cirolini / genai-code-review Goto Github PK

Hi everyone!

I am trying to use it with a private repo . but it seems doesn't work,
is there any configuration that could help to have this working with private repos?

if not, is there any plan to add support for a private repo?

thanks

🚀 Resumo da funcionalidade solicitada:
Olá @cirolini, tomei a liberdade de abrir essa issue com um template que costumo usar para requisições de features. Primeiramente, parabéns pela iniciativa em criar essa action. Ao tentar utilizar a action pela primeira vez em meu repositório, me deparei com uma limitação de caracteres enviados ao ChatGPT para análise e revisão.

Traceback:

Traceback (most recent call last):
  File "/main.py", line 36, in <module>
    response = openai.Completion.create(
  File "/usr/local/lib/python3.[8](https://github.com/ThiagoPanini/terraglue/actions/runs/4038680923/jobs/6942850497#step:3:9)/site-packages/openai/api_resources/completion.py", line 25, in create
    return super().create(*args, **kwargs)
  File "/usr/local/lib/python3.8/site-packages/openai/api_resources/abstract/engine_api_resource.py", line 153, in create
    response, _, api_key = requestor.request(
  File "/usr/local/lib/python3.8/site-packages/openai/api_requestor.py", line 227, in request
    resp, got_stream = self._interpret_response(result, stream)
  File "/usr/local/lib/python3.8/site-packages/openai/api_requestor.py", line 620, in _interpret_response
    self._interpret_response_line(
  File "/usr/local/lib/python3.8/site-packages/openai/api_requestor.py", line 680, in _interpret_response_line
    raise self.handle_error_response(
openai.error.InvalidRequestError: This model's maximum context length is 40[9](https://github.com/ThiagoPanini/terraglue/actions/runs/4038680923/jobs/6942850497#step:3:10)7 tokens, however you requested 5939 tokens (3891 in your prompt; [20](https://github.com/ThiagoPanini/terraglue/actions/runs/4038680923/jobs/6942850497#step:3:21)48 for the completion). Please reduce your prompt; or completion length.

• Link da execução
• Link do PR

De fato, este meu repositório em questão possui arquivos com conteúdos geralmente densos e com muitas linhas. Sabendo dessa limitação da ChatGPT em termos de caracteres, o pedido que se segue é:

Existe a possibilidade de incluir algum flag na Action para não gerar erros na esteira em caso de falhas no geral?

🏆 Resumo sobre benefícios da nova funcionalidade:
Com a implementação dessa nova funcionalidade, os usuários poderiam:

• Não ter seus PRs bloqueados por erros na utilização desta action

📚 Provável complexidade:
A melhor opção que descreve a complexidade associada a esta funcionalidade é:

• Média complexidade

💡 Ideias de implementação:
Para implementação da funcionalidade, seria possível:

• Analisar a melhor maneira de parametrizar a action com algo como continue_if_fail

It would be useful to allow users to specify the prompt to add specific checks, such as "Ensure the PR contains telemetry if it's adding new UI features" and so on.

I added the prompt as optional argument in my fork here: https://github.com/panuhorsmalahti/chatgpt-github-actions - it could be quite easily polished to a PR.

See the following screenshot. I am getting error messages that read: ChatGPT was unable to process the response about XYZ:

This action has the correct permissions to write comments to the PR. Also, it appears the OpenAI token is working as I created it with maximum permissions on the OpenAI side, and I can see it is hitting the OpenAI API on the usage page for the token.

QUESTION: Any idea why I might be getting these responses?

This Github Action looks terrific and would love to be able to use it.

The code I am using is as follows. I removed the "davinci" engine that is in the sample / readme as I was receiving warnings it was deprecated in the Github Action logs:

jobs:
    review-1:
        runs-on: ubuntu-latest
        name: ChatGPT Cirolini Code Review
        steps:
        - name: ChatGPT Cirolini Code Review
          uses: cirolini/[email protected]
          with:
            openai_api_key: ${{ secrets.openai_api_key }}
            github_token: ${{ secrets.GITHUB_TOKEN }}
            github_pr_id: ${{ github.event.number }}
            openai_engine: "gpt-3.5-turbo-1106"
            openai_temperature: 0.5
            openai_max_tokens: 2048
            mode: patch

Run cirolini/genai-code-review@v2
with:
openai_api_key: ***
github_token: ***
github_pr_id: 2
openai_model: gpt-3.5-turbo
mode: files
language: java
openai_temperature: 0.5
openai_max_tokens: 2048
env:
JAVA_HOME: /opt/hostedtoolcache/Java_Adopt_jdk/11.0.23-9/x64
/usr/bin/docker run --name bd3e97b8141ed9284bb43c4748769_1c749f --label 066803 --workdir /github/workspace --rm -e "JAVA_HOME" -e "INPUT_OPENAI_API_KEY" -e "INPUT_GITHUB_TOKEN" -e "INPUT_GITHUB_PR_ID" -e "INPUT_OPENAI_MODEL" -e "INPUT_MODE" -e "INPUT_LANGUAGE" -e "INPUT_OPENAI_TEMPERATURE" -e "INPUT_OPENAI_MAX_TOKENS" -e "INPUT_CUSTOM_PROMPT" -e "OPENAI_API_KEY" -e "GITHUB_TOKEN" -e "GITHUB_PR_ID" -e "OPENAI_MODEL" -e "OPENAI_TEMPERATURE" -e "OPENAI_MAX_TOKENS" -e "MODE" -e "LANGUAGE" -e "CUSTOM_PROMPT" -e "HOME" -e "GITHUB_JOB" -e "GITHUB_REF" -e "GITHUB_SHA" -e "GITHUB_REPOSITORY" -e "GITHUB_REPOSITORY_OWNER" -e "GITHUB_REPOSITORY_OWNER_ID" -e "GITHUB_RUN_ID" -e "GITHUB_RUN_NUMBER" -e "GITHUB_RETENTION_DAYS" -e "GITHUB_RUN_ATTEMPT" -e "GITHUB_REPOSITORY_ID" -e "GITHUB_ACTOR_ID" -e "GITHUB_ACTOR" -e "GITHUB_TRIGGERING_ACTOR" -e "GITHUB_WORKFLOW" -e "GITHUB_HEAD_REF" -e "GITHUB_BASE_REF" -e "GITHUB_EVENT_NAME" -e "GITHUB_SERVER_URL" -e "GITHUB_API_URL" -e "GITHUB_GRAPHQL_URL" -e "GITHUB_REF_NAME" -
python: can't open file '/github/workspace/src/main.py': [Errno 2] No such file or directory

As far as I can tell, the last line of the yaml code example in Step 3 of the README should read

mode: files # files or patch

Instead of

mode: file # file or patch

Is it possible to use Copilot instead of ChatGPT to generate the review comments?

Possible?