Back to Signal Feed
CodeTracked since May 22, 2026

Track only accepted review suggestions in telemetry

Kilo-Org/kilocode now records review-telemetry only when a user accepts a review suggestion, while excluding dismissed, invalid, and non-review suggestions, and marks the next model response as suggest-tool-driven using sanitized review command names.

review suggestiontelemetrysuggest toolreview command names

What Happened

  • Kilo-Org/kilocode now records review-telemetry only when a user accepts a review suggestion, while excluding dismissed, invalid, and non-review suggestions, and marks the next model response as suggest-tool-driven using sanitized review command names.
  • Kilo-Org/kilocode now records review-telemetry only when a user accepts a review suggestion, while excluding dismissed, invalid, and non-review suggestions, and marks the next model response as suggest-tool-driven using sanitized review command names.
  • 1 evidence item attached for review.

What is Different

Before

Scattered source updates, isolated context, and manual follow-up across multiple feeds.

Now

Added acceptance-gated telemetry for code-review suggestions: only confirmed user-accepted suggestions increment suggestion metrics, and the immediate follow-up model completion is now attributed to the suggest tool with command names constrained to recognized review commands.

Why Track This

Why It Matters

Review workflow teams get cleaner, more actionable telemetry, because acceptance dashboards now reflect real accepted suggestions instead of overcounting dismissed or invalid ones and can better measure whether suggestion-based review automation is being used; operators should watch for any valid but custom-formatted suggestion commands that stop being tracked due to the new command-name allowlist. This reduces uncertainty in rollout decisions and bug triage, while introducing a new edge case where unsupported command variants may lower observability until command coverage is expanded.

Impact

Review workflow teams get cleaner, more actionable telemetry, because acceptance dashboards now reflect real accepted suggestions instead of overcounting dismissed or invalid ones and can better measure whether suggestion-based review automation is being used; operators should watch for any valid but custom-formatted suggestion commands that stop being tracked due to the new command-name allowlist. This reduces uncertainty in rollout decisions and bug triage, while introducing a new edge case where unsupported command variants may lower observability until command coverage is expanded.

What To Watch Next

  • Watch whether review suggestion becomes a repeated pattern.
  • Track follow-up changes around AI Code Review.
  • Compare future signals against this evidence trail.
  • Re-check risk flags: custom_review_commands_not_tracked, followup_model_response_misattribution.
Open Topic TimelineOpen Technical EventOpen Original Sourcecustom_review_commands_not_tracked / followup_model_response_misattribution / telemetry_gaps_for_nonstandard_inputs

Supporting Evidence

GITHUB PULL REQUESTHigh Trust

Kilo-Org/kilocode PR #10502: feat: track accepted review suggestions

The app now records a telemetry event only after a user accepts a review suggestion; dismissed, invalid, and non-review suggestions are no longer counted, and accepted-suggestion follow-up model responses are tagged as coming from the suggest tool with known review command names.