feat(orchestrator): run telemetry — the responsiveness A/B spine#638
Draft
gewenyu99 wants to merge 1 commit into
Draft
feat(orchestrator): run telemetry — the responsiveness A/B spine#638gewenyu99 wants to merge 1 commit into
gewenyu99 wants to merge 1 commit into
Conversation
Queue transitions emit orchestrator task enqueued/started/completed/skipped/ failed with the resolved model, attempts, duration, time-to-first-task and the gap between consecutive starts — responsiveness is the dark launch's headline metric. agent completed/aborted carry per-task type, id, model, tokens and cost. The run-end reflection remark fires once, on the task that is last in the queue when it starts. analytics tags every event with the variant. Closes #628 Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
🧙 Wizard CIRun the Wizard CI and test your changes against wizard-workbench example apps by replying with a GitHub comment using one of the following commands: Test all apps:
Test all apps in a directory:
Test an individual app:
Show more apps
Results will be posted here when complete. |
This was referenced Jun 10, 2026
Collaborator
Author
|
Warning This pull request is not mergeable via GitHub because a downstack PR is open. Once all requirements are satisfied, merge this PR as a stack on Graphite.
This stack of pull requests is managed by Graphite. Learn more about stacking. |
This was referenced Jun 10, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Per-task and per-run telemetry for the dark launch, segmentable from the linear baseline by variant. Queue transitions emit
orchestrator task enqueued/started/completed/skipped/failedwith the resolved model, attempts, and duration. Started events carry time since run start and the gap since the previous start. Responsiveness is the headline metric.agent completedcarries per-task tokens, cost, turns, and task type, the cost to watch. The run-end reflection remark fires once, on the task that is last in the queue.Closes #628.