Erick Kinnee 338c05dc6a fix(models): expose Ollama Cloud native effort tiers (#11307) ...

Validated on a 17-PR combined board: models-catalog-combo-metadata + ollama-cloud-reasoning-effort-tiers-10788 within the board's 287/287, typecheck:core clean, check:open-sse-typecheck clean, vitest 405/405. Publishes Ollama Cloud's native none/low/medium/high/max effort vocabulary for reasoning-capable passthrough/tagged models with no exact registry declaration, adds none to DeepSeek V4/GLM 5.x, and preserves narrower exact-model vocabularies (GPT-OSS) via intersection. Refs #10788. Thank you @ekinnee!

2026-08-24 01:55:47 -03:00

..

_helpers

…

_setup

…

benchmarks

…

boundary

…

e2e

…

fixtures

…

golden-set

…

helpers

fix(responses): replace synthetic reasoning keepalive (#10806)

2026-08-20 09:49:55 -03:00

homolog

…

integration

fix(tests): drain base-red cluster from 2026-08-23 merges (#9985) (#11280)

2026-08-23 20:32:46 -03:00

live

…

llm-security

…

load

…

manual

…

security

…

snapshots

Integration: security tier + self-hosted operator blockers (rebased onto v3.8.51) (#10952)

2026-08-23 16:51:25 -03:00

translator

…

unit

fix(models): expose Ollama Cloud native effort tiers (#11307)

2026-08-24 01:55:47 -03:00

_cp_mock_hook.mts

…

_cp_mock_module.mts

…

_run_dns_guard_test.sh

…

e2e-tool-calls.sh

…

theoldllm-stress.test.ts

…