feat: per-model failure counts and switch history in status#9
Merged
Conversation
The model_fallback_control status now reports `failureCounts` (how many retryable errors each model hit) and `switches` (last 20 model transitions with from/to/reason/timestamp; reasons: fallback, unavailable, recovery). Useful for diagnosing which models are flaky in a long session. Cleared on reset alongside the rest of the session state. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Merged
ShutovKS
added a commit
that referenced
this pull request
Jul 14, 2026
This was referenced Jul 14, 2026
Merged
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Проблема
Не видно, какие модели флакают в долгой сессии и как именно происходили переключения — поддержка не может диагностировать поведение.
Решение
model_fallback_controlstatus теперь дополнительно отдаёт:failureCounts— сколько ретраимых ошибок пришлось на каждую модель.switches— последние 20 переходов между моделями:from,to,reason(fallback|unavailable|recovery),at(timestamp).Заполняется в точках switch (event), unavailable-redirect (chat.message) и recovery (chat.message). Сбрасывается вместе с остальным состоянием в
reset.Тесты
failureCountsи две записиswitches(reason=fallback).resetочищает метрики и историю.Юнит-тесты 58/58, typecheck чист (попутно наведён type-narrowing в unavailable-ветке).
🤖 Generated with Claude Code