NVIDIAN 797d574dfd fix(deepseek): expose V4 max thinking levels (#73008) ...

Merged via squash.

Prepared head SHA: ef561a59de
Co-authored-by: ai-hpc <183861985+ai-hpc@users.noreply.github.com>
Co-authored-by: hxy91819 <8814856+hxy91819@users.noreply.github.com>
Reviewed-by: @hxy91819

2026-04-30 23:34:05 +08:00

..

api.ts

…

deepseek.live.test.ts

fix(deepseek): backfill v4 assistant reasoning replay

2026-04-28 10:07:39 +01:00

index.test.ts

fix(deepseek): expose V4 max thinking levels (#73008)

2026-04-30 23:34:05 +08:00

index.ts

fix(deepseek): expose V4 max thinking levels (#73008)

2026-04-30 23:34:05 +08:00

models.ts

fix(deepseek): expose V4 max thinking levels (#73008)

2026-04-30 23:34:05 +08:00

onboard.ts

…

openclaw.plugin.json

perf: mark provider plugins startup lazy

2026-04-28 04:33:47 +01:00

package.json

chore: bump version to 2026.4.25

2026-04-25 10:31:52 +01:00

provider-catalog.ts

…

provider-discovery.ts

…

provider-policy-api.test.ts

fix(deepseek): add provider-policy-api to hydrate contextWindow and cost from catalog (#74326)

2026-04-29 22:38:11 +10:00

provider-policy-api.ts

fix(deepseek): add provider-policy-api to hydrate contextWindow and cost from catalog (#74326)

2026-04-29 22:38:11 +10:00

stream.ts

fix(deepseek): expose V4 max thinking levels (#73008)

2026-04-30 23:34:05 +08:00

tsconfig.json

…