries, explore deeper below this confidence.
+        default=0.3,
-            exploration_budget: Number of LLM-driven exploration rounds during deep recall.
+        description="Weight for recency in the composite relevance score.",
-            query_analysis_threshold: Queries shorter than this skip LLM analysis during deep recall.
+    )
-            read_only: If True, remember() and remember_many() are silent no-ops.
+    semantic_weight: float = Field(
-        """
+        default=0.5,
-        self._read_only = read_only
+        description="Weight for semantic similarity in the composite relevance score.",
+    )
+    importance_weight: float = Field(
+        default=0.2,
+        description="Weight for importance in the composite relevance score.",
+    )
+    recency_half_life_days: int = Field(
+        default=30,
+        description="Recency score halves every N days (exponential decay).",
+    )
+    consolidation_threshold: float = Field(
+        default=0.85,
+        description="Similarity above which consolidation is triggered on save.",
+    )
+    consolidation_limit: int = Field(
+        default=5,
+        description="Max existing records to compare during consolidation.",
+    )
+    default_importance: float = Field(
+        default=0.5,
+        description="Default importance when not provided or inferred.",
+    )
+    confidence_threshold_high: float = Field(
+        default=0.8,
+        description="Recall confidence above which results are returned directly.",
+    )
+    confidence_threshold_low: float = Field(
+        default=0.5,
+        description="Recall confidence below which deeper exploration is triggered.",
+    )
+    complex_query_threshold: float = Field(
+        default=0.7,
+        description="For complex queries, explore deeper below this confidence.",
+    )
+    exploration_budget: int = Field(
+        default=1,
+        description="Number of LLM-driven exploration rounds during deep recall.",
+    )
+    query_analysis_threshold: int = Field(
+        default=200,
+        description="Queries shorter than this skip LLM analysis during deep recall.",
+    )
+    read_only: bool = Field(
+        default=False,
+        description="If True, remember() and remember_many() are silent no-ops.",
+    )
+
+    _config: MemoryConfig = PrivateAttr()
+    _llm_instance: BaseLLM | None = PrivateAttr(default=None)
+    _embedder_instance: Any = PrivateAttr(default=None)
+    _storage: StorageBackend = PrivateAttr()
+    _save_pool: ThreadPoolExecutor = PrivateAttr(
+        default_factory=lambda: ThreadPoolExecutor(
+            max_workers=1, thread_name_prefix="memory-save"
+        )
+    )
+    _pending_saves: list[Future[Any]] = PrivateAttr(default_factory=list)
+    _pending_lock: threading.Lock = PrivateAttr(default_factory=threading.Lock)
+
+    def model_post_init(self, __context: Any) -> None:
+        """Initialize runtime state from field values."""
         self._config = MemoryConfig(
-            recency_weight=recency_weight,
+            recency_weight=self.recency_weight,
-            semantic_weight=semantic_weight,
+            semantic_weight=self.semantic_weight,
-            importance_weight=importance_weight,
+            importance_weight=self.importance_weight,
-            recency_half_life_days=recency_half_life_days,
+            recency_half_life_days=self.recency_half_life_days,
-            consolidation_threshold=consolidation_threshold,
+            consolidation_threshold=self.consolidation_threshold,
-            consolidation_limit=consolidation_limit,
+            consolidation_limit=self.consolidation_limit,
-            default_importance=default_importance,
+            default_importance=self.default_importance,
-            confidence_threshold_high=confidence_threshold_high,
+            confidence_threshold_high=self.confidence_threshold_high,
-            confidence_threshold_low=confidence_threshold_low,
+            confidence_threshold_low=self.confidence_threshold_low,
-            complex_query_threshold=complex_query_threshold,
+            complex_query_threshold=self.complex_query_threshold,
-            exploration_budget=exploration_budget,
+            exploration_budget=self.exploration_budget,
-            query_analysis_threshold=query_analysis_threshold,
+            query_analysis_threshold=self.query_analysis_threshold,
         )
 
-        # Store raw config for lazy initialization. LLM and embedder are only
+        self._llm_instance = None if isinstance(self.llm, str) else self.llm
-        # built on first access so that Memory() never fails at construction
+        self._embedder_instance = (
-        # time (e.g. when auto-created by Flow without an API key set).
+            self.embedder
-        self._llm_config: BaseLLM | str = llm
+            if (self.embedder is not None and not isinstance(self.embedder, dict))
-        self._llm_instance: BaseLLM | None = None if isinstance(llm, str) else llm
-        self._embedder_config: Any = embedder
-        self._embedder_instance: Any = (
-            embedder
-            if (embedder is not None and not isinstance(embedder, dict))
             else None
         )
 
-        if isinstance(storage, str):
+        if isinstance(self.storage, str):
             from crewai.memory.storage.lancedb_storage import LanceDBStorage
 
-            self._storage = LanceDBStorage() if storage == "lancedb" else LanceDBStorage(path=storage)
+            self._storage = (
+                LanceDBStorage()
+                if self.storage == "lancedb"
+                else LanceDBStorage(path=self.storage)
+            )
         else:
-            self._storage = storage
+            self._storage = self.storage
-
-        # Background save queue. max_workers=1 serializes saves to avoid
-        # concurrent storage mutations (two saves finding the same similar
-        # record and both trying to update/delete it). Within each save,
-        # the parallel LLM calls still run on their own thread pool.
-        self._save_pool = ThreadPoolExecutor(
-            max_workers=1, thread_name_prefix="memory-save"
-        )
-        self._pending_saves: list[Future[Any]] = []
-        self._pending_lock = threading.Lock()
 
     _MEMORY_DOCS_URL = "https://docs.crewai.com/concepts/memory"
 
@@ -173,11 +184,7 @@ class Memory:
             from crewai.llm import LLM
 
             try:
-                model_name = (
+                model_name = self.llm if isinstance(self.llm, str) else str(self.llm)
-                    self._llm_config
-                    if isinstance(self._llm_config, str)
-                    else str(self._llm_config)
-                )
                 self._llm_instance = LLM(model=model_name)
             except Exception as e:
                 raise RuntimeError(
@@ -197,8 +204,8 @@ class Memory:
         """Lazy embedder initialization -- only created when first needed."""
         if self._embedder_instance is None:
             try:
-                if isinstance(self._embedder_config, dict):
+                if isinstance(self.embedder, dict):
-                    self._embedder_instance = build_embedder(self._embedder_config)
+                    self._embedder_instance = build_embedder(self.embedder)
                 else:
                     self._embedder_instance = _default_embedder()
             except Exception as e:
@@ -223,8 +230,9 @@ class Memory:
         If the pool has been shut down (e.g. after ``close()``), the save
         runs synchronously as a fallback so late saves still succeed.
         """
+        ctx = contextvars.copy_context()
         try:
-            future: Future[Any] = self._save_pool.submit(fn, *args, **kwargs)
+            future: Future[Any] = self._save_pool.submit(ctx.run, fn, *args, **kwargs)
         except RuntimeError:
             # Pool shut down -- run synchronously as fallback
             future = Future()
@@ -356,7 +364,7 @@ class Memory:
         Raises:
             Exception: On save failure (events emitted).
         """
-        if self._read_only:
+        if self.read_only:
             return None
         _source_type = "unified_memory"
         try:
@@ -444,7 +452,7 @@ class Memory:
         Returns:
             Empty list (records are not available until the background save completes).
         """
-        if not contents or self._read_only:
+        if not contents or self.read_only:
             return []
 
         self._submit_save(

lib/crewai/src/crewai/project/annotations.py

@@ -4,6 +4,7 @@ from __future__ import annotations
 
 import asyncio
 from collections.abc import Callable
+import contextvars
 from functools import wraps
 import inspect
 from typing import TYPE_CHECKING, Any, Concatenate, ParamSpec, TypeVar, overload
@@ -169,8 +170,9 @@ def _call_method(method: Callable[..., Any], *args: Any, **kwargs: Any) -> Any:
         if loop and loop.is_running():
             import concurrent.futures
 
+            ctx = contextvars.copy_context()
             with concurrent.futures.ThreadPoolExecutor() as pool:
-                return pool.submit(asyncio.run, result).result()
+                return pool.submit(ctx.run, asyncio.run, result).result()
         return asyncio.run(result)
     return result
 

lib/crewai/src/crewai/project/wrappers.py

@@ -4,6 +4,7 @@ from __future__ import annotations
 
 import asyncio
 from collections.abc import Callable
+import contextvars
 from functools import partial
 import inspect
 from pathlib import Path
@@ -146,8 +147,9 @@ def _resolve_result(result: Any) -> Any:
         if loop and loop.is_running():
             import concurrent.futures
 
+            ctx = contextvars.copy_context()
             with concurrent.futures.ThreadPoolExecutor() as pool:
-                return pool.submit(asyncio.run, result).result()
+                return pool.submit(ctx.run, asyncio.run, result).result()
         return asyncio.run(result)
     return result
 

lib/crewai/src/crewai/rag/chromadb/client.py

@@ -1,5 +1,8 @@
 """ChromaDB client implementation."""
 
+import asyncio
+from collections.abc import AsyncIterator
+from contextlib import AbstractContextManager, asynccontextmanager, nullcontext
 import logging
 from typing import Any
 
@@ -29,6 +32,7 @@ from crewai.rag.core.base_client import (
     BaseCollectionParams,
 )
 from crewai.rag.types import SearchResult
+from crewai.utilities.lock_store import lock as store_lock
 from crewai.utilities.logger_utils import suppress_logging
 
 
@@ -52,6 +56,7 @@ class ChromaDBClient(BaseClient):
         default_limit: int = 5,
         default_score_threshold: float = 0.6,
         default_batch_size: int = 100,
+        lock_name: str = "",
     ) -> None:
         """Initialize ChromaDBClient with client and embedding function.
 
@@ -61,12 +66,32 @@ class ChromaDBClient(BaseClient):
             default_limit: Default number of results to return in searches.
             default_score_threshold: Default minimum score for search results.
             default_batch_size: Default batch size for adding documents.
+            lock_name: Optional lock name for cross-process synchronization.
         """
         self.client = client
         self.embedding_function = embedding_function
         self.default_limit = default_limit
         self.default_score_threshold = default_score_threshold
         self.default_batch_size = default_batch_size
+        self._lock_name = lock_name
+
+    def _locked(self) -> AbstractContextManager[None]:
+        """Return a cross-process lock context manager, or nullcontext if no lock name."""
+        return store_lock(self._lock_name) if self._lock_name else nullcontext()
+
+    @asynccontextmanager
+    async def _alocked(self) -> AsyncIterator[None]:
+        """Async cross-process lock that acquires/releases in an executor."""
+        if not self._lock_name:
+            yield
+            return
+        lock_cm = store_lock(self._lock_name)
+        loop = asyncio.get_event_loop()
+        await loop.run_in_executor(None, lock_cm.__enter__)
+        try:
+            yield
+        finally:
+            await loop.run_in_executor(None, lock_cm.__exit__, None, None, None)
 
     def create_collection(
         self, **kwargs: Unpack[ChromaDBCollectionCreateParams]
@@ -313,23 +338,24 @@ class ChromaDBClient(BaseClient):
         if not documents:
             raise ValueError("Documents list cannot be empty")
 
-        collection = self.client.get_or_create_collection(
+        with self._locked():
-            name=_sanitize_collection_name(collection_name),
+            collection = self.client.get_or_create_collection(
-            embedding_function=self.embedding_function,
+                name=_sanitize_collection_name(collection_name),
-        )
+                embedding_function=self.embedding_function,
-
-        prepared = _prepare_documents_for_chromadb(documents)
-
-        for i in range(0, len(prepared.ids), batch_size):
-            batch_ids, batch_texts, batch_metadatas = _create_batch_slice(
-                prepared=prepared, start_index=i, batch_size=batch_size
             )
 
-            collection.upsert(
+            prepared = _prepare_documents_for_chromadb(documents)
-                ids=batch_ids,
+
-                documents=batch_texts,
+            for i in range(0, len(prepared.ids), batch_size):
-                metadatas=batch_metadatas,  # type: ignore[arg-type]
+                batch_ids, batch_texts, batch_metadatas = _create_batch_slice(
-            )
+                    prepared=prepared, start_index=i, batch_size=batch_size
+                )
+
+                collection.upsert(
+                    ids=batch_ids,
+                    documents=batch_texts,
+                    metadatas=batch_metadatas,  # type: ignore[arg-type]
+                )
 
     async def aadd_documents(self, **kwargs: Unpack[BaseCollectionAddParams]) -> None:
         """Add documents with their embeddings to a collection asynchronously.
@@ -363,22 +389,23 @@ class ChromaDBClient(BaseClient):
         if not documents:
             raise ValueError("Documents list cannot be empty")
 
-        collection = await self.client.get_or_create_collection(
+        async with self._alocked():
-            name=_sanitize_collection_name(collection_name),
+            collection = await self.client.get_or_create_collection(
-            embedding_function=self.embedding_function,
+                name=_sanitize_collection_name(collection_name),
-        )
+                embedding_function=self.embedding_function,
-        prepared = _prepare_documents_for_chromadb(documents)
-
-        for i in range(0, len(prepared.ids), batch_size):
-            batch_ids, batch_texts, batch_metadatas = _create_batch_slice(
-                prepared=prepared, start_index=i, batch_size=batch_size
             )
+            prepared = _prepare_documents_for_chromadb(documents)
 
-            await collection.upsert(
+            for i in range(0, len(prepared.ids), batch_size):
-                ids=batch_ids,
+                batch_ids, batch_texts, batch_metadatas = _create_batch_slice(
-                documents=batch_texts,
+                    prepared=prepared, start_index=i, batch_size=batch_size
-                metadatas=batch_metadatas,  # type: ignore[arg-type]
+                )
-            )
+
+                await collection.upsert(
+                    ids=batch_ids,
+                    documents=batch_texts,
+                    metadatas=batch_metadatas,  # type: ignore[arg-type]
+                )
 
     def search(
         self, **kwargs: Unpack[ChromaDBCollectionSearchParams]
@@ -531,7 +558,10 @@ class ChromaDBClient(BaseClient):
             )
 
         collection_name = kwargs["collection_name"]
-        self.client.delete_collection(name=_sanitize_collection_name(collection_name))
+        with self._locked():
+            self.client.delete_collection(
+                name=_sanitize_collection_name(collection_name)
+            )
 
     async def adelete_collection(self, **kwargs: Unpack[BaseCollectionParams]) -> None:
         """Delete a collection and all its data asynchronously.
@@ -561,9 +591,10 @@ class ChromaDBClient(BaseClient):
             )
 
         collection_name = kwargs["collection_name"]
-        await self.client.delete_collection(
+        async with self._alocked():
-            name=_sanitize_collection_name(collection_name)
+            await self.client.delete_collection(
-        )
+                name=_sanitize_collection_name(collection_name)
+            )
 
     def reset(self) -> None:
         """Reset the vector database by deleting all collections and data.
@@ -586,7 +617,8 @@ class ChromaDBClient(BaseClient):
                 "Use areset() for AsyncClientAPI."
             )
 
-        self.client.reset()
+        with self._locked():
+            self.client.reset()
 
     async def areset(self) -> None:
         """Reset the vector database by deleting all collections and data asynchronously.
@@ -612,4 +644,5 @@ class ChromaDBClient(BaseClient):
                 "Use reset() for ClientAPI."
             )
 
-        await self.client.reset()
+        async with self._alocked():
+            await self.client.reset()

lib/crewai/src/crewai/rag/chromadb/factory.py

@@ -1,13 +1,12 @@
 """Factory functions for creating ChromaDB clients."""
 
-from hashlib import md5
 import os
 
 from chromadb import PersistentClient
-import portalocker
 
 from crewai.rag.chromadb.client import ChromaDBClient
 from crewai.rag.chromadb.config import ChromaDBConfig
+from crewai.utilities.lock_store import lock
 
 
 def create_client(config: ChromaDBConfig) -> ChromaDBClient:
@@ -25,10 +24,8 @@ def create_client(config: ChromaDBConfig) -> ChromaDBClient:
 
     persist_dir = config.settings.persist_directory
     os.makedirs(persist_dir, exist_ok=True)
-    lock_id = md5(persist_dir.encode(), usedforsecurity=False).hexdigest()
-    lockfile = os.path.join(persist_dir, f"chromadb-{lock_id}.lock")
 
-    with portalocker.Lock(lockfile):
+    with lock(f"chromadb:{persist_dir}"):
         client = PersistentClient(
             path=persist_dir,
             settings=config.settings,
@@ -42,4 +39,5 @@ def create_client(config: ChromaDBConfig) -> ChromaDBClient:
         default_limit=config.limit,
         default_score_threshold=config.score_threshold,
         default_batch_size=config.batch_size,
+        lock_name=f"chromadb:{persist_dir}",
     )

lib/crewai/src/crewai/task.py

@@ -2,6 +2,7 @@ from __future__ import annotations
 
 import asyncio
 from concurrent.futures import Future
+import contextvars
 from copy import copy as shallow_copy
 import datetime
 from hashlib import md5
@@ -224,7 +225,6 @@ class Task(BaseModel):
     _guardrail_retry_counts: dict[int, int] = PrivateAttr(
         default_factory=dict,
     )
-    _execution_index: int | None = PrivateAttr(default=None)
     _original_description: str | None = PrivateAttr(default=None)
     _original_expected_output: str | None = PrivateAttr(default=None)
     _original_output_file: str | None = PrivateAttr(default=None)
@@ -525,10 +525,11 @@ class Task(BaseModel):
     ) -> Future[TaskOutput]:
         """Execute the task asynchronously."""
         future: Future[TaskOutput] = Future()
+        ctx = contextvars.copy_context()
         threading.Thread(
             daemon=True,
-            target=self._execute_task_async,
+            target=ctx.run,
-            args=(agent, context, tools, future),
+            args=(self._execute_task_async, agent, context, tools, future),
         ).start()
         return future
 

lib/crewai/src/crewai/telemetry/__init__.py

@@ -1,5 +1,4 @@
 from crewai.telemetry.telemetry import Telemetry
 
 
-
 __all__ = ["Telemetry"]

lib/crewai/src/crewai/telemetry/telemetry.py

@@ -173,6 +173,12 @@ class Telemetry:
 
         self._original_handlers: dict[int, Any] = {}
 
+        if threading.current_thread() is not threading.main_thread():
+            logger.debug(
+                "Skipping signal handler registration: not running in main thread"
+            )
+            return
+
         self._register_signal_handler(signal.SIGTERM, SigTermEvent, shutdown=True)
         self._register_signal_handler(signal.SIGINT, SigIntEvent, shutdown=True)
         if hasattr(signal, "SIGHUP"):

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

@@ -1,7 +1,6 @@
 from crewai.tools.base_tool import BaseTool, EnvVar, tool
 
 
-
 __all__ = [
     "BaseTool",
     "EnvVar",

lib/crewai/src/crewai/tools/mcp_native_tool.py

@@ -1,29 +1,31 @@
 """Native MCP tool wrapper for CrewAI agents.
 
-This module provides a tool wrapper that reuses existing MCP client sessions
+This module provides a tool wrapper that creates a fresh MCP client for every
-for better performance and connection management.
+invocation, ensuring safe parallel execution even when the same tool is called
+concurrently by the executor.
 """
 
 import asyncio
+from collections.abc import Callable
+import contextvars
 from typing import Any
 
 from crewai.tools import BaseTool
 
 
 class MCPNativeTool(BaseTool):
-    """Native MCP tool that reuses client sessions.
+    """Native MCP tool that creates a fresh client per invocation.
 
-    This tool wrapper is used when agents connect to MCP servers using
+    A ``client_factory`` callable produces an independent ``MCPClient`` +
-    structured configurations. It reuses existing client sessions for
+    transport for every ``_run_async`` call.  This guarantees that parallel
-    better performance and proper connection lifecycle management.
+    invocations -- whether of the *same* tool or *different* tools from the
-
+    same server -- never share mutable connection state (which would cause
-    Unlike MCPToolWrapper which connects on-demand, this tool uses
+    anyio cancel-scope errors).
-    a shared MCP client instance that maintains a persistent connection.
     """
 
     def __init__(
         self,
-        mcp_client: Any,
+        client_factory: Callable[[], Any],
         tool_name: str,
         tool_schema: dict[str, Any],
         server_name: str,
@@ -32,19 +34,16 @@ class MCPNativeTool(BaseTool):
         """Initialize native MCP tool.
 
         Args:
-            mcp_client: MCPClient instance with active session.
+            client_factory: Zero-arg callable that returns a new MCPClient.
             tool_name: Name of the tool (may be prefixed).
             tool_schema: Schema information for the tool.
             server_name: Name of the MCP server for prefixing.
             original_tool_name: Original name of the tool on the MCP server.
         """
-        # Create tool name with server prefix to avoid conflicts
         prefixed_name = f"{server_name}_{tool_name}"
 
-        # Handle args_schema properly - BaseTool expects a BaseModel subclass
         args_schema = tool_schema.get("args_schema")
 
-        # Only pass args_schema if it's provided
         kwargs = {
             "name": prefixed_name,
             "description": tool_schema.get(
@@ -57,16 +56,9 @@ class MCPNativeTool(BaseTool):
 
         super().__init__(**kwargs)
 
-        # Set instance attributes after super().__init__
+        self._client_factory = client_factory
-        self._mcp_client = mcp_client
         self._original_tool_name = original_tool_name or tool_name
         self._server_name = server_name
-        # self._logger = logging.getLogger(__name__)
-
-    @property
-    def mcp_client(self) -> Any:
-        """Get the MCP client instance."""
-        return self._mcp_client
 
     @property
     def original_tool_name(self) -> str:
@@ -93,9 +85,10 @@ class MCPNativeTool(BaseTool):
 
                 import concurrent.futures
 
+                ctx = contextvars.copy_context()
                 with concurrent.futures.ThreadPoolExecutor() as executor:
                     coro = self._run_async(**kwargs)
-                    future = executor.submit(asyncio.run, coro)
+                    future = executor.submit(ctx.run, asyncio.run, coro)
                     return future.result()
             except RuntimeError:
                 return asyncio.run(self._run_async(**kwargs))
@@ -108,51 +101,26 @@ class MCPNativeTool(BaseTool):
     async def _run_async(self, **kwargs) -> str:
         """Async implementation of tool execution.
 
+        A fresh ``MCPClient`` is created for every invocation so that
+        concurrent calls never share transport or session state.
+
         Args:
             **kwargs: Arguments to pass to the MCP tool.
 
         Returns:
             Result from the MCP tool execution.
         """
-        # Note: Since we use asyncio.run() which creates a new event loop each time,
+        client = self._client_factory()
-        # Always reconnect on-demand because asyncio.run() creates new event loops per call
+        await client.connect()
-        # All MCP transport context managers (stdio, streamablehttp_client, sse_client)
-        # use anyio.create_task_group() which can't span different event loops
-        if self._mcp_client.connected:
-            await self._mcp_client.disconnect()
-
-        await self._mcp_client.connect()
 
         try:
-            result = await self._mcp_client.call_tool(self.original_tool_name, kwargs)
+            result = await client.call_tool(self.original_tool_name, kwargs)
-
-        except Exception as e:
-            error_str = str(e).lower()
-            if (
-                "not connected" in error_str
-                or "connection" in error_str
-                or "send" in error_str
-            ):
-                await self._mcp_client.disconnect()
-                await self._mcp_client.connect()
-                # Retry the call
-                result = await self._mcp_client.call_tool(
-                    self.original_tool_name, kwargs
-                )
-            else:
-                raise
-
         finally:
-            # Always disconnect after tool call to ensure clean context manager lifecycle
+            await client.disconnect()
-            # This prevents "exit cancel scope in different task" errors
-            # All transport context managers must be exited in the same event loop they were entered
-            await self._mcp_client.disconnect()
 
-        # Extract result content
         if isinstance(result, str):
             return result
 
-        # Handle various result formats
         if hasattr(result, "content") and result.content:
             if isinstance(result.content, list) and len(result.content) > 0:
                 content_item = result.content[0]

lib/crewai/src/crewai/tools/memory_tools.py

@@ -49,7 +49,7 @@ class RecallMemoryTool(BaseTool):
         all_lines: list[str] = []
         seen_ids: set[str] = set()
         for query in queries:
-            matches = self.memory.recall(query)
+            matches = self.memory.recall(query, limit=20)
             for m in matches:
                 if m.record.id not in seen_ids:
                     seen_ids.add(m.record.id)
@@ -121,7 +121,7 @@ def create_memory_tools(memory: Any) -> list[BaseTool]:
             description=i18n.tools("recall_memory"),
         ),
     ]
-    if not getattr(memory, "_read_only", False):
+    if not memory.read_only:
         tools.append(
             RememberTool(
                 memory=memory,

lib/crewai/src/crewai/translations/en.json

@@ -7,7 +7,7 @@
   "slices": {
     "observation": "\nObservation:",
     "task": "\nCurrent Task: {input}\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:",
-    "memory": "\n\n# Useful context: \n{memory}",
+    "memory": "\n\n# Memories from past conversations:\n{memory}\n\nIMPORTANT: The memories above are an automatic selection and may be INCOMPLETE. If the task involves counting, listing, or summing items (e.g. 'how many', 'total', 'list all'), you MUST use the Search memory tool with several different queries before answering — do NOT rely solely on the memories shown above. Enumerate each distinct item you find before giving a final count.",
     "role_playing": "You are {role}. {backstory}\nYour personal goal is: {goal}",
     "tools": "\nYou ONLY have access to the following tools, and should NEVER make up tools that are not listed here:\n\n{tools}\n\nIMPORTANT: Use the following format in your response:\n\n```\nThought: you should always think about what to do\nAction: the action to take, only one name of [{tool_names}], just the name, exactly as it's written.\nAction Input: the input to the action, just a simple JSON object, enclosed in curly braces, using \" to wrap keys and values.\nObservation: the result of the action\n```\n\nOnce all necessary information is gathered, return the following format:\n\n```\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question\n```",
     "no_tools": "",
@@ -60,12 +60,12 @@
       "description": "See image to understand its content, you can optionally ask a question about the image",
       "default_action": "Please provide a detailed description of this image, including all visual elements, context, and any notable details you can observe."
     },
-    "recall_memory": "Search through the team's shared memory for relevant information. Pass one or more queries to search for multiple things at once. Use this when you need to find facts, decisions, preferences, or past results that may have been stored previously.",
+    "recall_memory": "Search through the team's shared memory for relevant information. Pass one or more queries to search for multiple things at once. Use this when you need to find facts, decisions, preferences, or past results that may have been stored previously. IMPORTANT: For questions that require counting, summing, or listing items across multiple conversations (e.g. 'how many X', 'total Y', 'list all Z'), you MUST search multiple times with different phrasings to ensure you find ALL relevant items before giving a final count or total. Do not rely on a single search — items may be described differently across conversations.",
     "save_to_memory": "Store one or more important facts, decisions, observations, or lessons in memory so they can be recalled later by you or other agents. Pass multiple items at once when you have several things worth remembering."
   },
   "memory": {
     "query_system": "You analyze a query for searching memory.\nGiven the query and available scopes, output:\n1. keywords: Key entities or keywords that can be used to filter by category.\n2. suggested_scopes: Which available scopes are most relevant (empty for all).\n3. complexity: 'simple' or 'complex'.\n4. recall_queries: 1-3 short, targeted search phrases distilled from the query. Each should be a concise phrase optimized for semantic vector search. If the query is already short and focused, return it as-is in a single-item list. For long task descriptions, extract the distinct things worth searching for.\n5. time_filter: If the query references a time period (like 'last week', 'yesterday', 'in January'), return an ISO 8601 date string for the earliest relevant date (e.g. '2026-02-01'). Return null if no time constraint is implied.",
-    "extract_memories_system": "You extract discrete, reusable memory statements from raw content (e.g. a task description and its result).\n\nFor the given content, output a list of memory statements. Each memory must:\n- Be one clear sentence or short statement\n- Be understandable without the original context\n- Capture a decision, fact, outcome, preference, lesson, or observation worth remembering\n- NOT be a vague summary or a restatement of the task description\n- NOT duplicate the same idea in different words\n\nIf there is nothing worth remembering (e.g. empty result, no decisions or facts), return an empty list.\nOutput a JSON object with a single key \"memories\" whose value is a list of strings.",
+    "extract_memories_system": "You extract discrete, reusable memory statements from raw content (e.g. a task description and its result, or a conversation between a user and an assistant).\n\nFor the given content, output a list of memory statements. Each memory must:\n- Be one clear sentence or short statement\n- Be understandable without the original context\n- Capture a decision, fact, outcome, preference, lesson, or observation worth remembering\n- NOT be a vague summary or a restatement of the task description\n- NOT duplicate the same idea in different words\n\nWhen the content is a conversation, pay special attention to facts stated by the user (first-person statements). These personal facts are HIGH PRIORITY and must always be extracted:\n- What the user did, bought, made, visited, attended, or completed\n- Names of people, pets, places, brands, and specific items the user mentions\n- Quantities, durations, dates, and measurements the user states\n- Subordinate clauses and casual asides often contain important personal details (e.g. \"by the way, it took me 4 hours\" or \"my Golden Retriever Max\")\n\nPreserve exact names and numbers — never generalize (e.g. keep \"lavender gin fizz\" not just \"cocktail\", keep \"12 largemouth bass\" not just \"fish caught\", keep \"Golden Retriever\" not just \"dog\").\n\nAdditional extraction rules:\n- Presupposed facts: When the user reveals a fact indirectly in a question (e.g. \"What collar suits a Golden Retriever like Max?\" presupposes Max is a Golden Retriever), extract that fact as a separate memory.\n- Date precision: Always preserve the full date including day-of-month when stated (e.g. \"February 14th\" not just \"February\", \"March 5\" not just \"March\").\n- Life events in passing: When the user mentions a life event (birth, wedding, graduation, move, adoption) while discussing something else, extract the life event as its own memory (e.g. \"my friend David had a baby boy named Jasper\" is a birth fact, even if mentioned while planning to send congratulations).\n\nIf there is nothing worth remembering (e.g. empty result, no decisions or facts), return an empty list.\nOutput a JSON object with a single key \"memories\" whose value is a list of strings.",
     "extract_memories_user": "Content:\n{content}\n\nExtract memory statements as described. Return structured output.",
     "query_user": "Query: {query}\n\nAvailable scopes: {available_scopes}\n{scope_desc}\n\nReturn the analysis as structured output.",
     "save_system": "You analyze content to be stored in a hierarchical memory system.\nGiven the content and the existing scopes and categories, output:\n1. suggested_scope: The best matching existing scope path, or a new path if none fit (use / for root).\n2. categories: A list of categories (reuse existing when relevant, add new ones if needed).\n3. importance: A number from 0.0 to 1.0 indicating how significant this memory is.\n4. extracted_metadata: A JSON object with any entities, dates, or topics you can extract.",

lib/crewai/src/crewai/utilities/agent_utils.py

@@ -3,6 +3,7 @@ from __future__ import annotations
 import asyncio
 from collections.abc import Callable, Sequence
 import concurrent.futures
+import contextvars
 import inspect
 import json
 import re
@@ -907,8 +908,9 @@ def summarize_messages(
             chunks=chunks, llm=llm, callbacks=callbacks, i18n=i18n
         )
         if is_inside_event_loop():
+            ctx = contextvars.copy_context()
             with concurrent.futures.ThreadPoolExecutor(max_workers=1) as pool:
-                summarized_contents = pool.submit(asyncio.run, coro).result()
+                summarized_contents = pool.submit(ctx.run, asyncio.run, coro).result()
         else:
             summarized_contents = asyncio.run(coro)