Repository navigation
Conversation
A tool that calls another tool with `api.executeTool()`, as a code mode script does, starts a `pi.tool` task that resolves its tool among `agent.callable`. The integration only wrapped `agent.tools`, so these calls had no span. They now get a `gen_ai.execute_tool` span under the calling tool's span, with the result that `execute()` returned. Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Contributor
size-limit report 📦Compared: 434debb (PR test merge using fix/pi-durable-runtime-identity at ac5afcd) Against: 5a39728 (fix/pi-durable-runtime-identity) · base run #67367
|
Contributor
Optional E2E testsSome optional checks were not successful. They do not block the merge. 5 not successful, 56 successful. See the run.
Successful checks
|
This branch has not been deployed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
piDurableIntegrationnow traces the tool calls that a tool makes withapi.executeTool(). Each one gets agen_ai.execute_toolspan under the span of the calling tool, with its arguments and result.This is what a pi-durable code mode script does. Until now a script was one
execute_tool codemodespan, and the calls inside it did not appear in the trace.Why
pi-durable resolves a model-issued call among
agent.toolsand a nested call amongagent.callable(since 1.2.0). The integration wrapped onlyagent.tools.A nested call is a
pi.tooltask of its own, so its span would otherwise sit next to the calling tool under the run. It gives its result to the calling tool and commits no result entry, so the span records whatexecute()returned.Checked with pi-durable 1.6.0 code mode: one run with 4 scripts shows 21 nested tool spans, each under its script and with its result.
Stacked on #26718, which touches the same lines.