roboomp c00790fa3a fix(catalog): cap ollama cloud deepseek-v4 output at 65536 ...

Ollama Cloud's deepseek-v4-pro and deepseek-v4-flash deployments reject any
output budget above 65536 with HTTP 400, despite advertising a 1M context /
384K output (ollama/ollama#16890). Ollama's /api/show never reports this cap,
so the catalog left the base models at the full context window and the dated
tag deepseek-v4-flash:0731 at a stale 8192 fallback. Pin these ids (base plus
tag variants) to min(contextWindow, 65536) at both runtime discovery and
generation; other cloud models keep their discovered limits.

Fixes #7266

2026-08-01 15:30:17 +00:00

..

equivalence.ts

feat(coding-agent): removed canonical model variant selection and tracking

2026-07-01 05:22:42 +02:00

generate-models.ts

fix(catalog): cap ollama cloud deepseek-v4 output at 65536

2026-08-01 15:30:17 +00:00

generated-policies.ts

fix(catalog): cap ollama cloud deepseek-v4 output at 65536

2026-08-01 15:30:17 +00:00