kevinveenbirkenbachandClaude Opus 5 539e27795f feat(svc-ai-litellm): weight each routing factor from services.yml ...

The router ranked surviving routes lexicographically: local, then price,
then speed, then alias. How much a factor counted was its position in
that tuple, so a deployment could not say that it cares about price more
than about speed.

Each factor now carries a 0..1 weight in services.litellm.router_weights.
A factor is scaled to 0..1 inside the candidate set before its weight
applies, because the raw units do not compare: a per-token price is a
millionth of a cent and a rate is tens of tokens per second. A factor
whose value is identical across the set scores every route 1 and drops
out, rather than deciding on a rounding artefact.

Confidentiality stays out of the score. local_reason removes every remote
candidate before decide() runs, so no weighting can send a request that
must stay local to a third party; a weight is a preference, and a
credential leaving the cluster is not something a preference should be
able to buy. The shipped weights additionally keep locality worth at
least cost and speed combined, and a test reads them out of
meta/services.yml rather than repeating them.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

2026-09-24 00:32:07 +02:00

..

cli

feat(ci-trigger): state the selection and its axes, and refuse one that cannot deploy

2026-09-23 11:56:24 +02:00

group_vars

fix(svc-ai-litellm): let the key-slot guard accept the mock provider

2026-09-23 16:28:19 +02:00

library

…

plugins

perf(deploy): keep the roles no host carries out of the stage loop

2026-09-23 23:17:37 +02:00

roles

feat(svc-ai-litellm): weight each routing factor from services.yml

2026-09-24 00:32:07 +02:00

scripts

fix(diagnostics): let the in-zone probes read the drop-in that holds the zone

2026-09-03 12:50:58 +02:00

utils

feat(ci): deploy only the variants a change reaches

2026-09-21 22:51:03 +02:00

__init__.py

…