chore(release): v1.7.6 — token usage dashboard + auto-memory#54
Merged
Conversation
Token usage dashboard: adaptive-resolution activity heatmap (1h boxes for 7d, 12h for 30d, 1-day GitHub-style grid for all, always 7 rows tall so the card height stays constant across ranges, padded to 180 days minimum), gamified stats (streaks, peak hour, favorite model), a per-model breakdown with a stacked usage chart, and a milestone/fun-fact card. New nav entry "Usage", positioned before Developer. Auto-memory: background extraction of durable facts from the user's own chat messages via the model's own inference (never attachments/tool output), gated by a new off-by-default Settings toggle, with a view+delete-only fact list. Facts are injected into new conversations' system prompt only — verified end-to-end against the actual outbound request payload, not just DB state.
New feature with a narrow silent-extraction scope; the badge sets expectations before it sees broader use.
Bumps to 1.7.6 (patch, founder call), updates the changelog/README/persona knowledge base for the two new features, and applies fixes from the pre-release Opus review of PR #54: - memory.ts: dedup was Jaccard-comparing raw words, so filler words (I/my/is/ in/as/a) dominated the overlap score and distinct facts of the same shape ("I live in Paris" vs "I live in Berlin") were silently dropped. Now compares content words only, with a regression test covering the exact cases the review reproduced. - personas.ts: cap injected memory facts to the most recent 50 so a long-lived account's fact list can't quietly eat an ever-growing slice of every new chat's context window. - DailyBarChart.tsx: fixed a y-axis tick formatter that collapsed adjacent values (e.g. 2000 and 1500) to the same "2K" label. - TokensScreen.tsx: raised the fun-fact multiplier floor from 1x to 2x so a total near a band's own lower boundary can't land a weak "~1x" comparison depending on which reference the random pick landed on.
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.
Summary
Test plan
npm run typecheck(frontend)