Make long-context pricing warnings server-driven#12227
Draft
dagmfactory wants to merge 7 commits into
Draft
Conversation
- removed GPTConfigurableContextWindow flag so that server controls behavior - server determines and sends long context threshold instead of hardcoding on client
…-billing # Conflicts: # crates/warp_features/src/lib.rs
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
Make configurable context windows and long-context pricing warnings server-driven.
long_context_usedmetadata through live updates, restore, and shared-session replayDeployment order: deploy the corresponding warp-server GraphQL/model metadata and billing changes before shipping this client. Related changes: warp-server#11673, warp-server#11678, and warp-proto-apis#319.
Linked Issue
ready-to-specorready-to-implement.No linked issue.
Testing
./script/formatcargo clippy --locked -p warp --all-targets --all-features --tests -j 10 -- -D warningscargo test --locked -p warp -j 10 long_context -- --nocapturecargo test --locked -p persistence -j 10 model_token_usage -- --nocapturegit diff --check./script/runIntegration coverage was not added; focused unit regressions cover server-driven thresholds, active-model attribution, custom endpoint exclusion, persistence, restore, and replay behavior.
Screenshots / Videos
Final screenshots for the latest warning/normal states should be attached before marking ready for review. Iterative screenshots and review context: https://staging.warp.dev/conversation/92de2f7b-4e87-4e54-9c40-4ab72dd0b6ba
Agent Mode
Related PRs: warpdotdev/warp-proto-apis#319 | https://github.com/warpdotdev/warp-server/pull/11673 | #12227
Loom
https://www.loom.com/share/2dd5937596c1469c9550b4afdb56dc8a
CHANGELOG-IMPROVEMENT: Added configurable context windows for eligible models and a warning when OpenAI long-context pricing is applied.
Co-Authored-By: Oz oz-agent@warp.dev