docs: clarify the wrap_llm README section - #26
Closed
tishachawla-jg wants to merge 1 commit into
Closed
Conversation
The previous text had a broken sentence ("use wrap_llm gives the same
...") and did not make clear when to reach for wrap_llm. Rewrite it to
state plainly: use it when your model call is a plain function you pass
around, spell out live vs replay behavior, and note that inputs are read
by name automatically.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Signed-off-by: Tisha Chawla <tisha.chawla2020@vitalum.ac.in>
Contributor
Author
|
Superseded by #27, which restructures the whole README (including this wrap_llm section) and adds the I/O-vs-side-effects clarification. Closing in favor of that. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What
Fixes the
wrap_llmsection of the README, which was unclear onmain.The old text had a broken sentence ("...use
wrap_llmgives the same record +on_crossingcontract...") and never said plainly when you would reach forwrap_llminstead of a decorator.After
The section now:
wrap_llmwhen your model call is a plain function you pass around (rather than a named function you can decorate with@boundary).llmenvelope; Replay (stubbed) returns the recorded result without calling the function.messages/model/providerare read from the arguments automatically, soextract_inputis only needed for unusual signatures.Docs-only, single file. No em/en dashes.