codeburn/docs
iamtoruk 7bb4e7f8e1 docs(grok): state the mixed-session drop and the global daily re-derivation plainly
The daily-cache re-derivation test seeded v18, a version that only ever
existed as an unreleased draft of this change. Seed the shipped v17 so the
test models the 17 -> 19 upgrade path users actually hit, and rename it: the
bump re-derives every day for every provider, not just Grok, because the
daily cache has no per-provider invalidation. The Grok day stays as the
fixture since Grok is what the bump exists to correct.

The changelog entry now says outright that Grok totals change materially on
upgrade (150K -> 96.3M cache-read tokens on a 568-session corpus), that a
turn without a turn_completed record inside an otherwise-covered session is
dropped rather than estimated, and that the one-time daily re-derivation
reads the warm session cache and keeps the superseded file. The
context-bloat denominator fix moves to Fixed and names the providers it
corrects.

docs/providers/grok.md gets the same undercount warning in the token model
and a matching entry under Quirks.
2026-08-18 10:22:36 -07:00
..
design Scope the root test script to tests/ so npm test runs from a clean install 2026-08-09 10:19:58 -05:00
providers docs(grok): state the mixed-session drop and the global daily re-derivation plainly 2026-08-18 10:22:36 -07:00
sync fix(sync): close credential-leak paths; session retraction; span/key/CLI hardening 2026-08-02 12:56:59 +00:00
architecture.md docs: surface the Windows menubar 2026-08-18 04:14:05 -07:00
optimize.md Merge remote-tracking branch 'origin/main' into feat/optimize-recurring-context 2026-08-18 03:31:16 -07:00