The cost backfill hardcoded codex|gemini as cache-inclusive apps, so
grokbuild TOTAL-semantics rows were priced on full input tokens with
cache reads double-counted. Converge the writer (proxy logger and
calculator) and the backfill recompute onto a single
sql_helpers::is_cache_inclusive_app predicate backed by the existing
CACHE_INCLUSIVE_APP_TYPES constant, and add a regression test for the
grokbuild backfill path.
Parse cache_write_tokens from OpenAI usage details and preserve cache creation data across Chat, Responses, and Anthropic conversion paths.
Add explicit input-token semantics to request logs and rollups so legacy rows subtract cache reads only while new total-inclusive rows subtract both cache reads and writes. Migrate v12 databases, normalize rollups to fresh input, and cover historical backfill behavior with regression tests.
- Normalize OpenAI/Gemini input_tokens semantics in SQL via the new
fresh_input_sql helper (cache_read subtracted at query time, no data
migration). Recovers correct cache hit rates for Codex/Gemini.
- Add get_usage_summary_by_app endpoint for per-app split (single
UNION ALL + GROUP BY, avoids N+1).
- Replace UsageSummaryCards + AppBreakdownRail with a single
filter-driven UsageHero card; clicking a filter button now truly
changes the displayed numbers and the title accent color.
- Tighten KNOWN_APP_TYPES to the 3 app_types whose token data is
reliably collected (claude/codex/gemini); hide claude-desktop,
hermes, opencode, openclaw filter buttons and i18n keys.
- Flag cache_creation as N/A for OpenAI-style protocols (Codex,
Gemini); show a "partial" tooltip when the All view mixes both
protocol families.
Jason