feat(agent): Improve history format for code flow execution results

- Amend `main.py:update_user(..)` to improve displaying of existing + new prompt strategy output
- Replace `"execute_code_flow"` literals with references to the command definition

.dockerignore

@@ -2,11 +2,11 @@
 *
 
 # AutoGPT
-!original_autogpt/autogpt/
-!original_autogpt/pyproject.toml
-!original_autogpt/poetry.lock
-!original_autogpt/README.md
-!original_autogpt/tests/
+!autogpt/autogpt/
+!autogpt/pyproject.toml
+!autogpt/poetry.lock
+!autogpt/README.md
+!autogpt/tests/
 
 # Benchmark
 !benchmark/agbenchmark/
@@ -15,7 +15,7 @@
 !benchmark/README.md
 
 # Forge
-!forge/
+!forge/forge/
 !forge/pyproject.toml
 !forge/poetry.lock
 !forge/README.md

.gitattributes

@@ -1,10 +1,8 @@
-classic/frontend/build/** linguist-generated
+frontend/build/** linguist-generated
 
 **/poetry.lock linguist-generated
 
 docs/_javascript/** linguist-vendored
 
 # Exclude VCR cassettes from stats
-classic/forge/tests/vcr_cassettes/**/**.y*ml linguist-generated
-
-* text=auto
+forge/tests/vcr_cassettes/**/**.y*ml linguist-generated

.github/CODEOWNERS

@@ -1,7 +1,5 @@
-* @Significant-Gravitas/maintainers
-.github/workflows/ @Significant-Gravitas/devops
-classic/forge/ @Significant-Gravitas/forge-maintainers
-classic/benchmark/ @Significant-Gravitas/benchmark-maintainers
-classic/frontend/ @Significant-Gravitas/frontend-maintainers
-autogpt_platform/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/PULL_REQUEST_TEMPLATE.md

@@ -6,18 +6,26 @@
 
 <!-- Concisely describe all of the changes made in this pull request: -->
 
-
-### Testing 🔍
-> [!NOTE] 
-Only for the new autogpt platform, currently in autogpt_platform/
+### PR Quality Scorecard ✨
 
 <!--
-Please make sure your changes have been tested and are in good working condition. 
-Here is a list of our critical paths, if you need some inspiration on what and how to test:
+Check out our contribution guide:
+https://github.com/Significant-Gravitas/AutoGPT/wiki/Contributing
+
+1. Avoid duplicate work, issues, PRs etc.
+2. Also consider contributing something other than code; see the [contribution guide]
+   for options.
+3. Clearly explain your changes.
+4. Avoid making unnecessary changes, especially if they're purely based on personal
+   preferences. Doing so is the maintainers' job. ;-)
 -->
 
-- Create from scratch and execute an agent with at least 3 blocks
-- Import an agent from file upload, and confirm it executes correctly
-- Upload agent to marketplace
-- Import an agent from marketplace and confirm it executes correctly
-- Edit an agent from monitor, and confirm it executes correctly
+- [x] Have you used the PR description template? &ensp; `+2 pts`
+- [ ] Is your pull request atomic, focusing on a single change? &ensp; `+5 pts`
+- [ ] Have you linked the GitHub issue(s) that this PR addresses? &ensp; `+5 pts`
+- [ ] Have you documented your changes clearly and comprehensively? &ensp; `+5 pts`
+- [ ] Have you changed or added a feature? &ensp; `-4 pts`
+  - [ ] Have you added/updated corresponding documentation? &ensp; `+4 pts`
+  - [ ] Have you added/updated corresponding integration tests? &ensp; `+5 pts`
+- [ ] Have you changed the behavior of AutoGPT? &ensp; `-5 pts`
+  - [ ] Have you also run `agbenchmark` to verify that these changes do not regress performance? &ensp; `+10 pts`

.github/labeler.yml

@@ -1,18 +1,18 @@
 AutoGPT Agent:
 - changed-files:
-  - any-glob-to-any-file: classic/original_autogpt/**
+  - any-glob-to-any-file: autogpt/**
 
 Forge:
 - changed-files:
-  - any-glob-to-any-file: classic/forge/**
+  - any-glob-to-any-file: forge/**
 
 Benchmark:
 - changed-files:
-  - any-glob-to-any-file: classic/benchmark/**
+  - any-glob-to-any-file: benchmark/**
 
 Frontend:
 - changed-files:
-  - any-glob-to-any-file: classic/frontend/**
+  - any-glob-to-any-file: frontend/**
 
 documentation:
 - changed-files:
@@ -20,8 +20,8 @@ documentation:
 
 Builder:
 - changed-files:
-  - any-glob-to-any-file: autogpt_platform/autogpt_builder/**
+  - any-glob-to-any-file: rnd/autogpt_builder/**
 
 Server:
 - changed-files:
-  - any-glob-to-any-file: autogpt_platform/autogpt_server/**
+  - any-glob-to-any-file: rnd/autogpt_server/**

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

@@ -1,23 +1,22 @@
-name: Platform - AutoGPT Builder CI
+name: AutoGPT Builder CI
 
 on:
   push:
     branches: [ master ]
     paths:
       - '.github/workflows/autogpt-builder-ci.yml'
-      - 'autogpt_platform/autogpt_builder/**'
+      - 'rnd/autogpt_builder/**'
   pull_request:
     paths:
       - '.github/workflows/autogpt-builder-ci.yml'
-      - 'autogpt_platform/autogpt_builder/**'
+      - 'rnd/autogpt_builder/**'
 
 defaults:
   run:
     shell: bash
-    working-directory: autogpt_platform/autogpt_builder
+    working-directory: rnd/autogpt_builder
 
 jobs:
-
   lint:
     runs-on: ubuntu-latest
 
@@ -32,10 +31,6 @@ jobs:
       run: |
         npm install
 
-    - name: Check formatting with Prettier
-      run: |
-        npx prettier --check .
-
     - name: Run lint
       run: |
         npm run lint

.github/workflows/autogpt-ci.yml

@@ -1,25 +1,25 @@
-name: Classic - AutoGPT CI
+name: AutoGPT CI
 
 on:
   push:
     branches: [ master, development, ci-test* ]
     paths:
-      - '.github/workflows/classic-autogpt-ci.yml'
-      - 'classic/original_autogpt/**'
+      - '.github/workflows/autogpt-ci.yml'
+      - 'autogpt/**'
   pull_request:
     branches: [ master, development, release-* ]
     paths:
-      - '.github/workflows/classic-autogpt-ci.yml'
-      - 'classic/original_autogpt/**'
+      - '.github/workflows/autogpt-ci.yml'
+      - 'autogpt/**'
 
 concurrency:
-  group: ${{ format('classic-autogpt-ci-{0}', github.head_ref && format('{0}-{1}', github.event_name, github.event.pull_request.number) || github.sha) }}
+  group: ${{ format('autogpt-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: classic/original_autogpt
+    working-directory: autogpt
 
 jobs:
   test:
@@ -86,7 +86,7 @@ jobs:
         uses: actions/cache@v4
         with:
           path: ${{ runner.os == 'macOS' && '~/Library/Caches/pypoetry' || '~/.cache/pypoetry' }}
-          key: poetry-${{ runner.os }}-${{ hashFiles('classic/original_autogpt/poetry.lock') }}
+          key: poetry-${{ runner.os }}-${{ hashFiles('autogpt/poetry.lock') }}
 
       - name: Install Poetry (Unix)
         if: runner.os != 'Windows'
@@ -135,4 +135,4 @@ jobs:
         uses: actions/upload-artifact@v4
         with:
           name: test-logs
-          path: classic/original_autogpt/logs/
+          path: autogpt/logs/

.github/workflows/autogpt-docker-cache-clean.yml

@@ -1,4 +1,4 @@
-name: Classic - Purge Auto-GPT Docker CI cache
+name: Purge Auto-GPT Docker CI cache
 
 on:
   schedule:
@@ -25,8 +25,7 @@ jobs:
       name: Build image
       uses: docker/build-push-action@v5
       with:
-        context: classic/
-        file: classic/Dockerfile.autogpt
+        file: Dockerfile.autogpt
         build-args: BUILD_TYPE=${{ matrix.build-type }}
         load: true    # save to docker images
         # use GHA cache as read-only

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

@@ -1,26 +1,24 @@
-name: Classic - AutoGPT Docker CI
+name: AutoGPT Docker CI
 
 on:
   push:
     branches: [ master, development ]
     paths:
-      - '.github/workflows/classic-autogpt-docker-ci.yml'
-      - 'classic/original_autogpt/**'
-      - 'classic/forge/**'
+      - '.github/workflows/autogpt-docker-ci.yml'
+      - 'autogpt/**'
   pull_request:
     branches: [ master, development, release-* ]
     paths:
-      - '.github/workflows/classic-autogpt-docker-ci.yml'
-      - 'classic/original_autogpt/**'
-      - 'classic/forge/**'
+      - '.github/workflows/autogpt-docker-ci.yml'
+      - 'autogpt/**'
 
 concurrency:
-  group: ${{ format('classic-autogpt-docker-ci-{0}', github.head_ref && format('pr-{0}', github.event.pull_request.number) || github.sha) }}
+  group: ${{ format('autogpt-docker-ci-{0}', github.head_ref && format('pr-{0}', github.event.pull_request.number) || github.sha) }}
   cancel-in-progress: ${{ github.event_name == 'pull_request' }}
 
 defaults:
   run:
-    working-directory: classic/original_autogpt
+    working-directory: autogpt
 
 env:
   IMAGE_NAME: auto-gpt
@@ -49,8 +47,7 @@ jobs:
       name: Build image
       uses: docker/build-push-action@v5
       with:
-        context: classic/
-        file: classic/Dockerfile.autogpt
+        file: Dockerfile.autogpt
         build-args: BUILD_TYPE=${{ matrix.build-type }}
         tags: ${{ env.IMAGE_NAME }}
         labels: GIT_REVISION=${{ github.sha }}
@@ -119,8 +116,7 @@ jobs:
         name: Build image
         uses: docker/build-push-action@v5
         with:
-          context: classic/
-          file: classic/Dockerfile.autogpt
+          file: Dockerfile.autogpt
           build-args: BUILD_TYPE=dev  # include pytest
           tags: >
             ${{ env.IMAGE_NAME }},

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

@@ -1,4 +1,4 @@
-name: Classic - AutoGPT Docker Release
+name: AutoGPT Docker Release
 
 on:
   release:
@@ -44,7 +44,6 @@ jobs:
       name: Build image
       uses: docker/build-push-action@v5
       with:
-        context: classic/
         file: Dockerfile.autogpt
         build-args: BUILD_TYPE=release
         load: true    # save to docker images

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

@@ -1,16 +1,16 @@
-name: Platform - AutoGPT Server CI
+name: AutoGPT Server CI
 
 on:
   push:
     branches: [master, development, ci-test*]
     paths:
       - ".github/workflows/autogpt-server-ci.yml"
-      - "autogpt_platform/autogpt_server/**"
+      - "rnd/autogpt_server/**"
   pull_request:
     branches: [master, development, release-*]
     paths:
       - ".github/workflows/autogpt-server-ci.yml"
-      - "autogpt_platform/autogpt_server/**"
+      - "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) }}
@@ -19,7 +19,7 @@ concurrency:
 defaults:
   run:
     shell: bash
-    working-directory: autogpt_platform/autogpt_server
+    working-directory: rnd/autogpt_server
 
 jobs:
   test:
@@ -37,8 +37,8 @@ jobs:
       - name: Setup PostgreSQL
         uses: ikalnytskyi/action-setup-postgres@v6
         with:
-          username: ${{ secrets.DB_USER || 'postgres' }}
-          password: ${{ secrets.DB_PASS || 'postgres' }}
+          username: ${{ secrets.DB_USER }}
+          password: ${{ secrets.DB_PASS }}
           database: postgres
           port: 5432
         id: postgres
@@ -90,7 +90,7 @@ jobs:
         uses: actions/cache@v4
         with:
           path: ${{ runner.os == 'macOS' && '~/Library/Caches/pypoetry' || '~/.cache/pypoetry' }}
-          key: poetry-${{ runner.os }}-${{ hashFiles('autogpt_platform/autogpt_server/poetry.lock') }}
+          key: poetry-${{ runner.os }}-${{ hashFiles('rnd/autogpt_server/poetry.lock') }}
 
       - name: Install Poetry (Unix)
         if: runner.os != 'Windows'
@@ -115,38 +115,31 @@ jobs:
         run: poetry install
 
       - name: Generate Prisma Client
-        run: poetry run prisma generate
+        run: poetry run prisma generate --schema postgres/schema.prisma
 
       - name: Run Database Migrations
-        run: poetry run prisma migrate dev --name updates
+        run: poetry run prisma migrate dev --schema postgres/schema.prisma --name updates
         env:
           CONNECTION_STR: ${{ steps.postgres.outputs.connection-uri }}
 
-      - id: lint
-        name: Run Linter
+      - 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' }}
+          poetry run pytest -vv \
+            test
     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_USER: ${{ secrets.DB_USER }}
+      DB_PASS: ${{ secrets.DB_PASS }}
       DB_NAME: postgres
       DB_PORT: 5432
       RUN_ENV: local
       PORT: 8080
-      DATABASE_URL: postgresql://${{ secrets.DB_USER || 'postgres' }}:${{ secrets.DB_PASS || 'postgres' }}@localhost:5432/${{ secrets.DB_NAME || 'postgres'}}
+      DATABASE_URL: postgresql://${{ secrets.DB_USER }}:${{ secrets.DB_PASS }}@localhost:5432/${{ secrets.DB_NAME }}
 
       # - name: Upload coverage reports to Codecov
       #   uses: codecov/codecov-action@v4

.github/workflows/autogpts-benchmark.yml

@@ -0,0 +1,97 @@
+name: AutoGPTs Nightly Benchmark
+
+on:
+  workflow_dispatch:
+  schedule:
+    - cron: '0 2 * * *'
+
+jobs:
+  benchmark:
+    permissions:
+      contents: write
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        agent-name: [ autogpt ]
+      fail-fast: false
+    timeout-minutes: 120
+    env:
+      min-python-version: '3.10'
+      REPORTS_BRANCH: data/benchmark-reports
+      REPORTS_FOLDER: ${{ format('benchmark/reports/{0}', matrix.agent-name) }}
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          submodules: true
+
+      - name: Set up Python ${{ env.min-python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ env.min-python-version }}
+
+      - name: Install Poetry
+        run: curl -sSL https://install.python-poetry.org | python -
+
+      - name: Prepare reports folder
+        run: mkdir -p ${{ env.REPORTS_FOLDER }}
+
+      - run: poetry -C benchmark install
+
+      - name: Benchmark ${{ matrix.agent-name }}
+        run: |
+          ./run agent start ${{ matrix.agent-name }}
+          cd ${{ matrix.agent-name }}
+
+          set +e  # Do not quit on non-zero exit codes
+          poetry run agbenchmark run -N 3 \
+            --test=ReadFile \
+            --test=BasicRetrieval --test=RevenueRetrieval2 \
+            --test=CombineCsv --test=LabelCsv --test=AnswerQuestionCombineCsv \
+            --test=UrlShortener --test=TicTacToe --test=Battleship \
+            --test=WebArenaTask_0 --test=WebArenaTask_21 --test=WebArenaTask_124 \
+            --test=WebArenaTask_134 --test=WebArenaTask_163
+
+            # Convert exit code 1 (some challenges failed) to exit code 0
+            if [ $? -eq 0 ] || [ $? -eq 1 ]; then
+              exit 0
+            else
+              exit $?
+            fi
+        env:
+          AGENT_NAME: ${{ matrix.agent-name }}
+          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+          REQUESTS_CA_BUNDLE: /etc/ssl/certs/ca-certificates.crt
+          REPORTS_FOLDER: ${{ format('../../{0}', env.REPORTS_FOLDER) }}  # account for changed workdir
+
+          TELEMETRY_ENVIRONMENT: autogpt-benchmark-ci
+          TELEMETRY_OPT_IN: ${{ github.ref_name == 'master' }}
+
+      - name: Push reports to data branch
+        run: |
+          # BODGE: Remove success_rate.json and regression_tests.json to avoid conflicts on checkout
+          rm ${{ env.REPORTS_FOLDER }}/*.json
+
+          # Find folder with newest (untracked) report in it
+          report_subfolder=$(find ${{ env.REPORTS_FOLDER }} -type f -name 'report.json' \
+            | xargs -I {} dirname {} \
+            | xargs -I {} git ls-files --others --exclude-standard {} \
+            | xargs -I {} dirname {} \
+            | sort -u)
+          json_report_file="$report_subfolder/report.json"
+
+          # Convert JSON report to Markdown
+          markdown_report_file="$report_subfolder/report.md"
+          poetry -C benchmark run benchmark/reports/format.py "$json_report_file" > "$markdown_report_file"
+          cat "$markdown_report_file" >> $GITHUB_STEP_SUMMARY
+
+          git config --global user.name 'GitHub Actions'
+          git config --global user.email 'github-actions@agpt.co'
+          git fetch origin ${{ env.REPORTS_BRANCH }}:${{ env.REPORTS_BRANCH }} \
+            && git checkout ${{ env.REPORTS_BRANCH }} \
+            || git checkout --orphan ${{ env.REPORTS_BRANCH }}
+          git reset --hard
+          git add ${{ env.REPORTS_FOLDER }}
+          git commit -m "Benchmark report for ${{ matrix.agent-name }} @ $(date +'%Y-%m-%d')" \
+            && git push origin ${{ env.REPORTS_BRANCH }}

.github/workflows/autogpts-ci.yml

@@ -1,4 +1,4 @@
-name: Classic - Agent smoke tests
+name: Agent smoke tests
 
 on:
   workflow_dispatch:
@@ -7,37 +7,32 @@ on:
   push:
     branches: [ master, development, ci-test* ]
     paths:
-      - '.github/workflows/classic-autogpts-ci.yml'
-      - 'classic/original_autogpt/**'
-      - 'classic/forge/**'
-      - 'classic/benchmark/**'
-      - 'classic/run'
-      - 'classic/cli.py'
-      - 'classic/setup.py'
+      - '.github/workflows/autogpts-ci.yml'
+      - 'autogpt/**'
+      - 'forge/**'
+      - 'benchmark/**'
+      - 'run'
+      - 'cli.py'
+      - 'setup.py'
       - '!**/*.md'
   pull_request:
     branches: [ master, development, release-* ]
     paths:
-      - '.github/workflows/classic-autogpts-ci.yml'
-      - 'classic/original_autogpt/**'
-      - 'classic/forge/**'
-      - 'classic/benchmark/**'
-      - 'classic/run'
-      - 'classic/cli.py'
-      - 'classic/setup.py'
+      - '.github/workflows/autogpts-ci.yml'
+      - 'autogpt/**'
+      - 'forge/**'
+      - 'benchmark/**'
+      - 'run'
+      - 'cli.py'
+      - 'setup.py'
       - '!**/*.md'
 
-defaults:
-  run:
-    shell: bash
-    working-directory: classic
-
 jobs:
   serve-agent-protocol:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        agent-name: [ original_autogpt ]
+        agent-name: [ autogpt ]
       fail-fast: false
     timeout-minutes: 20
     env:
@@ -55,7 +50,7 @@ jobs:
           python-version: ${{ env.min-python-version }}
 
       - name: Install Poetry
-        working-directory: ./classic/${{ matrix.agent-name }}/
+        working-directory: ./${{ matrix.agent-name }}/
         run: |
           curl -sSL https://install.python-poetry.org | python -
 

.github/workflows/benchmark-ci.yml

@@ -1,18 +1,18 @@
-name: Classic - AGBenchmark CI
+name: AGBenchmark CI
 
 on:
   push:
     branches: [ master, development, ci-test* ]
     paths:
-      - 'classic/benchmark/**'
-      - '!classic/benchmark/reports/**'
-      - .github/workflows/classic-benchmark-ci.yml
+      - 'benchmark/**'
+      - .github/workflows/benchmark-ci.yml
+      - '!benchmark/reports/**'
   pull_request:
     branches: [ master, development, release-* ]
     paths:
-      - 'classic/benchmark/**'
-      - '!classic/benchmark/reports/**'
-      - .github/workflows/classic-benchmark-ci.yml
+      - 'benchmark/**'
+      - '!benchmark/reports/**'
+      - .github/workflows/benchmark-ci.yml
 
 concurrency:
   group: ${{ format('benchmark-ci-{0}', github.head_ref && format('{0}-{1}', github.event_name, github.event.pull_request.number) || github.sha) }}
@@ -39,7 +39,7 @@ jobs:
     defaults:
       run:
         shell: bash
-        working-directory: classic/benchmark
+        working-directory: benchmark
     steps:
       - name: Checkout repository
         uses: actions/checkout@v4
@@ -58,7 +58,7 @@ jobs:
         uses: actions/cache@v4
         with:
           path: ${{ runner.os == 'macOS' && '~/Library/Caches/pypoetry' || '~/.cache/pypoetry' }}
-          key: poetry-${{ runner.os }}-${{ hashFiles('classic/benchmark/poetry.lock') }}
+          key: poetry-${{ runner.os }}-${{ hashFiles('benchmark/poetry.lock') }}
 
       - name: Install Poetry (Unix)
         if: runner.os != 'Windows'
@@ -122,7 +122,7 @@ jobs:
           curl -sSL https://install.python-poetry.org | python -
 
       - name: Run regression tests
-        working-directory: classic
+        working-directory: .
         run: |
           ./run agent start ${{ matrix.agent-name }}
           cd ${{ matrix.agent-name }}
@@ -155,7 +155,7 @@ jobs:
 
           poetry run agbenchmark --mock
 
-          CHANGED=$(git diff --name-only | grep -E '(agbenchmark/challenges)|(../classic/frontend/assets)') || echo "No diffs"
+          CHANGED=$(git diff --name-only | grep -E '(agbenchmark/challenges)|(../frontend/assets)') || echo "No diffs"
           if [ ! -z "$CHANGED" ]; then
             echo "There are unstaged changes please run agbenchmark and commit those changes since they are needed."
             echo "$CHANGED"

.github/workflows/benchmark_publish_package.yml

@@ -1,4 +1,4 @@
-name: Classic - Publish to PyPI
+name: Publish to PyPI
 
 on:
   workflow_dispatch:
@@ -21,21 +21,21 @@ jobs:
         python-version: 3.8
 
     - name: Install Poetry
-      working-directory: ./classic/benchmark/
+      working-directory: ./benchmark/
       run: |
         curl -sSL https://install.python-poetry.org | python3 -
         echo "$HOME/.poetry/bin" >> $GITHUB_PATH
 
     - name: Build project for distribution
-      working-directory: ./classic/benchmark/
+      working-directory: ./benchmark/
       run: poetry build
 
     - name: Install dependencies
-      working-directory: ./classic/benchmark/
+      working-directory: ./benchmark/
       run: poetry install
 
     - name: Check Version
-      working-directory: ./classic/benchmark/
+      working-directory: ./benchmark/
       id: check-version
       run: |
         echo version=$(poetry version --short) >> $GITHUB_OUTPUT
@@ -43,7 +43,7 @@ jobs:
     - name: Create Release
       uses: ncipollo/release-action@v1
       with:
-        artifacts: "classic/benchmark/dist/*"
+        artifacts: "benchmark/dist/*"
         token: ${{ secrets.GITHUB_TOKEN }}
         draft: false
         generateReleaseNotes: false
@@ -51,5 +51,5 @@ jobs:
         commit: master
 
     - name: Build and publish
-      working-directory: ./classic/benchmark/
+      working-directory: ./benchmark/
       run: poetry publish -u __token__ -p ${{ secrets.PYPI_API_TOKEN }}

.github/workflows/close-stale-issues.yml

@@ -1,4 +1,4 @@
-name: Repo - Close stale issues
+name: 'Close stale issues'
 on:
   schedule:
     - cron: '30 1 * * *'

.github/workflows/forge-ci.yml

@@ -1,18 +1,18 @@
-name: Classic - Forge CI
+name: Forge CI
 
 on:
   push:
     branches: [ master, development, ci-test* ]
     paths:
-      - '.github/workflows/classic-forge-ci.yml'
-      - 'classic/forge/**'
-      - '!classic/forge/tests/vcr_cassettes'
+      - '.github/workflows/forge-ci.yml'
+      - 'forge/**'
+      - '!forge/tests/vcr_cassettes'
   pull_request:
     branches: [ master, development, release-* ]
     paths:
-      - '.github/workflows/classic-forge-ci.yml'
-      - 'classic/forge/**'
-      - '!classic/forge/tests/vcr_cassettes'
+      - '.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) }}
@@ -21,7 +21,7 @@ concurrency:
 defaults:
   run:
     shell: bash
-    working-directory: classic/forge
+    working-directory: forge
 
 jobs:
   test:
@@ -110,7 +110,7 @@ jobs:
         uses: actions/cache@v4
         with:
           path: ${{ runner.os == 'macOS' && '~/Library/Caches/pypoetry' || '~/.cache/pypoetry' }}
-          key: poetry-${{ runner.os }}-${{ hashFiles('classic/forge/poetry.lock') }}
+          key: poetry-${{ runner.os }}-${{ hashFiles('forge/poetry.lock') }}
 
       - name: Install Poetry (Unix)
         if: runner.os != 'Windows'
@@ -233,4 +233,4 @@ jobs:
         uses: actions/upload-artifact@v4
         with:
           name: test-logs
-          path: classic/forge/logs/
+          path: forge/logs/

.github/workflows/frontend-ci.yml

@@ -1,4 +1,4 @@
-name: Classic - Frontend CI/CD
+name: Frontend CI/CD
 
 on:
   push:
@@ -7,11 +7,11 @@ on:
       - development
       - 'ci-test*' # This will match any branch that starts with "ci-test"
     paths:
-      - 'classic/frontend/**'
+      - 'frontend/**'
       - '.github/workflows/frontend-ci.yml'
   pull_request:
     paths:
-      - 'classic/frontend/**'
+      - 'frontend/**'
       - '.github/workflows/frontend-ci.yml'
 
 jobs:
@@ -34,7 +34,7 @@ jobs:
 
     - name: Build Flutter to Web
       run: |
-        cd classic/frontend
+        cd frontend
         flutter build web --base-href /app/
 
     # - name: Commit and Push to ${{ env.BUILD_BRANCH }}
@@ -42,7 +42,7 @@ jobs:
     #   run: |
     #     git config --local user.email "action@github.com"
     #     git config --local user.name "GitHub Action"
-    #     git add classic/frontend/build/web
+    #     git add frontend/build/web
     #     git checkout -B ${{ env.BUILD_BRANCH }}
     #     git commit -m "Update frontend build to ${GITHUB_SHA:0:7}" -a
     #     git push -f origin ${{ env.BUILD_BRANCH }}
@@ -51,7 +51,7 @@ jobs:
       if: github.event_name == 'push'
       uses: peter-evans/create-pull-request@v6
       with:
-        add-paths: classic/frontend/build/web
+        add-paths: frontend/build/web
         base: ${{ github.ref_name }}
         branch: ${{ env.BUILD_BRANCH }}
         delete-branch: true

.github/workflows/hackathon.yml

@@ -0,0 +1,133 @@
+name: Hackathon
+
+on:
+  workflow_dispatch:
+    inputs:
+      agents:
+        description: "Agents to run (comma-separated)"
+        required: false
+        default: "autogpt" # Default agents if none are specified
+
+jobs:
+  matrix-setup:
+    runs-on: ubuntu-latest
+    # Service containers to run with `matrix-setup`
+    services:
+      # Label used to access the service container
+      postgres:
+        # Docker Hub image
+        image: postgres
+        # Provide the password for postgres
+        env:
+          POSTGRES_PASSWORD: postgres
+        # Set health checks to wait until postgres has started
+        options: >-
+          --health-cmd pg_isready
+          --health-interval 10s
+          --health-timeout 5s
+          --health-retries 5
+        ports:
+          # Maps tcp port 5432 on service container to the host
+          - 5432:5432
+    outputs:
+      matrix: ${{ steps.set-matrix.outputs.matrix }}
+      env-name: ${{ steps.set-matrix.outputs.env-name }}
+    steps:
+      - id: set-matrix
+        run: |
+          if [ "${{ github.event_name }}" == "schedule" ]; then
+            echo "::set-output name=env-name::production"
+            echo "::set-output name=matrix::[ 'irrelevant']"
+          elif [ "${{ github.event_name }}" == "workflow_dispatch" ]; then
+            IFS=',' read -ra matrix_array <<< "${{ github.event.inputs.agents }}"
+            matrix_string="[ \"$(echo "${matrix_array[@]}" | sed 's/ /", "/g')\" ]"
+            echo "::set-output name=env-name::production"
+            echo "::set-output name=matrix::$matrix_string"
+          else
+            echo "::set-output name=env-name::testing"
+            echo "::set-output name=matrix::[ 'irrelevant' ]"
+          fi
+
+  tests:
+    environment:
+      name: "${{ needs.matrix-setup.outputs.env-name }}"
+    needs: matrix-setup
+    env:
+      min-python-version: "3.10"
+    name: "${{ matrix.agent-name }}"
+    runs-on: ubuntu-latest
+    services:
+      # Label used to access the service container
+      postgres:
+        # Docker Hub image
+        image: postgres
+        # Provide the password for postgres
+        env:
+          POSTGRES_PASSWORD: postgres
+        # Set health checks to wait until postgres has started
+        options: >-
+          --health-cmd pg_isready
+          --health-interval 10s
+          --health-timeout 5s
+          --health-retries 5
+        ports:
+          # Maps tcp port 5432 on service container to the host
+          - 5432:5432
+    timeout-minutes: 50
+    strategy:
+      fail-fast: false
+      matrix:
+        agent-name: ${{fromJson(needs.matrix-setup.outputs.matrix)}}
+    steps:
+      - name: Print Environment Name
+        run: |
+          echo "Matrix Setup Environment Name: ${{ needs.matrix-setup.outputs.env-name }}"
+
+      - name: Check Docker Container
+        id: check
+        run: docker ps
+
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          submodules: true
+
+      - name: Set up Python ${{ env.min-python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ env.min-python-version }}
+
+      - id: get_date
+        name: Get date
+        run: echo "date=$(date +'%Y-%m-%d')" >> $GITHUB_OUTPUT
+
+      - name: Install Poetry
+        run: |
+          curl -sSL https://install.python-poetry.org | python -
+
+      - name: Install Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: v18.15
+
+      - name: Run benchmark
+        run: |
+          link=$(jq -r '.["github_repo_url"]' arena/$AGENT_NAME.json)
+          branch=$(jq -r '.["branch_to_benchmark"]' arena/$AGENT_NAME.json)
+          git clone "$link" -b "$branch" "$AGENT_NAME"
+          cd $AGENT_NAME
+          cp ./$AGENT_NAME/.env.example ./$AGENT_NAME/.env || echo "file not found"
+          ./run agent start $AGENT_NAME
+          cd ../benchmark
+          poetry install
+          poetry run agbenchmark --no-dep
+        env:
+          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+          SERP_API_KEY: ${{ secrets.SERP_API_KEY }}
+          SERPAPI_API_KEY: ${{ secrets.SERP_API_KEY }}
+          WEAVIATE_API_KEY: ${{ secrets.WEAVIATE_API_KEY }}
+          WEAVIATE_URL: ${{ secrets.WEAVIATE_URL }}
+          GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
+          GOOGLE_CUSTOM_SEARCH_ENGINE_ID: ${{ secrets.GOOGLE_CUSTOM_SEARCH_ENGINE_ID }}
+          AGENT_NAME: ${{ matrix.agent-name }}

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

@@ -1,56 +0,0 @@
-name: Platform - AutoGPT Builder Infra
-
-on:
-  push:
-    branches: [ master ]
-    paths:
-      - '.github/workflows/autogpt-infra-ci.yml'
-      - 'autogpt_platform/infra/**'
-  pull_request:
-    paths:
-      - '.github/workflows/autogpt-infra-ci.yml'
-      - 'autogpt_platform/infra/**'
-
-defaults:
-  run:
-    shell: bash
-    working-directory: autogpt_platform/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/pr-label.yml

@@ -1,12 +1,12 @@
-name: Repo - Pull Request auto-label
+name: "Pull Request auto-label"
 
 on:
   # So that PRs touching the same files as the push are updated
   push:
     branches: [ master, development, release-* ]
     paths-ignore:
-      - 'classic/forge/tests/vcr_cassettes'
-      - 'classic/benchmark/reports/**'
+      - 'forge/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.
   # In `pull_request` we wouldn't be able to change labels of fork PRs

.github/workflows/python-checks.yml

@@ -1,24 +1,24 @@
-name: Classic - Python checks
+name: Python checks
 
 on:
   push:
     branches: [ master, development, ci-test* ]
     paths:
       - '.github/workflows/lint-ci.yml'
-      - 'classic/original_autogpt/**'
-      - 'classic/forge/**'
-      - 'classic/benchmark/**'
+      - 'autogpt/**'
+      - 'forge/**'
+      - 'benchmark/**'
       - '**.py'
-      - '!classic/forge/tests/vcr_cassettes'
+      - '!forge/tests/vcr_cassettes'
   pull_request:
     branches: [ master, development, release-* ]
     paths:
       - '.github/workflows/lint-ci.yml'
-      - 'classic/original_autogpt/**'
-      - 'classic/forge/**'
-      - 'classic/benchmark/**'
+      - 'autogpt/**'
+      - 'forge/**'
+      - 'benchmark/**'
       - '**.py'
-      - '!classic/forge/tests/vcr_cassettes'
+      - '!forge/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) }}
@@ -40,18 +40,18 @@ jobs:
         uses: dorny/paths-filter@v3
         with:
           filters: |
-            original_autogpt:
-              - classic/original_autogpt/autogpt/**
-              - classic/original_autogpt/tests/**
-              - classic/original_autogpt/poetry.lock
+            autogpt:
+              - autogpt/autogpt/**
+              - autogpt/tests/**
+              - autogpt/poetry.lock
             forge:
-              - classic/forge/forge/**
-              - classic/forge/tests/**
-              - classic/forge/poetry.lock
+              - forge/forge/**
+              - forge/tests/**
+              - forge/poetry.lock
             benchmark:
-              - classic/benchmark/agbenchmark/**
-              - classic/benchmark/tests/**
-              - classic/benchmark/poetry.lock
+              - benchmark/agbenchmark/**
+              - benchmark/tests/**
+              - benchmark/poetry.lock
     outputs:
       changed-parts: ${{ steps.changes-in.outputs.changes }}
 
@@ -89,23 +89,23 @@ jobs:
       # Install dependencies
 
       - name: Install Python dependencies
-        run: poetry -C classic/${{ matrix.sub-package }} install
+        run: poetry -C ${{ matrix.sub-package }} install
 
       # Lint
 
       - name: Lint (isort)
         run: poetry run isort --check .
-        working-directory: classic/${{ matrix.sub-package }}
+        working-directory: ${{ matrix.sub-package }}
 
       - name: Lint (Black)
         if: success() || failure()
         run: poetry run black --check .
-        working-directory: classic/${{ matrix.sub-package }}
+        working-directory: ${{ matrix.sub-package }}
 
       - name: Lint (Flake8)
         if: success() || failure()
         run: poetry run flake8 .
-        working-directory: classic/${{ matrix.sub-package }}
+        working-directory: ${{ matrix.sub-package }}
 
   types:
     needs: get-changed-parts
@@ -141,11 +141,11 @@ jobs:
       # Install dependencies
 
       - name: Install Python dependencies
-        run: poetry -C classic/${{ matrix.sub-package }} install
+        run: poetry -C ${{ matrix.sub-package }} install
 
       # Typecheck
 
       - name: Typecheck
         if: success() || failure()
         run: poetry run pyright
-        working-directory: classic/${{ matrix.sub-package }}
+        working-directory: ${{ matrix.sub-package }}

.github/workflows/repo-stats.yml

@@ -1,4 +1,4 @@
-name: Repo - Github Stats
+name: github-repo-stats
 
 on:
   schedule:

.github/workflows/repo-workflow-checker.yml

@@ -1,31 +0,0 @@
-name: Repo - 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 .github/workflows/scripts/check_actions_status.py
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/scripts/check_actions_status.py

@@ -1,109 +1,55 @@
-import json
 import os
 import requests
 import sys
-import time
-from typing import Dict, List, Tuple
 
+# GitHub API endpoint
+api_url = os.environ["GITHUB_API_URL"]
+repo = os.environ["GITHUB_REPOSITORY"]
+sha = os.environ["GITHUB_SHA"]
 
-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)
+# GitHub token for authentication
+github_token = os.environ["GITHUB_TOKEN"]
 
-        sha = event["pull_request"]["head"]["sha"]
+# API endpoint for check runs for the specific SHA
+endpoint = f"{api_url}/repos/{repo}/commits/{sha}/check-runs"
 
-        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)
+# Set up headers for authentication
+headers = {
+    "Authorization": f"token {github_token}",
+    "Accept": "application/vnd.github.v3+json"
+}
 
+# Make the API request
+response = requests.get(endpoint, headers=headers)
 
-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)
+if response.status_code != 200:
+    print(f"Error: Unable to fetch check runs data. Status code: {response.status_code}")
+    sys.exit(1)
 
+check_runs = response.json()["check_runs"]
 
-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
+# Flag to track if all other check runs have passed
+all_others_passed = True
 
-    for run in check_runs:
-        if str(run["name"]) != "Check PR Status":
-            status = run["status"]
-            conclusion = run["conclusion"]
+# Current run id
+current_run_id = os.environ["GITHUB_RUN_ID"]
 
-            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}.")
+for run in check_runs:
+    if str(run["id"]) != current_run_id:
+        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:
-            print(
-                f"Skipping check run {run['name']} (ID: {run['id']}) as it is the current run."
-            )
+            print(f"Check run {run['name']} (ID: {run['id']}) is still {status}.")
+            all_others_passed = False
 
-    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()
+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)

.github/workflows/workflow-checker.yml

@@ -0,0 +1,51 @@
+name: PR Status Checker
+on:
+  workflow_run:
+    workflows: ["*"]
+    types:
+      - completed
+
+jobs:
+  status-check:
+    name: Check Actions Status
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4
+    - 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: Debug Information
+      run: |
+        echo "Event name: ${{ github.event_name }}"
+        echo "Workflow: ${{ github.workflow }}"
+        echo "Action: ${{ github.action }}"
+        echo "Actor: ${{ github.actor }}"
+        echo "Repository: ${{ github.repository }}"
+        echo "Ref: ${{ github.ref }}"
+        echo "Head ref: ${{ github.head_ref }}"
+        echo "Base ref: ${{ github.base_ref }}"
+        echo "Event payload:"
+        cat $GITHUB_EVENT_PATH
+    - name: Debug File Structure
+      run: |
+        echo "Current directory:"
+        pwd
+        echo "Directory contents:"
+        ls -R
+        echo "GitHub workspace:"
+        echo $GITHUB_WORKSPACE
+        echo "GitHub workspace contents:"
+        ls -R $GITHUB_WORKSPACE
+    - name: Check Actions Status
+      run: |
+        echo "Current directory before running Python script:"
+        pwd
+        echo "Attempting to run Python script:"
+        python .github/scripts/check_actions_status.py
+      env:
+        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.gitignore

@@ -1,7 +1,7 @@
 ## Original ignores
 .github_access_token
-classic/original_autogpt/keys.py
-classic/original_autogpt/*.json
+autogpt/keys.py
+autogpt/*.json
 auto_gpt_workspace/*
 *.mpeg
 .env
@@ -157,7 +157,7 @@ openai/
 CURRENT_BULLETIN.md
 
 # AgBenchmark
-classic/benchmark/agbenchmark/reports/
+agbenchmark/reports/
 
 # Nodejs
 package-lock.json
@@ -170,4 +170,4 @@ pri*
 ig*
 .github_access_token
 LICENSE.rtf
-autogpt_platform/autogpt_server/settings.py
+rnd/autogpt_server/settings.py

.gitmodules

@@ -1,6 +1,3 @@
-[submodule "classic/forge/tests/vcr_cassettes"]
-	path = classic/forge/tests/vcr_cassettes
+[submodule "forge/tests/vcr_cassettes"]
+	path = forge/tests/vcr_cassettes
 	url = https://github.com/Significant-Gravitas/Auto-GPT-test-cassettes
-[submodule "autogpt_platform/supabase"]
-	path = autogpt_platform/supabase
-	url = https://github.com/supabase/supabase.git

.pre-commit-config.yaml

@@ -16,22 +16,22 @@ repos:
     hooks:
       - id: isort-autogpt
         name: Lint (isort) - AutoGPT
-        entry: poetry -C classic/original_autogpt run isort
-        files: ^classic/original_autogpt/
+        entry: poetry -C autogpt run isort
+        files: ^autogpt/
         types: [file, python]
         language: system
 
       - id: isort-forge
         name: Lint (isort) - Forge
-        entry: poetry -C classic/forge run isort
-        files: ^classic/forge/
+        entry: poetry -C forge run isort
+        files: ^forge/
         types: [file, python]
         language: system
 
       - id: isort-benchmark
         name: Lint (isort) - Benchmark
-        entry: poetry -C classic/benchmark run isort
-        files: ^classic/benchmark/
+        entry: poetry -C benchmark run isort
+        files: ^benchmark/
         types: [file, python]
         language: system
 
@@ -52,20 +52,20 @@ repos:
       - id: flake8
         name: Lint (Flake8) - AutoGPT
         alias: flake8-autogpt
-        files: ^classic/original_autogpt/(autogpt|scripts|tests)/
-        args: [--config=classic/original_autogpt/.flake8]
+        files: ^autogpt/(autogpt|scripts|tests)/
+        args: [--config=autogpt/.flake8]
 
       - id: flake8
         name: Lint (Flake8) - Forge
         alias: flake8-forge
-        files: ^classic/forge/(forge|tests)/
-        args: [--config=classic/forge/.flake8]
+        files: ^forge/(forge|tests)/
+        args: [--config=forge/.flake8]
 
       - id: flake8
         name: Lint (Flake8) - Benchmark
         alias: flake8-benchmark
-        files: ^classic/benchmark/(agbenchmark|tests)/((?!reports).)*[/.]
-        args: [--config=classic/benchmark/.flake8]
+        files: ^benchmark/(agbenchmark|tests)/((?!reports).)*[/.]
+        args: [--config=benchmark/.flake8]
 
   - repo: local
     # To have watertight type checking, we check *all* the files in an affected
@@ -74,10 +74,10 @@ repos:
       - id: pyright
         name: Typecheck - AutoGPT
         alias: pyright-autogpt
-        entry: poetry -C classic/original_autogpt run pyright
+        entry: poetry -C autogpt run pyright
         args: [-p, autogpt, autogpt]
         # include forge source (since it's a path dependency) but exclude *_test.py files:
-        files: ^(classic/original_autogpt/((autogpt|scripts|tests)/|poetry\.lock$)|classic/forge/(classic/forge/.*(?<!_test)\.py|poetry\.lock)$)
+        files: ^(autogpt/((autogpt|scripts|tests)/|poetry\.lock$)|forge/(forge/.*(?<!_test)\.py|poetry\.lock)$)
         types: [file]
         language: system
         pass_filenames: false
@@ -85,9 +85,9 @@ repos:
       - id: pyright
         name: Typecheck - Forge
         alias: pyright-forge
-        entry: poetry -C classic/forge run pyright
+        entry: poetry -C forge run pyright
         args: [-p, forge, forge]
-        files: ^classic/forge/(classic/forge/|poetry\.lock$)
+        files: ^forge/(forge/|poetry\.lock$)
         types: [file]
         language: system
         pass_filenames: false
@@ -95,9 +95,9 @@ repos:
       - id: pyright
         name: Typecheck - Benchmark
         alias: pyright-benchmark
-        entry: poetry -C classic/benchmark run pyright
+        entry: poetry -C benchmark run pyright
         args: [-p, benchmark, benchmark]
-        files: ^classic/benchmark/(agbenchmark/|tests/|poetry\.lock$)
+        files: ^benchmark/(agbenchmark/|tests/|poetry\.lock$)
         types: [file]
         language: system
         pass_filenames: false
@@ -106,22 +106,22 @@ repos:
     hooks:
       - id: pytest-autogpt
         name: Run tests - AutoGPT (excl. slow tests)
-        entry: bash -c 'cd classic/original_autogpt && poetry run pytest --cov=autogpt -m "not slow" tests/unit tests/integration'
+        entry: bash -c 'cd autogpt && poetry run pytest --cov=autogpt -m "not slow" tests/unit tests/integration'
         # include forge source (since it's a path dependency) but exclude *_test.py files:
-        files: ^(classic/original_autogpt/((autogpt|tests)/|poetry\.lock$)|classic/forge/(classic/forge/.*(?<!_test)\.py|poetry\.lock)$)
+        files: ^(autogpt/((autogpt|tests)/|poetry\.lock$)|forge/(forge/.*(?<!_test)\.py|poetry\.lock)$)
         language: system
         pass_filenames: false
 
       - id: pytest-forge
         name: Run tests - Forge (excl. slow tests)
-        entry: bash -c 'cd classic/forge && poetry run pytest --cov=forge -m "not slow"'
-        files: ^classic/forge/(classic/forge/|tests/|poetry\.lock$)
+        entry: bash -c 'cd forge && poetry run pytest --cov=forge -m "not slow"'
+        files: ^forge/(forge/|tests/|poetry\.lock$)
         language: system
         pass_filenames: false
 
       - id: pytest-benchmark
         name: Run tests - Benchmark
-        entry: bash -c 'cd classic/benchmark && poetry run pytest --cov=benchmark'
-        files: ^classic/benchmark/(agbenchmark/|tests/|poetry\.lock$)
+        entry: bash -c 'cd benchmark && poetry run pytest --cov=benchmark'
+        files: ^benchmark/(agbenchmark/|tests/|poetry\.lock$)
         language: system
         pass_filenames: false

.vscode/all-projects.code-workspace

@@ -1,53 +1,39 @@
 {
   "folders": [
     {
-      "name": "autogpt_server",
-      "path": "../autogpt_platform/autogpt_server"
+      "name": "autogpt",
+      "path": "../autogpt"
     },
     {
-      "name": "autogpt_builder",
-      "path": "../autogpt_platform/autogpt_builder"
-    },
-    {
-      "name": "market",
-      "path": "../autogpt_platform/market"
-    },
-    {
-      "name": "lib",
-      "path": "../autogpt_platform/autogpt_libs"
-    },
-    {
-      "name": "infra",
-      "path": "../autogpt_platform/infra"
+      "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": "[root]",
       "path": ".."
-    },
-    {
-      "name": "classic - autogpt",
-      "path": "../classic/original_autogpt"
-    },
-    {
-      "name": "classic - benchmark",
-      "path": "../classic/benchmark"
-    },
-    {
-      "name": "classic - forge",
-      "path": "../classic/forge"
-    },
-    {
-      "name": "classic - frontend",
-      "path": "../classic/frontend"
-    },
+    }
   ],
-  "settings": {
-    "python.analysis.typeCheckingMode": "basic"
-  },
+  "settings": {},
   "extensions": {
     "recommendations": [
       "charliermarsh.ruff",

Dockerfile.autogpt

@@ -29,7 +29,7 @@ ENV PATH="$POETRY_HOME/bin:$PATH"
 RUN poetry config installer.max-workers 10
 
 WORKDIR /app/autogpt
-COPY original_autogpt/pyproject.toml original_autogpt/poetry.lock ./
+COPY autogpt/pyproject.toml autogpt/poetry.lock ./
 
 # Include forge so it can be used as a path dependency
 COPY forge/ ../forge
@@ -42,17 +42,19 @@ ENTRYPOINT ["poetry", "run", "autogpt"]
 CMD []
 
 # dev build -> include everything
-FROM autogpt-base AS autogpt-dev
+FROM autogpt-base as autogpt-dev
 RUN poetry install --no-cache --no-root \
     && rm -rf $(poetry env info --path)/src
-ONBUILD COPY original_autogpt/ ./
+ONBUILD COPY autogpt/ ./
 
 # release build -> include bare minimum
-FROM autogpt-base AS autogpt-release
+FROM autogpt-base as autogpt-release
 RUN poetry install --no-cache --no-root --without dev \
     && rm -rf $(poetry env info --path)/src
-ONBUILD COPY original_autogpt/ ./autogpt
-ONBUILD COPY original_autogpt/README.md ./README.md
+ONBUILD COPY autogpt/autogpt/ ./autogpt
+ONBUILD COPY autogpt/scripts/ ./scripts
+ONBUILD COPY autogpt/plugins/ ./plugins
+ONBUILD COPY autogpt/README.md ./README.md
 ONBUILD RUN mkdir ./data
 
 FROM autogpt-${BUILD_TYPE} AS autogpt

README.md

@@ -55,16 +55,15 @@ Be part of the revolution! **AutoGPT** is here to stay, at the forefront of AI i
 ## 🤖 AutoGPT Classic
 > Below is information about the classic version of AutoGPT.
 
-**🛠️ [Build your own Agent - Quickstart](classic/FORGE-QUICKSTART.md)**
-
+**🛠️ [Build your own Agent - Quickstart](FORGE-QUICKSTART.md)**
 ### 🏗️ Forge
 
-**Forge your own agent!** – Forge is a ready-to-go toolkit to build your own agent application. It handles most of the boilerplate code, 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 [`forge`](/classic/forge/) can also be used individually to speed up development and reduce boilerplate in your agent project.
+**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.
 
-🚀 [**Getting Started with Forge**](https://github.com/Significant-Gravitas/AutoGPT/blob/master/classic/forge/tutorials/001_getting_started.md) –
+🚀 [**Getting Started with Forge**](https://github.com/Significant-Gravitas/AutoGPT/blob/master/forge/tutorials/001_getting_started.md) –
 This guide will walk you through the process of creating your own agent and using the benchmark and user interface.
 
-📘 [Learn More](https://github.com/Significant-Gravitas/AutoGPT/tree/master/classic/forge) about Forge
+📘 [Learn More](https://github.com/Significant-Gravitas/AutoGPT/tree/master/forge) about Forge
 
 ### 🎯 Benchmark
 
@@ -84,7 +83,7 @@ This guide will walk you through the process of creating your own agent and usin
 
 The frontend works out-of-the-box with all agents in the repo. Just use the [CLI] to run your agent of choice!
 
-📘 [Learn More](https://github.com/Significant-Gravitas/AutoGPT/tree/master/classic/frontend) about the Frontend
+📘 [Learn More](https://github.com/Significant-Gravitas/AutoGPT/tree/master/frontend) about the Frontend
 
 ### ⌨️ CLI
 

autogpt/.coveragerc

@@ -1,2 +1,2 @@
-[run]
+[run]
 relative_files = true

autogpt/.env.template

@@ -105,7 +105,6 @@
 ## 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)

autogpt/.gitignore

@@ -1,6 +1,6 @@
 ## Original ignores
-classic/original_autogpt/keys.py
-classic/original_autogpt/*.json
+autogpt/keys.py
+autogpt/*.json
 *.mpeg
 .env
 azure.yaml

autogpt/README.md

@@ -120,9 +120,9 @@ by default on `http://localhost:8000`.
 For more comprehensive instructions, see the [user guide][docs/usage].
 
 [docs]: https://docs.agpt.co/autogpt
-[docs/setup]: https://docs.agpt.co/classic/original_autogpt/setup
-[docs/usage]: https://docs.agpt.co/classic/original_autogpt/usage
-[docs/plugins]: https://docs.agpt.co/classic/original_autogpt/plugins
+[docs/setup]: https://docs.agpt.co/autogpt/setup
+[docs/usage]: https://docs.agpt.co/autogpt/usage
+[docs/plugins]: https://docs.agpt.co/autogpt/plugins
 
 ## 📚 Resources
 * 📔 AutoGPT [project wiki](https://github.com/Significant-Gravitas/AutoGPT/wiki)

autogpt/autogpt/agents/README.md

@@ -34,4 +34,4 @@ class MyAgent(Agent):
         self.my_component = MyComponent()
 ```
 
-For more customization, you can override the `propose_action` and `execute` or even subclass `BaseAgent` directly. This way you can have full control over the agent's components and behavior. Have a look at the [implementation of Agent](https://github.com/Significant-Gravitas/AutoGPT/tree/master/classic/original_autogpt/agents/agent.py) for more details.
+For more customization, you can override the `propose_action` and `execute` or even subclass `BaseAgent` directly. This way you can have full control over the agent's components and behavior. Have a look at the [implementation of Agent](https://github.com/Significant-Gravitas/AutoGPT/tree/master/autogpt/autogpt/agents/agent.py) for more details.

autogpt/autogpt/agents/agent.py

@@ -23,6 +23,7 @@ from forge.components.code_executor.code_executor import (
     CodeExecutorComponent,
     CodeExecutorConfiguration,
 )
+from forge.components.code_flow_executor import CodeFlowExecutionComponent
 from forge.components.context.context import AgentContext, ContextComponent
 from forge.components.file_manager import FileManagerComponent
 from forge.components.git_operations import GitOperationsComponent
@@ -40,7 +41,6 @@ from forge.llm.providers import (
     ChatModelResponse,
     MultiProvider,
 )
-from forge.llm.providers.utils import function_specs_from_commands
 from forge.models.action import (
     ActionErrorResult,
     ActionInterruptedByHuman,
@@ -56,6 +56,7 @@ from forge.utils.exceptions import (
 )
 from pydantic import Field
 
+from .prompt_strategies.code_flow import CodeFlowAgentPromptStrategy
 from .prompt_strategies.one_shot import (
     OneShotAgentActionProposal,
     OneShotAgentPromptStrategy,
@@ -96,11 +97,14 @@ class Agent(BaseAgent[OneShotAgentActionProposal], Configurable[AgentSettings]):
         llm_provider: MultiProvider,
         file_storage: FileStorage,
         app_config: AppConfig,
+        prompt_strategy_class: type[
+            OneShotAgentPromptStrategy | CodeFlowAgentPromptStrategy
+        ] = CodeFlowAgentPromptStrategy,
     ):
         super().__init__(settings)
 
         self.llm_provider = llm_provider
-        prompt_config = OneShotAgentPromptStrategy.default_configuration.model_copy(
+        prompt_config = prompt_strategy_class.default_configuration.model_copy(
             deep=True
         )
         prompt_config.use_functions_api = (
@@ -108,7 +112,7 @@ class Agent(BaseAgent[OneShotAgentActionProposal], Configurable[AgentSettings]):
             # Anthropic currently doesn't support tools + prefilling :(
             and self.llm.provider_name != "anthropic"
         )
-        self.prompt_strategy = OneShotAgentPromptStrategy(prompt_config, logger)
+        self.prompt_strategy = prompt_strategy_class(prompt_config, logger)
         self.commands: list[Command] = []
 
         # Components
@@ -145,6 +149,7 @@ class Agent(BaseAgent[OneShotAgentActionProposal], Configurable[AgentSettings]):
         self.watchdog = WatchdogComponent(settings.config, settings.history).run_after(
             ContextComponent
         )
+        self.code_flow_executor = CodeFlowExecutionComponent(lambda: self.commands)
 
         self.event_history = settings.history
         self.app_config = app_config
@@ -185,7 +190,7 @@ class Agent(BaseAgent[OneShotAgentActionProposal], Configurable[AgentSettings]):
             task=self.state.task,
             ai_profile=self.state.ai_profile,
             ai_directives=directives,
-            commands=function_specs_from_commands(self.commands),
+            commands=self.commands,
             include_os_info=include_os_info,
         )
 
@@ -201,9 +206,7 @@ class Agent(BaseAgent[OneShotAgentActionProposal], Configurable[AgentSettings]):
         if exception:
             prompt.messages.append(ChatMessage.system(f"Error: {exception}"))
 
-        response: ChatModelResponse[
-            OneShotAgentActionProposal
-        ] = await self.llm_provider.create_chat_completion(
+        response: ChatModelResponse = await self.llm_provider.create_chat_completion(
             prompt.messages,
             model_name=self.llm.name,
             completion_parser=self.prompt_strategy.parse_response_content,
@@ -281,7 +284,7 @@ class Agent(BaseAgent[OneShotAgentActionProposal], Configurable[AgentSettings]):
         except AgentException:
             raise
         except Exception as e:
-            raise CommandExecutionError(str(e))
+            raise CommandExecutionError(str(e)) from e
 
     def _get_command(self, command_name: str) -> Command:
         for command in reversed(self.commands):

autogpt/autogpt/agents/prompt_strategies/code_flow.py

@@ -0,0 +1,355 @@
+import inspect
+import re
+from logging import Logger
+from typing import Callable, Iterable, Sequence, get_args, get_origin
+
+from forge.command import Command
+from forge.components.code_flow_executor import CodeFlowExecutionComponent
+from forge.config.ai_directives import AIDirectives
+from forge.config.ai_profile import AIProfile
+from forge.json.parsing import extract_dict_from_json
+from forge.llm.prompting import ChatPrompt, LanguageModelClassification, PromptStrategy
+from forge.llm.prompting.utils import indent
+from forge.llm.providers.schema import (
+    AssistantChatMessage,
+    AssistantFunctionCall,
+    ChatMessage,
+)
+from forge.models.config import SystemConfiguration
+from forge.models.json_schema import JSONSchema
+from forge.utils.exceptions import InvalidAgentResponseError
+from forge.utils.function.code_validation import CodeValidator
+from forge.utils.function.model import FunctionDef
+from pydantic import BaseModel, Field
+
+from autogpt.agents.prompt_strategies.one_shot import (
+    AssistantThoughts,
+    OneShotAgentActionProposal,
+    OneShotAgentPromptConfiguration,
+)
+
+_RESPONSE_INTERFACE_NAME = "AssistantResponse"
+
+
+class CodeFlowAgentActionProposal(BaseModel):
+    thoughts: AssistantThoughts
+    immediate_plan: str = Field(
+        ...,
+        description="We will be running an iterative process to execute the plan, "
+        "Write the partial / immediate plan to execute your plan as detailed and "
+        "efficiently as possible without the help of the reasoning/intelligence. "
+        "The plan should describe the output of the immediate plan, so that the next "
+        "iteration can be executed by taking the output into account. "
+        "Try to do as much as possible without making any assumption or uninformed "
+        "guesses. Avoid large output at all costs!!!\n"
+        "Format: Objective[Objective of this iteration, explain what's the use of this "
+        "iteration for the next one] Plan[Plan that does not require any reasoning or "
+        "intelligence] Output[Output of the plan / should be small, avoid whole file "
+        "output]",
+    )
+    python_code: str = Field(
+        ...,
+        description=(
+            "Write the fully-functional Python code of the immediate plan. "
+            "The output will be an `async def main() -> str` function of the immediate "
+            "plan that return the string output, the output will be passed into the "
+            "LLM context window so avoid returning the whole content!. "
+            "Use ONLY the listed available functions and built-in Python features. "
+            "Leverage the given magic functions to implement function calls for which "
+            "the arguments can't be determined yet. "
+            "Example:`async def main() -> str:\n"
+            "    return await provided_function('arg1', 'arg2').split('\\n')[0]`"
+        ),
+    )
+
+
+FINAL_INSTRUCTION: str = (
+    "You have to give the answer in the from of JSON schema specified previously. "
+    "For the `python_code` field, you have to write Python code to execute your plan "
+    "as efficiently as possible. Your code will be executed directly without any "
+    "editing, if it doesn't work you will be held responsible. "
+    "Use ONLY the listed available functions and built-in Python features. "
+    "Do not make uninformed assumptions "
+    "(e.g. about the content or format of an unknown file). Leverage the given magic "
+    "functions to implement function calls for which the arguments can't be determined "
+    "yet. Reduce the amount of unnecessary data passed into these magic functions "
+    "where possible, because magic costs money and magically processing large amounts "
+    "of data is expensive. If you think are done with the task, you can simply call "
+    "finish(reason='your reason') to end the task, "
+    "a function that has one `finish` command, don't mix finish with other functions! "
+    "If you still need to do other functions, "
+    "let the next cycle execute the `finish` function. "
+    "Avoid hard-coding input values as input, and avoid returning large outputs. "
+    "The code that you have been executing in the past cycles can also be buggy, "
+    "so if you see undesired output, you can always try to re-plan, and re-code. "
+)
+
+
+class CodeFlowAgentPromptStrategy(PromptStrategy):
+    default_configuration: OneShotAgentPromptConfiguration = (
+        OneShotAgentPromptConfiguration()
+    )
+
+    def __init__(
+        self,
+        configuration: SystemConfiguration,
+        logger: Logger,
+    ):
+        self.config = configuration
+        self.response_schema = JSONSchema.from_dict(
+            CodeFlowAgentActionProposal.model_json_schema()
+        )
+        self.logger = logger
+        self.commands: Sequence[Command] = []  # Sequence -> disallow list modification
+
+    @property
+    def llm_classification(self) -> LanguageModelClassification:
+        return LanguageModelClassification.SMART_MODEL  # FIXME: dynamic switching
+
+    def build_prompt(
+        self,
+        *,
+        messages: list[ChatMessage],
+        task: str,
+        ai_profile: AIProfile,
+        ai_directives: AIDirectives,
+        commands: Sequence[Command],
+        **extras,
+    ) -> ChatPrompt:
+        """Constructs and returns a prompt with the following structure:
+        1. System prompt
+        3. `cycle_instruction`
+        """
+        system_prompt, response_prefill = self.build_system_prompt(
+            ai_profile=ai_profile,
+            ai_directives=ai_directives,
+            commands=commands,
+        )
+
+        self.commands = commands
+        final_instruction_msg = ChatMessage.system(FINAL_INSTRUCTION)
+
+        return ChatPrompt(
+            messages=[
+                ChatMessage.system(system_prompt),
+                ChatMessage.user(f'"""{task}"""'),
+                *messages,
+                *(
+                    [final_instruction_msg]
+                    if not any(m.role == "assistant" for m in messages)
+                    else []
+                ),
+            ],
+            prefill_response=response_prefill,
+        )
+
+    def build_system_prompt(
+        self,
+        ai_profile: AIProfile,
+        ai_directives: AIDirectives,
+        commands: Iterable[Command],
+    ) -> tuple[str, str]:
+        """
+        Builds the system prompt.
+
+        Returns:
+            str: The system prompt body
+            str: The desired start for the LLM's response; used to steer the output
+        """
+        response_fmt_instruction, response_prefill = self.response_format_instruction()
+        system_prompt_parts = (
+            self._generate_intro_prompt(ai_profile)
+            + [
+                "## Your Task\n"
+                "The user will specify a task for you to execute, in triple quotes,"
+                " in the next message. Your job is to complete the task, "
+                "and terminate when your task is done."
+            ]
+            + ["## Available Functions\n" + self._generate_function_headers(commands)]
+            + ["## RESPONSE FORMAT\n" + response_fmt_instruction]
+        )
+
+        # Join non-empty parts together into paragraph format
+        return (
+            "\n\n".join(filter(None, system_prompt_parts)).strip("\n"),
+            response_prefill,
+        )
+
+    def response_format_instruction(self) -> tuple[str, str]:
+        response_schema = self.response_schema.model_copy(deep=True)
+        assert response_schema.properties
+
+        # Unindent for performance
+        response_format = re.sub(
+            r"\n\s+",
+            "\n",
+            response_schema.to_typescript_object_interface(_RESPONSE_INTERFACE_NAME),
+        )
+        response_prefill = f'{{\n    "{list(response_schema.properties.keys())[0]}":'
+
+        return (
+            (
+                f"YOU MUST ALWAYS RESPOND WITH A JSON OBJECT OF THE FOLLOWING TYPE:\n"
+                f"{response_format}"
+            ),
+            response_prefill,
+        )
+
+    def _generate_intro_prompt(self, ai_profile: AIProfile) -> list[str]:
+        """Generates the introduction part of the prompt.
+
+        Returns:
+            list[str]: A list of strings forming the introduction part of the prompt.
+        """
+        return [
+            f"You are {ai_profile.ai_name}, {ai_profile.ai_role.rstrip('.')}.",
+            # "Your decisions must always be made independently without seeking "
+            # "user assistance. Play to your strengths as an LLM and pursue "
+            # "simple strategies with no legal complications.",
+        ]
+
+    def _generate_function_headers(self, commands: Iterable[Command]) -> str:
+        function_stubs: list[str] = []
+        annotation_types_in_context: set[type] = set()
+        for f in commands:
+            # Add source code of non-builtin types from function signatures
+            new_annotation_types = extract_annotation_types(f.method).difference(
+                annotation_types_in_context
+            )
+            new_annotation_types_src = [
+                f"# {a.__module__}.{a.__qualname__}\n{inspect.getsource(a)}"
+                for a in new_annotation_types
+            ]
+            annotation_types_in_context.update(new_annotation_types)
+
+            param_descriptions = "\n".join(
+                f"{param.name}: {param.spec.description}"
+                for param in f.parameters
+                if param.spec.description
+            )
+            full_function_stub = (
+                ("\n".join(new_annotation_types_src) + "\n" + f.header).strip()
+                + "\n"
+                + indent(
+                    (
+                        '"""\n'
+                        f"{f.description}\n\n"
+                        f"Params:\n{indent(param_descriptions)}\n"
+                        '"""\n'
+                        "pass"
+                    ),
+                )
+            )
+            function_stubs.append(full_function_stub)
+
+        return "\n\n\n".join(function_stubs)
+
+    async def parse_response_content(
+        self,
+        response: AssistantChatMessage,
+    ) -> OneShotAgentActionProposal:
+        if not response.content:
+            raise InvalidAgentResponseError("Assistant response has no text content")
+
+        self.logger.debug(
+            "LLM response content:"
+            + (
+                f"\n{response.content}"
+                if "\n" in response.content
+                else f" '{response.content}'"
+            )
+        )
+        assistant_reply_dict = extract_dict_from_json(response.content)
+
+        parsed_response = CodeFlowAgentActionProposal.model_validate(
+            assistant_reply_dict
+        )
+        if not parsed_response.python_code:
+            raise ValueError("python_code is empty")
+
+        available_functions = {
+            c.name: FunctionDef(
+                name=c.name,
+                arg_types=[(p.name, p.spec.python_type) for p in c.parameters],
+                arg_descs={p.name: p.spec.description for p in c.parameters},
+                arg_defaults={
+                    p.name: p.spec.default or "None"
+                    for p in c.parameters
+                    if p.spec.default or not p.spec.required
+                },
+                return_type=c.return_type,
+                return_desc="Output of the function",
+                function_desc=c.description,
+                is_async=c.is_async,
+            )
+            for c in self.commands
+        }
+        available_functions.update(
+            {
+                "main": FunctionDef(
+                    name="main",
+                    arg_types=[],
+                    arg_descs={},
+                    return_type="str",
+                    return_desc="Output of the function",
+                    function_desc="The main function to execute the plan",
+                    is_async=True,
+                )
+            }
+        )
+        code_validation = await CodeValidator(
+            function_name="main",
+            available_functions=available_functions,
+        ).validate_code(parsed_response.python_code)
+
+        clean_response = response.model_copy()
+        clean_response.content = parsed_response.model_dump_json(indent=4)
+
+        # TODO: prevent combining finish with other functions
+        if _finish_call := re.search(
+            r"finish\((reason=)?(.*?)\)", code_validation.functionCode
+        ):
+            finish_reason = _finish_call.group(2)[1:-1]  # remove quotes
+            result = OneShotAgentActionProposal(
+                thoughts=parsed_response.thoughts,
+                use_tool=AssistantFunctionCall(
+                    name="finish",
+                    arguments={"reason": finish_reason},
+                ),
+                raw_message=clean_response,
+            )
+        else:
+            result = OneShotAgentActionProposal(
+                thoughts=parsed_response.thoughts,
+                use_tool=AssistantFunctionCall(
+                    name=CodeFlowExecutionComponent.execute_code_flow.name,
+                    arguments={
+                        "python_code": code_validation.functionCode,
+                        "plan_text": parsed_response.immediate_plan,
+                    },
+                ),
+                raw_message=clean_response,
+            )
+        return result
+
+
+def extract_annotation_types(func: Callable) -> set[type]:
+    annotation_types = set()
+    for annotation in inspect.get_annotations(func).values():
+        annotation_types.update(_get_nested_types(annotation))
+    return annotation_types
+
+
+def _get_nested_types(annotation: type) -> Iterable[type]:
+    if _args := get_args(annotation):
+        for a in _args:
+            yield from _get_nested_types(a)
+    if not _is_builtin_type(_a := get_origin(annotation) or annotation):
+        yield _a
+
+
+def _is_builtin_type(_type: type):
+    """Check if a given type is a built-in type."""
+    import sys
+
+    return _type.__module__ in sys.stdlib_module_names

autogpt/autogpt/agents/prompt_strategies/one_shot.py

@@ -6,6 +6,7 @@ import re
 from logging import Logger
 
 import distro
+from forge.command import Command
 from forge.config.ai_directives import AIDirectives
 from forge.config.ai_profile import AIProfile
 from forge.json.parsing import extract_dict_from_json
@@ -16,6 +17,7 @@ from forge.llm.providers.schema import (
     ChatMessage,
     CompletionModelFunction,
 )
+from forge.llm.providers.utils import function_specs_from_commands
 from forge.models.action import ActionProposal
 from forge.models.config import SystemConfiguration, UserConfigurable
 from forge.models.json_schema import JSONSchema
@@ -27,13 +29,21 @@ _RESPONSE_INTERFACE_NAME = "AssistantResponse"
 
 
 class AssistantThoughts(ModelWithSummary):
+    past_action_summary: str = Field(
+        ...,
+        description="Summary of the last action you took, if there is none, "
+        "you can leave it empty",
+    )
     observations: str = Field(
-        description="Relevant observations from your last action (if any)"
+        description="Relevant observations from your last actions (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")
+    plan: list[str] = Field(
+        description="Short list that conveys the long-term plan, "
+        "considering the progress on your task so far",
+    )
     speak: str = Field(description="Summary of thoughts, to say to user")
 
     def summary(self) -> str:
@@ -101,7 +111,7 @@ class OneShotAgentPromptStrategy(PromptStrategy):
 
     @property
     def llm_classification(self) -> LanguageModelClassification:
-        return LanguageModelClassification.FAST_MODEL  # FIXME: dynamic switching
+        return LanguageModelClassification.SMART_MODEL  # FIXME: dynamic switching
 
     def build_prompt(
         self,
@@ -110,7 +120,7 @@ class OneShotAgentPromptStrategy(PromptStrategy):
         task: str,
         ai_profile: AIProfile,
         ai_directives: AIDirectives,
-        commands: list[CompletionModelFunction],
+        commands: list[Command],
         include_os_info: bool,
         **extras,
     ) -> ChatPrompt:
@@ -118,10 +128,11 @@ class OneShotAgentPromptStrategy(PromptStrategy):
         1. System prompt
         3. `cycle_instruction`
         """
+        functions = function_specs_from_commands(commands)
         system_prompt, response_prefill = self.build_system_prompt(
             ai_profile=ai_profile,
             ai_directives=ai_directives,
-            commands=commands,
+            functions=functions,
             include_os_info=include_os_info,
         )
 
@@ -135,14 +146,14 @@ class OneShotAgentPromptStrategy(PromptStrategy):
                 final_instruction_msg,
             ],
             prefill_response=response_prefill,
-            functions=commands if self.config.use_functions_api else [],
+            functions=functions if self.config.use_functions_api else [],
         )
 
     def build_system_prompt(
         self,
         ai_profile: AIProfile,
         ai_directives: AIDirectives,
-        commands: list[CompletionModelFunction],
+        functions: list[CompletionModelFunction],
         include_os_info: bool,
     ) -> tuple[str, str]:
         """
@@ -162,7 +173,7 @@ class OneShotAgentPromptStrategy(PromptStrategy):
                 self.config.body_template.format(
                     constraints=format_numbered_list(ai_directives.constraints),
                     resources=format_numbered_list(ai_directives.resources),
-                    commands=self._generate_commands_list(commands),
+                    commands=self._generate_commands_list(functions),
                     best_practices=format_numbered_list(ai_directives.best_practices),
                 )
             ]

autogpt/autogpt/app/agent_protocol_server.py

@@ -23,6 +23,7 @@ from forge.agent_protocol.models import (
     TaskRequestBody,
     TaskStepsListResponse,
 )
+from forge.components.code_flow_executor import CodeFlowExecutionComponent
 from forge.file_storage import FileStorage
 from forge.llm.providers import ModelProviderBudget, MultiProvider
 from forge.models.action import ActionErrorResult, ActionSuccessResult
@@ -97,9 +98,7 @@ class AgentProtocolServer:
         app.include_router(router, prefix="/ap/v1")
         script_dir = os.path.dirname(os.path.realpath(__file__))
         frontend_path = (
-            pathlib.Path(script_dir)
-            .joinpath("../../../classic/frontend/build/web")
-            .resolve()
+            pathlib.Path(script_dir).joinpath("../../../frontend/build/web").resolve()
         )
 
         if os.path.exists(frontend_path):
@@ -300,11 +299,16 @@ class AgentProtocolServer:
             else ""
         )
         output += f"{assistant_response.thoughts.speak}\n\n"
-        output += (
-            f"Next Command: {next_tool_to_use}"
-            if next_tool_to_use.name != ASK_COMMAND
-            else next_tool_to_use.arguments["question"]
-        )
+        if next_tool_to_use.name == CodeFlowExecutionComponent.execute_code_flow.name:
+            code = next_tool_to_use.arguments["python_code"]
+            plan = next_tool_to_use.arguments["plan_text"]
+            output += f"Code for next step:\n```py\n# {plan}\n\n{code}\n```"
+        else:
+            output += (
+                f"Next Command: {next_tool_to_use}"
+                if next_tool_to_use.name != ASK_COMMAND
+                else next_tool_to_use.arguments["question"]
+            )
 
         additional_output = {
             **(

autogpt/autogpt/app/config.py

@@ -148,7 +148,7 @@ async def assert_config_has_required_llm_api_keys(config: AppConfig) -> None:
                 )
                 logger.info(
                     "For further instructions: "
-                    "https://docs.agpt.co/classic/original_autogpt/setup/#anthropic"
+                    "https://docs.agpt.co/autogpt/setup/#anthropic"
                 )
 
             raise ValueError("Anthropic is unavailable: can't load credentials") from e
@@ -176,15 +176,14 @@ async def assert_config_has_required_llm_api_keys(config: AppConfig) -> None:
 
             logger.error("Set your Groq API key in .env or as an environment variable")
             logger.info(
-                "For further instructions: "
-                + "https://docs.agpt.co/classic/original_autogpt/setup/#groq"
+                "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/classic/original_autogpt/setup/#groq"
+                "https://docs.agpt.co/autogpt/setup/#groq"
             )
             raise ValueError("Groq is unavailable: invalid API key") from e
 
@@ -203,15 +202,14 @@ async def assert_config_has_required_llm_api_keys(config: AppConfig) -> None:
                 "Set your OpenAI API key in .env or as an environment variable"
             )
             logger.info(
-                "For further instructions: "
-                + "https://docs.agpt.co/classic/original_autogpt/setup/#openai"
+                "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/classic/original_autogpt/setup/#openai"
+                "https://docs.agpt.co/autogpt/setup/#openai"
             )
             raise ValueError("OpenAI is unavailable: invalid API key") from e
 

autogpt/autogpt/app/main.py

@@ -630,6 +630,9 @@ def update_user(
         command_args: The arguments for the command.
         assistant_reply_dict: The assistant's reply.
     """
+    from forge.components.code_flow_executor import CodeFlowExecutionComponent
+    from forge.llm.prompting.utils import indent
+
     logger = logging.getLogger(__name__)
 
     print_assistant_thoughts(
@@ -644,15 +647,29 @@ def update_user(
     # First log new-line so user can differentiate sections better in console
     print()
     safe_tool_name = remove_ansi_escape(action_proposal.use_tool.name)
-    logger.info(
-        f"COMMAND = {Fore.CYAN}{safe_tool_name}{Style.RESET_ALL}  "
-        f"ARGUMENTS = {Fore.CYAN}{action_proposal.use_tool.arguments}{Style.RESET_ALL}",
-        extra={
-            "title": "NEXT ACTION:",
-            "title_color": Fore.CYAN,
-            "preserve_color": True,
-        },
-    )
+    if safe_tool_name == CodeFlowExecutionComponent.execute_code_flow.name:
+        plan = action_proposal.use_tool.arguments["plan_text"]
+        code = action_proposal.use_tool.arguments["python_code"]
+        logger.info(
+            f"\n{indent(code, f'{Fore.GREEN}>>> {Fore.RESET}')}\n",
+            extra={
+                "title": "PROPOSED ACTION:",
+                "title_color": Fore.GREEN,
+                "preserve_color": True,
+            },
+        )
+        logger.debug(
+            f"{plan}\n", extra={"title": "EXPLANATION:", "title_color": Fore.YELLOW}
+        )
+    else:
+        logger.info(
+            str(action_proposal.use_tool),
+            extra={
+                "title": "PROPOSED ACTION:",
+                "title_color": Fore.GREEN,
+                "preserve_color": True,
+            },
+        )
 
 
 async def get_user_feedback(
@@ -732,6 +749,12 @@ def print_assistant_thoughts(
     )
 
     if isinstance(thoughts, AssistantThoughts):
+        if thoughts.observations:
+            print_attribute(
+                "OBSERVATIONS",
+                remove_ansi_escape(thoughts.observations),
+                title_color=Fore.YELLOW,
+            )
         print_attribute(
             "REASONING", remove_ansi_escape(thoughts.reasoning), title_color=Fore.YELLOW
         )
@@ -753,7 +776,7 @@ def print_assistant_thoughts(
                     line.strip(), extra={"title": "- ", "title_color": Fore.GREEN}
                 )
         print_attribute(
-            "CRITICISM",
+            "SELF-CRITICISM",
             remove_ansi_escape(thoughts.self_criticism),
             title_color=Fore.YELLOW,
         )
@@ -764,7 +787,7 @@ def print_assistant_thoughts(
                 speak(assistant_thoughts_speak)
             else:
                 print_attribute(
-                    "SPEAK", assistant_thoughts_speak, title_color=Fore.YELLOW
+                    "TL;DR", assistant_thoughts_speak, title_color=Fore.YELLOW
                 )
     else:
         speak(thoughts_text)

autogpt/autogpt/app/utils.py

@@ -22,7 +22,7 @@ logger = logging.getLogger(__name__)
 def get_bulletin_from_web():
     try:
         response = requests.get(
-            "https://raw.githubusercontent.com/Significant-Gravitas/AutoGPT/master/classic/original_autogpt/BULLETIN.md"  # noqa: E501
+            "https://raw.githubusercontent.com/Significant-Gravitas/AutoGPT/master/autogpt/BULLETIN.md"  # noqa: E501
         )
         if response.status_code == 200:
             return response.text
@@ -45,7 +45,7 @@ def vcs_state_diverges_from_master() -> bool:
     """
     Returns whether a git repo is present and contains changes that are not in `master`.
     """
-    paths_we_care_about = "classic/original_autogpt/classic/original_autogpt/**/*.py"
+    paths_we_care_about = "autogpt/autogpt/**/*.py"
     try:
         repo = Repo(search_parent_directories=True)
 

autogpt/docker-compose.yml

@@ -14,7 +14,7 @@ services:
     ports:
       - "8000:8000"
     volumes:
-      - ./:/app/classic/original_autogpt/
+      - ./:/app/autogpt/
       - ./docker-compose.yml:/app/docker-compose.yml:ro
       # - ./Dockerfile:/app/Dockerfile:ro
     profiles: ["exclude-from-up"]
@@ -33,8 +33,8 @@ services:
     entrypoint: ["poetry", "run"]
     command: ["pytest", "-v"]
     volumes:
-      - ./autogpt:/app/classic/original_autogpt/autogpt
-      - ./tests:/app/classic/original_autogpt/tests
+      - ./autogpt:/app/autogpt/autogpt
+      - ./tests:/app/autogpt/tests
     depends_on:
       - minio
     profiles: ["exclude-from-up"]

autogpt/poetry.lock

@@ -348,10 +348,10 @@ tiktoken = ">=0.7.0,<1.0.0"
 toml = "^0.10.2"
 uvicorn = {version = ">=0.23.2,<1", extras = ["standard"]}
 watchdog = "4.0.0"
-webdriver-manager = "^4.0.2"
+webdriver-manager = "^4.0.1"
 
 [package.extras]
-benchmark = ["agbenchmark @ file:///home/reinier/code/agpt/AutoGPT/classic/benchmark"]
+benchmark = ["agbenchmark @ file:///Users/czerwinski/Projects/AutoGPT/benchmark"]
 
 [package.source]
 type = "directory"
@@ -4216,7 +4216,7 @@ test = ["enum34", "ipaddress", "mock", "pywin32", "wmi"]
 name = "ptyprocess"
 version = "0.7.0"
 description = "Run a subprocess in a pseudo terminal"
-optional = true
+optional = false
 python-versions = "*"
 files = [
     {file = "ptyprocess-0.7.0-py2.py3-none-any.whl", hash = "sha256:4b41f3967fce3af57cc7e94b888626c18bf37a083e3651ca8feeb66d492fef35"},
@@ -5212,6 +5212,32 @@ files = [
 [package.dependencies]
 pyasn1 = ">=0.1.3"
 
+[[package]]
+name = "ruff"
+version = "0.4.4"
+description = "An extremely fast Python linter and code formatter, written in Rust."
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "ruff-0.4.4-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:29d44ef5bb6a08e235c8249294fa8d431adc1426bfda99ed493119e6f9ea1bf6"},
+    {file = "ruff-0.4.4-py3-none-macosx_11_0_arm64.whl", hash = "sha256:c4efe62b5bbb24178c950732ddd40712b878a9b96b1d02b0ff0b08a090cbd891"},
+    {file = "ruff-0.4.4-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4c8e2f1e8fc12d07ab521a9005d68a969e167b589cbcaee354cb61e9d9de9c15"},
+    {file = "ruff-0.4.4-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:60ed88b636a463214905c002fa3eaab19795679ed55529f91e488db3fe8976ab"},
+    {file = "ruff-0.4.4-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b90fc5e170fc71c712cc4d9ab0e24ea505c6a9e4ebf346787a67e691dfb72e85"},
+    {file = "ruff-0.4.4-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:8e7e6ebc10ef16dcdc77fd5557ee60647512b400e4a60bdc4849468f076f6eef"},
+    {file = "ruff-0.4.4-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:b9ddb2c494fb79fc208cd15ffe08f32b7682519e067413dbaf5f4b01a6087bcd"},
+    {file = "ruff-0.4.4-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:c51c928a14f9f0a871082603e25a1588059b7e08a920f2f9fa7157b5bf08cfe9"},
+    {file = "ruff-0.4.4-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b5eb0a4bfd6400b7d07c09a7725e1a98c3b838be557fee229ac0f84d9aa49c36"},
+    {file = "ruff-0.4.4-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:b1867ee9bf3acc21778dcb293db504692eda5f7a11a6e6cc40890182a9f9e595"},
+    {file = "ruff-0.4.4-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:1aecced1269481ef2894cc495647392a34b0bf3e28ff53ed95a385b13aa45768"},
+    {file = "ruff-0.4.4-py3-none-musllinux_1_2_i686.whl", hash = "sha256:9da73eb616b3241a307b837f32756dc20a0b07e2bcb694fec73699c93d04a69e"},
+    {file = "ruff-0.4.4-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:958b4ea5589706a81065e2a776237de2ecc3e763342e5cc8e02a4a4d8a5e6f95"},
+    {file = "ruff-0.4.4-py3-none-win32.whl", hash = "sha256:cb53473849f011bca6e754f2cdf47cafc9c4f4ff4570003a0dad0b9b6890e876"},
+    {file = "ruff-0.4.4-py3-none-win_amd64.whl", hash = "sha256:424e5b72597482543b684c11def82669cc6b395aa8cc69acc1858b5ef3e5daae"},
+    {file = "ruff-0.4.4-py3-none-win_arm64.whl", hash = "sha256:39df0537b47d3b597293edbb95baf54ff5b49589eb7ff41926d8243caa995ea6"},
+    {file = "ruff-0.4.4.tar.gz", hash = "sha256:f87ea42d5cdebdc6a69761a9d0bc83ae9b3b30d0ad78952005ba6568d6c022af"},
+]
+
 [[package]]
 name = "s3transfer"
 version = "0.10.0"
@@ -6416,13 +6442,13 @@ wasabi = ">=0.9.1,<1.2.0"
 
 [[package]]
 name = "webdriver-manager"
-version = "4.0.2"
+version = "4.0.1"
 description = "Library provides the way to automatically manage drivers for different browsers"
 optional = false
 python-versions = ">=3.7"
 files = [
-    {file = "webdriver_manager-4.0.2-py2.py3-none-any.whl", hash = "sha256:75908d92ecc45ff2b9953614459c633db8f9aa1ff30181cefe8696e312908129"},
-    {file = "webdriver_manager-4.0.2.tar.gz", hash = "sha256:efedf428f92fd6d5c924a0d054e6d1322dd77aab790e834ee767af392b35590f"},
+    {file = "webdriver_manager-4.0.1-py2.py3-none-any.whl", hash = "sha256:d7970052295bb9cda2c1a24cf0b872dd2c41ababcc78f7b6b8dc37a41e979a7e"},
+    {file = "webdriver_manager-4.0.1.tar.gz", hash = "sha256:25ec177c6a2ce9c02fb8046f1b2732701a9418d6a977967bb065d840a3175d87"},
 ]
 
 [package.dependencies]
@@ -6758,4 +6784,4 @@ benchmark = ["agbenchmark"]
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.10"
-content-hash = "b3d4efee5861b32152024dada1ec61f4241122419cb538012c00a6ed55ac8a4b"
+content-hash = "c729e10fd5ac85400d2499397974d1b1831fed3b591657a2fea9e86501b96e19"

autogpt/pyproject.toml

@@ -30,9 +30,12 @@ gitpython = "^3.1.32"
 hypercorn = "^0.14.4"
 openai = "^1.7.2"
 orjson = "^3.8.10"
+ptyprocess = "^0.7.0"
 pydantic = "^2.7.2"
+pyright = "^1.1.364"
 python-dotenv = "^1.0.0"
 requests = "*"
+ruff = "^0.4.4"
 sentry-sdk = "^1.40.4"
 
 # Benchmarking
@@ -47,7 +50,6 @@ black = "^23.12.1"
 flake8 = "^7.0.0"
 isort = "^5.13.1"
 pre-commit = "*"
-pyright = "^1.1.364"
 
 # Type stubs
 types-colorama = "*"
@@ -88,4 +90,4 @@ skip_glob = ["data"]
 [tool.pyright]
 pythonVersion = "3.10"
 exclude = ["data/**", "**/node_modules", "**/__pycache__", "**/.*"]
-ignore = ["../classic/forge/**"]
+ignore = ["../forge/**"]

autogpt/scripts/git_log_to_release_notes.py

@@ -55,7 +55,7 @@ async def generate_release_notes(repo_path: Optional[str | Path] = None):
 
     git_log = repo.git.log(
         f"{last_release_tag.name}...{new_release_ref}",
-        "classic/original_autogpt/",
+        "autogpt/",
         no_merges=True,
         follow=True,
     )
@@ -81,7 +81,7 @@ EXAMPLE_RELEASE_NOTES = """
 First some important notes w.r.t. using the application:
 * `run.sh` has been renamed to `autogpt.sh`
 * The project has been restructured. The AutoGPT Agent is now located in `autogpt`.
-* The application no longer uses a single workspace for all tasks. Instead, every task that you run the agent on creates a new workspace folder. See the [usage guide](https://docs.agpt.co/classic/original_autogpt/usage/#workspace) for more information.
+* The application no longer uses a single workspace for all tasks. Instead, every task that you run the agent on creates a new workspace folder. See the [usage guide](https://docs.agpt.co/autogpt/usage/#workspace) for more information.
 
 ## New features ✨
 
@@ -94,7 +94,7 @@ First some important notes w.r.t. using the application:
 * **Resuming agents 🔄️**
   In TTY mode, the application will now save the agent's state when quitting, and allows resuming where you left off at a later time!
 * **GCS and S3 workspace backends 📦**
-  To further support running the application as part of a larger system, Google Cloud Storage and S3 workspace backends were added. Configuration options for this can be found in [`.env.template`](/classic/original_autogpt/.env.template).
+  To further support running the application as part of a larger system, Google Cloud Storage and S3 workspace backends were added. Configuration options for this can be found in [`.env.template`](/autogpt/.env.template).
 * **Documentation Rewrite 📖**
   The [documentation](https://docs.agpt.co) has been restructured and mostly rewritten to clarify and simplify the instructions, and also to accommodate the other subprojects that are now in the repo.
 * **New Project CLI 🔧**

autogpt/scripts/llamafile/serve.py

@@ -80,7 +80,7 @@ def main(
         ):
             return
 
-    # Go to classic/original_autogpt/scripts/llamafile/
+    # Go to autogpt/scripts/llamafile/
     os.chdir(Path(__file__).resolve().parent)
 
     on_windows = platform.system() == "Windows"

autogpt/setup.py

@@ -59,10 +59,7 @@ txt_to_rtf("../LICENSE", license_file)
 setup(
     executables=[
         Executable(
-            "classic/original_autogpt/__main__.py",
-            target_name="autogpt",
-            base="console",
-            icon=icon,
+            "autogpt/__main__.py", target_name="autogpt", base="console", icon=icon
         ),
     ],
     options={