Commit Graph
5 Commits
Author SHA1 Message Date
Marc-André Bombeck fb9cd9b965 refactor(ai): move the stored-key opener and the Anthropic host check out of provider.ts
Both are self-contained; provider.ts stays within its size baseline.
2026-10-23 17:19:21 +02:00
Marc-André Bombeck f8a88d1361 perf(auth): read the operator settings once per request
An app boot's /api/auth/me read the AppSettings singleton six times, each
reader with its own few columns: the MFA policy, the Assistant switches,
the module availability, the provider presence, the AI usage bounds and
the reasoning controls. They now take their columns from one read,
memoised for the request and read afresh inside a background job like the
readers themselves. No answer changes.
2026-10-22 07:25:00 +02:00
Marc-André Bombeck 74dcc67ef7 feat(insights): let the usage level decide the background AI work
The level now sets, per record: the status-card regeneration gap after a
sync (frugal 24 h, standard the operator's gap, full 1 h) and after a hand
entry (frugal 6 h, otherwise 1 h); the status snapshot cap (10 000 compact
characters on frugal, 14 000 above); background reasoning for the briefing
and the period narratives (off on frugal); the daily briefing's form (a
short form on frugal that keeps every field and at most one
recommendation, the full contract on standard and full); and whether the
automatic document read may act (frugal reads on request only, the stored
switch is kept).

A deterministic simulation of a watch-synced day through the invalidator
counts 122 ingest-driven status generations on full (the v1.42 behaviour),
25 on standard and 2 on frugal, plus the nightly warm on each.

Refs #1217
2026-10-15 22:55:40 +02:00
Marc-André Bombeck ae5cee331e feat(coach): resolve the turn's thinking depth from the person and the operator
The chat route hands the turn the level resolveCoachTurnReasoningLevel
returns: the stored Coach preference, absent read as medium, after the
operator's switch and cap. The turn still applies the operator-paid
ceiling once its chain is known. The controls loader no longer throws
when the request cache cannot serve it; it fails closed to off. The
admin guard pins the route to the resolver.
2026-10-06 19:57:04 +02:00
Marc-André Bombeck 74e68745c1 feat(ai): resolve the reasoning level against the operator's controls
Add resolveReasoning, the one decision for how hard a call may think:
the operator's switch, then the provider's ability, then the requested
level (the person's Coach preference, or a background job's own level),
then the operator's cap, then a medium ceiling when the operator pays.
The answer names the layer that decided it.

loadReasoningControls reads the two app_settings columns, memoised per
request, read afresh in background runs, and fails closed to "off".
loadCoachReasoningState resolves the published Coach state from the
memoised provider presence; resolveJobReasoning resolves one background
call and never fails it.

A guard proves the switch and the cap over the whole input space and
requires every call that carries reasoning to take it from the
resolver.
2026-10-06 19:44:51 +02:00