feat(sdk): emit a per-run message event for Pydantic AI - #196
Closed
victorludvig wants to merge 1 commit into
Closed
victorludvig wants to merge 1 commit into
victorludvig wants to merge 1 commit into
Conversation
Placeholder commit opening PR 13/15 of the LLM message logging stack; the change lands on this branch.
This was referenced Sep 8, 2026
victorludvig
changed the title
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Design: LLM message logging design · implementation spec. Plan target: merge by Thu 17 Sep.
What is changing
emit_run_messages()besideemit_run_usage()inadapters/pydantic_ai/usage.py, called from the four sites inagent.py; one event from the result's message history (all_messages()),message_seq=0, no cursor.Why is this change necessary
Pydantic AI has no per-call hook short of
iter(); per-run mirrors its existing usage reporting.iter()-level capture is a follow-up. First scope cut if the sprint slips.Tests
tests/adapters/pydantic_ai/test_usage.pyextended; integration case.🤖 Generated with Claude Code