Update frontend build based on commit 8e5535157f

.dockerignore

@@ -23,16 +23,6 @@
 # Frontend
 !frontend/build/web/
 
-# rnd
-!rnd/
-
 # Explicitly re-ignore some folders
 .*
 **/__pycache__
-# rnd
-rnd/autogpt_builder/.next/
-rnd/autogpt_builder/node_modules
-rnd/autogpt_builder/.env.example
-rnd/autogpt_builder/.env.local
-rnd/autogpt_server/.env
-rnd/autogpt_server/.venv/

.gitattributes

@@ -3,8 +3,3 @@ frontend/build/** linguist-generated
 **/poetry.lock linguist-generated
 
 docs/_javascript/** linguist-vendored
-
-# Exclude VCR cassettes from stats
-forge/tests/vcr_cassettes/**/**.y*ml linguist-generated
-
-* text=auto

.github/CODEOWNERS

@@ -1,7 +1,5 @@
-* @Significant-Gravitas/maintainers
-.github/workflows/ @Significant-Gravitas/devops
-forge/ @Significant-Gravitas/forge-maintainers
-benchmark/ @Significant-Gravitas/benchmark-maintainers
-frontend/ @Significant-Gravitas/frontend-maintainers
-rnd/infra @Significant-Gravitas/devops
-.github/CODEOWNERS @Significant-Gravitas/admins
+.github/workflows/  @Significant-Gravitas/devops
+autogpt/   @Significant-Gravitas/maintainers
+forge/     @Significant-Gravitas/forge-maintainers
+benchmark/          @Significant-Gravitas/benchmark-maintainers
+frontend/           @Significant-Gravitas/frontend-maintainers

.github/ISSUE_TEMPLATE/1.bug.yml

@@ -16,7 +16,7 @@ body:
         [discussions]: https://github.com/Significant-Gravitas/AutoGPT/discussions
         [#tech-support]: https://discord.com/channels/1092243196446249134/1092275629602394184
         [existing issues]: https://github.com/Significant-Gravitas/AutoGPT/issues?q=is%3Aissue
-        [wiki page on Contributing]: https://github.com/Significant-Gravitas/AutoGPT/wiki/Contributing
+        [wiki page on Contributing]: https://github.com/Significant-Gravitas/Nexus/wiki/Contributing
 
   - type: checkboxes
     attributes:
@@ -88,16 +88,14 @@ body:
 
   - type: dropdown
     attributes:
-      label: What LLM Provider do you use?
+      label: Do you use OpenAI GPT-3 or GPT-4?
       description: >
         If you are using AutoGPT with `SMART_LLM=gpt-3.5-turbo`, your problems may be caused by
         the [limitations](https://github.com/Significant-Gravitas/AutoGPT/issues?q=is%3Aissue+label%3A%22AI+model+limitation%22) of GPT-3.5.
       options:
-        - Azure
-        - Groq
-        - Anthropic
-        - Llamafile
-        - Other (detail in issue)
+        - GPT-3.5
+        - GPT-4
+        - GPT-4(32k)
     validations:
       required: true
 
@@ -128,13 +126,6 @@ body:
             label: Specify the area
             description: Please specify the area you think is best related to the issue.
 
-  - type: input
-    attributes:
-      label: What commit or version are you using?
-      description: It is helpful for us to reproduce to know what version of the software you were using when this happened. Please run `git log -n 1 --pretty=format:"%H"` to output the full commit hash.
-    validations:
-      required: true
-
   - type: textarea
     attributes:
       label: Describe your issue.

.github/ISSUE_TEMPLATE/2.feature.yml

@@ -5,7 +5,7 @@ body:
   - type: markdown
     attributes:
       value: |
-        First, check out our [wiki page on Contributing](https://github.com/Significant-Gravitas/AutoGPT/wiki/Contributing)
+        First, check out our [wiki page on Contributing](https://github.com/Significant-Gravitas/Nexus/wiki/Contributing)
         Please provide a searchable summary of the issue in the title above ⬆️.
   - type: checkboxes
     attributes:

.github/PULL_REQUEST_TEMPLATE.md

@@ -10,7 +10,7 @@
 
 <!--
 Check out our contribution guide:
-https://github.com/Significant-Gravitas/AutoGPT/wiki/Contributing
+https://github.com/Significant-Gravitas/Nexus/wiki/Contributing
 
 1. Avoid duplicate work, issues, PRs etc.
 2. Also consider contributing something other than code; see the [contribution guide]

.github/labeler.yml

@@ -17,11 +17,3 @@ Frontend:
 documentation:
 - changed-files:
   - any-glob-to-any-file: docs/**
-
-Builder:
-- changed-files:
-  - any-glob-to-any-file: rnd/autogpt_builder/**
-
-Server:
-- changed-files:
-  - any-glob-to-any-file: rnd/autogpt_server/**

.github/workflows/autogpt-builder-ci.yml

@@ -1,41 +0,0 @@
-name: AutoGPT Builder CI
-
-on:
-  push:
-    branches: [ master ]
-    paths:
-      - '.github/workflows/autogpt-builder-ci.yml'
-      - 'rnd/autogpt_builder/**'
-  pull_request:
-    paths:
-      - '.github/workflows/autogpt-builder-ci.yml'
-      - 'rnd/autogpt_builder/**'
-
-defaults:
-  run:
-    shell: bash
-    working-directory: rnd/autogpt_builder
-
-jobs:
-
-  lint:
-    runs-on: ubuntu-latest
-
-    steps:
-    - uses: actions/checkout@v4
-    - name: Set up Node.js
-      uses: actions/setup-node@v4
-      with:
-        node-version: '21'
-
-    - name: Install dependencies
-      run: |
-        npm install
-
-    - name: Check formatting with Prettier
-      run: |
-        npx prettier --check .
-
-    - name: Run lint
-      run: |
-        npm run lint

.github/workflows/autogpt-ci.yml

@@ -6,11 +6,13 @@ on:
     paths:
       - '.github/workflows/autogpt-ci.yml'
       - 'autogpt/**'
+      - '!autogpt/tests/vcr_cassettes'
   pull_request:
     branches: [ master, development, release-* ]
     paths:
       - '.github/workflows/autogpt-ci.yml'
       - 'autogpt/**'
+      - '!autogpt/tests/vcr_cassettes'
 
 concurrency:
   group: ${{ format('autogpt-ci-{0}', github.head_ref && format('{0}-{1}', github.event_name, github.event.pull_request.number) || github.sha) }}
@@ -71,6 +73,37 @@ jobs:
           git config --global user.name "Auto-GPT-Bot"
           git config --global user.email "github-bot@agpt.co"
 
+      - name: Checkout cassettes
+        if: ${{ startsWith(github.event_name, 'pull_request') }}
+        env:
+          PR_BASE: ${{ github.event.pull_request.base.ref }}
+          PR_BRANCH: ${{ github.event.pull_request.head.ref }}
+          PR_AUTHOR: ${{ github.event.pull_request.user.login }}
+        run: |
+          cassette_branch="${PR_AUTHOR}-${PR_BRANCH}"
+          cassette_base_branch="${PR_BASE}"
+          cd tests/vcr_cassettes
+
+          if ! git ls-remote --exit-code --heads origin $cassette_base_branch ; then
+            cassette_base_branch="master"
+          fi
+
+          if git ls-remote --exit-code --heads origin $cassette_branch ; then
+            git fetch origin $cassette_branch
+            git fetch origin $cassette_base_branch
+
+            git checkout $cassette_branch
+
+            # Pick non-conflicting cassette updates from the base branch
+            git merge --no-commit --strategy-option=ours origin/$cassette_base_branch
+            echo "Using cassettes from mirror branch '$cassette_branch'," \
+              "synced to upstream branch '$cassette_base_branch'."
+          else
+            git checkout -b $cassette_branch
+            echo "Branch '$cassette_branch' does not exist in cassette submodule." \
+              "Using cassettes from '$cassette_base_branch'."
+          fi
+
       - name: Set up Python ${{ matrix.python-version }}
         uses: actions/setup-python@v5
         with:
@@ -130,6 +163,80 @@ jobs:
           token: ${{ secrets.CODECOV_TOKEN }}
           flags: autogpt-agent,${{ runner.os }}
 
+      - id: setup_git_auth
+        name: Set up git token authentication
+        # Cassettes may be pushed even when tests fail
+        if: success() || failure()
+        run: |
+          config_key="http.${{ github.server_url }}/.extraheader"
+          if [ "${{ runner.os }}" = 'macOS' ]; then
+            base64_pat=$(echo -n "pat:${{ secrets.PAT_REVIEW }}" | base64)
+          else
+            base64_pat=$(echo -n "pat:${{ secrets.PAT_REVIEW }}" | base64 -w0)
+          fi
+
+          git config "$config_key" \
+            "Authorization: Basic $base64_pat"
+
+          cd tests/vcr_cassettes
+          git config "$config_key" \
+            "Authorization: Basic $base64_pat"
+
+          echo "config_key=$config_key" >> $GITHUB_OUTPUT
+
+      - id: push_cassettes
+        name: Push updated cassettes
+        # For pull requests, push updated cassettes even when tests fail
+        if: github.event_name == 'push' || (! github.event.pull_request.head.repo.fork && (success() || failure()))
+        env:
+          PR_BRANCH: ${{ github.event.pull_request.head.ref }}
+          PR_AUTHOR: ${{ github.event.pull_request.user.login }}
+        run: |
+          if [ "${{ startsWith(github.event_name, 'pull_request') }}" = "true" ]; then
+            is_pull_request=true
+            cassette_branch="${PR_AUTHOR}-${PR_BRANCH}"
+          else
+            cassette_branch="${{ github.ref_name }}"
+          fi
+
+          cd tests/vcr_cassettes
+          # Commit & push changes to cassettes if any
+          if ! git diff --quiet; then
+            git add .
+            git commit -m "Auto-update cassettes"
+            git push origin HEAD:$cassette_branch
+            if [ ! $is_pull_request ]; then
+              cd ../..
+              git add tests/vcr_cassettes
+              git commit -m "Update cassette submodule"
+              git push origin HEAD:$cassette_branch
+            fi
+            echo "updated=true" >> $GITHUB_OUTPUT
+          else
+            echo "updated=false" >> $GITHUB_OUTPUT
+            echo "No cassette changes to commit"
+          fi
+
+      - name: Post Set up git token auth
+        if: steps.setup_git_auth.outcome == 'success'
+        run: |
+          git config --unset-all '${{ steps.setup_git_auth.outputs.config_key }}'
+          git submodule foreach git config --unset-all '${{ steps.setup_git_auth.outputs.config_key }}'
+
+      - name: Apply "behaviour change" label and comment on PR
+        if: ${{ startsWith(github.event_name, 'pull_request') }}
+        run: |
+          PR_NUMBER="${{ github.event.pull_request.number }}"
+          TOKEN="${{ secrets.PAT_REVIEW }}"
+          REPO="${{ github.repository }}"
+
+          if [[ "${{ steps.push_cassettes.outputs.updated }}" == "true" ]]; then
+            echo "Adding label and comment..."
+            echo $TOKEN | gh auth login --with-token
+            gh issue edit $PR_NUMBER --add-label "behaviour change"
+            gh issue comment $PR_NUMBER --body "You changed AutoGPT's behaviour on ${{ runner.os }}. The cassettes have been updated and will be merged to the submodule when this Pull Request gets merged."
+          fi
+
       - name: Upload logs to artifact
         if: always()
         uses: actions/upload-artifact@v4

.github/workflows/autogpt-docker-ci.yml

@@ -6,11 +6,13 @@ on:
     paths:
       - '.github/workflows/autogpt-docker-ci.yml'
       - 'autogpt/**'
+      - '!autogpt/tests/vcr_cassettes'
   pull_request:
     branches: [ master, development, release-* ]
     paths:
       - '.github/workflows/autogpt-docker-ci.yml'
       - 'autogpt/**'
+      - '!autogpt/tests/vcr_cassettes'
 
 concurrency:
   group: ${{ format('autogpt-docker-ci-{0}', github.head_ref && format('pr-{0}', github.event.pull_request.number) || github.sha) }}

.github/workflows/autogpt-infra-ci.yml

@@ -1,56 +0,0 @@
-name: AutoGPT Builder Infra
-
-on:
-  push:
-    branches: [ master ]
-    paths:
-      - '.github/workflows/autogpt-infra-ci.yml'
-      - 'rnd/infra/**'
-  pull_request:
-    paths:
-      - '.github/workflows/autogpt-infra-ci.yml'
-      - 'rnd/infra/**'
-
-defaults:
-  run:
-    shell: bash
-    working-directory: rnd/infra
-
-jobs:
-  lint:
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v2
-        with:
-          fetch-depth: 0
-
-      - name: TFLint
-        uses: pauloconnor/tflint-action@v0.0.2
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        with:
-            tflint_path: terraform/
-            tflint_recurse: true
-            tflint_changed_only: false
-
-      - name: Set up Helm
-        uses: azure/setup-helm@v4.2.0
-        with:
-          version: v3.14.4
-
-      - name: Set up chart-testing
-        uses: helm/chart-testing-action@v2.6.0
-
-      - name: Run chart-testing (list-changed)
-        id: list-changed
-        run: |
-          changed=$(ct list-changed --target-branch ${{ github.event.repository.default_branch }})
-          if [[ -n "$changed" ]]; then
-            echo "changed=true" >> "$GITHUB_OUTPUT"
-          fi
-
-      - name: Run chart-testing (lint)
-        if: steps.list-changed.outputs.changed == 'true'
-        run: ct lint --target-branch ${{ github.event.repository.default_branch }}

.github/workflows/autogpt-server-ci.yml

@@ -1,155 +0,0 @@
-name: AutoGPT Server CI
-
-on:
-  push:
-    branches: [master, development, ci-test*]
-    paths:
-      - ".github/workflows/autogpt-server-ci.yml"
-      - "rnd/autogpt_server/**"
-  pull_request:
-    branches: [master, development, release-*]
-    paths:
-      - ".github/workflows/autogpt-server-ci.yml"
-      - "rnd/autogpt_server/**"
-
-concurrency:
-  group: ${{ format('autogpt-server-ci-{0}', github.head_ref && format('{0}-{1}', github.event_name, github.event.pull_request.number) || github.sha) }}
-  cancel-in-progress: ${{ startsWith(github.event_name, 'pull_request') }}
-
-defaults:
-  run:
-    shell: bash
-    working-directory: rnd/autogpt_server
-
-jobs:
-  test:
-    permissions:
-      contents: read
-    timeout-minutes: 30
-    strategy:
-      fail-fast: false
-      matrix:
-        python-version: ["3.10"]
-        platform-os: [ubuntu, macos, macos-arm64, windows]
-    runs-on: ${{ matrix.platform-os != 'macos-arm64' && format('{0}-latest', matrix.platform-os) || 'macos-14' }}
-
-    steps:
-      - name: Setup PostgreSQL
-        uses: ikalnytskyi/action-setup-postgres@v6
-        with:
-          username: ${{ secrets.DB_USER || 'postgres' }}
-          password: ${{ secrets.DB_PASS || 'postgres' }}
-          database: postgres
-          port: 5432
-        id: postgres
-
-      # Quite slow on macOS (2~4 minutes to set up Docker)
-      # - name: Set up Docker (macOS)
-      #   if: runner.os == 'macOS'
-      #   uses: crazy-max/ghaction-setup-docker@v3
-
-      - name: Start MinIO service (Linux)
-        if: runner.os == 'Linux'
-        working-directory: "."
-        run: |
-          docker pull minio/minio:edge-cicd
-          docker run -d -p 9000:9000 minio/minio:edge-cicd
-
-      - name: Start MinIO service (macOS)
-        if: runner.os == 'macOS'
-        working-directory: ${{ runner.temp }}
-        run: |
-          brew install minio/stable/minio
-          mkdir data
-          minio server ./data &
-
-      # No MinIO on Windows:
-      # - Windows doesn't support running Linux Docker containers
-      # - It doesn't seem possible to start background processes on Windows. They are
-      #   killed after the step returns.
-      #   See: https://github.com/actions/runner/issues/598#issuecomment-2011890429
-
-      - name: Checkout repository
-        uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-          submodules: true
-
-      - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v5
-        with:
-          python-version: ${{ matrix.python-version }}
-
-      - id: get_date
-        name: Get date
-        run: echo "date=$(date +'%Y-%m-%d')" >> $GITHUB_OUTPUT
-
-      - name: Set up Python dependency cache
-        # On Windows, unpacking cached dependencies takes longer than just installing them
-        if: runner.os != 'Windows'
-        uses: actions/cache@v4
-        with:
-          path: ${{ runner.os == 'macOS' && '~/Library/Caches/pypoetry' || '~/.cache/pypoetry' }}
-          key: poetry-${{ runner.os }}-${{ hashFiles('rnd/autogpt_server/poetry.lock') }}
-
-      - name: Install Poetry (Unix)
-        if: runner.os != 'Windows'
-        run: |
-          curl -sSL https://install.python-poetry.org | python3 -
-
-          if [ "${{ runner.os }}" = "macOS" ]; then
-            PATH="$HOME/.local/bin:$PATH"
-            echo "$HOME/.local/bin" >> $GITHUB_PATH
-          fi
-
-      - name: Install Poetry (Windows)
-        if: runner.os == 'Windows'
-        shell: pwsh
-        run: |
-          (Invoke-WebRequest -Uri https://install.python-poetry.org -UseBasicParsing).Content | python -
-
-          $env:PATH += ";$env:APPDATA\Python\Scripts"
-          echo "$env:APPDATA\Python\Scripts" >> $env:GITHUB_PATH
-
-      - name: Install Python dependencies
-        run: poetry install
-
-      - name: Generate Prisma Client
-        run: poetry run prisma generate
-
-      - name: Run Database Migrations
-        run: poetry run prisma migrate dev --name updates
-        env:
-          CONNECTION_STR: ${{ steps.postgres.outputs.connection-uri }}
-
-      - id: lint
-        name: Run Linter
-        run: poetry run lint
-
-      - name: Run pytest with coverage
-        run: |
-          if [[ "${{ runner.debug }}" == "1" ]]; then
-            poetry run pytest -vv -o log_cli=true -o log_cli_level=DEBUG test
-          else
-            poetry run pytest -vv test
-          fi
-        if: success() || (failure() && steps.lint.outcome == 'failure')
-        env:
-          LOG_LEVEL: ${{ runner.debug && 'DEBUG' || 'INFO' }}
-    env:
-      CI: true
-      PLAIN_OUTPUT: True
-      OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-      DB_USER: ${{ secrets.DB_USER || 'postgres' }}
-      DB_PASS: ${{ secrets.DB_PASS || 'postgres' }}
-      DB_NAME: postgres
-      DB_PORT: 5432
-      RUN_ENV: local
-      PORT: 8080
-      DATABASE_URL: postgresql://${{ secrets.DB_USER || 'postgres' }}:${{ secrets.DB_PASS || 'postgres' }}@localhost:5432/${{ secrets.DB_NAME || 'postgres'}}
-
-      # - name: Upload coverage reports to Codecov
-      #   uses: codecov/codecov-action@v4
-      #   with:
-      #     token: ${{ secrets.CODECOV_TOKEN }}
-      #     flags: autogpt-server,${{ runner.os }}

.github/workflows/forge-ci.yml

@@ -6,13 +6,11 @@ on:
     paths:
       - '.github/workflows/forge-ci.yml'
       - 'forge/**'
-      - '!forge/tests/vcr_cassettes'
   pull_request:
     branches: [ master, development, release-* ]
     paths:
       - '.github/workflows/forge-ci.yml'
       - 'forge/**'
-      - '!forge/tests/vcr_cassettes'
 
 concurrency:
   group: ${{ format('forge-ci-{0}', github.head_ref && format('{0}-{1}', github.event_name, github.event.pull_request.number) || github.sha) }}
@@ -68,37 +66,6 @@ jobs:
           fetch-depth: 0
           submodules: true
 
-      - name: Checkout cassettes
-        if: ${{ startsWith(github.event_name, 'pull_request') }}
-        env:
-          PR_BASE: ${{ github.event.pull_request.base.ref }}
-          PR_BRANCH: ${{ github.event.pull_request.head.ref }}
-          PR_AUTHOR: ${{ github.event.pull_request.user.login }}
-        run: |
-          cassette_branch="${PR_AUTHOR}-${PR_BRANCH}"
-          cassette_base_branch="${PR_BASE}"
-          cd tests/vcr_cassettes
-
-          if ! git ls-remote --exit-code --heads origin $cassette_base_branch ; then
-            cassette_base_branch="master"
-          fi
-
-          if git ls-remote --exit-code --heads origin $cassette_branch ; then
-            git fetch origin $cassette_branch
-            git fetch origin $cassette_base_branch
-
-            git checkout $cassette_branch
-
-            # Pick non-conflicting cassette updates from the base branch
-            git merge --no-commit --strategy-option=ours origin/$cassette_base_branch
-            echo "Using cassettes from mirror branch '$cassette_branch'," \
-              "synced to upstream branch '$cassette_base_branch'."
-          else
-            git checkout -b $cassette_branch
-            echo "Branch '$cassette_branch' does not exist in cassette submodule." \
-              "Using cassettes from '$cassette_base_branch'."
-          fi
-
       - name: Set up Python ${{ matrix.python-version }}
         uses: actions/setup-python@v5
         with:
@@ -154,80 +121,6 @@ jobs:
           token: ${{ secrets.CODECOV_TOKEN }}
           flags: forge,${{ runner.os }}
 
-      - id: setup_git_auth
-        name: Set up git token authentication
-        # Cassettes may be pushed even when tests fail
-        if: success() || failure()
-        run: |
-          config_key="http.${{ github.server_url }}/.extraheader"
-          if [ "${{ runner.os }}" = 'macOS' ]; then
-            base64_pat=$(echo -n "pat:${{ secrets.PAT_REVIEW }}" | base64)
-          else
-            base64_pat=$(echo -n "pat:${{ secrets.PAT_REVIEW }}" | base64 -w0)
-          fi
-
-          git config "$config_key" \
-            "Authorization: Basic $base64_pat"
-
-          cd tests/vcr_cassettes
-          git config "$config_key" \
-            "Authorization: Basic $base64_pat"
-
-          echo "config_key=$config_key" >> $GITHUB_OUTPUT
-
-      - id: push_cassettes
-        name: Push updated cassettes
-        # For pull requests, push updated cassettes even when tests fail
-        if: github.event_name == 'push' || (! github.event.pull_request.head.repo.fork && (success() || failure()))
-        env:
-          PR_BRANCH: ${{ github.event.pull_request.head.ref }}
-          PR_AUTHOR: ${{ github.event.pull_request.user.login }}
-        run: |
-          if [ "${{ startsWith(github.event_name, 'pull_request') }}" = "true" ]; then
-            is_pull_request=true
-            cassette_branch="${PR_AUTHOR}-${PR_BRANCH}"
-          else
-            cassette_branch="${{ github.ref_name }}"
-          fi
-
-          cd tests/vcr_cassettes
-          # Commit & push changes to cassettes if any
-          if ! git diff --quiet; then
-            git add .
-            git commit -m "Auto-update cassettes"
-            git push origin HEAD:$cassette_branch
-            if [ ! $is_pull_request ]; then
-              cd ../..
-              git add tests/vcr_cassettes
-              git commit -m "Update cassette submodule"
-              git push origin HEAD:$cassette_branch
-            fi
-            echo "updated=true" >> $GITHUB_OUTPUT
-          else
-            echo "updated=false" >> $GITHUB_OUTPUT
-            echo "No cassette changes to commit"
-          fi
-
-      - name: Post Set up git token auth
-        if: steps.setup_git_auth.outcome == 'success'
-        run: |
-          git config --unset-all '${{ steps.setup_git_auth.outputs.config_key }}'
-          git submodule foreach git config --unset-all '${{ steps.setup_git_auth.outputs.config_key }}'
-
-      - name: Apply "behaviour change" label and comment on PR
-        if: ${{ startsWith(github.event_name, 'pull_request') }}
-        run: |
-          PR_NUMBER="${{ github.event.pull_request.number }}"
-          TOKEN="${{ secrets.PAT_REVIEW }}"
-          REPO="${{ github.repository }}"
-
-          if [[ "${{ steps.push_cassettes.outputs.updated }}" == "true" ]]; then
-            echo "Adding label and comment..."
-            echo $TOKEN | gh auth login --with-token
-            gh issue edit $PR_NUMBER --add-label "behaviour change"
-            gh issue comment $PR_NUMBER --body "You changed AutoGPT's behaviour on ${{ runner.os }}. The cassettes have been updated and will be merged to the submodule when this Pull Request gets merged."
-          fi
-
       - name: Upload logs to artifact
         if: always()
         uses: actions/upload-artifact@v4

.github/workflows/pr-label.yml

@@ -5,7 +5,7 @@ on:
   push:
     branches: [ master, development, release-* ]
     paths-ignore:
-      - 'forge/tests/vcr_cassettes'
+      - 'autogpt/tests/vcr_cassettes'
       - 'benchmark/reports/**'
   # So that the `dirtyLabel` is removed if conflicts are resolve
   # We recommend `pull_request_target` so that github secrets are available.

.github/workflows/python-checks.yml

@@ -9,7 +9,7 @@ on:
       - 'forge/**'
       - 'benchmark/**'
       - '**.py'
-      - '!forge/tests/vcr_cassettes'
+      - '!autogpt/tests/vcr_cassettes'
   pull_request:
     branches: [ master, development, release-* ]
     paths:
@@ -18,7 +18,7 @@ on:
       - 'forge/**'
       - 'benchmark/**'
       - '**.py'
-      - '!forge/tests/vcr_cassettes'
+      - '!autogpt/tests/vcr_cassettes'
 
 concurrency:
   group: ${{ format('lint-ci-{0}', github.head_ref && format('{0}-{1}', github.event_name, github.event.pull_request.number) || github.sha) }}

.github/workflows/workflow-checker.yml

@@ -1,31 +0,0 @@
-name: PR Status Checker
-on:
-  pull_request:
-    types: [opened, synchronize, reopened]
-
-jobs:
-  status-check:
-    name: Check PR Status
-    runs-on: ubuntu-latest
-    steps:
-      # - name: Wait some time for all actions to start
-      #   run: sleep 30
-      - uses: actions/checkout@v4
-        # with:
-          # fetch-depth: 0
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: "3.10"
-      - name: Install dependencies
-        run: |
-          python -m pip install --upgrade pip
-          pip install requests
-      - name: Check PR Status
-        run: |
-          echo "Current directory before running Python script:"
-          pwd
-          echo "Attempting to run Python script:"
-          python check_actions_status.py
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.gitignore

@@ -32,6 +32,7 @@ dist/
 downloads/
 eggs/
 .eggs/
+lib/
 lib64/
 parts/
 sdist/
@@ -161,7 +162,7 @@ agbenchmark/reports/
 
 # Nodejs
 package-lock.json
-
+package.json
 
 # Allow for locally private items
 # private
@@ -169,5 +170,3 @@ pri*
 # ignore
 ig*
 .github_access_token
-LICENSE.rtf
-rnd/autogpt_server/settings.py

.gitmodules

@@ -1,3 +1,3 @@
-[submodule "forge/tests/vcr_cassettes"]
-	path = forge/tests/vcr_cassettes
+[submodule "autogpt/tests/vcr_cassettes"]
+	path = autogpt/tests/vcr_cassettes
 	url = https://github.com/Significant-Gravitas/Auto-GPT-test-cassettes

.pre-commit-config.yaml

@@ -97,7 +97,7 @@ repos:
         alias: pyright-benchmark
         entry: poetry -C benchmark run pyright
         args: [-p, benchmark, benchmark]
-        files: ^benchmark/(agbenchmark/|tests/|poetry\.lock$)
+        files: ^benchmark/(agbenchmark|tests)/
         types: [file]
         language: system
         pass_filenames: false

.vscode/all-projects.code-workspace

@@ -1,61 +0,0 @@
-{
-  "folders": [
-    {
-      "name": "autogpt",
-      "path": "../autogpt"
-    },
-    {
-      "name": "benchmark",
-      "path": "../benchmark"
-    },
-    {
-      "name": "docs",
-      "path": "../docs"
-    },
-    {
-      "name": "forge",
-      "path": "../forge"
-    },
-    {
-      "name": "frontend",
-      "path": "../frontend"
-    },
-    {
-      "name": "autogpt_server",
-      "path": "../rnd/autogpt_server"
-    },
-    {
-      "name": "autogpt_builder",
-      "path": "../rnd/autogpt_builder"
-    },
-    {
-      "name": "market",
-      "path": "../rnd/market"
-    },
-    {
-      "name": "lib",
-      "path": "../rnd/autogpt_libs"
-    },
-    {
-      "name": "infra",
-      "path": "../rnd/infra"
-    },
-    {
-      "name": "[root]",
-      "path": ".."
-    }
-  ],
-  "settings": {
-    "python.analysis.typeCheckingMode": "basic"
-  },
-  "extensions": {
-    "recommendations": [
-      "charliermarsh.ruff",
-      "dart-code.flutter",
-      "ms-python.black-formatter",
-      "ms-python.vscode-pylance",
-      "prisma.prisma",
-      "qwtel.sqlite-viewer"
-    ]
-  }
-}

CONTRIBUTING.md

@@ -1,38 +1,34 @@
 # AutoGPT Contribution Guide
-If you are reading this, you are probably looking for the full **[contribution guide]**,
-which is part of our [wiki].
+If you are reading this, you are probably looking for our **[contribution guide]**,
+which is part of our [knowledge base].
 
-Also check out our [🚀 Roadmap][roadmap] for information about our priorities and associated tasks.
-<!-- You can find our immediate priorities and their progress on our public [kanban board]. -->
+You can find our immediate priorities and their progress on our public [kanban board].
 
-[contribution guide]: https://github.com/Significant-Gravitas/AutoGPT/wiki/Contributing
-[wiki]: https://github.com/Significant-Gravitas/AutoGPT/wiki
-[roadmap]: https://github.com/Significant-Gravitas/AutoGPT/discussions/6971
+[contribution guide]: https://github.com/Significant-Gravitas/Nexus/wiki/Contributing
+[knowledge base]: https://github.com/Significant-Gravitas/Nexus/wiki
 [kanban board]: https://github.com/orgs/Significant-Gravitas/projects/1
 
 ## In short
 1. Avoid duplicate work, issues, PRs etc.
 2. We encourage you to collaborate with fellow community members on some of our bigger
-   [todo's][roadmap]!
+   [todo's][kanban board]!
    * We highly recommend to post your idea and discuss it in the [dev channel].
-3. Create a draft PR when starting work on bigger changes.
-4. Adhere to the [Code Guidelines]
+4. Create a draft PR when starting work on bigger changes.
+3. Please also consider contributing something other than code; see the
+   [contribution guide] for options.
 5. Clearly explain your changes when submitting a PR.
-6. Don't submit broken code: test/validate your changes.
+6. Don't submit stuff that's broken.
 7. Avoid making unnecessary changes, especially if they're purely based on your personal
    preferences. Doing so is the maintainers' job. ;-)
-8. Please also consider contributing something other than code; see the
-   [contribution guide] for options.
 
 [dev channel]: https://discord.com/channels/1092243196446249134/1095817829405704305
-[code guidelines]: https://github.com/Significant-Gravitas/AutoGPT/wiki/Contributing#code-guidelines
 
 If you wish to involve with the project (beyond just contributing PRs), please read the
-wiki page about [Catalyzing](https://github.com/Significant-Gravitas/AutoGPT/wiki/Catalyzing).
+wiki [catalyzing](https://github.com/Significant-Gravitas/Nexus/wiki/Catalyzing) page.
 
 In fact, why not just look through the whole wiki (it's only a few pages) and
 hop on our Discord. See you there! :-)
 
-❤️ & 🔆
-The team @ AutoGPT
+❤️ & 🔆  
+The team @ AutoGPT  
 https://discord.gg/autogpt

QUICKSTART.md

@@ -2,11 +2,11 @@
 
 > For the complete getting started [tutorial series](https://aiedge.medium.com/autogpt-forge-e3de53cc58ec) <- click here
 
-Welcome to the Quickstart Guide! This guide will walk you through setting up, building, and running your own AutoGPT agent. Whether you're a seasoned AI developer or just starting out, this guide will provide you with the steps to jumpstart your journey in AI development with AutoGPT.
+Welcome to the Quickstart Guide! This guide will walk you through the process of setting up and running your own AutoGPT agent. Whether you're a seasoned AI developer or just starting out, this guide will provide you with the necessary steps to jumpstart your journey in the world of AI development with AutoGPT.
 
 ## System Requirements
 
-This project supports Linux (Debian-based), Mac, and Windows Subsystem for Linux (WSL). If you use a Windows system, you must install WSL. You can find the installation instructions for WSL [here](https://learn.microsoft.com/en-us/windows/wsl/).
+This project supports Linux (Debian based), Mac, and Windows Subsystem for Linux (WSL). If you are using a Windows system, you will need to install WSL. You can find the installation instructions for WSL [here](https://learn.microsoft.com/en-us/windows/wsl/).
 
 
 ## Getting Setup
@@ -18,11 +18,11 @@ This project supports Linux (Debian-based), Mac, and Windows Subsystem for Linux
    - In the top-right corner of the page, click Fork.
 
    ![Create Fork UI](docs/content/imgs/quickstart/002_fork.png)
-   - On the next page, select your GitHub account to create the fork.
+   - On the next page, select your GitHub account to create the fork under.
    - Wait for the forking process to complete. You now have a copy of the repository in your GitHub account.
 
 2. **Clone the Repository**
-   To clone the repository, you need to have Git installed on your system. If you don't have Git installed, download it from [here](https://git-scm.com/downloads). Once you have Git installed, follow these steps:
+   To clone the repository, you need to have Git installed on your system. If you don't have Git installed, you can download it from [here](https://git-scm.com/downloads). Once you have Git installed, follow these steps:
    - Open your terminal.
    - Navigate to the directory where you want to clone the repository.
    - Run the git clone command for the fork you just created
@@ -34,11 +34,11 @@ This project supports Linux (Debian-based), Mac, and Windows Subsystem for Linux
    ![Open the Project in your IDE](docs/content/imgs/quickstart/004_ide.png)
 
 4. **Setup the Project**
-    Next, we need to set up the required dependencies. We have a tool to help you perform all the tasks on the repo.
+    Next we need to setup the required dependencies. We have a tool for helping you do all the tasks you need to on the repo.
     It can be accessed by running the `run` command by typing `./run` in the terminal.
 
-    The first command you need to use is `./run setup.` This will guide you through setting up your system.
-    Initially, you will get instructions for installing Flutter and Chrome and setting up your GitHub access token like the following image:
+    The first command you need to use is `./run setup` This will guide you through the process of setting up your system.
+    Initially you will get instructions for installing flutter, chrome and setting up your github access token like the following image:
     
     ![Setup the Project](docs/content/imgs/quickstart/005_setup.png)
 
@@ -47,7 +47,7 @@ This project supports Linux (Debian-based), Mac, and Windows Subsystem for Linux
 If you're a Windows user and experience issues after installing WSL, follow the steps below to resolve them. 
 
 #### Update WSL 
-Run the following command in Powershell or Command Prompt:
+Run the following command in Powershell or Command Prompt to:
 1. Enable the optional WSL and Virtual Machine Platform components.
 2. Download and install the latest Linux kernel.
 3. Set WSL 2 as the default.
@@ -73,7 +73,7 @@ dos2unix ./run
 After executing the above commands, running `./run setup` should work successfully. 
 
 #### Store Project Files within the WSL File System
-If you continue to experience issues, consider storing your project files within the WSL file system instead of the Windows file system. This method avoids path translations and permissions issues and provides a more consistent development environment.
+If you continue to experience issues, consider storing your project files within the WSL file system instead of the Windows file system. This method avoids issues related to path translations and permissions and provides a more consistent development environment.
 
 You can keep running the command to get feedback on where you are up to with your setup. 
 When setup has been completed, the command will return an output like this:
@@ -83,7 +83,7 @@ When setup has been completed, the command will return an output like this:
 ## Creating Your Agent
 
 After completing the setup, the next step is to create your agent template.
-Execute the command `./run agent create YOUR_AGENT_NAME`, where `YOUR_AGENT_NAME` should be replaced with your chosen name.
+Execute the command `./run agent create YOUR_AGENT_NAME`, where `YOUR_AGENT_NAME` should be replaced with a name of your choosing.
 
 Tips for naming your agent:
 * Give it its own unique name, or name it after yourself
@@ -101,21 +101,21 @@ This starts the agent on the URL: `http://localhost:8000/`
 
 ![Start the Agent](docs/content/imgs/quickstart/009_start_agent.png)
 
-The front end can be accessed from `http://localhost:8000/`; first, you must log in using either a Google account or your GitHub account.
+The frontend can be accessed from `http://localhost:8000/`, you will first need to login using either a google account or your github account.
 
 ![Login](docs/content/imgs/quickstart/010_login.png)
 
-Upon logging in, you will get a page that looks something like this: your task history down the left-hand side of the page, and the 'chat' window to send tasks to your agent.
+Upon logging in you will get a page that looks something like this. With your task history down the left hand side of the page and the 'chat' window to send tasks to your agent.
 
 ![Login](docs/content/imgs/quickstart/011_home.png)
 
-When you have finished with your agent or just need to restart it, use Ctl-C to end the session. Then, you can re-run the start command.
+When you have finished with your agent, or if you just need to restart it, use Ctl-C to end the session then you can re-run the start command.
 
-If you are having issues and want to ensure the agent has been stopped, there is a `./run agent stop` command, which will kill the process using port 8000, which should be the agent. 
+If you are having issues and want to ensure the agent has been stopped there is a `./run agent stop` command which will kill the process using port 8000, which should be the agent. 
 
 ## Benchmarking your Agent
 
-The benchmarking system can also be accessed using the CLI too:
+The benchmarking system can also be accessed using the cli too:
 
 ```bash
 agpt % ./run benchmark
@@ -163,7 +163,7 @@ The benchmark has been split into different categories of skills you can test yo
 ![Login](docs/content/imgs/quickstart/012_tests.png)
 
 
-Finally, you can run the benchmark with
+Finally you can run the benchmark with
 
 ```bash
 ./run benchmark start YOUR_AGENT_NAME

README.md

@@ -1,44 +1,10 @@
-# AutoGPT: Build & Use AI Agents
+# AutoGPT: build & use AI agents
 
 [![Discord Follow](https://dcbadge.vercel.app/api/server/autogpt?style=flat)](https://discord.gg/autogpt)  
 [![Twitter Follow](https://img.shields.io/twitter/follow/Auto_GPT?style=social)](https://twitter.com/Auto_GPT)  
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 
-**AutoGPT** is a powerful tool that lets you create and run intelligent agents. These agents can perform various tasks automatically, making your life easier.
-
-## How to Get Started
-
-https://github.com/user-attachments/assets/8508f4dc-b362-4cab-900f-644964a96cdf
-
-### 🧱 AutoGPT Builder 
-
-The AutoGPT Builder is the frontend. It allows you to design agents using an easy flowchart style. You build your agent by connecting blocks, where each block performs a single action. It's simple and intuitive!
-
-[Read this guide](https://docs.agpt.co/server/new_blocks/) to learn how to build your own custom blocks.
-
-### 💽 AutoGPT Server
-
-The AutoGPT Server is the backend. This is where your agents run. Once deployed, agents can be triggered by external sources and can operate continuously.
-
-### 🐙 Example Agents
-
-Here are two examples of what you can do with AutoGPT:
-
-1. **Reddit Marketing Agent**
-   - This agent reads comments on Reddit.
-   - It looks for people asking about your product.
-   - It then automatically responds to them.
-
-2. **YouTube Content Repurposing Agent**
-   - This agent subscribes to your YouTube channel.
-   - When you post a new video, it transcribes it.
-   - It uses AI to write a search engine optimized blog post.
-   - Then, it publishes this blog post to your Medium account.
-
-These examples show just a glimpse of what you can achieve with AutoGPT!
-
----
-Our mission is to provide the tools, so that you can focus on what matters:
+**AutoGPT** is the vision of the power of AI accessible to everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters:
 
 - 🏗️ **Building** - Lay the foundation for something amazing.
 - 🧪 **Testing** - Fine-tune your agent to perfection.
@@ -49,13 +15,11 @@ Be part of the revolution! **AutoGPT** is here to stay, at the forefront of AI i
 **📖 [Documentation](https://docs.agpt.co)**
  | 
 **🚀 [Contributing](CONTRIBUTING.md)**
+ | 
+**🛠️ [Build your own Agent - Quickstart](QUICKSTART.md)**
 
+## 🧱 Building blocks
 
----
-## 🤖 AutoGPT Classic
-> Below is information about the classic version of AutoGPT.
-
-**🛠️ [Build your own Agent - Quickstart](FORGE-QUICKSTART.md)**
 ### 🏗️ Forge
 
 **Forge your own agent!** – Forge is a ready-to-go template for your agent application. All the boilerplate code is already handled, letting you channel all your creativity into the things that set *your* agent apart. All tutorials are located [here](https://medium.com/@aiedge/autogpt-forge-e3de53cc58ec). Components from the [`forge.sdk`](/forge/forge/sdk) can also be used individually to speed up development and reduce boilerplate in your agent project.

autogpt/.env.template

@@ -11,15 +11,12 @@
 ## GROQ_API_KEY - Groq API Key (Example: gsk_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx)
 # GROQ_API_KEY=
 
-## LLAMAFILE_API_BASE - Llamafile API base URL
-# LLAMAFILE_API_BASE=http://localhost:8080/v1
-
 ## TELEMETRY_OPT_IN - Share telemetry on errors and other issues with the AutoGPT team, e.g. through Sentry.
 ##   This helps us to spot and solve problems earlier & faster. (Default: DISABLED)
 # TELEMETRY_OPT_IN=true
 
-## COMPONENT_CONFIG_FILE - Path to the json config file (Default: None)
-# COMPONENT_CONFIG_FILE=
+## EXECUTE_LOCAL_COMMANDS - Allow local command execution (Default: False)
+# EXECUTE_LOCAL_COMMANDS=False
 
 ### Workspace ###
 
@@ -47,6 +44,9 @@
 
 ### Miscellaneous ###
 
+## USER_AGENT - Define the user-agent used by the requests library to browse website (string)
+# USER_AGENT="Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36"
+
 ## AUTHORISE COMMAND KEY - Key to authorise commands
 # AUTHORISE_COMMAND_KEY=y
 
@@ -96,21 +96,59 @@
 ## EMBEDDING_MODEL - Model to use for creating embeddings
 # EMBEDDING_MODEL=text-embedding-3-small
 
+################################################################################
+### SHELL EXECUTION
+################################################################################
+
+## SHELL_COMMAND_CONTROL - Whether to use "allowlist" or "denylist" to determine what shell commands can be executed (Default: denylist)
+# SHELL_COMMAND_CONTROL=denylist
+
+## ONLY if SHELL_COMMAND_CONTROL is set to denylist:
+## SHELL_DENYLIST - List of shell commands that ARE NOT allowed to be executed by AutoGPT (Default: sudo,su)
+# SHELL_DENYLIST=sudo,su
+
+## ONLY if SHELL_COMMAND_CONTROL is set to allowlist:
+## SHELL_ALLOWLIST - List of shell commands that ARE allowed to be executed by AutoGPT (Default: None)
+# SHELL_ALLOWLIST=
+
 ################################################################################
 ### IMAGE GENERATION PROVIDER
 ################################################################################
 
+### Common
+
+## IMAGE_PROVIDER - Image provider (Default: dalle)
+# IMAGE_PROVIDER=dalle
+
+## IMAGE_SIZE - Image size (Default: 256)
+# IMAGE_SIZE=256
+
 ### Huggingface (IMAGE_PROVIDER=huggingface)
 
+## HUGGINGFACE_IMAGE_MODEL - Text-to-image model from Huggingface (Default: CompVis/stable-diffusion-v1-4)
+# HUGGINGFACE_IMAGE_MODEL=CompVis/stable-diffusion-v1-4
+
 ## HUGGINGFACE_API_TOKEN - HuggingFace API token (Default: None)
 # HUGGINGFACE_API_TOKEN=
 
-
 ### Stable Diffusion (IMAGE_PROVIDER=sdwebui)
 
 ## SD_WEBUI_AUTH - Stable Diffusion Web UI username:password pair (Default: None)
 # SD_WEBUI_AUTH=
 
+## SD_WEBUI_URL - Stable Diffusion Web UI API URL (Default: http://localhost:7860)
+# SD_WEBUI_URL=http://localhost:7860
+
+################################################################################
+### AUDIO TO TEXT PROVIDER
+################################################################################
+
+## AUDIO_TO_TEXT_PROVIDER - Audio-to-text provider (Default: huggingface)
+# AUDIO_TO_TEXT_PROVIDER=huggingface
+
+## HUGGINGFACE_AUDIO_TO_TEXT_MODEL - The model for HuggingFace to use (Default: CompVis/stable-diffusion-v1-4)
+# HUGGINGFACE_AUDIO_TO_TEXT_MODEL=CompVis/stable-diffusion-v1-4
+
 ################################################################################
 ### GITHUB
 ################################################################################
@@ -125,6 +163,18 @@
 ### WEB BROWSING
 ################################################################################
 
+## HEADLESS_BROWSER - Whether to run the browser in headless mode (default: True)
+# HEADLESS_BROWSER=True
+
+## USE_WEB_BROWSER - Sets the web-browser driver to use with selenium (default: chrome)
+# USE_WEB_BROWSER=chrome
+
+## BROWSE_CHUNK_MAX_LENGTH - When browsing website, define the length of chunks to summarize (Default: 3000)
+# BROWSE_CHUNK_MAX_LENGTH=3000
+
+## BROWSE_SPACY_LANGUAGE_MODEL - spaCy language model](https://spacy.io/usage/models) to use when creating chunks. (Default: en_core_web_sm)
+# BROWSE_SPACY_LANGUAGE_MODEL=en_core_web_sm
+
 ## GOOGLE_API_KEY - Google API key (Default: None)
 # GOOGLE_API_KEY=
 
@@ -148,6 +198,13 @@
 ## ELEVENLABS_VOICE_ID - Eleven Labs voice ID (Example: None)
 # ELEVENLABS_VOICE_ID=
 
+################################################################################
+### CHAT MESSAGES
+################################################################################
+
+## CHAT_MESSAGES_ENABLED - Enable chat messages (Default: False)
+# CHAT_MESSAGES_ENABLED=False
+
 ################################################################################
 ### LOGGING
 ################################################################################

autogpt/.gitattributes

@@ -0,0 +1,5 @@
+# Exclude VCR cassettes from stats
+tests/vcr_cassettes/**/**.y*ml linguist-generated
+
+# Mark documentation as such
+docs/**.md linguist-documentation

autogpt/.vscode/settings.json

@@ -1,3 +0,0 @@
-{
-  "python.analysis.typeCheckingMode": "basic",
-}

autogpt/BULLETIN.md

@@ -2,7 +2,7 @@
 # --------------
 🌎 *Official Website*: https://agpt.co.
 📖 *User Guide*: https://docs.agpt.co/autogpt.
-👩 *Contributors Wiki*: https://github.com/Significant-Gravitas/AutoGPT/wiki/Contributing.
+👩 *Contributors Wiki*: https://github.com/Significant-Gravitas/Nexus/wiki/Contributing.
 
 # v0.5.0 RELEASE HIGHLIGHTS! 🚀🚀
 # -------------------------------

autogpt/README.md

@@ -68,6 +68,10 @@ Options:
                                   continuous mode
   --speak                         Enable Speak Mode
   --debug                         Enable Debug Mode
+  -b, --browser-name TEXT         Specifies which web-browser to use when
+                                  using selenium to scrape the web.
+  --allow-downloads               Dangerous: Allows AutoGPT to download files
+                                  natively.
   --skip-news                     Specifies whether to suppress the output of
                                   latest news on startup.
   --install-plugin-deps           Installs external dependencies for 3rd party
@@ -86,7 +90,6 @@ Options:
   --override-directives           If specified, --constraint, --resource and
                                   --best-practice will override the AI's
                                   directives instead of being appended to them
-  --component-config-file TEXT    Path to the json configuration file.
   --help                          Show this message and exit.
 ```
 </details>
@@ -108,6 +111,10 @@ Usage: python -m autogpt serve [OPTIONS]
 
 Options:
   --debug                     Enable Debug Mode
+  -b, --browser-name TEXT     Specifies which web-browser to use when using
+                              selenium to scrape the web.
+  --allow-downloads           Dangerous: Allows AutoGPT to download files
+                              natively.
   --install-plugin-deps       Installs external dependencies for 3rd party
                               plugins.
   --help                      Show this message and exit.
@@ -125,7 +132,7 @@ For more comprehensive instructions, see the [user guide][docs/usage].
 [docs/plugins]: https://docs.agpt.co/autogpt/plugins
 
 ## 📚 Resources
-* 📔 AutoGPT [project wiki](https://github.com/Significant-Gravitas/AutoGPT/wiki)
+* 📔 AutoGPT [team wiki](https://github.com/Significant-Gravitas/Nexus/wiki)
 * 🧮 AutoGPT [project kanban](https://github.com/orgs/Significant-Gravitas/projects/1)
 * 🌃 AutoGPT [roadmap](https://github.com/orgs/Significant-Gravitas/projects/2)
 

autogpt/autogpt/agent_factory/configurators.py

@@ -2,17 +2,17 @@ from typing import Optional
 
 from forge.config.ai_directives import AIDirectives
 from forge.config.ai_profile import AIProfile
+from forge.config.config import Config
 from forge.file_storage.base import FileStorage
 from forge.llm.providers import MultiProvider
 
 from autogpt.agents.agent import Agent, AgentConfiguration, AgentSettings
-from autogpt.app.config import AppConfig
 
 
 def create_agent(
     agent_id: str,
     task: str,
-    app_config: AppConfig,
+    app_config: Config,
     file_storage: FileStorage,
     llm_provider: MultiProvider,
     ai_profile: Optional[AIProfile] = None,
@@ -38,7 +38,7 @@ def create_agent(
 
 def configure_agent_with_state(
     state: AgentSettings,
-    app_config: AppConfig,
+    app_config: Config,
     file_storage: FileStorage,
     llm_provider: MultiProvider,
 ) -> Agent:
@@ -51,7 +51,7 @@ def configure_agent_with_state(
 
 
 def _configure_agent(
-    app_config: AppConfig,
+    app_config: Config,
     llm_provider: MultiProvider,
     file_storage: FileStorage,
     agent_id: str = "",
@@ -80,7 +80,7 @@ def _configure_agent(
         settings=agent_state,
         llm_provider=llm_provider,
         file_storage=file_storage,
-        app_config=app_config,
+        legacy_config=app_config,
     )
 
 
@@ -89,7 +89,7 @@ def create_agent_state(
     task: str,
     ai_profile: AIProfile,
     directives: AIDirectives,
-    app_config: AppConfig,
+    app_config: Config,
 ) -> AgentSettings:
     return AgentSettings(
         agent_id=agent_id,
@@ -104,5 +104,5 @@ def create_agent_state(
             allow_fs_access=not app_config.restrict_to_workspace,
             use_functions_api=app_config.openai_functions,
         ),
-        history=Agent.default_settings.history.model_copy(deep=True),
+        history=Agent.default_settings.history.copy(deep=True),
     )

autogpt/autogpt/agent_factory/generators.py

@@ -6,7 +6,7 @@ from forge.file_storage.base import FileStorage
 
 if TYPE_CHECKING:
     from autogpt.agents.agent import Agent
-    from autogpt.app.config import AppConfig
+    from forge.config.config import Config
     from forge.llm.providers import MultiProvider
 
 from .configurators import _configure_agent
@@ -16,7 +16,7 @@ from .profile_generator import generate_agent_profile_for_task
 async def generate_agent_for_task(
     agent_id: str,
     task: str,
-    app_config: AppConfig,
+    app_config: Config,
     file_storage: FileStorage,
     llm_provider: MultiProvider,
 ) -> Agent:

autogpt/autogpt/agent_factory/profile_generator.py

@@ -3,6 +3,7 @@ import logging
 
 from forge.config.ai_directives import AIDirectives
 from forge.config.ai_profile import AIProfile
+from forge.config.config import Config
 from forge.llm.prompting import ChatPrompt, LanguageModelClassification, PromptStrategy
 from forge.llm.providers import MultiProvider
 from forge.llm.providers.schema import (
@@ -13,13 +14,11 @@ from forge.llm.providers.schema import (
 from forge.models.config import SystemConfiguration, UserConfigurable
 from forge.models.json_schema import JSONSchema
 
-from autogpt.app.config import AppConfig
-
 logger = logging.getLogger(__name__)
 
 
 class AgentProfileGeneratorConfiguration(SystemConfiguration):
-    llm_classification: LanguageModelClassification = UserConfigurable(
+    model_classification: LanguageModelClassification = UserConfigurable(
         default=LanguageModelClassification.SMART_MODEL
     )
     _example_call: object = {
@@ -137,7 +136,7 @@ class AgentProfileGeneratorConfiguration(SystemConfiguration):
                     required=True,
                 ),
             },
-        ).model_dump()
+        ).dict()
     )
 
 
@@ -148,21 +147,21 @@ class AgentProfileGenerator(PromptStrategy):
 
     def __init__(
         self,
-        llm_classification: LanguageModelClassification,
+        model_classification: LanguageModelClassification,
         system_prompt: str,
         user_prompt_template: str,
         create_agent_function: dict,
     ):
-        self._llm_classification = llm_classification
+        self._model_classification = model_classification
         self._system_prompt_message = system_prompt
         self._user_prompt_template = user_prompt_template
-        self._create_agent_function = CompletionModelFunction.model_validate(
+        self._create_agent_function = CompletionModelFunction.parse_obj(
             create_agent_function
         )
 
     @property
-    def llm_classification(self) -> LanguageModelClassification:
-        return self._llm_classification
+    def model_classification(self) -> LanguageModelClassification:
+        return self._model_classification
 
     def build_prompt(self, user_objective: str = "", **kwargs) -> ChatPrompt:
         system_message = ChatMessage.system(self._system_prompt_message)
@@ -213,7 +212,7 @@ class AgentProfileGenerator(PromptStrategy):
 
 async def generate_agent_profile_for_task(
     task: str,
-    app_config: AppConfig,
+    app_config: Config,
     llm_provider: MultiProvider,
 ) -> tuple[AIProfile, AIDirectives]:
     """Generates an AIConfig object from the given string.
@@ -222,7 +221,7 @@ async def generate_agent_profile_for_task(
     AIConfig: The AIConfig object tailored to the user's input
     """
     agent_profile_generator = AgentProfileGenerator(
-        **AgentProfileGenerator.default_configuration.model_dump()  # HACK
+        **AgentProfileGenerator.default_configuration.dict()  # HACK
     )
 
     prompt = agent_profile_generator.build_prompt(task)

autogpt/autogpt/agents/README.md

@@ -26,10 +26,10 @@ class MyAgent(Agent):
         settings: AgentSettings,
         llm_provider: MultiProvider
         file_storage: FileStorage,
-        app_config: AppConfig,
+        legacy_config: Config,
     ):
         # Call the parent constructor to bring in the default components
-        super().__init__(settings, llm_provider, file_storage, app_config)
+        super().__init__(settings, llm_provider, file_storage, legacy_config)
         # Add your custom component
         self.my_component = MyComponent()
 ```

autogpt/autogpt/agents/agent.py

@@ -18,11 +18,7 @@ from forge.components.action_history import (
     ActionHistoryComponent,
     EpisodicActionHistory,
 )
-from forge.components.action_history.action_history import ActionHistoryConfiguration
-from forge.components.code_executor.code_executor import (
-    CodeExecutorComponent,
-    CodeExecutorConfiguration,
-)
+from forge.components.code_executor.code_executor import CodeExecutorComponent
 from forge.components.context.context import AgentContext, ContextComponent
 from forge.components.file_manager import FileManagerComponent
 from forge.components.git_operations import GitOperationsComponent
@@ -62,7 +58,7 @@ from .prompt_strategies.one_shot import (
 )
 
 if TYPE_CHECKING:
-    from autogpt.app.config import AppConfig
+    from forge.config.config import Config
 
 logger = logging.getLogger(__name__)
 
@@ -95,14 +91,12 @@ class Agent(BaseAgent[OneShotAgentActionProposal], Configurable[AgentSettings]):
         settings: AgentSettings,
         llm_provider: MultiProvider,
         file_storage: FileStorage,
-        app_config: AppConfig,
+        legacy_config: Config,
     ):
         super().__init__(settings)
 
         self.llm_provider = llm_provider
-        prompt_config = OneShotAgentPromptStrategy.default_configuration.model_copy(
-            deep=True
-        )
+        prompt_config = OneShotAgentPromptStrategy.default_configuration.copy(deep=True)
         prompt_config.use_functions_api = (
             settings.config.use_functions_api
             # Anthropic currently doesn't support tools + prefilling :(
@@ -113,41 +107,33 @@ class Agent(BaseAgent[OneShotAgentActionProposal], Configurable[AgentSettings]):
 
         # Components
         self.system = SystemComponent()
-        self.history = (
-            ActionHistoryComponent(
-                settings.history,
-                lambda x: self.llm_provider.count_tokens(x, self.llm.name),
-                llm_provider,
-                ActionHistoryConfiguration(
-                    llm_name=app_config.fast_llm, max_tokens=self.send_token_limit
-                ),
-            )
-            .run_after(WatchdogComponent)
-            .run_after(SystemComponent)
-        )
-        if not app_config.noninteractive_mode:
-            self.user_interaction = UserInteractionComponent()
-        self.file_manager = FileManagerComponent(file_storage, settings)
+        self.history = ActionHistoryComponent(
+            settings.history,
+            self.send_token_limit,
+            lambda x: self.llm_provider.count_tokens(x, self.llm.name),
+            legacy_config,
+            llm_provider,
+        ).run_after(WatchdogComponent)
+        self.user_interaction = UserInteractionComponent(legacy_config)
+        self.file_manager = FileManagerComponent(settings, file_storage)
         self.code_executor = CodeExecutorComponent(
             self.file_manager.workspace,
-            CodeExecutorConfiguration(
-                docker_container_name=f"{settings.agent_id}_sandbox"
-            ),
+            settings,
+            legacy_config,
         )
-        self.git_ops = GitOperationsComponent()
-        self.image_gen = ImageGeneratorComponent(self.file_manager.workspace)
-        self.web_search = WebSearchComponent()
-        self.web_selenium = WebSeleniumComponent(
-            llm_provider,
-            app_config.app_data_dir,
+        self.git_ops = GitOperationsComponent(legacy_config)
+        self.image_gen = ImageGeneratorComponent(
+            self.file_manager.workspace, legacy_config
         )
+        self.web_search = WebSearchComponent(legacy_config)
+        self.web_selenium = WebSeleniumComponent(legacy_config, llm_provider, self.llm)
         self.context = ContextComponent(self.file_manager.workspace, settings.context)
         self.watchdog = WatchdogComponent(settings.config, settings.history).run_after(
             ContextComponent
         )
 
         self.event_history = settings.history
-        self.app_config = app_config
+        self.legacy_config = legacy_config
 
     async def propose_action(self) -> OneShotAgentActionProposal:
         """Proposes the next action to execute, based on the task and current state.
@@ -162,7 +148,7 @@ class Agent(BaseAgent[OneShotAgentActionProposal], Configurable[AgentSettings]):
         constraints = await self.run_pipeline(DirectiveProvider.get_constraints)
         best_practices = await self.run_pipeline(DirectiveProvider.get_best_practices)
 
-        directives = self.state.directives.model_copy(deep=True)
+        directives = self.state.directives.copy(deep=True)
         directives.resources += resources
         directives.constraints += constraints
         directives.best_practices += best_practices
@@ -174,19 +160,13 @@ class Agent(BaseAgent[OneShotAgentActionProposal], Configurable[AgentSettings]):
         # Get messages
         messages = await self.run_pipeline(MessageProvider.get_messages)
 
-        include_os_info = (
-            self.code_executor.config.execute_local_commands
-            if hasattr(self, "code_executor")
-            else False
-        )
-
         prompt: ChatPrompt = self.prompt_strategy.build_prompt(
             messages=messages,
             task=self.state.task,
             ai_profile=self.state.ai_profile,
             ai_directives=directives,
             commands=function_specs_from_commands(self.commands),
-            include_os_info=include_os_info,
+            include_os_info=self.legacy_config.execute_local_commands,
         )
 
         logger.debug(f"Executing prompt:\n{dump_prompt(prompt)}")
@@ -297,7 +277,7 @@ class Agent(BaseAgent[OneShotAgentActionProposal], Configurable[AgentSettings]):
             command
             for command in self.commands
             if not any(
-                name in self.app_config.disabled_commands for name in command.names
+                name in self.legacy_config.disabled_commands for name in command.names
             )
         ]
 

autogpt/autogpt/agents/prompt_strategies/one_shot.py

@@ -28,13 +28,15 @@ _RESPONSE_INTERFACE_NAME = "AssistantResponse"
 
 class AssistantThoughts(ModelWithSummary):
     observations: str = Field(
-        description="Relevant observations from your last action (if any)"
+        ..., description="Relevant observations from your last action (if any)"
     )
-    text: str = Field(description="Thoughts")
-    reasoning: str = Field(description="Reasoning behind the thoughts")
-    self_criticism: str = Field(description="Constructive self-criticism")
-    plan: list[str] = Field(description="Short list that conveys the long-term plan")
-    speak: str = Field(description="Summary of thoughts, to say to user")
+    text: str = Field(..., description="Thoughts")
+    reasoning: str = Field(..., description="Reasoning behind the thoughts")
+    self_criticism: str = Field(..., description="Constructive self-criticism")
+    plan: list[str] = Field(
+        ..., description="Short list that conveys the long-term plan"
+    )
+    speak: str = Field(..., description="Summary of thoughts, to say to user")
 
     def summary(self) -> str:
         return self.text
@@ -94,13 +96,11 @@ class OneShotAgentPromptStrategy(PromptStrategy):
         logger: Logger,
     ):
         self.config = configuration
-        self.response_schema = JSONSchema.from_dict(
-            OneShotAgentActionProposal.model_json_schema()
-        )
+        self.response_schema = JSONSchema.from_dict(OneShotAgentActionProposal.schema())
         self.logger = logger
 
     @property
-    def llm_classification(self) -> LanguageModelClassification:
+    def model_classification(self) -> LanguageModelClassification:
         return LanguageModelClassification.FAST_MODEL  # FIXME: dynamic switching
 
     def build_prompt(
@@ -182,7 +182,7 @@ class OneShotAgentPromptStrategy(PromptStrategy):
         )
 
     def response_format_instruction(self, use_functions_api: bool) -> tuple[str, str]:
-        response_schema = self.response_schema.model_copy(deep=True)
+        response_schema = self.response_schema.copy(deep=True)
         assert response_schema.properties
         if use_functions_api and "use_tool" in response_schema.properties:
             del response_schema.properties["use_tool"]
@@ -274,8 +274,5 @@ class OneShotAgentPromptStrategy(PromptStrategy):
                 raise InvalidAgentResponseError("Assistant did not use a tool")
             assistant_reply_dict["use_tool"] = response.tool_calls[0].function
 
-        parsed_response = OneShotAgentActionProposal.model_validate(
-            assistant_reply_dict
-        )
-        parsed_response.raw_message = response.copy()
+        parsed_response = OneShotAgentActionProposal.parse_obj(assistant_reply_dict)
         return parsed_response

autogpt/autogpt/app/agent_protocol_server.py

@@ -23,6 +23,7 @@ from forge.agent_protocol.models import (
     TaskRequestBody,
     TaskStepsListResponse,
 )
+from forge.config.config import Config
 from forge.file_storage import FileStorage
 from forge.llm.providers import ModelProviderBudget, MultiProvider
 from forge.models.action import ActionErrorResult, ActionSuccessResult
@@ -34,7 +35,6 @@ from sentry_sdk import set_user
 
 from autogpt.agent_factory.configurators import configure_agent_with_state, create_agent
 from autogpt.agents.agent_manager import AgentManager
-from autogpt.app.config import AppConfig
 from autogpt.app.utils import is_port_free
 
 logger = logging.getLogger(__name__)
@@ -45,7 +45,7 @@ class AgentProtocolServer:
 
     def __init__(
         self,
-        app_config: AppConfig,
+        app_config: Config,
         database: AgentDB,
         file_storage: FileStorage,
         llm_provider: MultiProvider,
@@ -314,7 +314,7 @@ class AgentProtocolServer:
                             ""
                             if tool_result is None
                             else (
-                                orjson.loads(tool_result.model_dump_json())
+                                orjson.loads(tool_result.json())
                                 if not isinstance(tool_result, ActionErrorResult)
                                 else {
                                     "error": str(tool_result.error),
@@ -327,7 +327,7 @@ class AgentProtocolServer:
                 if last_proposal and tool_result
                 else {}
             ),
-            **assistant_response.model_dump(),
+            **assistant_response.dict(),
         }
 
         task_cumulative_cost = agent.llm_provider.get_incurred_cost()
@@ -451,9 +451,7 @@ class AgentProtocolServer:
         """
         task_llm_budget = self._task_budgets[task.task_id]
 
-        task_llm_provider_config = self.llm_provider._configuration.model_copy(
-            deep=True
-        )
+        task_llm_provider_config = self.llm_provider._configuration.copy(deep=True)
         _extra_request_headers = task_llm_provider_config.extra_request_headers
         _extra_request_headers["AP-TaskID"] = task.task_id
         if step_id:
@@ -461,7 +459,7 @@ class AgentProtocolServer:
         if task.additional_input and (user_id := task.additional_input.get("user_id")):
             _extra_request_headers["AutoGPT-UserID"] = user_id
 
-        settings = self.llm_provider._settings.model_copy()
+        settings = self.llm_provider._settings.copy()
         settings.budget = task_llm_budget
         settings.configuration = task_llm_provider_config
         task_llm_provider = self.llm_provider.__class__(

autogpt/autogpt/app/cli.py

@@ -28,6 +28,24 @@ def cli(ctx: click.Context):
     help="Defines the number of times to run in continuous mode",
 )
 @click.option("--speak", is_flag=True, help="Enable Speak Mode")
+@click.option(
+    "-b",
+    "--browser-name",
+    help="Specifies which web-browser to use when using selenium to scrape the web.",
+)
+@click.option(
+    "--allow-downloads",
+    is_flag=True,
+    help="Dangerous: Allows AutoGPT to download files natively.",
+)
+@click.option(
+    # TODO: this is a hidden option for now, necessary for integration testing.
+    # We should make this public once we're ready to roll out agent specific workspaces.
+    "--workspace-directory",
+    "-w",
+    type=click.Path(file_okay=False),
+    hidden=True,
+)
 @click.option(
     "--install-plugin-deps",
     is_flag=True,
@@ -110,15 +128,13 @@ def cli(ctx: click.Context):
     ),
     type=click.Choice([i.value for i in LogFormatName]),
 )
-@click.option(
-    "--component-config-file",
-    help="Path to a json configuration file",
-    type=click.Path(exists=True, dir_okay=False, resolve_path=True, path_type=Path),
-)
 def run(
     continuous: bool,
     continuous_limit: Optional[int],
     speak: bool,
+    browser_name: Optional[str],
+    allow_downloads: bool,
+    workspace_directory: Optional[Path],
     install_plugin_deps: bool,
     skip_news: bool,
     skip_reprompt: bool,
@@ -132,7 +148,6 @@ def run(
     log_level: Optional[str],
     log_format: Optional[str],
     log_file_format: Optional[str],
-    component_config_file: Optional[Path],
 ) -> None:
     """
     Sets up and runs an agent, based on the task specified by the user, or resumes an
@@ -150,7 +165,10 @@ def run(
         log_level=log_level,
         log_format=log_format,
         log_file_format=log_file_format,
+        browser_name=browser_name,
+        allow_downloads=allow_downloads,
         skip_news=skip_news,
+        workspace_directory=workspace_directory,
         install_plugin_deps=install_plugin_deps,
         override_ai_name=ai_name,
         override_ai_role=ai_role,
@@ -158,11 +176,20 @@ def run(
         constraints=list(constraint),
         best_practices=list(best_practice),
         override_directives=override_directives,
-        component_config_file=component_config_file,
     )
 
 
 @cli.command()
+@click.option(
+    "-b",
+    "--browser-name",
+    help="Specifies which web-browser to use when using selenium to scrape the web.",
+)
+@click.option(
+    "--allow-downloads",
+    is_flag=True,
+    help="Dangerous: Allows AutoGPT to download files natively.",
+)
 @click.option(
     "--install-plugin-deps",
     is_flag=True,
@@ -190,6 +217,8 @@ def run(
     type=click.Choice([i.value for i in LogFormatName]),
 )
 def serve(
+    browser_name: Optional[str],
+    allow_downloads: bool,
     install_plugin_deps: bool,
     debug: bool,
     log_level: Optional[str],
@@ -208,6 +237,8 @@ def serve(
         log_level=log_level,
         log_format=log_format,
         log_file_format=log_file_format,
+        browser_name=browser_name,
+        allow_downloads=allow_downloads,
         install_plugin_deps=install_plugin_deps,
     )
 

autogpt/autogpt/app/config.py

@@ -1,221 +0,0 @@
-"""Configuration class to store the state of bools for different scripts access."""
-from __future__ import annotations
-
-import logging
-import os
-import re
-from pathlib import Path
-from typing import Optional, Union
-
-import forge
-from forge.config.base import BaseConfig
-from forge.llm.providers import CHAT_MODELS, ModelName
-from forge.llm.providers.openai import OpenAICredentials, OpenAIModelName
-from forge.logging.config import LoggingConfig
-from forge.models.config import Configurable, UserConfigurable
-from pydantic import SecretStr, ValidationInfo, field_validator
-
-logger = logging.getLogger(__name__)
-
-PROJECT_ROOT = Path(forge.__file__).parent.parent
-AZURE_CONFIG_FILE = Path("azure.yaml")
-
-GPT_4_MODEL = OpenAIModelName.GPT4
-GPT_3_MODEL = OpenAIModelName.GPT3
-
-
-class AppConfig(BaseConfig):
-    name: str = "Auto-GPT configuration"
-    description: str = "Default configuration for the Auto-GPT application."
-
-    ########################
-    # Application Settings #
-    ########################
-    project_root: Path = PROJECT_ROOT
-    app_data_dir: Path = project_root / "data"
-    skip_news: bool = False
-    skip_reprompt: bool = False
-    authorise_key: str = UserConfigurable(default="y", from_env="AUTHORISE_COMMAND_KEY")
-    exit_key: str = UserConfigurable(default="n", from_env="EXIT_KEY")
-    noninteractive_mode: bool = False
-    logging: LoggingConfig = LoggingConfig()
-    component_config_file: Optional[Path] = UserConfigurable(
-        default=None, from_env="COMPONENT_CONFIG_FILE"
-    )
-
-    ##########################
-    # Agent Control Settings #
-    ##########################
-    # Model configuration
-    fast_llm: ModelName = UserConfigurable(
-        default=OpenAIModelName.GPT3,
-        from_env="FAST_LLM",
-    )
-    smart_llm: ModelName = UserConfigurable(
-        default=OpenAIModelName.GPT4_TURBO,
-        from_env="SMART_LLM",
-    )
-    temperature: float = UserConfigurable(default=0, from_env="TEMPERATURE")
-    openai_functions: bool = UserConfigurable(
-        default=False, from_env=lambda: os.getenv("OPENAI_FUNCTIONS", "False") == "True"
-    )
-    embedding_model: str = UserConfigurable(
-        default="text-embedding-3-small", from_env="EMBEDDING_MODEL"
-    )
-
-    # Run loop configuration
-    continuous_mode: bool = False
-    continuous_limit: int = 0
-
-    ############
-    # Commands #
-    ############
-    # General
-    disabled_commands: list[str] = UserConfigurable(
-        default_factory=list,
-        from_env=lambda: _safe_split(os.getenv("DISABLED_COMMANDS")),
-    )
-
-    # File ops
-    restrict_to_workspace: bool = UserConfigurable(
-        default=True,
-        from_env=lambda: os.getenv("RESTRICT_TO_WORKSPACE", "True") == "True",
-    )
-
-    ###############
-    # Credentials #
-    ###############
-    # OpenAI
-    openai_credentials: Optional[OpenAICredentials] = None
-    azure_config_file: Optional[Path] = UserConfigurable(
-        default=AZURE_CONFIG_FILE, from_env="AZURE_CONFIG_FILE"
-    )
-
-    @field_validator("openai_functions")
-    def validate_openai_functions(cls, value: bool, info: ValidationInfo):
-        if value:
-            smart_llm = info.data["smart_llm"]
-            assert CHAT_MODELS[smart_llm].has_function_call_api, (
-                f"Model {smart_llm} does not support tool calling. "
-                "Please disable OPENAI_FUNCTIONS or choose a suitable model."
-            )
-        return value
-
-
-class ConfigBuilder(Configurable[AppConfig]):
-    default_settings = AppConfig()
-
-    @classmethod
-    def build_config_from_env(cls, project_root: Path = PROJECT_ROOT) -> AppConfig:
-        """Initialize the Config class"""
-
-        config = cls.build_agent_configuration()
-        config.project_root = project_root
-
-        # Make relative paths absolute
-        for k in {
-            "azure_config_file",  # TODO: move from project root
-        }:
-            setattr(config, k, project_root / getattr(config, k))
-
-        if (
-            config.openai_credentials
-            and config.openai_credentials.api_type == SecretStr("azure")
-            and (config_file := config.azure_config_file)
-        ):
-            config.openai_credentials.load_azure_config(config_file)
-
-        return config
-
-
-async def assert_config_has_required_llm_api_keys(config: AppConfig) -> None:
-    """
-    Check if API keys (if required) are set for the configured SMART_LLM and FAST_LLM.
-    """
-    from forge.llm.providers.anthropic import AnthropicModelName
-    from forge.llm.providers.groq import GroqModelName
-    from pydantic import ValidationError
-
-    if set((config.smart_llm, config.fast_llm)).intersection(AnthropicModelName):
-        from forge.llm.providers.anthropic import AnthropicCredentials
-
-        try:
-            credentials = AnthropicCredentials.from_env()
-        except ValidationError as e:
-            if "api_key" in str(e):
-                logger.error(
-                    "Set your Anthropic API key in .env or as an environment variable"
-                )
-                logger.info(
-                    "For further instructions: "
-                    "https://docs.agpt.co/autogpt/setup/#anthropic"
-                )
-
-            raise ValueError("Anthropic is unavailable: can't load credentials") from e
-
-        key_pattern = r"^sk-ant-api03-[\w\-]{95}"
-
-        # If key is set, but it looks invalid
-        if not re.search(key_pattern, credentials.api_key.get_secret_value()):
-            logger.warning(
-                "Possibly invalid Anthropic API key! "
-                f"Configured Anthropic API key does not match pattern '{key_pattern}'. "
-                "If this is a valid key, please report this warning to the maintainers."
-            )
-
-    if set((config.smart_llm, config.fast_llm)).intersection(GroqModelName):
-        from forge.llm.providers.groq import GroqProvider
-        from groq import AuthenticationError
-
-        try:
-            groq = GroqProvider()
-            await groq.get_available_models()
-        except ValidationError as e:
-            if "api_key" not in str(e):
-                raise
-
-            logger.error("Set your Groq API key in .env or as an environment variable")
-            logger.info(
-                "For further instructions: https://docs.agpt.co/autogpt/setup/#groq"
-            )
-            raise ValueError("Groq is unavailable: can't load credentials")
-        except AuthenticationError as e:
-            logger.error("The Groq API key is invalid!")
-            logger.info(
-                "For instructions to get and set a new API key: "
-                "https://docs.agpt.co/autogpt/setup/#groq"
-            )
-            raise ValueError("Groq is unavailable: invalid API key") from e
-
-    if set((config.smart_llm, config.fast_llm)).intersection(OpenAIModelName):
-        from forge.llm.providers.openai import OpenAIProvider
-        from openai import AuthenticationError
-
-        try:
-            openai = OpenAIProvider()
-            await openai.get_available_models()
-        except ValidationError as e:
-            if "api_key" not in str(e):
-                raise
-
-            logger.error(
-                "Set your OpenAI API key in .env or as an environment variable"
-            )
-            logger.info(
-                "For further instructions: https://docs.agpt.co/autogpt/setup/#openai"
-            )
-            raise ValueError("OpenAI is unavailable: can't load credentials")
-        except AuthenticationError as e:
-            logger.error("The OpenAI API key is invalid!")
-            logger.info(
-                "For instructions to get and set a new API key: "
-                "https://docs.agpt.co/autogpt/setup/#openai"
-            )
-            raise ValueError("OpenAI is unavailable: invalid API key") from e
-
-
-def _safe_split(s: Union[str, None], sep: str = ",") -> list[str]:
-    """Split a string by a separator. Return an empty list if the string is None."""
-    if s is None:
-        return []
-    return s.split(sep)

autogpt/autogpt/app/configurator.py

@@ -5,18 +5,20 @@ import logging
 from typing import Literal, Optional
 
 import click
+from colorama import Back, Style
+from forge.config.config import GPT_3_MODEL, Config
 from forge.llm.providers import ModelName, MultiProvider
 
-from autogpt.app.config import GPT_3_MODEL, AppConfig
-
 logger = logging.getLogger(__name__)
 
 
 async def apply_overrides_to_config(
-    config: AppConfig,
+    config: Config,
     continuous: bool = False,
     continuous_limit: Optional[int] = None,
     skip_reprompt: bool = False,
+    browser_name: Optional[str] = None,
+    allow_downloads: bool = False,
     skip_news: bool = False,
 ) -> None:
     """Updates the config object with the given arguments.
@@ -31,6 +33,8 @@ async def apply_overrides_to_config(
         log_level (int): The global log level for the application.
         log_format (str): The format for the log(s).
         log_file_format (str): Override the format for the log file.
+        browser_name (str): The name of the browser to use for scraping the web.
+        allow_downloads (bool): Whether to allow AutoGPT to download files natively.
         skips_news (bool): Whether to suppress the output of latest news on startup.
     """
     config.continuous_mode = False
@@ -51,33 +55,44 @@ async def apply_overrides_to_config(
         raise click.UsageError("--continuous-limit can only be used with --continuous")
 
     # Check availability of configured LLMs; fallback to other LLM if unavailable
-    config.fast_llm, config.smart_llm = await check_models(
-        (config.fast_llm, "fast_llm"), (config.smart_llm, "smart_llm")
-    )
+    config.fast_llm = await check_model(config.fast_llm, "fast_llm")
+    config.smart_llm = await check_model(config.smart_llm, "smart_llm")
 
     if skip_reprompt:
         config.skip_reprompt = True
 
+    if browser_name:
+        config.selenium_web_browser = browser_name
+
+    if allow_downloads:
+        logger.warning(
+            msg=f"{Back.LIGHTYELLOW_EX}"
+            "AutoGPT will now be able to download and save files to your machine."
+            f"{Back.RESET}"
+            " It is recommended that you monitor any files it downloads carefully.",
+        )
+        logger.warning(
+            msg=f"{Back.RED + Style.BRIGHT}"
+            "NEVER OPEN FILES YOU AREN'T SURE OF!"
+            f"{Style.RESET_ALL}",
+        )
+        config.allow_downloads = True
+
     if skip_news:
         config.skip_news = True
 
 
-async def check_models(
-    *models: tuple[ModelName, Literal["smart_llm", "fast_llm"]]
-) -> tuple[ModelName, ...]:
+async def check_model(
+    model_name: ModelName, model_type: Literal["smart_llm", "fast_llm"]
+) -> ModelName:
     """Check if model is available for use. If not, return gpt-3.5-turbo."""
     multi_provider = MultiProvider()
-    available_models = await multi_provider.get_available_chat_models()
+    models = await multi_provider.get_available_chat_models()
 
-    checked_models: list[ModelName] = []
-    for model, model_type in models:
-        if any(model == m.name for m in available_models):
-            checked_models.append(model)
-        else:
-            logger.warning(
-                f"You don't have access to {model}. "
-                f"Setting {model_type} to {GPT_3_MODEL}."
-            )
-            checked_models.append(GPT_3_MODEL)
+    if any(model_name == m.name for m in models):
+        return model_name
 
-    return tuple(checked_models)
+    logger.warning(
+        f"You don't have access to {model_name}. Setting {model_type} to {GPT_3_MODEL}."
+    )
+    return GPT_3_MODEL

autogpt/autogpt/app/main.py

@@ -21,6 +21,7 @@ from forge.components.code_executor.code_executor import (
 )
 from forge.config.ai_directives import AIDirectives
 from forge.config.ai_profile import AIProfile
+from forge.config.config import Config, ConfigBuilder, assert_config_has_openai_api_key
 from forge.file_storage import FileStorageBackendName, get_storage
 from forge.llm.providers import MultiProvider
 from forge.logging.config import configure_logging
@@ -33,11 +34,6 @@ from forge.utils.exceptions import AgentTerminated, InvalidAgentResponseError
 from autogpt.agent_factory.configurators import configure_agent_with_state, create_agent
 from autogpt.agents.agent_manager import AgentManager
 from autogpt.agents.prompt_strategies.one_shot import AssistantThoughts
-from autogpt.app.config import (
-    AppConfig,
-    ConfigBuilder,
-    assert_config_has_required_llm_api_keys,
-)
 
 if TYPE_CHECKING:
     from autogpt.agents.agent import Agent
@@ -66,7 +62,10 @@ async def run_auto_gpt(
     log_level: Optional[str] = None,
     log_format: Optional[str] = None,
     log_file_format: Optional[str] = None,
+    browser_name: Optional[str] = None,
+    allow_downloads: bool = False,
     skip_news: bool = False,
+    workspace_directory: Optional[Path] = None,
     install_plugin_deps: bool = False,
     override_ai_name: Optional[str] = None,
     override_ai_role: Optional[str] = None,
@@ -74,7 +73,6 @@ async def run_auto_gpt(
     constraints: Optional[list[str]] = None,
     best_practices: Optional[list[str]] = None,
     override_directives: bool = False,
-    component_config_file: Optional[Path] = None,
 ):
     # Set up configuration
     config = ConfigBuilder.build_config_from_env()
@@ -100,13 +98,16 @@ async def run_auto_gpt(
         tts_config=config.tts_config,
     )
 
-    await assert_config_has_required_llm_api_keys(config)
+    # TODO: fill in llm values here
+    assert_config_has_openai_api_key(config)
 
     await apply_overrides_to_config(
         config=config,
         continuous=continuous,
         continuous_limit=continuous_limit,
         skip_reprompt=skip_reprompt,
+        browser_name=browser_name,
+        allow_downloads=allow_downloads,
         skip_news=skip_news,
     )
 
@@ -131,12 +132,15 @@ async def run_auto_gpt(
         print_python_version_info(logger)
         print_attribute("Smart LLM", config.smart_llm)
         print_attribute("Fast LLM", config.fast_llm)
+        print_attribute("Browser", config.selenium_web_browser)
         if config.continuous_mode:
             print_attribute("Continuous Mode", "ENABLED", title_color=Fore.YELLOW)
             if continuous_limit:
                 print_attribute("Continuous Limit", config.continuous_limit)
         if config.tts_config.speak_mode:
             print_attribute("Speak Mode", "ENABLED")
+        if config.allow_downloads:
+            print_attribute("Native Downloading", "ENABLED")
         if we_are_running_in_a_docker_container() or is_docker_available():
             print_attribute("Code Execution", "ENABLED")
         else:
@@ -323,14 +327,6 @@ async def run_auto_gpt(
         #     )
         # ).add_done_callback(update_agent_directives)
 
-    # Load component configuration from file
-    if _config_file := component_config_file or config.component_config_file:
-        try:
-            logger.info(f"Loading component configuration from {_config_file}")
-            agent.load_component_configs(_config_file.read_text())
-        except Exception as e:
-            logger.error(f"Could not load component configuration: {e}")
-
     #################
     # Run the Agent #
     #################
@@ -357,6 +353,8 @@ async def run_auto_gpt_server(
     log_level: Optional[str] = None,
     log_format: Optional[str] = None,
     log_file_format: Optional[str] = None,
+    browser_name: Optional[str] = None,
+    allow_downloads: bool = False,
     install_plugin_deps: bool = False,
 ):
     from .agent_protocol_server import AgentProtocolServer
@@ -382,10 +380,13 @@ async def run_auto_gpt_server(
         tts_config=config.tts_config,
     )
 
-    await assert_config_has_required_llm_api_keys(config)
+    # TODO: fill in llm values here
+    assert_config_has_openai_api_key(config)
 
     await apply_overrides_to_config(
         config=config,
+        browser_name=browser_name,
+        allow_downloads=allow_downloads,
     )
 
     llm_provider = _configure_llm_provider(config)
@@ -410,7 +411,7 @@ async def run_auto_gpt_server(
     )
 
 
-def _configure_llm_provider(config: AppConfig) -> MultiProvider:
+def _configure_llm_provider(config: Config) -> MultiProvider:
     multi_provider = MultiProvider()
     for model in [config.smart_llm, config.fast_llm]:
         # Ensure model providers for configured LLMs are available
@@ -450,15 +451,15 @@ async def run_interaction_loop(
         None
     """
     # These contain both application config and agent config, so grab them here.
-    app_config = agent.app_config
+    legacy_config = agent.legacy_config
     ai_profile = agent.state.ai_profile
     logger = logging.getLogger(__name__)
 
     cycle_budget = cycles_remaining = _get_cycle_budget(
-        app_config.continuous_mode, app_config.continuous_limit
+        legacy_config.continuous_mode, legacy_config.continuous_limit
     )
     spinner = Spinner(
-        "Thinking...", plain_output=app_config.logging.plain_console_output
+        "Thinking...", plain_output=legacy_config.logging.plain_console_output
     )
     stop_reason = None
 
@@ -507,25 +508,22 @@ async def run_interaction_loop(
         ########
         handle_stop_signal()
         # Have the agent determine the next action to take.
-        if not (_ep := agent.event_history.current_episode) or _ep.result:
-            with spinner:
-                try:
-                    action_proposal = await agent.propose_action()
-                except InvalidAgentResponseError as e:
-                    logger.warning(f"The agent's thoughts could not be parsed: {e}")
-                    consecutive_failures += 1
-                    if consecutive_failures >= 3:
-                        logger.error(
-                            "The agent failed to output valid thoughts"
-                            f" {consecutive_failures} times in a row. Terminating..."
-                        )
-                        raise AgentTerminated(
-                            "The agent failed to output valid thoughts"
-                            f" {consecutive_failures} times in a row."
-                        )
-                    continue
-        else:
-            action_proposal = _ep.action
+        with spinner:
+            try:
+                action_proposal = await agent.propose_action()
+            except InvalidAgentResponseError as e:
+                logger.warning(f"The agent's thoughts could not be parsed: {e}")
+                consecutive_failures += 1
+                if consecutive_failures >= 3:
+                    logger.error(
+                        "The agent failed to output valid thoughts"
+                        f" {consecutive_failures} times in a row. Terminating..."
+                    )
+                    raise AgentTerminated(
+                        "The agent failed to output valid thoughts"
+                        f" {consecutive_failures} times in a row."
+                    )
+                continue
 
         consecutive_failures = 0
 
@@ -536,7 +534,7 @@ async def run_interaction_loop(
         update_user(
             ai_profile,
             action_proposal,
-            speak_mode=app_config.tts_config.speak_mode,
+            speak_mode=legacy_config.tts_config.speak_mode,
         )
 
         ##################
@@ -545,7 +543,7 @@ async def run_interaction_loop(
         handle_stop_signal()
         if cycles_remaining == 1:  # Last cycle
             feedback_type, feedback, new_cycles_remaining = await get_user_feedback(
-                app_config,
+                legacy_config,
                 ai_profile,
             )
 
@@ -656,7 +654,7 @@ def update_user(
 
 
 async def get_user_feedback(
-    config: AppConfig,
+    config: Config,
     ai_profile: AIProfile,
 ) -> tuple[UserFeedback, str, int | None]:
     """Gets the user's feedback on the assistant's reply.

autogpt/autogpt/app/setup.py

@@ -4,10 +4,9 @@ from typing import Optional
 
 from forge.config.ai_directives import AIDirectives
 from forge.config.ai_profile import AIProfile
+from forge.config.config import Config
 from forge.logging.utils import print_attribute
 
-from autogpt.app.config import AppConfig
-
 from .input import clean_input
 
 logger = logging.getLogger(__name__)
@@ -47,7 +46,7 @@ def apply_overrides_to_ai_settings(
 async def interactively_revise_ai_settings(
     ai_profile: AIProfile,
     directives: AIDirectives,
-    app_config: AppConfig,
+    app_config: Config,
 ):
     """Interactively revise the AI settings.
 

autogpt/pyproject.toml

@@ -20,24 +20,44 @@ serve = "autogpt.app.cli:serve"
 
 [tool.poetry.dependencies]
 python = "^3.10"
+anthropic = "^0.25.1"
 autogpt-forge = { path = "../forge", develop = true }
 # autogpt-forge = {git = "https://github.com/Significant-Gravitas/AutoGPT.git", subdirectory = "forge"}
+beautifulsoup4 = "^4.12.2"
+charset-normalizer = "^3.1.0"
 click = "*"
 colorama = "^0.4.6"
 distro = "^1.8.0"
+en-core-web-sm = { url = "https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.7.1/en_core_web_sm-3.7.1-py3-none-any.whl" }
 fastapi = "^0.109.1"
-gitpython = "^3.1.32"
+ftfy = "^6.1.1"
+google-api-python-client = "*"
 hypercorn = "^0.14.4"
+inflection = "*"
+jsonschema = "*"
+numpy = "*"
 openai = "^1.7.2"
 orjson = "^3.8.10"
-pydantic = "^2.7.2"
+Pillow = "*"
+pydantic = "*"
+python-docx = "*"
 python-dotenv = "^1.0.0"
+pyyaml = "^6.0"
+readability-lxml = "^0.8.1"
 requests = "*"
 sentry-sdk = "^1.40.4"
+spacy = "^3.7.4"
+tenacity = "^8.2.2"
+
+# OpenAI and Generic plugins import
+openapi-python-client = "^0.14.0"
 
 # Benchmarking
 agbenchmark = { path = "../benchmark", optional = true }
 # agbenchmark = {git = "https://github.com/Significant-Gravitas/AutoGPT.git", subdirectory = "benchmark", optional = true}
+psycopg2-binary = "^2.9.9"
+multidict = "6.0.5"
+cx-freeze = "7.0.0"
 
 [tool.poetry.extras]
 benchmark = ["agbenchmark"]
@@ -45,28 +65,27 @@ benchmark = ["agbenchmark"]
 [tool.poetry.group.dev.dependencies]
 black = "^23.12.1"
 flake8 = "^7.0.0"
+gitpython = "^3.1.32"
 isort = "^5.13.1"
 pre-commit = "*"
 pyright = "^1.1.364"
-
-# Type stubs
+types-beautifulsoup4 = "*"
 types-colorama = "*"
+types-Markdown = "*"
+types-Pillow = "*"
 
 # Testing
+asynctest = "*"
+coverage = "*"
 pytest = "*"
 pytest-asyncio = "*"
+pytest-benchmark = "*"
 pytest-cov = "*"
+pytest-integration = "*"
 pytest-mock = "*"
 pytest-recording = "*"
 pytest-xdist = "*"
-
-[tool.poetry.group.build]
-optional = true
-
-[tool.poetry.group.build.dependencies]
-cx-freeze = { git = "https://github.com/ntindle/cx_Freeze.git", rev = "main" }
-# HACK: switch to cx-freeze release package after #2442 and #2472 are merged: https://github.com/marcelotduarte/cx_Freeze/pulls?q=is:pr+%232442+OR+%232472+
-# cx-freeze = { version = "^7.2.0", optional = true }
+vcrpy = { git = "https://github.com/Significant-Gravitas/vcrpy.git", rev = "master" }
 
 
 [build-system]
@@ -89,3 +108,7 @@ skip_glob = ["data"]
 pythonVersion = "3.10"
 exclude = ["data/**", "**/node_modules", "**/__pycache__", "**/.*"]
 ignore = ["../forge/**"]
+
+
+[tool.pytest.ini_options]
+markers = ["slow", "requires_openai_api_key", "requires_huggingface_api_key"]

autogpt/scripts/git_log_to_release_notes.py

@@ -19,7 +19,7 @@ from autogpt.app.utils import coroutine
     help="Path to the git repository",
 )
 @coroutine
-async def generate_release_notes(repo_path: Optional[str | Path] = None):
+async def generate_release_notes(repo_path: Optional[Path] = None):
     logger = logging.getLogger(generate_release_notes.name)  # pyright: ignore
 
     repo = Repo(repo_path, search_parent_directories=True)

autogpt/scripts/llamafile/.gitignore

@@ -1,3 +0,0 @@
-*.llamafile
-*.llamafile.exe
-llamafile.exe

autogpt/scripts/llamafile/serve.py

@@ -1,165 +0,0 @@
-#!/usr/bin/env python3
-"""
-Use llamafile to serve a (quantized) mistral-7b-instruct-v0.2 model
-
-Usage:
-  cd <repo-root>/autogpt
-  ./scripts/llamafile/serve.py
-"""
-
-import os
-import platform
-import subprocess
-from pathlib import Path
-from typing import Optional
-
-import click
-
-LLAMAFILE = Path("mistral-7b-instruct-v0.2.Q5_K_M.llamafile")
-LLAMAFILE_URL = f"https://huggingface.co/jartine/Mistral-7B-Instruct-v0.2-llamafile/resolve/main/{LLAMAFILE.name}"  # noqa
-LLAMAFILE_EXE = Path("llamafile.exe")
-LLAMAFILE_EXE_URL = "https://github.com/Mozilla-Ocho/llamafile/releases/download/0.8.6/llamafile-0.8.6"  # noqa
-
-
-@click.command()
-@click.option(
-    "--llamafile",
-    type=click.Path(dir_okay=False, path_type=Path),
-    help=f"Name of the llamafile to serve. Default: {LLAMAFILE.name}",
-)
-@click.option("--llamafile_url", help="Download URL for the llamafile you want to use")
-@click.option(
-    "--host", help="Specify the address for the llamafile server to listen on"
-)
-@click.option(
-    "--port", type=int, help="Specify the port for the llamafile server to listen on"
-)
-@click.option(
-    "--force-gpu",
-    is_flag=True,
-    hidden=platform.system() != "Darwin",
-    help="Run the model using only the GPU (AMD or Nvidia). "
-    "Otherwise, both CPU and GPU may be (partially) used.",
-)
-def main(
-    llamafile: Optional[Path] = None,
-    llamafile_url: Optional[str] = None,
-    host: Optional[str] = None,
-    port: Optional[int] = None,
-    force_gpu: bool = False,
-):
-    print(f"type(llamafile) = {type(llamafile)}")
-    if not llamafile:
-        if not llamafile_url:
-            llamafile = LLAMAFILE
-        else:
-            llamafile = Path(llamafile_url.rsplit("/", 1)[1])
-            if llamafile.suffix != ".llamafile":
-                click.echo(
-                    click.style(
-                        "The given URL does not end with '.llamafile' -> "
-                        "can't get filename from URL. "
-                        "Specify the filename using --llamafile.",
-                        fg="red",
-                    ),
-                    err=True,
-                )
-                return
-
-    if llamafile == LLAMAFILE and not llamafile_url:
-        llamafile_url = LLAMAFILE_URL
-    elif llamafile_url != LLAMAFILE_URL:
-        if not click.prompt(
-            click.style(
-                "You seem to have specified a different URL for the default model "
-                f"({llamafile.name}). Are you sure this is correct? "
-                "If you want to use a different model, also specify --llamafile.",
-                fg="yellow",
-            ),
-            type=bool,
-        ):
-            return
-
-    # Go to autogpt/scripts/llamafile/
-    os.chdir(Path(__file__).resolve().parent)
-
-    on_windows = platform.system() == "Windows"
-
-    if not llamafile.is_file():
-        if not llamafile_url:
-            click.echo(
-                click.style(
-                    "Please use --lamafile_url to specify a download URL for "
-                    f"'{llamafile.name}'. "
-                    "This will only be necessary once, so we can download the model.",
-                    fg="red",
-                ),
-                err=True,
-            )
-            return
-
-        download_file(llamafile_url, llamafile)
-
-        if not on_windows:
-            llamafile.chmod(0o755)
-            subprocess.run([llamafile, "--version"], check=True)
-
-    if not on_windows:
-        base_command = [f"./{llamafile}"]
-    else:
-        # Windows does not allow executables over 4GB, so we have to download a
-        # model-less llamafile.exe and run that instead.
-        if not LLAMAFILE_EXE.is_file():
-            download_file(LLAMAFILE_EXE_URL, LLAMAFILE_EXE)
-            LLAMAFILE_EXE.chmod(0o755)
-            subprocess.run([f".\\{LLAMAFILE_EXE}", "--version"], check=True)
-
-        base_command = [f".\\{LLAMAFILE_EXE}", "-m", llamafile]
-
-    if host:
-        base_command.extend(["--host", host])
-    if port:
-        base_command.extend(["--port", str(port)])
-    if force_gpu:
-        base_command.extend(["-ngl", "9999"])
-
-    subprocess.run(
-        [
-            *base_command,
-            "--server",
-            "--nobrowser",
-            "--ctx-size",
-            "0",
-            "--n-predict",
-            "1024",
-        ],
-        check=True,
-    )
-
-    # note: --ctx-size 0 means the prompt context size will be set directly from the
-    # underlying model configuration. This may cause slow response times or consume
-    # a lot of memory.
-
-
-def download_file(url: str, to_file: Path) -> None:
-    print(f"Downloading {to_file.name}...")
-    import urllib.request
-
-    urllib.request.urlretrieve(url, to_file, reporthook=report_download_progress)
-    print()
-
-
-def report_download_progress(chunk_number: int, chunk_size: int, total_size: int):
-    if total_size != -1:
-        downloaded_size = chunk_number * chunk_size
-        percent = min(1, downloaded_size / total_size)
-        bar = "#" * int(40 * percent)
-        print(
-            f"\rDownloading: [{bar:<40}] {percent:.0%}"
-            f" - {downloaded_size/1e6:.1f}/{total_size/1e6:.1f} MB",
-            end="",
-        )
-
-
-if __name__ == "__main__":
-    main()

autogpt/setup.py

@@ -1,9 +1,7 @@
-import platform
-from pathlib import Path
 from pkgutil import iter_modules
-from typing import Union
+from shutil import which
 
-from cx_Freeze import Executable, setup  # type: ignore
+from cx_Freeze import Executable, setup
 
 packages = [
     m.name
@@ -13,47 +11,11 @@ packages = [
     and ("poetry" in m.module_finder.path)  # type: ignore
 ]
 
-# set the icon based on the platform
-icon = "../../assets/gpt_dark_RGB.ico"
-if platform.system() == "Darwin":
-    icon = "../../assets/gpt_dark_RGB.icns"
-elif platform.system() == "Linux":
-    icon = "../../assets/gpt_dark_RGB.png"
-
-
-def txt_to_rtf(input_file: Union[str, Path], output_file: Union[str, Path]) -> None:
-    """
-    Convert a text file to RTF format.
-
-    Args:
-    input_file (Union[str, Path]): Path to the input text file.
-    output_file (Union[str, Path]): Path to the output RTF file.
-
-    Returns:
-    None
-    """
-    input_path = Path(input_file)
-    output_path = Path(output_file)
-
-    with input_path.open("r", encoding="utf-8") as txt_file:
-        content = txt_file.read()
-
-    # RTF header
-    rtf = r"{\rtf1\ansi\deff0 {\fonttbl {\f0 Times New Roman;}}\f0\fs24 "
-
-    # Replace newlines with RTF newline
-    rtf += content.replace("\n", "\\par ")
-
-    # Close RTF document
-    rtf += "}"
-
-    with output_path.open("w", encoding="utf-8") as rtf_file:
-        rtf_file.write(rtf)
-
-
-# Convert LICENSE to LICENSE.rtf
-license_file = "LICENSE.rtf"
-txt_to_rtf("../LICENSE", license_file)
+icon = (
+    "../../assets/gpt_dark_RGB.icns"
+    if which("sips")
+    else "../../assets/gpt_dark_RGB.ico"
+)
 
 
 setup(
@@ -93,7 +55,6 @@ setup(
             "target_name": "AutoGPT",
             "add_to_path": True,
             "install_icon": "../assets/gpt_dark_RGB.ico",
-            "license_file": license_file,
         },
     },
 )

autogpt/tests/conftest.py

@@ -6,6 +6,7 @@ from pathlib import Path
 
 import pytest
 from forge.config.ai_profile import AIProfile
+from forge.config.config import Config, ConfigBuilder
 from forge.file_storage.local import (
     FileStorage,
     FileStorageConfiguration,
@@ -15,11 +16,11 @@ from forge.llm.providers import MultiProvider
 from forge.logging.config import configure_logging
 
 from autogpt.agents.agent import Agent, AgentConfiguration, AgentSettings
-from autogpt.app.config import AppConfig, ConfigBuilder
 from autogpt.app.main import _configure_llm_provider
 
 pytest_plugins = [
     "tests.integration.agent_factory",
+    "tests.vcr",
 ]
 
 
@@ -61,7 +62,7 @@ def config(
 
 
 @pytest.fixture(scope="session")
-def setup_logger():
+def setup_logger(config: Config):
     configure_logging(
         debug=True,
         log_dir=Path(__file__).parent / "logs",
@@ -70,14 +71,12 @@ def setup_logger():
 
 
 @pytest.fixture
-def llm_provider(config: AppConfig) -> MultiProvider:
+def llm_provider(config: Config) -> MultiProvider:
     return _configure_llm_provider(config)
 
 
 @pytest.fixture
-def agent(
-    config: AppConfig, llm_provider: MultiProvider, storage: FileStorage
-) -> Agent:
+def agent(config: Config, llm_provider: MultiProvider, storage: FileStorage) -> Agent:
     ai_profile = AIProfile(
         ai_name="Base",
         ai_role="A base AI",
@@ -95,13 +94,13 @@ def agent(
             allow_fs_access=not config.restrict_to_workspace,
             use_functions_api=config.openai_functions,
         ),
-        history=Agent.default_settings.history.model_copy(deep=True),
+        history=Agent.default_settings.history.copy(deep=True),
     )
 
     agent = Agent(
         settings=agent_settings,
         llm_provider=llm_provider,
         file_storage=storage,
-        app_config=config,
+        legacy_config=config,
     )
     return agent

autogpt/tests/integration/agent_factory.py

@@ -2,15 +2,15 @@ from pathlib import Path
 
 import pytest
 from forge.config.ai_profile import AIProfile
+from forge.config.config import Config
 from forge.file_storage import FileStorageBackendName, get_storage
 from forge.llm.providers import MultiProvider
 
 from autogpt.agents.agent import Agent, AgentConfiguration, AgentSettings
-from autogpt.app.config import AppConfig
 
 
 @pytest.fixture
-def dummy_agent(config: AppConfig, llm_provider: MultiProvider):
+def dummy_agent(config: Config, llm_provider: MultiProvider):
     ai_profile = AIProfile(
         ai_name="Dummy Agent",
         ai_role="Dummy Role",
@@ -28,7 +28,7 @@ def dummy_agent(config: AppConfig, llm_provider: MultiProvider):
             smart_llm=config.smart_llm,
             use_functions_api=config.openai_functions,
         ),
-        history=Agent.default_settings.history.model_copy(deep=True),
+        history=Agent.default_settings.history.copy(deep=True),
     )
 
     local = config.file_storage_backend == FileStorageBackendName.LOCAL
@@ -44,7 +44,7 @@ def dummy_agent(config: AppConfig, llm_provider: MultiProvider):
         settings=agent_settings,
         llm_provider=llm_provider,
         file_storage=file_storage,
-        app_config=config,
+        legacy_config=config,
     )
 
     return agent

autogpt/tests/integration/test_execute_code.py

@@ -4,20 +4,20 @@ import tempfile
 from pathlib import Path
 
 import pytest
-
-from forge.file_storage.base import FileStorage
-from forge.utils.exceptions import InvalidArgumentError, OperationNotAllowedError
-
-from .code_executor import (
+from forge.components.code_executor.code_executor import (
+    ALLOWLIST_CONTROL,
     CodeExecutorComponent,
     is_docker_available,
     we_are_running_in_a_docker_container,
 )
+from forge.utils.exceptions import InvalidArgumentError, OperationNotAllowedError
+
+from autogpt.agents.agent import Agent
 
 
 @pytest.fixture
-def code_executor_component(storage: FileStorage):
-    return CodeExecutorComponent(storage)
+def code_executor_component(agent: Agent):
+    return agent.code_executor
 
 
 @pytest.fixture
@@ -26,8 +26,10 @@ def random_code(random_string) -> str:
 
 
 @pytest.fixture
-def python_test_file(storage: FileStorage, random_code: str):
-    temp_file = tempfile.NamedTemporaryFile(dir=storage.root, suffix=".py")
+def python_test_file(agent: Agent, random_code: str):
+    temp_file = tempfile.NamedTemporaryFile(
+        dir=agent.file_manager.workspace.root, suffix=".py"
+    )
     temp_file.write(str.encode(random_code))
     temp_file.flush()
 
@@ -36,8 +38,10 @@ def python_test_file(storage: FileStorage, random_code: str):
 
 
 @pytest.fixture
-def python_test_args_file(storage: FileStorage):
-    temp_file = tempfile.NamedTemporaryFile(dir=storage.root, suffix=".py")
+def python_test_args_file(agent: Agent):
+    temp_file = tempfile.NamedTemporaryFile(
+        dir=agent.file_manager.workspace.root, suffix=".py"
+    )
     temp_file.write(str.encode("import sys\nprint(sys.argv[1], sys.argv[2])"))
     temp_file.flush()
 
@@ -54,6 +58,7 @@ def test_execute_python_file(
     code_executor_component: CodeExecutorComponent,
     python_test_file: Path,
     random_string: str,
+    agent: Agent,
 ):
     if not (is_docker_available() or we_are_running_in_a_docker_container()):
         pytest.skip("Docker is not available")
@@ -66,6 +71,7 @@ def test_execute_python_file_args(
     code_executor_component: CodeExecutorComponent,
     python_test_args_file: Path,
     random_string: str,
+    agent: Agent,
 ):
     if not (is_docker_available() or we_are_running_in_a_docker_container()):
         pytest.skip("Docker is not available")
@@ -83,6 +89,7 @@ async def test_execute_python_code(
     code_executor_component: CodeExecutorComponent,
     random_code: str,
     random_string: str,
+    agent: Agent,
 ):
     if not (is_docker_available() or we_are_running_in_a_docker_container()):
         pytest.skip("Docker is not available")
@@ -91,12 +98,16 @@ async def test_execute_python_code(
     assert result.replace("\r", "") == f"Hello {random_string}!\n"
 
 
-def test_execute_python_file_invalid(code_executor_component: CodeExecutorComponent):
+def test_execute_python_file_invalid(
+    code_executor_component: CodeExecutorComponent, agent: Agent
+):
     with pytest.raises(InvalidArgumentError):
         code_executor_component.execute_python_file(Path("not_python.txt"))
 
 
-def test_execute_python_file_not_found(code_executor_component: CodeExecutorComponent):
+def test_execute_python_file_not_found(
+    code_executor_component: CodeExecutorComponent, agent: Agent
+):
     with pytest.raises(
         FileNotFoundError,
         match=r"python: can't open file '([a-zA-Z]:)?[/\\\-\w]*notexist.py': "
@@ -106,56 +117,52 @@ def test_execute_python_file_not_found(code_executor_component: CodeExecutorComp
 
 
 def test_execute_shell(
-    code_executor_component: CodeExecutorComponent, random_string: str
+    code_executor_component: CodeExecutorComponent, random_string: str, agent: Agent
 ):
-    code_executor_component.config.shell_command_control = "allowlist"
-    code_executor_component.config.shell_allowlist = ["echo"]
     result = code_executor_component.execute_shell(f"echo 'Hello {random_string}!'")
     assert f"Hello {random_string}!" in result
 
 
 def test_execute_shell_local_commands_not_allowed(
-    code_executor_component: CodeExecutorComponent, random_string: str
+    code_executor_component: CodeExecutorComponent, random_string: str, agent: Agent
 ):
-    with pytest.raises(OperationNotAllowedError, match="not allowed"):
-        code_executor_component.execute_shell(f"echo 'Hello {random_string}!'")
+    result = code_executor_component.execute_shell(f"echo 'Hello {random_string}!'")
+    assert f"Hello {random_string}!" in result
 
 
 def test_execute_shell_denylist_should_deny(
-    code_executor_component: CodeExecutorComponent, random_string: str
+    code_executor_component: CodeExecutorComponent, agent: Agent, random_string: str
 ):
-    code_executor_component.config.shell_command_control = "denylist"
-    code_executor_component.config.shell_denylist = ["echo"]
+    agent.legacy_config.shell_denylist = ["echo"]
 
     with pytest.raises(OperationNotAllowedError, match="not allowed"):
         code_executor_component.execute_shell(f"echo 'Hello {random_string}!'")
 
 
 def test_execute_shell_denylist_should_allow(
-    code_executor_component: CodeExecutorComponent, random_string: str
+    code_executor_component: CodeExecutorComponent, agent: Agent, random_string: str
 ):
-    code_executor_component.config.shell_command_control = "denylist"
-    code_executor_component.config.shell_denylist = ["cat"]
+    agent.legacy_config.shell_denylist = ["cat"]
 
     result = code_executor_component.execute_shell(f"echo 'Hello {random_string}!'")
     assert "Hello" in result and random_string in result
 
 
 def test_execute_shell_allowlist_should_deny(
-    code_executor_component: CodeExecutorComponent, random_string: str
+    code_executor_component: CodeExecutorComponent, agent: Agent, random_string: str
 ):
-    code_executor_component.config.shell_command_control = "allowlist"
-    code_executor_component.config.shell_allowlist = ["cat"]
+    agent.legacy_config.shell_command_control = ALLOWLIST_CONTROL
+    agent.legacy_config.shell_allowlist = ["cat"]
 
     with pytest.raises(OperationNotAllowedError, match="not allowed"):
         code_executor_component.execute_shell(f"echo 'Hello {random_string}!'")
 
 
 def test_execute_shell_allowlist_should_allow(
-    code_executor_component: CodeExecutorComponent, random_string: str
+    code_executor_component: CodeExecutorComponent, agent: Agent, random_string: str
 ):
-    code_executor_component.config.shell_command_control = "allowlist"
-    code_executor_component.config.shell_allowlist = ["echo"]
+    agent.legacy_config.shell_command_control = ALLOWLIST_CONTROL
+    agent.legacy_config.shell_allowlist = ["echo"]
 
     result = code_executor_component.execute_shell(f"echo 'Hello {random_string}!'")
     assert "Hello" in result and random_string in result

autogpt/tests/integration/test_image_gen.py

@@ -4,33 +4,15 @@ from pathlib import Path
 from unittest.mock import patch
 
 import pytest
-from PIL import Image
-from pydantic import SecretStr, ValidationError
-
 from forge.components.image_gen import ImageGeneratorComponent
-from forge.components.image_gen.image_gen import ImageGeneratorConfiguration
-from forge.file_storage.base import FileStorage
-from forge.llm.providers.openai import OpenAICredentials
+from PIL import Image
+
+from autogpt.agents.agent import Agent
 
 
 @pytest.fixture
-def image_gen_component(storage: FileStorage):
-    try:
-        cred = OpenAICredentials.from_env()
-    except ValidationError:
-        cred = OpenAICredentials(api_key=SecretStr("test"))
-
-    return ImageGeneratorComponent(storage, openai_credentials=cred)
-
-
-@pytest.fixture
-def huggingface_image_gen_component(storage: FileStorage):
-    config = ImageGeneratorConfiguration(
-        image_provider="huggingface",
-        huggingface_api_token=SecretStr("1"),
-        huggingface_image_model="CompVis/stable-diffusion-v1-4",
-    )
-    return ImageGeneratorComponent(storage, config=config)
+def image_gen_component(agent: Agent):
+    return agent.image_gen
 
 
 @pytest.fixture(params=[256, 512, 1024])
@@ -39,14 +21,20 @@ def image_size(request):
     return request.param
 
 
+@pytest.mark.requires_openai_api_key
 @pytest.mark.vcr
 def test_dalle(
     image_gen_component: ImageGeneratorComponent,
+    agent: Agent,
+    storage,
     image_size,
+    cached_openai_client,
 ):
     """Test DALL-E image generation."""
     generate_and_validate(
         image_gen_component,
+        agent,
+        storage,
         image_provider="dalle",
         image_size=image_size,
     )
@@ -56,18 +44,23 @@ def test_dalle(
     reason="The image is too big to be put in a cassette for a CI pipeline. "
     "We're looking into a solution."
 )
+@pytest.mark.requires_huggingface_api_key
 @pytest.mark.parametrize(
     "image_model",
     ["CompVis/stable-diffusion-v1-4", "stabilityai/stable-diffusion-2-1"],
 )
 def test_huggingface(
     image_gen_component: ImageGeneratorComponent,
+    agent: Agent,
+    storage,
     image_size,
     image_model,
 ):
     """Test HuggingFace image generation."""
     generate_and_validate(
         image_gen_component,
+        agent,
+        storage,
         image_provider="huggingface",
         image_size=image_size,
         hugging_face_image_model=image_model,
@@ -75,10 +68,14 @@ def test_huggingface(
 
 
 @pytest.mark.xfail(reason="SD WebUI call does not work.")
-def test_sd_webui(image_gen_component: ImageGeneratorComponent, image_size):
+def test_sd_webui(
+    image_gen_component: ImageGeneratorComponent, agent: Agent, storage, image_size
+):
     """Test SD WebUI image generation."""
     generate_and_validate(
         image_gen_component,
+        agent,
+        storage,
         image_provider="sd_webui",
         image_size=image_size,
     )
@@ -86,7 +83,7 @@ def test_sd_webui(image_gen_component: ImageGeneratorComponent, image_size):
 
 @pytest.mark.xfail(reason="SD WebUI call does not work.")
 def test_sd_webui_negative_prompt(
-    image_gen_component: ImageGeneratorComponent, image_size
+    image_gen_component: ImageGeneratorComponent, storage, image_size
 ):
     gen_image = functools.partial(
         image_gen_component.generate_image_with_sd_webui,
@@ -117,15 +114,17 @@ def lst(txt):
 
 def generate_and_validate(
     image_gen_component: ImageGeneratorComponent,
+    agent: Agent,
+    storage,
     image_size,
     image_provider,
     hugging_face_image_model=None,
     **kwargs,
 ):
     """Generate an image and validate the output."""
-    image_gen_component.config.image_provider = image_provider
+    agent.legacy_config.image_provider = image_provider
     if hugging_face_image_model:
-        image_gen_component.config.huggingface_image_model = hugging_face_image_model
+        agent.legacy_config.huggingface_image_model = hugging_face_image_model
     prompt = "astronaut riding a horse"
 
     image_path = lst(image_gen_component.generate_image(prompt, image_size, **kwargs))
@@ -150,7 +149,9 @@ def generate_and_validate(
 )
 @pytest.mark.parametrize("delay", [10, 0])
 def test_huggingface_fail_request_with_delay(
-    huggingface_image_gen_component: ImageGeneratorComponent,
+    image_gen_component: ImageGeneratorComponent,
+    agent: Agent,
+    storage,
     image_size,
     image_model,
     return_text,
@@ -172,12 +173,14 @@ def test_huggingface_fail_request_with_delay(
             mock_post.return_value.ok = False
             mock_post.return_value.text = return_text
 
-        huggingface_image_gen_component.config.huggingface_image_model = image_model
+        agent.legacy_config.image_provider = "huggingface"
+        agent.legacy_config.huggingface_api_token = "mock-api-key"
+        agent.legacy_config.huggingface_image_model = image_model
         prompt = "astronaut riding a horse"
 
         with patch("time.sleep") as mock_sleep:
             # Verify request fails.
-            result = huggingface_image_gen_component.generate_image(prompt, image_size)
+            result = image_gen_component.generate_image(prompt, image_size)
             assert result == "Error creating image."
 
             # Verify retry was called with delay if delay is in return_text
@@ -188,8 +191,10 @@ def test_huggingface_fail_request_with_delay(
 
 
 def test_huggingface_fail_request_no_delay(
-    mocker, huggingface_image_gen_component: ImageGeneratorComponent
+    mocker, image_gen_component: ImageGeneratorComponent, agent: Agent
 ):
+    agent.legacy_config.huggingface_api_token = "1"
+
     # Mock requests.post
     mock_post = mocker.patch("requests.post")
     mock_post.return_value.status_code = 500
@@ -201,9 +206,10 @@ def test_huggingface_fail_request_no_delay(
     # Mock time.sleep
     mock_sleep = mocker.patch("time.sleep")
 
-    result = huggingface_image_gen_component.generate_image(
-        "astronaut riding a horse", 512
-    )
+    agent.legacy_config.image_provider = "huggingface"
+    agent.legacy_config.huggingface_image_model = "CompVis/stable-diffusion-v1-4"
+
+    result = image_gen_component.generate_image("astronaut riding a horse", 512)
 
     assert result == "Error creating image."
 
@@ -212,8 +218,10 @@ def test_huggingface_fail_request_no_delay(
 
 
 def test_huggingface_fail_request_bad_json(
-    mocker, huggingface_image_gen_component: ImageGeneratorComponent
+    mocker, image_gen_component: ImageGeneratorComponent, agent: Agent
 ):
+    agent.legacy_config.huggingface_api_token = "1"
+
     # Mock requests.post
     mock_post = mocker.patch("requests.post")
     mock_post.return_value.status_code = 500
@@ -223,9 +231,10 @@ def test_huggingface_fail_request_bad_json(
     # Mock time.sleep
     mock_sleep = mocker.patch("time.sleep")
 
-    result = huggingface_image_gen_component.generate_image(
-        "astronaut riding a horse", 512
-    )
+    agent.legacy_config.image_provider = "huggingface"
+    agent.legacy_config.huggingface_image_model = "CompVis/stable-diffusion-v1-4"
+
+    result = image_gen_component.generate_image("astronaut riding a horse", 512)
 
     assert result == "Error creating image."
 
@@ -234,14 +243,17 @@ def test_huggingface_fail_request_bad_json(
 
 
 def test_huggingface_fail_request_bad_image(
-    mocker, huggingface_image_gen_component: ImageGeneratorComponent
+    mocker, image_gen_component: ImageGeneratorComponent, agent: Agent
 ):
+    agent.legacy_config.huggingface_api_token = "1"
+
     # Mock requests.post
     mock_post = mocker.patch("requests.post")
     mock_post.return_value.status_code = 200
 
-    result = huggingface_image_gen_component.generate_image(
-        "astronaut riding a horse", 512
-    )
+    agent.legacy_config.image_provider = "huggingface"
+    agent.legacy_config.huggingface_image_model = "CompVis/stable-diffusion-v1-4"
+
+    result = image_gen_component.generate_image("astronaut riding a horse", 512)
 
     assert result == "Error creating image."

autogpt/tests/integration/test_setup.py

@@ -3,8 +3,8 @@ from unittest.mock import patch
 import pytest
 from forge.config.ai_directives import AIDirectives
 from forge.config.ai_profile import AIProfile
+from forge.config.config import Config
 
-from autogpt.app.config import AppConfig
 from autogpt.app.setup import (
     apply_overrides_to_ai_settings,
     interactively_revise_ai_settings,
@@ -39,7 +39,7 @@ async def test_apply_overrides_to_ai_settings():
 
 
 @pytest.mark.asyncio
-async def test_interactively_revise_ai_settings(config: AppConfig):
+async def test_interactively_revise_ai_settings(config: Config):
     ai_profile = AIProfile(ai_name="Test AI", ai_role="Test Role")
     directives = AIDirectives(
         resources=["Resource1"],

autogpt/tests/integration/test_web_selenium.py

@@ -1,20 +1,19 @@
-from pathlib import Path
-
 import pytest
+from forge.components.web.selenium import BrowsingError, WebSeleniumComponent
 
-from forge.llm.providers.multi import MultiProvider
-
-from . import BrowsingError, WebSeleniumComponent
+from autogpt.agents.agent import Agent
 
 
 @pytest.fixture
-def web_selenium_component(app_data_dir: Path):
-    return WebSeleniumComponent(MultiProvider(), app_data_dir)
+def web_selenium_component(agent: Agent):
+    return agent.web_selenium
 
 
+@pytest.mark.vcr
+@pytest.mark.requires_openai_api_key
 @pytest.mark.asyncio
 async def test_browse_website_nonexistent_url(
-    web_selenium_component: WebSeleniumComponent,
+    web_selenium_component: WebSeleniumComponent, cached_openai_client: None
 ):
     url = "https://auto-gpt-thinks-this-website-does-not-exist.com"
     question = "How to execute a barrel roll"

autogpt/tests/unit/test_config.py

@@ -8,15 +8,15 @@ from typing import Any
 from unittest import mock
 
 import pytest
+from forge.config.config import GPT_3_MODEL, GPT_4_MODEL, Config, ConfigBuilder
 from openai.pagination import AsyncPage
 from openai.types import Model
 from pydantic import SecretStr
 
-from autogpt.app.config import GPT_3_MODEL, GPT_4_MODEL, AppConfig, ConfigBuilder
 from autogpt.app.configurator import apply_overrides_to_config
 
 
-def test_initial_values(config: AppConfig) -> None:
+def test_initial_values(config: Config) -> None:
     """
     Test if the initial values of the config class attributes are set correctly.
     """
@@ -29,7 +29,7 @@ def test_initial_values(config: AppConfig) -> None:
 @pytest.mark.asyncio
 @mock.patch("openai.resources.models.AsyncModels.list")
 async def test_fallback_to_gpt3_if_gpt4_not_available(
-    mock_list_models: Any, config: AppConfig
+    mock_list_models: Any, config: Config
 ) -> None:
     """
     Test if models update to gpt-3.5-turbo if gpt-4 is not available.
@@ -51,7 +51,7 @@ async def test_fallback_to_gpt3_if_gpt4_not_available(
     assert config.smart_llm == GPT_3_MODEL
 
 
-def test_missing_azure_config(config: AppConfig) -> None:
+def test_missing_azure_config(config: Config) -> None:
     assert config.openai_credentials is not None
 
     config_file = config.app_data_dir / "azure_config.yaml"
@@ -68,7 +68,7 @@ def test_missing_azure_config(config: AppConfig) -> None:
 
 
 @pytest.fixture
-def config_with_azure(config: AppConfig):
+def config_with_azure(config: Config):
     config_file = config.app_data_dir / "azure_config.yaml"
     config_file.write_text(
         f"""
@@ -91,7 +91,7 @@ azure_model_map:
     del os.environ["AZURE_CONFIG_FILE"]
 
 
-def test_azure_config(config_with_azure: AppConfig) -> None:
+def test_azure_config(config_with_azure: Config) -> None:
     assert (credentials := config_with_azure.openai_credentials) is not None
     assert credentials.api_type == SecretStr("azure")
     assert credentials.api_version == SecretStr("2023-06-01-preview")

autogpt/tests/unit/test_file_operations.py

@@ -2,11 +2,9 @@ import os
 from pathlib import Path
 
 import pytest
-
-from forge.agent.base import BaseAgentSettings
 from forge.file_storage import FileStorage
 
-from . import FileManagerComponent
+from autogpt.agents.agent import Agent
 
 
 @pytest.fixture()
@@ -15,13 +13,8 @@ def file_content():
 
 
 @pytest.fixture
-def file_manager_component(storage: FileStorage):
-    return FileManagerComponent(
-        storage,
-        BaseAgentSettings(
-            agent_id="TestAgent", name="TestAgent", description="Test Agent description"
-        ),
-    )
+def file_manager_component(agent: Agent):
+    return agent.file_manager
 
 
 @pytest.fixture()
@@ -48,14 +41,15 @@ def test_nested_file(storage: FileStorage):
 async def test_read_file(
     test_file_path: Path,
     file_content,
-    file_manager_component: FileManagerComponent,
+    file_manager_component,
+    agent: Agent,
 ):
-    await file_manager_component.workspace.write_file(test_file_path.name, file_content)
+    await agent.file_manager.workspace.write_file(test_file_path.name, file_content)
     content = file_manager_component.read_file(test_file_path.name)
     assert content.replace("\r", "") == file_content
 
 
-def test_read_file_not_found(file_manager_component: FileManagerComponent):
+def test_read_file_not_found(file_manager_component):
     filename = "does_not_exist.txt"
     with pytest.raises(FileNotFoundError):
         file_manager_component.read_file(filename)
@@ -63,12 +57,12 @@ def test_read_file_not_found(file_manager_component: FileManagerComponent):
 
 @pytest.mark.asyncio
 async def test_write_to_file_relative_path(
-    test_file_name: Path, file_manager_component: FileManagerComponent
+    test_file_name: Path, file_manager_component, agent: Agent
 ):
     new_content = "This is new content.\n"
     await file_manager_component.write_to_file(test_file_name, new_content)
     with open(
-        file_manager_component.workspace.get_path(test_file_name), "r", encoding="utf-8"
+        agent.file_manager.workspace.get_path(test_file_name), "r", encoding="utf-8"
     ) as f:
         content = f.read()
     assert content == new_content
@@ -76,7 +70,7 @@ async def test_write_to_file_relative_path(
 
 @pytest.mark.asyncio
 async def test_write_to_file_absolute_path(
-    test_file_path: Path, file_manager_component: FileManagerComponent
+    test_file_path: Path, file_manager_component
 ):
     new_content = "This is new content.\n"
     await file_manager_component.write_to_file(test_file_path, new_content)
@@ -86,18 +80,18 @@ async def test_write_to_file_absolute_path(
 
 
 @pytest.mark.asyncio
-async def test_list_files(file_manager_component: FileManagerComponent):
+async def test_list_files(file_manager_component, agent: Agent):
     # Create files A and B
     file_a_name = "file_a.txt"
     file_b_name = "file_b.txt"
     test_directory = Path("test_directory")
 
-    await file_manager_component.workspace.write_file(file_a_name, "This is file A.")
-    await file_manager_component.workspace.write_file(file_b_name, "This is file B.")
+    await agent.file_manager.workspace.write_file(file_a_name, "This is file A.")
+    await agent.file_manager.workspace.write_file(file_b_name, "This is file B.")
 
     # Create a subdirectory and place a copy of file_a in it
-    file_manager_component.workspace.make_dir(test_directory)
-    await file_manager_component.workspace.write_file(
+    agent.file_manager.workspace.make_dir(test_directory)
+    await agent.file_manager.workspace.write_file(
         test_directory / file_a_name, "This is file A in the subdirectory."
     )
 
@@ -107,10 +101,10 @@ async def test_list_files(file_manager_component: FileManagerComponent):
     assert os.path.join(test_directory, file_a_name) in files
 
     # Clean up
-    file_manager_component.workspace.delete_file(file_a_name)
-    file_manager_component.workspace.delete_file(file_b_name)
-    file_manager_component.workspace.delete_file(test_directory / file_a_name)
-    file_manager_component.workspace.delete_dir(test_directory)
+    agent.file_manager.workspace.delete_file(file_a_name)
+    agent.file_manager.workspace.delete_file(file_b_name)
+    agent.file_manager.workspace.delete_file(test_directory / file_a_name)
+    agent.file_manager.workspace.delete_dir(test_directory)
 
     # Case 2: Search for a file that does not exist and make sure we don't throw
     non_existent_file = "non_existent_file.txt"

autogpt/tests/unit/test_gcs_file_storage.py

@@ -4,12 +4,11 @@ from pathlib import Path
 
 import pytest
 import pytest_asyncio
+from forge.file_storage.gcs import GCSFileStorage, GCSFileStorageConfiguration
 from google.auth.exceptions import GoogleAuthError
 from google.cloud import storage
 from google.cloud.exceptions import NotFound
 
-from .gcs import GCSFileStorage, GCSFileStorageConfiguration
-
 try:
     storage.Client()
 except GoogleAuthError:

autogpt/tests/unit/test_git_commands.py

@@ -1,11 +1,11 @@
 import pytest
+from forge.components.git_operations import GitOperationsComponent
+from forge.file_storage.base import FileStorage
+from forge.utils.exceptions import CommandExecutionError
 from git.exc import GitCommandError
 from git.repo.base import Repo
 
-from forge.file_storage.base import FileStorage
-from forge.utils.exceptions import CommandExecutionError
-
-from . import GitOperationsComponent
+from autogpt.agents.agent import Agent
 
 
 @pytest.fixture
@@ -14,14 +14,15 @@ def mock_clone_from(mocker):
 
 
 @pytest.fixture
-def git_ops_component():
-    return GitOperationsComponent()
+def git_ops_component(agent: Agent):
+    return agent.git_ops
 
 
 def test_clone_auto_gpt_repository(
     git_ops_component: GitOperationsComponent,
     storage: FileStorage,
     mock_clone_from,
+    agent: Agent,
 ):
     mock_clone_from.return_value = None
 
@@ -36,7 +37,7 @@ def test_clone_auto_gpt_repository(
 
     assert clone_result == expected_output
     mock_clone_from.assert_called_once_with(
-        url=f"{scheme}{git_ops_component.config.github_username}:{git_ops_component.config.github_api_key}@{repo}",  # noqa: E501
+        url=f"{scheme}{agent.legacy_config.github_username}:{agent.legacy_config.github_api_key}@{repo}",  # noqa: E501
         to_path=clone_path,
     )
 
@@ -45,6 +46,7 @@ def test_clone_repository_error(
     git_ops_component: GitOperationsComponent,
     storage: FileStorage,
     mock_clone_from,
+    agent: Agent,
 ):
     url = "https://github.com/this-repository/does-not-exist.git"
     clone_path = storage.get_path("does-not-exist")

autogpt/tests/unit/test_json.py

@@ -1,8 +1,7 @@
 import json
 
 import pytest
-
-from .parsing import json_loads
+from forge.json.parsing import json_loads
 
 _JSON_FIXABLE: list[tuple[str, str]] = [
     # Missing comma

autogpt/tests/unit/test_local_file_storage.py

@@ -1,8 +1,7 @@
 from pathlib import Path
 
 import pytest
-
-from .local import FileStorageConfiguration, LocalFileStorage
+from forge.file_storage.local import FileStorageConfiguration, LocalFileStorage
 
 _ACCESSIBLE_PATHS = [
     Path("."),

autogpt/tests/unit/test_logs.py

@@ -1,6 +1,5 @@
 import pytest
-
-from .utils import remove_color_codes
+from forge.logging.utils import remove_color_codes
 
 
 @pytest.mark.parametrize(

autogpt/tests/unit/test_s3_file_storage.py

@@ -5,8 +5,7 @@ from pathlib import Path
 import pytest
 import pytest_asyncio
 from botocore.exceptions import ClientError
-
-from .s3 import S3FileStorage, S3FileStorageConfiguration
+from forge.file_storage.s3 import S3FileStorage, S3FileStorageConfiguration
 
 if not (os.getenv("S3_ENDPOINT_URL") and os.getenv("AWS_ACCESS_KEY_ID")):
     pytest.skip("S3 environment variables are not set", allow_module_level=True)

autogpt/tests/unit/test_text_file_parsers.py

@@ -9,8 +9,7 @@ import docx
 import pytest
 import yaml
 from bs4 import BeautifulSoup
-
-from .file_operations import decode_textual_file, is_file_binary_fn
+from forge.utils.file_operations import decode_textual_file, is_file_binary_fn
 
 logger = logging.getLogger(__name__)
 

autogpt/tests/unit/test_url_validation.py

@@ -1,8 +1,7 @@
 import pytest
+from forge.utils.url_validator import validate_url
 from pytest import raises
 
-from .url_validator import validate_url
-
 
 @validate_url
 def dummy_method(url):

autogpt/tests/unit/test_web_search.py

@@ -1,23 +1,16 @@
 import json
 
 import pytest
-from googleapiclient.errors import HttpError
-from httplib2 import Response
-from pydantic import SecretStr
-
+from forge.components.web.search import WebSearchComponent
 from forge.utils.exceptions import ConfigurationError
+from googleapiclient.errors import HttpError
 
-from . import WebSearchComponent
+from autogpt.agents.agent import Agent
 
 
 @pytest.fixture
-def web_search_component():
-    component = WebSearchComponent()
-    if component.config.google_api_key is None:
-        component.config.google_api_key = SecretStr("test")
-    if component.config.google_custom_search_engine_id is None:
-        component.config.google_custom_search_engine_id = SecretStr("test")
-    return component
+def web_search_component(agent: Agent):
+    return agent.web_search
 
 
 @pytest.mark.parametrize(
@@ -138,11 +131,16 @@ def test_google_official_search_errors(
     error_msg,
     web_search_component: WebSearchComponent,
 ):
+    class resp:
+        def __init__(self, _status, _reason):
+            self.status = _status
+            self.reason = _reason
+
     response_content = {
         "error": {"code": http_code, "message": error_msg, "reason": "backendError"}
     }
     error = HttpError(
-        resp=Response({"status": http_code, "reason": error_msg}),
+        resp=resp(http_code, error_msg),
         content=str.encode(json.dumps(response_content)),
         uri="https://www.googleapis.com/customsearch/v1?q=invalid+query&cx",
     )

benchmark/.vscode/settings.json

@@ -2,5 +2,5 @@
   "[python]": {
     "editor.defaultFormatter": "ms-python.black-formatter"
   },
-  "python.analysis.typeCheckingMode": "basic",
+  "python.formatting.provider": "none"
 }

benchmark/agbenchmark/__main__.py

@@ -97,9 +97,7 @@ def start():
     help="Write log output to a file instead of the terminal.",
 )
 # @click.argument(
-#     "agent_path",
-#     type=click.Path(exists=True, file_okay=False, path_type=Path),
-#     required=False,
+#     "agent_path", type=click.Path(exists=True, file_okay=False), required=False
 # )
 def run(
     maintain: bool,
@@ -278,9 +276,7 @@ def list_challenges(include_unavailable: bool, only_names: bool, output_json: bo
         return
 
     if output_json:
-        click.echo(
-            json.dumps([json.loads(c.info.model_dump_json()) for c in challenges])
-        )
+        click.echo(json.dumps([json.loads(c.info.json()) for c in challenges]))
         return
 
     headers = tuple(
@@ -328,7 +324,7 @@ def info(name: str, json: bool):
             continue
 
         if json:
-            click.echo(challenge.info.model_dump_json())
+            click.echo(challenge.info.json())
             break
 
         pretty_print_model(challenge.info)

benchmark/agbenchmark/app.py

@@ -16,7 +16,7 @@ from agent_protocol_client import AgentApi, ApiClient, ApiException, Configurati
 from agent_protocol_client.models import Task, TaskRequestBody
 from fastapi import APIRouter, FastAPI, HTTPException, Request, Response
 from fastapi.middleware.cors import CORSMiddleware
-from pydantic import BaseModel, ConfigDict, ValidationError
+from pydantic import BaseModel, Extra, ValidationError
 
 from agbenchmark.challenges import ChallengeInfo
 from agbenchmark.config import AgentBenchmarkConfig
@@ -52,9 +52,7 @@ while challenge_spec_files:
 
     logger.debug(f"Loading {challenge_relpath}...")
     try:
-        challenge_info = ChallengeInfo.model_validate_json(
-            challenge_spec_file.read_text()
-        )
+        challenge_info = ChallengeInfo.parse_file(challenge_spec_file)
     except ValidationError as e:
         if logging.getLogger().level == logging.DEBUG:
             logger.warning(f"Spec file {challenge_relpath} failed to load:\n{e}")
@@ -66,7 +64,7 @@ while challenge_spec_files:
         challenge_info.eval_id = str(uuid.uuid4())
         # this will sort all the keys of the JSON systematically
         # so that the order is always the same
-        write_pretty_json(challenge_info.model_dump(), challenge_spec_file)
+        write_pretty_json(challenge_info.dict(), challenge_spec_file)
 
     CHALLENGES[challenge_info.eval_id] = challenge_info
 
@@ -113,7 +111,8 @@ class CreateReportRequest(BaseModel):
     # category: Optional[str] = []
     mock: Optional[bool] = False
 
-    model_config = ConfigDict(extra="forbid")
+    class Config:
+        extra = Extra.forbid  # this will forbid any extra fields
 
 
 updates_list = []
@@ -154,7 +153,7 @@ def setup_fastapi_app(agbenchmark_config: AgentBenchmarkConfig) -> FastAPI:
         pids = find_agbenchmark_without_uvicorn()
         logger.info(f"pids already running with agbenchmark: {pids}")
 
-        logger.debug(f"Request to /reports: {body.model_dump()}")
+        logger.debug(f"Request to /reports: {body.dict()}")
 
         # Start the benchmark in a separate thread
         benchmark_process = Process(
@@ -327,9 +326,7 @@ def setup_fastapi_app(agbenchmark_config: AgentBenchmarkConfig) -> FastAPI:
                 config={},
             )
 
-            logger.debug(
-                f"Returning evaluation data:\n{eval_info.model_dump_json(indent=4)}"
-            )
+            logger.debug(f"Returning evaluation data:\n{eval_info.json(indent=4)}")
             return eval_info
         except ApiException as e:
             logger.error(f"Error {e} whilst trying to evaluate task: {task_id}")

benchmark/agbenchmark/challenges/builtin.py

@@ -15,13 +15,7 @@ from agent_protocol_client import Configuration as ClientConfig
 from agent_protocol_client import Step
 from colorama import Fore, Style
 from openai import _load_client as get_openai_client
-from pydantic import (
-    BaseModel,
-    Field,
-    StringConstraints,
-    ValidationInfo,
-    field_validator,
-)
+from pydantic import BaseModel, Field, constr, validator
 
 from agbenchmark.agent_api_interface import download_agent_artifacts_into_folder
 from agbenchmark.agent_interface import copy_challenge_artifacts_into_workspace
@@ -52,9 +46,7 @@ class BuiltinChallengeSpec(BaseModel):
 
     class Info(BaseModel):
         difficulty: DifficultyLevel
-        description: Annotated[
-            str, StringConstraints(pattern=r"^Tests if the agent can.*")
-        ]
+        description: Annotated[str, constr(regex=r"^Tests if the agent can.*")]
         side_effects: list[str] = Field(default_factory=list)
 
     info: Info
@@ -68,26 +60,23 @@ class BuiltinChallengeSpec(BaseModel):
 
         class Eval(BaseModel):
             type: str
-            scoring: Optional[Literal["percentage", "scale", "binary"]] = None
-            template: Optional[
-                Literal["rubric", "reference", "question", "custom"]
-            ] = None
-            examples: Optional[str] = None
+            scoring: Optional[Literal["percentage", "scale", "binary"]]
+            template: Optional[Literal["rubric", "reference", "question", "custom"]]
+            examples: Optional[str]
 
-            @field_validator("scoring", "template")
-            def validate_eval_fields(cls, value, info: ValidationInfo):
-                field_name = info.field_name
-                if "type" in info.data and info.data["type"] == "llm":
-                    if value is None:
+            @validator("scoring", "template", always=True)
+            def validate_eval_fields(cls, v, values, field):
+                if "type" in values and values["type"] == "llm":
+                    if v is None:
                         raise ValueError(
-                            f"{field_name} must be provided when eval type is 'llm'"
+                            f"{field.name} must be provided when eval type is 'llm'"
                         )
                 else:
-                    if value is not None:
+                    if v is not None:
                         raise ValueError(
-                            f"{field_name} should only exist when eval type is 'llm'"
+                            f"{field.name} should only exist when eval type is 'llm'"
                         )
-                return value
+                return v
 
         eval: Eval
 
@@ -153,7 +142,7 @@ class BuiltinChallenge(BaseChallenge):
 
     @classmethod
     def from_challenge_spec_file(cls, spec_file: Path) -> type["BuiltinChallenge"]:
-        challenge_spec = BuiltinChallengeSpec.model_validate_json(spec_file.read_text())
+        challenge_spec = BuiltinChallengeSpec.parse_file(spec_file)
         challenge_spec.spec_file = spec_file
         return cls.from_challenge_spec(challenge_spec)
 
@@ -198,7 +187,7 @@ class BuiltinChallenge(BaseChallenge):
                     task_id = step.task_id
 
                 n_steps += 1
-                steps.append(step.model_copy())
+                steps.append(step.copy())
                 if step.additional_output:
                     agent_task_cost = step.additional_output.get(
                         "task_total_cost",

benchmark/agbenchmark/challenges/verticals/code/6_battleship/artifacts_in/abstract_class.py

@@ -1,7 +1,7 @@
 from abc import ABC, abstractmethod
 from typing import Optional
 
-from pydantic import BaseModel, field_validator
+from pydantic import BaseModel, validator
 
 
 # Models for the request and response payloads
@@ -10,7 +10,7 @@ class ShipPlacement(BaseModel):
     start: dict  # {"row": int, "column": str}
     direction: str
 
-    @field_validator("start")
+    @validator("start")
     def validate_start(cls, start):
         row, column = start.get("row"), start.get("column")
 

benchmark/agbenchmark/challenges/verticals/code/6_battleship/artifacts_out/abstract_class.py

@@ -1,7 +1,7 @@
 from abc import ABC, abstractmethod
 from typing import Optional
 
-from pydantic import BaseModel, field_validator
+from pydantic import BaseModel, validator
 
 
 # Models for the request and response payloads
@@ -10,7 +10,7 @@ class ShipPlacement(BaseModel):
     start: dict  # {"row": int, "column": str}
     direction: str
 
-    @field_validator("start")
+    @validator("start")
     def validate_start(cls, start):
         row, column = start.get("row"), start.get("column")
 

benchmark/agbenchmark/challenges/webarena.py

@@ -6,7 +6,7 @@ from typing import ClassVar, Iterator, Literal
 import pytest
 import requests
 from agent_protocol_client import AgentApi, Step
-from pydantic import BaseModel, ValidationError, ValidationInfo, field_validator
+from pydantic import BaseModel, ValidationError, validator
 
 from agbenchmark.config import AgentBenchmarkConfig
 from agbenchmark.utils.data_types import Category, EvalResult
@@ -183,7 +183,7 @@ class WebArenaChallengeSpec(BaseModel):
     """The JungleGym site (base URL) at which to start"""
     require_login: bool
     require_reset: bool
-    storage_state: str | None = None
+    storage_state: str | None
 
     intent: str
     intent_template: str
@@ -195,36 +195,36 @@ class WebArenaChallengeSpec(BaseModel):
 
     class EvalSet(BaseModel):
         class StringMatchEvalSet(BaseModel):
-            exact_match: str | None = None
-            fuzzy_match: list[str] | None = None
-            must_include: list[str] | None = None
+            exact_match: str | None
+            fuzzy_match: list[str] | None
+            must_include: list[str] | None
 
-        reference_answers: StringMatchEvalSet | None = None
+        reference_answers: StringMatchEvalSet | None
         """For string_match eval, a set of criteria to judge the final answer"""
-        reference_answer_raw_annotation: str | None = None
-        string_note: str | None = None
-        annotation_note: str | None = None
+        reference_answer_raw_annotation: str | None
+        string_note: str | None
+        annotation_note: str | None
 
-        reference_url: str | None = None
+        reference_url: str | None
         """For url_match eval, the last URL that should be visited"""
-        url_note: str | None = None
+        url_note: str | None
 
         program_html: list[ProgramHtmlEval]
         """For program_html eval, a list of criteria to judge the site state by"""
 
         eval_types: list[EvalType]
 
-        @field_validator("eval_types")
-        def check_eval_parameters(cls, value: list[EvalType], info: ValidationInfo):
-            if "string_match" in value and not info.data["reference_answers"]:
+        @validator("eval_types")
+        def check_eval_parameters(cls, v: list[EvalType], values):
+            if "string_match" in v and not values.get("reference_answers"):
                 raise ValueError("'string_match' eval_type requires reference_answers")
-            if "url_match" in value and not info.data["reference_url"]:
+            if "url_match" in v and not values.get("reference_url"):
                 raise ValueError("'url_match' eval_type requires reference_url")
-            if "program_html" in value and not info.data["program_html"]:
+            if "program_html" in v and not values.get("program_html"):
                 raise ValueError(
                     "'program_html' eval_type requires at least one program_html eval"
                 )
-            return value
+            return v
 
         @property
         def evaluators(self) -> list[_Eval]:
@@ -292,7 +292,7 @@ class WebArenaChallenge(BaseChallenge):
         results = requests.get(source_url).json()["data"]
         if not results:
             raise ValueError(f"Could not fetch challenge {source_uri}")
-        return cls.from_challenge_spec(WebArenaChallengeSpec.model_validate(results[0]))
+        return cls.from_challenge_spec(WebArenaChallengeSpec.parse_obj(results[0]))
 
     @classmethod
     def from_challenge_spec(
@@ -500,7 +500,7 @@ def load_webarena_challenges(
     skipped = 0
     for entry in challenge_dicts:
         try:
-            challenge_spec = WebArenaChallengeSpec.model_validate(entry)
+            challenge_spec = WebArenaChallengeSpec.parse_obj(entry)
         except ValidationError as e:
             failed += 1
             logger.warning(f"Error validating WebArena challenge entry: {entry}")

benchmark/agbenchmark/config.py

@@ -4,8 +4,7 @@ from datetime import datetime
 from pathlib import Path
 from typing import Optional
 
-from pydantic import Field, ValidationInfo, field_validator
-from pydantic_settings import BaseSettings
+from pydantic import BaseSettings, Field, validator
 
 
 def _calculate_info_test_path(base_path: Path, benchmark_start_time: datetime) -> Path:
@@ -58,7 +57,7 @@ class AgentBenchmarkConfig(BaseSettings, extra="allow"):
     subject application exposes an Agent Protocol compliant API.
     """
 
-    agbenchmark_config_dir: Path = Field(exclude=True)
+    agbenchmark_config_dir: Path = Field(..., exclude=True)
     """Path to the agbenchmark_config folder of the subject agent application."""
 
     categories: list[str] | None = None
@@ -102,11 +101,11 @@ class AgentBenchmarkConfig(BaseSettings, extra="allow"):
     def config_file(self) -> Path:
         return self.agbenchmark_config_dir / "config.json"
 
-    @field_validator("reports_folder", mode="before")
-    def set_reports_folder(cls, value: Path, info: ValidationInfo):
-        if not value:
-            return info.data["agbenchmark_config_dir"] / "reports"
-        return value
+    @validator("reports_folder", pre=True, always=True)
+    def set_reports_folder(cls, v, values):
+        if not v:
+            return values["agbenchmark_config_dir"] / "reports"
+        return v
 
     def get_report_dir(self, benchmark_start_time: datetime) -> Path:
         return _calculate_info_test_path(self.reports_folder, benchmark_start_time)

benchmark/agbenchmark/reports/ReportManager.py

@@ -111,19 +111,17 @@ class SessionReportManager(BaseReportManager):
     def save(self) -> None:
         with self.report_file.open("w") as f:
             if self.report:
-                f.write(self.report.model_dump_json(indent=4))
+                f.write(self.report.json(indent=4))
             else:
-                json.dump(
-                    {k: v.model_dump() for k, v in self.tests.items()}, f, indent=4
-                )
+                json.dump({k: v.dict() for k, v in self.tests.items()}, f, indent=4)
 
     def load(self) -> None:
         super().load()
 
         if "tests" in self.tests:
-            self.report = Report.model_validate(self.tests)
+            self.report = Report.parse_obj(self.tests)
         else:
-            self.tests = {n: Test.model_validate(d) for n, d in self.tests.items()}
+            self.tests = {n: Test.parse_obj(d) for n, d in self.tests.items()}
 
     def add_test_report(self, test_name: str, test_report: Test) -> None:
         if self.report:
@@ -157,7 +155,7 @@ class SessionReportManager(BaseReportManager):
                 total_cost=self.get_total_costs(),
             ),
             tests=copy.copy(self.tests),
-            config=config.model_dump(exclude={"reports_folder"}, exclude_none=True),
+            config=config.dict(exclude={"reports_folder"}, exclude_none=True),
         )
 
         agent_categories = get_highest_achieved_difficulty_per_category(self.report)

benchmark/agbenchmark/reports/processing/process_report.py

@@ -27,7 +27,7 @@ def get_reports_data(report_path: str) -> dict[str, Any]:
         with open(Path(subdir) / file, "r") as f:
             # Load the JSON data from the file
             json_data = json.load(f)
-            converted_data = Report.model_validate(json_data)
+            converted_data = Report.parse_obj(json_data)
             # get the last directory name in the path as key
             reports_data[subdir_name] = converted_data
 

benchmark/agbenchmark/reports/processing/report_types.py

@@ -6,13 +6,7 @@ import logging
 from typing import Annotated, Any, Dict, List
 
 from agent_protocol_client import Step
-from pydantic import (
-    BaseModel,
-    Field,
-    StringConstraints,
-    ValidationInfo,
-    field_validator,
-)
+from pydantic import BaseModel, Field, constr, validator
 
 datetime_format = r"^\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}\+00:00$"
 logger = logging.getLogger(__name__)
@@ -36,20 +30,20 @@ class TestResult(BaseModel):
     cost: float | None = None
     """The (known) cost incurred by the run, e.g. from using paid LLM APIs"""
 
-    @field_validator("fail_reason")
-    def success_xor_fail_reason(cls, value, info: ValidationInfo):
-        if bool(value) == bool(info.data["success"]):
+    @validator("fail_reason")
+    def success_xor_fail_reason(cls, v: str | None, values: dict[str, Any]):
+        if bool(v) == bool(values["success"]):
             logger.error(
                 "Error validating `success ^ fail_reason` on TestResult: "
-                f"success = {repr(info.data['success'])}; "
-                f"fail_reason = {repr(value)}"
+                f"success = {repr(values['success'])}; "
+                f"fail_reason = {repr(v)}"
             )
-        if value:
-            success = info.data["success"]
+        if v:
+            success = values["success"]
             assert not success, "fail_reason must only be specified if success=False"
         else:
-            assert info.data["success"], "fail_reason is required if success=False"
-        return value
+            assert values["success"], "fail_reason is required if success=False"
+        return v
 
 
 class TestMetrics(BaseModel):
@@ -94,7 +88,7 @@ class Test(BaseModel):
 class ReportBase(BaseModel):
     command: str
     completion_time: str | None = None
-    benchmark_start_time: Annotated[str, StringConstraints(pattern=datetime_format)]
+    benchmark_start_time: Annotated[str, constr(regex=datetime_format)]
     metrics: MetricsOverall
     config: Dict[str, str | dict[str, str]]
     agent_git_commit_sha: str | None = None

benchmark/agbenchmark/reports/processing/report_types_v2.py

@@ -1,7 +1,7 @@
 """Model definitions for use in the API"""
 from typing import Annotated
 
-from pydantic import BaseModel, StringConstraints
+from pydantic import BaseModel, constr
 
 datetime_format = r"^\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}\+00:00$"
 
@@ -37,7 +37,7 @@ class RunDetails(BaseModel):
     run_id: str | None = None
     command: str
     completion_time: str | None = None
-    benchmark_start_time: Annotated[str, StringConstraints(pattern=datetime_format)]
+    benchmark_start_time: Annotated[str, constr(regex=datetime_format)]
 
 
 class BenchmarkRun(BaseModel):

benchmark/agbenchmark/reports/reports.py

@@ -45,7 +45,7 @@ def update_regression_tests(
         # if the last 3 tests were successful, add to the regression tests
         test_report.metrics.is_regression = True
         SingletonReportManager().REGRESSION_MANAGER.add_test(
-            test_name, test_report.model_dump(include={"difficulty", "data_path"})
+            test_name, test_report.dict(include={"difficulty", "data_path"})
         )
 
 

benchmark/agbenchmark/schema.py

@@ -7,9 +7,10 @@ from pydantic import BaseModel, Field
 
 class TaskRequestBody(BaseModel):
     input: str = Field(
+        ...,
         min_length=1,
         description="Input prompt for the task.",
-        examples=["Write the words you receive to the file 'output.txt'."],
+        example="Write the words you receive to the file 'output.txt'.",
     )
     additional_input: Optional[dict[str, Any]] = Field(default_factory=dict)
 

benchmark/agbenchmark/utils/dependencies/main.py

@@ -220,7 +220,7 @@ class DependencyManager(object):
         labels = {}
         for item in self.items:
             assert item.cls and issubclass(item.cls, BaseChallenge)
-            data = item.cls.info.model_dump()
+            data = item.cls.info.dict()
 
             node_name = get_name(item)
             data["name"] = node_name

benchmark/agbenchmark/utils/utils.py

@@ -135,7 +135,7 @@ def pretty_print_model(model: BaseModel, include_header: bool = True) -> None:
     if include_header:
         # Try to find the ID and/or name attribute of the model
         id, name = None, None
-        for attr, value in model.model_dump().items():
+        for attr, value in model.dict().items():
             if attr == "id" or attr.endswith("_id"):
                 id = value
             if attr.endswith("name"):
@@ -148,8 +148,8 @@ def pretty_print_model(model: BaseModel, include_header: bool = True) -> None:
         )
         indent = " " * 2
 
-    k_col_width = max(len(k) for k in model.model_dump().keys())
-    for k, v in model.model_dump().items():
+    k_col_width = max(len(k) for k in model.dict().keys())
+    for k, v in model.dict().items():
         v_fmt = repr(v)
         if v is None or v == "":
             v_fmt = click.style(v_fmt, fg="black")

benchmark/notebooks/LLM Score Experimentation.ipynb

@@ -0,0 +1,367 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "id": "15386da8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from dotenv import load_dotenv\n",
+    "from openai import OpenAI\n",
+    "\n",
+    "load_dotenv()\n",
+    "\n",
+    "def llm_eval(evaluation: str) -> float:\n",
+    "    openai_client = OpenAI()\n",
+    "    answer = openai_client.chat.completions.create(\n",
+    "        model=\"gpt-4\",\n",
+    "        messages=[\n",
+    "            {\"role\": \"system\", \"content\": evaluation},\n",
+    "        ],\n",
+    "    )\n",
+    "    return answer.choices[0].message.content"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "e9d1c3a6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "REFERENCE_PROMPT = \"\"\"Ignore previous directions. You are now an expert at evaluating how close machine generated responses are to human answers. You essentially act as a hyper advanced BLEU score.\n",
+    "In order to score the machine generated response you will {scoring}. Make sure to factor in the distance to the ideal response into your thinking, deliberation, and final result regarding scoring. Return nothing but a float score.\n",
+    "\n",
+    "Here is the given task for you to evaluate:\n",
+    "{task}\n",
+    "\n",
+    "Here is the ideal response you're comparing to based on the task:\n",
+    "{answer}\n",
+    "\n",
+    "Here are some examples of how to score a machine generated response compared to the above ideal response:\n",
+    "{examples}\n",
+    "\n",
+    "Here is the current machine generated response to the task that you need to evaluate:\n",
+    "{response}\n",
+    "\n",
+    "Remember to always end your response with nothing but a float score.\n",
+    "Float score:\n",
+    "\"\"\"\n",
+    "\n",
+    "RUBRIC_PROMPT = \"\"\"Ignore previous directions. You are now an expert at evaluating machine generated responses to given tasks.\n",
+    "In order to score the generated texts you will {scoring}. Make sure to factor in rubric into your thinking, deliberation, and final result regarding scoring. Return nothing but a float score.\n",
+    "\n",
+    "Here is the given task for you to evaluate:\n",
+    "{task}\n",
+    "\n",
+    "Use the below rubric to guide your thinking about scoring:\n",
+    "{answer}\n",
+    "\n",
+    "Here are some examples of how to score a machine generated response based on the above rubric.\n",
+    "{examples}\n",
+    "\n",
+    "Here is the current machine generated response to the task that you need to evaluate:\n",
+    "{response}\n",
+    "\n",
+    "Remember to always end your response with nothing but a float score.\n",
+    "Float score:\n",
+    "\"\"\"\n",
+    "\n",
+    "QUESTION_PROMPT = \"\"\"Ignore previous directions. You are now an expert at evaluating machine generated responses to given tasks.\n",
+    "In order to score the generated texts you will {scoring}. Make sure to think about whether the generated response answers the question well in order to score accurately. Return nothing but a float score.\n",
+    "\n",
+    "Here is the given task:\n",
+    "{task}\n",
+    "\n",
+    "Here is a question that checks if the task was completed correctly:\n",
+    "{answer}\n",
+    "\n",
+    "Here are some examples of how to score a machine generated response based on task-response pairs.\n",
+    "{examples}\n",
+    "\n",
+    "Here is the current machine generated response to the task that you need to evaluate:\n",
+    "{response}\n",
+    "\n",
+    "Remember to always end your response with nothing but a float score.\n",
+    "Float score:\n",
+    "\"\"\"\n",
+    "\n",
+    "CUSTOM_PROMPT = \"\"\"{custom}\n",
+    "{scoring}\"\"\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "8ff9cd33",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "task = \"As an agent powered by a large language model, you can execute any digital action. Your task is to find the cheapest flight to San Francisco from Toronto. Create a step by step plan for yourself to execute this task and output this plan into a .txt file.\"\n",
+    "\n",
+    "percentage = \"assign a float score that will represent a percentage out of 100. Use decimal points to be even more accurate. 0 represents the worst possible generation, while 100 represents the ideal generation\"\n",
+    "scale = \"assign an integer score from a scale of 1-10. 1 represents a really bad generation, while 10 represents an ideal generation\"\n",
+    "binary = \"assign a binary score of either 0 or 1. 0 represents a failure, while 1 represents a success\"\n",
+    "\n",
+    "reference_answer = \"\"\"1. Search 'Toronto to San Francisco flights' on the internet\n",
+    "2. Click on the first link that is a flight aggregator such as SkyScanner or Google Flights\n",
+    "3. Select the dates that you want to travel\n",
+    "3. Click on the 'one way' option and click search\n",
+    "4. Search through all of the given options and select the cheapest flight\"\"\"\n",
+    "\n",
+    "rubric_answer = \"\"\"- Reasonable: The plan's steps should be arranged in a logical sequence. Each step should naturally follow from the one before it, leading coherently towards the desired outcome.\n",
+    "- Atomic: Each step of the plan should be broken down into the smallest possible units of action. This level of detail allows for better tracking and control, as well as easier troubleshooting and adjustment of the plan if necessary.\n",
+    "- Relevant: Each step should directly contribute to achieving the end goal of the plan. Irrelevant steps can waste resources and detract from the main objectives.\n",
+    "- Timely: The plan should include a realistic timeline for each step, and not include any redundant steps.\"\"\"\n",
+    "\n",
+    "question_answer = \"Will this plan find the cheapest flight to San Francisco from Toronto consistently?\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "d0bfdce5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "FEW_SHOT_REFERENCE_EXAMPLES = \"\"\"EXAMPLE 1\n",
+    "Plan: 'Define the Parameters:\n",
+    "\n",
+    "Identify the potential range of dates for the journey. Ensure flexibility to capitalize on the best deals.\n",
+    "Research Airlines:\n",
+    "\n",
+    "Compile a list of airlines that operate flights between Toronto and San Francisco. This can be accomplished by checking each airline's website or using an airline directory.\n",
+    "Use Comparison Tools:\n",
+    "\n",
+    "Use flight comparison websites (such as Skyscanner, Expedia, Google Flights, etc.) to compare flight prices across different airlines. These tools aggregate flight data and can present the cheapest options available.\n",
+    "Set Price Alerts:\n",
+    "\n",
+    "If the trip is not immediate, set price alerts on these comparison websites. They will notify you when there is a significant drop in flight prices on the selected route.\n",
+    "Check Airlines' Official Websites:\n",
+    "\n",
+    "After identifying potential flights via comparison tools, visit the airlines' official websites. Sometimes airlines offer deals or discounts on their own websites that are not reflected on comparison sites.\n",
+    "Consider Nearby Airports:\n",
+    "\n",
+    "Check flight prices to and from airports in the vicinity of both Toronto and San Francisco. Sometimes less busy airports can offer cheaper flights.\n",
+    "Evaluate Cost Effectiveness:\n",
+    "\n",
+    "Consider factors such as baggage fees, meal costs, and transportation to and from the airport when evaluating the total cost of the flight. The cheapest ticket price does not necessarily mean the least expensive journey overall.\n",
+    "Book the Flight:\n",
+    "\n",
+    "Once the cheapest and most convenient flight has been identified, proceed to booking. Double-check the flight details before finalizing the booking.\n",
+    "Monitor Flight Details:\n",
+    "\n",
+    "After booking, keep an eye on flight status, gate information, and any potential changes to the flight schedule.'\n",
+    "Returned score: 82.7\n",
+    "Internal rationale: The plan is solid, however the plan goes to extreme lengths to make things cheap, sacrificing time and simplicity. The task just asks for a vague definition of booking a flight. There are some redundant steps.\n",
+    "\n",
+    "EXAMPLE 2\n",
+    "Plan: 'Determine the Travel Dates and Flexibility: Decide on the dates you want to travel to San Francisco and check if you have any flexibility in your travel schedule. Being flexible with your travel dates can often lead to finding cheaper flights.\n",
+    "\n",
+    "Use Flight Search Engines: Start by using popular flight search engines like Google Flights, Skyscanner, Kayak, or Expedia. These platforms allow you to compare prices from various airlines and find the most affordable options.\n",
+    "\n",
+    "Set Up Fare Alerts: If your travel dates are flexible, consider setting up fare alerts on the flight search engines. These alerts will notify you when the prices drop for the specified route.\n",
+    "\n",
+    "Check Nearby Airports: In both Toronto and San Francisco, there might be multiple airports. Check flights departing from nearby airports as they may offer better deals.\n",
+    "\n",
+    "Consider Layovers: Non-stop flights are usually more convenient but can be more expensive. Look for flights with one or more layovers as they may offer cost savings.\n",
+    "\n",
+    "Check Airlines' Official Websites: Once you find a potentially cheap flight on a search engine, verify the price directly on the airline's official website. Sometimes, booking directly with the airline can be cheaper due to exclusive deals and promotions.\n",
+    "\n",
+    "Use Incognito/Private Browsing Mode: Flight prices can sometimes increase if the website detects repeated searches for the same route. To avoid this, use the incognito or private browsing mode in your web browser.\n",
+    "\n",
+    "Consider Budget Airlines: Check if there are any budget airlines flying between Toronto and San Francisco. They often offer lower fares, but be mindful of additional fees for baggage and other services.\n",
+    "\n",
+    "Check for Deals and Promo Codes: Look for any ongoing deals or promo codes that can help you save on your flight booking. Airlines and travel websites occasionally offer special discounts.\n",
+    "\n",
+    "Be Flexible with Departure and Arrival Times: If possible, consider flying during off-peak hours or mid-week, as flights during these times can be less expensive.\n",
+    "\n",
+    "Factor in Total Costs: While searching for cheap flights, don't forget to consider other expenses like baggage fees, seat selection, and additional amenities. Some budget airlines might have hidden costs that could make the overall trip more expensive.\n",
+    "\n",
+    "Book Early: Flight prices tend to rise as the departure date approaches. Once you find a good deal that suits your preferences, don't wait too long to book your flight.'\n",
+    "Returned score: 74.9\n",
+    "Internal rationale: The individual components of this plan are better than the one previous. But this plan doesn't follow logical steps to completion, and is just more general advice.\n",
+    "\n",
+    "EXAMPLE 3\n",
+    "Plan: 'Search online for cheap flights.\n",
+    "Check different dates.\n",
+    "Look at nearby airports.\n",
+    "Consider layovers.\n",
+    "Try budget airlines.\n",
+    "Book early if you find a good deal.'\n",
+    "Returned score: 42.0\n",
+    "Internal rationale: This plan is too vague and does not provide enough detail to be useful.\n",
+    "\n",
+    "\"\"\"\n",
+    "FEW_SHOT_RUBRIC_EXAMPLES = \"\"\n",
+    "FEW_SHOT_QUESTION_EXAMPLES = \"\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 75,
+   "id": "3de1d6d4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "response1=\"\"\"Define the Parameters:\n",
+    "\n",
+    "Identify the potential range of dates for the journey. Ensure flexibility to capitalize on the best deals.\n",
+    "Research Airlines:\n",
+    "\n",
+    "Compile a list of airlines that operate flights between Toronto and San Francisco. This can be accomplished by checking each airline's website or using an airline directory.\n",
+    "Use Comparison Tools:\n",
+    "\n",
+    "Use flight comparison websites (such as Skyscanner, Expedia, Google Flights, etc.) to compare flight prices across different airlines. These tools aggregate flight data and can present the cheapest options available.\n",
+    "Set Price Alerts:\n",
+    "\n",
+    "If the trip is not immediate, set price alerts on these comparison websites. They will notify you when there is a significant drop in flight prices on the selected route.\n",
+    "Check Airlines' Official Websites:\n",
+    "\n",
+    "After identifying potential flights via comparison tools, visit the airlines' official websites. Sometimes airlines offer deals or discounts on their own websites that are not reflected on comparison sites.\n",
+    "Consider Nearby Airports:\n",
+    "\n",
+    "Check flight prices to and from airports in the vicinity of both Toronto and San Francisco. Sometimes less busy airports can offer cheaper flights.\n",
+    "Evaluate Cost Effectiveness:\n",
+    "\n",
+    "Consider factors such as baggage fees, meal costs, and transportation to and from the airport when evaluating the total cost of the flight. The cheapest ticket price does not necessarily mean the least expensive journey overall.\n",
+    "Book the Flight:\n",
+    "\n",
+    "Once the cheapest and most convenient flight has been identified, proceed to booking. Double-check the flight details before finalizing the booking.\n",
+    "Monitor Flight Details:\n",
+    "\n",
+    "After booking, keep an eye on flight status, gate information, and any potential changes to the flight schedule.\"\"\"\n",
+    "\n",
+    "response2=\"\"\"Determine the Travel Dates and Flexibility: Decide on the dates you want to travel to San Francisco and check if you have any flexibility in your travel schedule. Being flexible with your travel dates can often lead to finding cheaper flights.\n",
+    "\n",
+    "Use Flight Search Engines: Start by using popular flight search engines like Google Flights, Skyscanner, Kayak, or Expedia. These platforms allow you to compare prices from various airlines and find the most affordable options.\n",
+    "\n",
+    "Set Up Fare Alerts: If your travel dates are flexible, consider setting up fare alerts on the flight search engines. These alerts will notify you when the prices drop for the specified route.\n",
+    "\n",
+    "Check Nearby Airports: In both Toronto and San Francisco, there might be multiple airports. Check flights departing from nearby airports as they may offer better deals.\n",
+    "\n",
+    "Consider Layovers: Non-stop flights are usually more convenient but can be more expensive. Look for flights with one or more layovers as they may offer cost savings.\n",
+    "\n",
+    "Check Airlines' Official Websites: Once you find a potentially cheap flight on a search engine, verify the price directly on the airline's official website. Sometimes, booking directly with the airline can be cheaper due to exclusive deals and promotions.\n",
+    "\n",
+    "Use Incognito/Private Browsing Mode: Flight prices can sometimes increase if the website detects repeated searches for the same route. To avoid this, use the incognito or private browsing mode in your web browser.\n",
+    "\n",
+    "Consider Budget Airlines: Check if there are any budget airlines flying between Toronto and San Francisco. They often offer lower fares, but be mindful of additional fees for baggage and other services.\n",
+    "\n",
+    "Check for Deals and Promo Codes: Look for any ongoing deals or promo codes that can help you save on your flight booking. Airlines and travel websites occasionally offer special discounts.\n",
+    "\n",
+    "Be Flexible with Departure and Arrival Times: If possible, consider flying during off-peak hours or mid-week, as flights during these times can be less expensive.\n",
+    "\n",
+    "Factor in Total Costs: While searching for cheap flights, don't forget to consider other expenses like baggage fees, seat selection, and additional amenities. Some budget airlines might have hidden costs that could make the overall trip more expensive.\n",
+    "\n",
+    "Book Early: Flight prices tend to rise as the departure date approaches. Once you find a good deal that suits your preferences, don't wait too long to book your flight.\"\"\"\n",
+    "\n",
+    "response3 = \"\"\"Search online for cheap flights.\n",
+    "Check different dates.\n",
+    "Look at nearby airports.\n",
+    "Consider layovers.\n",
+    "Try budget airlines.\n",
+    "Book early if you find a good deal.\"\"\"\n",
+    "\n",
+    "ideal_response = \"\"\"1. Search 'Toronto to San Francisco flights' on the internet\n",
+    "2. Click on the first link that is a flight aggregator such as SkyScanner or Google Flights\n",
+    "3. Select the dates that you want to travel\n",
+    "3. Click on the 'one way' option and click search\n",
+    "4. Search through all of the given options and select the cheapest flight\"\"\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "a5bf2f5c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "reference_evaluation = REFERENCE_PROMPT.format(task=task, scoring=percentage, answer=reference_answer, response=ideal_response, examples=FEW_SHOT_REFERENCE_EXAMPLES)\n",
+    "rubric_evaluation = RUBRIC_PROMPT.format(task=task, scoring=percentage, answer=rubric_answer, response=ideal_response, examples=FEW_SHOT_REFERENCE_EXAMPLES)\n",
+    "question_evaluation = QUESTION_PROMPT.format(task=task, scoring=percentage, answer=question_answer, response=ideal_response, examples=FEW_SHOT_REFERENCE_EXAMPLES)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 82,
+   "id": "1cd01a4c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "reference_response = llm_eval(reference_evaluation)\n",
+    "rubric_response = llm_eval(rubric_evaluation)\n",
+    "question_response = llm_eval(question_evaluation)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 72,
+   "id": "72e6ac91",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "REFERENCE: 66.5 6.0 0.0\n",
+      "RUBRIC: 65.0 4.0 0.0\n",
+      "QUESTION: 87.0 6.5 0.0\n"
+     ]
+    }
+   ],
+   "source": [
+    "# response3 - the worst one\n",
+    "print('REFERENCE:', reference_response_percentage, reference_response_scale, reference_response_binary)\n",
+    "print('RUBRIC:', rubric_response_percentage, rubric_response_scale, rubric_response_binary)\n",
+    "print('QUESTION:', question_response_percentage, question_response_scale, question_response_binary)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 83,
+   "id": "a66014ee",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "REFERENCE: 100.0 10.0 1.0\n",
+      "RUBRIC: 88.0 7.5 1.0\n",
+      "QUESTION: 87.0 7.5 1.0\n"
+     ]
+    }
+   ],
+   "source": [
+    "# reference_response - the best one\n",
+    "print('REFERENCE:', reference_response_ideal_percentage, reference_response_ideal_scale, reference_response_ideal_binary)\n",
+    "print('RUBRIC:', rubric_response_ideal_percentage, rubric_response_ideal_scale, rubric_response_ideal_binary)\n",
+    "print('QUESTION:', question_response_ideal_percentage, question_response_ideal_scale, question_response_ideal_binary)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

benchmark/notebooks/selected_logs.json

@@ -0,0 +1,30 @@
+{
+    "1": {
+        "role": "assistant",
+        "content": "{\n  \"thoughts\": {\n    \"text\": \"I need to find Tesla's revenue in 2022.\",\n    \"reasoning\": \"I will perform a web search to find the information.\",\n    \"plan\": \"- Perform a web search\\n- Extract the revenue\\n- Write the revenue to a file\",\n    \"criticism\": \"I should be cautious about the reliability of the source I find.\",\n    \"speak\": \"I will search the web for Tesla's revenue in 2022.\"\n  },\n  \"command\": {\n    \"name\": \"web_search\",\n    \"args\": {\n      \"query\": \"Tesla revenue in 2022\"\n    }\n  }\n}"
+    },
+    "2": {
+        "role": "assistant",
+        "content": "{\n  \"thoughts\": {\n    \"text\": \"I found a reliable source for Tesla's revenue in 2022.\",\n    \"reasoning\": \"I will use the Statista source to extract the revenue information.\",\n    \"plan\": \"- Browse the Statista website\\n- Extract the revenue\\n- Write the revenue to a file\",\n    \"criticism\": \"I should verify the information on the Statista website.\",\n    \"speak\": \"I will browse the Statista website to find Tesla's revenue in 2022.\"\n  },\n  \"command\": {\n    \"name\": \"browse_website\",\n    \"args\": {\n      \"url\": \"https://www.statista.com/statistics/272120/revenue-of-tesla/\",\n      \"question\": \"What was Tesla's revenue in 2022?\"\n    }\n  }\n}"
+    },
+    "3": {
+        "role": "assistant",
+        "content": "Tesla's revenue in 2022 was nearly $81.5 billion, which represents a 51 percent increase from the previous year. The majority of the revenue, over $71 billion, was generated from Tesla's automotive segment. The Model Y emerged as Tesla's best-selling vehicle, and the company has been investing in the production of the Model 3 and Model Y."
+    },
+    "4": {
+        "role": "assistant",
+        "content": "The text provides various statistics and financial information about Tesla, including its revenue from 2008 to 2022. However, the specific revenue for 2022 is not mentioned in the text."
+    },
+    "5": {
+        "role": "assistant",
+        "content": "a description of different types of cookies used on a website and the options for accepting or rejecting them. There is no information provided about Tesla's revenue in 2022."
+    },
+    "6": {
+        "role": "assistant",
+        "content": "Tesla's revenue in 2022 increased by 51% to nearly $81.5 billion, with the majority coming from the automotive segment. The Model Y was the best-selling vehicle, and the company has been focusing on producing the Model 3 and Model Y."
+    },
+    "7": {
+        "role": "assistant",
+        "content": "{\n  \"thoughts\": {\n    \"text\": \"I found Tesla's revenue in 2022.\",\n    \"reasoning\": \"I will write the revenue to a file.\",\n    \"plan\": \"- Write the revenue to a file\",\n    \"criticism\": \"I should ensure the revenue is formatted correctly.\",\n    \"speak\": \"I will write Tesla's revenue in 2022 to a file.\"\n  },\n  \"command\": {\n    \"name\": \"write_to_file\",\n    \"args\": {\n      \"filename\": \"tesla_revenue_2022.txt\",\n      \"text\": \"Tesla's revenue in 2022 was $81,500,000,000.\"\n    }\n  }\n}"
+    }
+}

benchmark/notebooks/selected_logs_nested.json

@@ -0,0 +1,74 @@
+{
+    "1": {
+        "role": "assistant",
+        "content": {
+            "thoughts": {
+                "text": "I need to find Tesla's revenue in 2022.",
+                "reasoning": "I will perform a web search to find the information.",
+                "plan": "- Perform a web search\n- Extract the revenue\n- Write the revenue to a file",
+                "criticism": "I should be cautious about the reliability of the source I find.",
+                "speak": "I will search the web for Tesla's revenue in 2022."
+            },
+            "command": {
+                "name": "web_search",
+                "args": {
+                    "query": "Tesla revenue in 2022"
+                }
+            }
+        }
+    },
+    "2": {
+        "role": "assistant",
+        "content": {
+            "thoughts": {
+                "text": "I found a reliable source for Tesla's revenue in 2022.",
+                "reasoning": "I will use the Statista source to extract the revenue information.",
+                "plan": "- Browse the Statista website\n- Extract the revenue\n- Write the revenue to a file",
+                "criticism": "I should verify the information on the Statista website.",
+                "speak": "I will browse the Statista website to find Tesla's revenue in 2022."
+            },
+            "command": {
+                "name": "browse_website",
+                "args": {
+                    "url": "https://www.statista.com/statistics/272120/revenue-of-tesla/",
+                    "question": "What was Tesla's revenue in 2022?"
+                }
+            }
+        }
+    },
+    "3": {
+        "role": "assistant",
+        "content": "Tesla's revenue in 2022 was nearly $81.5 billion, which represents a 51 percent increase from the previous year. The majority of the revenue, over $71 billion, was generated from Tesla's automotive segment. The Model Y emerged as Tesla's best-selling vehicle, and the company has been investing in the production of the Model 3 and Model Y."
+    },
+    "4": {
+        "role": "assistant",
+        "content": "The text provides various statistics and financial information about Tesla, including its revenue from 2008 to 2022. However, the specific revenue for 2022 is not mentioned in the text."
+    },
+    "5": {
+        "role": "assistant",
+        "content": "a description of different types of cookies used on a website and the options for accepting or rejecting them. There is no information provided about Tesla's revenue in 2022."
+    },
+    "6": {
+        "role": "assistant",
+        "content": "Tesla's revenue in 2022 increased by 51% to nearly $81.5 billion, with the majority coming from the automotive segment. The Model Y was the best-selling vehicle, and the company has been focusing on producing the Model 3 and Model Y."
+    },
+    "7": {
+        "role": "assistant",
+        "content": {
+            "thoughts": {
+                "text": "I found Tesla's revenue in 2022.",
+                "reasoning": "I will write the revenue to a file.",
+                "plan": "- Write the revenue to a file",
+                "criticism": "I should ensure the revenue is formatted correctly.",
+                "speak": "I will write Tesla's revenue in 2022 to a file."
+            },
+            "command": {
+                "name": "write_to_file",
+                "args": {
+                    "filename": "tesla_revenue_2022.txt",
+                    "text": "Tesla's revenue in 2022 was $81,500,000,000."
+                }
+            }
+        }
+    }
+}

benchmark/poetry.lock

@@ -5,22 +5,17 @@ name = "agent-protocol-client"
 version = "1.1.0"
 description = "Agent Communication Protocol Client"
 optional = false
-python-versions = "^3.7"
-files = []
-develop = false
+python-versions = ">=3.7,<4.0"
+files = [
+    {file = "agent_protocol_client-1.1.0-py3-none-any.whl", hash = "sha256:0e8c6c97244189666ed18e320410abddce8c9dfb75437da1e590bbef3b6268be"},
+    {file = "agent_protocol_client-1.1.0.tar.gz", hash = "sha256:aa7e1042de1249477fdc29c2df08a44f2233dade9c02c1279e37c98e9d3a0d72"},
+]
 
 [package.dependencies]
-aiohttp = "^3.8.4"
-pydantic = ">=1.10.5, <3.0.0"
-python-dateutil = "^2.8.2"
-urllib3 = "^1.25.3"
-
-[package.source]
-type = "git"
-url = "https://github.com/Significant-Gravitas/agent-protocol.git"
-reference = "HEAD"
-resolved_reference = "beb098517b0b9e255024d1b57df236f0329f4b1c"
-subdirectory = "packages/client/python"
+aiohttp = ">=3.8.4,<4.0.0"
+pydantic = ">=1.10.5,<2.0.0"
+python-dateutil = ">=2.8.2,<3.0.0"
+urllib3 = ">=1.25.3,<2.0.0"
 
 [[package]]
 name = "aiohttp"
@@ -132,17 +127,6 @@ files = [
 [package.dependencies]
 frozenlist = ">=1.1.0"
 
-[[package]]
-name = "annotated-types"
-version = "0.7.0"
-description = "Reusable constraint types to use with typing.Annotated"
-optional = false
-python-versions = ">=3.8"
-files = [
-    {file = "annotated_types-0.7.0-py3-none-any.whl", hash = "sha256:1f02e8b43a8fbbc3f3e0d4f0f4bfc8131bcb4eebe8849b8e5c773f3a1c582a53"},
-    {file = "annotated_types-0.7.0.tar.gz", hash = "sha256:aff07c09a53a08bc8cfccb9c85b05f1aa9a2a6f23728d790723543408344ce89"},
-]
-
 [[package]]
 name = "anyio"
 version = "4.2.0"
@@ -1456,101 +1440,85 @@ files = [
 
 [[package]]
 name = "multidict"
-version = "6.0.5"
+version = "6.0.4"
 description = "multidict implementation"
 optional = false
 python-versions = ">=3.7"
 files = [
-    {file = "multidict-6.0.5-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:228b644ae063c10e7f324ab1ab6b548bdf6f8b47f3ec234fef1093bc2735e5f9"},
-    {file = "multidict-6.0.5-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:896ebdcf62683551312c30e20614305f53125750803b614e9e6ce74a96232604"},
-    {file = "multidict-6.0.5-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:411bf8515f3be9813d06004cac41ccf7d1cd46dfe233705933dd163b60e37600"},
-    {file = "multidict-6.0.5-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1d147090048129ce3c453f0292e7697d333db95e52616b3793922945804a433c"},
-    {file = "multidict-6.0.5-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:215ed703caf15f578dca76ee6f6b21b7603791ae090fbf1ef9d865571039ade5"},
-    {file = "multidict-6.0.5-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:7c6390cf87ff6234643428991b7359b5f59cc15155695deb4eda5c777d2b880f"},
-    {file = "multidict-6.0.5-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:21fd81c4ebdb4f214161be351eb5bcf385426bf023041da2fd9e60681f3cebae"},
-    {file = "multidict-6.0.5-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:3cc2ad10255f903656017363cd59436f2111443a76f996584d1077e43ee51182"},
-    {file = "multidict-6.0.5-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:6939c95381e003f54cd4c5516740faba40cf5ad3eeff460c3ad1d3e0ea2549bf"},
-    {file = "multidict-6.0.5-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:220dd781e3f7af2c2c1053da9fa96d9cf3072ca58f057f4c5adaaa1cab8fc442"},
-    {file = "multidict-6.0.5-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:766c8f7511df26d9f11cd3a8be623e59cca73d44643abab3f8c8c07620524e4a"},
-    {file = "multidict-6.0.5-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:fe5d7785250541f7f5019ab9cba2c71169dc7d74d0f45253f8313f436458a4ef"},
-    {file = "multidict-6.0.5-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:c1c1496e73051918fcd4f58ff2e0f2f3066d1c76a0c6aeffd9b45d53243702cc"},
-    {file = "multidict-6.0.5-cp310-cp310-win32.whl", hash = "sha256:7afcdd1fc07befad18ec4523a782cde4e93e0a2bf71239894b8d61ee578c1319"},
-    {file = "multidict-6.0.5-cp310-cp310-win_amd64.whl", hash = "sha256:99f60d34c048c5c2fabc766108c103612344c46e35d4ed9ae0673d33c8fb26e8"},
-    {file = "multidict-6.0.5-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:f285e862d2f153a70586579c15c44656f888806ed0e5b56b64489afe4a2dbfba"},
-    {file = "multidict-6.0.5-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:53689bb4e102200a4fafa9de9c7c3c212ab40a7ab2c8e474491914d2305f187e"},
-    {file = "multidict-6.0.5-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:612d1156111ae11d14afaf3a0669ebf6c170dbb735e510a7438ffe2369a847fd"},
-    {file = "multidict-6.0.5-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7be7047bd08accdb7487737631d25735c9a04327911de89ff1b26b81745bd4e3"},
-    {file = "multidict-6.0.5-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:de170c7b4fe6859beb8926e84f7d7d6c693dfe8e27372ce3b76f01c46e489fcf"},
-    {file = "multidict-6.0.5-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:04bde7a7b3de05732a4eb39c94574db1ec99abb56162d6c520ad26f83267de29"},
-    {file = "multidict-6.0.5-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:85f67aed7bb647f93e7520633d8f51d3cbc6ab96957c71272b286b2f30dc70ed"},
-    {file = "multidict-6.0.5-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:425bf820055005bfc8aa9a0b99ccb52cc2f4070153e34b701acc98d201693733"},
-    {file = "multidict-6.0.5-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:d3eb1ceec286eba8220c26f3b0096cf189aea7057b6e7b7a2e60ed36b373b77f"},
-    {file = "multidict-6.0.5-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:7901c05ead4b3fb75113fb1dd33eb1253c6d3ee37ce93305acd9d38e0b5f21a4"},
-    {file = "multidict-6.0.5-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:e0e79d91e71b9867c73323a3444724d496c037e578a0e1755ae159ba14f4f3d1"},
-    {file = "multidict-6.0.5-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:29bfeb0dff5cb5fdab2023a7a9947b3b4af63e9c47cae2a10ad58394b517fddc"},
-    {file = "multidict-6.0.5-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:e030047e85cbcedbfc073f71836d62dd5dadfbe7531cae27789ff66bc551bd5e"},
-    {file = "multidict-6.0.5-cp311-cp311-win32.whl", hash = "sha256:2f4848aa3baa109e6ab81fe2006c77ed4d3cd1e0ac2c1fbddb7b1277c168788c"},
-    {file = "multidict-6.0.5-cp311-cp311-win_amd64.whl", hash = "sha256:2faa5ae9376faba05f630d7e5e6be05be22913782b927b19d12b8145968a85ea"},
-    {file = "multidict-6.0.5-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:51d035609b86722963404f711db441cf7134f1889107fb171a970c9701f92e1e"},
-    {file = "multidict-6.0.5-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:cbebcd5bcaf1eaf302617c114aa67569dd3f090dd0ce8ba9e35e9985b41ac35b"},
-    {file = "multidict-6.0.5-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:2ffc42c922dbfddb4a4c3b438eb056828719f07608af27d163191cb3e3aa6cc5"},
-    {file = "multidict-6.0.5-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ceb3b7e6a0135e092de86110c5a74e46bda4bd4fbfeeb3a3bcec79c0f861e450"},
-    {file = "multidict-6.0.5-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:79660376075cfd4b2c80f295528aa6beb2058fd289f4c9252f986751a4cd0496"},
-    {file = "multidict-6.0.5-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:e4428b29611e989719874670fd152b6625500ad6c686d464e99f5aaeeaca175a"},
-    {file = "multidict-6.0.5-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d84a5c3a5f7ce6db1f999fb9438f686bc2e09d38143f2d93d8406ed2dd6b9226"},
-    {file = "multidict-6.0.5-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:76c0de87358b192de7ea9649beb392f107dcad9ad27276324c24c91774ca5271"},
-    {file = "multidict-6.0.5-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:79a6d2ba910adb2cbafc95dad936f8b9386e77c84c35bc0add315b856d7c3abb"},
-    {file = "multidict-6.0.5-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:92d16a3e275e38293623ebf639c471d3e03bb20b8ebb845237e0d3664914caef"},
-    {file = "multidict-6.0.5-cp312-cp312-musllinux_1_1_ppc64le.whl", hash = "sha256:fb616be3538599e797a2017cccca78e354c767165e8858ab5116813146041a24"},
-    {file = "multidict-6.0.5-cp312-cp312-musllinux_1_1_s390x.whl", hash = "sha256:14c2976aa9038c2629efa2c148022ed5eb4cb939e15ec7aace7ca932f48f9ba6"},
-    {file = "multidict-6.0.5-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:435a0984199d81ca178b9ae2c26ec3d49692d20ee29bc4c11a2a8d4514c67eda"},
-    {file = "multidict-6.0.5-cp312-cp312-win32.whl", hash = "sha256:9fe7b0653ba3d9d65cbe7698cca585bf0f8c83dbbcc710db9c90f478e175f2d5"},
-    {file = "multidict-6.0.5-cp312-cp312-win_amd64.whl", hash = "sha256:01265f5e40f5a17f8241d52656ed27192be03bfa8764d88e8220141d1e4b3556"},
-    {file = "multidict-6.0.5-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:19fe01cea168585ba0f678cad6f58133db2aa14eccaf22f88e4a6dccadfad8b3"},
-    {file = "multidict-6.0.5-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6bf7a982604375a8d49b6cc1b781c1747f243d91b81035a9b43a2126c04766f5"},
-    {file = "multidict-6.0.5-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:107c0cdefe028703fb5dafe640a409cb146d44a6ae201e55b35a4af8e95457dd"},
-    {file = "multidict-6.0.5-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:403c0911cd5d5791605808b942c88a8155c2592e05332d2bf78f18697a5fa15e"},
-    {file = "multidict-6.0.5-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:aeaf541ddbad8311a87dd695ed9642401131ea39ad7bc8cf3ef3967fd093b626"},
-    {file = "multidict-6.0.5-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e4972624066095e52b569e02b5ca97dbd7a7ddd4294bf4e7247d52635630dd83"},
-    {file = "multidict-6.0.5-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:d946b0a9eb8aaa590df1fe082cee553ceab173e6cb5b03239716338629c50c7a"},
-    {file = "multidict-6.0.5-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:b55358304d7a73d7bdf5de62494aaf70bd33015831ffd98bc498b433dfe5b10c"},
-    {file = "multidict-6.0.5-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:a3145cb08d8625b2d3fee1b2d596a8766352979c9bffe5d7833e0503d0f0b5e5"},
-    {file = "multidict-6.0.5-cp37-cp37m-musllinux_1_1_s390x.whl", hash = "sha256:d65f25da8e248202bd47445cec78e0025c0fe7582b23ec69c3b27a640dd7a8e3"},
-    {file = "multidict-6.0.5-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:c9bf56195c6bbd293340ea82eafd0071cb3d450c703d2c93afb89f93b8386ccc"},
-    {file = "multidict-6.0.5-cp37-cp37m-win32.whl", hash = "sha256:69db76c09796b313331bb7048229e3bee7928eb62bab5e071e9f7fcc4879caee"},
-    {file = "multidict-6.0.5-cp37-cp37m-win_amd64.whl", hash = "sha256:fce28b3c8a81b6b36dfac9feb1de115bab619b3c13905b419ec71d03a3fc1423"},
-    {file = "multidict-6.0.5-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:76f067f5121dcecf0d63a67f29080b26c43c71a98b10c701b0677e4a065fbd54"},
-    {file = "multidict-6.0.5-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:b82cc8ace10ab5bd93235dfaab2021c70637005e1ac787031f4d1da63d493c1d"},
-    {file = "multidict-6.0.5-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:5cb241881eefd96b46f89b1a056187ea8e9ba14ab88ba632e68d7a2ecb7aadf7"},
-    {file = "multidict-6.0.5-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e8e94e6912639a02ce173341ff62cc1201232ab86b8a8fcc05572741a5dc7d93"},
-    {file = "multidict-6.0.5-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:09a892e4a9fb47331da06948690ae38eaa2426de97b4ccbfafbdcbe5c8f37ff8"},
-    {file = "multidict-6.0.5-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:55205d03e8a598cfc688c71ca8ea5f66447164efff8869517f175ea632c7cb7b"},
-    {file = "multidict-6.0.5-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:37b15024f864916b4951adb95d3a80c9431299080341ab9544ed148091b53f50"},
-    {file = "multidict-6.0.5-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f2a1dee728b52b33eebff5072817176c172050d44d67befd681609b4746e1c2e"},
-    {file = "multidict-6.0.5-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:edd08e6f2f1a390bf137080507e44ccc086353c8e98c657e666c017718561b89"},
-    {file = "multidict-6.0.5-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:60d698e8179a42ec85172d12f50b1668254628425a6bd611aba022257cac1386"},
-    {file = "multidict-6.0.5-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:3d25f19500588cbc47dc19081d78131c32637c25804df8414463ec908631e453"},
-    {file = "multidict-6.0.5-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:4cc0ef8b962ac7a5e62b9e826bd0cd5040e7d401bc45a6835910ed699037a461"},
-    {file = "multidict-6.0.5-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:eca2e9d0cc5a889850e9bbd68e98314ada174ff6ccd1129500103df7a94a7a44"},
-    {file = "multidict-6.0.5-cp38-cp38-win32.whl", hash = "sha256:4a6a4f196f08c58c59e0b8ef8ec441d12aee4125a7d4f4fef000ccb22f8d7241"},
-    {file = "multidict-6.0.5-cp38-cp38-win_amd64.whl", hash = "sha256:0275e35209c27a3f7951e1ce7aaf93ce0d163b28948444bec61dd7badc6d3f8c"},
-    {file = "multidict-6.0.5-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:e7be68734bd8c9a513f2b0cfd508802d6609da068f40dc57d4e3494cefc92929"},
-    {file = "multidict-6.0.5-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:1d9ea7a7e779d7a3561aade7d596649fbecfa5c08a7674b11b423783217933f9"},
-    {file = "multidict-6.0.5-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:ea1456df2a27c73ce51120fa2f519f1bea2f4a03a917f4a43c8707cf4cbbae1a"},
-    {file = "multidict-6.0.5-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cf590b134eb70629e350691ecca88eac3e3b8b3c86992042fb82e3cb1830d5e1"},
-    {file = "multidict-6.0.5-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:5c0631926c4f58e9a5ccce555ad7747d9a9f8b10619621f22f9635f069f6233e"},
-    {file = "multidict-6.0.5-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:dce1c6912ab9ff5f179eaf6efe7365c1f425ed690b03341911bf4939ef2f3046"},
-    {file = "multidict-6.0.5-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c0868d64af83169e4d4152ec612637a543f7a336e4a307b119e98042e852ad9c"},
-    {file = "multidict-6.0.5-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:141b43360bfd3bdd75f15ed811850763555a251e38b2405967f8e25fb43f7d40"},
-    {file = "multidict-6.0.5-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:7df704ca8cf4a073334e0427ae2345323613e4df18cc224f647f251e5e75a527"},
-    {file = "multidict-6.0.5-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:6214c5a5571802c33f80e6c84713b2c79e024995b9c5897f794b43e714daeec9"},
-    {file = "multidict-6.0.5-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:cd6c8fca38178e12c00418de737aef1261576bd1b6e8c6134d3e729a4e858b38"},
-    {file = "multidict-6.0.5-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:e02021f87a5b6932fa6ce916ca004c4d441509d33bbdbeca70d05dff5e9d2479"},
-    {file = "multidict-6.0.5-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:ebd8d160f91a764652d3e51ce0d2956b38efe37c9231cd82cfc0bed2e40b581c"},
-    {file = "multidict-6.0.5-cp39-cp39-win32.whl", hash = "sha256:04da1bb8c8dbadf2a18a452639771951c662c5ad03aefe4884775454be322c9b"},
-    {file = "multidict-6.0.5-cp39-cp39-win_amd64.whl", hash = "sha256:d6f6d4f185481c9669b9447bf9d9cf3b95a0e9df9d169bbc17e363b7d5487755"},
-    {file = "multidict-6.0.5-py3-none-any.whl", hash = "sha256:0d63c74e3d7ab26de115c49bffc92cc77ed23395303d496eae515d4204a625e7"},
-    {file = "multidict-6.0.5.tar.gz", hash = "sha256:f7e301075edaf50500f0b341543c41194d8df3ae5caf4702f2095f3ca73dd8da"},
+    {file = "multidict-6.0.4-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:0b1a97283e0c85772d613878028fec909f003993e1007eafa715b24b377cb9b8"},
+    {file = "multidict-6.0.4-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:eeb6dcc05e911516ae3d1f207d4b0520d07f54484c49dfc294d6e7d63b734171"},
+    {file = "multidict-6.0.4-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:d6d635d5209b82a3492508cf5b365f3446afb65ae7ebd755e70e18f287b0adf7"},
+    {file = "multidict-6.0.4-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c048099e4c9e9d615545e2001d3d8a4380bd403e1a0578734e0d31703d1b0c0b"},
+    {file = "multidict-6.0.4-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:ea20853c6dbbb53ed34cb4d080382169b6f4554d394015f1bef35e881bf83547"},
+    {file = "multidict-6.0.4-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:16d232d4e5396c2efbbf4f6d4df89bfa905eb0d4dc5b3549d872ab898451f569"},
+    {file = "multidict-6.0.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:36c63aaa167f6c6b04ef2c85704e93af16c11d20de1d133e39de6a0e84582a93"},
+    {file = "multidict-6.0.4-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:64bdf1086b6043bf519869678f5f2757f473dee970d7abf6da91ec00acb9cb98"},
+    {file = "multidict-6.0.4-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:43644e38f42e3af682690876cff722d301ac585c5b9e1eacc013b7a3f7b696a0"},
+    {file = "multidict-6.0.4-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:7582a1d1030e15422262de9f58711774e02fa80df0d1578995c76214f6954988"},
+    {file = "multidict-6.0.4-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:ddff9c4e225a63a5afab9dd15590432c22e8057e1a9a13d28ed128ecf047bbdc"},
+    {file = "multidict-6.0.4-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:ee2a1ece51b9b9e7752e742cfb661d2a29e7bcdba2d27e66e28a99f1890e4fa0"},
+    {file = "multidict-6.0.4-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:a2e4369eb3d47d2034032a26c7a80fcb21a2cb22e1173d761a162f11e562caa5"},
+    {file = "multidict-6.0.4-cp310-cp310-win32.whl", hash = "sha256:574b7eae1ab267e5f8285f0fe881f17efe4b98c39a40858247720935b893bba8"},
+    {file = "multidict-6.0.4-cp310-cp310-win_amd64.whl", hash = "sha256:4dcbb0906e38440fa3e325df2359ac6cb043df8e58c965bb45f4e406ecb162cc"},
+    {file = "multidict-6.0.4-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:0dfad7a5a1e39c53ed00d2dd0c2e36aed4650936dc18fd9a1826a5ae1cad6f03"},
+    {file = "multidict-6.0.4-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:64da238a09d6039e3bd39bb3aee9c21a5e34f28bfa5aa22518581f910ff94af3"},
+    {file = "multidict-6.0.4-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:ff959bee35038c4624250473988b24f846cbeb2c6639de3602c073f10410ceba"},
+    {file = "multidict-6.0.4-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:01a3a55bd90018c9c080fbb0b9f4891db37d148a0a18722b42f94694f8b6d4c9"},
+    {file = "multidict-6.0.4-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c5cb09abb18c1ea940fb99360ea0396f34d46566f157122c92dfa069d3e0e982"},
+    {file = "multidict-6.0.4-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:666daae833559deb2d609afa4490b85830ab0dfca811a98b70a205621a6109fe"},
+    {file = "multidict-6.0.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:11bdf3f5e1518b24530b8241529d2050014c884cf18b6fc69c0c2b30ca248710"},
+    {file = "multidict-6.0.4-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7d18748f2d30f94f498e852c67d61261c643b349b9d2a581131725595c45ec6c"},
+    {file = "multidict-6.0.4-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:458f37be2d9e4c95e2d8866a851663cbc76e865b78395090786f6cd9b3bbf4f4"},
+    {file = "multidict-6.0.4-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:b1a2eeedcead3a41694130495593a559a668f382eee0727352b9a41e1c45759a"},
+    {file = "multidict-6.0.4-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:7d6ae9d593ef8641544d6263c7fa6408cc90370c8cb2bbb65f8d43e5b0351d9c"},
+    {file = "multidict-6.0.4-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:5979b5632c3e3534e42ca6ff856bb24b2e3071b37861c2c727ce220d80eee9ed"},
+    {file = "multidict-6.0.4-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:dcfe792765fab89c365123c81046ad4103fcabbc4f56d1c1997e6715e8015461"},
+    {file = "multidict-6.0.4-cp311-cp311-win32.whl", hash = "sha256:3601a3cece3819534b11d4efc1eb76047488fddd0c85a3948099d5da4d504636"},
+    {file = "multidict-6.0.4-cp311-cp311-win_amd64.whl", hash = "sha256:81a4f0b34bd92df3da93315c6a59034df95866014ac08535fc819f043bfd51f0"},
+    {file = "multidict-6.0.4-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:67040058f37a2a51ed8ea8f6b0e6ee5bd78ca67f169ce6122f3e2ec80dfe9b78"},
+    {file = "multidict-6.0.4-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:853888594621e6604c978ce2a0444a1e6e70c8d253ab65ba11657659dcc9100f"},
+    {file = "multidict-6.0.4-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:39ff62e7d0f26c248b15e364517a72932a611a9b75f35b45be078d81bdb86603"},
+    {file = "multidict-6.0.4-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:af048912e045a2dc732847d33821a9d84ba553f5c5f028adbd364dd4765092ac"},
+    {file = "multidict-6.0.4-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b1e8b901e607795ec06c9e42530788c45ac21ef3aaa11dbd0c69de543bfb79a9"},
+    {file = "multidict-6.0.4-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:62501642008a8b9871ddfccbf83e4222cf8ac0d5aeedf73da36153ef2ec222d2"},
+    {file = "multidict-6.0.4-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:99b76c052e9f1bc0721f7541e5e8c05db3941eb9ebe7b8553c625ef88d6eefde"},
+    {file = "multidict-6.0.4-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:509eac6cf09c794aa27bcacfd4d62c885cce62bef7b2c3e8b2e49d365b5003fe"},
+    {file = "multidict-6.0.4-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:21a12c4eb6ddc9952c415f24eef97e3e55ba3af61f67c7bc388dcdec1404a067"},
+    {file = "multidict-6.0.4-cp37-cp37m-musllinux_1_1_s390x.whl", hash = "sha256:5cad9430ab3e2e4fa4a2ef4450f548768400a2ac635841bc2a56a2052cdbeb87"},
+    {file = "multidict-6.0.4-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:ab55edc2e84460694295f401215f4a58597f8f7c9466faec545093045476327d"},
+    {file = "multidict-6.0.4-cp37-cp37m-win32.whl", hash = "sha256:5a4dcf02b908c3b8b17a45fb0f15b695bf117a67b76b7ad18b73cf8e92608775"},
+    {file = "multidict-6.0.4-cp37-cp37m-win_amd64.whl", hash = "sha256:6ed5f161328b7df384d71b07317f4d8656434e34591f20552c7bcef27b0ab88e"},
+    {file = "multidict-6.0.4-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:5fc1b16f586f049820c5c5b17bb4ee7583092fa0d1c4e28b5239181ff9532e0c"},
+    {file = "multidict-6.0.4-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:1502e24330eb681bdaa3eb70d6358e818e8e8f908a22a1851dfd4e15bc2f8161"},
+    {file = "multidict-6.0.4-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:b692f419760c0e65d060959df05f2a531945af31fda0c8a3b3195d4efd06de11"},
+    {file = "multidict-6.0.4-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:45e1ecb0379bfaab5eef059f50115b54571acfbe422a14f668fc8c27ba410e7e"},
+    {file = "multidict-6.0.4-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:ddd3915998d93fbcd2566ddf9cf62cdb35c9e093075f862935573d265cf8f65d"},
+    {file = "multidict-6.0.4-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:59d43b61c59d82f2effb39a93c48b845efe23a3852d201ed2d24ba830d0b4cf2"},
+    {file = "multidict-6.0.4-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:cc8e1d0c705233c5dd0c5e6460fbad7827d5d36f310a0fadfd45cc3029762258"},
+    {file = "multidict-6.0.4-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d6aa0418fcc838522256761b3415822626f866758ee0bc6632c9486b179d0b52"},
+    {file = "multidict-6.0.4-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:6748717bb10339c4760c1e63da040f5f29f5ed6e59d76daee30305894069a660"},
+    {file = "multidict-6.0.4-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:4d1a3d7ef5e96b1c9e92f973e43aa5e5b96c659c9bc3124acbbd81b0b9c8a951"},
+    {file = "multidict-6.0.4-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:4372381634485bec7e46718edc71528024fcdc6f835baefe517b34a33c731d60"},
+    {file = "multidict-6.0.4-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:fc35cb4676846ef752816d5be2193a1e8367b4c1397b74a565a9d0389c433a1d"},
+    {file = "multidict-6.0.4-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:4b9d9e4e2b37daddb5c23ea33a3417901fa7c7b3dee2d855f63ee67a0b21e5b1"},
+    {file = "multidict-6.0.4-cp38-cp38-win32.whl", hash = "sha256:e41b7e2b59679edfa309e8db64fdf22399eec4b0b24694e1b2104fb789207779"},
+    {file = "multidict-6.0.4-cp38-cp38-win_amd64.whl", hash = "sha256:d6c254ba6e45d8e72739281ebc46ea5eb5f101234f3ce171f0e9f5cc86991480"},
+    {file = "multidict-6.0.4-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:16ab77bbeb596e14212e7bab8429f24c1579234a3a462105cda4a66904998664"},
+    {file = "multidict-6.0.4-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:bc779e9e6f7fda81b3f9aa58e3a6091d49ad528b11ed19f6621408806204ad35"},
+    {file = "multidict-6.0.4-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:4ceef517eca3e03c1cceb22030a3e39cb399ac86bff4e426d4fc6ae49052cc60"},
+    {file = "multidict-6.0.4-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:281af09f488903fde97923c7744bb001a9b23b039a909460d0f14edc7bf59706"},
+    {file = "multidict-6.0.4-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:52f2dffc8acaba9a2f27174c41c9e57f60b907bb9f096b36b1a1f3be71c6284d"},
+    {file = "multidict-6.0.4-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b41156839806aecb3641f3208c0dafd3ac7775b9c4c422d82ee2a45c34ba81ca"},
+    {file = "multidict-6.0.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d5e3fc56f88cc98ef8139255cf8cd63eb2c586531e43310ff859d6bb3a6b51f1"},
+    {file = "multidict-6.0.4-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:8316a77808c501004802f9beebde51c9f857054a0c871bd6da8280e718444449"},
+    {file = "multidict-6.0.4-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:f70b98cd94886b49d91170ef23ec5c0e8ebb6f242d734ed7ed677b24d50c82cf"},
+    {file = "multidict-6.0.4-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:bf6774e60d67a9efe02b3616fee22441d86fab4c6d335f9d2051d19d90a40063"},
+    {file = "multidict-6.0.4-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:e69924bfcdda39b722ef4d9aa762b2dd38e4632b3641b1d9a57ca9cd18f2f83a"},
+    {file = "multidict-6.0.4-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:6b181d8c23da913d4ff585afd1155a0e1194c0b50c54fcfe286f70cdaf2b7176"},
+    {file = "multidict-6.0.4-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:52509b5be062d9eafc8170e53026fbc54cf3b32759a23d07fd935fb04fc22d95"},
+    {file = "multidict-6.0.4-cp39-cp39-win32.whl", hash = "sha256:27c523fbfbdfd19c6867af7346332b62b586eed663887392cff78d614f9ec313"},
+    {file = "multidict-6.0.4-cp39-cp39-win_amd64.whl", hash = "sha256:33029f5734336aa0d4c0384525da0387ef89148dc7191aae00ca5fb23d7aafc2"},
+    {file = "multidict-6.0.4.tar.gz", hash = "sha256:3666906492efb76453c0e7b97f2cf459b0682e7402c0489a95484965dbc1da49"},
 ]
 
 [[package]]
@@ -2080,132 +2048,55 @@ files = [
 
 [[package]]
 name = "pydantic"
-version = "2.7.4"
-description = "Data validation using Python type hints"
+version = "1.10.13"
+description = "Data validation and settings management using python type hints"
 optional = false
-python-versions = ">=3.8"
+python-versions = ">=3.7"
 files = [
-    {file = "pydantic-2.7.4-py3-none-any.whl", hash = "sha256:ee8538d41ccb9c0a9ad3e0e5f07bf15ed8015b481ced539a1759d8cc89ae90d0"},
-    {file = "pydantic-2.7.4.tar.gz", hash = "sha256:0c84efd9548d545f63ac0060c1e4d39bb9b14db8b3c0652338aecc07b5adec52"},
+    {file = "pydantic-1.10.13-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:efff03cc7a4f29d9009d1c96ceb1e7a70a65cfe86e89d34e4a5f2ab1e5693737"},
+    {file = "pydantic-1.10.13-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:3ecea2b9d80e5333303eeb77e180b90e95eea8f765d08c3d278cd56b00345d01"},
+    {file = "pydantic-1.10.13-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1740068fd8e2ef6eb27a20e5651df000978edce6da6803c2bef0bc74540f9548"},
+    {file = "pydantic-1.10.13-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:84bafe2e60b5e78bc64a2941b4c071a4b7404c5c907f5f5a99b0139781e69ed8"},
+    {file = "pydantic-1.10.13-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:bc0898c12f8e9c97f6cd44c0ed70d55749eaf783716896960b4ecce2edfd2d69"},
+    {file = "pydantic-1.10.13-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:654db58ae399fe6434e55325a2c3e959836bd17a6f6a0b6ca8107ea0571d2e17"},
+    {file = "pydantic-1.10.13-cp310-cp310-win_amd64.whl", hash = "sha256:75ac15385a3534d887a99c713aa3da88a30fbd6204a5cd0dc4dab3d770b9bd2f"},
+    {file = "pydantic-1.10.13-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:c553f6a156deb868ba38a23cf0df886c63492e9257f60a79c0fd8e7173537653"},
+    {file = "pydantic-1.10.13-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:5e08865bc6464df8c7d61439ef4439829e3ab62ab1669cddea8dd00cd74b9ffe"},
+    {file = "pydantic-1.10.13-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e31647d85a2013d926ce60b84f9dd5300d44535a9941fe825dc349ae1f760df9"},
+    {file = "pydantic-1.10.13-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:210ce042e8f6f7c01168b2d84d4c9eb2b009fe7bf572c2266e235edf14bacd80"},
+    {file = "pydantic-1.10.13-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:8ae5dd6b721459bfa30805f4c25880e0dd78fc5b5879f9f7a692196ddcb5a580"},
+    {file = "pydantic-1.10.13-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:f8e81fc5fb17dae698f52bdd1c4f18b6ca674d7068242b2aff075f588301bbb0"},
+    {file = "pydantic-1.10.13-cp311-cp311-win_amd64.whl", hash = "sha256:61d9dce220447fb74f45e73d7ff3b530e25db30192ad8d425166d43c5deb6df0"},
+    {file = "pydantic-1.10.13-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:4b03e42ec20286f052490423682016fd80fda830d8e4119f8ab13ec7464c0132"},
+    {file = "pydantic-1.10.13-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f59ef915cac80275245824e9d771ee939133be38215555e9dc90c6cb148aaeb5"},
+    {file = "pydantic-1.10.13-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:5a1f9f747851338933942db7af7b6ee8268568ef2ed86c4185c6ef4402e80ba8"},
+    {file = "pydantic-1.10.13-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:97cce3ae7341f7620a0ba5ef6cf043975cd9d2b81f3aa5f4ea37928269bc1b87"},
+    {file = "pydantic-1.10.13-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:854223752ba81e3abf663d685f105c64150873cc6f5d0c01d3e3220bcff7d36f"},
+    {file = "pydantic-1.10.13-cp37-cp37m-win_amd64.whl", hash = "sha256:b97c1fac8c49be29486df85968682b0afa77e1b809aff74b83081cc115e52f33"},
+    {file = "pydantic-1.10.13-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:c958d053453a1c4b1c2062b05cd42d9d5c8eb67537b8d5a7e3c3032943ecd261"},
+    {file = "pydantic-1.10.13-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:4c5370a7edaac06daee3af1c8b1192e305bc102abcbf2a92374b5bc793818599"},
+    {file = "pydantic-1.10.13-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7d6f6e7305244bddb4414ba7094ce910560c907bdfa3501e9db1a7fd7eaea127"},
+    {file = "pydantic-1.10.13-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d3a3c792a58e1622667a2837512099eac62490cdfd63bd407993aaf200a4cf1f"},
+    {file = "pydantic-1.10.13-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:c636925f38b8db208e09d344c7aa4f29a86bb9947495dd6b6d376ad10334fb78"},
+    {file = "pydantic-1.10.13-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:678bcf5591b63cc917100dc50ab6caebe597ac67e8c9ccb75e698f66038ea953"},
+    {file = "pydantic-1.10.13-cp38-cp38-win_amd64.whl", hash = "sha256:6cf25c1a65c27923a17b3da28a0bdb99f62ee04230c931d83e888012851f4e7f"},
+    {file = "pydantic-1.10.13-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:8ef467901d7a41fa0ca6db9ae3ec0021e3f657ce2c208e98cd511f3161c762c6"},
+    {file = "pydantic-1.10.13-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:968ac42970f57b8344ee08837b62f6ee6f53c33f603547a55571c954a4225691"},
+    {file = "pydantic-1.10.13-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9849f031cf8a2f0a928fe885e5a04b08006d6d41876b8bbd2fc68a18f9f2e3fd"},
+    {file = "pydantic-1.10.13-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:56e3ff861c3b9c6857579de282ce8baabf443f42ffba355bf070770ed63e11e1"},
+    {file = "pydantic-1.10.13-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:9f00790179497767aae6bcdc36355792c79e7bbb20b145ff449700eb076c5f96"},
+    {file = "pydantic-1.10.13-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:75b297827b59bc229cac1a23a2f7a4ac0031068e5be0ce385be1462e7e17a35d"},
+    {file = "pydantic-1.10.13-cp39-cp39-win_amd64.whl", hash = "sha256:e70ca129d2053fb8b728ee7d1af8e553a928d7e301a311094b8a0501adc8763d"},
+    {file = "pydantic-1.10.13-py3-none-any.whl", hash = "sha256:b87326822e71bd5f313e7d3bfdc77ac3247035ac10b0c0618bd99dcf95b1e687"},
+    {file = "pydantic-1.10.13.tar.gz", hash = "sha256:32c8b48dcd3b2ac4e78b0ba4af3a2c2eb6048cb75202f0ea7b34feb740efc340"},
 ]
 
 [package.dependencies]
-annotated-types = ">=0.4.0"
-pydantic-core = "2.18.4"
-typing-extensions = ">=4.6.1"
+typing-extensions = ">=4.2.0"
 
 [package.extras]
-email = ["email-validator (>=2.0.0)"]
-
-[[package]]
-name = "pydantic-core"
-version = "2.18.4"
-description = "Core functionality for Pydantic validation and serialization"
-optional = false
-python-versions = ">=3.8"
-files = [
-    {file = "pydantic_core-2.18.4-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:f76d0ad001edd426b92233d45c746fd08f467d56100fd8f30e9ace4b005266e4"},
-    {file = "pydantic_core-2.18.4-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:59ff3e89f4eaf14050c8022011862df275b552caef8082e37b542b066ce1ff26"},
-    {file = "pydantic_core-2.18.4-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a55b5b16c839df1070bc113c1f7f94a0af4433fcfa1b41799ce7606e5c79ce0a"},
-    {file = "pydantic_core-2.18.4-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:4d0dcc59664fcb8974b356fe0a18a672d6d7cf9f54746c05f43275fc48636851"},
-    {file = "pydantic_core-2.18.4-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:8951eee36c57cd128f779e641e21eb40bc5073eb28b2d23f33eb0ef14ffb3f5d"},
-    {file = "pydantic_core-2.18.4-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:4701b19f7e3a06ea655513f7938de6f108123bf7c86bbebb1196eb9bd35cf724"},
-    {file = "pydantic_core-2.18.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e00a3f196329e08e43d99b79b286d60ce46bed10f2280d25a1718399457e06be"},
-    {file = "pydantic_core-2.18.4-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:97736815b9cc893b2b7f663628e63f436018b75f44854c8027040e05230eeddb"},
-    {file = "pydantic_core-2.18.4-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:6891a2ae0e8692679c07728819b6e2b822fb30ca7445f67bbf6509b25a96332c"},
-    {file = "pydantic_core-2.18.4-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:bc4ff9805858bd54d1a20efff925ccd89c9d2e7cf4986144b30802bf78091c3e"},
-    {file = "pydantic_core-2.18.4-cp310-none-win32.whl", hash = "sha256:1b4de2e51bbcb61fdebd0ab86ef28062704f62c82bbf4addc4e37fa4b00b7cbc"},
-    {file = "pydantic_core-2.18.4-cp310-none-win_amd64.whl", hash = "sha256:6a750aec7bf431517a9fd78cb93c97b9b0c496090fee84a47a0d23668976b4b0"},
-    {file = "pydantic_core-2.18.4-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:942ba11e7dfb66dc70f9ae66b33452f51ac7bb90676da39a7345e99ffb55402d"},
-    {file = "pydantic_core-2.18.4-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:b2ebef0e0b4454320274f5e83a41844c63438fdc874ea40a8b5b4ecb7693f1c4"},
-    {file = "pydantic_core-2.18.4-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a642295cd0c8df1b86fc3dced1d067874c353a188dc8e0f744626d49e9aa51c4"},
-    {file = "pydantic_core-2.18.4-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:5f09baa656c904807e832cf9cce799c6460c450c4ad80803517032da0cd062e2"},
-    {file = "pydantic_core-2.18.4-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:98906207f29bc2c459ff64fa007afd10a8c8ac080f7e4d5beff4c97086a3dabd"},
-    {file = "pydantic_core-2.18.4-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:19894b95aacfa98e7cb093cd7881a0c76f55731efad31073db4521e2b6ff5b7d"},
-    {file = "pydantic_core-2.18.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0fbbdc827fe5e42e4d196c746b890b3d72876bdbf160b0eafe9f0334525119c8"},
-    {file = "pydantic_core-2.18.4-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:f85d05aa0918283cf29a30b547b4df2fbb56b45b135f9e35b6807cb28bc47951"},
-    {file = "pydantic_core-2.18.4-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:e85637bc8fe81ddb73fda9e56bab24560bdddfa98aa64f87aaa4e4b6730c23d2"},
-    {file = "pydantic_core-2.18.4-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:2f5966897e5461f818e136b8451d0551a2e77259eb0f73a837027b47dc95dab9"},
-    {file = "pydantic_core-2.18.4-cp311-none-win32.whl", hash = "sha256:44c7486a4228413c317952e9d89598bcdfb06399735e49e0f8df643e1ccd0558"},
-    {file = "pydantic_core-2.18.4-cp311-none-win_amd64.whl", hash = "sha256:8a7164fe2005d03c64fd3b85649891cd4953a8de53107940bf272500ba8a788b"},
-    {file = "pydantic_core-2.18.4-cp311-none-win_arm64.whl", hash = "sha256:4e99bc050fe65c450344421017f98298a97cefc18c53bb2f7b3531eb39bc7805"},
-    {file = "pydantic_core-2.18.4-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:6f5c4d41b2771c730ea1c34e458e781b18cc668d194958e0112455fff4e402b2"},
-    {file = "pydantic_core-2.18.4-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:2fdf2156aa3d017fddf8aea5adfba9f777db1d6022d392b682d2a8329e087cef"},
-    {file = "pydantic_core-2.18.4-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4748321b5078216070b151d5271ef3e7cc905ab170bbfd27d5c83ee3ec436695"},
-    {file = "pydantic_core-2.18.4-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:847a35c4d58721c5dc3dba599878ebbdfd96784f3fb8bb2c356e123bdcd73f34"},
-    {file = "pydantic_core-2.18.4-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:3c40d4eaad41f78e3bbda31b89edc46a3f3dc6e171bf0ecf097ff7a0ffff7cb1"},
-    {file = "pydantic_core-2.18.4-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:21a5e440dbe315ab9825fcd459b8814bb92b27c974cbc23c3e8baa2b76890077"},
-    {file = "pydantic_core-2.18.4-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:01dd777215e2aa86dfd664daed5957704b769e726626393438f9c87690ce78c3"},
-    {file = "pydantic_core-2.18.4-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:4b06beb3b3f1479d32befd1f3079cc47b34fa2da62457cdf6c963393340b56e9"},
-    {file = "pydantic_core-2.18.4-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:564d7922e4b13a16b98772441879fcdcbe82ff50daa622d681dd682175ea918c"},
-    {file = "pydantic_core-2.18.4-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:0eb2a4f660fcd8e2b1c90ad566db2b98d7f3f4717c64fe0a83e0adb39766d5b8"},
-    {file = "pydantic_core-2.18.4-cp312-none-win32.whl", hash = "sha256:8b8bab4c97248095ae0c4455b5a1cd1cdd96e4e4769306ab19dda135ea4cdb07"},
-    {file = "pydantic_core-2.18.4-cp312-none-win_amd64.whl", hash = "sha256:14601cdb733d741b8958224030e2bfe21a4a881fb3dd6fbb21f071cabd48fa0a"},
-    {file = "pydantic_core-2.18.4-cp312-none-win_arm64.whl", hash = "sha256:c1322d7dd74713dcc157a2b7898a564ab091ca6c58302d5c7b4c07296e3fd00f"},
-    {file = "pydantic_core-2.18.4-cp38-cp38-macosx_10_12_x86_64.whl", hash = "sha256:823be1deb01793da05ecb0484d6c9e20baebb39bd42b5d72636ae9cf8350dbd2"},
-    {file = "pydantic_core-2.18.4-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:ebef0dd9bf9b812bf75bda96743f2a6c5734a02092ae7f721c048d156d5fabae"},
-    {file = "pydantic_core-2.18.4-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ae1d6df168efb88d7d522664693607b80b4080be6750c913eefb77e34c12c71a"},
-    {file = "pydantic_core-2.18.4-cp38-cp38-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:f9899c94762343f2cc2fc64c13e7cae4c3cc65cdfc87dd810a31654c9b7358cc"},
-    {file = "pydantic_core-2.18.4-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:99457f184ad90235cfe8461c4d70ab7dd2680e28821c29eca00252ba90308c78"},
-    {file = "pydantic_core-2.18.4-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:18f469a3d2a2fdafe99296a87e8a4c37748b5080a26b806a707f25a902c040a8"},
-    {file = "pydantic_core-2.18.4-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b7cdf28938ac6b8b49ae5e92f2735056a7ba99c9b110a474473fd71185c1af5d"},
-    {file = "pydantic_core-2.18.4-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:938cb21650855054dc54dfd9120a851c974f95450f00683399006aa6e8abb057"},
-    {file = "pydantic_core-2.18.4-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:44cd83ab6a51da80fb5adbd9560e26018e2ac7826f9626bc06ca3dc074cd198b"},
-    {file = "pydantic_core-2.18.4-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:972658f4a72d02b8abfa2581d92d59f59897d2e9f7e708fdabe922f9087773af"},
-    {file = "pydantic_core-2.18.4-cp38-none-win32.whl", hash = "sha256:1d886dc848e60cb7666f771e406acae54ab279b9f1e4143babc9c2258213daa2"},
-    {file = "pydantic_core-2.18.4-cp38-none-win_amd64.whl", hash = "sha256:bb4462bd43c2460774914b8525f79b00f8f407c945d50881568f294c1d9b4443"},
-    {file = "pydantic_core-2.18.4-cp39-cp39-macosx_10_12_x86_64.whl", hash = "sha256:44a688331d4a4e2129140a8118479443bd6f1905231138971372fcde37e43528"},
-    {file = "pydantic_core-2.18.4-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:a2fdd81edd64342c85ac7cf2753ccae0b79bf2dfa063785503cb85a7d3593223"},
-    {file = "pydantic_core-2.18.4-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:86110d7e1907ab36691f80b33eb2da87d780f4739ae773e5fc83fb272f88825f"},
-    {file = "pydantic_core-2.18.4-cp39-cp39-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:46387e38bd641b3ee5ce247563b60c5ca098da9c56c75c157a05eaa0933ed154"},
-    {file = "pydantic_core-2.18.4-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:123c3cec203e3f5ac7b000bd82235f1a3eced8665b63d18be751f115588fea30"},
-    {file = "pydantic_core-2.18.4-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:dc1803ac5c32ec324c5261c7209e8f8ce88e83254c4e1aebdc8b0a39f9ddb443"},
-    {file = "pydantic_core-2.18.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:53db086f9f6ab2b4061958d9c276d1dbe3690e8dd727d6abf2321d6cce37fa94"},
-    {file = "pydantic_core-2.18.4-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:abc267fa9837245cc28ea6929f19fa335f3dc330a35d2e45509b6566dc18be23"},
-    {file = "pydantic_core-2.18.4-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:a0d829524aaefdebccb869eed855e2d04c21d2d7479b6cada7ace5448416597b"},
-    {file = "pydantic_core-2.18.4-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:509daade3b8649f80d4e5ff21aa5673e4ebe58590b25fe42fac5f0f52c6f034a"},
-    {file = "pydantic_core-2.18.4-cp39-none-win32.whl", hash = "sha256:ca26a1e73c48cfc54c4a76ff78df3727b9d9f4ccc8dbee4ae3f73306a591676d"},
-    {file = "pydantic_core-2.18.4-cp39-none-win_amd64.whl", hash = "sha256:c67598100338d5d985db1b3d21f3619ef392e185e71b8d52bceacc4a7771ea7e"},
-    {file = "pydantic_core-2.18.4-pp310-pypy310_pp73-macosx_10_12_x86_64.whl", hash = "sha256:574d92eac874f7f4db0ca653514d823a0d22e2354359d0759e3f6a406db5d55d"},
-    {file = "pydantic_core-2.18.4-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:1f4d26ceb5eb9eed4af91bebeae4b06c3fb28966ca3a8fb765208cf6b51102ab"},
-    {file = "pydantic_core-2.18.4-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:77450e6d20016ec41f43ca4a6c63e9fdde03f0ae3fe90e7c27bdbeaece8b1ed4"},
-    {file = "pydantic_core-2.18.4-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d323a01da91851a4f17bf592faf46149c9169d68430b3146dcba2bb5e5719abc"},
-    {file = "pydantic_core-2.18.4-pp310-pypy310_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:43d447dd2ae072a0065389092a231283f62d960030ecd27565672bd40746c507"},
-    {file = "pydantic_core-2.18.4-pp310-pypy310_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:578e24f761f3b425834f297b9935e1ce2e30f51400964ce4801002435a1b41ef"},
-    {file = "pydantic_core-2.18.4-pp310-pypy310_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:81b5efb2f126454586d0f40c4d834010979cb80785173d1586df845a632e4e6d"},
-    {file = "pydantic_core-2.18.4-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:ab86ce7c8f9bea87b9d12c7f0af71102acbf5ecbc66c17796cff45dae54ef9a5"},
-    {file = "pydantic_core-2.18.4-pp39-pypy39_pp73-macosx_10_12_x86_64.whl", hash = "sha256:90afc12421df2b1b4dcc975f814e21bc1754640d502a2fbcc6d41e77af5ec312"},
-    {file = "pydantic_core-2.18.4-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:51991a89639a912c17bef4b45c87bd83593aee0437d8102556af4885811d59f5"},
-    {file = "pydantic_core-2.18.4-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:293afe532740370aba8c060882f7d26cfd00c94cae32fd2e212a3a6e3b7bc15e"},
-    {file = "pydantic_core-2.18.4-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b48ece5bde2e768197a2d0f6e925f9d7e3e826f0ad2271120f8144a9db18d5c8"},
-    {file = "pydantic_core-2.18.4-pp39-pypy39_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:eae237477a873ab46e8dd748e515c72c0c804fb380fbe6c85533c7de51f23a8f"},
-    {file = "pydantic_core-2.18.4-pp39-pypy39_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:834b5230b5dfc0c1ec37b2fda433b271cbbc0e507560b5d1588e2cc1148cf1ce"},
-    {file = "pydantic_core-2.18.4-pp39-pypy39_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:e858ac0a25074ba4bce653f9b5d0a85b7456eaddadc0ce82d3878c22489fa4ee"},
-    {file = "pydantic_core-2.18.4-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:2fd41f6eff4c20778d717af1cc50eca52f5afe7805ee530a4fbd0bae284f16e9"},
-    {file = "pydantic_core-2.18.4.tar.gz", hash = "sha256:ec3beeada09ff865c344ff3bc2f427f5e6c26401cc6113d77e372c3fdac73864"},
-]
-
-[package.dependencies]
-typing-extensions = ">=4.6.0,<4.7.0 || >4.7.0"
-
-[[package]]
-name = "pydantic-settings"
-version = "2.3.4"
-description = "Settings management using Pydantic"
-optional = false
-python-versions = ">=3.8"
-files = [
-    {file = "pydantic_settings-2.3.4-py3-none-any.whl", hash = "sha256:11ad8bacb68a045f00e4f862c7a718c8a9ec766aa8fd4c32e39a0594b207b53a"},
-    {file = "pydantic_settings-2.3.4.tar.gz", hash = "sha256:c5802e3d62b78e82522319bbc9b8f8ffb28ad1c988a99311d04f2a6051fca0a7"},
-]
-
-[package.dependencies]
-pydantic = ">=2.7.0"
-python-dotenv = ">=0.21.0"
-
-[package.extras]
-toml = ["tomli (>=2.0.1)"]
-yaml = ["pyyaml (>=6.0.1)"]
+dotenv = ["python-dotenv (>=0.10.4)"]
+email = ["email-validator (>=1.0.3)"]
 
 [[package]]
 name = "pyflakes"
@@ -2301,21 +2192,21 @@ testing = ["argcomplete", "attrs (>=19.2.0)", "hypothesis (>=3.56)", "mock", "no
 
 [[package]]
 name = "pytest-asyncio"
-version = "0.23.7"
+version = "0.21.1"
 description = "Pytest support for asyncio"
 optional = false
-python-versions = ">=3.8"
+python-versions = ">=3.7"
 files = [
-    {file = "pytest_asyncio-0.23.7-py3-none-any.whl", hash = "sha256:009b48127fbe44518a547bddd25611551b0e43ccdbf1e67d12479f569832c20b"},
-    {file = "pytest_asyncio-0.23.7.tar.gz", hash = "sha256:5f5c72948f4c49e7db4f29f2521d4031f1c27f86e57b046126654083d4770268"},
+    {file = "pytest-asyncio-0.21.1.tar.gz", hash = "sha256:40a7eae6dded22c7b604986855ea48400ab15b069ae38116e8c01238e9eeb64d"},
+    {file = "pytest_asyncio-0.21.1-py3-none-any.whl", hash = "sha256:8666c1c8ac02631d7c51ba282e0c69a8a452b211ffedf2599099845da5c5c37b"},
 ]
 
 [package.dependencies]
-pytest = ">=7.0.0,<9"
+pytest = ">=7.0.0"
 
 [package.extras]
 docs = ["sphinx (>=5.3)", "sphinx-rtd-theme (>=1.0)"]
-testing = ["coverage (>=6.2)", "hypothesis (>=5.7.1)"]
+testing = ["coverage (>=6.2)", "flaky (>=3.5.0)", "hypothesis (>=5.7.1)", "mypy (>=0.931)", "pytest-trio (>=0.7.0)"]
 
 [[package]]
 name = "pytest-cov"
@@ -2737,6 +2628,31 @@ exceptiongroup = {version = "*", markers = "python_version < \"3.11\""}
 trio = ">=0.11"
 wsproto = ">=0.14"
 
+[[package]]
+name = "types-requests"
+version = "2.31.0.6"
+description = "Typing stubs for requests"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "types-requests-2.31.0.6.tar.gz", hash = "sha256:cd74ce3b53c461f1228a9b783929ac73a666658f223e28ed29753771477b3bd0"},
+    {file = "types_requests-2.31.0.6-py3-none-any.whl", hash = "sha256:a2db9cb228a81da8348b49ad6db3f5519452dd20a9c1e1a868c83c5fe88fd1a9"},
+]
+
+[package.dependencies]
+types-urllib3 = "*"
+
+[[package]]
+name = "types-urllib3"
+version = "1.26.25.14"
+description = "Typing stubs for urllib3"
+optional = false
+python-versions = "*"
+files = [
+    {file = "types-urllib3-1.26.25.14.tar.gz", hash = "sha256:229b7f577c951b8c1b92c1bc2b2fdb0b49847bd2af6d1cc2a2e3dd340f3bda8f"},
+    {file = "types_urllib3-1.26.25.14-py3-none-any.whl", hash = "sha256:9683bbb7fb72e32bfe9d2be6e04875fbe1b3eeec3cbb4ea231435aa7fd6b4f0e"},
+]
+
 [[package]]
 name = "typing-extensions"
 version = "4.9.0"
@@ -2948,4 +2864,4 @@ multidict = ">=4.0"
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.10"
-content-hash = "26bd75befe5223095b65be293086edf52f34f9043e49107c80a105dc0387dd6a"
+content-hash = "4a980e6d8f54a2f7f6a3c55d4f40ac3a4b27b5ac6573dd2a39e11213a4b126dd"

benchmark/pyproject.toml

@@ -9,47 +9,43 @@ packages = [{ include = "agbenchmark" }]
 
 [tool.poetry.dependencies]
 python = "^3.10"
-agent-protocol-client = {git = "https://github.com/Significant-Gravitas/agent-protocol.git", subdirectory = "packages/client/python"}
-click = "^8.1.3"
-click-default-group = "^1.2.4"
-colorama = "^0.4.6"
-fastapi = "^0.109.1"
-gitpython = "^3.1.32"
-httpx = "^0.24.0"
-matplotlib = "^3.7.2"
-# Multidict 6.0.4 fails to install and is a dependency of aiohttp which is a depenedency of agent-protocol-client
-multidict = "^6.0.5"
-networkx = "^3.1"
+pytest = "^7.3.2"
+requests = "^2.31.0"
 openai = "^1.7.2"
-pandas = "^2.0.3"
+pydantic = "^1.10.9"
+python-dotenv = "^1.0.0"
+click = "^8.1.3"
+types-requests = "^2.31.0.1"
 pexpect = "^4.8.0"
 psutil = "^5.9.5"
-pydantic = "^2.7.2"
-pydantic-settings = "^2.3.4"
-pytest = "^7.3.2"
-pytest-asyncio = "^0.23.3"
-python-dotenv = "^1.0.0"
-python-multipart = "^0.0.7"
+matplotlib = "^3.7.2"
+pandas = "^2.0.3"
+gitpython = "^3.1.32"
+networkx = "^3.1"
+colorama = "^0.4.6"
 pyvis = "^0.3.2"
-requests = "^2.31.0"
 selenium = "^4.11.2"
-tabulate = "^0.9.0"
+pytest-asyncio = "^0.21.1"
+uvicorn = "^0.23.2"
+fastapi = "^0.109.1"
+python-multipart = "^0.0.7"
 toml = "^0.10.2"
-uvicorn = ">=0.23.2,<1"
+# helicone = "^1.0.9"  # incompatible with openai@^1.0.0
+httpx = "^0.24.0"
+agent-protocol-client = "^1.1.0"
+click-default-group = "^1.2.4"
+tabulate = "^0.9.0"
 
 [tool.poetry.group.dev.dependencies]
 black = "^23.12.1"
 flake8 = "^7.0.0"
 isort = "^5.13.1"
 pyright = "^1.1.364"
-pre-commit = "^3.3.3"
-
-# Testing
-pytest-cov = "^5.0.0"
-
-# Dependencies for stuff in reports/
+pandas = "^2.0.3"
 gspread = "^5.10.0"
 oauth2client = "^4.1.3"
+pre-commit = "^3.3.3"
+pytest-cov = "^5.0.0"
 
 [tool.poetry.scripts]
 agbenchmark = "agbenchmark.__main__:cli"

benchmark/reports/format.py

@@ -1,24 +1,20 @@
 #!/usr/bin/env python3
 
-from pathlib import Path
-
 import click
 
 from agbenchmark.reports.processing.report_types import Report
 
 
 @click.command()
-@click.argument(
-    "report_json_file", type=click.Path(exists=True, dir_okay=False, path_type=Path)
-)
-def print_markdown_report(report_json_file: Path):
+@click.argument("report_json_file", type=click.Path(exists=True, dir_okay=False))
+def print_markdown_report(report_json_file: str):
     """
     Generates a Markdown report from a given report.json file.
 
     :param report_json_file: Path to the report.json file.
     :return: A string containing the Markdown formatted report.
     """
-    report = Report.model_validate_json(report_json_file.read_text())
+    report = Report.parse_file(report_json_file)
 
     # Header and metadata
     click.echo("# Benchmark Report")

benchmark/reports/match_records.py

@@ -14,7 +14,7 @@ from pydantic import BaseModel, Field
 class Metrics(BaseModel):
     difficulty: str
     success: bool
-    success_percent: float = Field(alias="success_%")
+    success_percent: float = Field(..., alias="success_%")
     run_time: Optional[str] = None
     fail_reason: Optional[str] = None
     attempted: Optional[bool] = None
@@ -100,7 +100,7 @@ def get_reports():
                         # Load the JSON data from the file
                         json_data = json.load(f)
                         print(f"Processing {report_file}")
-                        report = Report.model_validate(json_data)
+                        report = Report.parse_obj(json_data)
 
                         for test_name, test_data in report.tests.items():
                             test_json = {

check_actions_status.py

@@ -1,109 +0,0 @@
-import json
-import os
-import requests
-import sys
-import time
-from typing import Dict, List, Tuple
-
-
-def get_environment_variables() -> Tuple[str, str, str, str, str]:
-    """Retrieve and return necessary environment variables."""
-    try:
-        with open(os.environ["GITHUB_EVENT_PATH"]) as f:
-            event = json.load(f)
-
-        sha = event["pull_request"]["head"]["sha"]
-
-        return (
-            os.environ["GITHUB_API_URL"],
-            os.environ["GITHUB_REPOSITORY"],
-            sha,
-            os.environ["GITHUB_TOKEN"],
-            os.environ["GITHUB_RUN_ID"],
-        )
-    except KeyError as e:
-        print(f"Error: Missing required environment variable or event data: {e}")
-        sys.exit(1)
-
-
-def make_api_request(url: str, headers: Dict[str, str]) -> Dict:
-    """Make an API request and return the JSON response."""
-    try:
-        print("Making API request to:", url)
-        response = requests.get(url, headers=headers, timeout=10)
-        response.raise_for_status()
-        return response.json()
-    except requests.RequestException as e:
-        print(f"Error: API request failed. {e}")
-        sys.exit(1)
-
-
-def process_check_runs(check_runs: List[Dict]) -> Tuple[bool, bool]:
-    """Process check runs and return their status."""
-    runs_in_progress = False
-    all_others_passed = True
-
-    for run in check_runs:
-        if str(run["name"]) != "Check PR Status":
-            status = run["status"]
-            conclusion = run["conclusion"]
-
-            if status == "completed":
-                if conclusion not in ["success", "skipped", "neutral"]:
-                    all_others_passed = False
-                    print(
-                        f"Check run {run['name']} (ID: {run['id']}) has conclusion: {conclusion}"
-                    )
-            else:
-                runs_in_progress = True
-                print(f"Check run {run['name']} (ID: {run['id']}) is still {status}.")
-                all_others_passed = False
-        else:
-            print(
-                f"Skipping check run {run['name']} (ID: {run['id']}) as it is the current run."
-            )
-
-    return runs_in_progress, all_others_passed
-
-
-def main():
-    api_url, repo, sha, github_token, current_run_id = get_environment_variables()
-
-    endpoint = f"{api_url}/repos/{repo}/commits/{sha}/check-runs"
-    headers = {
-        "Accept": "application/vnd.github.v3+json",
-    }
-    if github_token:
-        headers["Authorization"] = f"token {github_token}"
-
-    print(f"Current run ID: {current_run_id}")
-
-    while True:
-        data = make_api_request(endpoint, headers)
-
-        check_runs = data["check_runs"]
-
-        print("Processing check runs...")
-
-        print(check_runs)
-
-        runs_in_progress, all_others_passed = process_check_runs(check_runs)
-
-        if not runs_in_progress:
-            break
-
-        print(
-            "Some check runs are still in progress. Waiting 3 minutes before checking again..."
-        )
-        time.sleep(180)
-
-    if all_others_passed:
-        print("All other completed check runs have passed. This check passes.")
-        sys.exit(0)
-    else:
-        print("Some check runs have failed or have not completed. This check fails.")
-        sys.exit(1)
-
-
-if __name__ == "__main__":
-    main()

cli.py

@@ -69,8 +69,6 @@ d88P     888  "Y88888  "Y888 "Y88P"   "Y8888P88 888           888
                 bold=True,
             )
         )
-    else:
-        click.echo(click.style("🎉 Setup completed!\n", fg="green"))
 
 
 @cli.group()
@@ -151,11 +149,10 @@ def start(agent_name: str, no_setup: bool):
             setup_process.wait()
             click.echo()
 
-        # FIXME: Doesn't work: Command not found: agbenchmark
-        # subprocess.Popen(["./run_benchmark", "serve"], cwd=agent_dir)
-        # click.echo("⌛ (Re)starting benchmark server...")
-        # wait_until_conn_ready(8080)
-        # click.echo()
+        subprocess.Popen(["./run_benchmark", "serve"], cwd=agent_dir)
+        click.echo("⌛ (Re)starting benchmark server...")
+        wait_until_conn_ready(8080)
+        click.echo()
 
         subprocess.Popen(["./run"], cwd=agent_dir)
         click.echo(f"⌛ (Re)starting agent '{agent_name}'...")

docs/content/AutoGPT/configuration/imagegen.md

@@ -0,0 +1,63 @@
+# 🖼 Image Generation configuration
+
+| Config variable  | Values                          |                      |
+| ---------------- | ------------------------------- | -------------------- |
+| `IMAGE_PROVIDER` | `dalle` `huggingface` `sdwebui` | **default: `dalle`** |
+
+## DALL-e
+
+In `.env`, make sure `IMAGE_PROVIDER` is commented (or set to `dalle`):
+
+```ini
+# IMAGE_PROVIDER=dalle    # this is the default
+```
+
+Further optional configuration:
+
+| Config variable  | Values             |                |
+| ---------------- | ------------------ | -------------- |
+| `IMAGE_SIZE`     | `256` `512` `1024` | default: `256` |
+
+## Hugging Face
+
+To use text-to-image models from Hugging Face, you need a Hugging Face API token.
+Link to the appropriate settings page: [Hugging Face > Settings > Tokens](https://huggingface.co/settings/tokens)
+
+Once you have an API token, uncomment and adjust these variables in your `.env`:
+
+```ini
+IMAGE_PROVIDER=huggingface
+HUGGINGFACE_API_TOKEN=your-huggingface-api-token
+```
+
+Further optional configuration:
+
+| Config variable           | Values                 |                                          |
+| ------------------------- | ---------------------- | ---------------------------------------- |
+| `HUGGINGFACE_IMAGE_MODEL` | see [available models] | default: `CompVis/stable-diffusion-v1-4` |
+
+[available models]: https://huggingface.co/models?pipeline_tag=text-to-image
+
+## Stable Diffusion WebUI
+
+It is possible to use your own self-hosted Stable Diffusion WebUI with AutoGPT:
+
+```ini
+IMAGE_PROVIDER=sdwebui
+```
+
+!!! note
+    Make sure you are running WebUI with `--api` enabled.
+
+Further optional configuration:
+
+| Config variable | Values                  |                                  |
+| --------------- | ----------------------- | -------------------------------- |
+| `SD_WEBUI_URL`  | URL to your WebUI       | default: `http://127.0.0.1:7860` |
+| `SD_WEBUI_AUTH` | `{username}:{password}` | *Note: do not copy the braces!*  |
+
+## Selenium
+
+```shell
+sudo Xvfb :10 -ac -screen 0 1024x768x24 & DISPLAY=:10 <YOUR_CLIENT>
+```

docs/content/AutoGPT/configuration/options.md

@@ -1,18 +1,21 @@
 # Configuration
 
-Configuration of sensitive settings such as API credentials is done through environment variables.
-You can set configuration variables via the `.env` file. If you don't have a `.env` file, create a copy of `.env.template` in your `AutoGPT` folder and name it `.env`.
+Configuration is controlled through the `Config` object. You can set configuration variables via the `.env` file. If you don't have a `.env` file, create a copy of `.env.template` in your `AutoGPT` folder and name it `.env`.
 
 ## Environment Variables
 
+- `AUDIO_TO_TEXT_PROVIDER`: Audio To Text Provider. Only option currently is `huggingface`. Default: huggingface
 - `AUTHORISE_COMMAND_KEY`: Key response accepted when authorising commands. Default: y
 - `ANTHROPIC_API_KEY`: Set this if you want to use Anthropic models with AutoGPT
 - `AZURE_CONFIG_FILE`: Location of the Azure Config file relative to the AutoGPT root directory. Default: azure.yaml
-- `COMPONENT_CONFIG_FILE`: Path to the component configuration file (json) for an agent. Optional
-- `DISABLED_COMMANDS`: Commands to disable. Use comma separated names of commands. See the list of commands from built-in components [here](../../forge/components/components.md). Default: None
+- `BROWSE_CHUNK_MAX_LENGTH`: When browsing website, define the length of chunks to summarize. Default: 3000
+- `BROWSE_SPACY_LANGUAGE_MODEL`: [spaCy language model](https://spacy.io/usage/models) to use when creating chunks. Default: en_core_web_sm
+- `CHAT_MESSAGES_ENABLED`: Enable chat messages. Optional
+- `DISABLED_COMMANDS`: Commands to disable. Use comma separated names of commands. See the list of commands from built-in components [here](../components/components.md). Default: None
 - `ELEVENLABS_API_KEY`: ElevenLabs API Key. Optional.
 - `ELEVENLABS_VOICE_ID`: ElevenLabs Voice ID. Optional.
 - `EMBEDDING_MODEL`: LLM Model to use for embedding tasks. Default: `text-embedding-3-small`
+- `EXECUTE_LOCAL_COMMANDS`: If shell commands should be executed locally. Default: False
 - `EXIT_KEY`: Exit key accepted to exit. Default: n
 - `FAST_LLM`: LLM Model to use for most tasks. Default: `gpt-3.5-turbo-0125`
 - `GITHUB_API_KEY`: [Github API Key](https://github.com/settings/tokens). Optional.
@@ -20,16 +23,26 @@ You can set configuration variables via the `.env` file. If you don't have a `.e
 - `GOOGLE_API_KEY`: Google API key. Optional.
 - `GOOGLE_CUSTOM_SEARCH_ENGINE_ID`: [Google custom search engine ID](https://programmablesearchengine.google.com/controlpanel/all). Optional.
 - `GROQ_API_KEY`: Set this if you want to use Groq models with AutoGPT
+- `HEADLESS_BROWSER`: Use a headless browser while AutoGPT uses a web browser. Setting to `False` will allow you to see AutoGPT operate the browser. Default: True
 - `HUGGINGFACE_API_TOKEN`: HuggingFace API, to be used for both image generation and audio to text. Optional.
+- `HUGGINGFACE_AUDIO_TO_TEXT_MODEL`: HuggingFace audio to text model. Default: CompVis/stable-diffusion-v1-4
 - `HUGGINGFACE_IMAGE_MODEL`: HuggingFace model to use for image generation. Default: CompVis/stable-diffusion-v1-4
-- `LLAMAFILE_API_BASE`: Llamafile API base URL. Default: `http://localhost:8080/v1`
-- `OPENAI_API_KEY`: Set this if you want to use OpenAI models; [OpenAI API Key](https://platform.openai.com/account/api-keys).
+- `IMAGE_PROVIDER`: Image provider. Options are `dalle`, `huggingface`, and `sdwebui`. Default: dalle
+- `IMAGE_SIZE`: Default size of image to generate. Default: 256
+- `OPENAI_API_KEY`: *REQUIRED*- Your [OpenAI API Key](https://platform.openai.com/account/api-keys).
 - `OPENAI_ORGANIZATION`: Organization ID in OpenAI. Optional.
 - `PLAIN_OUTPUT`: Plain output, which disables the spinner. Default: False
 - `RESTRICT_TO_WORKSPACE`: The restrict file reading and writing to the workspace directory. Default: True
 - `SD_WEBUI_AUTH`: Stable Diffusion Web UI username:password pair. Optional.
+- `SD_WEBUI_URL`: Stable Diffusion Web UI URL. Default: http://localhost:7860
+- `SHELL_ALLOWLIST`: List of shell commands that ARE allowed to be executed by AutoGPT. Only applies if `SHELL_COMMAND_CONTROL` is set to `allowlist`. Default: None
+- `SHELL_COMMAND_CONTROL`: Whether to use `allowlist` or `denylist` to determine what shell commands can be executed (Default: denylist)
+- `SHELL_DENYLIST`: List of shell commands that ARE NOT allowed to be executed by AutoGPT. Only applies if `SHELL_COMMAND_CONTROL` is set to `denylist`. Default: sudo,su
 - `SMART_LLM`: LLM Model to use for "smart" tasks. Default: `gpt-4-turbo-preview`
 - `STREAMELEMENTS_VOICE`: StreamElements voice to use. Default: Brian
 - `TEMPERATURE`: Value of temperature given to OpenAI. Value from 0 to 2. Lower is more deterministic, higher is more random. See https://platform.openai.com/docs/api-reference/completions/create#completions/create-temperature
 - `TEXT_TO_SPEECH_PROVIDER`: Text to Speech Provider. Options are `gtts`, `macos`, `elevenlabs`, and `streamelements`. Default: gtts
+- `USER_AGENT`: User-Agent given when browsing websites. Default: "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36"
 - `USE_AZURE`: Use Azure's LLM Default: False
+- `USE_WEB_BROWSER`: Which web browser to use. Options are `chrome`, `firefox`, `safari` or `edge` Default: chrome
+- `WIPE_REDIS_ON_START`: Wipes data / index on start. Default: True

docs/content/AutoGPT/configuration/search.md

@@ -2,36 +2,36 @@
 
 !!! note
     This section is optional. Use the official Google API if search attempts return
-    error 429. To use the `google` command, you need to set up your
-    Google API key in your environment variables or pass it with configuration to the [`WebSearchComponent`](../../forge/components/built-in-components.md).
+    error 429. To use the `google_official_search` command, you need to set up your
+    Google API key in your environment variables.
 
 Create your project:
 
 1. Go to the [Google Cloud Console](https://console.cloud.google.com/).
-1. If you don't already have an account, create one and log in
-1. Create a new project by clicking on the *Select a Project* dropdown at the top of the
+2. If you don't already have an account, create one and log in
+3. Create a new project by clicking on the *Select a Project* dropdown at the top of the
     page and clicking *New Project*
-1. Give it a name and click *Create*
-1. Set up a custom search API and add to your .env file:
-    1. Go to the [APIs & Services Dashboard](https://console.cloud.google.com/apis/dashboard)
-    1. Click *Enable APIs and Services*
-    1. Search for *Custom Search API* and click on it
-    1. Click *Enable*
-    1. Go to the [Credentials](https://console.cloud.google.com/apis/credentials) page
-    1. Click *Create Credentials*
-    1. Choose *API Key*
-    1. Copy the API key
-    1. Set it as the `GOOGLE_API_KEY` in your `.env` file
-1. [Enable](https://console.developers.google.com/apis/api/customsearch.googleapis.com)
+4. Give it a name and click *Create*
+5. Set up a custom search API and add to your .env file:
+    5. Go to the [APIs & Services Dashboard](https://console.cloud.google.com/apis/dashboard)
+    6. Click *Enable APIs and Services*
+    7. Search for *Custom Search API* and click on it
+    8. Click *Enable*
+    9. Go to the [Credentials](https://console.cloud.google.com/apis/credentials) page
+    10. Click *Create Credentials*
+    11. Choose *API Key*
+    12. Copy the API key
+    13. Set it as the `GOOGLE_API_KEY` in your `.env` file
+14. [Enable](https://console.developers.google.com/apis/api/customsearch.googleapis.com)
     the Custom Search API on your project. (Might need to wait few minutes to propagate.)
     Set up a custom search engine and add to your .env file:
-    1. Go to the [Custom Search Engine](https://cse.google.com/cse/all) page
-    1. Click *Add*
-    1. Set up your search engine by following the prompts.
+    15. Go to the [Custom Search Engine](https://cse.google.com/cse/all) page
+    16. Click *Add*
+    17. Set up your search engine by following the prompts.
         You can choose to search the entire web or specific sites
-    1. Once you've created your search engine, click on *Control Panel*
-    1. Click *Basics*
-    1. Copy the *Search engine ID*
-    1. Set it as the `CUSTOM_SEARCH_ENGINE_ID` in your `.env` file
+    18. Once you've created your search engine, click on *Control Panel*
+    19. Click *Basics*
+    20. Copy the *Search engine ID*
+    21. Set it as the `CUSTOM_SEARCH_ENGINE_ID` in your `.env` file
 
 _Remember that your free daily custom search quota allows only up to 100 searches. To increase this limit, you need to assign a billing account to the project to profit from up to 10K daily searches._

docs/content/AutoGPT/setup/docker.md

@@ -71,25 +71,18 @@
           - ./logs:/app/logs
           ## uncomment following lines if you want to make use of these files
           ## you must have them existing in the same folder as this docker-compose.yml
-          ## component configuration file
-          #- type: bind
-          #  source: ./config.json
-          #  target: /app/config.json
     ```
     </details>
 
 
-1. Download [`.env.template`][.env.template] and save it as `.env` in the AutoGPT folder.
-2. Follow the standard [configuration instructions](../index.md#completing-the-setup),
+4. Download [`.env.template`][.env.template] and save it as `.env` in the AutoGPT folder.
+5. Follow the standard [configuration instructions](../index.md#completing-the-setup),
    from step 3 onwards and excluding `poetry install` steps.
-3. Pull the latest image from [Docker Hub]
+6. Pull the latest image from [Docker Hub]
 
     ```shell
     docker pull significantgravitas/auto-gpt
     ```
-4. _Optional: mount configuration file._
-      If you have component configuration file, for example `config.json`, place it in `autogpt/data/` directory. Or place it in `autogpt/` and uncomment the line in `docker-compose.yml` that mounts it.
-      To learn more about configuring, see [Component configuration](../../forge/components/components.md#json-configuration)
 
 !!! note "Docker only supports headless browsing"
     AutoGPT uses a browser in headless mode by default: `HEADLESS_BROWSER=True`.

docs/content/AutoGPT/setup/index.md

@@ -50,13 +50,7 @@ Since we don't ship AutoGPT as a desktop application, you'll need to download th
 ### Completing the Setup
 
 Once you have cloned or downloaded the project, you can find the AutoGPT Agent in the
-`autogpt/` folder.
-Inside this folder you can configure the AutoGPT application with an `.env` file and (optionally) a JSON configuration file:
-
-- `.env` for environment variables, which are mostly used for sensitive data like API keys
-- a JSON configuration file to customize certain features of AutoGPT's [Components](../../forge/components/introduction.md)
-
-See the [Configuration](../configuration/options.md) reference for a list of available environment variables.
+`autogpt/` folder. In this folder:
 
 1. Find the file named `.env.template`. This file may
     be hidden by default in some operating systems due to the dot prefix. To reveal
@@ -77,9 +71,6 @@ See the [Configuration](../configuration/options.md) reference for a list of ava
 6. Save and close the `.env` file.
 7. _Optional: run `poetry install` to install all required dependencies._ The
     application also checks for and installs any required dependencies when it starts.
-8. _Optional: configure the JSON file (e.g. `config.json`) with your desired settings._
-    The application will use default settings if you don't provide a JSON configuration file.
-    Learn how to [set up the JSON configuration file](../../forge/components/components.md#json-configuration)
 
 You should now be able to explore the CLI (`./autogpt.sh --help`) and run the application.
 
@@ -88,6 +79,7 @@ See the [user guide](../usage.md) for further instructions.
 [show hidden files/Windows]: https://support.microsoft.com/en-us/windows/view-hidden-files-and-folders-in-windows-97fbc472-c603-9d90-91d0-1166d1d9f4b5
 [show hidden files/macOS]: https://www.pcmag.com/how-to/how-to-access-your-macs-hidden-files
 
+
 ## Setting up LLM providers
 
 You can use AutoGPT with any of the following LLM providers.
@@ -198,66 +190,3 @@ If you don't know which to choose, you can safely go with OpenAI*.
 
 [groq/api-keys]: https://console.groq.com/keys
 [groq/models]: https://console.groq.com/docs/models
-
-
-### Llamafile
-
-With llamafile you can run models locally, which means no need to set up billing,
-and guaranteed data privacy.
-
-For more information and in-depth documentation, check out the [llamafile documentation].
-
-!!! warning
-    At the moment, llamafile only serves one model at a time. This means you can not
-    set `SMART_LLM` and `FAST_LLM` to two different llamafile models.
-
-!!! warning
-    Due to the issues linked below, llamafiles don't work on WSL. To use a llamafile
-    with AutoGPT in WSL, you will have to run the llamafile in Windows (outside WSL).
-
-    <details>
-    <summary>Instructions</summary>
-
-    1. Get the `llamafile/serve.py` script through one of these two ways:
-        1. Clone the AutoGPT repo somewhere in your Windows environment,
-           with the script located at `autogpt/scripts/llamafile/serve.py`
-        2. Download just the [serve.py] script somewhere in your Windows environment
-    2. Make sure you have `click` installed: `pip install click`
-    3. Run `ip route | grep default | awk '{print $3}'` *inside WSL* to get the address
-       of the WSL host machine
-    4. Run `python3 serve.py --host {WSL_HOST_ADDR}`, where `{WSL_HOST_ADDR}`
-       is the address you found at step 3.
-       If port 8080 is taken, also specify a different port using `--port {PORT}`.
-    5. In WSL, set `LLAMAFILE_API_BASE=http://{WSL_HOST_ADDR}:8080/v1` in your `.env`.
-    6. Follow the rest of the regular instructions below.
-
-    [serve.py]: https://github.com/Significant-Gravitas/AutoGPT/blob/master/autogpt/scripts/llamafile/serve.py
-    </details>
-
-    * [Mozilla-Ocho/llamafile#356](https://github.com/Mozilla-Ocho/llamafile/issues/356)
-    * [Mozilla-Ocho/llamafile#100](https://github.com/Mozilla-Ocho/llamafile/issues/100)
-
-!!! note
-    These instructions will download and use `mistral-7b-instruct-v0.2.Q5_K_M.llamafile`.
-    `mistral-7b-instruct-v0.2` is currently the only tested and supported model.
-    If you want to try other models, you'll have to add them to `LlamafileModelName` in
-    [`llamafile.py`][forge/llamafile.py].
-    For optimal results, you may also have to add some logic to adapt the message format,
-    like `LlamafileProvider._adapt_chat_messages_for_mistral_instruct(..)` does.
-
-1. Run the llamafile serve script:
-   ```shell
-   python3 ./scripts/llamafile/serve.py
-   ```
-   The first time this is run, it will download a file containing the model + runtime,
-   which may take a while and a few gigabytes of disk space.
-
-   To force GPU acceleration, add `--use-gpu` to the command.
-
-3. In `.env`, set `SMART_LLM`/`FAST_LLM` or both to `mistral-7b-instruct-v0.2`
-
-4. If the server is running on different address than `http://localhost:8080/v1`,
-   set `LLAMAFILE_API_BASE` in `.env` to the right base URL
-
-[llamafile documentation]: https://github.com/Mozilla-Ocho/llamafile#readme
-[forge/llamafile.py]: https://github.com/Significant-Gravitas/AutoGPT/blob/master/forge/forge/llm/providers/llamafile/llamafile.py

docs/content/AutoGPT/usage.md

@@ -60,6 +60,10 @@ Options:
   --debug                         Enable Debug Mode
   --gpt3only                      Enable GPT3.5 Only Mode
   --gpt4only                      Enable GPT4 Only Mode
+  -b, --browser-name TEXT         Specifies which web-browser to use when
+                                  using selenium to scrape the web.
+  --allow-downloads               Dangerous: Allows AutoGPT to download files
+                                  natively.
   --skip-news                     Specifies whether to suppress the output of
                                   latest news on startup.
   --install-plugin-deps           Installs external dependencies for 3rd party
@@ -78,7 +82,6 @@ Options:
   --override-directives           If specified, --constraint, --resource and
                                   --best-practice will override the AI's
                                   directives instead of being appended to them
-  --component-config-file TEXT    Path to the json configuration file.
   --help                          Show this message and exit.
 ```
 </details>
@@ -125,6 +128,10 @@ Options:
   --debug                     Enable Debug Mode
   --gpt3only                  Enable GPT3.5 Only Mode
   --gpt4only                  Enable GPT4 Only Mode
+  -b, --browser-name TEXT     Specifies which web-browser to use when using
+                              selenium to scrape the web.
+  --allow-downloads           Dangerous: Allows AutoGPT to download files
+                              natively.
   --install-plugin-deps       Installs external dependencies for 3rd party
                               plugins.
   --help                      Show this message and exit.
@@ -213,5 +220,5 @@ For example, to disable python coding features, set it to the value below:
 DISABLED_COMMANDS=execute_python_code,execute_python_file
 ```
 
-[components]: ../forge/components/components.md
-[commands]: ../forge/components/built-in-components.md
+[components]: ./components/components.md
+[commands]: ./components/built-in-components.md