fix(desktop): show current context size, not cumulative cache totals#1643
Merged
Conversation
The right-side context meter summed cacheHitTokens and cacheMissTokens, which are session-wide running totals. After ~20 cached turns of a 50k-token context, the cumulative cacheHit alone reaches 1M+ and the panel renders "1,500,000 / 1,000,000" with the bar pegged at 100%. What the meter is supposed to show is the *current* context size — i.e. prompt_tokens of the most recent API call. That value is already captured per-turn as lastCallCacheHit / lastCallCacheMiss; switch the meter to use those. Cumulative totals are still used elsewhere (status bar / settings) for the cache-hit-rate display, where summing is the right semantic. Also mirror the reset into lastCall* on the $ctx_breakdown event so /compact takes effect immediately instead of waiting for the next model.final to overwrite a stale pre-compact value.
esengine
pushed a commit
that referenced
this pull request
May 24, 2026
…moved, persisted usage stats, plan dispatch gate Headline themes: - Desktop: bundle the CLI-hosted React dashboard, retire Tauri+Preact duplicate (#1418) - Config: drop preset abstraction; flash/pro are direct model selections (#1657, #1630) - Stats: persist cumulative usage to session meta + auto-restore on startup (#1667, #1680, #1643, #1628) - Plans: editMode="plan" enforced at the ToolRegistry dispatch gate (#1681); step advance fix (#1629) - Context: fold once at turn start, drop pre-flight + byte-ceiling (#1642, #1646); collapsible compacted card (#1649) - Subagents: per-skill flash/pro override + Settings UI (#1632) - Desktop polish: sidebar drag-resize (#1688), responsive collapse (#1585), copy/edit overlay + msg-history nav (#1645), Esc closes modal not turn (#1685), QQ tab isolation (#1672), DiffCard for edits (#1662), theme-aware highlighting (#1655), system events toggle (#1654/#1650), macOS TCC inheritance (#1614), dashboard.enabled (#1612) - Dashboard polish: persistent session URL (#1586, #1589, #1599), theme-aware highlighting (#1664), IME confirm-enter guard (#1689), code-fence lang fix (#1677), vendor chunk split (#1587), markdown table h-scroll (#1562) - TUI: Alt+S input stash/recall; static history isolated from input rerenders (#1635); legacy mouse drop (#1637, #1648); multi-edit gated in review (#1647) - Diff: SplitDiff column border holds under CJK (#1686) - MCP: workspace roots passed to servers (#1625); codeCommand honors mcpServers (#1603) - Config plumbing: (baseUrl, apiKey) resolved as a tuple (#1658); stale model id self-heal (#1663) See CHANGELOG for the full list.
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
The right-side context meter (sidebar) summed
cacheHitTokensandcacheMissTokens, which are session-wide running totals, and tried to render them against a 1M ceiling. After ~20 cached turns of a 50k-token context the cumulative cacheHit alone reaches 1M+ and the panel renders something like:…with the bar pegged at 100%. /compact partially patched this by resetting the cumulative counters via
\$ctx_breakdown, but the very nextmodel.finalstarted accumulating again, so the fix only held for one frame.Why
What the meter is supposed to show is the current context size — i.e.
prompt_tokensof the most recent API call. That value is already captured per-turn aslastCallCacheHit/lastCallCacheMissinApp.tsx—context-panel.tsxjust wasn't using them.Cumulative totals are still the right choice elsewhere (status bar and settings show cache hit rate, which legitimately wants the session-wide sum), so I left those alone.
How
context-panel.tsx: read fromlastCallCacheHit/lastCallCacheMiss(null-coalesced to 0 since the type allows null for "no call yet").App.tsx: on\$ctx_breakdownwithlogTokens(the post-/compactreset path), also seedlastCall*so the panel reflects the new size immediately instead of waiting for the nextmodel.final.How to verify
/compact— meter should drop to the post-compact log size immediately, then track real per-turn input thereafter.App.test.tsstill passes (no test was asserting the broken cumulative behavior).Checklist
npm run verifypasses locallyCo-Authored-By: ClaudetrailerCHANGELOG.md