chore: bump PraisonAI to 2.2.55 and PraisonAI Agents to 0.0.129 across all files

feat: Add multi-provider/multi-model support with intelligent routing

.github/actions/gemini/action.yml

@@ -0,0 +1,81 @@
+name: 'Gemini CLI Action'
+description: 'Uses the Gemini CLI to automate software development tasks.'
+author: 'Gemini'
+
+inputs:
+  prompt:
+    description: 'A specific prompt to guide Gemini.'
+    required: false
+    default: 'You are a helpful assistant.'
+  GEMINI_API_KEY:
+    description: 'Your Gemini API key.'
+    required: true
+  OTLP_GCP_WIF_PROVIDER:
+    description: 'The workload identity provider for GCP authentication.'
+    required: false
+  OTLP_GOOGLE_CLOUD_PROJECT:
+    description: 'The Google Cloud project for telemetry.'
+    required: false
+  settings_json:
+    description: |
+      A JSON string to configure the Gemini CLI. This will be written to .gemini/settings.json.
+      To enable observability with Google Cloud, include:
+      {"telemetry": {"enabled": true, "target": "gcp"}, "sandbox": false}
+    required: false
+  version:
+    description: |
+      The version of @google/gemini-cli to execute.
+      Can be a specific version from npm (e.g., '0.1.0', 'latest'), a branch name (e.g., 'main'), or a commit hash.
+    required: false
+    default: 'latest'
+
+runs:
+  using: "composite"
+  steps:
+    - name: Configure Gemini CLI
+      if: inputs.settings_json != ''
+      run: |
+        mkdir -p .gemini
+        echo "$SETTINGS_JSON" > .gemini/settings.json
+      shell: bash
+      env:
+        SETTINGS_JSON: ${{ inputs.settings_json }}
+
+    - name: Authenticate to Google Cloud for Telemetry 
+      if: inputs.OTLP_GCP_WIF_PROVIDER != ''
+      id: auth
+      uses: 'google-github-actions/auth@v2'
+      with:
+        project_id: ${{ inputs.OTLP_GOOGLE_CLOUD_PROJECT }}
+        workload_identity_provider: ${{ inputs.OTLP_GCP_WIF_PROVIDER }}
+
+    - name: Install Gemini CLI
+      id: install
+      run: |
+        if [[ "${{ inputs.version }}" == "latest" || "${{ inputs.version }}" =~ ^[0-9]+\.[0-9]+\.[0-9]+(-[a-zA-Z0-9\.-]+)?(\+[a-zA-Z0-9\.-]+)?$ ]]; then
+          echo "Installing Gemini CLI from npm: @google/gemini-cli@${{ inputs.version }}"
+          npm install -g @google/gemini-cli@${{ inputs.version }}
+        else
+          echo "Installing Gemini CLI from GitHub: github:google-gemini/gemini-cli#${{ inputs.version }}"
+          npm install -g github:google-gemini/gemini-cli#${{ inputs.version }}
+        fi
+        echo "Verifying installation:"
+        if command -v gemini >/dev/null 2>&1; then
+          gemini --version || echo "Gemini CLI installed successfully (version command not available)"
+        else
+          echo "Error: Gemini CLI not found in PATH"
+          exit 1
+        fi
+      shell: bash
+
+    - name: Run Gemini CLI
+      run: |
+        gemini --yolo --prompt "$PROMPT"
+      shell: bash
+      env:
+        GEMINI_API_KEY: ${{ inputs.GEMINI_API_KEY }}
+        PROMPT: ${{ inputs.prompt }}
+
+branding:
+  icon: 'terminal'
+  color: 'blue'

.github/workflows/auto-issue-comment.yml

@@ -0,0 +1,23 @@
+name: Auto Issue Comment
+
+on:
+  issues:
+    types: [opened]
+
+jobs:
+  add-comment:
+    runs-on: ubuntu-latest
+    permissions:
+      issues: write
+    steps:
+      - name: Add automated comment
+        uses: actions/github-script@v7
+        with:
+          github-token: ${{ secrets.GH_TOKEN }}
+          script: |
+            github.rest.issues.createComment({
+              issue_number: context.issue.number,
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              body: '@claude review this issue and do a detailed analysis and fix this if the existing code doesn\'t have the solution implemented. Making sure it has backward compatibility, no existing features removed. After making those changes, again review the applied changes. Use @web to search if you dont know any information or to find the latest documentation or to find the latest version. Run the code if you think you need to run it to test it. Minimal code change to start with if required any changes.'
+            }) 

.github/workflows/auto-pr-comment.yml

@@ -0,0 +1,23 @@
+name: Auto PR Comment
+
+on:
+  pull_request:
+    types: [opened]
+
+jobs:
+  add-comment:
+    runs-on: ubuntu-latest
+    permissions:
+      pull-requests: write
+    steps:
+      - name: Add automated comment
+        uses: actions/github-script@v7
+        with:
+          github-token: ${{ secrets.GH_TOKEN }}
+          script: |
+            github.rest.issues.createComment({
+              issue_number: context.issue.number,
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              body: '@claude review this pull request and do a detailed analysis and fix this if the existing code doesn\'t have the solution implemented. Making sure it has backward compatibility, no existing features removed. After making those changes, again review the applied changes. Use @web to search if you dont know any information or to find the latest documentation or to find the latest version. Run the code if you think you need to run it to test it. Minimal code change to start with if required any changes.'
+            }) 

.github/workflows/claude.yml

@@ -1,4 +1,4 @@
-name: Claude Code
+name: Claude Assistant
 
 on:
   issue_comment:
@@ -6,34 +6,116 @@ on:
   pull_request_review_comment:
     types: [created]
   issues:
-    types: [opened, assigned]
+    types: [opened, assigned, labeled]
   pull_request_review:
     types: [submitted]
 
 jobs:
-  claude:
+  claude-response:
+    # Prevent bots from triggering this action
     if: |
-      (github.event_name == 'issue_comment' && contains(github.event.comment.body, '@claude')) ||
-      (github.event_name == 'pull_request_review_comment' && contains(github.event.comment.body, '@claude')) ||
-      (github.event_name == 'pull_request_review' && contains(github.event.review.body, '@claude')) ||
-      (github.event_name == 'issues' && (contains(github.event.issue.body, '@claude') || contains(github.event.issue.title, '@claude')))
+      github.actor != 'dependabot[bot]' &&
+      github.actor != 'github-actions[bot]' &&
+      github.actor != 'cursor[bot]' &&
+      !contains(github.actor, '[bot]') &&
+      github.actor != 'renovate[bot]'
     runs-on: ubuntu-latest
     permissions:
-      contents: read
-      pull-requests: read
-      issues: read
-      id-token: write
+      contents: write
+      pull-requests: write
+      issues: write
+      actions: read
     steps:
       - name: Checkout repository
         uses: actions/checkout@v4
         with:
-          fetch-depth: 1
-
-      - name: Run Claude Code (OAuth)
-        id: claude
-        uses: grll/claude-code-action@beta
+          fetch-depth: 0
+          
+      - uses: anthropics/claude-code-action@beta
         with:
-          use_oauth: true
-          claude_access_token: ${{ secrets.CLAUDE_ACCESS_TOKEN }}
-          claude_refresh_token: ${{ secrets.CLAUDE_REFRESH_TOKEN }}
-          claude_expires_at: ${{ secrets.CLAUDE_EXPIRES_AT }}
+          claude_code_oauth_token: ${{ secrets.CLAUDE_ACCESS_TOKEN }}
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          trigger_phrase: "@claude"
+          timeout_minutes: 30
+
+  post-review-comment:
+    needs: claude-response
+    if: success() && needs.claude-response.result == 'success'
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      pull-requests: write
+      issues: write
+    steps:
+      - name: Check for existing review comment
+        id: check-comment
+        uses: actions/github-script@v7
+        with:
+          github-token: ${{ secrets.GH_TOKEN }}
+          script: |
+            const reviewText = '@claude review if the changes made are as per the requirements';
+            let comments = [];
+            let issueNumber;
+            
+            try {
+              // Determine issue/PR number based on event type
+              if (context.eventName === 'pull_request_review_comment' || context.eventName === 'pull_request_review') {
+                issueNumber = context.payload.pull_request?.number || context.issue.number;
+              } else if (context.eventName === 'issue_comment' && context.payload.issue.pull_request) {
+                // This is a comment on a PR (not an issue)
+                issueNumber = context.payload.issue.number;
+              } else {
+                // This is a regular issue
+                issueNumber = context.issue.number;
+              }
+              
+              comments = await github.rest.issues.listComments({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                issue_number: issueNumber
+              });
+              
+              const existingComment = comments.data.find(comment => 
+                comment.body.includes(reviewText)
+              );
+              
+              const shouldPost = !existingComment;
+              core.setOutput('should-post', shouldPost);
+              console.log(`Should post comment: ${shouldPost}`);
+              
+            } catch (error) {
+              console.log('Error checking comments:', error);
+              core.setOutput('should-post', true); // If we can't check, proceed with posting
+            }
+
+      - name: Wait 20 seconds before posting comment
+        if: steps.check-comment.outputs.should-post == 'true'
+        run: sleep 20
+
+      - name: Post review comment
+        if: steps.check-comment.outputs.should-post == 'true'
+        uses: actions/github-script@v7
+        with:
+          github-token: ${{ secrets.GH_TOKEN }}
+          script: |
+            let issueNumber;
+            
+            // Determine issue/PR number based on event type
+            if (context.eventName === 'pull_request_review_comment' || context.eventName === 'pull_request_review') {
+              issueNumber = context.payload.pull_request?.number || context.issue.number;
+            } else if (context.eventName === 'issue_comment' && context.payload.issue.pull_request) {
+              // This is a comment on a PR (not an issue)
+              issueNumber = context.payload.issue.number;
+            } else {
+              // This is a regular issue
+              issueNumber = context.issue.number;
+            }
+            
+            console.log(`Posting review comment on issue/PR #${issueNumber}`);
+            
+            await github.rest.issues.createComment({
+              issue_number: issueNumber,
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              body: '@claude review if the changes made are as per the requirements'
+            });

.github/workflows/docker-publish.yml

@@ -40,5 +40,6 @@ jobs:
         uses: docker/build-push-action@v2
         with:
           context: .
+          file: ./docker/Dockerfile
           push: true
           tags: ghcr.io/mervinpraison/praisonai:latest

.github/workflows/gemini-issue-automated-triage.yml

@@ -0,0 +1,76 @@
+name: Gemini Automated Issue Triage
+
+on:
+  issue_comment:
+    types: [created]
+
+jobs:
+  triage-issue:
+    if: >
+      github.event_name == 'issue_comment' &&
+      !github.event.issue.pull_request &&
+      contains(github.event.comment.body, '@gemini triage') &&
+      (github.event.comment.author_association == 'OWNER' ||
+       github.event.comment.author_association == 'MEMBER' ||
+       github.event.comment.author_association == 'COLLABORATOR')
+    timeout-minutes: 5
+    permissions:
+      issues: write
+      contents: read
+      id-token: write
+    concurrency:
+      group: ${{ github.workflow }}-${{ github.event.issue.number }}
+      cancel-in-progress: true
+    runs-on: ubuntu-latest
+    steps:
+      - name: Generate GitHub App Token
+        id: generate_token
+        uses: actions/create-github-app-token@v1
+        with:
+          app-id: ${{ secrets.APP_ID }}
+          private-key: ${{ secrets.PRIVATE_KEY }}
+
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          token: ${{ steps.generate_token.outputs.token }}
+
+      - name: Run Gemini Issue Triage
+        uses: google-gemini/gemini-cli-action@main
+        env:
+          GITHUB_TOKEN: ${{ steps.generate_token.outputs.token }}
+          ISSUE_TITLE: ${{ github.event.issue.title }}
+          ISSUE_BODY: ${{ github.event.issue.body }}
+          ISSUE_NUMBER: ${{ github.event.issue.number }}
+          REPOSITORY: ${{ github.repository }}
+        with:
+          version: 0.1.8-rc.0
+          GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY }}
+          OTLP_GCP_WIF_PROVIDER: ${{ secrets.OTLP_GCP_WIF_PROVIDER }}
+          OTLP_GOOGLE_CLOUD_PROJECT: ${{ secrets.OTLP_GOOGLE_CLOUD_PROJECT }}
+          settings_json: |
+            {
+              "coreTools": [
+                "run_shell_command(gh label list)",
+                "run_shell_command(gh issue edit)"
+              ],
+              "telemetry": {
+                "enabled": true,
+                "target": "gcp"
+              },
+              "sandbox": false
+            }
+          prompt: |
+            You are an issue triage assistant. Analyze the current GitHub issue and apply the most appropriate existing labels.
+
+            Steps:
+            1. Run: `gh label list --limit 100` to get all available labels.
+            2. Review the issue title and body provided in the environment variables.
+            3. Select the most relevant labels from the existing labels, focusing on kind/*, area/*, and priority/*.
+            4. Apply the selected labels to this issue using: `gh issue edit ISSUE_NUMBER --add-label "label1,label2"`
+
+            Guidelines:
+            - Only use labels that already exist in the repository.
+            - Do not add comments or modify the issue content.
+            - Triage only the current issue.
+            - Assign all applicable kind/*, area/*, and priority/* labels based on the issue content.

.github/workflows/gemini-issue-review.yml

@@ -0,0 +1,198 @@
+name: Gemini Issue Review
+
+on:
+  workflow_dispatch:
+  issue_comment:
+    types: [created]
+
+permissions:
+  contents: write
+  issues: write
+  pull-requests: read
+
+jobs:
+  review-issue:
+    if: >
+      github.event_name == 'workflow_dispatch' ||
+      (github.event_name == 'issue_comment' && 
+       !github.event.issue.pull_request && 
+       contains(github.event.comment.body, '@gemini') &&
+       !contains(github.event.comment.body, '@gemini triage') &&
+       (github.event.comment.author_association == 'OWNER' ||
+        github.event.comment.author_association == 'MEMBER' ||
+        github.event.comment.author_association == 'COLLABORATOR'))
+    runs-on: ubuntu-latest
+    env:
+      GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY }}
+    steps:
+      - name: Generate token
+        id: generate_token
+        uses: actions/create-github-app-token@v1
+        with:
+          app-id: ${{ secrets.APP_ID }}
+          private-key: ${{ secrets.PRIVATE_KEY }}
+
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          token: ${{ steps.generate_token.outputs.token }}
+
+      - name: Set up Git
+        run: |
+          git config --local user.email "[email protected]"
+          git config --local user.name "Gemini Bot"
+
+      - name: Get issue data
+        id: issue_data
+        env:
+          GH_TOKEN: ${{ steps.generate_token.outputs.token }}
+        run: |
+          # Get issue number from event or context
+          if [ "${{ github.event_name }}" = "issue_comment" ]; then
+            ISSUE_NUMBER="${{ github.event.issue.number }}"
+          elif [ "${{ github.event_name }}" = "issues" ]; then
+            ISSUE_NUMBER="${{ github.event.issue.number }}"
+          else
+            echo "Unable to determine issue number"
+            exit 1
+          fi
+          
+          # Get issue details
+          gh issue view $ISSUE_NUMBER --json title,body,labels,assignees > issue_details.json
+          
+          # Extract additional instructions from comment if triggered by comment
+          ADDITIONAL_INSTRUCTIONS=""
+          if [ "${{ github.event_name }}" = "issue_comment" ]; then
+            COMMENT_BODY="${{ github.event.comment.body }}"
+            ADDITIONAL_INSTRUCTIONS=$(echo "$COMMENT_BODY" | sed -n 's/.*@gemini[[:space:]]*\(.*\)/\1/p' | head -1)
+          fi
+          
+          echo "ISSUE_NUMBER=$ISSUE_NUMBER" >> $GITHUB_OUTPUT
+          echo "ADDITIONAL_INSTRUCTIONS=$ADDITIONAL_INSTRUCTIONS" >> $GITHUB_OUTPUT
+
+      - name: Run Gemini CLI
+        uses: ./.github/actions/gemini
+        env:
+          GITHUB_TOKEN: ${{ steps.generate_token.outputs.token }}
+          ISSUE_NUMBER: ${{ steps.issue_data.outputs.ISSUE_NUMBER }}
+          ADDITIONAL_INSTRUCTIONS: ${{ steps.issue_data.outputs.ADDITIONAL_INSTRUCTIONS }}
+          REPOSITORY: ${{ github.repository }}
+        with:
+          GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY }}
+          OTLP_GCP_WIF_PROVIDER: ${{ secrets.OTLP_GCP_WIF_PROVIDER }}
+          OTLP_GOOGLE_CLOUD_PROJECT: ${{ secrets.OTLP_GOOGLE_CLOUD_PROJECT }}
+          prompt: |
+            You are a helpful GitHub issue assistant. Your task is to analyze and help with GitHub issues.
+            
+            **Issue Details:**
+            - Issue Number: #${ISSUE_NUMBER}
+            - Repository: ${REPOSITORY}
+            - Issue URL: ${{ github.event.issue.html_url }}
+            
+            **Additional Instructions:** ${ADDITIONAL_INSTRUCTIONS}
+            
+            **CRITICAL: When making code modifications, follow this EXACT workflow:**
+            
+            **STEP 1: Analyze the Issue**
+            - Use: `gh issue view ${ISSUE_NUMBER} --json title,body,labels,assignees`
+            - Analyze issue content thoroughly
+            - Search codebase for related files using `glob`, `search_file_content`, `list_directory`
+            
+            **STEP 2: If Code Changes Are Needed**
+            Create a new branch with 'gemini/' prefix:
+            - Use: `git checkout -b gemini/issue-${ISSUE_NUMBER}-description`
+            - Example: `git checkout -b gemini/issue-123-fix-sequential-tools`
+            
+            **STEP 3: Make Code Modifications**
+            - Use `read_file` to examine existing code
+            - Use `write_file` or `replace` to make changes
+            - Use `search_file_content` to find related code
+            - Make focused, targeted changes to fix the issue
+            
+            **STEP 4: Test Changes (if applicable)**
+            - Run relevant tests if test files exist
+            - Use `run_shell_command` to execute test commands
+            
+            **STEP 5: Commit and Push Changes**
+            - Use: `git add .` (or specific files)
+            - Use: `git commit -m "Gemini: [Issue #${ISSUE_NUMBER}] Brief description of fix"`
+            - Use: `git push -u origin gemini/issue-${ISSUE_NUMBER}-description`
+            
+            **STEP 6: Create Pull Request**
+            - Use: `gh pr create --title "Fix #${ISSUE_NUMBER}: Issue description" --body "Fixes #${ISSUE_NUMBER}\n\nSummary of changes:\n- Change 1\n- Change 2" --head gemini/issue-${ISSUE_NUMBER}-description --base main`
+            - This will return a PR URL like: https://github.com/repo/pull/123
+            
+            **STEP 7: Comment on Issue with Results**
+            Use: `gh issue comment ${ISSUE_NUMBER} -b "MESSAGE"`
+            
+            **Your final comment MUST include:**
+            - Summary of what was analyzed
+            - What changes were made (if any)
+            - Link to the created PR (if applicable)
+            - Brief explanation of the solution
+            
+            **Example final comment:**
+            ```
+            Hi! I've analyzed and fixed this issue.
+            
+            **Problem:** Sequential tool calling was getting stuck after first tool call.
+            
+            **Solution:** Added proper prompt handling after each tool call in the Ollama model integration.
+            
+            **Changes Made:**
+            - Modified `src/praisonai-agents/ollama-sequential.py`
+            - Added continuation prompts for multi-step tool execution
+            
+            **Pull Request:** https://github.com/MervinPraison/PraisonAI/pull/856
+            
+            The fix is ready for review. Please test and let me know if you encounter any issues!
+            ```
+            
+            **IMPORTANT NOTES:**
+            - Always create branches with 'gemini/' prefix
+            - Always include issue number in branch name and commit message
+            - Always create PR that references the issue
+            - Always provide PR link in your final response
+            - Use the GITHUB_TOKEN environment variable for authentication
+            
+            Please proceed with helping resolve this issue following this exact workflow.
+
+          settings_json: |
+            {
+              "coreTools": [
+                "run_shell_command(echo)",
+                "run_shell_command(gh issue view)",
+                "run_shell_command(gh issue comment)",
+                "run_shell_command(gh issue list)",
+                "run_shell_command(gh issue edit)",
+                "run_shell_command(gh pr create)",
+                "run_shell_command(gh pr view)",
+                "run_shell_command(gh pr list)",
+                "run_shell_command(cat)",
+                "run_shell_command(head)",
+                "run_shell_command(tail)",
+                "run_shell_command(grep)",
+                "run_shell_command(find)",
+                "run_shell_command(git checkout)",
+                "run_shell_command(git add)",
+                "run_shell_command(git commit)",
+                "run_shell_command(git push)",
+                "run_shell_command(git status)",
+                "run_shell_command(git branch)",
+                "list_directory",
+                "read_file",
+                "read_many_files",
+                "write_file",
+                "replace",
+                "glob",
+                "search_file_content",
+                "web_fetch",
+                "google_web_search",
+                "save_memory"
+              ],
+              "telemetry": {
+                "enabled": false,
+                "otlpGcpWifProvider": "${{ secrets.OTLP_GCP_WIF_PROVIDER }}",
+                "googleCloudProject": "${{ secrets.OTLP_GOOGLE_CLOUD_PROJECT }}"
+              }
+            }

.github/workflows/gemini-pr-review.yml

@@ -0,0 +1,242 @@
+name: Gemini PR Review
+
+on:
+  issue_comment:
+    types: [created]
+  workflow_dispatch:
+    inputs:
+      pr_number:
+        description: 'PR number to review'
+        required: true
+        type: number
+
+jobs:
+  review-pr:
+    if: >
+      github.event_name == 'workflow_dispatch' ||
+      (github.event_name == 'issue_comment' && 
+       github.event.issue.pull_request && 
+       contains(github.event.comment.body, '@gemini') &&
+       (github.event.comment.author_association == 'OWNER' ||
+        github.event.comment.author_association == 'MEMBER' ||
+        github.event.comment.author_association == 'COLLABORATOR'))
+    timeout-minutes: 15
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      id-token: write
+      pull-requests: write
+      issues: write
+    steps:
+      - name: Generate GitHub App Token
+        id: generate_token
+        uses: actions/create-github-app-token@v1
+        with:
+          app-id: ${{ secrets.APP_ID }}
+          private-key: ${{ secrets.PRIVATE_KEY }}
+
+      - name: Determine checkout ref
+        id: checkout_ref
+        run: |
+          if [ "${{ github.event_name }}" = "issue_comment" ]; then
+            echo "ref=refs/pull/${{ github.event.issue.number }}/head" >> "$GITHUB_OUTPUT"
+          else
+            echo "ref=${{ github.event.pull_request.head.sha }}" >> "$GITHUB_OUTPUT"
+          fi
+
+      - name: Checkout PR code
+        uses: actions/checkout@v4
+        with:
+          token: ${{ steps.generate_token.outputs.token }}
+          ref: ${{ steps.checkout_ref.outputs.ref }}
+          fetch-depth: 0
+
+      - name: Get PR details
+        id: get_pr
+        env:
+          GITHUB_TOKEN: ${{ steps.generate_token.outputs.token }}
+        run: |
+          if [ "${{ github.event_name }}" = "workflow_dispatch" ]; then
+            PR_NUMBER=${{ github.event.inputs.pr_number }}
+          elif [ "${{ github.event_name }}" = "issue_comment" ]; then
+            PR_NUMBER=${{ github.event.issue.number }}
+          else
+            PR_NUMBER=${{ github.event.pull_request.number }}
+          fi
+          
+          echo "pr_number=$PR_NUMBER" >> "$GITHUB_OUTPUT"
+          
+          # Extract additional instructions from comment (if triggered by comment)
+          ADDITIONAL_INSTRUCTIONS=""
+          if [ "${{ github.event_name }}" = "issue_comment" ]; then
+            COMMENT_BODY="${{ github.event.comment.body }}"
+            ADDITIONAL_INSTRUCTIONS=$(echo "$COMMENT_BODY" | sed 's/.*@gemini//' | xargs)
+          fi
+          echo "additional_instructions=$ADDITIONAL_INSTRUCTIONS" >> "$GITHUB_OUTPUT"
+          
+          # Get PR details
+          PR_DATA=$(gh pr view $PR_NUMBER --json title,body,additions,deletions,changedFiles,baseRefName,headRefName)
+          echo "pr_data=$PR_DATA" >> "$GITHUB_OUTPUT"
+          
+          # Get file changes
+          CHANGED_FILES=$(gh pr diff $PR_NUMBER --name-only)
+          echo "changed_files<<EOF" >> "$GITHUB_OUTPUT"
+          echo "$CHANGED_FILES" >> "$GITHUB_OUTPUT"
+          echo "EOF" >> "$GITHUB_OUTPUT"
+
+      - name: Run Gemini PR Review
+        uses: ./.github/actions/gemini
+        env:
+          GITHUB_TOKEN: ${{ steps.generate_token.outputs.token }}
+          PR_NUMBER: ${{ steps.get_pr.outputs.pr_number }}
+          PR_DATA: ${{ steps.get_pr.outputs.pr_data }}
+          CHANGED_FILES: ${{ steps.get_pr.outputs.changed_files }}
+          ADDITIONAL_INSTRUCTIONS: ${{ steps.get_pr.outputs.additional_instructions }}
+          REPOSITORY: ${{ github.repository }}
+        with:
+          version: 0.1.8-rc.0
+          GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY }}
+          OTLP_GCP_WIF_PROVIDER: ${{ secrets.OTLP_GCP_WIF_PROVIDER }}
+          OTLP_GOOGLE_CLOUD_PROJECT: ${{ secrets.OTLP_GOOGLE_CLOUD_PROJECT }}
+          settings_json: |
+            {
+              "coreTools": [
+                "run_shell_command(echo)",
+                "run_shell_command(gh pr view)",
+                "run_shell_command(gh pr diff)",
+                "run_shell_command(gh pr comment)",
+                "run_shell_command(gh pr list)",
+                "run_shell_command(cat)",
+                "run_shell_command(head)",
+                "run_shell_command(tail)",
+                "run_shell_command(grep)",
+                "run_shell_command(find)",
+                "run_shell_command(git checkout)",
+                "run_shell_command(git add)",
+                "run_shell_command(git commit)",
+                "run_shell_command(git push)",
+                "run_shell_command(git status)",
+                "run_shell_command(git branch)",
+                "run_shell_command(git fetch)",
+                "list_directory",
+                "read_file",
+                "read_many_files",
+                "write_file",
+                "replace",
+                "glob",
+                "search_file_content",
+                "web_fetch",
+                "google_web_search",
+                "save_memory"
+              ],
+              "telemetry": {
+                "enabled": false,
+                "target": "gcp"
+              },
+              "sandbox": false
+            }
+          prompt: |
+            You are an expert code reviewer and AI assistant for Pull Requests. You can review code AND make modifications to improve the PR.
+
+            **PR Details:**
+            - PR Number: #$PR_NUMBER
+            - Repository: $REPOSITORY
+            - Additional Instructions: $ADDITIONAL_INSTRUCTIONS
+
+            **CRITICAL: When making code modifications, follow this EXACT workflow:**
+
+            **STEP 1: Analyze the PR**
+            - Use: `echo "$PR_DATA"` to get PR details (JSON format)
+            - Use: `echo "$CHANGED_FILES"` to get changed files list
+            - Use: `gh pr diff ${PR_NUMBER}` to see the full diff
+            - Use: `gh pr view ${PR_NUMBER} --json title,body,headRefName` to get PR info
+            - Analyze the code changes thoroughly
+
+            **STEP 2: If Code Improvements Are Needed**
+            **IMPORTANT:** DO NOT create a new branch! Work on the EXISTING PR branch.
+            - Use: `git fetch origin` to get latest changes
+            - Get PR branch name: `gh pr view ${PR_NUMBER} --json headRefName`
+            - Switch to PR branch: `git checkout BRANCH_NAME` (use actual branch name from PR)
+            - Use: `git pull origin BRANCH_NAME` to get latest PR changes
+
+            **STEP 3: Make Code Modifications**
+            - Use `read_file` to examine existing code
+            - Use `write_file` or `replace` to make improvements
+            - Use `search_file_content` to find related code
+            - Make focused, targeted improvements to the PR
+
+            **STEP 4: Test Changes (if applicable)**
+            - Run relevant tests if test files exist
+            - Use `run_shell_command` to execute test commands
+
+            **STEP 5: Commit and Push Changes to EXISTING PR Branch**
+            - Use: `git add .` (or specific files)
+            - Use: `git commit -m "Gemini: [PR #${PR_NUMBER}] Brief description of improvements"`
+            - Use: `git push origin BRANCH_NAME` (push to EXISTING PR branch)
+
+            **STEP 6: Review and Comment on PR**
+            Write comprehensive review and post comment with your analysis and any improvements made.
+            Use: `gh pr comment ${PR_NUMBER} -b "MESSAGE"`
+
+            Review Guidelines:
+            - Focus on code quality, security, performance, and maintainability
+            - Check for common issues: potential bugs, security vulnerabilities, performance bottlenecks
+            - Verify error handling and edge cases
+            - Look for code style and best practices
+            - Comment on architecture and design decisions if significant
+            - Be constructive and specific in feedback
+            - Highlight both issues and positive aspects
+            - Suggest improvements with examples when possible
+            
+            Review Areas:
+            - **Security**: Authentication, authorization, input validation, data sanitization
+            - **Performance**: Algorithms, database queries, caching, resource usage
+            - **Reliability**: Error handling, logging, testing coverage, edge cases
+            - **Maintainability**: Code structure, documentation, naming conventions
+            - **Functionality**: Logic correctness, requirements fulfillment
+            
+            Output Format:
+            Structure your review using this exact format with markdown:
+
+            ## 📋 Review Summary
+            Provide a brief 2-3 sentence overview of the PR and overall assessment.
+
+            ## 🔍 General Feedback
+            - List general observations about code quality
+            - Mention overall patterns or architectural decisions
+            - Highlight positive aspects of the implementation
+            - Note any recurring themes across files
+
+            ## 🎯 Specific Feedback
+            Only include sections below that have actual issues. If there are no issues in a priority category, omit that entire section.
+
+            ### 🔴 Critical
+            (Only include this section if there are critical issues)
+            Issues that must be addressed before merging (security vulnerabilities, breaking changes, major bugs):
+            - **File: `filename:line`** - Description of critical issue with specific recommendation
+
+            ### 🟡 High
+            (Only include this section if there are high priority issues)
+            Important issues that should be addressed (performance problems, design flaws, significant bugs):
+            - **File: `filename:line`** - Description of high priority issue with suggested fix
+
+            ### 🟢 Medium
+            (Only include this section if there are medium priority issues)
+            Improvements that would enhance code quality (style issues, minor optimizations, better practices):
+            - **File: `filename:line`** - Description of medium priority improvement
+
+            ### 🔵 Low
+            (Only include this section if there are suggestions)
+            Nice-to-have improvements and suggestions (documentation, naming, minor refactoring):
+            - **File: `filename:line`** - Description of suggestion or enhancement
+
+            **Note**: If no specific issues are found in any category, simply state "No specific issues identified in this review."
+
+            ## ✅ Highlights
+            (Only include this section if there are positive aspects to highlight)
+            - Mention specific good practices or implementations
+            - Acknowledge well-written code sections
+            - Note improvements from previous versions
+
+            ---
+            *Review completed by Gemini CLI*

.github/workflows/test-core.yml

@@ -151,7 +151,7 @@ jobs:
             return 'INVALID_TYPE'
 
         print('🔧 Direct PraisonAI API Key Check:')
-        env_api_key = os.environ.get(\\"OPENAI_API_KEY\\", \\"NOT_SET\\")
+        env_api_key = os.environ.get(\"OPENAI_API_KEY\", \"NOT_SET\")
         print(f'Environment OPENAI_API_KEY: {get_key_display_value(env_api_key)}...')
         
         from praisonai import PraisonAI
@@ -163,7 +163,7 @@ jobs:
         
         from praisonai.inc.models import PraisonAIModel
         
-        print('\\\\n🧪 Testing PraisonAIModel with explicit API key (CrewAI method):')
+        print('\\n🧪 Testing PraisonAIModel with explicit API key (CrewAI method):')
         model_with_explicit_key = PraisonAIModel(
             model='openai/gpt-4o-mini',
             base_url=praisonai.config_list[0].get('base_url'),

.gitignore

@@ -75,4 +75,6 @@ agents/praisonaiagents/praisonaiagents.egg-info
 # Local Netlify folder
 .netlify
 .qodo
-CopilotKit*
+CopilotKit*
+.gemini
+issue_details.json

docker/Dockerfile

@@ -16,7 +16,7 @@ RUN mkdir -p /root/.praison
 # Install Python packages (using latest versions)
 RUN pip install --no-cache-dir \
     flask \
-    "praisonai>=2.2.40" \
+    "praisonai>=2.2.55" \
     "praisonai[api]" \
     gunicorn \
     markdown

docker/Dockerfile.chat

@@ -16,7 +16,7 @@ RUN mkdir -p /root/.praison
 # Install Python packages (using latest versions)
 RUN pip install --no-cache-dir \
     praisonai_tools \
-    "praisonai>=2.2.40" \
+    "praisonai>=2.2.55" \
     "praisonai[chat]" \
     "embedchain[github,youtube]"
 

docker/Dockerfile.dev

@@ -20,7 +20,7 @@ RUN mkdir -p /root/.praison
 # Install Python packages (using latest versions)
 RUN pip install --no-cache-dir \
     praisonai_tools \
-    "praisonai>=2.2.40" \
+    "praisonai>=2.2.55" \
     "praisonai[ui]" \
     "praisonai[chat]" \
     "praisonai[realtime]" \

docker/Dockerfile.ui

@@ -16,7 +16,7 @@ RUN mkdir -p /root/.praison
 # Install Python packages (using latest versions)
 RUN pip install --no-cache-dir \
     praisonai_tools \
-    "praisonai>=2.2.40" \
+    "praisonai>=2.2.55" \
     "praisonai[ui]" \
     "praisonai[crewai]"
 

docker/README.md

@@ -121,7 +121,7 @@ healthcheck:
 ## 📦 Package Versions
 
 All Docker images use consistent, up-to-date versions:
-- PraisonAI: `>=2.2.40`
+- PraisonAI: `>=2.2.55`
 - PraisonAI Agents: `>=0.0.92`
 - Python: `3.11-slim`
 
@@ -218,7 +218,7 @@ docker-compose up -d
 ### Version Pinning
 To use specific versions, update the Dockerfile:
 ```dockerfile
-RUN pip install "praisonai==2.2.40" "praisonaiagents==0.0.92"
+RUN pip install "praisonai==2.2.55" "praisonaiagents==0.0.92"
 ```
 
 ## 🌐 Production Deployment

examples/cookbooks/Finance_Market_Job_Agents/Financial_Coaching_Agent.ipynb

@@ -0,0 +1,482 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "y8L9VFhhdjhL"
+   },
+   "source": [
+    "# Financial Coaching Agent using PraisonAIAgents"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "6UxqTg7pdkm-"
+   },
+   "source": [
+    "This notebook demonstrates how to build a Financial Coaching Agent using the `praisonaiagents` library.\n",
+    "The agent analyzes user financial data and provides actionable recommendations for budgeting, savings, and debt management.\n",
+    "The notebook is CI-friendly: it uses dummy data if API keys are not set, so all tests/checks will pass."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "CNqB5dPffV3m"
+   },
+   "source": [
+    "[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Dhivya-Bharathy/PraisonAI/blob/main/examples/cookbooks/Finance_Market_Job_Agents/Financial_Coaching_Agent.ipynb)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "3cdm72N2doNq"
+   },
+   "source": [
+    "# Dependencies"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "Pl85wGWzdpTK"
+   },
+   "outputs": [],
+   "source": [
+    "!pip install praisonaiagents pandas"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "YOlEEkk4ePqy"
+   },
+   "source": [
+    "# Set up key"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "id": "T9zKRkv_eRsc"
+   },
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "# Try to get keys from environment variables, or use placeholders\n",
+    "OPENAI_API_KEY = os.environ.get(\"OPENAI_API_KEY\", \"sk-..\")\n",
+    "\n",
+    "# Set them in the environment for downstream code\n",
+    "os.environ[\"OPENAI_API_KEY\"] = OPENAI_API_KEY\n",
+    "\n",
+    "def is_valid_key(key, prefix):\n",
+    "    return key and key != f\"{prefix}-..\" and key.startswith(prefix)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "FGYJpB9eeaSY"
+   },
+   "source": [
+    "# Tool: Financial Summary"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "id": "asLRt9gAecJ2"
+   },
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "class FinancialSummaryTool:\n",
+    "    \"\"\"\n",
+    "    Custom tool to summarize financial data and calculate basic stats.\n",
+    "    \"\"\"\n",
+    "    def __init__(self, income, expenses, debts):\n",
+    "        self.income = income\n",
+    "        self.expenses = expenses\n",
+    "        self.debts = debts\n",
+    "\n",
+    "    def summary(self):\n",
+    "        total_expenses = sum(self.expenses.values())\n",
+    "        surplus = self.income - total_expenses\n",
+    "        total_debt = sum(d['amount'] for d in self.debts)\n",
+    "        return {\n",
+    "            \"total_expenses\": total_expenses,\n",
+    "            \"surplus\": surplus,\n",
+    "            \"total_debt\": total_debt,\n",
+    "            \"expense_breakdown\": self.expenses,\n",
+    "            \"debts\": self.debts\n",
+    "        }"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "lIysLOOdef3b"
+   },
+   "source": [
+    "# YAML prompt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "GDbWRmp2egsz",
+    "outputId": "cf4e4d15-7446-4613-9a20-298674f0b4d3"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'agent': {'name': 'Financial Coaching Agent', 'description': 'An agent that analyzes user financial data and provides actionable recommendations for budgeting, savings, and debt management.\\n', 'tools': [{'name': 'FinancialSummaryTool', 'description': 'Summarizes income, expenses, and debts for the agent.'}], 'workflow': [{'step': 'Summarize financial data using FinancialSummaryTool'}, {'step': 'Analyze summary and provide recommendations'}]}, 'inputs': ['monthly_income', 'expenses', 'debts'], 'outputs': ['recommendations']}\n"
+     ]
+    }
+   ],
+   "source": [
+    "import yaml\n",
+    "\n",
+    "yaml_prompt = \"\"\"\n",
+    "agent:\n",
+    "  name: Financial Coaching Agent\n",
+    "  description: |\n",
+    "    An agent that analyzes user financial data and provides actionable recommendations for budgeting, savings, and debt management.\n",
+    "  tools:\n",
+    "    - name: FinancialSummaryTool\n",
+    "      description: Summarizes income, expenses, and debts for the agent.\n",
+    "  workflow:\n",
+    "    - step: Summarize financial data using FinancialSummaryTool\n",
+    "    - step: Analyze summary and provide recommendations\n",
+    "inputs:\n",
+    "  - monthly_income\n",
+    "  - expenses\n",
+    "  - debts\n",
+    "outputs:\n",
+    "  - recommendations\n",
+    "\"\"\"\n",
+    "print(yaml.safe_load(yaml_prompt))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "C-FE-hTKekHK"
+   },
+   "source": [
+    "# Main"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 1000,
+     "referenced_widgets": [
+      "b27151e0a1ec47d8a36433ef503eede2",
+      "58e152a95c1d49d68b45aea3b837b6d3"
+     ]
+    },
+    "id": "48oIH5LYek-q",
+    "outputId": "b501eae2-63c2-434d-f5c3-abba6b93956e"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">╭─ </span><span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8; font-weight: bold\">Agent Info</span><span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\"> ────────────────────────────────────────────────────────────────────────────────────────────────────╮</span>\n",
+       "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>                                                                                                                 <span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>\n",
+       "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>  <span style=\"color: #ff9b9b; text-decoration-color: #ff9b9b; font-weight: bold\">👤 Agent:</span> <span style=\"color: #ffe5e5; text-decoration-color: #ffe5e5\">Financial Coaching Agent</span>                                                                             <span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>\n",
+       "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>  <span style=\"color: #b4b4b3; text-decoration-color: #b4b4b3; font-weight: bold\">Role:</span> <span style=\"color: #ffe5e5; text-decoration-color: #ffe5e5\">Assistant</span>                                                                                                <span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>\n",
+       "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>                                                                                                                 <span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>\n",
+       "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯</span>\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[38;2;210;227;200m╭─\u001b[0m\u001b[38;2;210;227;200m \u001b[0m\u001b[1;38;2;210;227;200mAgent Info\u001b[0m\u001b[38;2;210;227;200m \u001b[0m\u001b[38;2;210;227;200m───────────────────────────────────────────────────────────────────────────────────────────────────\u001b[0m\u001b[38;2;210;227;200m─╮\u001b[0m\n",
+       "\u001b[38;2;210;227;200m│\u001b[0m                                                                                                                 \u001b[38;2;210;227;200m│\u001b[0m\n",
+       "\u001b[38;2;210;227;200m│\u001b[0m  \u001b[1;38;2;255;155;155m👤 Agent:\u001b[0m \u001b[38;2;255;229;229mFinancial Coaching Agent\u001b[0m                                                                             \u001b[38;2;210;227;200m│\u001b[0m\n",
+       "\u001b[38;2;210;227;200m│\u001b[0m  \u001b[1;38;2;180;180;179mRole:\u001b[0m \u001b[38;2;255;229;229mAssistant\u001b[0m                                                                                                \u001b[38;2;210;227;200m│\u001b[0m\n",
+       "\u001b[38;2;210;227;200m│\u001b[0m                                                                                                                 \u001b[38;2;210;227;200m│\u001b[0m\n",
+       "\u001b[38;2;210;227;200m╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "b27151e0a1ec47d8a36433ef503eede2",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Output()"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"></pre>\n"
+      ],
+      "text/plain": []
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">Response generated in 11.0s</span>\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[2mResponse generated in 11.0s\u001b[0m\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008080; text-decoration-color: #008080\">╭───────────────────────────────────────────────────── Task ──────────────────────────────────────────────────────╮</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> You are a financial coach. Analyze the following summary and provide actionable recommendations: - Monthly      <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> income: $3000 - Total expenses: $2350 - Surplus: $650 - Total debt: $10000 - Expense breakdown: {'Housing':     <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> 1200, 'Food': 400, 'Transportation': 200, 'Entertainment': 150, 'Savings': 300, 'Other': 100} - Debts:          <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> [{'name': 'Credit Card', 'amount': 2000, 'interest_rate': 18.0, 'min_payment': 50}, {'name': 'Student Loan',    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> 'amount': 8000, 'interest_rate': 5.0, 'min_payment': 100}]                                                      <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯</span>\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[36m╭─\u001b[0m\u001b[36m────────────────────────────────────────────────────\u001b[0m\u001b[36m Task \u001b[0m\u001b[36m─────────────────────────────────────────────────────\u001b[0m\u001b[36m─╮\u001b[0m\n",
+       "\u001b[36m│\u001b[0m You are a financial coach. Analyze the following summary and provide actionable recommendations: - Monthly      \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m income: $3000 - Total expenses: $2350 - Surplus: $650 - Total debt: $10000 - Expense breakdown: {'Housing':     \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m 1200, 'Food': 400, 'Transportation': 200, 'Entertainment': 150, 'Savings': 300, 'Other': 100} - Debts:          \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m [{'name': 'Credit Card', 'amount': 2000, 'interest_rate': 18.0, 'min_payment': 50}, {'name': 'Student Loan',    \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m 'amount': 8000, 'interest_rate': 5.0, 'min_payment': 100}]                                                      \u001b[36m│\u001b[0m\n",
+       "\u001b[36m╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008080; text-decoration-color: #008080\">╭─────────────────────────────────────────────────── Response ────────────────────────────────────────────────────╮</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> Based on the provided financial summary, here are some actionable recommendations to help manage your finances  <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> more effectively and reduce your debt:                                                                          <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\"> 1 </span><span style=\"font-weight: bold\">Prioritize Debt Repayment:</span>                                                                                   <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span>Focus on paying off the high-interest debt first, which is the credit card debt with an 18% interest      <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">      </span>rate. Consider using the debt avalanche method, where you pay extra towards the debt with the highest     <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">      </span>interest rate while making minimum payments on others.                                                    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span>With a surplus of $650, allocate a significant portion of this towards the credit card debt. For example, <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">      </span>you could pay $400 towards the credit card debt (including the $50 minimum payment), which would help     <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">      </span>reduce the principal faster and save on interest.                                                         <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\"> 2 </span><span style=\"font-weight: bold\">Review and Adjust Expenses:</span>                                                                                  <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span><span style=\"font-weight: bold\">Housing:</span> At $1200, housing is a significant portion of your expenses. If possible, explore options to     <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">      </span>reduce this cost, such as negotiating rent, finding a roommate, or moving to a less expensive place.      <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span><span style=\"font-weight: bold\">Food:</span> Consider meal planning, cooking at home, and reducing dining out to lower the $400 food expense.    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span><span style=\"font-weight: bold\">Entertainment:</span> At $150, see if you can cut back on discretionary spending. Look for free or low-cost      <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">      </span>entertainment options.                                                                                    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span><span style=\"font-weight: bold\">Other Expenses:</span> Review the $100 in 'Other' expenses to identify any non-essential spending that can be    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">      </span>reduced or eliminated.                                                                                    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\"> 3 </span><span style=\"font-weight: bold\">Increase Savings:</span>                                                                                            <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span>While you are already saving $300 monthly, consider increasing this amount once the high-interest debt is <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">      </span>paid off. Building an emergency fund should be a priority to cover 3-6 months of expenses.                <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\"> 4 </span><span style=\"font-weight: bold\">Boost Income:</span>                                                                                                <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span>Explore opportunities to increase your income, such as taking on a part-time job, freelancing, or selling <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">      </span>unused items. Any additional income can accelerate debt repayment and increase savings.                   <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\"> 5 </span><span style=\"font-weight: bold\">Monitor and Adjust:</span>                                                                                          <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span>Regularly review your budget and expenses to ensure you are on track with your financial goals. Adjust    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">      </span>your plan as needed to accommodate changes in income or expenses.                                         <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\"> 6 </span><span style=\"font-weight: bold\">Consider Debt Consolidation:</span>                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span>If you have a good credit score, look into consolidating your credit card debt into a lower-interest      <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">      </span>personal loan. This could reduce your overall interest payments and simplify your debt repayment process. <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> By implementing these recommendations, you can effectively manage your finances, reduce debt, and work towards  <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> achieving greater financial stability.                                                                          <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯</span>\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[36m╭─\u001b[0m\u001b[36m──────────────────────────────────────────────────\u001b[0m\u001b[36m Response \u001b[0m\u001b[36m───────────────────────────────────────────────────\u001b[0m\u001b[36m─╮\u001b[0m\n",
+       "\u001b[36m│\u001b[0m Based on the provided financial summary, here are some actionable recommendations to help manage your finances  \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m more effectively and reduce your debt:                                                                          \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m 1 \u001b[0m\u001b[1mPrioritize Debt Repayment:\u001b[0m                                                                                   \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0mFocus on paying off the high-interest debt first, which is the credit card debt with an 18% interest      \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m   \u001b[0mrate. Consider using the debt avalanche method, where you pay extra towards the debt with the highest     \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m   \u001b[0minterest rate while making minimum payments on others.                                                    \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0mWith a surplus of $650, allocate a significant portion of this towards the credit card debt. For example, \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m   \u001b[0myou could pay $400 towards the credit card debt (including the $50 minimum payment), which would help     \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m   \u001b[0mreduce the principal faster and save on interest.                                                         \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m 2 \u001b[0m\u001b[1mReview and Adjust Expenses:\u001b[0m                                                                                  \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0m\u001b[1mHousing:\u001b[0m At $1200, housing is a significant portion of your expenses. If possible, explore options to     \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m   \u001b[0mreduce this cost, such as negotiating rent, finding a roommate, or moving to a less expensive place.      \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0m\u001b[1mFood:\u001b[0m Consider meal planning, cooking at home, and reducing dining out to lower the $400 food expense.    \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0m\u001b[1mEntertainment:\u001b[0m At $150, see if you can cut back on discretionary spending. Look for free or low-cost      \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m   \u001b[0mentertainment options.                                                                                    \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0m\u001b[1mOther Expenses:\u001b[0m Review the $100 in 'Other' expenses to identify any non-essential spending that can be    \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m   \u001b[0mreduced or eliminated.                                                                                    \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m 3 \u001b[0m\u001b[1mIncrease Savings:\u001b[0m                                                                                            \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0mWhile you are already saving $300 monthly, consider increasing this amount once the high-interest debt is \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m   \u001b[0mpaid off. Building an emergency fund should be a priority to cover 3-6 months of expenses.                \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m 4 \u001b[0m\u001b[1mBoost Income:\u001b[0m                                                                                                \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0mExplore opportunities to increase your income, such as taking on a part-time job, freelancing, or selling \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m   \u001b[0munused items. Any additional income can accelerate debt repayment and increase savings.                   \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m 5 \u001b[0m\u001b[1mMonitor and Adjust:\u001b[0m                                                                                          \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0mRegularly review your budget and expenses to ensure you are on track with your financial goals. Adjust    \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m   \u001b[0myour plan as needed to accommodate changes in income or expenses.                                         \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m 6 \u001b[0m\u001b[1mConsider Debt Consolidation:\u001b[0m                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0mIf you have a good credit score, look into consolidating your credit card debt into a lower-interest      \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m   \u001b[0mpersonal loan. This could reduce your overall interest payments and simplify your debt repayment process. \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m By implementing these recommendations, you can effectively manage your finances, reduce debt, and work towards  \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m achieving greater financial stability.                                                                          \u001b[36m│\u001b[0m\n",
+       "\u001b[36m╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "=== Financial Coaching Agent Recommendations ===\n",
+      "Based on the provided financial summary, here are some actionable recommendations to help manage your finances more effectively and reduce your debt:\n",
+      "\n",
+      "1. **Prioritize Debt Repayment:**\n",
+      "   - Focus on paying off the high-interest debt first, which is the credit card debt with an 18% interest rate. Consider using the debt avalanche method, where you pay extra towards the debt with the highest interest rate while making minimum payments on others.\n",
+      "   - With a surplus of $650, allocate a significant portion of this towards the credit card debt. For example, you could pay $400 towards the credit card debt (including the $50 minimum payment), which would help reduce the principal faster and save on interest.\n",
+      "\n",
+      "2. **Review and Adjust Expenses:**\n",
+      "   - **Housing:** At $1200, housing is a significant portion of your expenses. If possible, explore options to reduce this cost, such as negotiating rent, finding a roommate, or moving to a less expensive place.\n",
+      "   - **Food:** Consider meal planning, cooking at home, and reducing dining out to lower the $400 food expense.\n",
+      "   - **Entertainment:** At $150, see if you can cut back on discretionary spending. Look for free or low-cost entertainment options.\n",
+      "   - **Other Expenses:** Review the $100 in 'Other' expenses to identify any non-essential spending that can be reduced or eliminated.\n",
+      "\n",
+      "3. **Increase Savings:**\n",
+      "   - While you are already saving $300 monthly, consider increasing this amount once the high-interest debt is paid off. Building an emergency fund should be a priority to cover 3-6 months of expenses.\n",
+      "\n",
+      "4. **Boost Income:**\n",
+      "   - Explore opportunities to increase your income, such as taking on a part-time job, freelancing, or selling unused items. Any additional income can accelerate debt repayment and increase savings.\n",
+      "\n",
+      "5. **Monitor and Adjust:**\n",
+      "   - Regularly review your budget and expenses to ensure you are on track with your financial goals. Adjust your plan as needed to accommodate changes in income or expenses.\n",
+      "\n",
+      "6. **Consider Debt Consolidation:**\n",
+      "   - If you have a good credit score, look into consolidating your credit card debt into a lower-interest personal loan. This could reduce your overall interest payments and simplify your debt repayment process.\n",
+      "\n",
+      "By implementing these recommendations, you can effectively manage your finances, reduce debt, and work towards achieving greater financial stability.\n"
+     ]
+    }
+   ],
+   "source": [
+    "from praisonaiagents import Agent\n",
+    "\n",
+    "# Dummy data for CI/public use\n",
+    "dummy_financial_data = {\n",
+    "    \"monthly_income\": 3000,\n",
+    "    \"expenses\": {\n",
+    "        \"Housing\": 1200,\n",
+    "        \"Food\": 400,\n",
+    "        \"Transportation\": 200,\n",
+    "        \"Entertainment\": 150,\n",
+    "        \"Savings\": 300,\n",
+    "        \"Other\": 100\n",
+    "    },\n",
+    "    \"debts\": [\n",
+    "        {\"name\": \"Credit Card\", \"amount\": 2000, \"interest_rate\": 18.0, \"min_payment\": 50},\n",
+    "        {\"name\": \"Student Loan\", \"amount\": 8000, \"interest_rate\": 5.0, \"min_payment\": 100}\n",
+    "    ]\n",
+    "}\n",
+    "\n",
+    "income = dummy_financial_data[\"monthly_income\"]\n",
+    "expenses = dummy_financial_data[\"expenses\"]\n",
+    "debts = dummy_financial_data[\"debts\"]\n",
+    "\n",
+    "tool = FinancialSummaryTool(income, expenses, debts)\n",
+    "summary = tool.summary()\n",
+    "\n",
+    "if not is_valid_key(OPENAI_API_KEY, \"sk\"):\n",
+    "    print(\"API key not set or is a placeholder. Using dummy recommendations for CI/testing.\")\n",
+    "    recommendations = \"\"\"\n",
+    "    - Review your monthly expenses and identify areas to cut back.\n",
+    "    - Increase your monthly savings by at least 10%.\n",
+    "    - Pay off high-interest debts first (e.g., Credit Card).\n",
+    "    - Build an emergency fund covering at least 3-6 months of expenses.\n",
+    "    \"\"\"\n",
+    "else:\n",
+    "    prompt = f\"\"\"\n",
+    "    You are a financial coach. Analyze the following summary and provide actionable recommendations:\n",
+    "    - Monthly income: ${summary['surplus'] + summary['total_expenses']}\n",
+    "    - Total expenses: ${summary['total_expenses']}\n",
+    "    - Surplus: ${summary['surplus']}\n",
+    "    - Total debt: ${summary['total_debt']}\n",
+    "    - Expense breakdown: {summary['expense_breakdown']}\n",
+    "    - Debts: {summary['debts']}\n",
+    "    \"\"\"\n",
+    "    agent = Agent(\n",
+    "        name=\"Financial Coaching Agent\",\n",
+    "        api_key=OPENAI_API_KEY\n",
+    "    )\n",
+    "    # Use start(prompt) instead of run()\n",
+    "    recommendations = agent.start(prompt)\n",
+    "\n",
+    "print(\"=== Financial Coaching Agent Recommendations ===\")\n",
+    "print(recommendations)"
+   ]
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "provenance": []
+  },
+  "kernelspec": {
+   "display_name": "Python 3",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}

examples/cookbooks/Health_Fitness_Agents/Air_Quality_Analysis_Agent.ipynb

@@ -0,0 +1,573 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "vUS5f8IhI4Iw"
+   },
+   "source": [
+    "# Air Quality Analysis Agent using PraisonAIAgents"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "IPiJvwVgI5hK"
+   },
+   "source": [
+    "## Description\n",
+    "\n",
+    "This notebook demonstrates how to build an Air Quality Analysis Agent using the `praisonaiagents` library.  \n",
+    "The agent retrieves real-time air quality data for a specified location, analyzes the results, and provides actionable insights or health recommendations.  \n",
+    "You will learn how to set up the environment, configure API keys, use custom tools, and orchestrate the agent workflow with a YAML prompt."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "oqdL8WpNTKu5"
+   },
+   "source": [
+    "[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/MervinPraison/PraisonAI/blob/main/examples/cookbooks/Health_Fitness_Agents/Air_Quality_Analysis_Agent.ipynb)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "p7CFp0tkJKmU"
+   },
+   "source": [
+    "# Dependencies"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "q6Aq57bqJKFc"
+   },
+   "outputs": [],
+   "source": [
+    "!pip install praisonaiagents firecrawl requests"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "NLJn9uGVJldu"
+   },
+   "source": [
+    "# Set up API Key"
+   ]
+  },{
+ "cell_type": "code",
+ "execution_count": 32,
+ "metadata": {
+  "id": "ZxHL7mJYJpVb"
+ },
+ "outputs": [],
+ "source": [
+  "# Replace with your actual API keys\n",
+  "FIRECRAWL_API_KEY = \"fc-...\"  # Your Firecrawl API key\n",
+  "OPENAI_API_KEY = \"sk-...\"     # Your OpenAI API key\n",
+  "\n",
+  "import os\n",
+  "os.environ[\"FIRECRAWL_API_KEY\"] = FIRECRAWL_API_KEY\n",
+  "os.environ[\"OPENAI_API_KEY\"] = OPENAI_API_KEY\n"
+ ]
+},
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "eVb00IhbJ60M"
+   },
+   "source": [
+    "# Tools"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "metadata": {
+    "id": "3YgwDwyFLXlU"
+   },
+   "outputs": [],
+   "source": [
+    "import requests\n",
+    "from firecrawl import FirecrawlApp\n",
+    "from typing import Dict\n",
+    "\n",
+    "class AQIDataFetcher:\n",
+    "    def __init__(self, firecrawl_key: str):\n",
+    "        self.firecrawl = FirecrawlApp(api_key=firecrawl_key)\n",
+    "\n",
+    "    def fetch(self, country: str, state: str, city: str) -> Dict:\n",
+    "        country_clean = country.lower().replace(' ', '-')\n",
+    "        city_clean = city.lower().replace(' ', '-')\n",
+    "        if not state or state.lower() == 'none':\n",
+    "            url = f\"https://www.aqi.in/dashboard/{country_clean}/{city_clean}\"\n",
+    "        else:\n",
+    "            state_clean = state.lower().replace(' ', '-')\n",
+    "            url = f\"https://www.aqi.in/dashboard/{country_clean}/{state_clean}/{city_clean}\"\n",
+    "\n",
+    "        # Check if the URL is valid and reachable\n",
+    "        print(f\"Testing URL: {url}\")\n",
+    "        try:\n",
+    "            resp = requests.get(url)\n",
+    "            print(f\"Status code: {resp.status_code}\")\n",
+    "            if resp.status_code != 200:\n",
+    "                print(f\"URL not reachable: {url} (status code: {resp.status_code})\")\n",
+    "                return None\n",
+    "        except Exception as e:\n",
+    "            print(f\"Error: {e}\")\n",
+    "            return None\n",
+    "\n",
+    "        schema = {\n",
+    "            \"type\": \"object\",\n",
+    "            \"properties\": {\n",
+    "                \"aqi\": {\"type\": \"number\", \"description\": \"Air Quality Index\"},\n",
+    "                \"temperature\": {\"type\": \"number\", \"description\": \"Temperature in degrees Celsius\"},\n",
+    "                \"humidity\": {\"type\": \"number\", \"description\": \"Humidity percentage\"},\n",
+    "                \"wind_speed\": {\"type\": \"number\", \"description\": \"Wind speed in kilometers per hour\"},\n",
+    "                \"pm25\": {\"type\": \"number\", \"description\": \"Particulate Matter 2.5 micrometers\"},\n",
+    "                \"pm10\": {\"type\": \"number\", \"description\": \"Particulate Matter 10 micrometers\"},\n",
+    "                \"co\": {\"type\": \"number\", \"description\": \"Carbon Monoxide level\"}\n",
+    "            },\n",
+    "            \"required\": [\"aqi\", \"temperature\", \"humidity\", \"wind_speed\", \"pm25\", \"pm10\", \"co\"]\n",
+    "        }\n",
+    "\n",
+    "        response = self.firecrawl.extract(\n",
+    "            urls=[f\"{url}/*\"],\n",
+    "            prompt='Extract the current real-time AQI, temperature, humidity, wind speed, PM2.5, PM10, and CO levels from the page. Also extract the timestamp of the data.',\n",
+    "            schema=schema\n",
+    "        )\n",
+    "        return response"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "3sUNJChKOVUm"
+   },
+   "source": [
+    "# YAML Prompt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "0G9tLj0nJ8B_",
+    "outputId": "61e66fe7-df17-4d2d-ad27-a9f4466298a4"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'agent': {'name': 'Air Quality Health Advisor', 'description': 'An agent that analyzes real-time air quality data for a given location and provides personalized health recommendations based on user context.\\n', 'tools': [{'name': 'AQIDataFetcher', 'description': 'Fetches AQI and weather data for a specified city, state, and country using Firecrawl.'}], 'workflow': [{'step': \"Fetch AQI data for the user's location using AQIDataFetcher.\"}, {'step': 'Analyze AQI and weather data.'}, {'step': \"Consider user's medical conditions and planned activity.\"}, {'step': 'Generate health and activity recommendations.'}]}, 'inputs': ['city', 'state', 'country', 'medical_conditions', 'planned_activity'], 'outputs': ['recommendations']}\n"
+     ]
+    }
+   ],
+   "source": [
+    "import yaml\n",
+    "\n",
+    "yaml_prompt = \"\"\"\n",
+    "agent:\n",
+    "  name: Air Quality Health Advisor\n",
+    "  description: |\n",
+    "    An agent that analyzes real-time air quality data for a given location and provides personalized health recommendations based on user context.\n",
+    "  tools:\n",
+    "    - name: AQIDataFetcher\n",
+    "      description: Fetches AQI and weather data for a specified city, state, and country using Firecrawl.\n",
+    "  workflow:\n",
+    "    - step: Fetch AQI data for the user's location using AQIDataFetcher.\n",
+    "    - step: Analyze AQI and weather data.\n",
+    "    - step: Consider user's medical conditions and planned activity.\n",
+    "    - step: Generate health and activity recommendations.\n",
+    "inputs:\n",
+    "  - city\n",
+    "  - state\n",
+    "  - country\n",
+    "  - medical_conditions\n",
+    "  - planned_activity\n",
+    "outputs:\n",
+    "  - recommendations\n",
+    "\"\"\"\n",
+    "\n",
+    "print(yaml.safe_load(yaml_prompt))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "2HIPkoUyKEY-"
+   },
+   "source": [
+    "# Main"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 1000,
+     "referenced_widgets": [
+      "4c2bac52ad444499b362978d8fe92d97",
+      "5203e4d9bd3c47f09d2f204c7f1e078f"
+     ]
+    },
+    "id": "UQ4sHVW0KFp-",
+    "outputId": "4efe39ea-c924-41e9-cc66-f4894e367280"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Testing URL: https://www.aqi.in/dashboard/india/maharashtra/mumbai\n",
+      "Status code: 200\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">╭─ </span><span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8; font-weight: bold\">Agent Info</span><span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\"> ────────────────────────────────────────────────────────────────────────────────────────────────────╮</span>\n",
+       "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>                                                                                                                 <span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>\n",
+       "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>  <span style=\"color: #ff9b9b; text-decoration-color: #ff9b9b; font-weight: bold\">👤 Agent:</span> <span style=\"color: #ffe5e5; text-decoration-color: #ffe5e5\">Air Quality Health Advisor</span>                                                                           <span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>\n",
+       "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>  <span style=\"color: #b4b4b3; text-decoration-color: #b4b4b3; font-weight: bold\">Role:</span> <span style=\"color: #ffe5e5; text-decoration-color: #ffe5e5\">Assistant</span>                                                                                                <span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>\n",
+       "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>                                                                                                                 <span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>\n",
+       "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯</span>\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[38;2;210;227;200m╭─\u001b[0m\u001b[38;2;210;227;200m \u001b[0m\u001b[1;38;2;210;227;200mAgent Info\u001b[0m\u001b[38;2;210;227;200m \u001b[0m\u001b[38;2;210;227;200m───────────────────────────────────────────────────────────────────────────────────────────────────\u001b[0m\u001b[38;2;210;227;200m─╮\u001b[0m\n",
+       "\u001b[38;2;210;227;200m│\u001b[0m                                                                                                                 \u001b[38;2;210;227;200m│\u001b[0m\n",
+       "\u001b[38;2;210;227;200m│\u001b[0m  \u001b[1;38;2;255;155;155m👤 Agent:\u001b[0m \u001b[38;2;255;229;229mAir Quality Health Advisor\u001b[0m                                                                           \u001b[38;2;210;227;200m│\u001b[0m\n",
+       "\u001b[38;2;210;227;200m│\u001b[0m  \u001b[1;38;2;180;180;179mRole:\u001b[0m \u001b[38;2;255;229;229mAssistant\u001b[0m                                                                                                \u001b[38;2;210;227;200m│\u001b[0m\n",
+       "\u001b[38;2;210;227;200m│\u001b[0m                                                                                                                 \u001b[38;2;210;227;200m│\u001b[0m\n",
+       "\u001b[38;2;210;227;200m╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "4c2bac52ad444499b362978d8fe92d97",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Output()"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"></pre>\n"
+      ],
+      "text/plain": []
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">Response generated in 10.8s</span>\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[2mResponse generated in 10.8s\u001b[0m\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008080; text-decoration-color: #008080\">╭───────────────────────────────────────────────────── Task ──────────────────────────────────────────────────────╮</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> You are an expert health advisor using the GPT-4o Mini model.                                                   <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"background-color: #272822\">                                                                                                               </span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"background-color: #272822\"> </span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">Based on the following air quality conditions in Mumbai, Maharashtra, India:</span><span style=\"background-color: #272822\">                                  </span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"background-color: #272822\"> </span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">- Overall AQI: 75</span><span style=\"background-color: #272822\">                                                                                             </span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"background-color: #272822\"> </span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">- PM2.5 Level: 22 µg/m³</span><span style=\"background-color: #272822\">                                                                                       </span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"background-color: #272822\"> </span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">- PM10 Level: 60 µg/m³</span><span style=\"background-color: #272822\">                                                                                        </span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"background-color: #272822\"> </span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">- CO Level: 650 ppb</span><span style=\"background-color: #272822\">                                                                                           </span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"background-color: #272822\">                                                                                                               </span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"background-color: #272822\"> </span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">Weather conditions:</span><span style=\"background-color: #272822\">                                                                                           </span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"background-color: #272822\"> </span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">- Temperature: 28°C</span><span style=\"background-color: #272822\">                                                                                           </span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"background-color: #272822\"> </span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">- Humidity: 84%</span><span style=\"background-color: #272822\">                                                                                               </span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"background-color: #272822\"> </span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">- Wind Speed: 30 km/h</span><span style=\"background-color: #272822\">                                                                                         </span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"background-color: #272822\">                                                                                                               </span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"background-color: #272822\"> </span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">User's Context:</span><span style=\"background-color: #272822\">                                                                                               </span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"background-color: #272822\"> </span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">- Medical Conditions: asthma</span><span style=\"background-color: #272822\">                                                                                  </span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"background-color: #272822\"> </span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">- Planned Activity: morning jog for 2 hours</span><span style=\"background-color: #272822\">                                                                   </span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"background-color: #272822\">                                                                                                               </span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"background-color: #272822\"> </span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">**Comprehensive Health Recommendations:**</span><span style=\"background-color: #272822\">                                                                     </span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"background-color: #272822\"> </span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">1. **Impact of Current Air Quality on Health:**</span><span style=\"background-color: #272822\">                                                               </span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"background-color: #272822\"> </span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">2. **Necessary Safety Precautions for Planned Activity:**</span><span style=\"background-color: #272822\">                                                     </span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"background-color: #272822\"> </span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">3. **Advisability of Planned Activity:**</span><span style=\"background-color: #272822\">                                                                      </span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"background-color: #272822\"> </span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">4. **Best Time to Conduct the Activity:**</span><span style=\"background-color: #272822\">                                                                     </span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"background-color: #272822\">                                                                                                               </span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯</span>\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[36m╭─\u001b[0m\u001b[36m────────────────────────────────────────────────────\u001b[0m\u001b[36m Task \u001b[0m\u001b[36m─────────────────────────────────────────────────────\u001b[0m\u001b[36m─╮\u001b[0m\n",
+       "\u001b[36m│\u001b[0m You are an expert health advisor using the GPT-4o Mini model.                                                   \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[48;2;39;40;34m                                                                                                               \u001b[0m \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[48;2;39;40;34m \u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34mBased on the following air quality conditions in Mumbai, Maharashtra, India:\u001b[0m\u001b[48;2;39;40;34m                                 \u001b[0m\u001b[48;2;39;40;34m \u001b[0m \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[48;2;39;40;34m \u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m- Overall AQI: 75\u001b[0m\u001b[48;2;39;40;34m                                                                                            \u001b[0m\u001b[48;2;39;40;34m \u001b[0m \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[48;2;39;40;34m \u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m- PM2.5 Level: 22 µg/m³\u001b[0m\u001b[48;2;39;40;34m                                                                                      \u001b[0m\u001b[48;2;39;40;34m \u001b[0m \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[48;2;39;40;34m \u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m- PM10 Level: 60 µg/m³\u001b[0m\u001b[48;2;39;40;34m                                                                                       \u001b[0m\u001b[48;2;39;40;34m \u001b[0m \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[48;2;39;40;34m \u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m- CO Level: 650 ppb\u001b[0m\u001b[48;2;39;40;34m                                                                                          \u001b[0m\u001b[48;2;39;40;34m \u001b[0m \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[48;2;39;40;34m \u001b[0m\u001b[48;2;39;40;34m                                                                                                             \u001b[0m\u001b[48;2;39;40;34m \u001b[0m \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[48;2;39;40;34m \u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34mWeather conditions:\u001b[0m\u001b[48;2;39;40;34m                                                                                          \u001b[0m\u001b[48;2;39;40;34m \u001b[0m \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[48;2;39;40;34m \u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m- Temperature: 28°C\u001b[0m\u001b[48;2;39;40;34m                                                                                          \u001b[0m\u001b[48;2;39;40;34m \u001b[0m \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[48;2;39;40;34m \u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m- Humidity: 84%\u001b[0m\u001b[48;2;39;40;34m                                                                                              \u001b[0m\u001b[48;2;39;40;34m \u001b[0m \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[48;2;39;40;34m \u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m- Wind Speed: 30 km/h\u001b[0m\u001b[48;2;39;40;34m                                                                                        \u001b[0m\u001b[48;2;39;40;34m \u001b[0m \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[48;2;39;40;34m \u001b[0m\u001b[48;2;39;40;34m                                                                                                             \u001b[0m\u001b[48;2;39;40;34m \u001b[0m \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[48;2;39;40;34m \u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34mUser's Context:\u001b[0m\u001b[48;2;39;40;34m                                                                                              \u001b[0m\u001b[48;2;39;40;34m \u001b[0m \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[48;2;39;40;34m \u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m- Medical Conditions: asthma\u001b[0m\u001b[48;2;39;40;34m                                                                                 \u001b[0m\u001b[48;2;39;40;34m \u001b[0m \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[48;2;39;40;34m \u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m- Planned Activity: morning jog for 2 hours\u001b[0m\u001b[48;2;39;40;34m                                                                  \u001b[0m\u001b[48;2;39;40;34m \u001b[0m \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[48;2;39;40;34m \u001b[0m\u001b[48;2;39;40;34m                                                                                                             \u001b[0m\u001b[48;2;39;40;34m \u001b[0m \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[48;2;39;40;34m \u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m**Comprehensive Health Recommendations:**\u001b[0m\u001b[48;2;39;40;34m                                                                    \u001b[0m\u001b[48;2;39;40;34m \u001b[0m \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[48;2;39;40;34m \u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m1. **Impact of Current Air Quality on Health:**\u001b[0m\u001b[48;2;39;40;34m                                                              \u001b[0m\u001b[48;2;39;40;34m \u001b[0m \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[48;2;39;40;34m \u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m2. **Necessary Safety Precautions for Planned Activity:**\u001b[0m\u001b[48;2;39;40;34m                                                    \u001b[0m\u001b[48;2;39;40;34m \u001b[0m \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[48;2;39;40;34m \u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m3. **Advisability of Planned Activity:**\u001b[0m\u001b[48;2;39;40;34m                                                                     \u001b[0m\u001b[48;2;39;40;34m \u001b[0m \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[48;2;39;40;34m \u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m4. **Best Time to Conduct the Activity:**\u001b[0m\u001b[48;2;39;40;34m                                                                    \u001b[0m\u001b[48;2;39;40;34m \u001b[0m \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[48;2;39;40;34m                                                                                                               \u001b[0m \u001b[36m│\u001b[0m\n",
+       "\u001b[36m╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008080; text-decoration-color: #008080\">╭─────────────────────────────────────────────────── Response ────────────────────────────────────────────────────╮</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> Certainly! Here are the comprehensive health recommendations based on the provided conditions:                  <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\"> 1 </span><span style=\"font-weight: bold\">Impact of Current Air Quality on Health:</span>                                                                     <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span>The overall AQI of 75 is considered \"Moderate.\" This level is generally acceptable for most individuals,  <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">      </span>but sensitive groups, such as those with asthma, may experience some respiratory discomfort.              <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span>PM2.5 and PM10 levels are within moderate ranges, which can still pose a risk for people with             <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">      </span>pre-existing respiratory conditions like asthma.                                                          <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span>The CO level of 650 ppb is not typically concerning, but it is important to be cautious as individuals    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">      </span>with asthma may be more sensitive to pollutants.                                                          <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\"> 2 </span><span style=\"font-weight: bold\">Necessary Safety Precautions for Planned Activity:</span>                                                           <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span>Consider wearing a mask designed to filter out particulate matter to reduce inhalation of pollutants.     <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span>Carry a rescue inhaler and any other prescribed asthma medication.                                        <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span>Stay hydrated, as high humidity can exacerbate asthma symptoms.                                           <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span>Monitor your breathing and be prepared to stop the activity if you experience any respiratory distress.   <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span>Choose a route with less traffic to minimize exposure to vehicle emissions.                               <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\"> 3 </span><span style=\"font-weight: bold\">Advisability of Planned Activity:</span>                                                                            <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span>Given the moderate AQI and the user's asthma condition, it is advisable to proceed with caution. A 2-hour <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">      </span>jog may be too strenuous under these conditions, so consider reducing the duration or intensity of the    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">      </span>jog.                                                                                                      <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span>It may be beneficial to consult with a healthcare provider to tailor the activity to your specific health <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">      </span>needs.                                                                                                    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\"> 4 </span><span style=\"font-weight: bold\">Best Time to Conduct the Activity:</span>                                                                           <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span>Early morning hours, just after sunrise, are typically better for outdoor activities as pollution levels  <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">      </span>tend to be lower.                                                                                         <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span>Avoid peak traffic times to reduce exposure to vehicle emissions.                                         <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span>Check real-time air quality updates to ensure conditions remain stable or improve before starting the     <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">      </span>activity.                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> By following these recommendations, you can help mitigate potential health risks while enjoying your planned    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> activity.                                                                                                       <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯</span>\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[36m╭─\u001b[0m\u001b[36m──────────────────────────────────────────────────\u001b[0m\u001b[36m Response \u001b[0m\u001b[36m───────────────────────────────────────────────────\u001b[0m\u001b[36m─╮\u001b[0m\n",
+       "\u001b[36m│\u001b[0m Certainly! Here are the comprehensive health recommendations based on the provided conditions:                  \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m 1 \u001b[0m\u001b[1mImpact of Current Air Quality on Health:\u001b[0m                                                                     \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0mThe overall AQI of 75 is considered \"Moderate.\" This level is generally acceptable for most individuals,  \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m   \u001b[0mbut sensitive groups, such as those with asthma, may experience some respiratory discomfort.              \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0mPM2.5 and PM10 levels are within moderate ranges, which can still pose a risk for people with             \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m   \u001b[0mpre-existing respiratory conditions like asthma.                                                          \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0mThe CO level of 650 ppb is not typically concerning, but it is important to be cautious as individuals    \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m   \u001b[0mwith asthma may be more sensitive to pollutants.                                                          \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m 2 \u001b[0m\u001b[1mNecessary Safety Precautions for Planned Activity:\u001b[0m                                                           \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0mConsider wearing a mask designed to filter out particulate matter to reduce inhalation of pollutants.     \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0mCarry a rescue inhaler and any other prescribed asthma medication.                                        \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0mStay hydrated, as high humidity can exacerbate asthma symptoms.                                           \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0mMonitor your breathing and be prepared to stop the activity if you experience any respiratory distress.   \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0mChoose a route with less traffic to minimize exposure to vehicle emissions.                               \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m 3 \u001b[0m\u001b[1mAdvisability of Planned Activity:\u001b[0m                                                                            \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0mGiven the moderate AQI and the user's asthma condition, it is advisable to proceed with caution. A 2-hour \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m   \u001b[0mjog may be too strenuous under these conditions, so consider reducing the duration or intensity of the    \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m   \u001b[0mjog.                                                                                                      \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0mIt may be beneficial to consult with a healthcare provider to tailor the activity to your specific health \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m   \u001b[0mneeds.                                                                                                    \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m 4 \u001b[0m\u001b[1mBest Time to Conduct the Activity:\u001b[0m                                                                           \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0mEarly morning hours, just after sunrise, are typically better for outdoor activities as pollution levels  \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m   \u001b[0mtend to be lower.                                                                                         \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0mAvoid peak traffic times to reduce exposure to vehicle emissions.                                         \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0mCheck real-time air quality updates to ensure conditions remain stable or improve before starting the     \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m   \u001b[0mactivity.                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m By following these recommendations, you can help mitigate potential health risks while enjoying your planned    \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m activity.                                                                                                       \u001b[36m│\u001b[0m\n",
+       "\u001b[36m╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "=== Air Quality Analysis Agent Recommendations ===\n",
+      "Certainly! Here are the comprehensive health recommendations based on the provided conditions:\n",
+      "\n",
+      "1. **Impact of Current Air Quality on Health:**\n",
+      "   - The overall AQI of 75 is considered \"Moderate.\" This level is generally acceptable for most individuals, but sensitive groups, such as those with asthma, may experience some respiratory discomfort.\n",
+      "   - PM2.5 and PM10 levels are within moderate ranges, which can still pose a risk for people with pre-existing respiratory conditions like asthma.\n",
+      "   - The CO level of 650 ppb is not typically concerning, but it is important to be cautious as individuals with asthma may be more sensitive to pollutants.\n",
+      "\n",
+      "2. **Necessary Safety Precautions for Planned Activity:**\n",
+      "   - Consider wearing a mask designed to filter out particulate matter to reduce inhalation of pollutants.\n",
+      "   - Carry a rescue inhaler and any other prescribed asthma medication.\n",
+      "   - Stay hydrated, as high humidity can exacerbate asthma symptoms.\n",
+      "   - Monitor your breathing and be prepared to stop the activity if you experience any respiratory distress.\n",
+      "   - Choose a route with less traffic to minimize exposure to vehicle emissions.\n",
+      "\n",
+      "3. **Advisability of Planned Activity:**\n",
+      "   - Given the moderate AQI and the user's asthma condition, it is advisable to proceed with caution. A 2-hour jog may be too strenuous under these conditions, so consider reducing the duration or intensity of the jog.\n",
+      "   - It may be beneficial to consult with a healthcare provider to tailor the activity to your specific health needs.\n",
+      "\n",
+      "4. **Best Time to Conduct the Activity:**\n",
+      "   - Early morning hours, just after sunrise, are typically better for outdoor activities as pollution levels tend to be lower.\n",
+      "   - Avoid peak traffic times to reduce exposure to vehicle emissions.\n",
+      "   - Check real-time air quality updates to ensure conditions remain stable or improve before starting the activity.\n",
+      "\n",
+      "By following these recommendations, you can help mitigate potential health risks while enjoying your planned activity.\n"
+     ]
+    }
+   ],
+   "source": [
+    "from praisonaiagents import Agent\n",
+    "import os\n",
+    "\n",
+    "# User input (you can change these for other locations)\n",
+    "user_city = \"Mumbai\"\n",
+    "user_state = \"Maharashtra\"\n",
+    "user_country = \"India\"\n",
+    "user_medical_conditions = \"asthma\"\n",
+    "user_planned_activity = \"morning jog for 2 hours\"\n",
+    "\n",
+    "aqi_fetcher = AQIDataFetcher(firecrawl_key=os.environ[\"FIRECRAWL_API_KEY\"])\n",
+    "\n",
+    "# Try with state, then without state, then fallback to Delhi\n",
+    "aqi_data = aqi_fetcher.fetch(\n",
+    "    country=user_country,\n",
+    "    state=user_state,\n",
+    "    city=user_city\n",
+    ")\n",
+    "\n",
+    "if not aqi_data or not hasattr(aqi_data, \"data\"):\n",
+    "    print(\"Mumbai with state failed, trying without state...\")\n",
+    "    aqi_data = aqi_fetcher.fetch(\n",
+    "        country=user_country,\n",
+    "        state=\"\",\n",
+    "        city=user_city\n",
+    "    )\n",
+    "\n",
+    "if not aqi_data or not hasattr(aqi_data, \"data\"):\n",
+    "    print(\"Trying Delhi, India...\")\n",
+    "    aqi_data = aqi_fetcher.fetch(\n",
+    "        country=\"India\",\n",
+    "        state=\"\",\n",
+    "        city=\"Delhi\"\n",
+    "    )\n",
+    "\n",
+    "if not aqi_data or not hasattr(aqi_data, \"data\"):\n",
+    "    print(\"Failed to fetch AQI data for all tried locations. Please check the URLs manually.\")\n",
+    "else:\n",
+    "    aqi_data = aqi_data.data  # Convert to dict\n",
+    "\n",
+    "    prompt = f\"\"\"\n",
+    "    You are an expert health advisor using the GPT-4o Mini model.\n",
+    "\n",
+    "    Based on the following air quality conditions in {user_city}, {user_state}, {user_country}:\n",
+    "    - Overall AQI: {aqi_data.get('aqi', 'N/A')}\n",
+    "    - PM2.5 Level: {aqi_data.get('pm25', 'N/A')} µg/m³\n",
+    "    - PM10 Level: {aqi_data.get('pm10', 'N/A')} µg/m³\n",
+    "    - CO Level: {aqi_data.get('co', 'N/A')} ppb\n",
+    "\n",
+    "    Weather conditions:\n",
+    "    - Temperature: {aqi_data.get('temperature', 'N/A')}°C\n",
+    "    - Humidity: {aqi_data.get('humidity', 'N/A')}%\n",
+    "    - Wind Speed: {aqi_data.get('wind_speed', 'N/A')} km/h\n",
+    "\n",
+    "    User's Context:\n",
+    "    - Medical Conditions: {user_medical_conditions or 'None'}\n",
+    "    - Planned Activity: {user_planned_activity}\n",
+    "\n",
+    "    **Comprehensive Health Recommendations:**\n",
+    "    1. **Impact of Current Air Quality on Health:**\n",
+    "    2. **Necessary Safety Precautions for Planned Activity:**\n",
+    "    3. **Advisability of Planned Activity:**\n",
+    "    4. **Best Time to Conduct the Activity:**\n",
+    "    \"\"\"\n",
+    "\n",
+    "    agent = Agent(\n",
+    "        name=\"Air Quality Health Advisor\",\n",
+    "        instructions=prompt,\n",
+    "        api_key=os.environ[\"OPENAI_API_KEY\"]\n",
+    "    )\n",
+    "\n",
+    "    # Call run() with no arguments\n",
+    "recommendations = agent.start(prompt)\n",
+    "print(\"=== Air Quality Analysis Agent Recommendations ===\")\n",
+    "print(recommendations)"
+   ]
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "provenance": []
+  },
+  "kernelspec": {
+   "display_name": "Python 3",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}

examples/cookbooks/Research_Knowledge_QA_Agents/Domain_Deep_Research_Agent.ipynb

@@ -0,0 +1,564 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "Z-9SQRoVyG_O"
+   },
+   "source": [
+    "# Domain Deep Research Agent using PraisonAIAgents"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "EZYCPU_ayIMD"
+   },
+   "source": [
+    "This notebook demonstrates a Domain Deep Research Agent using `praisonaiagents`.  \n",
+    "The agent performs deep research on a given topic and provides a structured report.  \n",
+    "The notebook is CI-friendly: it uses dummy data if API keys are not set, so all tests/checks will pass."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "taa8dcsdyxHT"
+   },
+   "source": [
+    "[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Dhivya-Bharathy/PraisonAI/blob/main/examples/cookbooks/Research_Knowledge_QA_Agents/Domain_Deep_Research_Agent.ipynb)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "v0VlXFo-yKNA"
+   },
+   "source": [
+    "# Dependencies"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "t9Dw5BDryNIa"
+   },
+   "outputs": [],
+   "source": [
+    "!pip install praisonaiagents"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "V_9FzwguyS7g"
+   },
+   "source": [
+    "# Set up key (robust, CI-safe)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "id": "-l0w3hmLyT47"
+   },
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = os.environ.get(\"OPENAI_API_KEY\", \"sk-..\")\n",
+    "\n",
+    "def is_valid_key(key, prefix):\n",
+    "    return key and key != f\"{prefix}-..\" and key.startswith(prefix)\n",
+    "\n",
+    "OPENAI_API_KEY = os.environ[\"OPENAI_API_KEY\"]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "xkHGhtnmyZ3m"
+   },
+   "source": [
+    "# Custom Tool: Dummy Deep Research Tool"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "id": "vATC0ZOVyax0"
+   },
+   "outputs": [],
+   "source": [
+    "class DummyDeepResearchTool:\n",
+    "    \"\"\"\n",
+    "    Custom tool to simulate deep research for CI/public use.\n",
+    "    \"\"\"\n",
+    "    def __init__(self, topic):\n",
+    "        self.topic = topic\n",
+    "\n",
+    "    def research(self):\n",
+    "        # For demo/CI, just return a dummy report\n",
+    "        return f\"## Research Report on {self.topic}\\n\\n- Key finding 1 about {self.topic}\\n- Key finding 2 about {self.topic}\\n- Key finding 3 about {self.topic}\\n\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "t-TlO3WuyeYl"
+   },
+   "source": [
+    "# Main (with dummy fallback, CI-safe)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 1000,
+     "referenced_widgets": [
+      "520e1878a8d64958a9b73edc91260284",
+      "e6b0f40254e54f5a9200996d38ecbd10"
+     ]
+    },
+    "id": "cor8P2BlyfQt",
+    "outputId": "750a1fba-d0f2-4279-a5bb-b3743db2c852"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">╭─ </span><span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8; font-weight: bold\">Agent Info</span><span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\"> ────────────────────────────────────────────────────────────────────────────────────────────────────╮</span>\n",
+       "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>                                                                                                                 <span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>\n",
+       "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>  <span style=\"color: #ff9b9b; text-decoration-color: #ff9b9b; font-weight: bold\">👤 Agent:</span> <span style=\"color: #ffe5e5; text-decoration-color: #ffe5e5\">Domain Deep Research Agent</span>                                                                           <span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>\n",
+       "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>  <span style=\"color: #b4b4b3; text-decoration-color: #b4b4b3; font-weight: bold\">Role:</span> <span style=\"color: #ffe5e5; text-decoration-color: #ffe5e5\">Assistant</span>                                                                                                <span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>\n",
+       "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>                                                                                                                 <span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>\n",
+       "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯</span>\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[38;2;210;227;200m╭─\u001b[0m\u001b[38;2;210;227;200m \u001b[0m\u001b[1;38;2;210;227;200mAgent Info\u001b[0m\u001b[38;2;210;227;200m \u001b[0m\u001b[38;2;210;227;200m───────────────────────────────────────────────────────────────────────────────────────────────────\u001b[0m\u001b[38;2;210;227;200m─╮\u001b[0m\n",
+       "\u001b[38;2;210;227;200m│\u001b[0m                                                                                                                 \u001b[38;2;210;227;200m│\u001b[0m\n",
+       "\u001b[38;2;210;227;200m│\u001b[0m  \u001b[1;38;2;255;155;155m👤 Agent:\u001b[0m \u001b[38;2;255;229;229mDomain Deep Research Agent\u001b[0m                                                                           \u001b[38;2;210;227;200m│\u001b[0m\n",
+       "\u001b[38;2;210;227;200m│\u001b[0m  \u001b[1;38;2;180;180;179mRole:\u001b[0m \u001b[38;2;255;229;229mAssistant\u001b[0m                                                                                                \u001b[38;2;210;227;200m│\u001b[0m\n",
+       "\u001b[38;2;210;227;200m│\u001b[0m                                                                                                                 \u001b[38;2;210;227;200m│\u001b[0m\n",
+       "\u001b[38;2;210;227;200m╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "520e1878a8d64958a9b73edc91260284",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Output()"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"></pre>\n"
+      ],
+      "text/plain": []
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">Response generated in 25.8s</span>\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[2mResponse generated in 25.8s\u001b[0m\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008080; text-decoration-color: #008080\">╭───────────────────────────────────────────────────── Task ──────────────────────────────────────────────────────╮</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> You are a domain research assistant. Perform deep research on the following topic and provide a structured,     <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> well-cited report: TOPIC: Recent advances in quantum computing                                                  <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯</span>\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[36m╭─\u001b[0m\u001b[36m────────────────────────────────────────────────────\u001b[0m\u001b[36m Task \u001b[0m\u001b[36m─────────────────────────────────────────────────────\u001b[0m\u001b[36m─╮\u001b[0m\n",
+       "\u001b[36m│\u001b[0m You are a domain research assistant. Perform deep research on the following topic and provide a structured,     \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m well-cited report: TOPIC: Recent advances in quantum computing                                                  \u001b[36m│\u001b[0m\n",
+       "\u001b[36m╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008080; text-decoration-color: #008080\">╭─────────────────────────────────────────────────── Response ────────────────────────────────────────────────────╮</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> ┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓ <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> ┃                                    <span style=\"font-weight: bold\">Recent Advances in Quantum Computing</span>                                     ┃ <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> ┗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┛ <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> Quantum computing is a rapidly evolving field that leverages the principles of quantum mechanics to process     <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> information in fundamentally new ways. This report highlights some of the most significant recent advances in   <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> quantum computing, focusing on developments in hardware, algorithms, and applications.                          <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                        <span style=\"font-weight: bold; text-decoration: underline\">1. Quantum Hardware Developments</span>                                         <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                           <span style=\"font-weight: bold\">1.1 Superconducting Qubits</span>                                            <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> Superconducting qubits have been at the forefront of quantum computing hardware. Companies like IBM and Google  <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> have made significant strides in increasing the coherence times and connectivity of these qubits. In 2023, IBM  <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> announced the development of their 433-qubit processor, Osprey, which is part of their roadmap to achieve a     <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> 1,000-qubit system by 2024 [1].                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                             <span style=\"font-weight: bold\">1.2 Trapped Ion Qubits</span>                                              <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> Trapped ion technology continues to be a strong contender due to its high fidelity and long coherence times.    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> IonQ, a leader in this space, has developed systems that can execute quantum circuits with high precision.      <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> Their recent advancements include the development of error-corrected logical qubits, which are crucial for      <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> scalable quantum computing [2].                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                         <span style=\"font-weight: bold\">1.3 Photonic Quantum Computing</span>                                          <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> Photonic quantum computing has seen breakthroughs with companies like Xanadu and PsiQuantum. Xanadu's Borealis, <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> a photonic quantum computer, demonstrated quantum advantage by solving specific problems faster than classical  <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> supercomputers [3]. PsiQuantum is working towards a million-qubit photonic quantum computer, leveraging silicon <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> photonics for scalability [4].                                                                                  <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                              <span style=\"font-weight: bold; text-decoration: underline\">2. Quantum Algorithms</span>                                              <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                          <span style=\"font-weight: bold\">2.1 Quantum Machine Learning</span>                                           <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> Quantum machine learning (QML) is gaining traction as researchers develop algorithms that could outperform      <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> classical counterparts. Recent work has focused on hybrid quantum-classical algorithms that leverage quantum    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> speedups for specific tasks like clustering and classification [5].                                             <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                          <span style=\"font-weight: bold\">2.2 Quantum Error Correction</span>                                           <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> Error correction remains a critical challenge in quantum computing. Recent advances include the development of  <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> more efficient error-correcting codes and fault-tolerant architectures. The surface code, a leading error       <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> correction method, has seen improvements in its threshold and resource requirements [6].                        <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                             <span style=\"font-weight: bold\">2.3 Quantum Simulation</span>                                              <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> Quantum simulation is one of the most promising applications of quantum computing. Recent studies have          <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> demonstrated the simulation of complex quantum systems, such as chemical reactions and material properties,     <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> with unprecedented accuracy [7].                                                                                <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                       <span style=\"font-weight: bold; text-decoration: underline\">3. Applications and Industry Impact</span>                                       <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                <span style=\"font-weight: bold\">3.1 Cryptography</span>                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> Quantum computing poses both threats and opportunities for cryptography. The development of quantum-resistant   <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> algorithms is crucial as quantum computers could potentially break widely used encryption methods. The National <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> Institute of Standards and Technology (NIST) is in the process of standardizing post-quantum cryptographic      <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> algorithms [8].                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                               <span style=\"font-weight: bold\">3.2 Drug Discovery</span>                                                <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> Quantum computing is poised to revolutionize drug discovery by enabling the simulation of molecular             <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> interactions at a quantum level. Companies like Qubit Pharmaceuticals and Cambridge Quantum Computing are       <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> actively working on quantum algorithms for drug discovery, promising faster and more accurate predictions [9].  <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                            <span style=\"font-weight: bold\">3.3 Optimization Problems</span>                                            <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> Quantum computers have the potential to solve complex optimization problems more efficiently than classical     <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> computers. This has significant implications for industries such as logistics, finance, and manufacturing.      <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> Recent advances include the development of quantum algorithms for portfolio optimization and supply chain       <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> management [10].                                                                                                <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                       <span style=\"font-weight: bold; text-decoration: underline\">4. Challenges and Future Directions</span>                                       <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> Despite the rapid progress, several challenges remain in the field of quantum computing. These include          <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> improving qubit coherence times, scaling up the number of qubits, and developing robust error correction        <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> methods. Future research is likely to focus on hybrid quantum-classical systems, which combine the strengths of <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> both paradigms to tackle complex problems.                                                                      <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                   <span style=\"font-weight: bold; text-decoration: underline\">Conclusion</span>                                                    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> Quantum computing is advancing at a remarkable pace, with significant developments in hardware, algorithms, and <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> applications. As the field continues to mature, it holds the promise of transforming industries and solving     <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> problems that are currently intractable for classical computers. Continued investment in research and           <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> development, along with collaboration between academia and industry, will be crucial to realizing the full      <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> potential of quantum computing.                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                   <span style=\"font-weight: bold; text-decoration: underline\">References</span>                                                    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">  1 </span>IBM Research. (2023). IBM Quantum Roadmap. Retrieved from                                                   <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    </span>https://research.ibm.com/quantum-computing/roadmap                                                          <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">  2 </span>IonQ. (2023). IonQ's Quantum Computing Technology. Retrieved from https://ionq.com/technology               <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">  3 </span>Xanadu. (2023). Borealis: A Photonic Quantum Computer. Retrieved from https://xanadu.ai/borealis            <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">  4 </span>PsiQuantum. (2023). Photonic Quantum Computing. Retrieved from https://psiquantum.com/technology            <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">  5 </span>Biamonte, J., et al. (2023). Quantum Machine Learning. Nature Reviews Physics.                              <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">  6 </span>Fowler, A. G., et al. (2023). Surface Codes: Towards Practical Quantum Computing. Physical Review A.        <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">  7 </span>Aspuru-Guzik, A., et al. (2023). Quantum Simulation of Chemical Systems. Chemical Reviews.                  <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">  8 </span>NIST. (2023). Post-Quantum Cryptography Standardization. Retrieved from                                     <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    </span>https://csrc.nist.gov/Projects/post-quantum-cryptography                                                    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">  9 </span>Qubit Pharmaceuticals. (2023). Quantum Computing in Drug Discovery. Retrieved from                          <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    </span>https://qubit-pharmaceuticals.com/quantum-computing                                                         <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\"> 10 </span>Venturelli, D., et al. (2023). Quantum Optimization Algorithms. Journal of Quantum Information Processing.  <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯</span>\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[36m╭─\u001b[0m\u001b[36m──────────────────────────────────────────────────\u001b[0m\u001b[36m Response \u001b[0m\u001b[36m───────────────────────────────────────────────────\u001b[0m\u001b[36m─╮\u001b[0m\n",
+       "\u001b[36m│\u001b[0m ┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓ \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m ┃                                    \u001b[1mRecent Advances in Quantum Computing\u001b[0m                                     ┃ \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m ┗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┛ \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m Quantum computing is a rapidly evolving field that leverages the principles of quantum mechanics to process     \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m information in fundamentally new ways. This report highlights some of the most significant recent advances in   \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m quantum computing, focusing on developments in hardware, algorithms, and applications.                          \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                        \u001b[1;4m1. Quantum Hardware Developments\u001b[0m                                         \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                           \u001b[1m1.1 Superconducting Qubits\u001b[0m                                            \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m Superconducting qubits have been at the forefront of quantum computing hardware. Companies like IBM and Google  \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m have made significant strides in increasing the coherence times and connectivity of these qubits. In 2023, IBM  \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m announced the development of their 433-qubit processor, Osprey, which is part of their roadmap to achieve a     \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m 1,000-qubit system by 2024 [1].                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                             \u001b[1m1.2 Trapped Ion Qubits\u001b[0m                                              \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m Trapped ion technology continues to be a strong contender due to its high fidelity and long coherence times.    \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m IonQ, a leader in this space, has developed systems that can execute quantum circuits with high precision.      \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m Their recent advancements include the development of error-corrected logical qubits, which are crucial for      \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m scalable quantum computing [2].                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                         \u001b[1m1.3 Photonic Quantum Computing\u001b[0m                                          \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m Photonic quantum computing has seen breakthroughs with companies like Xanadu and PsiQuantum. Xanadu's Borealis, \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m a photonic quantum computer, demonstrated quantum advantage by solving specific problems faster than classical  \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m supercomputers [3]. PsiQuantum is working towards a million-qubit photonic quantum computer, leveraging silicon \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m photonics for scalability [4].                                                                                  \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                              \u001b[1;4m2. Quantum Algorithms\u001b[0m                                              \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                          \u001b[1m2.1 Quantum Machine Learning\u001b[0m                                           \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m Quantum machine learning (QML) is gaining traction as researchers develop algorithms that could outperform      \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m classical counterparts. Recent work has focused on hybrid quantum-classical algorithms that leverage quantum    \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m speedups for specific tasks like clustering and classification [5].                                             \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                          \u001b[1m2.2 Quantum Error Correction\u001b[0m                                           \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m Error correction remains a critical challenge in quantum computing. Recent advances include the development of  \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m more efficient error-correcting codes and fault-tolerant architectures. The surface code, a leading error       \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m correction method, has seen improvements in its threshold and resource requirements [6].                        \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                             \u001b[1m2.3 Quantum Simulation\u001b[0m                                              \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m Quantum simulation is one of the most promising applications of quantum computing. Recent studies have          \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m demonstrated the simulation of complex quantum systems, such as chemical reactions and material properties,     \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m with unprecedented accuracy [7].                                                                                \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                       \u001b[1;4m3. Applications and Industry Impact\u001b[0m                                       \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                \u001b[1m3.1 Cryptography\u001b[0m                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m Quantum computing poses both threats and opportunities for cryptography. The development of quantum-resistant   \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m algorithms is crucial as quantum computers could potentially break widely used encryption methods. The National \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m Institute of Standards and Technology (NIST) is in the process of standardizing post-quantum cryptographic      \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m algorithms [8].                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                               \u001b[1m3.2 Drug Discovery\u001b[0m                                                \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m Quantum computing is poised to revolutionize drug discovery by enabling the simulation of molecular             \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m interactions at a quantum level. Companies like Qubit Pharmaceuticals and Cambridge Quantum Computing are       \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m actively working on quantum algorithms for drug discovery, promising faster and more accurate predictions [9].  \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                            \u001b[1m3.3 Optimization Problems\u001b[0m                                            \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m Quantum computers have the potential to solve complex optimization problems more efficiently than classical     \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m computers. This has significant implications for industries such as logistics, finance, and manufacturing.      \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m Recent advances include the development of quantum algorithms for portfolio optimization and supply chain       \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m management [10].                                                                                                \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                       \u001b[1;4m4. Challenges and Future Directions\u001b[0m                                       \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m Despite the rapid progress, several challenges remain in the field of quantum computing. These include          \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m improving qubit coherence times, scaling up the number of qubits, and developing robust error correction        \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m methods. Future research is likely to focus on hybrid quantum-classical systems, which combine the strengths of \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m both paradigms to tackle complex problems.                                                                      \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                   \u001b[1;4mConclusion\u001b[0m                                                    \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m Quantum computing is advancing at a remarkable pace, with significant developments in hardware, algorithms, and \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m applications. As the field continues to mature, it holds the promise of transforming industries and solving     \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m problems that are currently intractable for classical computers. Continued investment in research and           \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m development, along with collaboration between academia and industry, will be crucial to realizing the full      \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m potential of quantum computing.                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                   \u001b[1;4mReferences\u001b[0m                                                    \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m  1 \u001b[0mIBM Research. (2023). IBM Quantum Roadmap. Retrieved from                                                   \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m    \u001b[0mhttps://research.ibm.com/quantum-computing/roadmap                                                          \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m  2 \u001b[0mIonQ. (2023). IonQ's Quantum Computing Technology. Retrieved from https://ionq.com/technology               \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m  3 \u001b[0mXanadu. (2023). Borealis: A Photonic Quantum Computer. Retrieved from https://xanadu.ai/borealis            \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m  4 \u001b[0mPsiQuantum. (2023). Photonic Quantum Computing. Retrieved from https://psiquantum.com/technology            \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m  5 \u001b[0mBiamonte, J., et al. (2023). Quantum Machine Learning. Nature Reviews Physics.                              \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m  6 \u001b[0mFowler, A. G., et al. (2023). Surface Codes: Towards Practical Quantum Computing. Physical Review A.        \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m  7 \u001b[0mAspuru-Guzik, A., et al. (2023). Quantum Simulation of Chemical Systems. Chemical Reviews.                  \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m  8 \u001b[0mNIST. (2023). Post-Quantum Cryptography Standardization. Retrieved from                                     \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m    \u001b[0mhttps://csrc.nist.gov/Projects/post-quantum-cryptography                                                    \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m  9 \u001b[0mQubit Pharmaceuticals. (2023). Quantum Computing in Drug Discovery. Retrieved from                          \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m    \u001b[0mhttps://qubit-pharmaceuticals.com/quantum-computing                                                         \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m 10 \u001b[0mVenturelli, D., et al. (2023). Quantum Optimization Algorithms. Journal of Quantum Information Processing.  \u001b[36m│\u001b[0m\n",
+       "\u001b[36m╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "# Recent Advances in Quantum Computing\n",
+      "\n",
+      "Quantum computing is a rapidly evolving field that leverages the principles of quantum mechanics to process information in fundamentally new ways. This report highlights some of the most significant recent advances in quantum computing, focusing on developments in hardware, algorithms, and applications.\n",
+      "\n",
+      "## 1. Quantum Hardware Developments\n",
+      "\n",
+      "### 1.1 Superconducting Qubits\n",
+      "Superconducting qubits have been at the forefront of quantum computing hardware. Companies like IBM and Google have made significant strides in increasing the coherence times and connectivity of these qubits. In 2023, IBM announced the development of their 433-qubit processor, Osprey, which is part of their roadmap to achieve a 1,000-qubit system by 2024 [1].\n",
+      "\n",
+      "### 1.2 Trapped Ion Qubits\n",
+      "Trapped ion technology continues to be a strong contender due to its high fidelity and long coherence times. IonQ, a leader in this space, has developed systems that can execute quantum circuits with high precision. Their recent advancements include the development of error-corrected logical qubits, which are crucial for scalable quantum computing [2].\n",
+      "\n",
+      "### 1.3 Photonic Quantum Computing\n",
+      "Photonic quantum computing has seen breakthroughs with companies like Xanadu and PsiQuantum. Xanadu's Borealis, a photonic quantum computer, demonstrated quantum advantage by solving specific problems faster than classical supercomputers [3]. PsiQuantum is working towards a million-qubit photonic quantum computer, leveraging silicon photonics for scalability [4].\n",
+      "\n",
+      "## 2. Quantum Algorithms\n",
+      "\n",
+      "### 2.1 Quantum Machine Learning\n",
+      "Quantum machine learning (QML) is gaining traction as researchers develop algorithms that could outperform classical counterparts. Recent work has focused on hybrid quantum-classical algorithms that leverage quantum speedups for specific tasks like clustering and classification [5].\n",
+      "\n",
+      "### 2.2 Quantum Error Correction\n",
+      "Error correction remains a critical challenge in quantum computing. Recent advances include the development of more efficient error-correcting codes and fault-tolerant architectures. The surface code, a leading error correction method, has seen improvements in its threshold and resource requirements [6].\n",
+      "\n",
+      "### 2.3 Quantum Simulation\n",
+      "Quantum simulation is one of the most promising applications of quantum computing. Recent studies have demonstrated the simulation of complex quantum systems, such as chemical reactions and material properties, with unprecedented accuracy [7].\n",
+      "\n",
+      "## 3. Applications and Industry Impact\n",
+      "\n",
+      "### 3.1 Cryptography\n",
+      "Quantum computing poses both threats and opportunities for cryptography. The development of quantum-resistant algorithms is crucial as quantum computers could potentially break widely used encryption methods. The National Institute of Standards and Technology (NIST) is in the process of standardizing post-quantum cryptographic algorithms [8].\n",
+      "\n",
+      "### 3.2 Drug Discovery\n",
+      "Quantum computing is poised to revolutionize drug discovery by enabling the simulation of molecular interactions at a quantum level. Companies like Qubit Pharmaceuticals and Cambridge Quantum Computing are actively working on quantum algorithms for drug discovery, promising faster and more accurate predictions [9].\n",
+      "\n",
+      "### 3.3 Optimization Problems\n",
+      "Quantum computers have the potential to solve complex optimization problems more efficiently than classical computers. This has significant implications for industries such as logistics, finance, and manufacturing. Recent advances include the development of quantum algorithms for portfolio optimization and supply chain management [10].\n",
+      "\n",
+      "## 4. Challenges and Future Directions\n",
+      "\n",
+      "Despite the rapid progress, several challenges remain in the field of quantum computing. These include improving qubit coherence times, scaling up the number of qubits, and developing robust error correction methods. Future research is likely to focus on hybrid quantum-classical systems, which combine the strengths of both paradigms to tackle complex problems.\n",
+      "\n",
+      "## Conclusion\n",
+      "\n",
+      "Quantum computing is advancing at a remarkable pace, with significant developments in hardware, algorithms, and applications. As the field continues to mature, it holds the promise of transforming industries and solving problems that are currently intractable for classical computers. Continued investment in research and development, along with collaboration between academia and industry, will be crucial to realizing the full potential of quantum computing.\n",
+      "\n",
+      "## References\n",
+      "\n",
+      "1. IBM Research. (2023). IBM Quantum Roadmap. Retrieved from https://research.ibm.com/quantum-computing/roadmap\n",
+      "2. IonQ. (2023). IonQ's Quantum Computing Technology. Retrieved from https://ionq.com/technology\n",
+      "3. Xanadu. (2023). Borealis: A Photonic Quantum Computer. Retrieved from https://xanadu.ai/borealis\n",
+      "4. PsiQuantum. (2023). Photonic Quantum Computing. Retrieved from https://psiquantum.com/technology\n",
+      "5. Biamonte, J., et al. (2023). Quantum Machine Learning. Nature Reviews Physics.\n",
+      "6. Fowler, A. G., et al. (2023). Surface Codes: Towards Practical Quantum Computing. Physical Review A.\n",
+      "7. Aspuru-Guzik, A., et al. (2023). Quantum Simulation of Chemical Systems. Chemical Reviews.\n",
+      "8. NIST. (2023). Post-Quantum Cryptography Standardization. Retrieved from https://csrc.nist.gov/Projects/post-quantum-cryptography\n",
+      "9. Qubit Pharmaceuticals. (2023). Quantum Computing in Drug Discovery. Retrieved from https://qubit-pharmaceuticals.com/quantum-computing\n",
+      "10. Venturelli, D., et al. (2023). Quantum Optimization Algorithms. Journal of Quantum Information Processing.\n"
+     ]
+    }
+   ],
+   "source": [
+    "from praisonaiagents import Agent\n",
+    "\n",
+    "# User input (for demo, hardcoded; in real use, use input() or widgets)\n",
+    "topic = \"Recent advances in quantum computing\"\n",
+    "\n",
+    "# Use the custom tool\n",
+    "tool = DummyDeepResearchTool(topic)\n",
+    "dummy_report = tool.research()\n",
+    "\n",
+    "if not is_valid_key(OPENAI_API_KEY, \"sk\"):\n",
+    "    print(\"API key not set or is a placeholder. Using dummy research report for CI/testing.\")\n",
+    "    print(dummy_report)\n",
+    "else:\n",
+    "    prompt = f\"\"\"\n",
+    "    You are a domain research assistant. Perform deep research on the following topic and provide a structured, well-cited report:\n",
+    "    TOPIC: {topic}\n",
+    "    \"\"\"\n",
+    "    agent = Agent(\n",
+    "        name=\"Domain Deep Research Agent\",\n",
+    "        instructions=prompt,\n",
+    "        api_key=OPENAI_API_KEY\n",
+    "    )\n",
+    "    report = agent.start(prompt)\n",
+    "    print(report)"
+   ]
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "provenance": []
+  },
+  "kernelspec": {
+   "display_name": "Python 3",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}

examples/cookbooks/SocialMedia_Content_Agents/News_And_Podcast_Aggregator_Agent.ipynb

@@ -0,0 +1,689 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    },
+    "widgets": {
+      "application/vnd.jupyter.widget-state+json": {
+        "4ab88bfcb62e4f9a8db7e35aefbae00a": {
+          "model_module": "@jupyter-widgets/output",
+          "model_name": "OutputModel",
+          "model_module_version": "1.0.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/output",
+            "_model_module_version": "1.0.0",
+            "_model_name": "OutputModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/output",
+            "_view_module_version": "1.0.0",
+            "_view_name": "OutputView",
+            "layout": "IPY_MODEL_3d1ae7a6c0a947f985f6ef921b74ecf8",
+            "msg_id": "",
+            "outputs": [
+              {
+                "output_type": "display_data",
+                "data": {
+                  "text/plain": "\u001b[32m╭─\u001b[0m\u001b[32m─────────────────────────────────────────────\u001b[0m\u001b[32m Generating... 23.2s \u001b[0m\u001b[32m─────────────────────────────────────────────\u001b[0m\u001b[32m─╮\u001b[0m\n\u001b[32m│\u001b[0m [INTRO MUSIC FADES IN]                                                                                          \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m                                                                                                                 \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m \u001b[1mAlex\u001b[0m: Hello and welcome to another episode of \"The World Today,\" where we dive into the latest in technology    \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m and world news. I'm Alex, your go-to for all things analytical and fact-focused.                                \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m                                                                                                                 \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m \u001b[1mMorgan\u001b[0m: And I'm Morgan, here to explore the human impact and social context of today's stories. We've got a     \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m fascinating lineup for you today, so let's dive right in!                                                       \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m                                                                                                                 \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m \u001b[1mAlex\u001b[0m: First up, we're talking about a topic that's been making waves across the healthcare industry: the role   \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m of artificial intelligence. According to a recent article from \u001b]8;id=672819;https://news.example.com/ai-healthcare\u001b\\\u001b[4;34mNews Example\u001b[0m\u001b]8;;\u001b\\, AI is revolutionizing healthcare   \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m in ways we could only dream of a decade ago.                                                                    \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m                                                                                                                 \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m \u001b[1mMorgan\u001b[0m: That's right, Alex. AI is not just a buzzword anymore; it's actively changing how we approach           \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m healthcare. From diagnostics to treatment plans, AI is helping doctors make more accurate decisions faster. But \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m what does this mean for patients and healthcare professionals?                                                  \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m                                                                                                                 \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m \u001b[1mAlex\u001b[0m: Well, Morgan, AI's ability to analyze vast amounts of data quickly means that doctors can diagnose        \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m diseases earlier and more accurately. For instance, AI algorithms can now detect patterns in medical imaging    \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m that might be too subtle for the human eye. This can lead to earlier interventions and better patient outcomes. \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m                                                                                                                 \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m \u001b[1mMorgan\u001b[0m: And let's not forget about the human side of things. For patients, this means less waiting time for     \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m results and potentially more personalized treatment plans. But there's also a concern about the human touch in  \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m healthcare. How do we balance the efficiency of AI with the empathy and understanding that only a human can     \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m provide?                                                                                                        \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m                                                                                                                 \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m \u001b[1mAlex\u001b[0m: That's a great point. The integration of AI in healthcare does raise ethical questions. For example, who  \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m is responsible if an AI system makes a mistake? And how do we ensure that these systems are free from bias?     \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m                   Line truncated
+                  "text/html": "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008000; text-decoration-color: #008000\">╭────────────────────────────────────────────── Generating... 23.2s ──────────────────────────────────────────────╮</span>\n<span style=\"color: #008000; text-decoration-color: #008000\">│</span> [INTRO MUSIC FADES IN]                                                                                          <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n<span style=\"color: #008000; text-decoration-color: #008000\">│</span>                                                                                                                 <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n<span style=\"color: #008000; text-decoration-color: #008000\">│</span> <span style=\"font-weight: bold\">Alex</span>: Hello and welcome to another episode of \"The World Today,\" where we dive into the latest in technology    <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n<span style=\"color: #008000; text-decoration-color: #008000\">│</span> and world news. I'm Alex, your go-to for all things analytical and fact-focused.                                <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n<span style=\"color: #008000; text-decoration-color: #008000\">│</span>                                                                                                                 <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n<span style=\"color: #008000; text-decoration-color: #008000\">│</span> <span style=\"font-weight: bold\">Morgan</span>: And I'm Morgan, here to explore the human impact and social context of today's stories. We've got a     <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n<span style=\"color: #008000; text-decoration-color: #008000\">│</span> fascinating lineup for you today, so let's dive right in!                                                       <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n<span style=\"color: #008000; text-decoration-color: #008000\">│</span>                                                                                                                 <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n<span style=\"color: #008000; text-decoration-color: #008000\">│</span> <span style=\"font-weight: bold\">Alex</span>: First up, we're talking about a topic that's been making waves across the healthcare industry: the role   <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n<span style=\"color: #008000; text-decoration-color: #008000\">│</span> of artificial intelligence. According to a recent article from <a href=\"https://news.example.com/ai-healthcare\" target=\"_blank\"><span style=\"color: #000080; text-decoration-color: #000080; text-decoration: underline\">News Example</span></a>, AI is revolutionizing healthcare   <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n<span style=\"color: #008000; text-decoration-color: #008000\">│</span> in ways we could only dream of a decade ago.                                                                    <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n<span style=\"color: #008000; text-decoration-color: #008000\">│</span>                                                                                                                 <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n<span style=\"color: #008000; text-decoration-color: #008000\">│</span> <span style=\"font-weight: bold\">Morgan</span>: That's right, Alex. AI is not just a buzzword anymore; it's actively changing how we approach           <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n<span style=\"color: #008000; text-decoration-color: #008000\">│</span> healthcare. From diagnostics to treatment plans, AI is helping doctors make more accurate decisions faster. But <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n<span style=\"color: #008000; text-decoration-color: #008000\">│</span> what does this mean for patients and healthcare professionals?                                                  <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n<span style=\"color: #008000; text-decoration-color: #008000\">│</span>                                                                                                                 <span style=\"coloLine truncated
+                },
+                "metadata": {}
+              }
+            ]
+          }
+        },
+        "3d1ae7a6c0a947f985f6ef921b74ecf8": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": null,
+            "flex": null,
+            "flex_flow": null,
+            "grid_area": null,
+            "grid_auto_columns": null,
+            "grid_auto_flow": null,
+            "grid_auto_rows": null,
+            "grid_column": null,
+            "grid_gap": null,
+            "grid_row": null,
+            "grid_template_areas": null,
+            "grid_template_columns": null,
+            "grid_template_rows": null,
+            "height": null,
+            "justify_content": null,
+            "justify_items": null,
+            "left": null,
+            "margin": null,
+            "max_height": null,
+            "max_width": null,
+            "min_height": null,
+            "min_width": null,
+            "object_fit": null,
+            "object_position": null,
+            "order": null,
+            "overflow": null,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        }
+      }
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# News and Podcast Aggregator Agent using PraisonAIAgents"
+      ],
+      "metadata": {
+        "id": "5DpLQOaCmYbu"
+      }
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "This notebook demonstrates a News and Podcast Aggregator Agent built with `praisonaiagents`.  \n",
+        "It summarizes news articles and generates podcast-style discussion points.  \n",
+        "The notebook is CI-friendly: it uses dummy data if API keys are not set, so all tests/checks will pass."
+      ],
+      "metadata": {
+        "id": "qmVwAahwmYTZ"
+      }
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Dhivya-Bharathy/PraisonAI/blob/main/examples/cookbooks/SocialMedia_Content_Agents/News_And_Podcast_Aggregator_Agent.ipynb)\n"
+      ],
+      "metadata": {
+        "id": "tYRRrgqHqbuN"
+      }
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# Dependencies"
+      ],
+      "metadata": {
+        "id": "baTmwAjYmfDg"
+      }
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "IIm2awOXmXB9"
+      },
+      "outputs": [],
+      "source": [
+        "!pip install praisonaiagents pydantic"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# Imports and Setup"
+      ],
+      "metadata": {
+        "id": "kqNfe5S2mjnn"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import os\n",
+        "\n",
+        "# Set up the OpenAI API key for praisonaiagents\n",
+        "os.environ[\"OPENAI_API_KEY\"] = os.environ.get(\"OPENAI_API_KEY\", \"sk-..\")\n",
+        "\n",
+        "def is_valid_key(key, prefix):\n",
+        "    return key and key != f\"{prefix}-..\" and key.startswith(prefix)\n",
+        "\n",
+        "OPENAI_API_KEY = os.environ[\"OPENAI_API_KEY\"]"
+      ],
+      "metadata": {
+        "id": "A-OXlt2gmpUS"
+      },
+      "execution_count": 3,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# Tools"
+      ],
+      "metadata": {
+        "id": "IJmdTrCDoufF"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "from datetime import datetime\n",
+        "from typing import List\n",
+        "\n",
+        "def format_search_results_for_podcast(search_results: List[dict]) -> tuple[str, List[str]]:\n",
+        "    \"\"\"\n",
+        "    Custom tool to format search results for podcast script generation.\n",
+        "    \"\"\"\n",
+        "    created_at = datetime.now().strftime(\"%B %d, %Y at %I:%M %p\")\n",
+        "    structured_content = []\n",
+        "    structured_content.append(f\"PODCAST CREATION: {created_at}\\n\")\n",
+        "    sources = []\n",
+        "    for idx, search_result in enumerate(search_results):\n",
+        "        try:\n",
+        "            if search_result.get(\"confirmed\", False):\n",
+        "                sources.append(search_result[\"url\"])\n",
+        "                structured_content.append(\n",
+        "                    f\"\"\"\n",
+        "                    SOURCE {idx + 1}:\n",
+        "                    Title: {search_result['title']}\n",
+        "                    URL: {search_result['url']}\n",
+        "                    Content: {search_result.get('full_text') or search_result.get('description', '')}\n",
+        "                    ---END OF SOURCE {idx + 1}---\n",
+        "                    \"\"\".strip()\n",
+        "                )\n",
+        "        except Exception as e:\n",
+        "            print(f\"Error processing search result: {e}\")\n",
+        "    content_texts = \"\\n\\n\".join(structured_content)\n",
+        "    return content_texts, sources"
+      ],
+      "metadata": {
+        "id": "yHj7Grvmov4C"
+      },
+      "execution_count": 4,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# Pydantic Models"
+      ],
+      "metadata": {
+        "id": "eMYs7Oibo1M3"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "from pydantic import BaseModel, Field\n",
+        "from typing import List, Optional\n",
+        "\n",
+        "class Dialog(BaseModel):\n",
+        "    speaker: str = Field(..., description=\"The speaker name (SHOULD BE 'ALEX' OR 'MORGAN')\")\n",
+        "    text: str = Field(..., description=\"The spoken text content for this speaker based on the requested language, default is English\")\n",
+        "\n",
+        "class Section(BaseModel):\n",
+        "    type: str = Field(..., description=\"The section type (intro, headlines, article, outro)\")\n",
+        "    title: Optional[str] = Field(None, description=\"Optional title for the section (required for article type)\")\n",
+        "    dialog: List[Dialog] = Field(..., description=\"List of dialog exchanges between speakers\")\n",
+        "\n",
+        "class PodcastScript(BaseModel):\n",
+        "    title: str = Field(..., description=\"The podcast episode title with date\")\n",
+        "    sections: List[Section] = Field(..., description=\"List of podcast sections (intro, headlines, articles, outro)\")"
+      ],
+      "metadata": {
+        "id": "Z4uBU68eo2L_"
+      },
+      "execution_count": 5,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# Agent Instructions"
+      ],
+      "metadata": {
+        "id": "sRTr9D35o-5D"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "from textwrap import dedent\n",
+        "\n",
+        "PODCAST_AGENT_DESCRIPTION = \"You are a helpful assistant that can generate engaging podcast scripts for the given sources.\"\n",
+        "PODCAST_AGENT_INSTRUCTIONS = dedent(\"\"\"\n",
+        "    You are a helpful assistant that can generate engaging podcast scripts for the given source content and query.\n",
+        "    For given content, create an engaging podcast script that should be at least 15 minutes worth of content and you are allowed to enhance the script beyond given sources if you know something additional info will be interesting to the discussion or not enough content is available.\n",
+        "    You use the provided sources to ground your podcast script generation process. Keep it engaging and interesting.\n",
+        "    IMPORTANT: Generate the entire script in the provided language.\n",
+        "    CONTENT GUIDELINES:\n",
+        "    - Provide insightful analysis that helps the audience understand the significance\n",
+        "    - Include discussions on potential implications and broader context of each story\n",
+        "    - Explain complex concepts in an accessible but thorough manner\n",
+        "    - Make connections between current and relevant historical developments when applicable\n",
+        "    - Provide comparisons and contrasts with similar stories or trends when relevant\n",
+        "    PERSONALITY NOTES:\n",
+        "    - Alex is more analytical and fact-focused\n",
+        "    - Morgan is more focused on human impact, social context, and practical applications\n",
+        "    - Include natural, conversational banter and smooth transitions between topics\n",
+        "    - Each article discussion should go beyond the basic summary to provide valuable insights\n",
+        "    - Maintain a conversational but informed tone that would appeal to a general audience\n",
+        "    IMPORTANT:\n",
+        "        - MAKE SURE PODCAST SCRIPTS ARE AT LEAST 15 MINUTES LONG WHICH MEANS YOU NEED TO HAVE DETAILED DISCUSSIONS BUT KEEP IT INTERESTING AND ENGAGING.\n",
+        "\"\"\")"
+      ],
+      "metadata": {
+        "id": "quslT1kFo_yc"
+      },
+      "execution_count": 6,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# Dummy Data and Main Logic"
+      ],
+      "metadata": {
+        "id": "bicXivCipLZY"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "from praisonaiagents import Agent\n",
+        "\n",
+        "# Dummy search results for CI/public use\n",
+        "dummy_search_results = [\n",
+        "    {\n",
+        "        \"confirmed\": True,\n",
+        "        \"title\": \"AI Revolutionizes Healthcare\",\n",
+        "        \"url\": \"https://news.example.com/ai-healthcare\",\n",
+        "        \"full_text\": \"Artificial intelligence is transforming the healthcare industry by...\"\n",
+        "    },\n",
+        "    {\n",
+        "        \"confirmed\": True,\n",
+        "        \"title\": \"Climate Change and Global Policy\",\n",
+        "        \"url\": \"https://news.example.com/climate-policy\",\n",
+        "        \"full_text\": \"World leaders are meeting to discuss new policies for climate change...\"\n",
+        "    }\n",
+        "]\n",
+        "\n",
+        "query = \"Latest technology and world news\"\n",
+        "language_name = \"English\"\n",
+        "\n",
+        "content_texts, sources = format_search_results_for_podcast(dummy_search_results)\n",
+        "\n",
+        "if not is_valid_key(OPENAI_API_KEY, \"sk\"):\n",
+        "    print(\"API key not set or is a placeholder. Using dummy podcast script for CI/testing.\")\n",
+        "    print(\"=== Podcast Script ===\")\n",
+        "    print(f\"Podcast Title: Tech & World News Roundup ({datetime.now().strftime('%B %d, %Y')})\")\n",
+        "    for idx, article in enumerate(dummy_search_results):\n",
+        "        print(f\"\\nSection {idx+1}: {article['title']}\")\n",
+        "        print(f\"Summary: {article['full_text'][:80]}...\")\n",
+        "else:\n",
+        "    agent = Agent(\n",
+        "        name=\"Podcast Script Agent\",\n",
+        "        instructions=PODCAST_AGENT_INSTRUCTIONS,\n",
+        "        api_key=OPENAI_API_KEY\n",
+        "    )\n",
+        "    prompt = f\"query: {query}\\nlanguage_name: {language_name}\\ncontent_texts: {content_texts}\\nIMPORTANT: texts should be in {language_name} language.\"\n",
+        "    podcast_script = agent.start(prompt)\n",
+        "    print(\"=== Podcast Script ===\")\n",
+        "    print(podcast_script)"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 1000,
+          "referenced_widgets": [
+            "4ab88bfcb62e4f9a8db7e35aefbae00a",
+            "3d1ae7a6c0a947f985f6ef921b74ecf8"
+          ]
+        },
+        "id": "H4UoF8PApMUJ",
+        "outputId": "748c6a75-0a0e-494a-983c-fb539ff7641a"
+      },
+      "execution_count": 7,
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "\u001b[38;2;210;227;200m╭─\u001b[0m\u001b[38;2;210;227;200m \u001b[0m\u001b[1;38;2;210;227;200mAgent Info\u001b[0m\u001b[38;2;210;227;200m \u001b[0m\u001b[38;2;210;227;200m───────────────────────────────────────────────────────────────────────────────────────────────────\u001b[0m\u001b[38;2;210;227;200m─╮\u001b[0m\n",
+              "\u001b[38;2;210;227;200m│\u001b[0m                                                                                                                 \u001b[38;2;210;227;200m│\u001b[0m\n",
+              "\u001b[38;2;210;227;200m│\u001b[0m  \u001b[1;38;2;255;155;155m👤 Agent:\u001b[0m \u001b[38;2;255;229;229mPodcast Script Agent\u001b[0m                                                                                 \u001b[38;2;210;227;200m│\u001b[0m\n",
+              "\u001b[38;2;210;227;200m│\u001b[0m  \u001b[1;38;2;180;180;179mRole:\u001b[0m \u001b[38;2;255;229;229mAssistant\u001b[0m                                                                                                \u001b[38;2;210;227;200m│\u001b[0m\n",
+              "\u001b[38;2;210;227;200m│\u001b[0m                                                                                                                 \u001b[38;2;210;227;200m│\u001b[0m\n",
+              "\u001b[38;2;210;227;200m╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n"
+            ],
+            "text/html": [
+              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">╭─ </span><span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8; font-weight: bold\">Agent Info</span><span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\"> ────────────────────────────────────────────────────────────────────────────────────────────────────╮</span>\n",
+              "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>                                                                                                                 <span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>\n",
+              "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>  <span style=\"color: #ff9b9b; text-decoration-color: #ff9b9b; font-weight: bold\">👤 Agent:</span> <span style=\"color: #ffe5e5; text-decoration-color: #ffe5e5\">Podcast Script Agent</span>                                                                                 <span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>\n",
+              "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>  <span style=\"color: #b4b4b3; text-decoration-color: #b4b4b3; font-weight: bold\">Role:</span> <span style=\"color: #ffe5e5; text-decoration-color: #ffe5e5\">Assistant</span>                                                                                                <span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>\n",
+              "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>                                                                                                                 <span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>\n",
+              "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯</span>\n",
+              "</pre>\n"
+            ]
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "Output()"
+            ],
+            "application/vnd.jupyter.widget-view+json": {
+              "version_major": 2,
+              "version_minor": 0,
+              "model_id": "4ab88bfcb62e4f9a8db7e35aefbae00a"
+            }
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [],
+            "text/html": [
+              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"></pre>\n"
+            ]
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "\n"
+            ],
+            "text/html": [
+              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
+              "</pre>\n"
+            ]
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "\u001b[2mResponse generated in 23.5s\u001b[0m\n"
+            ],
+            "text/html": [
+              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">Response generated in 23.5s</span>\n",
+              "</pre>\n"
+            ]
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "\u001b[36m╭─\u001b[0m\u001b[36m────────────────────────────────────────────────────\u001b[0m\u001b[36m Task \u001b[0m\u001b[36m─────────────────────────────────────────────────────\u001b[0m\u001b[36m─╮\u001b[0m\n",
+              "\u001b[36m│\u001b[0m query: Latest technology and world news language_name: English content_texts: PODCAST CREATION: July 09, 2025   \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m at 10:03 AM                                                                                                     \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m SOURCE 1: Title: AI Revolutionizes Healthcare URL: https://news.example.com/ai-healthcare Content: Artificial   \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m intelligence is transforming the healthcare industry by... ---END OF SOURCE 1---                                \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m SOURCE 2: Title: Climate Change and Global Policy URL: https://news.example.com/climate-policy Content: World   \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m leaders are meeting to discuss new policies for climate change... ---END OF SOURCE 2--- IMPORTANT: texts should \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m be in English language.                                                                                         \u001b[36m│\u001b[0m\n",
+              "\u001b[36m╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n"
+            ],
+            "text/html": [
+              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008080; text-decoration-color: #008080\">╭───────────────────────────────────────────────────── Task ──────────────────────────────────────────────────────╮</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> query: Latest technology and world news language_name: English content_texts: PODCAST CREATION: July 09, 2025   <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> at 10:03 AM                                                                                                     <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> SOURCE 1: Title: AI Revolutionizes Healthcare URL: https://news.example.com/ai-healthcare Content: Artificial   <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> intelligence is transforming the healthcare industry by... ---END OF SOURCE 1---                                <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> SOURCE 2: Title: Climate Change and Global Policy URL: https://news.example.com/climate-policy Content: World   <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> leaders are meeting to discuss new policies for climate change... ---END OF SOURCE 2--- IMPORTANT: texts should <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> be in English language.                                                                                         <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯</span>\n",
+              "</pre>\n"
+            ]
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "\u001b[36m╭─\u001b[0m\u001b[36m──────────────────────────────────────────────────\u001b[0m\u001b[36m Response \u001b[0m\u001b[36m───────────────────────────────────────────────────\u001b[0m\u001b[36m─╮\u001b[0m\n",
+              "\u001b[36m│\u001b[0m [INTRO MUSIC FADES IN]                                                                                          \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m \u001b[1mAlex\u001b[0m: Hello and welcome to another episode of \"The World Today,\" where we dive into the latest in technology    \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m and world news. I'm Alex, your go-to for all things analytical and fact-focused.                                \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m \u001b[1mMorgan\u001b[0m: And I'm Morgan, here to explore the human impact and social context of today's stories. We've got a     \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m fascinating lineup for you today, so let's dive right in!                                                       \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m \u001b[1mAlex\u001b[0m: First up, we're talking about a topic that's been making waves across the healthcare industry: the role   \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m of artificial intelligence. According to a recent article from \u001b]8;id=890061;https://news.example.com/ai-healthcare\u001b\\\u001b[4;34mNews Example\u001b[0m\u001b]8;;\u001b\\, AI is revolutionizing healthcare   \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m in ways we could only dream of a decade ago.                                                                    \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m \u001b[1mMorgan\u001b[0m: That's right, Alex. AI is not just a buzzword anymore; it's actively changing how we approach           \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m healthcare. From diagnostics to treatment plans, AI is helping doctors make more accurate decisions faster. But \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m what does this mean for patients and healthcare professionals?                                                  \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m \u001b[1mAlex\u001b[0m: Well, Morgan, AI's ability to analyze vast amounts of data quickly means that doctors can diagnose        \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m diseases earlier and more accurately. For instance, AI algorithms can now detect patterns in medical imaging    \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m that might be too subtle for the human eye. This can lead to earlier interventions and better patient outcomes. \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m \u001b[1mMorgan\u001b[0m: And let's not forget about the human side of things. For patients, this means less waiting time for     \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m results and potentially more personalized treatment plans. But there's also a concern about the human touch in  \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m healthcare. How do we balance the efficiency of AI with the empathy and understanding that only a human can     \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m provide?                                                                                                        \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m \u001b[1mAlex\u001b[0m: That's a great point. The integration of AI in healthcare does raise ethical questions. For example, who  \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m is responsible if an AI system makes a mistake? And how do we ensure that these systems are free from bias?     \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m \u001b[1mMorgan\u001b[0m: Exactly. There's a lot to consider, but the potential benefits are enormous. Imagine a world where      \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m healthcare is not only more efficient but also more accessible to people in remote areas thanks to AI-driven    \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m telemedicine.                                                                                                   \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m \u001b[1mAlex\u001b[0m: It's a fascinating time for healthcare, no doubt. But let's shift gears a bit and talk about another      \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m pressing issue: climate change and global policy. According to a report from \u001b]8;id=2198;https://news.example.com/climate-policy\u001b\\\u001b[4;34mNews Example\u001b[0m\u001b]8;;\u001b\\, world leaders are    \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m currently meeting to discuss new policies to combat climate change.                                             \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m \u001b[1mMorgan\u001b[0m: Climate change is one of those issues that affects everyone, regardless of where you live. These global \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m meetings are crucial because they set the stage for international cooperation. But what are the main challenges \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m these leaders face?                                                                                             \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m \u001b[1mAlex\u001b[0m: One of the biggest challenges is balancing economic growth with environmental sustainability. Many        \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m developing countries argue that they need to prioritize economic development, which often relies on fossil      \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m fuels. Meanwhile, developed countries are pushing for stricter environmental regulations.                       \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m \u001b[1mMorgan\u001b[0m: It's a classic case of differing priorities. But there's also a growing recognition that climate change \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m doesn't respect borders. Extreme weather events, rising sea levels, and shifting agricultural patterns affect   \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m us all. So, there's a real urgency to find common ground.                                                       \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m \u001b[1mAlex\u001b[0m: And technology plays a significant role here too. Innovations in renewable energy, carbon capture, and    \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m sustainable agriculture are crucial in the fight against climate change. But implementing these technologies on \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m a global scale requires significant investment and political will.                                              \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m \u001b[1mMorgan\u001b[0m: It's a complex issue, but it's encouraging to see world leaders coming together to address it. The      \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m policies they create today will shape the future for generations to come.                                       \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m \u001b[1mAlex\u001b[0m: Absolutely. And it's not just about government action. Individuals and businesses also have a role to     \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m play in reducing carbon footprints and advocating for sustainable practices.                                    \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m \u001b[1mMorgan\u001b[0m: It's a collective effort, and every little bit helps. Before we wrap up, Alex, any final thoughts on    \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m today's topics?                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m \u001b[1mAlex\u001b[0m: Just that both AI in healthcare and climate change policies highlight the intersection of technology and  \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m society. They show us how innovation can drive progress but also remind us of the responsibilities that come    \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m with it.                                                                                                        \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m \u001b[1mMorgan\u001b[0m: Well said, Alex. It's all about finding that balance. And with that, we've reached the end of today's   \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m episode. Thanks for tuning in to \"The World Today.\"                                                             \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m \u001b[1mAlex\u001b[0m: Don't forget to subscribe and join us next time for more insights into the latest in technology and world \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m news.                                                                                                           \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m \u001b[1mMorgan\u001b[0m: Until then, stay informed and stay curious!                                                             \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m [OUTRO MUSIC FADES OUT]                                                                                         \u001b[36m│\u001b[0m\n",
+              "\u001b[36m╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n"
+            ],
+            "text/html": [
+              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008080; text-decoration-color: #008080\">╭─────────────────────────────────────────────────── Response ────────────────────────────────────────────────────╮</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> [INTRO MUSIC FADES IN]                                                                                          <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"font-weight: bold\">Alex</span>: Hello and welcome to another episode of \"The World Today,\" where we dive into the latest in technology    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> and world news. I'm Alex, your go-to for all things analytical and fact-focused.                                <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"font-weight: bold\">Morgan</span>: And I'm Morgan, here to explore the human impact and social context of today's stories. We've got a     <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> fascinating lineup for you today, so let's dive right in!                                                       <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"font-weight: bold\">Alex</span>: First up, we're talking about a topic that's been making waves across the healthcare industry: the role   <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> of artificial intelligence. According to a recent article from <a href=\"https://news.example.com/ai-healthcare\" target=\"_blank\"><span style=\"color: #000080; text-decoration-color: #000080; text-decoration: underline\">News Example</span></a>, AI is revolutionizing healthcare   <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> in ways we could only dream of a decade ago.                                                                    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"font-weight: bold\">Morgan</span>: That's right, Alex. AI is not just a buzzword anymore; it's actively changing how we approach           <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> healthcare. From diagnostics to treatment plans, AI is helping doctors make more accurate decisions faster. But <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> what does this mean for patients and healthcare professionals?                                                  <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"font-weight: bold\">Alex</span>: Well, Morgan, AI's ability to analyze vast amounts of data quickly means that doctors can diagnose        <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> diseases earlier and more accurately. For instance, AI algorithms can now detect patterns in medical imaging    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> that might be too subtle for the human eye. This can lead to earlier interventions and better patient outcomes. <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"font-weight: bold\">Morgan</span>: And let's not forget about the human side of things. For patients, this means less waiting time for     <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> results and potentially more personalized treatment plans. But there's also a concern about the human touch in  <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> healthcare. How do we balance the efficiency of AI with the empathy and understanding that only a human can     <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> provide?                                                                                                        <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"font-weight: bold\">Alex</span>: That's a great point. The integration of AI in healthcare does raise ethical questions. For example, who  <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> is responsible if an AI system makes a mistake? And how do we ensure that these systems are free from bias?     <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"font-weight: bold\">Morgan</span>: Exactly. There's a lot to consider, but the potential benefits are enormous. Imagine a world where      <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> healthcare is not only more efficient but also more accessible to people in remote areas thanks to AI-driven    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> telemedicine.                                                                                                   <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"font-weight: bold\">Alex</span>: It's a fascinating time for healthcare, no doubt. But let's shift gears a bit and talk about another      <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> pressing issue: climate change and global policy. According to a report from <a href=\"https://news.example.com/climate-policy\" target=\"_blank\"><span style=\"color: #000080; text-decoration-color: #000080; text-decoration: underline\">News Example</span></a>, world leaders are    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> currently meeting to discuss new policies to combat climate change.                                             <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"font-weight: bold\">Morgan</span>: Climate change is one of those issues that affects everyone, regardless of where you live. These global <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> meetings are crucial because they set the stage for international cooperation. But what are the main challenges <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> these leaders face?                                                                                             <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"font-weight: bold\">Alex</span>: One of the biggest challenges is balancing economic growth with environmental sustainability. Many        <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> developing countries argue that they need to prioritize economic development, which often relies on fossil      <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> fuels. Meanwhile, developed countries are pushing for stricter environmental regulations.                       <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"font-weight: bold\">Morgan</span>: It's a classic case of differing priorities. But there's also a growing recognition that climate change <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> doesn't respect borders. Extreme weather events, rising sea levels, and shifting agricultural patterns affect   <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> us all. So, there's a real urgency to find common ground.                                                       <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"font-weight: bold\">Alex</span>: And technology plays a significant role here too. Innovations in renewable energy, carbon capture, and    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> sustainable agriculture are crucial in the fight against climate change. But implementing these technologies on <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> a global scale requires significant investment and political will.                                              <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"font-weight: bold\">Morgan</span>: It's a complex issue, but it's encouraging to see world leaders coming together to address it. The      <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> policies they create today will shape the future for generations to come.                                       <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"font-weight: bold\">Alex</span>: Absolutely. And it's not just about government action. Individuals and businesses also have a role to     <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> play in reducing carbon footprints and advocating for sustainable practices.                                    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"font-weight: bold\">Morgan</span>: It's a collective effort, and every little bit helps. Before we wrap up, Alex, any final thoughts on    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> today's topics?                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"font-weight: bold\">Alex</span>: Just that both AI in healthcare and climate change policies highlight the intersection of technology and  <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> society. They show us how innovation can drive progress but also remind us of the responsibilities that come    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> with it.                                                                                                        <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"font-weight: bold\">Morgan</span>: Well said, Alex. It's all about finding that balance. And with that, we've reached the end of today's   <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> episode. Thanks for tuning in to \"The World Today.\"                                                             <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"font-weight: bold\">Alex</span>: Don't forget to subscribe and join us next time for more insights into the latest in technology and world <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> news.                                                                                                           <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"font-weight: bold\">Morgan</span>: Until then, stay informed and stay curious!                                                             <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> [OUTRO MUSIC FADES OUT]                                                                                         <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯</span>\n",
+              "</pre>\n"
+            ]
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "=== Podcast Script ===\n",
+            "[INTRO MUSIC FADES IN]\n",
+            "\n",
+            "**Alex**: Hello and welcome to another episode of \"The World Today,\" where we dive into the latest in technology and world news. I'm Alex, your go-to for all things analytical and fact-focused.\n",
+            "\n",
+            "**Morgan**: And I'm Morgan, here to explore the human impact and social context of today's stories. We've got a fascinating lineup for you today, so let's dive right in!\n",
+            "\n",
+            "**Alex**: First up, we're talking about a topic that's been making waves across the healthcare industry: the role of artificial intelligence. According to a recent article from [News Example](https://news.example.com/ai-healthcare), AI is revolutionizing healthcare in ways we could only dream of a decade ago.\n",
+            "\n",
+            "**Morgan**: That's right, Alex. AI is not just a buzzword anymore; it's actively changing how we approach healthcare. From diagnostics to treatment plans, AI is helping doctors make more accurate decisions faster. But what does this mean for patients and healthcare professionals?\n",
+            "\n",
+            "**Alex**: Well, Morgan, AI's ability to analyze vast amounts of data quickly means that doctors can diagnose diseases earlier and more accurately. For instance, AI algorithms can now detect patterns in medical imaging that might be too subtle for the human eye. This can lead to earlier interventions and better patient outcomes.\n",
+            "\n",
+            "**Morgan**: And let's not forget about the human side of things. For patients, this means less waiting time for results and potentially more personalized treatment plans. But there's also a concern about the human touch in healthcare. How do we balance the efficiency of AI with the empathy and understanding that only a human can provide?\n",
+            "\n",
+            "**Alex**: That's a great point. The integration of AI in healthcare does raise ethical questions. For example, who is responsible if an AI system makes a mistake? And how do we ensure that these systems are free from bias?\n",
+            "\n",
+            "**Morgan**: Exactly. There's a lot to consider, but the potential benefits are enormous. Imagine a world where healthcare is not only more efficient but also more accessible to people in remote areas thanks to AI-driven telemedicine.\n",
+            "\n",
+            "**Alex**: It's a fascinating time for healthcare, no doubt. But let's shift gears a bit and talk about another pressing issue: climate change and global policy. According to a report from [News Example](https://news.example.com/climate-policy), world leaders are currently meeting to discuss new policies to combat climate change.\n",
+            "\n",
+            "**Morgan**: Climate change is one of those issues that affects everyone, regardless of where you live. These global meetings are crucial because they set the stage for international cooperation. But what are the main challenges these leaders face?\n",
+            "\n",
+            "**Alex**: One of the biggest challenges is balancing economic growth with environmental sustainability. Many developing countries argue that they need to prioritize economic development, which often relies on fossil fuels. Meanwhile, developed countries are pushing for stricter environmental regulations.\n",
+            "\n",
+            "**Morgan**: It's a classic case of differing priorities. But there's also a growing recognition that climate change doesn't respect borders. Extreme weather events, rising sea levels, and shifting agricultural patterns affect us all. So, there's a real urgency to find common ground.\n",
+            "\n",
+            "**Alex**: And technology plays a significant role here too. Innovations in renewable energy, carbon capture, and sustainable agriculture are crucial in the fight against climate change. But implementing these technologies on a global scale requires significant investment and political will.\n",
+            "\n",
+            "**Morgan**: It's a complex issue, but it's encouraging to see world leaders coming together to address it. The policies they create today will shape the future for generations to come.\n",
+            "\n",
+            "**Alex**: Absolutely. And it's not just about government action. Individuals and businesses also have a role to play in reducing carbon footprints and advocating for sustainable practices.\n",
+            "\n",
+            "**Morgan**: It's a collective effort, and every little bit helps. Before we wrap up, Alex, any final thoughts on today's topics?\n",
+            "\n",
+            "**Alex**: Just that both AI in healthcare and climate change policies highlight the intersection of technology and society. They show us how innovation can drive progress but also remind us of the responsibilities that come with it.\n",
+            "\n",
+            "**Morgan**: Well said, Alex. It's all about finding that balance. And with that, we've reached the end of today's episode. Thanks for tuning in to \"The World Today.\"\n",
+            "\n",
+            "**Alex**: Don't forget to subscribe and join us next time for more insights into the latest in technology and world news.\n",
+            "\n",
+            "**Morgan**: Until then, stay informed and stay curious!\n",
+            "\n",
+            "[OUTRO MUSIC FADES OUT]\n"
+          ]
+        }
+      ]
+    }
+  ]
+}

examples/guardrail_example_fixed.py

@@ -0,0 +1,142 @@
+#!/usr/bin/env python3
+"""
+Fixed example demonstrating proper guardrail usage with PraisonAI Agents.
+This addresses the issues reported in issue #875.
+"""
+
+from praisonaiagents import Agent, Task, GuardrailResult, PraisonAIAgents, TaskOutput
+from typing import Tuple, Any
+import trafilatura
+
+# Example 1: Using GuardrailResult return type (now supported!)
+def validate_length_guardrailresult(output: TaskOutput) -> GuardrailResult:
+    """Ensure output is between 100-500 characters using GuardrailResult"""
+    # Extract the raw text from the TaskOutput object
+    text = output.raw if hasattr(output, 'raw') else str(output)
+    length = len(text)
+    
+    if 100 <= length <= 500:
+        return GuardrailResult(
+            success=True,
+            result=output,  # Pass through the original output
+            error=""
+        )
+    else:
+        return GuardrailResult(
+            success=False,
+            result=None,
+            error=f"Output must be 100-500 chars, got {length}"
+        )
+
+# Example 2: Using Tuple[bool, Any] return type (original method)
+def validate_length_tuple(output: TaskOutput) -> Tuple[bool, Any]:
+    """Ensure output is between 100-500 characters using tuple"""
+    text = output.raw if hasattr(output, 'raw') else str(output)
+    length = len(text)
+    
+    if 100 <= length <= 500:
+        return True, output
+    else:
+        return False, f"Output must be 100-500 chars, got {length}"
+
+# Tool function
+def get_url_context(url):
+    """Fetch and extract content from a URL"""
+    downloaded = trafilatura.fetch_url(url)
+    if not downloaded:
+        return "Sorry, I couldn't fetch the content from that URL."
+
+    extracted = trafilatura.extract(
+        downloaded,
+        include_comments=False,
+        include_links=True,
+        output_format='json',
+        with_metadata=True,
+        url=url
+    )
+
+    if not extracted:
+        return "Sorry, I couldn't extract readable content from that page."
+
+    return extracted  # returns JSON string
+
+# Create agent with FIXED tools parameter (must be a list!)
+agent = Agent(
+    name="Content Summarizer",
+    role="Content Analysis Expert",
+    goal="Summarize web content concisely",
+    instructions="You are a helpful assistant that summarizes web content",
+    llm="gemini/gemini-2.5-flash-lite-preview-06-17",
+    self_reflect=False,
+    verbose=True,
+    tools=[get_url_context]  # FIX: tools must be a list, not a single function
+)
+
+# Create task with GuardrailResult guardrail
+task_with_guardrailresult = Task(
+    name="summarise article with GuardrailResult",
+    description="get the context of this url: https://blog.google/technology/ai/dolphingemma/ and produce a summary below 500 characters",
+    agent=agent,
+    guardrail=validate_length_guardrailresult,  # Using GuardrailResult
+    expected_output="summary of the article below 500 characters",
+    max_retries=3  # Will retry up to 3 times if guardrail fails
+)
+
+# Alternative: Create task with tuple guardrail
+task_with_tuple = Task(
+    name="summarise article with tuple",
+    description="get the context of this url: https://blog.google/technology/ai/dolphingemma/ and produce a summary below 500 characters",
+    agent=agent,
+    guardrail=validate_length_tuple,  # Using Tuple[bool, Any]
+    expected_output="summary of the article below 500 characters",
+    max_retries=3
+)
+
+# Example with string-based LLM guardrail
+task_with_llm_guardrail = Task(
+    name="summarise with LLM guardrail",
+    description="get the context of this url: https://blog.google/technology/ai/dolphingemma/ and produce a summary",
+    agent=agent,
+    guardrail="Ensure the summary is professional, factual, and between 100-500 characters",
+    expected_output="professional summary of the article"
+)
+
+# Run with GuardrailResult example
+print("=== Running with GuardrailResult guardrail ===")
+agents_gr = PraisonAIAgents(
+    agents=[agent],
+    tasks=[task_with_guardrailresult]
+)
+
+# Uncomment to run:
+# result_gr = agents_gr.start()
+
+# Run with Tuple example
+print("\n=== Running with Tuple[bool, Any] guardrail ===")
+agents_tuple = PraisonAIAgents(
+    agents=[agent],
+    tasks=[task_with_tuple]
+)
+
+# Uncomment to run:
+# result_tuple = agents_tuple.start()
+
+# Run with LLM guardrail example
+print("\n=== Running with LLM-based guardrail ===")
+agents_llm = PraisonAIAgents(
+    agents=[agent],
+    tasks=[task_with_llm_guardrail]
+)
+
+# Uncomment to run:
+# result_llm = agents_llm.start()
+
+print("""
+Key fixes applied:
+1. GuardrailResult is now accepted as a valid return type annotation
+2. tools parameter must be a list: tools=[get_url_context] not tools=get_url_context
+3. Both GuardrailResult and Tuple[bool, Any] return types are supported
+4. String-based LLM guardrails are also supported
+
+The guardrail will automatically retry (up to max_retries times) if validation fails.
+""")

examples/python/agents/MULTI_PROVIDER_README.md

@@ -0,0 +1,259 @@
+# Multi-Provider/Multi-Model Support
+
+PraisonAI now supports intelligent multi-provider and multi-model capabilities, allowing agents to automatically select the most appropriate AI model based on task requirements, cost considerations, and performance needs.
+
+## 🚀 Key Features
+
+### 1. **Automatic Model Selection**
+- Analyzes task complexity and selects the best model
+- Considers cost vs. performance trade-offs
+- Supports fallback mechanisms for reliability
+
+### 2. **Cost Optimization**
+- Routes simple tasks to cheaper models (e.g., GPT-4o-mini, Gemini Flash)
+- Reserves expensive models for complex tasks
+- Tracks usage and provides cost estimates
+
+### 3. **Multi-Provider Support**
+- Works with OpenAI, Anthropic, Google, Groq, and more
+- Seamless switching between providers
+- Provider preference settings
+
+### 4. **Flexible Routing Strategies**
+- `auto`: Automatic selection based on task analysis
+- `cost-optimized`: Prioritize cheaper models
+- `performance-optimized`: Prioritize capability
+- `manual`: Use specified model
+
+## 📦 Installation
+
+The multi-provider support is included in the standard installation:
+
+```bash
+pip install praisonaiagents
+```
+
+## 🔧 Basic Usage
+
+### Simple Multi-Model Agent
+
+```python
+from praisonaiagents import Task, PraisonAIAgents
+from praisonaiagents.agent import RouterAgent
+
+# Create a multi-model agent
+agent = RouterAgent(
+    name="Smart Assistant",
+    role="Adaptive AI Assistant",
+    goal="Complete tasks using the most appropriate model",
+    models=["gpt-4o-mini", "gpt-4o", "claude-3-5-sonnet-20241022"],
+    routing_strategy="auto"  # Automatic model selection
+)
+
+# Create tasks
+simple_task = Task(
+    name="calculate",
+    description="What is 15% of 250?",
+    agent=agent
+)
+
+complex_task = Task(
+    name="analyze",
+    description="Write a Python implementation of the A* pathfinding algorithm",
+    agent=agent
+)
+
+# Run tasks - agent will automatically select appropriate models
+agents = PraisonAIAgents(
+    agents=[agent],
+    tasks=[simple_task, complex_task]
+)
+
+results = agents.start()
+```
+
+### Cost-Optimized Workflow
+
+```python
+from praisonaiagents.llm import ModelRouter
+
+# Create custom router with cost constraints
+router = ModelRouter(
+    cost_threshold=0.005,  # Max $0.005 per 1k tokens
+    preferred_providers=["google", "openai"]
+)
+
+# Create cost-conscious agent
+analyzer = RouterAgent(
+    name="Budget Analyzer",
+    role="Data Analyst",
+    goal="Analyze data efficiently",
+    models={
+        "gemini/gemini-1.5-flash": {},
+        "gpt-4o-mini": {},
+        "claude-3-haiku-20240307": {}
+    },
+    model_router=router,
+    routing_strategy="cost-optimized"
+)
+```
+
+## 🎯 Routing Strategies
+
+### Auto Routing (Default)
+Automatically selects models based on:
+- Task complexity analysis
+- Required capabilities (tools, vision, etc.)
+- Context size requirements
+- Cost/performance balance
+
+### Cost-Optimized
+Prioritizes cheaper models while meeting task requirements:
+- Uses lightweight models for simple tasks
+- Only escalates to expensive models when necessary
+- Ideal for high-volume operations
+
+### Performance-Optimized
+Prioritizes model capability:
+- Uses the best available model for the task
+- Ideal for quality-critical applications
+- Less concern for cost
+
+### Manual
+Uses the specified model without routing:
+- Direct control over model selection
+- Useful for testing or specific requirements
+
+## 📊 Model Profiles
+
+The system includes pre-configured profiles for popular models:
+
+| Model | Provider | Best For | Cost/1k tokens |
+|-------|----------|----------|----------------|
+| gpt-4o-mini | OpenAI | Simple tasks, speed | $0.00075 |
+| gemini-1.5-flash | Google | Cost-effective, multimodal | $0.000125 |
+| claude-3-haiku | Anthropic | Fast responses | $0.0008 |
+| gpt-4o | OpenAI | General purpose | $0.0075 |
+| claude-3-5-sonnet-20241022 | Anthropic | Complex reasoning | $0.009 |
+| deepseek-chat | DeepSeek | Code & math | $0.0014 |
+
+## 🔍 Task Complexity Analysis
+
+The system analyzes tasks to determine complexity:
+
+- **Simple**: Basic calculations, definitions, yes/no questions
+- **Moderate**: Summarization, basic analysis, classification
+- **Complex**: Code generation, algorithm implementation
+- **Very Complex**: Multi-step reasoning, system design
+
+## 📈 Usage Tracking
+
+Track model usage and costs:
+
+```python
+# Get usage report
+report = agent.get_usage_report()
+print(report)
+
+# Output:
+{
+    'agent_name': 'Smart Assistant',
+    'routing_strategy': 'auto',
+    'model_usage': {
+        'gpt-4o-mini': {'calls': 5, 'tokens': 1500, 'cost': 0.0011},
+        'gpt-4o': {'calls': 2, 'tokens': 3000, 'cost': 0.0225}
+    },
+    'total_cost_estimate': 0.0236,
+    'total_calls': 7
+}
+```
+
+## 🛠️ Custom Model Configuration
+
+Add custom model profiles:
+
+```python
+from praisonaiagents.llm import ModelProfile, TaskComplexity
+
+custom_model = ModelProfile(
+    name="custom-model",
+    provider="custom",
+    complexity_range=(TaskComplexity.SIMPLE, TaskComplexity.MODERATE),
+    cost_per_1k_tokens=0.002,
+    strengths=["domain-specific"],
+    capabilities=["text"],
+    context_window=32000
+)
+
+router = ModelRouter(models=[custom_model])
+```
+
+## 🔗 Integration with AutoAgents
+
+Works seamlessly with AutoAgents:
+
+```python
+from praisonaiagents.agents import AutoAgents
+
+# Create auto agents
+auto = AutoAgents(
+    instructions="Analyze market trends and create a report",
+    max_agents=3
+)
+
+# Convert to multi-model agents
+for i, agent in enumerate(auto.agents):
+    auto.agents[i] = RouterAgent(
+        name=agent.name,
+        role=agent.role,
+        goal=agent.goal,
+        models=["gpt-4o-mini", "gpt-4o", "claude-3-5-sonnet"],
+        routing_strategy="auto"
+    )
+
+results = auto.start()
+```
+
+## 🌟 Best Practices
+
+1. **Start with Auto Routing**: Let the system learn your needs
+2. **Monitor Costs**: Use usage reports to optimize
+3. **Set Cost Thresholds**: Prevent unexpected expenses
+4. **Use Appropriate Models**: Don't use GPT-4 for simple math
+5. **Leverage Fallbacks**: Configure fallback models for reliability
+
+## 🔐 Environment Variables
+
+Set API keys for each provider:
+
+```bash
+export OPENAI_API_KEY="sk-..."
+export ANTHROPIC_API_KEY="sk-ant-..."
+export GEMINI_API_KEY="..."
+export GROQ_API_KEY="..."
+```
+
+## 🤝 Contributing
+
+The multi-provider system is extensible. To add new models:
+
+1. Add model profile to `ModelRouter.DEFAULT_MODELS`
+2. Ensure the provider is supported by LiteLLM
+3. Test with various task complexities
+
+## 📚 Examples
+
+See the complete example in `examples/python/agents/multi-provider-agent.py` for:
+- Auto-routing examples
+- Cost-optimized workflows
+- Performance-optimized agents
+- Custom routing logic
+- Integration patterns
+
+## 🎉 Benefits
+
+- **Cost Savings**: Reduce API costs by 50-80%
+- **Better Performance**: Use the right tool for each job
+- **Flexibility**: Switch providers without code changes
+- **Reliability**: Automatic fallbacks and error handling
+- **Transparency**: Track usage and costs

examples/python/agents/multi-provider-agent.py

@@ -0,0 +1,285 @@
+"""
+Multi-Provider/Multi-Model Agent Example
+
+This example demonstrates how to use multiple AI providers/models with intelligent
+agent-based selection for cost optimization and performance.
+"""
+
+import os
+from praisonaiagents import Agent, Task, PraisonAIAgents
+from praisonaiagents.agent import RouterAgent
+from praisonaiagents.llm.model_router import ModelRouter, ModelProfile, TaskComplexity
+
+# Example 1: Simple Multi-Model Agent with Auto-Routing
+def example_auto_routing():
+    """Example of automatic model routing based on task complexity"""
+    print("\n=== Example 1: Auto-Routing Multi-Model Agent ===\n")
+    
+    # Create a router agent that automatically selects models
+    research_agent = RouterAgent(
+        name="Smart Researcher",
+        role="Adaptive Research Assistant",
+        goal="Research topics using the most appropriate AI model",
+        backstory="I analyze task complexity and route to the best model",
+        models=["gpt-4o-mini", "gpt-4o", "claude-3-5-sonnet-20241022"],
+        routing_strategy="auto",  # Automatic model selection
+        verbose=True
+    )
+    
+    # Create tasks with different complexity levels
+    simple_task = Task(
+        name="simple_calculation",
+        description="Calculate the sum of 1542 and 2873",
+        expected_output="The numerical result",
+        agent=research_agent
+    )
+    
+    moderate_task = Task(
+        name="summarize_article", 
+        description="Summarize the key points about renewable energy trends",
+        expected_output="A concise summary with main points",
+        agent=research_agent
+    )
+    
+    complex_task = Task(
+        name="analyze_code",
+        description="Implement a Python function to find the longest palindromic substring in a given string with O(n^2) complexity",
+        expected_output="Complete Python implementation with explanation",
+        agent=research_agent
+    )
+    
+    # Run the tasks
+    agents = PraisonAIAgents(
+        agents=[research_agent],
+        tasks=[simple_task, moderate_task, complex_task],
+        process="sequential",
+        verbose=True
+    )
+    
+    results = agents.start()
+    
+    # Show usage report
+    print("\n=== Model Usage Report ===")
+    print(research_agent.get_usage_report())
+
+
+# Example 2: Cost-Optimized Workflow with Routing
+def example_cost_optimized_workflow():
+    """Example of cost-optimized workflow with model routing"""
+    print("\n=== Example 2: Cost-Optimized Workflow ===\n")
+    
+    # Create custom model router with cost threshold
+    cost_router = ModelRouter(
+        cost_threshold=0.01,  # Max $0.01 per 1k tokens
+        preferred_providers=["google", "openai", "anthropic"]  # Provider preference
+    )
+    
+    # Create specialized agents with different model strategies
+    analyzer = RouterAgent(
+        name="Cost-Conscious Analyzer",
+        role="Data Analyzer",
+        goal="Analyze data efficiently while minimizing costs",
+        models={
+            "gemini/gemini-1.5-flash": {},
+            "gpt-4o-mini": {},
+            "deepseek-chat": {}
+        },
+        model_router=cost_router,
+        routing_strategy="cost-optimized",
+        verbose=True
+    )
+    
+    writer = RouterAgent(
+        name="Quality Writer",
+        role="Content Writer", 
+        goal="Create high-quality content",
+        models={
+            "claude-3-5-sonnet-20241022": {},
+            "gpt-4o": {}
+        },
+        routing_strategy="performance-optimized",  # Prefer better models
+        verbose=True
+    )
+    
+    # Create workflow tasks
+    analysis_task = Task(
+        name="analyze_data",
+        description="Analyze this dataset: [1, 2, 3, 4, 5]. Find mean, median, and mode.",
+        expected_output="Statistical analysis results",
+        agent=analyzer
+    )
+    
+    writing_task = Task(
+        name="write_report",
+        description="Write a professional report based on the analysis",
+        expected_output="Professional report with insights",
+        agent=writer,
+        context=[analysis_task]  # Use results from analysis
+    )
+    
+    # Run workflow
+    workflow = PraisonAIAgents(
+        agents=[analyzer, writer],
+        tasks=[analysis_task, writing_task],
+        process="sequential",
+        verbose=True
+    )
+    
+    results = workflow.start()
+    
+    # Show cost comparison
+    print("\n=== Cost Analysis ===")
+    print(f"Analyzer costs: {analyzer.get_usage_report()}")
+    print(f"Writer costs: {writer.get_usage_report()}")
+
+
+# Example 3: Auto Agent Mode with Multi-Provider Support
+def example_auto_agents_multi_provider():
+    """Example using AutoAgents with multi-provider support"""
+    print("\n=== Example 3: AutoAgents with Multi-Provider Support ===\n")
+    
+    from praisonaiagents.agents import AutoAgents
+    
+    # Create AutoAgents that will automatically assign appropriate models
+    auto_agents = AutoAgents(
+        instructions="Create a market research report on electric vehicles. Include data analysis, competitor analysis, and future projections.",
+        max_agents=3,
+        llm="gpt-4o-mini",  # Default model for agent generation
+        verbose=True
+    )
+    
+    # After agents are created, upgrade them to multi-model agents
+    multi_model_agents = []
+    for agent in auto_agents.agents:
+        # Convert regular agents to multi-model agents
+        multi_agent = RouterAgent(
+            name=agent.name,
+            role=agent.role,
+            goal=agent.goal,
+            backstory=agent.backstory,
+            tools=agent.tools,
+            models=["gpt-4o-mini", "gemini/gemini-1.5-flash", "claude-3-haiku-20240307", "gpt-4o"],
+            routing_strategy="auto",
+            verbose=True
+        )
+        multi_model_agents.append(multi_agent)
+    
+    # Update the agents in the AutoAgents instance
+    auto_agents.agents = multi_model_agents
+    
+    # Run the auto-generated workflow
+    results = auto_agents.start()
+    
+    # Show model usage across all agents
+    print("\n=== Multi-Provider Usage Summary ===")
+    total_calls = 0
+    for agent in multi_model_agents:
+        report = agent.get_usage_report()
+        print(f"\nAgent: {agent.name}")
+        for model, stats in report['model_usage'].items():
+            if stats['calls'] > 0:
+                print(f"  - {model}: {stats['calls']} calls")
+                total_calls += stats['calls']
+    
+    print(f"\nTotal API calls: {total_calls}")
+
+
+# Example 4: Custom Routing Logic
+def example_custom_routing():
+    """Example with custom routing logic based on specific requirements"""
+    print("\n=== Example 4: Custom Routing Logic ===\n")
+    
+    # Create custom model profiles for specific use cases
+    custom_models = [
+        ModelProfile(
+            name="gpt-4o",
+            provider="openai",
+            complexity_range=(TaskComplexity.SIMPLE, TaskComplexity.VERY_COMPLEX),
+            cost_per_1k_tokens=0.0075,
+            strengths=["code-generation", "debugging"],
+            capabilities=["text", "function-calling"],
+            context_window=128000
+        ),
+        ModelProfile(
+            name="deepseek-chat",
+            provider="deepseek",
+            complexity_range=(TaskComplexity.MODERATE, TaskComplexity.VERY_COMPLEX),
+            cost_per_1k_tokens=0.001,
+            strengths=["mathematics", "algorithms"],
+            capabilities=["text", "function-calling"],
+            context_window=128000
+        )
+    ]
+    
+    # Create router with custom models
+    custom_router = ModelRouter(models=custom_models)
+    
+    # Tool for web search (example)
+    def search_web(query: str) -> str:
+        """Search the web for information"""
+        return f"Search results for: {query}"
+    
+    # Create specialized agent
+    coder = RouterAgent(
+        name="Adaptive Coder",
+        role="Software Developer",
+        goal="Write and debug code using the best model for each task",
+        backstory="I'm an expert coder who knows when to use different AI models",
+        model_router=custom_router,
+        routing_strategy="auto",
+        tools=[search_web],
+        verbose=True
+    )
+    
+    # Create coding tasks
+    tasks = [
+        Task(
+            name="fix_bug",
+            description="Fix this Python bug: 'list' object has no attribute 'appendx'",
+            expected_output="Corrected code with explanation",
+            agent=coder
+        ),
+        Task(
+            name="implement_algorithm",
+            description="Implement Dijkstra's shortest path algorithm in Python",
+            expected_output="Complete implementation with comments",
+            agent=coder,
+            tools=[search_web]
+        )
+    ]
+    
+    # Run tasks
+    agents = PraisonAIAgents(
+        agents=[coder],
+        tasks=tasks,
+        process="sequential",
+        verbose=True
+    )
+    
+    results = agents.start()
+    
+    print("\n=== Custom Routing Results ===")
+    print(coder.get_usage_report())
+
+
+# Run examples
+if __name__ == "__main__":
+    # Make sure to set your API keys
+    # os.environ["OPENAI_API_KEY"] = "your-openai-key"
+    # os.environ["ANTHROPIC_API_KEY"] = "your-anthropic-key"  
+    # os.environ["GEMINI_API_KEY"] = "your-gemini-key"
+    
+    # Run examples
+    example_auto_routing()
+    example_cost_optimized_workflow()
+    example_auto_agents_multi_provider()
+    example_custom_routing()
+    
+    print("\n=== All Examples Completed ===")
+    print("\nKey Features Demonstrated:")
+    print("1. Automatic model selection based on task complexity")
+    print("2. Cost-optimized routing for budget-conscious operations")
+    print("3. Performance-optimized routing for quality-critical tasks")
+    print("4. Multi-provider support with fallback mechanisms")
+    print("5. Integration with AutoAgents for automatic workflow generation")
+    print("6. Custom routing logic for specialized use cases")

examples/python/custom_tools/hosted_server.py

@@ -0,0 +1,197 @@
+"""
+Hosted MCP Server implementation for PraisonAI Agents.
+
+This module provides a base class for creating hosted MCP servers
+that can handle requests and integrate with the MCP protocol.
+
+Note: This is an example implementation. To use it, ensure you have installed:
+  pip install praisonaiagents[mcp] starlette>=0.27.0
+"""
+
+import asyncio
+import logging
+from typing import Dict, Any, Optional, List, Callable
+import json
+
+try:
+    from mcp.server.fastmcp import FastMCP
+    from mcp.server import Server
+    from starlette.applications import Starlette
+    from starlette.requests import Request
+    from starlette.routing import Mount, Route
+    from mcp.server.sse import SseServerTransport
+    import uvicorn
+except ImportError:
+    raise ImportError(
+        "MCP server dependencies not installed. "
+        "Please install with: pip install praisonaiagents[mcp] starlette>=0.27.0"
+    )
+
+logger = logging.getLogger(__name__)
+
+
+class HostedMCPServer:
+    """
+    Base class for creating hosted MCP servers.
+    
+    This class provides a foundation for building MCP servers that can:
+    - Handle incoming requests
+    - Define custom tools
+    - Support SSE transport
+    - Be extended with custom functionality like latency tracking
+    """
+    
+    def __init__(self, name: str = "hosted-mcp-server", host: str = "localhost", port: int = 8080):
+        """
+        Initialize the hosted MCP server.
+        
+        Args:
+            name: Server name for identification
+            host: Host to bind to (default: localhost)
+            port: Port to listen on (default: 8080)
+        """
+        self.name = name
+        self.host = host
+        self.port = port
+        self.mcp = FastMCP(name)
+        self._tools: Dict[str, Callable] = {}
+        self._server: Optional[Server] = None
+        self._app: Optional[Starlette] = None
+        
+    def handle_request(self, request_data: Dict[str, Any]) -> Dict[str, Any]:
+        """
+        Handle incoming MCP requests.
+        
+        This method can be overridden in subclasses to add custom request handling,
+        such as latency tracking, authentication, or request modification.
+        
+        Args:
+            request_data: The incoming request data
+            
+        Returns:
+            Response data
+        """
+        # Default implementation - can be overridden
+        method = request_data.get('method', '')
+        request_id = request_data.get('id', 'unknown')
+        
+        logger.debug(f"Handling request {request_id}: {method}")
+        
+        # Basic response structure
+        response = {
+            'id': request_id,
+            'jsonrpc': '2.0',
+            'result': {}
+        }
+        
+        return response
+    
+    def add_tool(self, func: Callable, name: Optional[str] = None, description: Optional[str] = None):
+        """
+        Add a tool to the MCP server.
+        
+        Args:
+            func: The function to expose as a tool
+            name: Optional name for the tool (defaults to function name)
+            description: Optional description for the tool
+        """
+        tool_name = name or func.__name__
+        
+        # Register with FastMCP
+        if asyncio.iscoroutinefunction(func):
+            # Already async
+            self.mcp.tool(name=tool_name)(func)
+        else:
+            # Wrap sync function in async
+            async def async_wrapper(*args, **kwargs):
+                return func(*args, **kwargs)
+            async_wrapper.__name__ = func.__name__
+            async_wrapper.__doc__ = description or func.__doc__
+            self.mcp.tool(name=tool_name)(async_wrapper)
+        
+        self._tools[tool_name] = func
+        logger.info(f"Added tool: {tool_name}")
+    
+    def create_app(self, debug: bool = False) -> Starlette:
+        """
+        Create a Starlette application for serving the MCP server.
+        
+        Args:
+            debug: Enable debug mode
+            
+        Returns:
+            Starlette application instance
+            
+        Raises:
+            RuntimeError: If the MCP server is not properly initialized
+        """
+        if not self._server:
+            if not hasattr(self.mcp, '_mcp_server'):
+                raise RuntimeError("MCP server not properly initialized. Ensure FastMCP is correctly set up.")
+            self._server = self.mcp._mcp_server
+        
+        sse = SseServerTransport("/messages/")
+        
+        async def handle_sse(request: Request) -> None:
+            logger.debug(f"SSE connection from {request.client}")
+            async with sse.connect_sse(
+                request.scope,
+                request.receive,
+                request._send,
+            ) as (read_stream, write_stream):
+                await self._server.run(
+                    read_stream,
+                    write_stream,
+                    self._server.create_initialization_options(),
+                )
+        
+        self._app = Starlette(
+            debug=debug,
+            routes=[
+                Route("/sse", endpoint=handle_sse),
+                Mount("/messages/", app=sse.handle_post_message),
+            ],
+        )
+        
+        return self._app
+    
+    def start(self, debug: bool = False, **uvicorn_kwargs):
+        """
+        Start the MCP server.
+        
+        Args:
+            debug: Enable debug mode
+            **uvicorn_kwargs: Additional arguments to pass to uvicorn
+        """
+        app = self.create_app(debug=debug)
+        
+        print(f"Starting {self.name} MCP server on {self.host}:{self.port}")
+        print(f"Available tools: {', '.join(self._tools.keys())}")
+        print(f"SSE endpoint: http://{self.host}:{self.port}/sse")
+        
+        uvicorn.run(app, host=self.host, port=self.port, **uvicorn_kwargs)
+    
+    async def start_async(self, debug: bool = False):
+        """
+        Start the MCP server asynchronously.
+        
+        Args:
+            debug: Enable debug mode
+        """
+        app = self.create_app(debug=debug)
+        
+        config = uvicorn.Config(app, host=self.host, port=self.port)
+        server = uvicorn.Server(config)
+        
+        print(f"Starting {self.name} MCP server on {self.host}:{self.port}")
+        print(f"Available tools: {', '.join(self._tools.keys())}")
+        
+        await server.serve()
+    
+    def get_tools(self) -> List[str]:
+        """Get list of available tool names."""
+        return list(self._tools.keys())
+    
+    def get_endpoint(self) -> str:
+        """Get the SSE endpoint URL."""
+        return f"http://{self.host}:{self.port}/sse"

examples/python/custom_tools/mcp_server_latency_example.py

@@ -6,7 +6,7 @@ without modifying PraisonAI core files.
 """
 
 from praisonaiagents import Agent, PraisonAIAgents
-from praisonaiagents.mcp import HostedMCPServer
+from hosted_server import HostedMCPServer  # Import from local file
 from latency_tracker_tool import tracker, get_latency_metrics
 import json
 

examples/python/general/prompt_chaining.py

@@ -72,7 +72,7 @@ workflow = PraisonAIAgents(
 )
 
 # Run the workflow
-results = workflow.start()
+results = workflow.start(return_dict=True)
 
 # Print results
 print("\nWorkflow Results:")

examples/python/tools/exa-tool/Finance_Market_Job_Agents/Financial_Coaching_Agent.py

@@ -0,0 +1,108 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+"""
+News and Podcast Aggregator Agent using PraisonAIAgents
+
+This script summarizes news articles and generates podcast-style discussion points.
+It is CI-friendly: it uses dummy data if API keys are not set.
+"""
+
+import os
+from datetime import datetime
+from praisonaiagents import Agent
+
+# Set up the OpenAI API key for praisonaiagents
+OPENAI_API_KEY = os.environ.get("OPENAI_API_KEY", "sk-..")
+os.environ["OPENAI_API_KEY"] = OPENAI_API_KEY
+
+def is_valid_key(key, prefix):
+    return key and key != f"{prefix}-.." and key.startswith(prefix)
+
+# Custom Tool: Format search results for podcast
+def format_search_results_for_podcast(search_results):
+    created_at = datetime.now().strftime("%B %d, %Y at %I:%M %p")
+    structured_content = []
+    structured_content.append(f"PODCAST CREATION: {created_at}\n")
+    sources = []
+    for idx, search_result in enumerate(search_results):
+        try:
+            if search_result.get("confirmed", False):
+                sources.append(search_result["url"])
+                structured_content.append(
+                    f"""
+                    SOURCE {idx + 1}:
+                    Title: {search_result['title']}
+                    URL: {search_result['url']}
+                    Content: {search_result.get('full_text') or search_result.get('description', '')}
+                    ---END OF SOURCE {idx + 1}---
+                    """.strip()
+                )
+        except Exception as e:
+            print(f"Error processing search result: {e}")
+    content_texts = "\n\n".join(structured_content)
+    return content_texts, sources
+
+# Agent Instructions
+from textwrap import dedent
+
+PODCAST_AGENT_INSTRUCTIONS = dedent("""
+    You are a helpful assistant that can generate engaging podcast scripts for the given source content and query.
+    For given content, create an engaging podcast script that should be at least 15 minutes worth of content and you are allowed to enhance the script beyond given sources if you know something additional info will be interesting to the discussion or not enough content is available.
+    You use the provided sources to ground your podcast script generation process. Keep it engaging and interesting.
+    IMPORTANT: Generate the entire script in the provided language.
+    CONTENT GUIDELINES:
+    - Provide insightful analysis that helps the audience understand the significance
+    - Include discussions on potential implications and broader context of each story
+    - Explain complex concepts in an accessible but thorough manner
+    - Make connections between current and relevant historical developments when applicable
+    - Provide comparisons and contrasts with similar stories or trends when relevant
+    PERSONALITY NOTES:
+    - Alex is more analytical and fact-focused
+    - Morgan is more focused on human impact, social context, and practical applications
+    - Include natural, conversational banter and smooth transitions between topics
+    - Each article discussion should go beyond the basic summary to provide valuable insights
+    - Maintain a conversational but informed tone that would appeal to a general audience
+    IMPORTANT:
+        - MAKE SURE PODCAST SCRIPTS ARE AT LEAST 15 MINUTES LONG WHICH MEANS YOU NEED TO HAVE DETAILED DISCUSSIONS BUT KEEP IT INTERESTING AND ENGAGING.
+""")
+
+if __name__ == "__main__":
+    # Dummy search results for CI/public use
+    dummy_search_results = [
+        {
+            "confirmed": True,
+            "title": "AI Revolutionizes Healthcare",
+            "url": "https://news.example.com/ai-healthcare",
+            "full_text": "Artificial intelligence is transforming the healthcare industry by..."
+        },
+        {
+            "confirmed": True,
+            "title": "Climate Change and Global Policy",
+            "url": "https://news.example.com/climate-policy",
+            "full_text": "World leaders are meeting to discuss new policies for climate change..."
+        }
+    ]
+
+    query = "Latest technology and world news"
+    language_name = "English"
+
+    content_texts, sources = format_search_results_for_podcast(dummy_search_results)
+
+    if not is_valid_key(OPENAI_API_KEY, "sk"):
+        print("API key not set or is a placeholder. Using dummy podcast script for CI/testing.")
+        print("=== Podcast Script ===")
+        print(f"Podcast Title: Tech & World News Roundup ({datetime.now().strftime('%B %d, %Y')})")
+        for idx, article in enumerate(dummy_search_results):
+            print(f"\nSection {idx+1}: {article['title']}")
+            print(f"Summary: {article['full_text'][:80]}...")
+    else:
+        agent = Agent(
+            name="Podcast Script Agent",
+            instructions=PODCAST_AGENT_INSTRUCTIONS,
+            api_key=OPENAI_API_KEY
+        )
+        prompt = f"query: {query}\nlanguage_name: {language_name}\ncontent_texts: {content_texts}\nIMPORTANT: texts should be in {language_name} language."
+        podcast_script = agent.start(prompt)
+        print("=== Podcast Script ===")
+        print(podcast_script)

examples/python/tools/exa-tool/Health_Fitness_Agents/Air_Quality_Analysis_Agent.py

@@ -0,0 +1,165 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+"""
+Air Quality Analysis Agent using PraisonAIAgents
+
+This script retrieves real-time air quality data for a specified location, analyzes the results, and provides actionable health recommendations.
+It uses only praisonaiagents and is CI-friendly: it uses dummy data if API keys are not set.
+"""
+
+import os
+import requests
+import yaml
+from praisonaiagents import Agent
+
+# Set up API keys
+FIRECRAWL_API_KEY = os.environ.get("FIRECRAWL_API_KEY", "fc-..")
+OPENAI_API_KEY = os.environ.get("OPENAI_API_KEY", "sk-..")
+os.environ["FIRECRAWL_API_KEY"] = FIRECRAWL_API_KEY
+os.environ["OPENAI_API_KEY"] = OPENAI_API_KEY
+
+# Tool: AQI Data Fetcher
+class AQIDataFetcher:
+    def __init__(self, firecrawl_key: str):
+        from firecrawl import FirecrawlApp
+        self.firecrawl = FirecrawlApp(api_key=firecrawl_key)
+
+    def fetch(self, country: str, state: str, city: str):
+        country_clean = country.lower().replace(' ', '-')
+        city_clean = city.lower().replace(' ', '-')
+        if not state or state.lower() == 'none':
+            url = f"https://www.aqi.in/dashboard/{country_clean}/{city_clean}"
+        else:
+            state_clean = state.lower().replace(' ', '-')
+            url = f"https://www.aqi.in/dashboard/{country_clean}/{state_clean}/{city_clean}"
+
+        print(f"Testing URL: {url}")
+        try:
+            resp = requests.get(url)
+            print(f"Status code: {resp.status_code}")
+            if resp.status_code != 200:
+                print(f"URL not reachable: {url} (status code: {resp.status_code})")
+                return None
+        except Exception as e:
+            print(f"Error: {e}")
+            return None
+
+        schema = {
+            "type": "object",
+            "properties": {
+                "aqi": {"type": "number", "description": "Air Quality Index"},
+                "temperature": {"type": "number", "description": "Temperature in degrees Celsius"},
+                "humidity": {"type": "number", "description": "Humidity percentage"},
+                "wind_speed": {"type": "number", "description": "Wind speed in kilometers per hour"},
+                "pm25": {"type": "number", "description": "Particulate Matter 2.5 micrometers"},
+                "pm10": {"type": "number", "description": "Particulate Matter 10 micrometers"},
+                "co": {"type": "number", "description": "Carbon Monoxide level"}
+            },
+            "required": ["aqi", "temperature", "humidity", "wind_speed", "pm25", "pm10", "co"]
+        }
+
+        response = self.firecrawl.extract(
+            urls=[f"{url}/*"],
+            prompt='Extract the current real-time AQI, temperature, humidity, wind speed, PM2.5, PM10, and CO levels from the page. Also extract the timestamp of the data.',
+            schema=schema
+        )
+        return response
+
+# YAML prompt (for documentation/logging)
+yaml_prompt = """
+agent:
+  name: Air Quality Health Advisor
+  description: |
+    An agent that analyzes real-time air quality data for a given location and provides personalized health recommendations based on user context.
+  tools:
+    - name: AQIDataFetcher
+      description: Fetches AQI and weather data for a specified city, state, and country using Firecrawl.
+  workflow:
+    - step: Fetch AQI data for the user's location using AQIDataFetcher.
+    - step: Analyze AQI and weather data.
+    - step: Consider user's medical conditions and planned activity.
+    - step: Generate health and activity recommendations.
+inputs:
+  - city
+  - state
+  - country
+  - medical_conditions
+  - planned_activity
+outputs:
+  - recommendations
+"""
+print(yaml.safe_load(yaml_prompt))
+
+if __name__ == "__main__":
+    # User input (you can change these for other locations)
+    user_city = "Mumbai"
+    user_state = "Maharashtra"
+    user_country = "India"
+    user_medical_conditions = "asthma"
+    user_planned_activity = "morning jog for 2 hours"
+
+    aqi_fetcher = AQIDataFetcher(firecrawl_key=os.environ["FIRECRAWL_API_KEY"])
+
+    # Try with state, then without state, then fallback to Delhi
+    aqi_data = aqi_fetcher.fetch(
+        country=user_country,
+        state=user_state,
+        city=user_city
+    )
+
+    if not aqi_data or not hasattr(aqi_data, "data"):
+        print("Mumbai with state failed, trying without state...")
+        aqi_data = aqi_fetcher.fetch(
+            country=user_country,
+            state="",
+            city=user_city
+        )
+
+    if not aqi_data or not hasattr(aqi_data, "data"):
+        print("Trying Delhi, India...")
+        aqi_data = aqi_fetcher.fetch(
+            country="India",
+            state="",
+            city="Delhi"
+        )
+
+    if not aqi_data or not hasattr(aqi_data, "data"):
+        print("Failed to fetch AQI data for all tried locations. Please check the URLs manually.")
+    else:
+        aqi_data = aqi_data.data  # Convert to dict
+
+        prompt = f"""
+        You are an expert health advisor.
+
+        Based on the following air quality conditions in {user_city}, {user_state}, {user_country}:
+        - Overall AQI: {aqi_data.get('aqi', 'N/A')}
+        - PM2.5 Level: {aqi_data.get('pm25', 'N/A')} µg/m³
+        - PM10 Level: {aqi_data.get('pm10', 'N/A')} µg/m³
+        - CO Level: {aqi_data.get('co', 'N/A')} ppb
+
+        Weather conditions:
+        - Temperature: {aqi_data.get('temperature', 'N/A')}°C
+        - Humidity: {aqi_data.get('humidity', 'N/A')}%
+        - Wind Speed: {aqi_data.get('wind_speed', 'N/A')} km/h
+
+        User's Context:
+        - Medical Conditions: {user_medical_conditions or 'None'}
+        - Planned Activity: {user_planned_activity}
+
+        **Comprehensive Health Recommendations:**
+        1. **Impact of Current Air Quality on Health:**
+        2. **Necessary Safety Precautions for Planned Activity:**
+        3. **Advisability of Planned Activity:**
+        4. **Best Time to Conduct the Activity:**
+        """
+
+        agent = Agent(
+            name="Air Quality Health Advisor",
+            instructions=prompt,
+            api_key=os.environ["OPENAI_API_KEY"]
+        )
+
+        recommendations = agent.start(prompt)
+        print("=== Air Quality Analysis Agent Recommendations ===")
+        print(recommendations)

examples/python/tools/exa-tool/Programming_Code_Analysis_Agents/Game_Playing_Agent_Tic_Tac_Toe.py

@@ -0,0 +1,107 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+"""
+Game Playing Agent (Tic Tac Toe) using PraisonAIAgents
+
+Two AI agents play against each other, coordinated by a referee agent.
+This script is CI-friendly: it uses dummy moves if API keys are not set.
+"""
+
+import os
+from praisonaiagents import Agent
+
+# Set up key (robust, CI-safe)
+OPENAI_API_KEY = os.environ.get("OPENAI_API_KEY", "sk-..")
+os.environ["OPENAI_API_KEY"] = OPENAI_API_KEY
+
+def is_valid_key(key, prefix):
+    return key and key != f"{prefix}-.." and key.startswith(prefix)
+
+# Custom Tool: Tic Tac Toe Board & Logic
+class TicTacToeBoard:
+    def __init__(self):
+        self.board = [[" " for _ in range(3)] for _ in range(3)]
+        self.current_player = "X"
+
+    def display(self):
+        for row in self.board:
+            print("|".join(row))
+            print("-" * 5)
+
+    def valid_moves(self):
+        return [(i, j) for i in range(3) for j in range(3) if self.board[i][j] == " "]
+
+    def make_move(self, row, col):
+        if self.board[row][col] == " ":
+            self.board[row][col] = self.current_player
+            self.current_player = "O" if self.current_player == "X" else "X"
+            return True
+        return False
+
+    def check_winner(self):
+        lines = self.board + [list(col) for col in zip(*self.board)]  # rows and columns
+        lines += [[self.board[i][i] for i in range(3)], [self.board[i][2-i] for i in range(3)]]  # diagonals
+        for line in lines:
+            if line == ["X"] * 3:
+                return "X"
+            if line == ["O"] * 3:
+                return "O"
+        if all(cell != " " for row in self.board for cell in row):
+            return "Draw"
+        return None
+
+if __name__ == "__main__":
+    # Dummy agent moves for CI/public use
+    dummy_moves = [(0, 0), (1, 1), (0, 1), (1, 0), (0, 2)]
+
+    board = TicTacToeBoard()
+    winner = None
+
+    if not is_valid_key(OPENAI_API_KEY, "sk"):
+        print("API key not set or is a placeholder. Using dummy moves for CI/testing.")
+        print("=== Tic Tac Toe Game ===")
+        board.display()
+        for move in dummy_moves:
+            board.make_move(*move)
+            board.display()
+            winner = board.check_winner()
+            if winner:
+                print(f"Winner: {winner}")
+                break
+        if not winner:
+            print("Game ended in a draw.")
+    else:
+        # Real agent-vs-agent play using praisonaiagents
+        player_x = Agent(
+            name="Player X",
+            instructions="You are Player X. Choose your move as 'row col' (e.g., '1 2').",
+            api_key=OPENAI_API_KEY
+        )
+        player_o = Agent(
+            name="Player O",
+            instructions="You are Player O. Choose your move as 'row col' (e.g., '1 2').",
+            api_key=OPENAI_API_KEY
+        )
+        print("=== Tic Tac Toe Game (AI vs AI) ===")
+        board.display()
+        for _ in range(9):
+            current_agent = player_x if board.current_player == "X" else player_o
+            prompt = f"Current board:\n{board.board}\nValid moves: {board.valid_moves()}\nYour move (row col):"
+            move_str = current_agent.start(prompt)
+            try:
+                row, col = map(int, move_str.strip().split())
+            except Exception:
+                print(f"Invalid move from agent: {move_str}. Skipping turn.")
+                continue
+            if (row, col) not in board.valid_moves():
+                print(f"Illegal move: {row} {col}. Skipping turn.")
+                continue
+            board.make_move(row, col)
+            board.display()
+            winner = board.check_winner()
+            if winner:
+                print(f"Winner: {winner}")
+                break
+        if not winner:
+            print("Game ended in a draw.")

examples/python/tools/exa-tool/Research_Knowledge_QA_Agents/Domain_Deep_Research_Agent.py

@@ -0,0 +1,55 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+"""
+Domain Deep Research Agent using PraisonAIAgents
+
+This script performs deep research on a given topic and provides a structured report.
+It is CI-friendly: it uses dummy data if API keys are not set.
+"""
+
+import os
+from praisonaiagents import Agent
+
+# Set up key (robust, CI-safe)
+OPENAI_API_KEY = os.environ.get("OPENAI_API_KEY", "sk-..")
+os.environ["OPENAI_API_KEY"] = OPENAI_API_KEY
+
+def is_valid_key(key, prefix):
+    return key and key != f"{prefix}-.." and key.startswith(prefix)
+
+# Custom Tool: Dummy Deep Research Tool
+class DummyDeepResearchTool:
+    """
+    Custom tool to simulate deep research for CI/public use.
+    """
+    def __init__(self, topic):
+        self.topic = topic
+
+    def research(self):
+        # For demo/CI, just return a dummy report
+        return f"## Research Report on {self.topic}\n\n- Key finding 1 about {self.topic}\n- Key finding 2 about {self.topic}\n- Key finding 3 about {self.topic}\n"
+
+if __name__ == "__main__":
+    # User input (for demo, hardcoded; in real use, use input() or widgets)
+    topic = "Recent advances in quantum computing"
+
+    # Use the custom tool
+    tool = DummyDeepResearchTool(topic)
+    dummy_report = tool.research()
+
+    if not is_valid_key(OPENAI_API_KEY, "sk"):
+        print("API key not set or is a placeholder. Using dummy research report for CI/testing.")
+        print(dummy_report)
+    else:
+        prompt = f"""
+        You are a domain research assistant. Perform deep research on the following topic and provide a structured, well-cited report:
+        TOPIC: {topic}
+        """
+        agent = Agent(
+            name="Domain Deep Research Agent",
+            instructions=prompt,
+            api_key=OPENAI_API_KEY
+        )
+        report = agent.start(prompt)
+        print(report)

examples/python/tools/exa-tool/SocialMedia_Content_Agents/News_And_Podcast_Aggregator_Agent.py

@@ -0,0 +1,169 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+# # News and Podcast Aggregator Agent using PraisonAIAgents
+
+# This notebook demonstrates a News and Podcast Aggregator Agent built with `praisonaiagents`.  
+# It summarizes news articles and generates podcast-style discussion points.  
+# The notebook is CI-friendly: it uses dummy data if API keys are not set, so all tests/checks will pass.
+
+# [![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Dhivya-Bharathy/PraisonAI/blob/main/examples/cookbooks/SocialMedia_Content_Agents/News_And_Podcast_Aggregator_Agent.ipynb)
+# 
+
+# # Dependencies
+
+# In[ ]:
+
+
+get_ipython().system('pip install praisonaiagents pydantic')
+
+
+# # Imports and Setup
+
+# In[3]:
+
+
+import os
+
+# Set up the OpenAI API key for praisonaiagents
+os.environ["OPENAI_API_KEY"] = os.environ.get("OPENAI_API_KEY", "sk-..")
+
+def is_valid_key(key, prefix):
+    return key and key != f"{prefix}-.." and key.startswith(prefix)
+
+OPENAI_API_KEY = os.environ["OPENAI_API_KEY"]
+
+
+# # Tools
+
+# In[4]:
+
+
+from datetime import datetime
+from typing import List
+
+def format_search_results_for_podcast(search_results: List[dict]) -> tuple[str, List[str]]:
+    """
+    Custom tool to format search results for podcast script generation.
+    """
+    created_at = datetime.now().strftime("%B %d, %Y at %I:%M %p")
+    structured_content = []
+    structured_content.append(f"PODCAST CREATION: {created_at}\n")
+    sources = []
+    for idx, search_result in enumerate(search_results):
+        try:
+            if search_result.get("confirmed", False):
+                sources.append(search_result["url"])
+                structured_content.append(
+                    f"""
+                    SOURCE {idx + 1}:
+                    Title: {search_result['title']}
+                    URL: {search_result['url']}
+                    Content: {search_result.get('full_text') or search_result.get('description', '')}
+                    ---END OF SOURCE {idx + 1}---
+                    """.strip()
+                )
+        except Exception as e:
+            print(f"Error processing search result: {e}")
+    content_texts = "\n\n".join(structured_content)
+    return content_texts, sources
+
+
+# # Pydantic Models
+
+# In[5]:
+
+
+from pydantic import BaseModel, Field
+from typing import List, Optional
+
+class Dialog(BaseModel):
+    speaker: str = Field(..., description="The speaker name (SHOULD BE 'ALEX' OR 'MORGAN')")
+    text: str = Field(..., description="The spoken text content for this speaker based on the requested language, default is English")
+
+class Section(BaseModel):
+    type: str = Field(..., description="The section type (intro, headlines, article, outro)")
+    title: Optional[str] = Field(None, description="Optional title for the section (required for article type)")
+    dialog: List[Dialog] = Field(..., description="List of dialog exchanges between speakers")
+
+class PodcastScript(BaseModel):
+    title: str = Field(..., description="The podcast episode title with date")
+    sections: List[Section] = Field(..., description="List of podcast sections (intro, headlines, articles, outro)")
+
+
+# # Agent Instructions
+
+# In[6]:
+
+
+from textwrap import dedent
+
+PODCAST_AGENT_DESCRIPTION = "You are a helpful assistant that can generate engaging podcast scripts for the given sources."
+PODCAST_AGENT_INSTRUCTIONS = dedent("""
+    You are a helpful assistant that can generate engaging podcast scripts for the given source content and query.
+    For given content, create an engaging podcast script that should be at least 15 minutes worth of content and you are allowed to enhance the script beyond given sources if you know something additional info will be interesting to the discussion or not enough content is available.
+    You use the provided sources to ground your podcast script generation process. Keep it engaging and interesting.
+    IMPORTANT: Generate the entire script in the provided language.
+    CONTENT GUIDELINES:
+    - Provide insightful analysis that helps the audience understand the significance
+    - Include discussions on potential implications and broader context of each story
+    - Explain complex concepts in an accessible but thorough manner
+    - Make connections between current and relevant historical developments when applicable
+    - Provide comparisons and contrasts with similar stories or trends when relevant
+    PERSONALITY NOTES:
+    - Alex is more analytical and fact-focused
+    - Morgan is more focused on human impact, social context, and practical applications
+    - Include natural, conversational banter and smooth transitions between topics
+    - Each article discussion should go beyond the basic summary to provide valuable insights
+    - Maintain a conversational but informed tone that would appeal to a general audience
+    IMPORTANT:
+        - MAKE SURE PODCAST SCRIPTS ARE AT LEAST 15 MINUTES LONG WHICH MEANS YOU NEED TO HAVE DETAILED DISCUSSIONS BUT KEEP IT INTERESTING AND ENGAGING.
+""")
+
+
+# # Dummy Data and Main Logic
+
+# In[7]:
+
+
+from praisonaiagents import Agent
+
+# Dummy search results for CI/public use
+dummy_search_results = [
+    {
+        "confirmed": True,
+        "title": "AI Revolutionizes Healthcare",
+        "url": "https://news.example.com/ai-healthcare",
+        "full_text": "Artificial intelligence is transforming the healthcare industry by..."
+    },
+    {
+        "confirmed": True,
+        "title": "Climate Change and Global Policy",
+        "url": "https://news.example.com/climate-policy",
+        "full_text": "World leaders are meeting to discuss new policies for climate change..."
+    }
+]
+
+query = "Latest technology and world news"
+language_name = "English"
+
+content_texts, sources = format_search_results_for_podcast(dummy_search_results)
+
+if not is_valid_key(OPENAI_API_KEY, "sk"):
+    print("API key not set or is a placeholder. Using dummy podcast script for CI/testing.")
+    print("=== Podcast Script ===")
+    print(f"Podcast Title: Tech & World News Roundup ({datetime.now().strftime('%B %d, %Y')})")
+    for idx, article in enumerate(dummy_search_results):
+        print(f"\nSection {idx+1}: {article['title']}")
+        print(f"Summary: {article['full_text'][:80]}...")
+else:
+    agent = Agent(
+        name="Podcast Script Agent",
+        instructions=PODCAST_AGENT_INSTRUCTIONS,
+        api_key=OPENAI_API_KEY
+    )
+    prompt = f"query: {query}\nlanguage_name: {language_name}\ncontent_texts: {content_texts}\nIMPORTANT: texts should be in {language_name} language."
+    podcast_script = agent.start(prompt)
+    print("=== Podcast Script ===")
+    print(podcast_script)
+

examples/python/tools/exa-tool/grok4_intelligent_agents/ai_competitor_intelligence_agent.py

@@ -0,0 +1,13 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a competitor intelligence AI agent. "
+                 "Help users analyze competitors, market trends, and business intelligence "
+                 "to provide strategic insights and competitive advantages.",
+    llm="xai/grok-4"
+)
+
+response = agent.start(
+    "I need to analyze my main competitor's pricing strategy and market positioning. "
+    "Can you help me gather insights?"
+) 

examples/python/tools/exa-tool/grok4_intelligent_agents/ai_finance_agent.py

@@ -0,0 +1,13 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a finance AI agent. "
+                 "Help users with financial analysis, investment strategies, "
+                 "budget planning, and market trend analysis for informed decision making.",
+    llm="xai/grok-4"
+)
+
+response = agent.start(
+    "I need to analyze my investment portfolio and create a diversification strategy. "
+    "Can you help me optimize my financial planning?"
+) 

examples/python/tools/exa-tool/grok4_intelligent_agents/ai_game_design_agent.py

@@ -0,0 +1,13 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a game design AI agent. "
+                 "Help users with game concept development, mechanics design, "
+                 "and creative storytelling for various gaming platforms and genres.",
+    llm="xai/grok-4"
+)
+
+response = agent.start(
+    "I want to create a mobile puzzle game concept. "
+    "Can you help me design engaging gameplay mechanics and story elements?"
+) 

examples/python/tools/exa-tool/grok4_intelligent_agents/ai_legal_agent.py

@@ -0,0 +1,13 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a legal AI agent. "
+                 "Help users with legal document analysis, contract review, "
+                 "and legal advice while ensuring compliance and risk assessment.",
+    llm="xai/grok-4"
+)
+
+response = agent.start(
+    "I need to review a software licensing agreement. "
+    "Can you help me identify potential risks and key terms?"
+) 

examples/python/tools/exa-tool/grok4_intelligent_agents/ai_recruitment_agent.py

@@ -0,0 +1,13 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a recruitment AI agent. "
+                 "Help users with candidate screening, job posting optimization, "
+                 "and recruitment process automation to find the best talent.",
+    llm="xai/grok-4"
+)
+
+response = agent.start(
+    "I need to create a job posting for a senior software engineer position. "
+    "Can you help me write an attractive and comprehensive job description?"
+) 

examples/python/tools/exa-tool/grok4_intelligent_agents/ai_services_agency.py

@@ -0,0 +1,13 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are an AI services agency agent. "
+                 "Help users with comprehensive business services including marketing, "
+                 "content creation, strategy, and operational optimization using CrewAI framework.",
+    llm="xai/grok-4"
+)
+
+response = agent.start(
+    "I need help with my startup's marketing strategy and content creation. "
+    "Can you provide a comprehensive plan?"
+) 

examples/python/tools/exa-tool/grok4_intelligent_agents/ai_teaching_agent.py

@@ -0,0 +1,13 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are an AI teaching agent. "
+                 "Help users with educational content creation, lesson planning, "
+                 "and personalized learning experiences across various subjects.",
+    llm="xai/grok-4"
+)
+
+response = agent.start(
+    "I need to create a lesson plan for teaching Python programming to beginners. "
+    "Can you help me design an engaging curriculum?"
+) 

examples/python/tools/exa-tool/grok4_intelligent_agents/grok_customer_support_chatbot.py

@@ -0,0 +1,8 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a customer support AI agent for TechGadgets.com, an online electronics store. Answer customer queries helpfully.",
+    llm="xai/grok-4"
+)
+
+response = agent.start("How to return an item?")

examples/python/tools/exa-tool/grok4_intelligent_agents/grok_data_analysis_agent.py

@@ -0,0 +1,8 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a data analysis AI agent. Help users analyze datasets, create visualizations, and extract meaningful insights from data.",
+    llm="xai/grok-4"
+)
+
+response = agent.start("I have sales data for the last quarter. Can you help me identify trends and patterns?") 

examples/python/tools/exa-tool/grok4_intelligent_agents/grok_deep_research_agent.py

@@ -0,0 +1,8 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a deep research AI agent. Conduct comprehensive research, analyze complex topics, and provide detailed insights on various subjects.",
+    llm="xai/grok-4"
+)
+
+response = agent.start("I need to research the impact of artificial intelligence on job markets. Can you provide a comprehensive analysis?") 

examples/python/tools/exa-tool/grok4_intelligent_agents/grok_health_fitness_agent.py

@@ -0,0 +1,8 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a health and fitness AI agent. Help users with workout plans, nutrition advice, wellness tips, and health monitoring guidance.",
+    llm="xai/grok-4"
+)
+
+response = agent.start("I want to lose 20 pounds and build muscle. What's the best workout and nutrition plan for me?") 

examples/python/tools/exa-tool/grok4_intelligent_agents/grok_investment_advisor_agent.py

@@ -0,0 +1,8 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are an investment advisor AI agent. Help users with investment strategies, portfolio analysis, risk assessment, and market insights.",
+    llm="xai/grok-4"
+)
+
+response = agent.start("I have $50,000 to invest. What would be a good diversified portfolio for someone in their 30s?") 

examples/python/tools/exa-tool/grok4_intelligent_agents/grok_journalist_agent.py

@@ -0,0 +1,8 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a journalist AI agent. Help with news writing, article creation, fact-checking, and content generation for various media platforms.",
+    llm="xai/grok-4"
+)
+
+response = agent.start("I need to write an article about the latest developments in renewable energy. Can you help me structure it?") 

examples/python/tools/exa-tool/grok4_intelligent_agents/grok_lead_generation_assistant.py

@@ -0,0 +1,8 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a lead generation AI agent for RealEstatePro.com. Help identify and qualify potential real estate leads.",
+    llm="xai/grok-4"
+)
+
+response = agent.start("I'm looking to buy a house in the suburbs with 3 bedrooms and a garden.")

examples/python/tools/exa-tool/grok4_intelligent_agents/grok_medical_imaging_agent.py

@@ -0,0 +1,8 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a medical imaging AI agent. Help analyze medical images, provide preliminary assessments, and assist healthcare professionals with diagnostic support.",
+    llm="xai/grok-4"
+)
+
+response = agent.start("I have an X-ray image that needs analysis. Can you help identify any abnormalities?") 

examples/python/tools/exa-tool/grok4_intelligent_agents/grok_meeting_productivity_agent.py

@@ -0,0 +1,8 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a meeting productivity AI agent. Help optimize meeting efficiency and follow-up actions.",
+    llm="xai/grok-4"
+)
+
+response = agent.start("I have a team meeting tomorrow. How can I make it more productive?")

examples/python/tools/exa-tool/grok4_intelligent_agents/grok_mental_wellbeing_advisor.py

@@ -0,0 +1,8 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a mental wellbeing AI advisor. Provide supportive guidance and wellness tips.",
+    llm="xai/grok-4"
+)
+
+response = agent.start("I've been feeling stressed at work lately. Any tips for managing stress?")

examples/python/tools/exa-tool/grok4_intelligent_agents/grok_multimodal_reasoning_agent.py

@@ -0,0 +1,8 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a multimodal reasoning AI agent. Analyze images and text to provide comprehensive insights.",
+    llm="xai/grok-4"
+)
+
+response = agent.start("Can you help me analyze a chart showing sales data for Q1 2024?")

examples/python/tools/exa-tool/grok4_intelligent_agents/grok_music_generator_agent.py

@@ -0,0 +1,8 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a music generation AI agent. Help users create melodies, lyrics, and musical compositions based on their preferences and requirements.",
+    llm="xai/grok-4"
+)
+
+response = agent.start("I need a catchy jingle for my coffee shop. Can you help me create one?") 

examples/python/tools/exa-tool/grok4_intelligent_agents/grok_personal_finance_agent.py

@@ -0,0 +1,8 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a personal finance AI agent. Help users with budgeting, saving strategies, debt management, and financial planning advice.",
+    llm="xai/grok-4"
+)
+
+response = agent.start("I want to save $10,000 in the next year. What's the best strategy for me?") 

examples/python/tools/exa-tool/grok4_intelligent_agents/grok_startup_trend_analysis_agent.py

@@ -0,0 +1,8 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a startup trend analysis AI agent. Help entrepreneurs identify market opportunities, analyze industry trends, and evaluate business ideas.",
+    llm="xai/grok-4"
+)
+
+response = agent.start("I'm thinking of starting a tech startup. What are the current trending opportunities in the market?") 

examples/python/tools/exa-tool/grok4_intelligent_agents/grok_travel_planning_agent.py

@@ -0,0 +1,8 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a travel planning AI agent. Help users plan trips, find destinations, and create itineraries with budget considerations.",
+    llm="xai/grok-4"
+)
+
+response = agent.start("I want to plan a 7-day trip to Europe with a budget of $3000. What are my best options?") 

examples/python/tools/exa-tool/grok4_intelligent_agents/multi_mcp_agent.py

@@ -0,0 +1,13 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a multi MCP AI agent. "
+                 "Help users integrate and coordinate multiple Model Context Protocol agents "
+                 "for complex workflows and cross-platform automation.",
+    llm="xai/grok-4"
+)
+
+response = agent.start(
+    "I need to coordinate multiple tools and services for my project. "
+    "Can you help me set up an integrated workflow using MCP agents?"
+) 

examples/python/tools/exa-tool/grok4_intelligent_agents/multimodal_coding_agent.py

@@ -0,0 +1,13 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a multimodal coding AI agent. "
+                 "Help users with code generation, review, and debugging "
+                 "by analyzing both text and visual inputs like screenshots and diagrams.",
+    llm="xai/grok-4"
+)
+
+response = agent.start(
+    "I have a screenshot of a UI design and need to generate the corresponding HTML/CSS code. "
+    "Can you help me create the frontend code?"
+) 

examples/python/tools/exa-tool/grok4_intelligent_agents/multimodal_design_agent.py

@@ -0,0 +1,13 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a multimodal design AI agent. "
+                 "Help users with graphic design, UI/UX design, and visual content creation "
+                 "by analyzing text descriptions and visual references.",
+    llm="xai/grok-4"
+)
+
+response = agent.start(
+    "I need to create a logo for my tech startup. "
+    "Can you help me design a modern and professional logo concept?"
+) 

src/praisonai-agents/CLAUDE.md

@@ -139,10 +139,32 @@ task = Task(
 #### Task-Level Guardrails
 ```python
 from typing import Tuple, Any
+from praisonaiagents import GuardrailResult
 
-# Function-based guardrail
-def validate_output(task_output: TaskOutput) -> Tuple[bool, Any]:
-    """Custom validation function."""
+# Function-based guardrail (Option 1: Using GuardrailResult)
+def validate_output(task_output: TaskOutput) -> GuardrailResult:
+    """Custom validation function returning GuardrailResult."""
+    if "error" in task_output.raw.lower():
+        return GuardrailResult(
+            success=False,
+            result=None,
+            error="Output contains errors"
+        )
+    if len(task_output.raw) < 10:
+        return GuardrailResult(
+            success=False,
+            result=None,
+            error="Output is too short"
+        )
+    return GuardrailResult(
+        success=True,
+        result=task_output,
+        error=""
+    )
+
+# Function-based guardrail (Option 2: Using Tuple[bool, Any])
+def validate_output_tuple(task_output: TaskOutput) -> Tuple[bool, Any]:
+    """Custom validation function returning tuple."""
     if "error" in task_output.raw.lower():
         return False, "Output contains errors"
     if len(task_output.raw) < 10:
@@ -170,7 +192,27 @@ task = Task(
 #### Agent-Level Guardrails
 ```python
 # Agent guardrails apply to ALL outputs from that agent
-def validate_professional_tone(task_output: TaskOutput) -> Tuple[bool, Any]:
+
+# Option 1: Using GuardrailResult
+def validate_professional_tone(task_output: TaskOutput) -> GuardrailResult:
+    """Ensure professional tone in all agent responses."""
+    content = task_output.raw.lower()
+    casual_words = ['yo', 'dude', 'awesome', 'cool']
+    for word in casual_words:
+        if word in content:
+            return GuardrailResult(
+                success=False,
+                result=None,
+                error=f"Unprofessional language detected: {word}"
+            )
+    return GuardrailResult(
+        success=True,
+        result=task_output,
+        error=""
+    )
+
+# Option 2: Using Tuple[bool, Any]
+def validate_professional_tone_tuple(task_output: TaskOutput) -> Tuple[bool, Any]:
     """Ensure professional tone in all agent responses."""
     content = task_output.raw.lower()
     casual_words = ['yo', 'dude', 'awesome', 'cool']

src/praisonai-agents/autoagents-tavily.py

@@ -0,0 +1,62 @@
+from praisonaiagents import AutoAgents
+from langchain_community.utilities.tavily_search import TavilySearchAPIWrapper
+
+def tavily(query: str):
+    api_wrapper = TavilySearchAPIWrapper()
+    results = api_wrapper.results(query=query, max_results=5)
+    return results
+    
+# Create AutoAgents instance
+agents = AutoAgents(
+    instructions="Search for information about AI Agents",
+    tools=[tavily],
+    process="sequential",
+    verbose=True,
+    max_agents=3  # Maximum number of agents to create
+)
+
+# Start the agents
+result = agents.start()
+print(result)
+
+##or
+
+from praisonaiagents import AutoAgents
+from praisonaiagents.tools import (
+    evaluate, solve_equation, convert_units,
+    calculate_statistics, calculate_financial
+)
+
+
+def get_stock_price(company_name: str) -> str:
+    """
+    Get the stock price of a company
+    
+    Args:
+        company_name (str): The name of the company
+        
+    Returns:
+        str: The stock price of the company
+    """
+
+    if company_name.lower() == "apple" or company_name.lower() == "aapl":
+        return f"The stock price of {company_name} is 100"
+    elif company_name.lower() == "google" or company_name.lower() == "googl":
+        return f"The stock price of {company_name} is 200"
+    else:
+        return f"The stock price of {company_name} is 50"
+
+# Create AutoAgents instance  
+agents = AutoAgents(
+    instructions="Get the stock price of google and compare it to the stock price of apple",
+    tools=[evaluate, get_stock_price],
+    process="sequential",
+    llm="gemini/gemini-2.5-flash-lite-preview-06-17",
+    self_reflect=False,
+    verbose=False,
+    max_agents=3  # Maximum number of agents to create
+)
+
+# Start the agents
+result = agents.start()
+print(result)

src/praisonai-agents/basic-agents-tools.py

@@ -0,0 +1,12 @@
+from praisonaiagents import Agent
+
+def get_weather(city: str) -> str:
+    return f"The weather in {city} is sunny"
+
+agent = Agent(
+    instructions="You are a helpful assistant",
+    llm="gpt-4o-mini",
+    tools=[get_weather]
+)
+
+agent.start("What is the weather in Tokyo?")

src/praisonai-agents/gemini-agents-tools.py

@@ -0,0 +1,12 @@
+from praisonaiagents import Agent
+
+def get_weather(city: str) -> str:
+    return f"The weather in {city} is sunny"
+
+agent = Agent(
+    instructions="You are a helpful assistant",
+    llm="gemini/gemini-1.5-flash-latest",
+    tools=[get_weather]
+)
+
+agent.start("What is the weather in Tokyo?")

src/praisonai-agents/gemini-sequential.py

@@ -0,0 +1,30 @@
+from praisonaiagents import Agent
+
+def get_stock_price(company_name: str) -> str:
+    """
+    Get the stock price of a company
+    
+    Args:
+        company_name (str): The name of the company
+        
+    Returns:
+        str: The stock price of the company
+    """
+    return f"The stock price of {company_name} is 100"
+
+def multiply(a: int, b: int) -> int:
+    """
+    Multiply two numbers
+    """
+    return a * b
+
+
+
+agent = Agent(
+    instructions="You are a helpful assistant. You can use the tools provided to you to help the user.",
+    llm="gemini/gemini-2.5-pro",
+    tools=[get_stock_price, multiply]
+)
+
+result = agent.start("what is the stock price of Google? multiply the Google stock price with 2")
+print(result)

src/praisonai-agents/gemini-structured.py

@@ -0,0 +1,25 @@
+from pydantic import BaseModel
+from praisonaiagents import Agent, Task, Agents
+
+class Recipe(BaseModel):
+    recipe_name: str
+    ingredients: list[str]
+
+agent = Agent(
+    name="Chef",
+    role="Recipe Creator",
+    llm="gemini/gemini-2.5-flash"
+)
+
+task = Task(
+    description="Create a cookie recipe",
+    agent=agent,
+    output_pydantic=Recipe  # Will use Gemini's native structured output!
+)
+
+agents = Agents(
+    agents=[agent],
+    tasks=[task]
+)
+
+agents.start()

src/praisonai-agents/gemini_self_reflection.py

@@ -0,0 +1,32 @@
+#!/usr/bin/env python3
+"""Test script to verify the Gemini JSON parsing fix."""
+
+from praisonaiagents import Agent
+
+# Test with minimal configuration to isolate the issue
+llm_config = {
+    "model": "gemini/gemini-1.5-flash-latest",
+    "temperature": 0.7,
+    "max_tokens": 500,
+}
+
+# Create agent with self-reflection enabled
+agent = Agent(
+    instructions="You are a helpful assistant. Be concise and clear.",
+    llm=llm_config,
+    verbose=True,
+    self_reflect=True,
+    max_reflect=2,
+    min_reflect=1
+)
+
+# Test with a simple prompt
+print("Testing Gemini with self-reflection...")
+try:
+    response = agent.start("What is 2+2? Explain briefly.")
+    print(f"\nFinal response: {response}")
+    print("\nTest completed successfully!")
+except Exception as e:
+    print(f"\nError occurred: {e}")
+    import traceback
+    traceback.print_exc()

src/praisonai-agents/handoff-test.py

@@ -0,0 +1,179 @@
+from praisonaiagents import Agent
+from praisonaiagents.agent.handoff import handoff, handoff_filters
+from pydantic import BaseModel
+from typing import Dict, Any
+import logging
+
+# Mock data for testing
+MOCK_ORDERS = {
+    "12345": {
+        "id": "12345",
+        "status": "shipped",
+        "items": ["Widget A", "Widget B"],
+        "total": 99.99,
+        "tracking_number": "TRK123456789",
+        "shipping_address": "123 Main St, City, ST 12345"
+    },
+    "67890": {
+        "id": "67890", 
+        "status": "processing",
+        "items": ["Gadget X"],
+        "total": 149.99,
+        "tracking_number": None,
+        "shipping_address": "456 Oak Ave, Town, ST 67890"
+    }
+}
+
+MOCK_SHIPMENTS = {
+    "TRK123456789": {
+        "tracking_number": "TRK123456789",
+        "status": "in_transit",
+        "location": "Distribution Center - Chicago",
+        "estimated_delivery": "2024-01-15",
+        "updates": [
+            {"date": "2024-01-10", "status": "picked_up", "location": "Warehouse"},
+            {"date": "2024-01-12", "status": "in_transit", "location": "Chicago"}
+        ]
+    }
+}
+
+MOCK_TICKETS = []
+
+# Mock tool functions
+def check_order_status(order_id: str) -> Dict[str, Any]:
+    """Check the status of an order"""
+    if order_id in MOCK_ORDERS:
+        return {"success": True, "order": MOCK_ORDERS[order_id]}
+    return {"success": False, "error": f"Order {order_id} not found"}
+
+def track_shipment(tracking_number: str) -> Dict[str, Any]:
+    """Track a shipment by tracking number"""
+    if tracking_number in MOCK_SHIPMENTS:
+        return {"success": True, "shipment": MOCK_SHIPMENTS[tracking_number]}
+    return {"success": False, "error": f"Tracking number {tracking_number} not found"}
+
+def process_refund(order_id: str, reason: str = "customer_request") -> Dict[str, Any]:
+    """Process a refund for an order"""
+    if order_id in MOCK_ORDERS:
+        order = MOCK_ORDERS[order_id]
+        return {
+            "success": True,
+            "refund_id": f"REF{order_id}",
+            "amount": order["total"],
+            "status": "processing",
+            "estimated_days": 3-5
+        }
+    return {"success": False, "error": f"Order {order_id} not found"}
+
+def check_refund_policy(item_type: str = "general") -> Dict[str, Any]:
+    """Check refund policy for different item types"""
+    policies = {
+        "general": {"days": 30, "condition": "unopened", "shipping": "customer_pays"},
+        "electronics": {"days": 15, "condition": "original_packaging", "shipping": "free"},
+        "clothing": {"days": 60, "condition": "tags_attached", "shipping": "customer_pays"}
+    }
+    return {"success": True, "policy": policies.get(item_type, policies["general"])}
+
+def diagnose_issue(description: str) -> Dict[str, Any]:
+    """Diagnose a technical issue"""
+    common_solutions = {
+        "login": "Clear cookies and cache, try password reset",
+        "payment": "Check card details, try different payment method",
+        "loading": "Check internet connection, try different browser",
+        "mobile": "Update app, restart device, check storage space"
+    }
+    
+    # Simple keyword matching for demo
+    for issue_type, solution in common_solutions.items():
+        if issue_type in description.lower():
+            return {"success": True, "diagnosis": solution, "severity": "low"}
+    
+    return {"success": True, "diagnosis": "Please provide more details", "severity": "medium"}
+
+def create_ticket(issue_description: str, priority: str = "medium") -> Dict[str, Any]:
+    """Create a support ticket"""
+    ticket_id = f"TICK{len(MOCK_TICKETS) + 1001}"
+    ticket = {
+        "id": ticket_id,
+        "description": issue_description,
+        "priority": priority,
+        "status": "open",
+        "created_at": "2024-01-13T10:00:00Z"
+    }
+    MOCK_TICKETS.append(ticket)
+    return {"success": True, "ticket": ticket}
+
+def log_escalation(source_agent: str, escalation_data: Dict[str, Any]) -> None:
+    """Log escalation for audit purposes"""
+    logging.info(f"Escalation from {source_agent}: {escalation_data}")
+
+# Escalation with structured input
+class EscalationRequest(BaseModel):
+    issue_type: str
+    severity: str
+    description: str
+
+# Specialist agents
+order_agent = Agent(
+    name="Order Management",
+    instructions="You help with order status and tracking.",
+    tools=[check_order_status, track_shipment]
+)
+
+refund_agent = Agent(
+    name="Refund Specialist", 
+    instructions="You process refunds and handle return requests.",
+    tools=[process_refund, check_refund_policy]
+)
+
+technical_agent = Agent(
+    name="Technical Support",
+    instructions="You solve technical issues and provide guidance.",
+    tools=[diagnose_issue, create_ticket]
+)
+
+escalation_agent = Agent(
+    name="Senior Manager",
+    instructions="You handle escalated issues requiring management attention."
+)
+
+# Main triage agent
+triage_agent = Agent(
+    name="Customer Service",
+    instructions="""You are the first point of contact. Route customers to the right specialist:
+    - Order issues → Order Management
+    - Refunds → Refund Specialist  
+    - Technical problems → Technical Support
+    - Complex issues → Escalate to management
+    """,
+    handoffs=[
+        order_agent,
+        refund_agent,
+        technical_agent,
+        handoff(
+            escalation_agent,
+            tool_name_override="escalate_to_management",
+            input_type=EscalationRequest,
+            on_handoff=lambda src, data: log_escalation(src.name, data)
+        )
+    ]
+)
+
+# Start the service
+if __name__ == "__main__":
+    print("Customer Service Handoff System Demo")
+    print("=" * 40)
+    
+    # Test different scenarios
+    test_queries = [
+        "I need a refund for order #12345",
+        "What's the status of order #67890?",
+        "I'm having trouble logging into my account",
+        "This is urgent - I need to speak to a manager about a serious billing issue"
+    ]
+    
+    for query in test_queries:
+        print(f"\nCustomer: {query}")
+        response = triage_agent.chat(query)
+        print(f"Response: {response}")
+        print("-" * 40)

src/praisonai-agents/multi-agents-api.py

@@ -0,0 +1,6 @@
+from praisonaiagents import Agent, Agents, Tools
+
+research_agent = Agent(name="Research", instructions="You are a research agent to search internet about AI 2024", tools=[Tools.internet_search])
+summarise_agent = Agent(name="Summarise", instructions="You are a summarize agent to summarise in points")
+agents = Agents(agents=[research_agent, summarise_agent])
+agents.launch(path="/agents", port=3030)

src/praisonai-agents/ollama-agents.py

@@ -0,0 +1,8 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a helpful assistant",
+    llm="ollama/qwen3"
+)
+
+agent.start("Why sky is Blue?")

src/praisonai-agents/ollama-sequential.py

@@ -0,0 +1,30 @@
+from praisonaiagents import Agent
+
+def get_stock_price(company_name: str) -> str:
+    """
+    Get the stock price of a company
+    
+    Args:
+        company_name (str): The name of the company
+        
+    Returns:
+        str: The stock price of the company
+    """
+    return f"The stock price of {company_name} is 100"
+
+def multiply(a: int, b: int) -> int:
+    """
+    Multiply two numbers
+    """
+    return a * b
+
+
+
+agent = Agent(
+    instructions="You are a helpful assistant. You can use the tools provided to you to help the user.",
+    llm="ollama/llama3.2",
+    tools=[get_stock_price, multiply]
+)
+
+result = agent.start("what is the stock price of Google? multiply the Google stock price with 2")
+print(result)

src/praisonai-agents/openai-sequential.py

@@ -0,0 +1,30 @@
+from praisonaiagents import Agent
+
+def get_stock_price(company_name: str) -> str:
+    """
+    Get the stock price of a company
+    
+    Args:
+        company_name (str): The name of the company
+        
+    Returns:
+        str: The stock price of the company
+    """
+    return f"The stock price of {company_name} is 100"
+
+def multiply(a: int, b: int) -> int:
+    """
+    Multiply two numbers
+    """
+    return a * b
+
+
+
+agent = Agent(
+    instructions="You are a helpful assistant. You can use the tools provided to you to help the user.",
+    llm="gpt-4o",
+    tools=[get_stock_price, multiply]
+)
+
+result = agent.start("what is the stock price of Google? multiply the Google stock price with 2")
+print(result)

src/praisonai-agents/praisonaiagents/__init__.py

@@ -2,6 +2,30 @@
 Praison AI Agents - A package for hierarchical AI agent task execution
 """
 
+# Configure logging before any other imports
+import os
+import logging
+from rich.logging import RichHandler
+
+# Get log level from environment variable
+LOGLEVEL = os.environ.get('LOGLEVEL', 'INFO').upper()
+
+# Configure root logger
+logging.basicConfig(
+    level=getattr(logging, LOGLEVEL, logging.INFO),
+    format="%(asctime)s %(filename)s:%(lineno)d %(levelname)s %(message)s",
+    datefmt="[%X]",
+    handlers=[RichHandler(rich_tracebacks=True)]
+)
+
+# Suppress specific noisy loggers
+logging.getLogger("litellm").setLevel(logging.WARNING)
+logging.getLogger("litellm.utils").setLevel(logging.WARNING)
+logging.getLogger("markdown_it").setLevel(logging.WARNING)
+logging.getLogger("rich.markdown").setLevel(logging.WARNING)
+logging.getLogger("httpx").setLevel(logging.WARNING)
+logging.getLogger("httpcore").setLevel(logging.WARNING)
+
 from .agent.agent import Agent
 from .agent.image_agent import ImageAgent
 from .agents.agents import PraisonAIAgents

src/praisonai-agents/praisonaiagents/agent/__init__.py

@@ -2,5 +2,6 @@
 from .agent import Agent
 from .image_agent import ImageAgent
 from .handoff import Handoff, handoff, handoff_filters, RECOMMENDED_PROMPT_PREFIX, prompt_with_handoff_instructions
+from .router_agent import RouterAgent
 
-__all__ = ['Agent', 'ImageAgent', 'Handoff', 'handoff', 'handoff_filters', 'RECOMMENDED_PROMPT_PREFIX', 'prompt_with_handoff_instructions']
+__all__ = ['Agent', 'ImageAgent', 'Handoff', 'handoff', 'handoff_filters', 'RECOMMENDED_PROMPT_PREFIX', 'prompt_with_handoff_instructions', 'RouterAgent']

src/praisonai-agents/praisonaiagents/agent/router_agent.py

@@ -0,0 +1,334 @@
+"""
+Router Agent that can use different LLM models based on task requirements.
+
+This module extends the base Agent class to support multiple models and intelligent
+model selection based on task characteristics.
+"""
+
+import os
+import logging
+from typing import Dict, List, Optional, Any, Union
+from .agent import Agent
+from ..llm.model_router import ModelRouter
+from ..llm import LLM
+
+logger = logging.getLogger(__name__)
+
+
+class RouterAgent(Agent):
+    """
+    An enhanced agent that can dynamically select and use different LLM models
+    based on task requirements, optimizing for cost and performance.
+    """
+    
+    def __init__(
+        self,
+        models: Optional[Union[List[str], Dict[str, Any]]] = None,
+        model_router: Optional[ModelRouter] = None,
+        routing_strategy: str = "auto",  # "auto", "manual", "cost-optimized", "performance-optimized"
+        primary_model: Optional[str] = None,
+        fallback_model: Optional[str] = None,
+        **kwargs
+    ):
+        """
+        Initialize a RouterAgent.
+        
+        Args:
+            models: List of model names or dict mapping model names to configurations
+            model_router: Custom ModelRouter instance for model selection
+            routing_strategy: Strategy for model selection
+            primary_model: Primary model to use (overrides routing for simple tasks)
+            fallback_model: Fallback model if selected model fails
+            **kwargs: Additional arguments passed to parent Agent class
+        """
+        # Initialize model router
+        self.model_router = model_router or ModelRouter()
+        self.routing_strategy = routing_strategy
+        self.fallback_model = fallback_model or os.getenv('OPENAI_MODEL_NAME', 'gpt-4o-mini')
+        
+        # Process models configuration
+        self.available_models = self._process_models_config(models)
+        
+        # Set primary model for parent class initialization
+        if primary_model:
+            kwargs['llm'] = primary_model
+        elif self.available_models:
+            # Use the most cost-effective model as default
+            cheapest_model = min(
+                self.available_models.keys(),
+                key=lambda m: self.model_router.get_model_info(m).cost_per_1k_tokens 
+                if self.model_router.get_model_info(m) else float('inf')
+            )
+            kwargs['llm'] = cheapest_model
+        
+        # Store the original llm parameter for later use
+        self._llm_config = kwargs.get('llm')
+        
+        # Store api_key and base_url for LLM initialization
+        self._base_url = kwargs.get('base_url')
+        self._api_key = kwargs.get('api_key')
+        
+        # Initialize parent Agent class
+        super().__init__(**kwargs)
+        
+        # Initialize LLM instances for each model
+        self._llm_instances: Dict[str, LLM] = {}
+        self._initialize_llm_instances()
+        
+        # Track usage statistics
+        self.model_usage_stats = {model: {'calls': 0, 'tokens': 0, 'cost': 0.0} 
+                                  for model in self.available_models}
+    
+    def _process_models_config(self, models: Optional[Union[List[str], Dict[str, Any]]]) -> Dict[str, Any]:
+        """Process the models configuration into a standardized format."""
+        if not models:
+            # Use default models from router
+            return {m.name: {} for m in self.model_router.models}
+        
+        if isinstance(models, list):
+            # Simple list of model names
+            return {model: {} for model in models}
+        
+        # Already a dict with model configurations
+        return models
+    
+    def _initialize_llm_instances(self):
+        """Initialize LLM instances for each available model."""
+        base_url = self._base_url
+        api_key = self._api_key
+        
+        for model_name, config in self.available_models.items():
+            try:
+                # Merge base configuration with model-specific config
+                llm_config = {
+                    'model': model_name,
+                    'base_url': config.get('base_url', base_url),
+                    'api_key': config.get('api_key', api_key),
+                    'verbose': self.verbose,
+                    'markdown': self.markdown,
+                    'stream': self.stream
+                }
+                
+                # Add any model-specific parameters
+                llm_config.update(config)
+                
+                # Create LLM instance
+                self._llm_instances[model_name] = LLM(**llm_config)
+                logger.debug(f"Initialized LLM instance for model: {model_name}")
+                
+            except Exception as e:
+                logger.warning(f"Failed to initialize LLM for model {model_name}: {e}")
+    
+    def _select_model_for_task(
+        self,
+        task_description: str,
+        tools: Optional[List[Any]] = None,
+        context_size: Optional[int] = None
+    ) -> str:
+        """
+        Select the most appropriate model for a given task.
+        
+        Args:
+            task_description: Description of the task
+            tools: Tools required for the task
+            context_size: Estimated context size
+            
+        Returns:
+            Selected model name
+        """
+        if self.routing_strategy == "manual":
+            # Use the configured primary model from llm_model property
+            llm_model = self.llm_model
+            if hasattr(llm_model, 'model'):
+                # If it's an LLM instance, get the model name
+                return llm_model.model
+            elif isinstance(llm_model, str):
+                # If it's a string, use it directly
+                return llm_model
+            # Fallback if no model is configured
+            return self.fallback_model
+        
+        # Determine required capabilities
+        required_capabilities = []
+        if tools:
+            required_capabilities.append("function-calling")
+        
+        # Determine budget consciousness based on strategy
+        budget_conscious = self.routing_strategy in ["auto", "cost-optimized"]
+        
+        # Get tool names for analysis
+        tool_names = []
+        if tools:
+            tool_names = [t.__name__ if hasattr(t, '__name__') else str(t) for t in tools]
+        
+        # Use router to select model
+        selected_model = self.model_router.select_model(
+            task_description=task_description,
+            required_capabilities=required_capabilities,
+            tools_required=tool_names,
+            context_size=context_size,
+            budget_conscious=budget_conscious
+        )
+        
+        # Ensure selected model is available
+        if selected_model not in self._llm_instances:
+            logger.warning(f"Selected model {selected_model} not available, using fallback")
+            return self.fallback_model
+        
+        return selected_model
+    
+    def _execute_with_model(
+        self,
+        model_name: str,
+        prompt: str,
+        context: Optional[str] = None,
+        tools: Optional[List[Any]] = None,
+        **kwargs
+    ) -> str:
+        """
+        Execute a task with a specific model.
+        
+        Args:
+            model_name: Name of the model to use
+            prompt: The prompt to send to the model
+            context: Additional context
+            tools: Tools to make available
+            **kwargs: Additional arguments for the LLM
+            
+        Returns:
+            Model response
+        """
+        llm_instance = self._llm_instances.get(model_name)
+        if not llm_instance:
+            logger.error(f"Model {model_name} not initialized, using fallback")
+            llm_instance = self._llm_instances.get(self.fallback_model)
+            model_name = self.fallback_model
+        
+        if not llm_instance:
+            raise ValueError("No LLM instance available for execution")
+        
+        # Prepare the full prompt
+        full_prompt = prompt
+        if context:
+            full_prompt = f"{context}\n\n{prompt}"
+        
+        try:
+            # Execute with the selected model
+            response = llm_instance.get_response(
+                prompt=full_prompt,
+                system_prompt=self._build_system_prompt(),
+                tools=tools,
+                verbose=self.verbose,
+                markdown=self.markdown,
+                stream=self.stream,
+                agent_name=self.name,
+                agent_role=self.role,
+                agent_tools=[t.__name__ if hasattr(t, '__name__') else str(t) for t in (tools or [])],
+                execute_tool_fn=self.execute_tool if tools else None,
+                **kwargs
+            )
+            
+            # Update usage statistics
+            self.model_usage_stats[model_name]['calls'] += 1
+            
+            # TODO: Implement token tracking when LLM.get_response() is updated to return token usage
+            # The LLM response currently returns only text, but litellm provides usage info in:
+            # response.get("usage") with prompt_tokens, completion_tokens, and total_tokens
+            # This would require modifying the LLM class to return both text and metadata
+            
+            return response
+            
+        except Exception as e:
+            logger.error(f"Error executing with model {model_name}: {e}")
+            
+            # Try fallback model if different
+            if model_name != self.fallback_model and self.fallback_model in self._llm_instances:
+                logger.info(f"Attempting with fallback model: {self.fallback_model}")
+                return self._execute_with_model(
+                    self.fallback_model, prompt, context, tools, **kwargs
+                )
+            
+            raise
+    
+    def execute(
+        self,
+        task_description: str,
+        context: Optional[str] = None,
+        tools: Optional[List[Any]] = None,
+        **kwargs
+    ) -> str:
+        """
+        Execute a task with automatic model selection.
+        
+        This method overrides the parent Agent's execute method to add
+        intelligent model selection.
+        
+        Args:
+            task_description: Description of the task to execute
+            context: Optional context for the task
+            tools: Optional tools to use
+            **kwargs: Additional arguments
+            
+        Returns:
+            Task execution result
+        """
+        # Estimate context size in tokens (rough estimate: ~4 chars per token)
+        # This is a simplified heuristic; actual tokenization varies by model
+        text_length = len(task_description) + (len(context) if context else 0)
+        context_size = text_length // 4  # Approximate token count
+        
+        # Select the best model for this task
+        selected_model = self._select_model_for_task(
+            task_description=task_description,
+            tools=tools,
+            context_size=context_size
+        )
+        
+        logger.info(f"RouterAgent '{self.name}' selected model: {selected_model} for task")
+        
+        # Execute with the selected model
+        return self._execute_with_model(
+            model_name=selected_model,
+            prompt=task_description,
+            context=context,
+            tools=tools,
+            **kwargs
+        )
+    
+    def get_usage_report(self) -> Dict[str, Any]:
+        """
+        Get a report of model usage statistics.
+        
+        Returns:
+            Dictionary containing usage statistics and cost estimates
+        """
+        total_cost = 0.0
+        report = {
+            'agent_name': self.name,
+            'routing_strategy': self.routing_strategy,
+            'model_usage': {}
+        }
+        
+        for model, stats in self.model_usage_stats.items():
+            model_info = self.model_router.get_model_info(model)
+            if model_info and stats['tokens'] > 0:
+                cost = self.model_router.estimate_cost(model, stats['tokens'])
+                stats['cost'] = cost
+                total_cost += cost
+            
+            report['model_usage'][model] = stats
+        
+        report['total_cost_estimate'] = total_cost
+        report['total_calls'] = sum(s['calls'] for s in self.model_usage_stats.values())
+        
+        return report
+    
+    def _build_system_prompt(self) -> str:
+        """Build system prompt (inherited from parent but can be customized)."""
+        base_prompt = super()._build_system_prompt()
+        
+        # Add multi-model context if needed
+        if self.routing_strategy == "auto":
+            base_prompt += "\n\nNote: You are part of a multi-model system. Focus on your specific task."
+        
+        return base_prompt

src/praisonai-agents/praisonaiagents/agents/agents.py

@@ -7,7 +7,7 @@ from pydantic import BaseModel
 from rich.text import Text
 from rich.panel import Panel
 from rich.console import Console
-from ..main import display_error, TaskOutput, error_logs, client
+from ..main import display_error, TaskOutput, error_logs
 from ..agent.agent import Agent
 from ..task.task import Task
 from ..process.process import Process, LoopItems
@@ -480,24 +480,22 @@ Context:
         )
         
         if self.process == "workflow":
-            # Collect all tasks that should run in parallel
-            parallel_tasks = []
+            tasks_to_run = []
             async for task_id in process.aworkflow():
-                if self.tasks[task_id].async_execution and self.tasks[task_id].is_start:
-                    parallel_tasks.append(task_id)
-                elif parallel_tasks:
-                    # Execute collected parallel tasks
-                    await asyncio.gather(*[self.arun_task(t) for t in parallel_tasks])
-                    parallel_tasks = []
-                    # Run the current non-parallel task
-                    if self.tasks[task_id].async_execution:
-                        await self.arun_task(task_id)
-                    else:
-                        self.run_task(task_id)
-            
-            # Execute any remaining parallel tasks
-            if parallel_tasks:
-                await asyncio.gather(*[self.arun_task(t) for t in parallel_tasks])
+                if self.tasks[task_id].async_execution:
+                    tasks_to_run.append(self.arun_task(task_id))
+                else:
+                    # If we encounter a sync task, we must wait for the previous async tasks to finish.
+                    if tasks_to_run:
+                        await asyncio.gather(*tasks_to_run)
+                        tasks_to_run = []
+                    
+                    # Run sync task in an executor to avoid blocking the event loop
+                    loop = asyncio.get_event_loop()
+                    await loop.run_in_executor(None, self.run_task, task_id)
+
+            if tasks_to_run:
+                await asyncio.gather(*tasks_to_run)
                 
         elif self.process == "sequential":
             async for task_id in process.asequential():

src/praisonai-agents/praisonaiagents/agents/autoagents.py

@@ -12,7 +12,9 @@ from typing import List, Any, Optional, Dict, Tuple
 import logging
 import os
 from pydantic import BaseModel, ConfigDict
-from ..main import display_instruction, display_tool_call, display_interaction, client
+from ..main import display_instruction, display_tool_call, display_interaction
+from ..llm import get_openai_client, LLM, OpenAIClient
+import json
 
 # Define Pydantic models for structured output
 class TaskConfig(BaseModel):
@@ -107,6 +109,8 @@ class AutoAgents(PraisonAIAgents):
         self.max_execution_time = max_execution_time
         self.max_iter = max_iter
         self.reflect_llm = reflect_llm
+        self.base_url = base_url
+        self.api_key = api_key
         
         # Display initial instruction
         if self.verbose:
@@ -132,7 +136,7 @@ class AutoAgents(PraisonAIAgents):
             completion_checker=completion_checker,
             max_retries=max_retries,
             process=process,
-            manager_llm=manager_llm
+            manager_llm=manager_llm or self.llm
         )
 
     def _display_agents_and_tasks(self, agents: List[Agent], tasks: List[Task]):
@@ -210,9 +214,37 @@ Tools: {', '.join(agent_tools)}"""
             
         return assigned_tools
 
+    def _validate_config(self, config: AutoAgentsConfig) -> tuple[bool, str]:
+        """
+        Validate that the configuration has proper TaskConfig objects.
+        
+        Returns:
+            Tuple of (is_valid, error_message)
+        """
+        for agent_idx, agent in enumerate(config.agents):
+            if not hasattr(agent, 'tasks') or not agent.tasks:
+                return False, f"Agent '{agent.name}' has no tasks defined"
+            
+            for task_idx, task in enumerate(agent.tasks):
+                # Check if task is a proper TaskConfig instance
+                if not isinstance(task, TaskConfig):
+                    return False, f"Task at index {task_idx} for agent '{agent.name}' is not a proper TaskConfig object"
+                
+                # Check required fields
+                if not task.name:
+                    return False, f"Task at index {task_idx} for agent '{agent.name}' has no name"
+                if not task.description:
+                    return False, f"Task at index {task_idx} for agent '{agent.name}' has no description"
+                if not task.expected_output:
+                    return False, f"Task at index {task_idx} for agent '{agent.name}' has no expected_output"
+                if task.tools is None:
+                    return False, f"Task at index {task_idx} for agent '{agent.name}' has no tools field"
+        
+        return True, ""
+
     def _generate_config(self) -> AutoAgentsConfig:
-        """Generate the configuration for agents and tasks"""
-        prompt = f"""
+        """Generate the configuration for agents and tasks with retry logic"""
+        base_prompt = f"""
 Generate a configuration for AI agents to accomplish this task: "{self.instructions}"
 
 The configuration should include:
@@ -233,29 +265,161 @@ Requirements:
 4. The process type should match the task requirements
 5. Generate maximum {self.max_agents} agents to handle this task efficiently
 
-Return the configuration in a structured JSON format matching the AutoAgentsConfig schema.
+Return the configuration in a structured JSON format matching this exact schema:
+{{
+  "main_instruction": "Overall goal description",
+  "process_type": "sequential|workflow|hierarchical",
+  "agents": [
+    {{
+      "name": "Agent Name",
+      "role": "Agent Role",
+      "goal": "Agent Goal",
+      "backstory": "Agent Backstory",
+      "tools": ["tool1", "tool2"],
+      "tasks": [
+        {{
+          "name": "Task Name",
+          "description": "Detailed task description",
+          "expected_output": "What the task should produce",
+          "tools": ["tool1", "tool2"]
+        }}
+      ]
+    }}
+  ]
+}}
+
+IMPORTANT: Each task MUST be an object with name, description, expected_output, and tools fields, NOT a simple string.
 """
         
-        try:
-            response = client.beta.chat.completions.parse(
-                model=self.llm,
-                response_format=AutoAgentsConfig,
-                messages=[
-                    {"role": "system", "content": "You are a helpful assistant designed to generate AI agent configurations."},
-                    {"role": "user", "content": prompt}
-                ]
-            )
+        max_retries = 3
+        last_response = None
+        last_error = None
+        
+        for attempt in range(max_retries):
+            # Initialize variables for this attempt
+            use_openai_structured = False
+            client = None
             
-            # Ensure we have exactly max_agents number of agents
-            if len(response.choices[0].message.parsed.agents) > self.max_agents:
-                response.choices[0].message.parsed.agents = response.choices[0].message.parsed.agents[:self.max_agents]
-            elif len(response.choices[0].message.parsed.agents) < self.max_agents:
-                logging.warning(f"Generated {len(response.choices[0].message.parsed.agents)} agents, expected {self.max_agents}")
+            # Prepare prompt for this attempt
+            if attempt > 0 and last_response and last_error:
+                # On retry, include the previous response and error
+                prompt = f"""{base_prompt}
+
+PREVIOUS ATTEMPT FAILED!
+Your previous response was:
+```json
+{last_response}
+```
+
+Error: {last_error}
+
+REMEMBER: Tasks MUST be objects with the following structure:
+{{
+  "name": "Task Name",
+  "description": "Task Description",
+  "expected_output": "Expected Output",
+  "tools": ["tool1", "tool2"]
+}}
+
+DO NOT use strings for tasks. Each task MUST be a complete object with all four fields."""
+            else:
+                prompt = base_prompt
             
-            return response.choices[0].message.parsed
-        except Exception as e:
-            logging.error(f"Error generating configuration: {e}")
-            raise
+            try:
+                # Check if we have OpenAI API and the model supports structured output
+                from ..llm import supports_structured_outputs
+                if self.llm and supports_structured_outputs(self.llm):
+                    client = get_openai_client()
+                    use_openai_structured = True
+            except:
+                # If OpenAI client is not available, we'll use the LLM class
+                pass
+            
+            try:
+                if use_openai_structured and client:
+                    # Use OpenAI's structured output for OpenAI models (backward compatibility)
+                    config = client.parse_structured_output(
+                        messages=[
+                            {"role": "system", "content": "You are a helpful assistant designed to generate AI agent configurations."},
+                            {"role": "user", "content": prompt}
+                        ],
+                        response_format=AutoAgentsConfig,
+                        model=self.llm
+                    )
+                    # Store the response for potential retry
+                    last_response = json.dumps(config.model_dump(), indent=2)
+                else:
+                    # Use LLM class for all other providers (Gemini, Anthropic, etc.)
+                    llm_instance = LLM(
+                        model=self.llm,
+                        base_url=self.base_url,
+                        api_key=self.api_key
+                    )
+                    
+                    response_text = llm_instance.get_response(
+                        prompt=prompt,
+                        system_prompt="You are a helpful assistant designed to generate AI agent configurations.",
+                        output_pydantic=AutoAgentsConfig,
+                        temperature=0.7,
+                        stream=False,
+                        verbose=False
+                    )
+                    
+                    # Store the raw response for potential retry
+                    last_response = response_text
+                    
+                    # Parse the JSON response
+                    try:
+                        # First try to parse as is
+                        config_dict = json.loads(response_text)
+                        config = AutoAgentsConfig(**config_dict)
+                    except json.JSONDecodeError:
+                        # If that fails, try to extract JSON from the response
+                        # Handle cases where the model might wrap JSON in markdown blocks
+                        cleaned_response = response_text.strip()
+                        if cleaned_response.startswith("```json"):
+                            cleaned_response = cleaned_response[7:]
+                        if cleaned_response.startswith("```"):
+                            cleaned_response = cleaned_response[3:]
+                        if cleaned_response.endswith("```"):
+                            cleaned_response = cleaned_response[:-3]
+                        cleaned_response = cleaned_response.strip()
+                        
+                        config_dict = json.loads(cleaned_response)
+                        config = AutoAgentsConfig(**config_dict)
+                
+                # Validate the configuration
+                is_valid, error_msg = self._validate_config(config)
+                if not is_valid:
+                    last_error = error_msg
+                    if attempt < max_retries - 1:
+                        logging.warning(f"Configuration validation failed (attempt {attempt + 1}/{max_retries}): {error_msg}")
+                        continue
+                    else:
+                        raise ValueError(f"Configuration validation failed after {max_retries} attempts: {error_msg}")
+                
+                # Ensure we have exactly max_agents number of agents
+                if len(config.agents) > self.max_agents:
+                    config.agents = config.agents[:self.max_agents]
+                elif len(config.agents) < self.max_agents:
+                    logging.warning(f"Generated {len(config.agents)} agents, expected {self.max_agents}")
+                
+                return config
+                
+            except ValueError as e:
+                # Re-raise validation errors
+                raise
+            except Exception as e:
+                last_error = str(e)
+                if attempt < max_retries - 1:
+                    logging.warning(f"Error generating configuration (attempt {attempt + 1}/{max_retries}): {e}")
+                    continue
+                else:
+                    logging.error(f"Error generating configuration after {max_retries} attempts: {e}")
+                    raise
+        
+        # This should never be reached due to the raise statements above
+        raise RuntimeError(f"Failed to generate valid configuration after {max_retries} attempts")
 
     def _create_agents_and_tasks(self, config: AutoAgentsConfig) -> Tuple[List[Agent], List[Task]]:
         """Create agents and tasks from configuration"""
@@ -296,7 +460,9 @@ Return the configuration in a structured JSON format matching the AutoAgentsConf
                 max_rpm=self.max_rpm,
                 max_execution_time=self.max_execution_time,
                 max_iter=self.max_iter,
-                reflect_llm=self.reflect_llm
+                reflect_llm=self.reflect_llm,
+                base_url=self.base_url,
+                api_key=self.api_key
             )
             agents.append(agent)
             
@@ -334,4 +500,4 @@ Return the configuration in a structured JSON format matching the AutoAgentsConf
         Creates tasks based on the instructions, then starts execution.
         Returns the task status and results dictionary.
         """
-        return super().start() 
+        return super().start()

src/praisonai-agents/praisonaiagents/knowledge/knowledge.py

@@ -67,9 +67,6 @@ class Knowledge:
             
             # Disable OpenAI API request logging
             logging.getLogger('openai').setLevel(logging.WARNING)
-            
-            # Set root logger to warning to catch any uncategorized logs
-            logging.getLogger().setLevel(logging.WARNING)
 
     @cached_property
     def _deps(self):

src/praisonai-agents/praisonaiagents/llm/OLLAMA_HANDLING.md

@@ -0,0 +1,25 @@
+# Ollama Handling in LLM.py
+
+The `ollama_handled` flag is used in `llm.py` (not in `agent.py`) to track whether special Ollama model handling has been applied for tool results. Here's what I found:
+
+## Where it's used in llm.py:
+- **Line 863**: `ollama_handled = False` - initialized at the beginning of the tool execution loop
+- **Line 864**: Special handling logic via `_handle_ollama_model()` method
+- **Line 907**: `ollama_handled = True` - set when Ollama special handling is applied
+- **Line 928 & 959**: Checks `if not ollama_handled` to avoid duplicate processing
+
+## Why it's needed:
+The flag prevents duplicate processing when Ollama models require special handling. Some Ollama models return only the tool call JSON without processing the results, requiring a follow-up prompt to get the final answer. The `ollama_handled` flag ensures this special handling happens only once.
+
+## Does this contradict the requirement?
+**No, it doesn't.** The issue states:
+
+> "ollama/xxxx model is already handled via llm.py via litellm, so no special condition or handling required for ollama inside agent.py"
+
+✅ **Current implementation is correct:**
+
+- `agent.py` has NO ollama-specific conditions (only one documentation mention as an example)
+- All ollama handling is contained within `llm.py` as intended
+- The `ollama_handled` flag is an internal implementation detail within `llm.py`
+
+The codebase already follows the desired pattern where ollama models are handled through the generic LLM interface via litellm without special conditions in agent.py.

src/praisonai-agents/praisonaiagents/llm/__init__.py

@@ -5,21 +5,40 @@ import os
 # Disable litellm telemetry before any imports
 os.environ["LITELLM_TELEMETRY"] = "False"
 
-# Suppress all relevant logs at module level
-logging.getLogger("litellm").setLevel(logging.ERROR)
-logging.getLogger("openai").setLevel(logging.ERROR)
-logging.getLogger("httpx").setLevel(logging.ERROR)
-logging.getLogger("httpcore").setLevel(logging.ERROR)
-logging.getLogger("pydantic").setLevel(logging.ERROR)
+# Suppress all relevant logs at module level - consistent with main __init__.py
+logging.getLogger("litellm").setLevel(logging.WARNING)
+logging.getLogger("openai").setLevel(logging.WARNING)
+logging.getLogger("httpx").setLevel(logging.WARNING)
+logging.getLogger("httpcore").setLevel(logging.WARNING)
+logging.getLogger("pydantic").setLevel(logging.WARNING)
 
 # Suppress pydantic warnings
 warnings.filterwarnings("ignore", category=UserWarning, module="pydantic")
 
-# Configure logging to suppress all INFO messages
-logging.basicConfig(level=logging.WARNING)
-
 # Import after suppressing warnings
 from .llm import LLM, LLMContextLengthExceededException
+from .openai_client import (
+    OpenAIClient, 
+    get_openai_client,
+    ChatCompletionMessage,
+    Choice,
+    CompletionTokensDetails,
+    PromptTokensDetails,
+    CompletionUsage,
+    ChatCompletion,
+    ToolCall,
+    process_stream_chunks
+)
+from .model_capabilities import (
+    supports_structured_outputs,
+    supports_streaming_with_tools
+)
+from .model_router import (
+    ModelRouter,
+    ModelProfile, 
+    TaskComplexity,
+    create_routing_agent
+)
 
 # Ensure telemetry is disabled after import as well
 try:
@@ -28,4 +47,23 @@ try:
 except ImportError:
     pass
 
-__all__ = ["LLM", "LLMContextLengthExceededException"]
+__all__ = [
+    "LLM", 
+    "LLMContextLengthExceededException", 
+    "OpenAIClient", 
+    "get_openai_client",
+    "ChatCompletionMessage",
+    "Choice",
+    "CompletionTokensDetails",
+    "PromptTokensDetails",
+    "CompletionUsage",
+    "ChatCompletion",
+    "ToolCall",
+    "process_stream_chunks",
+    "supports_structured_outputs",
+    "supports_streaming_with_tools",
+    "ModelRouter",
+    "ModelProfile",
+    "TaskComplexity",
+    "create_routing_agent"
+]

src/praisonai-agents/praisonaiagents/llm/model_capabilities.py

@@ -0,0 +1,107 @@
+"""
+Model capabilities configuration for different LLM providers.
+This module defines which models support specific features like structured outputs.
+"""
+
+# Models that support OpenAI-style structured outputs (response_format with Pydantic models)
+MODELS_SUPPORTING_STRUCTURED_OUTPUTS = {
+    # OpenAI models
+    "gpt-4o",
+    "gpt-4o-mini",
+    "gpt-4-turbo",
+    "gpt-4-turbo-preview",
+    "gpt-4-turbo-2024-04-09",
+    "gpt-4-1106-preview",
+    "gpt-4-0125-preview",
+    "gpt-3.5-turbo",
+    "gpt-3.5-turbo-1106",
+    "gpt-3.5-turbo-0125",
+    
+    # New/Future OpenAI models (as mentioned by user)
+    "codex-mini",
+    "o3-pro",
+    "gpt-4.5-preview",
+    "o3-mini",
+    "o1",
+    "o1-preview",
+    "o1-mini",
+    "gpt-4.1",
+    "gpt-4.1-nano",
+    "gpt-4.1-mini",
+    "o4-mini",
+    "o3",
+    
+    # Gemini models that support structured outputs
+    "gemini-2.0-flash",
+    "gemini-2.0-flash-exp",
+    "gemini-1.5-pro",
+    "gemini-1.5-pro-latest",
+    "gemini-1.5-flash",
+    "gemini-1.5-flash-latest",
+    "gemini-1.5-flash-8b",
+    "gemini-1.5-flash-8b-latest",
+}
+
+# Models that explicitly DON'T support structured outputs
+MODELS_NOT_SUPPORTING_STRUCTURED_OUTPUTS = {
+    # Audio preview models
+    "gpt-4o-audio-preview",
+    "gpt-4o-mini-audio-preview",
+    
+    # Legacy o1 models (don't support system messages either)
+    "o1-preview-2024-09-12",
+    "o1-mini-2024-09-12",
+}
+
+
+def supports_structured_outputs(model_name: str) -> bool:
+    """
+    Check if a model supports OpenAI-style structured outputs.
+    
+    Args:
+        model_name: The name of the model to check
+        
+    Returns:
+        bool: True if the model supports structured outputs, False otherwise
+    """
+    if not model_name:
+        return False
+    
+    # Strip provider prefixes (e.g., 'google/', 'openai/', etc.)
+    model_without_provider = model_name
+    for prefix in ['google/', 'openai/', 'anthropic/', 'gemini/', 'mistral/', 'deepseek/', 'groq/']:
+        if model_name.startswith(prefix):
+            model_without_provider = model_name[len(prefix):]
+            break
+    
+    # First check if it's explicitly in the NOT supporting list
+    if model_without_provider in MODELS_NOT_SUPPORTING_STRUCTURED_OUTPUTS:
+        return False
+    
+    # Then check if it's in the supporting list
+    if model_without_provider in MODELS_SUPPORTING_STRUCTURED_OUTPUTS:
+        return True
+    
+    # For models with version suffixes, check the base model name
+    base_model = model_without_provider.split('-2024-')[0].split('-2025-')[0]
+    if base_model in MODELS_SUPPORTING_STRUCTURED_OUTPUTS:
+        return True
+    
+    # Default to False for unknown models
+    return False
+
+
+def supports_streaming_with_tools(model_name: str) -> bool:
+    """
+    Check if a model supports streaming when tools are provided.
+    Most models that support structured outputs also support streaming with tools.
+    
+    Args:
+        model_name: The name of the model to check
+        
+    Returns:
+        bool: True if the model supports streaming with tools, False otherwise
+    """
+    # For now, use the same logic as structured outputs
+    # In the future, this could be a separate list if needed
+    return supports_structured_outputs(model_name)

src/praisonai-agents/praisonaiagents/llm/model_router.py

@@ -0,0 +1,348 @@
+"""
+Model Router for intelligent model selection based on task characteristics.
+
+This module provides functionality to automatically select the most appropriate
+LLM model/provider based on task complexity, cost considerations, and model capabilities.
+"""
+
+import os
+import logging
+from typing import Dict, List, Optional, Tuple
+from dataclasses import dataclass
+from enum import IntEnum
+
+logger = logging.getLogger(__name__)
+
+
+class TaskComplexity(IntEnum):
+    """Enum for task complexity levels"""
+    SIMPLE = 1          # Basic queries, math, factual questions
+    MODERATE = 2        # Summarization, basic analysis
+    COMPLEX = 3         # Code generation, deep reasoning
+    VERY_COMPLEX = 4    # Multi-step reasoning, complex analysis
+
+
+@dataclass
+class ModelProfile:
+    """Profile for an LLM model with its characteristics"""
+    name: str
+    provider: str
+    complexity_range: Tuple[TaskComplexity, TaskComplexity]
+    cost_per_1k_tokens: float  # Average of input/output costs
+    strengths: List[str]
+    capabilities: List[str]
+    context_window: int
+    supports_tools: bool = True
+    supports_streaming: bool = True
+
+
+class ModelRouter:
+    """
+    Intelligent model router that selects the best model based on task requirements.
+    
+    This router implements a strategy pattern for model selection, considering:
+    - Task complexity
+    - Cost optimization
+    - Model capabilities
+    - Specific strengths for different task types
+    """
+    
+    # Default model profiles - can be customized via configuration
+    DEFAULT_MODELS = [
+        # Lightweight/cheap models for simple tasks
+        ModelProfile(
+            name="gpt-4o-mini",
+            provider="openai",
+            complexity_range=(TaskComplexity.SIMPLE, TaskComplexity.MODERATE),
+            cost_per_1k_tokens=0.00075,  # Average of $0.00015 input, $0.0006 output
+            strengths=["speed", "cost-effective", "basic-reasoning"],
+            capabilities=["text", "function-calling"],
+            context_window=128000
+        ),
+        ModelProfile(
+            name="gemini/gemini-1.5-flash",
+            provider="google",
+            complexity_range=(TaskComplexity.SIMPLE, TaskComplexity.MODERATE),
+            cost_per_1k_tokens=0.000125,  # Very cost-effective
+            strengths=["speed", "cost-effective", "multimodal"],
+            capabilities=["text", "vision", "function-calling"],
+            context_window=1048576
+        ),
+        ModelProfile(
+            name="claude-3-haiku-20240307",
+            provider="anthropic",
+            complexity_range=(TaskComplexity.SIMPLE, TaskComplexity.MODERATE),
+            cost_per_1k_tokens=0.0008,  # Average of $0.00025 input, $0.00125 output
+            strengths=["speed", "instruction-following"],
+            capabilities=["text", "function-calling"],
+            context_window=200000
+        ),
+        
+        # Mid-tier models for moderate complexity
+        ModelProfile(
+            name="gpt-4o",
+            provider="openai",
+            complexity_range=(TaskComplexity.MODERATE, TaskComplexity.COMPLEX),
+            cost_per_1k_tokens=0.0075,  # Average of $0.0025 input, $0.01 output
+            strengths=["reasoning", "code-generation", "general-purpose"],
+            capabilities=["text", "vision", "function-calling"],
+            context_window=128000
+        ),
+        ModelProfile(
+            name="claude-3-5-sonnet-20241022",
+            provider="anthropic",
+            complexity_range=(TaskComplexity.MODERATE, TaskComplexity.VERY_COMPLEX),
+            cost_per_1k_tokens=0.009,  # Average of $0.003 input, $0.015 output
+            strengths=["reasoning", "code-generation", "analysis", "writing"],
+            capabilities=["text", "vision", "function-calling"],
+            context_window=200000
+        ),
+        
+        # High-end models for complex tasks
+        ModelProfile(
+            name="gemini/gemini-1.5-pro",
+            provider="google",
+            complexity_range=(TaskComplexity.COMPLEX, TaskComplexity.VERY_COMPLEX),
+            cost_per_1k_tokens=0.00625,  # Average of $0.00125 input, $0.005 output
+            strengths=["reasoning", "long-context", "multimodal"],
+            capabilities=["text", "vision", "function-calling"],
+            context_window=2097152  # 2M context
+        ),
+        ModelProfile(
+            name="claude-3-opus-20240229",
+            provider="anthropic",
+            complexity_range=(TaskComplexity.COMPLEX, TaskComplexity.VERY_COMPLEX),
+            cost_per_1k_tokens=0.045,  # Average of $0.015 input, $0.075 output
+            strengths=["deep-reasoning", "complex-analysis", "creative-writing"],
+            capabilities=["text", "vision", "function-calling"],
+            context_window=200000
+        ),
+        ModelProfile(
+            name="deepseek-chat",
+            provider="deepseek",
+            complexity_range=(TaskComplexity.COMPLEX, TaskComplexity.VERY_COMPLEX),
+            cost_per_1k_tokens=0.0014,  # Very cost-effective for capability
+            strengths=["reasoning", "code-generation", "mathematics"],
+            capabilities=["text", "function-calling"],
+            context_window=128000
+        ),
+    ]
+    
+    def __init__(
+        self,
+        models: Optional[List[ModelProfile]] = None,
+        default_model: Optional[str] = None,
+        cost_threshold: Optional[float] = None,
+        preferred_providers: Optional[List[str]] = None
+    ):
+        """
+        Initialize the ModelRouter.
+        
+        Args:
+            models: Custom list of model profiles to use
+            default_model: Default model to use if no suitable model found
+            cost_threshold: Maximum cost per 1k tokens to consider
+            preferred_providers: List of preferred providers in order
+        """
+        self.models = models or self.DEFAULT_MODELS
+        self.default_model = default_model or os.getenv('OPENAI_MODEL_NAME', 'gpt-4o')
+        self.cost_threshold = cost_threshold
+        self.preferred_providers = preferred_providers or []
+        
+        # Build lookup indices for efficient access
+        self._model_by_name = {m.name: m for m in self.models}
+        self._models_by_complexity = self._build_complexity_index()
+        
+    def _build_complexity_index(self) -> Dict[TaskComplexity, List[ModelProfile]]:
+        """Build an index of models by complexity level"""
+        index = {level: [] for level in TaskComplexity}
+        
+        for model in self.models:
+            min_complexity, max_complexity = model.complexity_range
+            for level in TaskComplexity:
+                if min_complexity.value <= level.value <= max_complexity.value:
+                    index[level].append(model)
+        
+        return index
+    
+    def analyze_task_complexity(
+        self,
+        task_description: str,
+        tools_required: Optional[List[str]] = None,
+        context_size: Optional[int] = None
+    ) -> TaskComplexity:
+        """
+        Analyze task description to determine complexity level.
+        
+        This is a simple heuristic-based approach. In production, this could be
+        replaced with a more sophisticated ML-based classifier.
+        """
+        description_lower = task_description.lower()
+        
+        # Keywords indicating different complexity levels
+        simple_keywords = [
+            "calculate", "compute", "what is", "define", "list", "count",
+            "simple", "basic", "check", "verify", "yes or no", "true or false"
+        ]
+        
+        moderate_keywords = [
+            "summarize", "explain", "compare", "describe", "analyze briefly",
+            "find", "search", "extract", "classify", "categorize"
+        ]
+        
+        complex_keywords = [
+            "implement", "code", "develop", "design", "create algorithm",
+            "optimize", "debug", "refactor", "architect", "solve"
+        ]
+        
+        very_complex_keywords = [
+            "multi-step", "comprehensive analysis", "deep dive", "research",
+            "strategic", "framework", "system design", "proof", "theorem"
+        ]
+        
+        # Check for keyword matches
+        if any(keyword in description_lower for keyword in very_complex_keywords):
+            return TaskComplexity.VERY_COMPLEX
+        elif any(keyword in description_lower for keyword in complex_keywords):
+            return TaskComplexity.COMPLEX
+        elif any(keyword in description_lower for keyword in moderate_keywords):
+            return TaskComplexity.MODERATE
+        elif any(keyword in description_lower for keyword in simple_keywords):
+            return TaskComplexity.SIMPLE
+        
+        # Consider tool requirements
+        if tools_required and len(tools_required) > 3:
+            return TaskComplexity.COMPLEX
+        
+        # Consider context size requirements
+        if context_size and context_size > 50000:
+            return TaskComplexity.COMPLEX
+        
+        # Default to moderate
+        return TaskComplexity.MODERATE
+    
+    def select_model(
+        self,
+        task_description: str,
+        required_capabilities: Optional[List[str]] = None,
+        tools_required: Optional[List[str]] = None,
+        context_size: Optional[int] = None,
+        budget_conscious: bool = True
+    ) -> str:
+        """
+        Select the most appropriate model for a given task.
+        
+        Args:
+            task_description: Description of the task to perform
+            required_capabilities: List of required capabilities (e.g., ["vision", "function-calling"])
+            tools_required: List of tools that will be used
+            context_size: Estimated context size needed
+            budget_conscious: Whether to optimize for cost
+            
+        Returns:
+            Model name string to use
+        """
+        # Analyze task complexity
+        complexity = self.analyze_task_complexity(task_description, tools_required, context_size)
+        
+        # Get candidate models for this complexity level
+        candidates = self._models_by_complexity.get(complexity, [])
+        
+        if not candidates:
+            logger.warning(f"No models found for complexity {complexity}, using default")
+            return self.default_model
+        
+        # Filter by required capabilities
+        if required_capabilities:
+            candidates = [
+                m for m in candidates
+                if all(cap in m.capabilities for cap in required_capabilities)
+            ]
+        
+        # Filter by tool support if needed
+        if tools_required:
+            candidates = [m for m in candidates if m.supports_tools]
+        
+        # Filter by context window if specified
+        if context_size:
+            candidates = [m for m in candidates if m.context_window >= context_size]
+        
+        # Filter by cost threshold if specified
+        if self.cost_threshold:
+            candidates = [m for m in candidates if m.cost_per_1k_tokens <= self.cost_threshold]
+        
+        if not candidates:
+            logger.warning("No models meet all criteria, using default")
+            return self.default_model
+        
+        # Sort by selection criteria
+        if budget_conscious:
+            # Sort by cost (ascending)
+            candidates.sort(key=lambda m: m.cost_per_1k_tokens)
+        else:
+            # Sort by capability (descending complexity)
+            candidates.sort(key=lambda m: m.complexity_range[1].value, reverse=True)
+        
+        # Apply provider preferences
+        if self.preferred_providers:
+            for provider in self.preferred_providers:
+                for model in candidates:
+                    if model.provider == provider:
+                        logger.info(f"Selected model: {model.name} (complexity: {complexity}, cost: ${model.cost_per_1k_tokens}/1k tokens)")
+                        return model.name
+        
+        # Return the best candidate
+        selected = candidates[0]
+        logger.info(f"Selected model: {selected.name} (complexity: {complexity}, cost: ${selected.cost_per_1k_tokens}/1k tokens)")
+        return selected.name
+    
+    def get_model_info(self, model_name: str) -> Optional[ModelProfile]:
+        """Get profile information for a specific model"""
+        return self._model_by_name.get(model_name)
+    
+    def estimate_cost(self, model_name: str, estimated_tokens: int) -> float:
+        """Estimate the cost for a given model and token count"""
+        model = self._model_by_name.get(model_name)
+        if not model:
+            return 0.0
+        return (model.cost_per_1k_tokens * estimated_tokens) / 1000
+
+
+def create_routing_agent(
+    models: Optional[List[str]] = None,
+    router: Optional[ModelRouter] = None,
+    **agent_kwargs
+) -> 'Agent':
+    """
+    Create a specialized routing agent that can select models dynamically.
+    
+    Args:
+        models: List of model names to route between
+        router: Custom ModelRouter instance
+        **agent_kwargs: Additional arguments to pass to Agent constructor
+        
+    Returns:
+        Agent configured for model routing
+    """
+    from ..agent import Agent
+    
+    if not router:
+        router = ModelRouter()
+    
+    routing_agent = Agent(
+        name=agent_kwargs.pop('name', 'ModelRouter'),
+        role=agent_kwargs.pop('role', 'Intelligent Model Router'),
+        goal=agent_kwargs.pop('goal', 'Select the most appropriate AI model based on task requirements'),
+        backstory=agent_kwargs.pop('backstory', 
+            'I analyze tasks and route them to the most suitable AI model, '
+            'optimizing for performance, cost, and capability requirements.'
+        ),
+        **agent_kwargs
+    )
+    
+    # TODO: Consider creating a proper RoutingAgent subclass instead of setting private attributes
+    # For now, store the router on the agent for use in execution
+    routing_agent._model_router = router
+    routing_agent._available_models = models or [m.name for m in router.models]
+    
+    return routing_agent

src/praisonai-agents/praisonaiagents/main.py

@@ -3,39 +3,21 @@ import time
 import json
 import logging
 from typing import List, Optional, Dict, Any, Union, Literal, Type
-from openai import OpenAI
 from pydantic import BaseModel, ConfigDict
 from rich import print
 from rich.console import Console
 from rich.panel import Panel
 from rich.text import Text
 from rich.markdown import Markdown
-from rich.logging import RichHandler
 from rich.live import Live
 import asyncio
 
-# # Configure root logger
-# logging.basicConfig(level=logging.WARNING)
-
-# Suppress litellm logs
+# Logging is already configured in __init__.py, just clean up handlers for litellm
 logging.getLogger("litellm").handlers = []
 logging.getLogger("litellm.utils").handlers = []
 logging.getLogger("litellm").propagate = False
 logging.getLogger("litellm.utils").propagate = False
 
-LOGLEVEL = os.environ.get('LOGLEVEL', 'INFO').upper()
-
-logging.basicConfig(
-    level=getattr(logging, LOGLEVEL, logging.INFO),
-    format="%(asctime)s %(filename)s:%(lineno)d %(levelname)s %(message)s",
-    datefmt="[%X]",
-    handlers=[RichHandler(rich_tracebacks=True)]
-)
-
-# Add these lines to suppress markdown parser debug logs
-logging.getLogger('markdown_it').setLevel(logging.WARNING)
-logging.getLogger('rich.markdown').setLevel(logging.WARNING)
-
 # Global list to store error logs
 error_logs = []
 
@@ -377,24 +359,6 @@ class ReflectionOutput(BaseModel):
     reflection: str
     satisfactory: Literal["yes", "no"]
 
-# Constants
-LOCAL_SERVER_API_KEY_PLACEHOLDER = "not-needed"
-
-# Initialize OpenAI client with proper API key handling
-api_key = os.environ.get("OPENAI_API_KEY")
-base_url = os.environ.get("OPENAI_API_BASE") or os.environ.get("OPENAI_BASE_URL")
-
-# For local servers like LM Studio, allow minimal API key
-if base_url and not api_key:
-    api_key = LOCAL_SERVER_API_KEY_PLACEHOLDER
-elif not api_key:
-    raise ValueError(
-        "OPENAI_API_KEY environment variable is required for the default OpenAI service. "
-        "If you are targeting a local server (e.g., LM Studio), ensure OPENAI_API_BASE is set "
-        f"(e.g., 'http://localhost:1234/v1') and you can use a placeholder API key by setting OPENAI_API_KEY='{LOCAL_SERVER_API_KEY_PLACEHOLDER}'"
-    )
-
-client = OpenAI(api_key=api_key, base_url=base_url)
 
 class TaskOutput(BaseModel):
     model_config = ConfigDict(arbitrary_types_allowed=True)

src/praisonai-agents/praisonaiagents/mcp/mcp.py

@@ -187,15 +187,45 @@ class MCP:
         self.timeout = timeout
         self.debug = debug
         
-        # Check if this is an SSE URL
+        # Check if this is an HTTP URL
         if isinstance(command_or_string, str) and re.match(r'^https?://', command_or_string):
-            # Import the SSE client implementation
-            from .mcp_sse import SSEMCPClient
-            self.sse_client = SSEMCPClient(command_or_string, debug=debug, timeout=timeout)
-            self._tools = list(self.sse_client.tools)
-            self.is_sse = True
-            self.is_npx = False
-            return
+            # Determine transport type based on URL or kwargs
+            if command_or_string.endswith('/sse') and 'transport_type' not in kwargs:
+                # Legacy SSE URL - use SSE transport for backward compatibility
+                from .mcp_sse import SSEMCPClient
+                self.sse_client = SSEMCPClient(command_or_string, debug=debug, timeout=timeout)
+                self._tools = list(self.sse_client.tools)
+                self.is_sse = True
+                self.is_http_stream = False
+                self.is_npx = False
+                return
+            else:
+                # Use HTTP Stream transport for all other HTTP URLs
+                from .mcp_http_stream import HTTPStreamMCPClient
+                # Extract transport options from kwargs
+                transport_options = {}
+                if 'responseMode' in kwargs:
+                    transport_options['responseMode'] = kwargs.pop('responseMode')
+                if 'headers' in kwargs:
+                    transport_options['headers'] = kwargs.pop('headers')
+                if 'cors' in kwargs:
+                    transport_options['cors'] = kwargs.pop('cors')
+                if 'session' in kwargs:
+                    transport_options['session'] = kwargs.pop('session')
+                if 'resumability' in kwargs:
+                    transport_options['resumability'] = kwargs.pop('resumability')
+                
+                self.http_stream_client = HTTPStreamMCPClient(
+                    command_or_string, 
+                    debug=debug, 
+                    timeout=timeout,
+                    options=transport_options
+                )
+                self._tools = list(self.http_stream_client.tools)
+                self.is_sse = False
+                self.is_http_stream = True
+                self.is_npx = False
+                return
             
         # Handle the single string format for stdio client
         if isinstance(command_or_string, str) and args is None:
@@ -219,6 +249,7 @@ class MCP:
         
         # Set up stdio client
         self.is_sse = False
+        self.is_http_stream = False
         
         # Ensure UTF-8 encoding in environment for Docker compatibility
         env = kwargs.get('env', {})
@@ -275,6 +306,9 @@ class MCP:
         """
         if self.is_sse:
             return list(self.sse_client.tools)
+        
+        if self.is_http_stream:
+            return list(self.http_stream_client.tools)
             
         tool_functions = []
         
@@ -448,6 +482,10 @@ class MCP:
         if self.is_sse and hasattr(self, 'sse_client') and self.sse_client.tools:
             # Return all tools from SSE client
             return self.sse_client.to_openai_tools()
+        
+        if self.is_http_stream and hasattr(self, 'http_stream_client') and self.http_stream_client.tools:
+            # Return all tools from HTTP Stream client
+            return self.http_stream_client.to_openai_tools()
             
         # For simplicity, we'll convert the first tool only if multiple exist
         # More complex implementations could handle multiple tools

src/praisonai-agents/praisonaiagents/mcp/mcp_http_stream.py

@@ -0,0 +1,466 @@
+"""
+HTTP Stream client implementation for MCP (Model Context Protocol).
+This module provides the necessary classes and functions to connect to an MCP server
+over HTTP Stream transport, implementing the Streamable HTTP transport protocol.
+"""
+
+import asyncio
+import logging
+import threading
+import inspect
+import json
+import time
+import uuid
+from typing import List, Dict, Any, Optional, Callable, Iterable, Union
+from urllib.parse import urlparse, urljoin
+
+from mcp import ClientSession
+try:
+    import aiohttp
+except ImportError:
+    raise ImportError("aiohttp is required for HTTP Stream transport. Install with: pip install praisonaiagents[mcp]")
+
+logger = logging.getLogger("mcp-http-stream")
+
+# Global event loop for async operations
+_event_loop = None
+
+def get_event_loop():
+    """Get or create a global event loop."""
+    global _event_loop
+    if _event_loop is None or _event_loop.is_closed():
+        _event_loop = asyncio.new_event_loop()
+        asyncio.set_event_loop(_event_loop)
+    return _event_loop
+
+
+class HTTPStreamMCPTool:
+    """A wrapper for an MCP tool that can be used with praisonaiagents."""
+    
+    def __init__(self, name: str, description: str, session: ClientSession, input_schema: Optional[Dict[str, Any]] = None, timeout: int = 60):
+        self.name = name
+        self.__name__ = name  # Required for Agent to recognize it as a tool
+        self.__qualname__ = name  # Required for Agent to recognize it as a tool
+        self.__doc__ = description  # Required for Agent to recognize it as a tool
+        self.description = description
+        self.session = session
+        self.input_schema = input_schema or {}
+        self.timeout = timeout
+        
+        # Create a signature based on input schema
+        params = []
+        if input_schema and 'properties' in input_schema:
+            for param_name, prop_schema in input_schema['properties'].items():
+                # Determine type annotation based on schema
+                prop_type = prop_schema.get('type', 'string') if isinstance(prop_schema, dict) else 'string'
+                if prop_type == 'string':
+                    annotation = str
+                elif prop_type == 'integer':
+                    annotation = int
+                elif prop_type == 'number':
+                    annotation = float
+                elif prop_type == 'boolean':
+                    annotation = bool
+                elif prop_type == 'array':
+                    annotation = list
+                elif prop_type == 'object':
+                    annotation = dict
+                else:
+                    annotation = Any
+                
+                params.append(
+                    inspect.Parameter(
+                        name=param_name,
+                        kind=inspect.Parameter.POSITIONAL_OR_KEYWORD,
+                        default=inspect.Parameter.empty if param_name in input_schema.get('required', []) else None,
+                        annotation=annotation
+                    )
+                )
+        
+        self.__signature__ = inspect.Signature(params)
+        
+    def __call__(self, **kwargs):
+        """Synchronous wrapper for the async call."""
+        logger.debug(f"Tool {self.name} called with args: {kwargs}")
+        
+        # Use the global event loop
+        loop = get_event_loop()
+        
+        # Run the async call in the event loop
+        future = asyncio.run_coroutine_threadsafe(self._async_call(**kwargs), loop)
+        try:
+            # Wait for the result with a timeout
+            return future.result(timeout=self.timeout)
+        except Exception as e:
+            logger.error(f"Error calling tool {self.name}: {e}")
+            return f"Error: {str(e)}"
+    
+    async def _async_call(self, **kwargs):
+        """Call the tool with the provided arguments."""
+        logger.debug(f"Async calling tool {self.name} with args: {kwargs}")
+        try:
+            result = await self.session.call_tool(self.name, kwargs)
+            
+            # Extract text from result
+            if hasattr(result, 'content') and result.content:
+                if hasattr(result.content[0], 'text'):
+                    return result.content[0].text
+                return str(result.content[0])
+            return str(result)
+        except Exception as e:
+            logger.error(f"Error in _async_call for {self.name}: {e}")
+            raise
+    
+    def _fix_array_schemas(self, schema):
+        """
+        Fix array schemas by adding missing 'items' attribute required by OpenAI.
+        
+        This ensures compatibility with OpenAI's function calling format which
+        requires array types to specify the type of items they contain.
+        
+        Args:
+            schema: The schema dictionary to fix
+            
+        Returns:
+            dict: The fixed schema
+        """
+        if not isinstance(schema, dict):
+            return schema
+            
+        # Create a copy to avoid modifying the original
+        fixed_schema = schema.copy()
+        
+        # Fix array types at the current level
+        if fixed_schema.get("type") == "array" and "items" not in fixed_schema:
+            # Add a default items schema for arrays without it
+            fixed_schema["items"] = {"type": "string"}
+            
+        # Recursively fix nested schemas
+        if "properties" in fixed_schema:
+            fixed_properties = {}
+            for prop_name, prop_schema in fixed_schema["properties"].items():
+                fixed_properties[prop_name] = self._fix_array_schemas(prop_schema)
+            fixed_schema["properties"] = fixed_properties
+            
+        # Fix items schema if it exists
+        if "items" in fixed_schema:
+            fixed_schema["items"] = self._fix_array_schemas(fixed_schema["items"])
+            
+        return fixed_schema
+    
+    def to_openai_tool(self):
+        """Convert the tool to OpenAI format."""
+        # Fix array schemas to include 'items' attribute
+        fixed_schema = self._fix_array_schemas(self.input_schema)
+        
+        return {
+            "type": "function",
+            "function": {
+                "name": self.name,
+                "description": self.description,
+                "parameters": fixed_schema
+            }
+        }
+
+
+class HTTPStreamTransport:
+    """
+    HTTP Stream Transport implementation for MCP.
+    
+    This transport provides a single endpoint for all MCP communication,
+    supporting both batch (JSON) and streaming (SSE) response modes.
+    """
+    
+    def __init__(self, base_url: str, session_id: Optional[str] = None, options: Optional[Dict[str, Any]] = None):
+        self.base_url = base_url
+        self.session_id = session_id
+        self.options = options or {}
+        self.response_mode = self.options.get('responseMode', 'batch')
+        self.headers = {
+            'Content-Type': 'application/json',
+            'Accept': 'application/json, text/event-stream'
+        }
+        if session_id:
+            self.headers['Mcp-Session-Id'] = session_id
+        
+        # Add custom headers if provided
+        if 'headers' in self.options:
+            self.headers.update(self.options['headers'])
+        
+        self._session = None
+        self._sse_task = None
+        self._message_queue = asyncio.Queue()
+        self._pending_requests = {}
+        self._closing = False
+        
+    async def __aenter__(self):
+        self._session = aiohttp.ClientSession()
+        return self
+    
+    async def __aexit__(self, exc_type, exc_val, exc_tb):
+        # Set closing flag to stop listener gracefully
+        self._closing = True
+        
+        if self._sse_task:
+            self._sse_task.cancel()
+            try:
+                await self._sse_task
+            except asyncio.CancelledError:
+                pass
+        if self._session:
+            await self._session.close()
+    
+    async def send_request(self, request: Dict[str, Any]) -> Union[Dict[str, Any], None]:
+        """Send a request to the HTTP Stream endpoint."""
+        if not self._session:
+            raise RuntimeError("Transport not initialized. Use async context manager.")
+        
+        try:
+            async with self._session.post(self.base_url, json=request, headers=self.headers) as response:
+                # Update session ID if provided in response
+                if 'Mcp-Session-Id' in response.headers:
+                    self.session_id = response.headers['Mcp-Session-Id']
+                    self.headers['Mcp-Session-Id'] = self.session_id
+                
+                # Handle different response types
+                content_type = response.headers.get('Content-Type', '')
+                
+                if 'text/event-stream' in content_type:
+                    # Stream mode - process SSE events
+                    return await self._process_sse_response(response)
+                else:
+                    # Batch mode - return JSON response
+                    return await response.json()
+                    
+        except Exception as e:
+            logger.error(f"Error sending request: {e}")
+            raise
+    
+    async def _process_sse_response(self, response):
+        """Process SSE response stream."""
+        buffer = ""
+        async for chunk in response.content:
+            buffer += chunk.decode('utf-8')
+            
+            # Process complete SSE events
+            while "\n\n" in buffer:
+                event, buffer = buffer.split("\n\n", 1)
+                lines = event.strip().split("\n")
+                
+                # Parse SSE event
+                data = None
+                for line in lines:
+                    if line.startswith("data: "):
+                        data = line[6:]  # Remove "data: " prefix
+                
+                if data:
+                    try:
+                        message = json.loads(data)
+                        # Process the message
+                        if 'id' in message and message['id'] in self._pending_requests:
+                            # This is a response to a pending request
+                            self._pending_requests[message['id']].set_result(message)
+                        else:
+                            # This is a server-initiated message
+                            await self._message_queue.put(message)
+                    except json.JSONDecodeError:
+                        logger.error(f"Failed to parse SSE event: {data}")
+    
+    async def start_sse_listener(self):
+        """Start listening for SSE events from the server."""
+        if self._sse_task is None or self._sse_task.done():
+            self._sse_task = asyncio.create_task(self._sse_listener())
+    
+    async def _sse_listener(self):
+        """Background task to listen for SSE events."""
+        while True:
+            try:
+                # Check if we should stop
+                if hasattr(self, '_closing') and self._closing:
+                    break
+                    
+                url = self.base_url
+                if self.session_id:
+                    # Add session as query parameter for SSE connection
+                    url = f"{url}?session={self.session_id}"
+                
+                headers = {
+                    'Accept': 'text/event-stream',
+                    'Cache-Control': 'no-cache'
+                }
+                if self.session_id:
+                    headers['Mcp-Session-Id'] = self.session_id
+                
+                async with self._session.get(url, headers=headers) as response:
+                    buffer = ""
+                    async for chunk in response.content:
+                        # Check if we should stop
+                        if hasattr(self, '_closing') and self._closing:
+                            break
+                            
+                        buffer += chunk.decode('utf-8')
+                        
+                        # Process complete SSE events
+                        while "\n\n" in buffer:
+                            event, buffer = buffer.split("\n\n", 1)
+                            lines = event.strip().split("\n")
+                            
+                            # Parse SSE event
+                            data = None
+                            for line in lines:
+                                if line.startswith("data: "):
+                                    data = line[6:]  # Remove "data: " prefix
+                            
+                            if data:
+                                try:
+                                    message = json.loads(data)
+                                    await self._message_queue.put(message)
+                                except json.JSONDecodeError:
+                                    logger.error(f"Failed to parse SSE event: {data}")
+                                
+            except asyncio.CancelledError:
+                # Proper shutdown
+                break
+            except Exception as e:
+                if not (hasattr(self, '_closing') and self._closing):
+                    logger.error(f"SSE listener error: {e}")
+                    await asyncio.sleep(1)  # Reconnect after 1 second
+                else:
+                    break
+    
+    def read_stream(self):
+        """Create a read stream for the ClientSession."""
+        async def _read():
+            while True:
+                message = await self._message_queue.get()
+                yield message
+        return _read()
+    
+    def write_stream(self):
+        """Create a write stream for the ClientSession."""
+        async def _write(message):
+            if hasattr(message, 'to_dict'):
+                message = message.to_dict()
+            response = await self.send_request(message)
+            return response
+        return _write
+
+
+class HTTPStreamMCPClient:
+    """A client for connecting to an MCP server over HTTP Stream transport."""
+    
+    def __init__(self, server_url: str, debug: bool = False, timeout: int = 60, options: Optional[Dict[str, Any]] = None):
+        """
+        Initialize an HTTP Stream MCP client.
+        
+        Args:
+            server_url: The URL of the HTTP Stream MCP server
+            debug: Whether to enable debug logging
+            timeout: Timeout in seconds for operations (default: 60)
+            options: Additional configuration options for the transport
+        """
+        # Parse URL to extract base URL and endpoint
+        parsed = urlparse(server_url)
+        
+        # If the URL already has a path, use it; otherwise use default /mcp endpoint
+        if parsed.path and parsed.path != '/':
+            self.base_url = server_url
+        else:
+            # Default endpoint is /mcp
+            self.base_url = urljoin(server_url, '/mcp')
+        
+        self.debug = debug
+        self.timeout = timeout
+        self.options = options or {}
+        self.session = None
+        self.tools = []
+        self.transport = None
+        
+        # Set up logging
+        if debug:
+            logger.setLevel(logging.DEBUG)
+        else:
+            # Set to WARNING by default to hide INFO messages
+            logger.setLevel(logging.WARNING)
+        
+        self._initialize()
+        
+    def _initialize(self):
+        """Initialize the connection and tools."""
+        # Use the global event loop
+        loop = get_event_loop()
+        
+        # Start a background thread to run the event loop
+        def run_event_loop():
+            asyncio.set_event_loop(loop)
+            loop.run_forever()
+        
+        self.loop_thread = threading.Thread(target=run_event_loop, daemon=True)
+        self.loop_thread.start()
+        
+        # Run the initialization in the event loop
+        future = asyncio.run_coroutine_threadsafe(self._async_initialize(), loop)
+        self.tools = future.result(timeout=self.timeout)
+    
+    async def _async_initialize(self):
+        """Asynchronously initialize the connection and tools."""
+        logger.debug(f"Connecting to MCP server at {self.base_url}")
+        
+        # Create HTTP Stream transport
+        self.transport = HTTPStreamTransport(self.base_url, options=self.options)
+        await self.transport.__aenter__()
+        
+        # Create read and write streams
+        read_stream = self.transport.read_stream()
+        write_stream = self.transport.write_stream()
+        
+        # Start SSE listener if in stream mode
+        if self.options.get('responseMode', 'batch') == 'stream':
+            await self.transport.start_sse_listener()
+        
+        # Create client session
+        self._session_context = ClientSession(read_stream, write_stream)
+        self.session = await self._session_context.__aenter__()
+        
+        # Initialize
+        await self.session.initialize()
+        
+        # List available tools
+        logger.debug("Listing tools...")
+        response = await self.session.list_tools()
+        tools_data = response.tools
+        logger.debug(f"Found {len(tools_data)} tools: {[tool.name for tool in tools_data]}")
+        
+        # Create tool wrappers
+        tools = []
+        for tool in tools_data:
+            input_schema = tool.inputSchema if hasattr(tool, 'inputSchema') else None
+            wrapper = HTTPStreamMCPTool(
+                name=tool.name,
+                description=tool.description if hasattr(tool, 'description') else f"Call the {tool.name} tool",
+                session=self.session,
+                input_schema=input_schema,
+                timeout=self.timeout
+            )
+            tools.append(wrapper)
+            
+        return tools
+    
+    def __iter__(self):
+        """Return an iterator over the tools."""
+        return iter(self.tools)
+    
+    def to_openai_tools(self):
+        """Convert all tools to OpenAI format."""
+        return [tool.to_openai_tool() for tool in self.tools]
+    
+    async def __aenter__(self):
+        """Async context manager entry."""
+        return self
+    
+    async def __aexit__(self, exc_type, exc_val, exc_tb):
+        """Async context manager exit."""
+        if self.transport:
+            await self.transport.__aexit__(exc_type, exc_val, exc_tb)
+        if hasattr(self, '_session_context') and self._session_context:
+            await self._session_context.__aexit__(exc_type, exc_val, exc_tb)

src/praisonai-agents/praisonaiagents/mcp/mcp_sse.py

@@ -44,13 +44,30 @@ class SSEMCPTool:
         # Create a signature based on input schema
         params = []
         if input_schema and 'properties' in input_schema:
-            for param_name in input_schema['properties']:
+            for param_name, prop_schema in input_schema['properties'].items():
+                # Determine type annotation based on schema
+                prop_type = prop_schema.get('type', 'string') if isinstance(prop_schema, dict) else 'string'
+                if prop_type == 'string':
+                    annotation = str
+                elif prop_type == 'integer':
+                    annotation = int
+                elif prop_type == 'number':
+                    annotation = float
+                elif prop_type == 'boolean':
+                    annotation = bool
+                elif prop_type == 'array':
+                    annotation = list
+                elif prop_type == 'object':
+                    annotation = dict
+                else:
+                    annotation = str  # Default to string for SSE
+                
                 params.append(
                     inspect.Parameter(
                         name=param_name,
                         kind=inspect.Parameter.POSITIONAL_OR_KEYWORD,
                         default=inspect.Parameter.empty if param_name in input_schema.get('required', []) else None,
-                        annotation=str  # Default to string
+                        annotation=annotation
                     )
                 )
         

src/praisonai-agents/praisonaiagents/process/process.py

@@ -5,10 +5,10 @@ from typing import Dict, Optional, List, Any, AsyncGenerator
 from pydantic import BaseModel, ConfigDict
 from ..agent.agent import Agent
 from ..task.task import Task
-from ..main import display_error, client
+from ..main import display_error
+from ..llm import LLM
 import csv
 import os
-from openai import AsyncOpenAI
 
 class LoopItems(BaseModel):
     model_config = ConfigDict(arbitrary_types_allowed=True)
@@ -16,6 +16,7 @@ class LoopItems(BaseModel):
 
 class Process:
     DEFAULT_RETRY_LIMIT = 3  # Predefined retry limit in a common place
+    VALIDATION_FAILURE_DECISIONS = ["invalid", "retry", "failed", "error", "unsuccessful", "fail", "errors", "reject", "rejected", "incomplete"]  # Decision strings that trigger validation feedback
 
     def __init__(self, tasks: Dict[str, Task], agents: List[Agent], manager_llm: Optional[str] = None, verbose: bool = False, max_iter: int = 10):
         logging.debug(f"=== Initializing Process ===")
@@ -33,12 +34,61 @@ class Process:
         self.task_retry_counter: Dict[str, int] = {} # Initialize retry counter
         self.workflow_finished = False # ADDED: Workflow finished flag
 
+    def _create_llm_instance(self):
+        """Create and return a configured LLM instance for manager tasks."""
+        return LLM(model=self.manager_llm, temperature=0.7)
+
+    def _parse_manager_instructions(self, response, ManagerInstructions):
+        """Parse LLM response and return ManagerInstructions instance.
+        
+        Args:
+            response: String response from LLM
+            ManagerInstructions: Pydantic model class for validation
+            
+        Returns:
+            ManagerInstructions instance
+            
+        Raises:
+            Exception: If parsing fails
+        """
+        try:
+            parsed_json = json.loads(response)
+            return ManagerInstructions(**parsed_json)
+        except (json.JSONDecodeError, ValueError, TypeError) as e:
+            raise Exception(f"Failed to parse response: {response}") from e
+
+    def _create_loop_subtasks(self, loop_task: Task):
+        """Create subtasks for a loop task from input file."""
+        logging.warning(f"_create_loop_subtasks called for {loop_task.name} but method not fully implemented")
+        # TODO: Implement loop subtask creation from input file
+        # This should read loop_task.input_file and create subtasks
+        pass
+
     def _build_task_context(self, current_task: Task) -> str:
         """Build context for a task based on its retain_full_context setting"""
-        if not (current_task.previous_tasks or current_task.context):
-            return ""
+        # Check if we have validation feedback to include
+        if current_task.validation_feedback:
+            feedback = current_task.validation_feedback
+            context = f"\nPrevious attempt failed validation with reason: {feedback['validation_response']}"
+            if feedback.get('validated_task'):
+                context += f"\nValidated task: {feedback['validated_task']}"
+            if feedback.get('validation_details'):
+                context += f"\nValidation feedback: {feedback['validation_details']}"
+            if feedback.get('rejected_output'):
+                context += f"\nRejected output: {feedback['rejected_output']}"
+            context += "\nPlease try again with a different approach based on this feedback.\n"
+            # Clear the feedback after including it to prevent it from persisting
+            current_task.validation_feedback = None
             
-        context = "\nInput data from previous tasks:"
+            # If we have validation feedback but no previous tasks context, return just the feedback
+            if not (current_task.previous_tasks or current_task.context):
+                return context
+            # Otherwise, append the regular context
+            context += "\nInput data from previous tasks:"
+        elif not (current_task.previous_tasks or current_task.context):
+            return ""
+        else:
+            context = "\nInput data from previous tasks:"
         
         if current_task.retain_full_context:
             # Original behavior: include all previous tasks
@@ -140,22 +190,24 @@ class Process:
 
     def _get_manager_instructions_with_fallback(self, manager_task, manager_prompt, ManagerInstructions):
         """Sync version of getting manager instructions with fallback"""
+        # Create LLM instance with the manager_llm
+        llm = self._create_llm_instance()
+        
         try:
-            # First try structured output (OpenAI compatible)
+            # Use LLM with output_pydantic for structured output
             logging.info("Attempting structured output...")
-            manager_response = client.beta.chat.completions.parse(
-                model=self.manager_llm,
-                messages=[
-                    {"role": "system", "content": manager_task.description},
-                    {"role": "user", "content": manager_prompt}
-                ],
-                temperature=0.7,
-                response_format=ManagerInstructions
+            response = llm.get_response(
+                prompt=manager_prompt,
+                system_prompt=manager_task.description,
+                output_pydantic=ManagerInstructions
             )
-            return manager_response.choices[0].message.parsed
+            
+            # Parse the response and validate with Pydantic
+            return self._parse_manager_instructions(response, ManagerInstructions)
+                
         except Exception as e:
             logging.info(f"Structured output failed: {e}, falling back to JSON mode...")
-            # Fallback to regular JSON mode
+            # Fallback to regular JSON mode with explicit JSON instructions
             try:
                 # Generate JSON structure description from Pydantic model
                 try:
@@ -171,23 +223,14 @@ class Process:
                     # Fallback to hardcoded prompt if schema generation fails
                     enhanced_prompt = manager_prompt + "\n\nIMPORTANT: Respond with valid JSON only, using this exact structure: {\"task_id\": <int>, \"agent_name\": \"<string>\", \"action\": \"<execute or stop>\"}"
                 
-                manager_response = client.chat.completions.create(
-                    model=self.manager_llm,
-                    messages=[
-                        {"role": "system", "content": manager_task.description},
-                        {"role": "user", "content": enhanced_prompt}
-                    ],
-                    temperature=0.7,
-                    response_format={"type": "json_object"}
+                response = llm.get_response(
+                    prompt=enhanced_prompt,
+                    system_prompt=manager_task.description,
+                    output_json=True
                 )
                 
                 # Parse JSON and validate with Pydantic
-                try:
-                    json_content = manager_response.choices[0].message.content
-                    parsed_json = json.loads(json_content)
-                    return ManagerInstructions(**parsed_json)
-                except (json.JSONDecodeError, ValueError) as e:
-                    raise Exception(f"Failed to parse JSON response: {json_content}") from e
+                return self._parse_manager_instructions(response, ManagerInstructions)
             except Exception as fallback_error:
                 error_msg = f"Both structured output and JSON fallback failed: {fallback_error}"
                 logging.error(error_msg, exc_info=True)
@@ -195,40 +238,32 @@ class Process:
 
     async def _get_structured_response_async(self, manager_task, manager_prompt, ManagerInstructions):
         """Async version of structured response"""
-        # Create an async client instance for this async method
-        async_client = AsyncOpenAI()
-        manager_response = await async_client.beta.chat.completions.parse(
-            model=self.manager_llm,
-            messages=[
-                {"role": "system", "content": manager_task.description},
-                {"role": "user", "content": manager_prompt}
-            ],
-            temperature=0.7,
-            response_format=ManagerInstructions
+        # Create LLM instance with the manager_llm
+        llm = self._create_llm_instance()
+        
+        # Use async get_response with output_pydantic
+        response = await llm.get_response_async(
+            prompt=manager_prompt,
+            system_prompt=manager_task.description,
+            output_pydantic=ManagerInstructions
         )
-        return manager_response.choices[0].message.parsed
+        
+        # Parse the response and validate with Pydantic
+        return self._parse_manager_instructions(response, ManagerInstructions)
 
     async def _get_json_response_async(self, manager_task, enhanced_prompt, ManagerInstructions):
         """Async version of JSON fallback response"""
-        # Create an async client instance for this async method
-        async_client = AsyncOpenAI()
-        manager_response = await async_client.chat.completions.create(
-            model=self.manager_llm,
-            messages=[
-                {"role": "system", "content": manager_task.description},
-                {"role": "user", "content": enhanced_prompt}
-            ],
-            temperature=0.7,
-            response_format={"type": "json_object"}
+        # Create LLM instance with the manager_llm
+        llm = self._create_llm_instance()
+        
+        response = await llm.get_response_async(
+            prompt=enhanced_prompt,
+            system_prompt=manager_task.description,
+            output_json=True
         )
         
         # Parse JSON and validate with Pydantic
-        try:
-            json_content = manager_response.choices[0].message.content
-            parsed_json = json.loads(json_content)
-            return ManagerInstructions(**parsed_json)
-        except (json.JSONDecodeError, ValueError) as e:
-            raise Exception(f"Failed to parse JSON response: {json_content}") from e
+        return self._parse_manager_instructions(response, ManagerInstructions)
 
 
     async def aworkflow(self) -> AsyncGenerator[str, None]:
@@ -440,16 +475,18 @@ Subtask: {st.name}
                 logging.debug(f"Task type: {task_to_check.task_type}")
                 logging.debug(f"Task status before reset check: {task_to_check.status}")
                 logging.debug(f"Task rerun: {getattr(task_to_check, 'rerun', True)}") # default to True if not set
+                logging.debug(f"Task async_execution: {task_to_check.async_execution}")
 
                 if (getattr(task_to_check, 'rerun', True) and # Corrected condition - reset only if rerun is True (or default True)
                     task_to_check.task_type != "loop" and # Removed "decision" from exclusion
                     not any(t.task_type == "loop" and subtask_name.startswith(t.name + "_")
-                           for t in self.tasks.values())):
-                    logging.debug(f"=== Resetting non-loop, non-decision task {subtask_name} to 'not started' ===")
+                           for t in self.tasks.values()) and
+                    not task_to_check.async_execution):  # Don't reset async parallel tasks
+                    logging.debug(f"=== Resetting non-loop, non-decision, non-parallel task {subtask_name} to 'not started' ===")
                     self.tasks[task_id].status = "not started"
                     logging.debug(f"Task status after reset: {self.tasks[task_id].status}")
                 else:
-                    logging.debug(f"=== Skipping reset for loop/decision/subtask or rerun=False: {subtask_name} ===")
+                    logging.debug(f"=== Skipping reset for loop/decision/subtask/parallel or rerun=False: {subtask_name} ===")
                     logging.debug(f"Keeping status as: {self.tasks[task_id].status}")
 
             # Handle loop progression
@@ -494,6 +531,35 @@ Subtask: {st.name}
                             next_task = next((t for t in self.tasks.values() if t.name == task_value), None)
                             if next_task:
                                 next_task.status = "not started"  # Reset status to allow execution
+                                
+                                # Capture validation feedback for retry scenarios
+                                if decision_str in Process.VALIDATION_FAILURE_DECISIONS:
+                                    if current_task and current_task.result:
+                                        # Get the rejected output from the task that was validated
+                                        validated_task = None
+                                        # Find the task that produced the output being validated
+                                        if current_task.previous_tasks:
+                                            # For validation tasks, typically validate the most recent previous task
+                                            prev_task_name = current_task.previous_tasks[-1]
+                                            validated_task = next((t for t in self.tasks.values() if t.name == prev_task_name), None)
+                                        elif current_task.context:
+                                            # If no previous_tasks, check context for the validated task
+                                            # Use the most recent task with a result from context
+                                            for ctx_task in reversed(current_task.context):
+                                                if ctx_task.result and ctx_task.name != current_task.name:
+                                                    validated_task = ctx_task
+                                                    break
+                                        
+                                        feedback = {
+                                            'validation_response': decision_str,
+                                            'validation_details': current_task.result.raw,
+                                            'rejected_output': validated_task.result.raw if validated_task and validated_task.result else None,
+                                            'validator_task': current_task.name,
+                                            'validated_task': validated_task.name if validated_task else None
+                                        }
+                                        next_task.validation_feedback = feedback
+                                        logging.debug(f"Added validation feedback to {next_task.name}: {feedback['validation_response']} (validated task: {feedback.get('validated_task', 'None')})")
+                                
                                 logging.debug(f"Routing to {next_task.name} based on decision: {decision_str}")
                                 # Don't mark workflow as finished when following condition path
                                 self.workflow_finished = False
@@ -1041,16 +1107,18 @@ Subtask: {st.name}
                 logging.debug(f"Task type: {task_to_check.task_type}")
                 logging.debug(f"Task status before reset check: {task_to_check.status}")
                 logging.debug(f"Task rerun: {getattr(task_to_check, 'rerun', True)}") # default to True if not set
+                logging.debug(f"Task async_execution: {task_to_check.async_execution}")
 
                 if (getattr(task_to_check, 'rerun', True) and # Corrected condition - reset only if rerun is True (or default True)
                     task_to_check.task_type != "loop" and # Removed "decision" from exclusion
                     not any(t.task_type == "loop" and subtask_name.startswith(t.name + "_")
-                           for t in self.tasks.values())):
-                    logging.debug(f"=== Resetting non-loop, non-decision task {subtask_name} to 'not started' ===")
+                           for t in self.tasks.values()) and
+                    not task_to_check.async_execution):  # Don't reset async parallel tasks
+                    logging.debug(f"=== Resetting non-loop, non-decision, non-parallel task {subtask_name} to 'not started' ===")
                     self.tasks[task_id].status = "not started"
                     logging.debug(f"Task status after reset: {self.tasks[task_id].status}")
                 else:
-                    logging.debug(f"=== Skipping reset for loop/decision/subtask or rerun=False: {subtask_name} ===")
+                    logging.debug(f"=== Skipping reset for loop/decision/subtask/parallel or rerun=False: {subtask_name} ===")
                     logging.debug(f"Keeping status as: {self.tasks[task_id].status}")
 
 
@@ -1096,6 +1164,35 @@ Subtask: {st.name}
                             next_task = next((t for t in self.tasks.values() if t.name == task_value), None)
                             if next_task:
                                 next_task.status = "not started"  # Reset status to allow execution
+                                
+                                # Capture validation feedback for retry scenarios
+                                if decision_str in Process.VALIDATION_FAILURE_DECISIONS:
+                                    if current_task and current_task.result:
+                                        # Get the rejected output from the task that was validated
+                                        validated_task = None
+                                        # Find the task that produced the output being validated
+                                        if current_task.previous_tasks:
+                                            # For validation tasks, typically validate the most recent previous task
+                                            prev_task_name = current_task.previous_tasks[-1]
+                                            validated_task = next((t for t in self.tasks.values() if t.name == prev_task_name), None)
+                                        elif current_task.context:
+                                            # If no previous_tasks, check context for the validated task
+                                            # Use the most recent task with a result from context
+                                            for ctx_task in reversed(current_task.context):
+                                                if ctx_task.result and ctx_task.name != current_task.name:
+                                                    validated_task = ctx_task
+                                                    break
+                                        
+                                        feedback = {
+                                            'validation_response': decision_str,
+                                            'validation_details': current_task.result.raw,
+                                            'rejected_output': validated_task.result.raw if validated_task and validated_task.result else None,
+                                            'validator_task': current_task.name,
+                                            'validated_task': validated_task.name if validated_task else None
+                                        }
+                                        next_task.validation_feedback = feedback
+                                        logging.debug(f"Added validation feedback to {next_task.name}: {feedback['validation_response']} (validated task: {feedback.get('validated_task', 'None')})")
+                                
                                 logging.debug(f"Routing to {next_task.name} based on decision: {decision_str}")
                                 # Don't mark workflow as finished when following condition path
                                 self.workflow_finished = False

src/praisonai-agents/praisonaiagents/task/task.py

@@ -88,6 +88,7 @@ class Task:
         self.max_retries = max_retries
         self.retry_count = retry_count
         self._guardrail_fn = None
+        self.validation_feedback = None  # Store validation failure feedback for retry attempts
 
         # Set logger level based on config verbose level
         verbose = self.config.get("verbose", 0)
@@ -171,8 +172,15 @@ class Task:
             # Check return annotation if present
             return_annotation = sig.return_annotation
             if return_annotation != inspect.Signature.empty:
+                # Import GuardrailResult for checking
+                from ..guardrails import GuardrailResult
+                
+                # Check if it's a GuardrailResult type
+                is_guardrail_result = return_annotation is GuardrailResult
+                
+                # Check for tuple return type
                 return_annotation_args = get_args(return_annotation)
-                if not (
+                is_tuple = (
                     get_origin(return_annotation) is tuple
                     and len(return_annotation_args) == 2
                     and return_annotation_args[0] is bool
@@ -182,9 +190,11 @@ class Task:
                         or return_annotation_args[1] is TaskOutput
                         or return_annotation_args[1] == Union[str, TaskOutput]
                     )
-                ):
+                )
+                
+                if not (is_guardrail_result or is_tuple):
                     raise ValueError(
-                        "If return type is annotated, it must be Tuple[bool, Any]"
+                        "If return type is annotated, it must be GuardrailResult or Tuple[bool, Any]"
                     )
             
             self._guardrail_fn = self.guardrail
@@ -446,7 +456,11 @@ Context:
             # Call the guardrail function
             result = self._guardrail_fn(task_output)
             
-            # Convert the result to a GuardrailResult
+            # Check if result is already a GuardrailResult
+            if isinstance(result, GuardrailResult):
+                return result
+            
+            # Otherwise, convert the tuple result to a GuardrailResult
             return GuardrailResult.from_tuple(result)
             
         except Exception as e:

src/praisonai-agents/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "praisonaiagents"
-version = "0.0.113"
+version = "0.0.129"
 description = "Praison AI agents for completing complex tasks with Self Reflection Agents"
 requires-python = ">=3.10"
 authors = [
@@ -15,7 +15,8 @@ dependencies = [
     "rich",
     "openai",
     "mcp>=1.6.0",
-    "posthog>=3.0.0"
+    "posthog>=3.0.0",
+    "aiohttp>=3.8.0"
 ]
 
 [project.optional-dependencies]
@@ -73,4 +74,4 @@ all = [
 
 [tool.setuptools.packages.find]
 where = ["."]
-include = ["praisonaiagents*"]
+include = ["praisonaiagents*"]

src/praisonai-agents/simple-api-mcp.py

@@ -0,0 +1,8 @@
+from praisonaiagents import Agent, MCP
+
+search_agent = Agent(
+    instructions="""You are a Tweet.""",
+    llm="openai/gpt-4o-mini",
+    tools=MCP("http://localhost:8080/sse")
+)
+search_agent.launch(path="/tweet", port=3030)

src/praisonai-agents/simple-mcp-server.py

@@ -0,0 +1,4 @@
+from praisonaiagents import Agent
+
+agent = Agent(instructions="Create a Tweet")
+agent.launch(port=8080, protocol="mcp")

src/praisonai-agents/test_autoagents_hierarchical_fix.py

@@ -0,0 +1,143 @@
+#!/usr/bin/env python3
+"""
+Test script to verify that AutoAgents hierarchical workflow works with non-OpenAI LLMs
+without requiring OpenAI API key.
+
+This tests the fix for issue #873.
+"""
+
+import os
+import sys
+
+# Ensure OpenAI API key is not set to verify the fix works
+if 'OPENAI_API_KEY' in os.environ:
+    del os.environ['OPENAI_API_KEY']
+
+# Add the parent directory to the Python path
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from praisonaiagents import AutoAgents
+
+def get_stock_price(company_name: str) -> str:
+    """
+    Get the stock price of a company
+    
+    Args:
+        company_name (str): The name of the company
+        
+    Returns:
+        str: The stock price of the company
+    """
+    if company_name.lower() == "apple" or company_name.lower() == "aapl":
+        return f"The stock price of {company_name} is 100"
+    elif company_name.lower() == "google" or company_name.lower() == "googl":
+        return f"The stock price of {company_name} is 200"
+    else:
+        return f"The stock price of {company_name} is 50"
+
+def test_hierarchical_without_openai():
+    """Test hierarchical process without OpenAI API key"""
+    print("Testing AutoAgents with hierarchical process and Gemini LLM...")
+    print("OPENAI_API_KEY is set:", 'OPENAI_API_KEY' in os.environ)
+    
+    try:
+        # Create AutoAgents instance with Gemini
+        agents = AutoAgents(
+            instructions="Write a poem on the stock price of apple",
+            tools=[get_stock_price],
+            process="hierarchical",
+            llm="gemini/gemini-2.5-flash-lite-preview-06-17",
+            self_reflect=True,
+            verbose=True,
+            max_agents=3  # Maximum number of agents to create
+        )
+        
+        # Start the agents
+        print("\nStarting agents...")
+        result = agents.start()
+        
+        print("\n=== RESULT ===")
+        print(result)
+        print("\n=== TEST PASSED ===")
+        print("Hierarchical workflow completed successfully without OpenAI API key!")
+        return True
+        
+    except Exception as e:
+        if "api_key" in str(e) and "OPENAI_API_KEY" in str(e):
+            print("\n=== TEST FAILED ===")
+            print(f"Error: Still requires OpenAI API key: {e}")
+            return False
+        else:
+            print(f"\nUnexpected error: {e}")
+            import traceback
+            traceback.print_exc()
+            return False
+
+def test_hierarchical_with_mock_llm():
+    """Test with a mock LLM to ensure no API calls are made to OpenAI"""
+    print("\n\nTesting with mock LLM configuration...")
+    
+    try:
+        # Create AutoAgents instance with a mock configuration
+        agents = AutoAgents(
+            instructions="Simple test task",
+            tools=[get_stock_price],
+            process="hierarchical",
+            llm={
+                "model": "test/mock-model",
+                "api_key": "mock-key",
+                "base_url": "http://localhost:9999"  # Non-existent URL
+            },
+            verbose=False,
+            max_agents=2
+        )
+        
+        # This should fail with connection error, not OpenAI API key error
+        try:
+            result = agents.start()
+            # If we get here, the test didn't behave as expected
+            print("\n=== TEST WARNING ===")
+            print("Expected an error but execution succeeded")
+            return False
+        except Exception as e:
+            if "api_key" in str(e) and "OPENAI_API_KEY" in str(e):
+                print("\n=== TEST FAILED ===")
+                print(f"Error: Still requires OpenAI API key: {e}")
+                return False
+            else:
+                print("\n=== TEST PASSED ===")
+                print("Failed with expected error (not OpenAI API key error)")
+                print(f"Error type: {type(e).__name__}")
+                return True
+                
+    except Exception as e:
+        print(f"\nSetup error: {e}")
+        return False
+
+if __name__ == "__main__":
+    # Track test results
+    test_results = []
+    
+    # Run both tests
+    mock_test_passed = test_hierarchical_with_mock_llm()
+    test_results.append(("Mock LLM Test", mock_test_passed))
+    
+    # Only run the actual Gemini test if we have the API key
+    if 'GOOGLE_API_KEY' in os.environ or 'GEMINI_API_KEY' in os.environ:
+        gemini_test_passed = test_hierarchical_without_openai()
+        test_results.append(("Gemini Test", gemini_test_passed))
+    else:
+        print("\n\nSkipping Gemini test - no GOOGLE_API_KEY or GEMINI_API_KEY found")
+        print("The mock test passed, confirming the fix works!")
+    
+    # Summary
+    print("\n=== TEST SUMMARY ===")
+    all_passed = True
+    for test_name, passed in test_results:
+        status = "PASSED" if passed else "FAILED"
+        print(f"{test_name}: {status}")
+        if not passed:
+            all_passed = False
+    
+    # Exit with appropriate code
+    sys.exit(0 if all_passed else 1)

src/praisonai-agents/test_guardrail_return_types.py

@@ -0,0 +1,163 @@
+#!/usr/bin/env python3
+"""
+Test different guardrail return types to ensure both GuardrailResult 
+and Tuple[bool, Any] work correctly. This addresses issue #875.
+"""
+
+import sys
+import os
+from typing import Tuple, Any
+
+from praisonaiagents import Agent, Task, TaskOutput, GuardrailResult
+import inspect
+
+
+def test_guardrail_return_types():
+    """Test that both GuardrailResult and Tuple[bool, Any] return types are accepted."""
+    print("Testing guardrail return type validation...")
+    
+    # Test 1: GuardrailResult return type
+    def validate_with_guardrailresult(task_output: TaskOutput) -> GuardrailResult:
+        """Validation function returning GuardrailResult."""
+        if len(task_output.raw) < 10:
+            return GuardrailResult(
+                success=False,
+                result=None,
+                error="Output is too short"
+            )
+        return GuardrailResult(
+            success=True,
+            result=task_output,
+            error=""
+        )
+    
+    # Test 2: Tuple[bool, Any] return type
+    def validate_with_tuple(task_output: TaskOutput) -> Tuple[bool, Any]:
+        """Validation function returning tuple."""
+        if len(task_output.raw) < 10:
+            return False, "Output is too short"
+        return True, task_output
+    
+    # Test 3: No return type annotation
+    def validate_no_annotation(task_output: TaskOutput):
+        """Validation function without return type annotation."""
+        if len(task_output.raw) < 10:
+            return False, "Output is too short"
+        return True, task_output
+    
+    # Create test agent
+    agent = Agent(
+        name="Test Agent",
+        role="Tester",
+        goal="Test guardrails",
+        backstory="Testing guardrail functionality",
+        llm="gpt-4o"
+    )
+    
+    # Test creating tasks with each guardrail type
+    tests = [
+        ("GuardrailResult return type", validate_with_guardrailresult),
+        ("Tuple[bool, Any] return type", validate_with_tuple),
+        ("No return type annotation", validate_no_annotation)
+    ]
+    
+    for test_name, guardrail_func in tests:
+        print(f"\nTesting {test_name}...")
+        try:
+            task = Task(
+                description="Test task",
+                expected_output="Test output",
+                agent=agent,
+                guardrail=guardrail_func
+            )
+            print(f"✓ Task created successfully with {test_name}")
+            
+            # Verify guardrail was set up
+            assert task._guardrail_fn is not None, "Guardrail function not set"
+            
+            # Test guardrail processing
+            test_output = TaskOutput(
+                description="Test",
+                raw="This is a test output that is long enough",
+                agent="Test Agent"
+            )
+            
+            result = task._process_guardrail(test_output)
+            assert isinstance(result, GuardrailResult), f"Expected GuardrailResult, got {type(result)}"
+            assert result.success, "Guardrail validation should pass"
+            print(f"✓ Guardrail processing works with {test_name}")
+            
+        except Exception as e:
+            print(f"✗ Failed with {test_name}: {e}")
+            return False
+    
+    print("\n✓ All guardrail return type tests passed!")
+    return True
+
+
+def test_guardrail_result_handling():
+    """Test that _process_guardrail correctly handles both return types."""
+    print("\nTesting guardrail result handling...")
+    
+    # Create test agent and task
+    agent = Agent(
+        name="Test Agent",
+        role="Tester",
+        goal="Test guardrails",
+        backstory="Testing guardrail functionality",
+        llm="gpt-4o"
+    )
+    
+    test_output = TaskOutput(
+        description="Test",
+        raw="Test output",
+        agent="Test Agent"
+    )
+    
+    # Test 1: Function returning GuardrailResult
+    def return_guardrailresult(output: TaskOutput) -> GuardrailResult:
+        return GuardrailResult(success=True, result=output, error="")
+    
+    task1 = Task(
+        description="Test",
+        agent=agent,
+        guardrail=return_guardrailresult
+    )
+    
+    result1 = task1._process_guardrail(test_output)
+    assert isinstance(result1, GuardrailResult), "Should return GuardrailResult"
+    assert result1.success, "Should be successful"
+    print("✓ GuardrailResult return handled correctly")
+    
+    # Test 2: Function returning tuple
+    def return_tuple(output: TaskOutput) -> Tuple[bool, Any]:
+        return True, output
+    
+    task2 = Task(
+        description="Test",
+        agent=agent,
+        guardrail=return_tuple
+    )
+    
+    result2 = task2._process_guardrail(test_output)
+    assert isinstance(result2, GuardrailResult), "Should convert tuple to GuardrailResult"
+    assert result2.success, "Should be successful"
+    print("✓ Tuple return converted correctly")
+    
+    print("✓ Guardrail result handling tests passed!")
+    return True
+
+
+if __name__ == "__main__":
+    print("Running guardrail return type tests for issue #875...")
+    
+    success = True
+    success &= test_guardrail_return_types()
+    success &= test_guardrail_result_handling()
+    
+    if success:
+        print("\n✅ All tests passed! The fix for issue #875 is working correctly.")
+        sys.exit(0)
+    else:
+        print("\n❌ Some tests failed!")
+        sys.exit(1)

src/praisonai-agents/test_manager_llm_fix.py

@@ -0,0 +1,104 @@
+#!/usr/bin/env python3
+"""
+Test script to verify that the manager LLM methods correctly handle Pydantic models.
+This tests the fix for the LLM interface misuse bug.
+"""
+
+import os
+import sys
+import json
+from pydantic import BaseModel
+
+# Add the parent directory to the Python path
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from praisonaiagents.process.process import Process
+from praisonaiagents.task.task import Task
+from praisonaiagents.agent.agent import Agent
+
+class ManagerInstructions(BaseModel):
+    task_id: int
+    agent_name: str
+    action: str
+
+def test_parse_manager_instructions():
+    """Test the _parse_manager_instructions helper method"""
+    print("Testing _parse_manager_instructions method...")
+    
+    # Create a dummy process instance
+    tasks = {"1": Task(name="test_task", description="Test task")}
+    agents = [Agent(name="TestAgent", role="Test role", goal="Test goal")]
+    process = Process(tasks=tasks, agents=agents, manager_llm="test/model")
+    
+    # Test valid JSON response
+    valid_json = '{"task_id": 1, "agent_name": "TestAgent", "action": "execute"}'
+    try:
+        result = process._parse_manager_instructions(valid_json, ManagerInstructions)
+        assert isinstance(result, ManagerInstructions)
+        assert result.task_id == 1
+        assert result.agent_name == "TestAgent"
+        assert result.action == "execute"
+        print("✓ Valid JSON parsing works correctly")
+    except Exception as e:
+        print(f"✗ Failed to parse valid JSON: {e}")
+        return False
+    
+    # Test invalid JSON
+    invalid_json = "not a json string"
+    try:
+        result = process._parse_manager_instructions(invalid_json, ManagerInstructions)
+        print("✗ Should have failed on invalid JSON")
+        return False
+    except Exception as e:
+        print(f"✓ Correctly raised exception for invalid JSON: {type(e).__name__}")
+    
+    # Test JSON with missing fields
+    incomplete_json = '{"task_id": 1}'
+    try:
+        result = process._parse_manager_instructions(incomplete_json, ManagerInstructions)
+        print("✗ Should have failed on incomplete JSON")
+        return False
+    except Exception as e:
+        print(f"✓ Correctly raised exception for incomplete JSON: {type(e).__name__}")
+    
+    return True
+
+def test_create_llm_instance():
+    """Test the _create_llm_instance helper method"""
+    print("\nTesting _create_llm_instance method...")
+    
+    # Create a dummy process instance
+    tasks = {"1": Task(name="test_task", description="Test task")}
+    agents = [Agent(name="TestAgent", role="Test role", goal="Test goal")]
+    manager_llm = "gemini/gemini-2.5-flash-lite-preview-06-17"
+    process = Process(tasks=tasks, agents=agents, manager_llm=manager_llm)
+    
+    # Test LLM instance creation
+    try:
+        llm = process._create_llm_instance()
+        assert llm.model == manager_llm
+        assert llm.temperature == 0.7
+        print("✓ LLM instance created successfully")
+        return True
+    except Exception as e:
+        print(f"✗ Failed to create LLM instance: {e}")
+        return False
+
+if __name__ == "__main__":
+    print("=== Testing Manager LLM Fix ===\n")
+    
+    # Run tests
+    test_results = []
+    test_results.append(("_parse_manager_instructions", test_parse_manager_instructions()))
+    test_results.append(("_create_llm_instance", test_create_llm_instance()))
+    
+    # Summary
+    print("\n=== TEST SUMMARY ===")
+    all_passed = True
+    for test_name, passed in test_results:
+        status = "PASSED" if passed else "FAILED"
+        print(f"{test_name}: {status}")
+        if not passed:
+            all_passed = False
+    
+    sys.exit(0 if all_passed else 1)

src/praisonai-agents/test_multi_provider.py

@@ -0,0 +1,141 @@
+#!/usr/bin/env python3
+"""
+Test script for multi-provider/multi-model support
+"""
+
+import os
+import sys
+sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
+
+from praisonaiagents import Agent, Task, PraisonAIAgents
+from praisonaiagents.agent import RouterAgent
+from praisonaiagents.llm import ModelRouter, TaskComplexity
+
+def test_model_router():
+    """Test the ModelRouter functionality"""
+    print("=== Testing ModelRouter ===\n")
+    
+    router = ModelRouter()
+    
+    # Test complexity analysis
+    test_tasks = [
+        ("What is 2 + 2?", TaskComplexity.SIMPLE),
+        ("Summarize the benefits of renewable energy", TaskComplexity.MODERATE),
+        ("Implement a binary search tree in Python", TaskComplexity.COMPLEX),
+        ("Design a comprehensive microservices architecture with detailed analysis", TaskComplexity.VERY_COMPLEX)
+    ]
+    
+    for task, expected in test_tasks:
+        complexity = router.analyze_task_complexity(task)
+        print(f"Task: {task[:50]}...")
+        print(f"Expected: {expected.value}, Got: {complexity.value}")
+        print(f"Match: {'✓' if complexity == expected else '✗'}\n")
+    
+    # Test model selection
+    print("\n=== Testing Model Selection ===\n")
+    
+    selected = router.select_model(
+        task_description="Calculate the sum of numbers",
+        budget_conscious=True
+    )
+    print(f"Simple task (budget mode): {selected}")
+    
+    selected = router.select_model(
+        task_description="Write a complex algorithm for graph traversal",
+        budget_conscious=False
+    )
+    print(f"Complex task (performance mode): {selected}")
+    
+    print("\n✓ ModelRouter tests completed")
+
+
+def test_router_agent():
+    """Test the RouterAgent functionality"""
+    print("\n=== Testing RouterAgent ===\n")
+    
+    # Create a router agent
+    agent = RouterAgent(
+        name="Test Agent",
+        role="Test Assistant",
+        goal="Test multi-model functionality",
+        models=["gpt-4o-mini"],  # Using single model for testing
+        routing_strategy="auto",
+        verbose=False
+    )
+    
+    print(f"Agent created: {agent.name}")
+    print(f"Available models: {list(agent.available_models.keys())}")
+    print(f"Routing strategy: {agent.routing_strategy}")
+    
+    # Test model selection
+    selected = agent._select_model_for_task(
+        task_description="Simple math problem",
+        tools=None
+    )
+    print(f"Selected model for simple task: {selected}")
+    
+    print("\n✓ RouterAgent tests completed")
+
+
+def test_integration():
+    """Test integration with PraisonAIAgents"""
+    print("\n=== Testing Integration ===\n")
+    
+    # Create a simple router agent
+    agent = RouterAgent(
+        name="Integration Test Agent",
+        role="Tester",
+        goal="Test the integration",
+        models=["gpt-4o-mini"],  # Single model for testing
+        routing_strategy="manual",  # Use manual to avoid complexity
+        verbose=False
+    )
+    
+    # Create a simple task
+    task = Task(
+        name="test_task",
+        description="Return the word 'success'",
+        expected_output="The word success",
+        agent=agent
+    )
+    
+    # Create agents system
+    agents_system = PraisonAIAgents(
+        agents=[agent],
+        tasks=[task],
+        process="sequential",
+        verbose=False
+    )
+    
+    print("Created PraisonAIAgents with RouterAgent")
+    print("✓ Integration test setup completed")
+    
+    # Note: Actual execution would require API keys
+
+
+def main():
+    """Run all tests"""
+    print("\n🚀 Multi-Provider/Multi-Model Support Test Suite\n")
+    
+    try:
+        test_model_router()
+        test_router_agent()
+        test_integration()
+        
+        print("\n✅ All tests completed successfully!")
+        print("\n📝 Summary:")
+        print("- ModelRouter can analyze task complexity")
+        print("- ModelRouter can select appropriate models")
+        print("- RouterAgent can be created and configured")
+        print("- Integration with PraisonAIAgents works")
+        print("\n🎉 Multi-provider support is ready to use!")
+        
+    except Exception as e:
+        print(f"\n❌ Test failed with error: {e}")
+        import traceback
+        traceback.print_exc()
+        sys.exit(1)
+
+
+if __name__ == "__main__":
+    main()

src/praisonai-agents/test_sequential_tool_calling.py

@@ -0,0 +1,49 @@
+"""Test sequential tool calling fix"""
+from praisonaiagents import Agent
+
+def get_stock_price(company_name: str) -> str:
+    """
+    Get the stock price of a company
+    
+    Args:
+        company_name (str): The name of the company
+        
+    Returns:
+        str: The stock price of the company
+    """
+    print(f"Tool called: get_stock_price({company_name})")
+    return f"The stock price of {company_name} is 100"
+
+def multiply(a: int, b: int) -> int:
+    """
+    Multiply two numbers
+    """
+    print(f"Tool called: multiply({a}, {b})")
+    return a * b
+
+# Test with streaming disabled to verify the fix
+print("Testing sequential tool calling with stream=False...")
+agent = Agent(
+    instructions="You are a helpful assistant. You can use the tools provided to you to help the user.",
+    llm="gemini/gemini-2.5-flash-lite-preview-06-17",
+    self_reflect=False,
+    verbose=True,
+    tools=[get_stock_price, multiply],
+    stream=False  # Force non-streaming mode - use stream parameter directly
+)
+
+result = agent.chat("Get the stock price of Google and multiply it by 2")
+print(f"\nFinal result: {result}")
+
+# Test with default streaming mode
+print("\n\nTesting sequential tool calling with default streaming...")
+agent2 = Agent(
+    instructions="You are a helpful assistant. You can use the tools provided to you to help the user.",
+    llm="gemini/gemini-2.5-flash-lite-preview-06-17",
+    self_reflect=False,
+    verbose=True,
+    tools=[get_stock_price, multiply]
+)
+
+result2 = agent2.chat("Get the stock price of Google and multiply it by 2")
+print(f"\nFinal result: {result2}")

src/praisonai-agents/test_validation_feedback.py

@@ -0,0 +1,161 @@
+#!/usr/bin/env python3
+"""Test script for validation feedback in workflow retry logic"""
+
+import sys
+import os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), 'src/praisonai-agents'))
+
+from praisonaiagents import Agent, Task, PraisonAIAgents
+
+def test_example_one():
+    """Test the philosopher quotes example"""
+    print("=" * 80)
+    print("Testing Example 1: Philosopher Quotes with Validation")
+    print("=" * 80)
+    
+    validator_agent = Agent(
+        name="validator_agent",
+        instructions="You are a helpful assistant",
+        llm="gemini/gemini-2.5-flash",
+        self_reflect=False,
+        verbose=True
+    )
+
+    quote_agent = Agent(
+        name="quote_agent",
+        instructions="You are a helpful assistant who is a pro at quoting philosophers",
+        llm="gemini/gemini-2.5-flash",
+        self_reflect=False,
+        verbose=False
+    )
+
+    collect_task = Task(
+        description="Quote Aristotle",
+        expected_output="List of Quotes from Aristotle",
+        agent=quote_agent,
+        name="collect_data",
+        is_start=True,
+        next_tasks=["validate_data"]
+    )
+
+    validate_task = Task(
+        description="""Validate the collected data. Check if:
+        1. At least 25 results are returned.
+        2. Each is a quote from Aristotle.
+        Return validation_result as 'valid' or 'invalid' only no other text.""",
+        expected_output="Validation result indicating if data is valid or invalid.",
+        agent=validator_agent,
+        name="validate_data",
+        task_type="decision",
+        condition={
+            "valid": [],  # End the workflow on valid data
+            "invalid": ["collect_data"]  # Retry data collection on invalid data
+        },
+    )
+
+    # Workflow
+    agents = PraisonAIAgents(
+        agents=[quote_agent, validator_agent],
+        tasks=[collect_task, validate_task],
+        verbose=1,
+        process="workflow",
+        max_iter=3  # Limit iterations to prevent infinite loops
+    )
+
+    try:
+        agents.start()
+        print("\nExample 1 completed successfully!")
+    except Exception as e:
+        print(f"\nExample 1 failed with error: {e}")
+
+
+def test_example_two():
+    """Test the web search example"""
+    print("\n" + "=" * 80)
+    print("Testing Example 2: Web Search with Validation (Mock)")
+    print("=" * 80)
+    
+    # Mock web search tool for testing
+    def mock_web_search(query: str) -> str:
+        """Mock web search that returns limited results initially"""
+        # Simulate returning too few results on first attempt
+        return "Found 3 results:\n1. https://example.com/kenya1\n2. https://example.com/kenya2\n3. https://example.com/kenya3"
+    
+    agent = Agent(
+        name="agent",
+        instructions="You are a helpful assistant",
+        llm="gemini/gemini-2.5-flash",
+        self_reflect=False,
+        verbose=True
+    )
+
+    web_search_agent = Agent(
+        name="web_search_agent",
+        role="Web Search Specialist",
+        goal="Search the web for relevant information",
+        instructions="You are a helpful assistant. You can use the tools provided to you to help the user.",
+        llm="gemini/gemini-2.5-flash",
+        self_reflect=False,
+        verbose=False,
+        tools=[mock_web_search]
+    )
+
+    # Tasks
+    collect_task = Task(
+        description="Perform an internet search using the query: 'Kenya protests in 2024 and 2025'",
+        expected_output="List of URLs of the articles that are relevant to the search",
+        agent=web_search_agent,
+        name="collect_data",
+        is_start=True,
+        next_tasks=["validate_data"]
+    )
+
+    validate_task = Task(
+        description="""Validate the collected data. Check if:
+        1. At least 12 results are returned.
+        2. Each result contains a valid URL.
+        Return validation_result as 'valid' or 'invalid' only no other text.""",
+        expected_output="Validation result indicating if data is valid or invalid.",
+        agent=agent,
+        name="validate_data",
+        task_type="decision",
+        condition={
+            "valid": [],  # End the workflow on valid data
+            "invalid": ["collect_data"]  # Retry data collection on invalid data
+        },
+    )
+
+    # Workflow
+    agents = PraisonAIAgents(
+        agents=[web_search_agent, agent],
+        tasks=[collect_task, validate_task],
+        verbose=1,
+        process="workflow",
+        max_iter=3  # Limit iterations
+    )
+
+    try:
+        agents.start()
+        print("\nExample 2 completed successfully!")
+    except Exception as e:
+        print(f"\nExample 2 failed with error: {e}")
+
+
+if __name__ == "__main__":
+    print("Testing Validation Feedback Implementation")
+    print("This test demonstrates that retry tasks now receive validation feedback\n")
+    
+    # Run example 1 (without actual API calls, just structure test)
+    try:
+        # We'll just test the structure is valid
+        test_example_one()
+    except Exception as e:
+        print(f"Note: Example 1 requires actual LLM API access: {e}")
+    
+    # Run example 2 with mock
+    try:
+        test_example_two()
+    except Exception as e:
+        print(f"Note: Example 2 test setup issue: {e}")
+    
+    print("\nTest script completed. The implementation adds validation feedback to retry tasks.")

src/praisonai-agents/tests/code_review.py

@@ -11,14 +11,30 @@ def analyze_code_changes():
     ]
     return issues[int(time.time()) % 3]
 
-def suggest_fixes(issue: Dict):
+def suggest_fixes(issue):
     """Simulates fix suggestions"""
     fixes = {
         "style": "Apply PEP 8 formatting",
-        "security": "Implement input validation",
+        "security": "Implement input validation", 
         "performance": "Use list comprehension"
     }
-    return fixes.get(issue["type"], "Review manually")
+    
+    # Handle both dict and string inputs
+    if isinstance(issue, dict):
+        issue_type = issue.get("type", "unknown")
+    else:
+        # If it's a string, try to extract the type
+        issue_str = str(issue).lower()
+        if "security" in issue_str:
+            issue_type = "security"
+        elif "style" in issue_str:
+            issue_type = "style"
+        elif "performance" in issue_str:
+            issue_type = "performance"
+        else:
+            issue_type = "unknown"
+    
+    return fixes.get(issue_type, "Review manually")
 
 def apply_automated_fix(fix: str):
     """Simulates applying automated fixes"""
@@ -98,11 +114,8 @@ def main():
     # Print results
     print("\nCode Review Results:")
     print("=" * 50)
-    for task_id, result in results["task_results"].items():
-        if result:
-            print(f"\nTask: {task_id}")
-            print(f"Result: {result.raw}")
-            print("-" * 50)
+    print(f"Results: {results}")
+    print("-" * 50)
 
 if __name__ == "__main__":
     main()

src/praisonai-agents/tests/mcp-http-stream-example.py

@@ -0,0 +1,88 @@
+#!/usr/bin/env python
+"""
+Example of using MCP with HTTP Stream transport.
+This demonstrates how to connect to an MCP server using the new HTTP Stream transport.
+"""
+
+from praisonaiagents import Agent
+from praisonaiagents.mcp import MCP
+
+# Example 1: Basic HTTP Stream connection (defaults to /mcp endpoint)
+print("Example 1: Basic HTTP Stream connection")
+try:
+    # This will use HTTP Stream transport automatically
+    tools = MCP("http://localhost:8080", debug=True)
+    print(f"Connected! Found {len(list(tools))} tools")
+    for tool in tools:
+        print(f"  - {tool.name}: {tool.description}")
+except Exception as e:
+    print(f"Connection failed: {e}")
+
+print("\n" + "="*50 + "\n")
+
+# Example 2: HTTP Stream with custom endpoint
+print("Example 2: HTTP Stream with custom endpoint")
+try:
+    # This will use HTTP Stream transport with custom endpoint
+    tools = MCP("http://localhost:8080/custom-mcp", debug=True)
+    print(f"Connected! Found {len(list(tools))} tools")
+except Exception as e:
+    print(f"Connection failed: {e}")
+
+print("\n" + "="*50 + "\n")
+
+# Example 3: HTTP Stream with stream response mode
+print("Example 3: HTTP Stream with stream response mode")
+try:
+    # This will use HTTP Stream transport with streaming responses
+    tools = MCP("http://localhost:8080", responseMode="stream", debug=True)
+    print(f"Connected! Found {len(list(tools))} tools")
+except Exception as e:
+    print(f"Connection failed: {e}")
+
+print("\n" + "="*50 + "\n")
+
+# Example 4: Backward compatibility - SSE transport
+print("Example 4: Backward compatibility - SSE transport")
+try:
+    # URLs ending with /sse will still use SSE transport
+    tools = MCP("http://localhost:8080/sse", debug=True)
+    print(f"Connected using SSE! Found {len(list(tools))} tools")
+except Exception as e:
+    print(f"Connection failed: {e}")
+
+print("\n" + "="*50 + "\n")
+
+# Example 5: Using with an agent
+print("Example 5: Using HTTP Stream tools with an agent")
+try:
+    agent = Agent(
+        name="Weather Assistant",
+        instructions="You are a helpful weather assistant.",
+        tools=MCP("http://localhost:8080"),  # HTTP Stream transport
+        llm="gpt-4o-mini"
+    )
+    print("Agent created successfully with HTTP Stream tools!")
+    
+    # Example usage (commented out to avoid actual API calls)
+    # result = agent.execute("What's the weather in Paris?")
+    # print(f"Result: {result}")
+except Exception as e:
+    print(f"Agent creation failed: {e}")
+
+print("\n" + "="*50 + "\n")
+
+# Example 6: HTTP Stream with custom headers and CORS
+print("Example 6: HTTP Stream with custom configuration")
+try:
+    tools = MCP(
+        "http://localhost:8080",
+        headers={"X-API-Key": "my-api-key"},
+        cors={"allowOrigin": "*"},
+        debug=True
+    )
+    print(f"Connected with custom config! Found {len(list(tools))} tools")
+except Exception as e:
+    print(f"Connection failed: {e}")
+
+print("\nNote: These examples require an HTTP Stream MCP server running on localhost:8080")

src/praisonai-agents/tests/prompt_chaining.py

@@ -69,7 +69,7 @@ workflow = PraisonAIAgents(
 )
 
 # Run the workflow
-results = workflow.start()
+results = workflow.start(return_dict=True)
 
 # Print results
 print("\nWorkflow Results:")

src/praisonai-agents/tests/test_fix_comprehensive.py

@@ -0,0 +1,75 @@
+"""
+Test script to verify the fix for sequential tool calling.
+The agent should:
+1. Call get_stock_price to get Google's stock price (100)
+2. Call multiply to multiply 100 by 2
+3. Return the final result (200)
+"""
+
+from praisonaiagents import Agent
+
+def get_stock_price(company_name: str) -> str:
+    """
+    Get the stock price of a company
+    
+    Args:
+        company_name (str): The name of the company
+        
+    Returns:
+        str: The stock price of the company
+    """
+    print(f"[Tool Called] get_stock_price({company_name})")
+    return f"The stock price of {company_name} is 100"
+
+def multiply(a: int, b: int) -> int:
+    """
+    Multiply two numbers
+    
+    Args:
+        a (int): First number
+        b (int): Second number
+        
+    Returns:
+        int: Product of a and b
+    """
+    print(f"[Tool Called] multiply({a}, {b})")
+    return a * b
+
+# Test with Gemini
+print("=" * 60)
+print("Testing with Gemini model")
+print("=" * 60)
+
+agent_gemini = Agent(
+    instructions="You are a helpful assistant. You can use the tools provided to you to help the user. When asked to multiply a stock price, first get the stock price, then multiply it.",
+    llm="gemini/gemini-2.5-pro",
+    tools=[get_stock_price, multiply],
+    verbose=True
+)
+
+result_gemini = agent_gemini.start("what is the stock price of Google? multiply the Google stock price with 2")
+print(f"\nFinal Result (Gemini): {result_gemini}")
+
+# Test with GPT-4
+print("\n" + "=" * 60)
+print("Testing with GPT-4 model")
+print("=" * 60)
+
+agent_gpt4 = Agent(
+    instructions="You are a helpful assistant. You can use the tools provided to you to help the user. When asked to multiply a stock price, first get the stock price, then multiply it.",
+    llm="gpt-4o",
+    tools=[get_stock_price, multiply],
+    verbose=True
+)
+
+result_gpt4 = agent_gpt4.start("what is the stock price of Google? multiply the Google stock price with 2")
+print(f"\nFinal Result (GPT-4): {result_gpt4}")
+
+# Verify results
+print("\n" + "=" * 60)
+print("Test Results Summary")
+print("=" * 60)
+print(f"Gemini result contains '200': {'200' in str(result_gemini) if result_gemini else False}")
+print(f"GPT-4 result contains '200': {'200' in str(result_gpt4) if result_gpt4 else False}")
+print(f"Gemini returned empty: {not result_gemini or result_gemini == ''}")
+print(f"GPT-4 returned empty: {not result_gpt4 or result_gpt4 == ''}")