kevinveenbirkenbachandClaude Opus 5 f4f7c64761 refactor(svc-ai-litellm): build the model routes once instead of a loop per source ...

The proxy config grew a loop per model source, so the rule for how an alias is called lived in four places - and they had drifted: the LM Studio branch published no model_info.max_input_tokens although the role's README says a model entry carrying context publishes exactly that. Serving anything new meant a fifth branch.

The sources now meet in one filter that returns {alias, params, context}, and the template renders a single loop. Every value goes through to_json, so a response carrying a colon, a quote or a newline cannot break the YAML it is written into.

Publication order is a contract, not an accident of how the loops were stacked: LITELLM_CHAT_MODEL takes the first alias, so a locally served model has to outrank a declared one. That is now stated in the module and asserted, instead of being implied.

The gateway lint had to widen with it. Its canary checks that some gateway template still matches the provider-URL pattern, because without one the rule would pass vacuously on every consumer; the pattern demanded {{ … }} while the template now sets the URL in {% set … %}. Widening it to {{ or {% makes the rule stricter, since a provider URL in a set block is just as direct an address and would have slipped through anywhere else.

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

2026-09-23 15:57:14 +02:00

..

action

perf(constructor): carry the applications SPOT through the merge block

2026-09-14 18:10:40 +02:00

filter

refactor(svc-ai-litellm): build the model routes once instead of a loop per source

2026-09-23 15:57:14 +02:00

lookup

Merge branch 'main' into feature/svc-ai-litellm/remote-models-config

2026-09-22 21:42:10 +02:00

__init__.py

…