Auto gpt cassettes

.github/workflows/add-cassettes.yml

@@ -0,0 +1,26 @@
+name: Merge and Commit Cassettes
+
+on:
+  pull_request_target:
+    types:
+      - closed
+
+jobs:
+  update-cassettes:
+    if: github.event.pull_request.merged == true
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0  # This is necessary to fetch all branches and tags
+
+      - name: Download diff artifact
+        uses: dawidd6/action-download-artifact@v2
+        with:
+          github_token: ${{secrets.GITHUB_TOKEN}}
+          workflow: Python CI
+          name: cassette-diff
+          path: .
+          pr: ${{ github.event.pull_request.number }}

.github/workflows/ci.yml

@@ -3,12 +3,12 @@ name: Python CI
 on:
   push:
     branches: [ master ]
-  pull_request:
+  pull_request_target:
     branches: [ master, stable ]
 
 concurrency:
   group: ${{ format('ci-{0}', github.head_ref && format('pr-{0}', github.event.pull_request.number) || github.sha) }}
-  cancel-in-progress: ${{ github.event_name == 'pull_request' }}
+  cancel-in-progress: ${{ github.event_name == 'pull_request_target' }}
 
 jobs:
   lint:
@@ -43,12 +43,7 @@ jobs:
 
   test:
     permissions:
-      # Gives the action the necessary permissions for publishing new
-      # comments in pull requests.
       pull-requests: write
-      # Gives the action the necessary permissions for pushing data to the
-      # python-coverage-comment-action branch, and for editing existing
-      # comments (to avoid publishing multiple comments in the same PR)
       contents: write
     runs-on: ubuntu-latest
     strategy:
@@ -58,6 +53,8 @@ jobs:
     steps:
       - name: Check out repository
         uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
 
       - name: Set up Python ${{ matrix.python-version }}
         uses: actions/setup-python@v2
@@ -71,9 +68,26 @@ jobs:
 
       - name: Run unittest tests with coverage
         run: |
-          pytest --cov=autogpt --cov-report term-missing --cov-branch --cov-report xml --cov-report term
+          pytest -s tests/integration/goal_oriented/test_write_file.py
         env:
           CI: true
+          PROXY: https://us-central1-prod-benchmarks-core.cloudfunctions.net/proxy_function
+
+      - name: Stage new files
+        run: |
+          git add .
+
+      - name: Create diff and save to file
+        run: |
+          git diff --cached > cassette-diff-${{ github.run_number }}-${{ github.sha }}.txt || echo "No diff to create"
+
+      - name: Create new branch and commit changes
+        run: |
+          git checkout -b Auto-GPT-cassettes || git checkout Auto-GPT-cassettes
+          git config user.email "github-actions@github.com"
+          git config user.name "GitHub Actions"
+          git add cassette-diff-${{ github.run_number }}-${{ github.sha }}.txt
+          git commit -m "Add cassette diff"
+          git push origin Auto-GPT-cassettes
+
 
-      - name: Upload coverage reports to Codecov
-        uses: codecov/codecov-action@v3

.github/workflows/docker-release.yml

@@ -79,3 +79,5 @@ jobs:
 
       run: .github/workflows/scripts/docker-release-summary.sh >> $GITHUB_STEP_SUMMARY
       continue-on-error: true
+# rand
+# rand

autogpt/prompts/prompt.py

@@ -10,9 +10,7 @@
 
 CFG = Config()
 
-DEFAULT_TRIGGERING_PROMPT = (
-    "Determine which next command to use, and respond using the format specified above:"
-)
+DEFAULT_TRIGGERING_PROMPT = "Determindfsdfse which next command to use, and respond using the format specified above:"
 
 
 def build_default_prompt_generator() -> PromptGenerator:

cassette-diff-353-f75fcc72ce20b5cacc240db20e6d35c07c1724bf.txt

@@ -0,0 +1,116 @@
+diff --git a/tests/integration/goal_oriented/cassettes/test_write_file/test_write_file.yaml b/tests/integration/goal_oriented/cassettes/test_write_file/test_write_file.yaml
+index ef390a5..2bde595 100644
+--- a/tests/integration/goal_oriented/cassettes/test_write_file/test_write_file.yaml
++++ b/tests/integration/goal_oriented/cassettes/test_write_file/test_write_file.yaml
+@@ -690,4 +690,111 @@ interactions:
+     status:
+       code: 200
+       message: OK
++- request:
++    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
++      are write_to_file-GPT, an AI designed to use the write_to_file command to write
++      ''Hello World'' into a file named \"hello_world.txt\" and then use the task_complete
++      command to complete the task.\nYour 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.\n\nGOALS:\n\n1. Use the write_to_file
++      command to write ''Hello World'' into a file named \"hello_world.txt\".\n2.
++      Use the task_complete command to complete the task.\n3. Do not use andfsfdsy
++      other commands.\n\n\nConstraints:\n1. ~4000 word limit for short term memory.
++      Your short term memory is short, so immediately save important information to
++      files.\n2. If you are unsure how you previously did something or want to recall
++      past events, thinking about similar events will help you remember.\n3. No user
++      assistance\n4. Exclusively use the commands listed in double quotes e.g. \"command
++      name\"\n\nCommands:\n1. append_to_file: Append to file, args: \"filename\":
++      \"<filename>\", \"text\": \"<text>\"\n2. delete_file: Delete file, args: \"filename\":
++      \"<filename>\"\n3. list_files: List Files in Directory, args: \"directory\":
++      \"<directory>\"\n4. read_file: Read file, args: \"filename\": \"<filename>\"\n5.
++      write_to_file: Write to file, args: \"filename\": \"<filename>\", \"text\":
++      \"<text>\"\n6. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7.
++      get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8. get_text_summary:
++      Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n9.
++      list_agents: List GPT Agents, args: () -> str\n10. message_agent: Message GPT
++      Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11. start_agent:
++      Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
++      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
++      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
++      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
++      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
++      Continuously review and analyze your actions to ensure you are performing to
++      the best of your abilities.\n2. Constructively self-criticize your big-picture
++      behavior constantly.\n3. Reflect on past decisions and strategies to refine
++      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
++      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
++      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
++      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
++      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
++      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
++      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
++      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
++      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
++      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
++      reminds you of these events from your past: \nI was created and nothing new
++      has happened."}, {"role": "user", "content": "Determine which next command to
++      use, and respond using the format specified above:"}, {"role": "assistant",
++      "content": "{\n    \"thoughts\": {\n        \"text\": \"I need to use the write_to_file
++      command to write ''Hello World'' into a file named ''hello_world.txt''.\",\n        \"reasoning\":
++      \"The task requires me to write ''Hello World'' into a file named ''hello_world.txt'',
++      and the write_to_file command is the appropriate command for this task.\",\n        \"plan\":
++      \"- Use the write_to_file command to write ''Hello World'' into a file named
++      ''hello_world.txt''.\",\n        \"criticism\": \"I need to ensure that I use
++      the correct file name and text to write to the file.\",\n        \"speak\":
++      \"I will use the write_to_file command to write ''Hello World'' into a file
++      named ''hello_world.txt''.\"\n    },\n    \"command\": {\n        \"name\":
++      \"write_to_file\",\n        \"args\": {\n            \"filename\": \"hello_world.txt\",\n            \"text\":
++      \"Hello World\"\n        }\n    }\n}"}, {"role": "system", "content": "Command
++      write_to_file returned: File written to successfully."}, {"role": "user", "content":
++      "Determine which next command to use, and respond using the format specified
++      above:"}], "temperature": 0, "max_tokens": 0}'
++    headers:
++      Accept:
++      - '*/*'
++      Accept-Encoding:
++      - gzip, deflate
++      Connection:
++      - keep-alive
++      Content-Length:
++      - '4660'
++      Content-Type:
++      - application/json
++    method: POST
++    uri: https://api.openai.com/v1/chat/completions
++  response:
++    body:
++      string: '{"id":"chatcmpl-7FMsZlCgaqEI6ebydODAT47LprpFA","object":"chat.completion","created":1683897223,"model":"gpt-3.5-turbo-0301","usage":{"prompt_tokens":1031,"completion_tokens":201,"total_tokens":1232},"choices":[{"message":{"role":"assistant","content":"{\n    \"thoughts\":
++        {\n        \"text\": \"I have successfully written ''Hello World'' into a
++        file named ''hello_world.txt''. The next step is to use the task_complete
++        command to complete the task.\",\n        \"reasoning\": \"The task requires
++        me to write ''Hello World'' into a file named ''hello_world.txt'' and then
++        complete the task. Since I have successfully written to the file, the next
++        step is to use the task_complete command to complete the task.\",\n        \"plan\":
++        \"- Use the task_complete command to complete the task.\",\n        \"criticism\":
++        \"I need to ensure that I provide a valid reason for completing the task.\",\n        \"speak\":
++        \"I will use the task_complete command to complete the task.\"\n    },\n    \"command\":
++        {\n        \"name\": \"task_complete\",\n        \"args\": {\n            \"reason\":
++        \"I have successfully written ''Hello World'' into a file named ''hello_world.txt''.\"\n        }\n    }\n}"},"finish_reason":"stop","index":0}]}'
++    headers:
++      Alt-Svc:
++      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
++      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
++      Content-Length:
++      - '1221'
++      Content-Type:
++      - application/json
++      Date:
++      - Fri, 12 May 2023 13:14:02 GMT
++      Function-Execution-Id:
++      - ea42yneiu06g
++      Server:
++      - Google Frontend
++      X-Cloud-Trace-Context:
++      - 78cd3f6b10f6ed7cdd88e530a2abe3ee;o=1
++      X-Powered-By:
++      - Express
++    status:
++      code: 200
++      message: OK
+ version: 1

tests/conftest.py

@@ -1,3 +1,4 @@
+import os
 from pathlib import Path
 
 import pytest
@@ -9,6 +10,8 @@
 
 pytest_plugins = ["tests.integration.agent_factory"]
 
+PROXY = os.environ.get("PROXY")
+
 
 @pytest.fixture()
 def workspace_root(tmp_path: Path) -> Path:

tests/integration/agent_factory.py

@@ -89,7 +89,7 @@ def writer_agent(agent_test_config, memory_none: NoMemory, workspace: Workspace)
         ai_goals=[
             "Use the write_to_file command to write 'Hello World' into a file named \"hello_world.txt\".",
             "Use the task_complete command to complete the task.",
-            "Do not use any other commands.",
+            "Do not use andfsfdsy other commands.",
         ],
     )
     ai_config.command_registry = command_registry

tests/integration/challenges/information_retrieval/test_information_retrieval_challenge_a.py

@@ -26,7 +26,7 @@ def input_generator(input_sequence: list) -> Generator[str, None, None]:
 @requires_api_key("OPENAI_API_KEY")
 @run_multiple_times(3)
 def test_information_retrieval_challenge_a(
-    get_company_revenue_agent, monkeypatch
+    get_company_revenue_agent, monkeypatch, patched_api_requestor
 ) -> None:
     """
     Test the challenge_a function in a given agent by mocking user inputs and checking the output file content.

tests/integration/challenges/memory/test_memory_challenge_a.py

@@ -13,7 +13,7 @@
 @pytest.mark.vcr
 @requires_api_key("OPENAI_API_KEY")
 def test_memory_challenge_a(
-    memory_management_agent: Agent, user_selected_level: int
+    memory_management_agent: Agent, user_selected_level: int, patched_api_requestor
 ) -> None:
     """
     The agent reads a file containing a task_id. Then, it reads a series of other files.

tests/integration/challenges/memory/test_memory_challenge_b.py

@@ -14,7 +14,7 @@
 @pytest.mark.vcr
 @requires_api_key("OPENAI_API_KEY")
 def test_memory_challenge_b(
-    memory_management_agent: Agent, user_selected_level: int
+    memory_management_agent: Agent, user_selected_level: int, patched_api_requestor
 ) -> None:
     """
     The agent reads a series of files, each containing a task_id and noise. After reading 'n' files,

tests/integration/challenges/memory/test_memory_challenge_c.py

@@ -14,7 +14,7 @@
 @pytest.mark.vcr
 @requires_api_key("OPENAI_API_KEY")
 def test_memory_challenge_c(
-    memory_management_agent: Agent, user_selected_level: int
+    memory_management_agent: Agent, user_selected_level: int, patched_api_requestor
 ) -> None:
     """
     Instead of reading task Ids from files as with the previous challenges, the agent now must remember

tests/integration/conftest.py

@@ -1,7 +1,9 @@
 import os
 
+import openai
 import pytest
 
+from tests.conftest import PROXY
 from tests.vcr.vcr_filter import before_record_request, before_record_response
 
 
@@ -17,5 +19,25 @@ def vcr_config():
             "X-OpenAI-Client-User-Agent",
             "User-Agent",
         ],
-        "match_on": ["method", "uri", "body"],
+        "match_on": ["method", "body"],
     }
+
+
+def patch_api_base(requestor):
+    new_api_base = f"{PROXY}/v1"
+    requestor.api_base = new_api_base
+    return requestor
+
+
+@pytest.fixture
+def patched_api_requestor(mocker):
+    original_init = openai.api_requestor.APIRequestor.__init__
+
+    def patched_init(requestor, *args, **kwargs):
+        original_init(requestor, *args, **kwargs)
+        patch_api_base(requestor)
+
+    if PROXY:
+        mocker.patch("openai.api_requestor.APIRequestor.__init__", new=patched_init)
+
+    return mocker