Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Idea here is that all of the tool-specific implementation (including config JSON) lives in one directory.
Dependencies move from the JSON file into a
pyproject.toml
file, which also breaks out any framework-specific dependencies, like the version of CrewAI it uses, into a tag underoptional-dependencies
.We still need to discuss a preferred package manager so I dove into to the docs of the top four and put together some possible commands.
uv
andpip
do what we need out of the box.poetry
can still help us with dependencies, but copying the actual source files rolls back to a manual copy.conda
would be similar to pip, since we'd probably just fall back to pip in that case; it doesn't have any CLI flags for this kind of conditional copying nor does it really supportpyproject.toml
.agent_connect
is the only tool dir that I reorganized so far to reflect this new structure.Would be cool to explicitly specify a preferred package manager in
agentstack.json
if we do go with multiple managers.Needs tests before merge as well.
This addresses #43