fix(reporting): Include auxiliary model costs#854
Draft
dcramer wants to merge 1 commit into
Draft
Conversation
Conversation cost totals only included the main agent loop, so advisor, compaction, vision, title, prompt-enrichment, and classifier calls were omitted. Persist idempotent auxiliary usage events on the root conversation and preserve them across execution summary replacement. Extend legacy migration adoption for the new table. Co-Authored-By: GPT-5 Codex <noreply@openai.com>
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Conversation cost reports now include model calls made on behalf of the root conversation outside the main agent loop: advisor runs, compaction, vision summaries, title generation, image-prompt enrichment, and structured reply classification. Child conversations remain excluded from top-level reporting while their model usage rolls into the parent.
Auxiliary contributions are stored in
junior_conversation_usage_eventswith a unique call ID, making persistence retries idempotent while the conversation row remains the reporting read model. Legacy Drizzle adoption now distinguishes baseline, metrics-only, and usage-event schemas so older deployments apply only the missing migrations. Image-generation media charges remain outside this text-model estimate because the raw image endpoint does not expose normalized model cost; prompt enrichment is included.