snoop

p](https://github.com/alexmojaki/snoop) because I like the features and output formatting, but it doesn't support async. I have found [ASnooper](https://github.com/LL-Ling/ASnooper), but it only supports async. I'd like to add ASnooper's async feature to snoop. I'm thinking of creating a project that imports both, and patches the relevant parts of snoop with the async functionality from ASnooper. I have some notes from looking into the snoop code: - A `ConfiguredTracer` object is exposed in `builtins` (configuration.py, line 142). - Whenever the `ConfiguredTracer` object is called with an async function, it raises (tracer.py, line 166). - The trace event is passed to a formatter, and then a writer (tracer.py, line 280-281). ... and in the ASnooper code: - An `ASnooper` object is exposed (__init__.py). - Whenever the `ASnooper` object is called on an async function, it creates formatter and writer objects (core.py, line 69-75). The approach I'm considering is to wrap `ConfiguredTracer.__call__` with a method that delegates async function tracing to `ASnooper`, and replace the `OutputFormatter` and `OutputWriter` classes with versions that delegate to `snoop`'s implementation. I've prepared a repo for the solution: """ . ./README.md ./pyproject.toml ./tests ./tests/__init__.py ./src ./src/async_patched_snoop ./src/async_patched_snoop/__init__.py """ I've also extracted excerpts from both projects, as unified diff contexts (attached). Any issues, questions or suggestions? Or a better approach that doesn't involve forking the targeted projects? =============== I prompted Claude with this along with a file containing the diffs (constructed with the help of another prompted tool), Claude informed me of the issues in my approach and suggested a couple alternate solutions, I selected the one 1 preferred, Claude asked for some more context and then did the implementation, and now I have async support in snoop. Probably took me over an hour to construct that initial prompt, and under 5 minutes of conversion to completed solution. I really don't think that that's boring.

red by many open source libraries that I've created which are designed to also be useful in their own right: Debuggers: these are integrated in the site but also usable in any environment: - https://github.com/alexmojaki/birdseye - https://github.com/alexmojaki/snoop - https://github.com/alexmojaki/cheap_repr (not a debugger, but used by the above two as well as directly by futurecoder) Tracebacks: - https://github.com/alexmojaki/stack_data (this is also what powers the new IPython tracebacks) - https://github.com/alexmojaki/executing (allows highlighting the exact spot where the error occurred, but also enables loads of other magical applications) - https://github.com/alexmojaki/pure_eval You can see a nicer presentation (with pictures) of the above as well as other projects of mine on my profile https://github.com/alexmojaki Libraries which I specifically extracted from futurecoder to help build another similar educational site https://papyros.dodona.be/?locale=en (which does have a canvas output, at least for matplotlib): - https://github.com/alexmojaki/sync-message (allows synchronous communication with web workers to make input() work properly) - https://github.com/alexmojaki/comsync - https://github.com/alexmojaki/pyodide-worker-runner - https://github.com/alexmojaki/python_runner