docs: document the context window usage breakdown - #456
Closed
hongyi-chen wants to merge 1 commit into
Closed
Conversation
The ContextWindowUsageBreakdown feature flag was promoted dogfood -> GA. Document the per-segment breakdown in the context window management section, including each segment category and how to use the breakdown to reclaim context. Co-Authored-By: Oz <oz-agent@warp.dev>
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
Collaborator
Author
|
Heads-up on overlap: #451 also documents the context window usage breakdown, but it edits |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What
Documents the per-segment context window breakdown under Context window management in
agents/local-agents/interacting-with-agents/index.mdx.Why
Found by the
missing_docsdrift-watch audit:ContextWindowUsageBreakdownwas promoteddogfood → GA, and the breakdown it adds to the usage summary was undocumented.
Source of truth
app/src/ai/blocklist/usage/conversation_usage_view.rs—append_context_window_segment_rowsand
context_window_segment_display_rows(percentages are shares of total context window usage;rows sort descending with
Otherlast; zero rows are dropped), plus theOthertooltip copy.crates/persistence/src/model.rs— theContextWindowSegmentTypevariants that produce thesegment labels.
Deferred findings from this run
Nothing from the audit was silently dropped. The full deferral list lives in the companion
bookkeeping PR (
docs/missing-docs-audit-bookkeeping); in summary:sync-openapi-specskill rather than hand-written, per the skill's public/private guardrail.style_lintskill.report_external_reference) — reached only through the hiddenoz harness-supportCLI, so no public surface to document yet.Conversation: https://staging.warp.dev/conversation/c45bb2ea-d33b-4723-8249-478547f81a47
Run: https://oz.staging.warp.dev/runs/019fc891-7c04-779b-b006-328169d8a0d7
This PR was generated with Oz.