* feat(web): show exact per-turn token usage * test(runtime): refresh exact token usage snapshots * refactor(token-meter): own per-turn usage folding * perf(ui-chat): bound paging anchor layout reads * test(web): align usage golden with system prompt row * fix(test): resolve token-meter client from source * test(token-meter): cover retry without usage --------- Co-authored-by: ZiyaZhang <199893125+ZiyaZhang@users.noreply.github.com>
6 lines
446 B
YAML
6 lines
446 B
YAML
# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
|
|
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
|
# after editing either side, bring the other along and re-record with:
|
|
# pnpm run verify-translation-pairing --write docs/subsystems/llm-streaming.md
|
|
llm-streaming.md: 29efabd2b01659bdf2cc798ceadb4bb495e1731e
|
|
llm-streaming.zh.md: 21ad56e526b9a507644b436b41ad063c5310b2ce
|