feat: Display model + tokens in PR code reviews summary#407
Merged
alex-alecu merged 16 commits intomainfrom Feb 23, 2026
Merged
feat: Display model + tokens in PR code reviews summary#407alex-alecu merged 16 commits intomainfrom
alex-alecu merged 16 commits intomainfrom
Conversation
![kilo-code-bot[bot]](https://avatars.githubusercontent.com/in/2193792?s=60&v=4){kind=small}
Contributor
Code Review SummaryStatus: 1 Issue Found | Recommendation: Merge with minor improvement Overview
Issue Details (click to expand)SUGGESTION
What Looks Good
Files Reviewed (14 files)
|
…usage data Use 3 retries with 200/400/800ms delays instead of a single 2-second sleep. Reduces average latency when data is already present and provides more attempts when it isn't.
Cover buildUsageFooter and appendUsageFooter including first-time append, footer replacement with exact and variant whitespace, empty body, unrelated horizontal rules, and multi-slash model slugs.
Sync model/token/cost accumulators to this.state on every LLM API event so they are written to durable storage by the existing event batch save. Restore them in loadState() so accumulation resumes correctly after a DO restart.
…-to-pr-review-summary # Conflicts: # src/app/api/internal/code-review-status/[reviewId]/route.ts # src/db/migrations/meta/0021_snapshot.json # src/db/migrations/meta/_journal.json # src/db/schema.ts # src/lib/code-reviews/db/code-reviews.ts
…dateCodeReviewUsage
…-to-pr-review-summary # Conflicts: # src/db/migrations/meta/0022_snapshot.json # src/db/migrations/meta/_journal.json
| } | ||
| } | ||
| } catch (reactionError) { | ||
| } catch (postCompletionError) { |
Contributor
There was a problem hiding this comment.
[SUGGESTION]: Missing captureException — this catch block now covers usage footer updates (API calls to find + update PR comments) in addition to reactions, but errors are only logged, not reported to Sentry.
Consider adding captureException(postCompletionError, { tags: { source: 'code-review-status-post-completion' } }) so failures in the expanded scope are visible in monitoring.
marius-kilocode
approved these changes
Feb 23, 2026
This was referenced Feb 24, 2026
alex-alecu
added a commit
that referenced
this pull request
Mar 4, 2026
Even if this PR #407 was implemented, it doesn't work because cloudflare code review worker is not setup. It was probably deployed once locally. I have tried a manual pipeline deploy and it failed https://github.com/Kilo-Org/cloud/actions/workflows/deploy-code-review-worker.yml I'll first fix the manual pipeline and then merge this automated CD.
alex-alecu
added a commit
that referenced
this pull request
Mar 10, 2026
…eviews PR #407 added model/token tracking to the review summary, but it only works for v1 (SSE) reviews. All reviews now use v2 (cloud-agent-next), which skips SSE stream processing entirely, so usage is never reported. Fix: when the code_reviews record has no usage data, query the billing tables (microdollar_usage + metadata) by cli_session_id to get the model, tokens, and cost. Back-fill the code_reviews record so future reads skip the aggregation.
3 tasks
alex-alecu
added a commit
that referenced
this pull request
Mar 10, 2026
…iews (#978) ## Summary [PR #407](#407) added model + token info to the PR review summary comment (the "Reviewed by claude-sonnet-4.6 · 12,345 tokens" footer). But it only works for v1 (SSE-based) reviews. All reviews now run on v2 (cloud-agent-next), which is callback-based — it never streams SSE events, so usage data is never collected and the `model`, `total_tokens_in`, `total_tokens_out` columns stay null. **The fix:** when the `code_reviews` record has no usage data, we query the billing tables (`microdollar_usage` + `microdollar_usage_metadata`) by `cli_session_id`. The billing system already tracks every LLM call with model, tokens, and cost — we just aggregate it per session. We also back-fill the `code_reviews` record so future reads don't repeat the aggregation. ## Verification - [x] `pnpm typecheck` — no new errors (pre-existing errors in kiloclaw only) - [x] `pnpm test usage-footer` — 10/10 pass - [x] Read through the billing schema to confirm `microdollar_usage_metadata.session_id` matches `code_reviews.cli_session_id` ## Visual Changes N/A ## Reviewer Notes - The billing query groups by model and picks the one with the most tokens (the primary review model). This handles sessions that use multiple models (e.g. a cheaper model for sub-tasks). - The back-fill write to `code_reviews` is fire-and-forget (`.catch()`) — if it fails, the footer still shows correctly; we just won't cache the result. - Long-term, cloud-agent-next could include usage data in its `ExecutionCallbackPayload`, but that's a bigger change. This fix works today with no changes outside the Next.js app.
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.
We cannot include the total tokens in the first summary because we would exclude the tokens used to generate the summary* itself. Instead we manually add the footer after the summary is posted.
The costs for Code Reviewer are already visible in
/usage-details: