Commit Graph

9 Commits

Author SHA1 Message Date
Maximillian von Briesen
cleanup/refactor (#1)
focus on fully automated as basic/default functionality. remove unnecessary commands except for local git debug. remove unnecessary interfaces and code. remove local git functionality from github client. probably some other stuff too
2023-05-04 20:01:46 -04:00
Moby von Briesen
99bd1929b5 add basic run command 2023-05-02 20:07:48 -04:00
Moby von Briesen
10c77854a9 Create "local git client" and "openai client"
OpenAIClient can be used to interact with OpenAI's API. Untested at the
moment (except with an API key that does not yet have perms)
Local git client splits the "git" functionality (e.g. make commits,
checkout branches, etc...) away from the "github" client

I also removed a lot of duplicate code for the different commands in cmd
And created a basic "local issue" command to send a "code change
request" to the llm, and receive a code change response. Eventually, I
want this to make the corresponding local git changes, for the user to

TODO: github client should only be responsible for github-specific
actions, e.g. opening a PR or listing issues/comments
2023-04-25 20:32:08 -04:00
Moby von Briesen
726e34d093 Add command to list comments on PR
Only comments in the configured "users to listen to" are listed
Still need to add additional filtering in the future
2023-04-24 20:29:26 -04:00
Moby von Briesen
9cc0f4a1b8 Add plain "list issues" command and reorganize
* Add configurable users to list issues from
* Add configurable labels to require on issues
* Add a CLI subcommand that lists issues according to the criteria and
  does nothing else
* Update existing CLI REPL to list issues according to the new criteria
* Clean up and reorganize config code a little
* Add some basic types and function signature for listing comments on
  code change requests
2023-04-24 19:49:10 -04:00
Moby von Briesen
529b720eb6 Loop prompt generation/response parsing
Alternate between generating prompts via Github issues and parsing LLM
responses until the user exits.

Also slightly modify LLM response parsing to handle some unintentional
text which is copied from ChatGPT's web UI for code blocks.
2023-04-22 22:44:44 -04:00
Moby von Briesen
e648ed50a4 Add ability to copy LLM prompt directly to clipboard 2023-04-22 21:56:52 -04:00
Moby von Briesen
b9b0b9cf12 It's working
Implement cobra and stuff
Right now there is just one root command
You can set a config file, or pass flags in via CLI
Haven't figured out how to use env variables yet
But if you run the root command,
It'll check the repo for issues, and generate an LLM prompt
You can copy-paste it to the LLM chat, then copy-paste the response to a
different file
Then press enter in the CLI tool, and it will parse the response and
open a PR with the change
2023-04-22 21:41:28 -04:00
Moby von Briesen
a570437b9c Initial commit (part 2)
I added some code
and comments too
it's almost set up
for me and you
2023-04-22 14:50:15 -04:00