Repository navigation
feat: run gitdog on claude opus 5.5 with 2x quota weight - #29
Merged
Merged
Conversation
Gitdog's own generation moves from Sonnet 5.5 to Opus 5.5 at medium effort, and the Sol fallback runs at high effort. A model catalog prices every chat model and gives Opus a quota weight of 2: reservations hold the highest routed weight, settlement charges the lower of the model's and the reservation's weight, and reservations made before weights keep 1x. Usage on the owner's own key is never weighted. A refusal fallback is priced at the model that served it. The README now covers using Gitdog; development material moved to CONTRIBUTING.md.
|
Reviewed c85f630 · see the review |
hyochan
commented
Nov 17, 2026
|
Visit the preview URL for this PR (updated for commit c85f630): https://codeyou-df251--pr29-feat-model-catalog-xeirp5jo.web.app (expires Tue, 24 Nov 2026 18:08:14 GMT) 🔥 via Firebase Hosting GitHub Action 🌎 Sign: 844dad9c62537d028cabc21008e4e2e4031ce4e5 |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
mediumeffort (was Sonnet 5.5 athigh); the GPT-6.1 Sol fallback runs athigh(wasxhigh).CHAT_MODELScatalog prices every chat model and gives each a quota weight. Opus 5.5 ($4/$20) counts 2× against the user's tokens on Gitdog's key; Sol and the retired Sonnet count 1×. Usage on the owner's own key is never weighted or debited.RESERVATION_QUOTA_WEIGHT) and store it; settlement chargesmin(model weight, reservation weight). A reservation made before this change keeps weight 1, so retries across the deploy still match its identity and are never charged more than they reserved.servedModeland priced at that model; quota stays bound to the requested model.maxTokens.Verification
bun run lint,typecheck,build,test(2057 tests),format:check,check:api,typecheck:cli,test:cli,bun audit🤖 Generated with Claude Code