feat(site/src/pages/AgentsPage): show model context window in compaction settings - #29445
Conversation
…ow in compaction settings
Codex Review SummaryThis comment shows the latest Codex review activity on this pull request.
ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings. |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: feb8254b95
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
… move assertions to Vitest
…ap for React Compiler
DanielleMaywood
left a comment
There was a problem hiding this comment.
I'm not a huge fan of the design but I'm not sure what can be done to save it in its current state 💀
Closes CODAGT-936.
Adds a Context column to the compaction settings table showing each model's compaction window (e.g.
128K tokens) and the token count the effective threshold resolves to (Compacts at ~102K). The trigger point follows the typed draft before saving, so the threshold can be set without remembering the limit. Hidden at 100% (never auto-compacts); showsUnknownwhen no limit is known.The window mirrors the backend rule in
generation_preparer.go: when the organization routes compaction through an override model, the smaller of the chat and override windows is used. The page fetches per-org model overrides (readable by org members) to resolve this; a failed request falls back to the chat model's own window.