Marc-André Bombeck b0ea3b1654 fix(ai): charge what failed hops spent when a later hop answers ...

A chain whose first provider reasoned without answering and whose second
one answered billed only the answer: result.tokensUsed is the answering
call's alone, and the failed hop's spend, already reported on its
FallbackHop, was dropped by every caller that reconciles the day's ledger.

The raw runners now report tokensSpent on success too, the sum the failed
hops before the answer reported. The briefing, status, Coach (no-tools path
and every tool-loop round) and medication-extract reconciles charge it on
top of the answer. On failure, the Coach turn ledger's close keeps what the
failed chain reported spending instead of refunding everything, and the
medication-extract and document-chat routes charge it too, as the status
and briefing paths already did. Document indexing resolves a single provider
and already charged its failed call.

Refs #1279

2026-10-25 00:33:18 +02:00

..

browser

test(measurements): drive the measurement form in a real browser

2026-10-23 13:07:29 +02:00

durations

test: drop the timings of test files that no longer exist

2026-10-23 17:54:22 +02:00

fixtures

docs: publish the UI standards in docs/contributing

2026-10-21 19:37:22 +02:00

integration

fix(ai): charge what failed hops spent when a later hop answers

2026-10-25 00:33:18 +02:00

kit

fix(analytics): cut every summary window on the request's clock

2026-10-24 12:14:33 +02:00

property

ci: fail the mutation floors step, and scale nightly property runs by a factor

2026-10-22 19:04:20 +02:00

quarantine

test: a flaky-test quarantine with an expiry the guard enforces

2026-10-22 05:33:09 +02:00

support

test: fail a test whose code caught and logged a missing mock export

2026-10-22 23:15:43 +02:00

unit-projects.ts

ci: shard both suites by measured duration and split the unit suite

2026-10-22 05:39:35 +02:00