Files
OmniRoute/tests
Paco Cartones 8e474914ea fix(providers): mark groq compound and allam-2-7b as non-reasoning models (#12379)
groq/compound and allam-2-7b were absent from the curated Groq registry, so the capability heuristic defaulted them to reasoning-capable and forwarded reasoning_effort verbatim — Groq answers HTTP 400. Declaring supportsReasoning: false makes applyThinkingBudget() strip reasoning_effort, output_config.effort and thinking, same class as #3258. The gpt-oss reasoning models keep the field.

Validated in a combined worktree with all 25 PRs of this batch boarded together: typecheck:core clean, 443/443 node-runner tests plus 14/14 vitest across every test file the batch touches, and check-changelog-integrity, check:cycles (418 files), check:provider-consistency (272 REGISTRY entries, 355 canonical providers), check:docs-counts, check:docs-sync (42 locales) and check-file-size all green.

Thanks @pacocartones.
2026-09-02 03:12:18 -03:00
..
2026-08-26 14:25:01 -03:00