changeset: release polyglot tool-span parity - #491
Merged
Conversation
🦋 Changeset detectedLatest commit: 59275ed The changes in this PR will be included in the next version bump. This PR includes changesets to release 2 packages
Not sure what this means? Click here to learn what changesets are. Click here if you're a maintainer who wants to add another changeset to this PR |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Releases #490. Fifth PR in a row on this ticket to merge without a changeset (#470, #471, #474, #488, #490) — see the note below on closing that loop.
What #490 fixes
All four non-Rust engines omitted
gen_ai.systemfrom the tool span, so OTLP consumers that gate on it — SmooAI's does — discarded every tool span those engines ever emitted, identically to the Rust engine. Each now carries its owngen_ai.system,gen_ai.operation.name(literallychat/tool, taken verbatim by ingest),gen_ai.conversation.id, andsmooai.org_id. Child spans need their own copies: ingest merges resource attributes with that span's attributes, with no parent inheritance.Cost reaches the span for the first time in all four, with a gateway zero recorded as
cost_unavailable = "unpriced"rather than as a cost — unpriced is not free.Two more fabricated values, removed rather than ported
TurnUsage(0, …)on the cost fallback, under an XML doc reading "0 means 'nothing priced it', not 'free'". The comment was right; the code shipped the zero anyway.input_tokens = 0by guarding onsawUsagealone — a usage chunk with null counts sets that flag while both totals collapse to0via?? 0. The other three guard on the counts.That makes six such values found today. The consistent tell: the comment is accurate about the mechanism and silent about the consequence.
Worth closing the changeset loop
Anchor Guard already runs on every PR and checks that a changeset names the right package. It just doesn't check one exists for a PR touching published trees. Same script, one condition wider — and it would have caught all five.
🤖 Generated with Claude Code
https://claude.ai/code/session_01LkCz96UfUxcai5RU4LwPnG