Populate tool_events distance-to-human columns - #8
Merged
Conversation
The schema documented distance_from_previous_human_message, distance_to_next_human_message, tools_since_previous_human, and tools_until_next_human, but the ingest hardcoded all four to NULL. Compute them from the nearest human message on each side of every tool event, document the zero-byte-glob Binder Error in the ingest header, and record the SSH tag-signing setup in RELEASING. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Rectifies the three items deferred from v0.1.1.
tool_eventsnow computes the four documented distance columns instead of leaving them NULL: session-row distances to the nearest human message on each side, and 1-based tool positions within the run between two human messages. NULL when no human message exists on that side.Verified with a new regression test on the shipped fixture plus a denser synthetic session (two humans, four tool events across three assistant turns) checked against hand-computed expectations. 27 tests pass; ruff/format clean.
Metric note: the four columns previously carried NULL, so any consumer that filtered on them now sees values for the first time.
🤖 Generated with Claude Code