mirror of https://github.com/openclaw/openclaw.git synced 2026-09-28 14:12:28 +08:00

Files

T

History

Peter Steinberger 2f844f3e6d test(plugins,net-policy): remove low-value tests (batch d046) (#159181 )

* test(plugins): deslop s286 tests

* test(plugins): preserve Responses transport coverage

* test(kimi): deslop s292 tests

* test(llm-task): deslop s297 tests

* test(anthropic-vertex): deslop s289 tests

* test(zai): deslop s291 tests

* test(exa): deslop s300 tests

* test(runway): deslop s299 tests

* test(arcee): deslop s298 tests

* test(net-policy): deslop s295 tests

* test(plugins): retain catalog and public export coverage

2026-09-26 21:51:57 +00:00

assets

improve(plugins): give bundled logos consistent white icon tiles (#155259 )

2026-09-23 19:09:26 -07:00

api.ts

…

implicit-provider.test.ts

test(plugins,net-policy): remove low-value tests (batch d046) (#159181 )

2026-09-26 21:51:57 +00:00

index.test.ts

test(plugins,net-policy): remove low-value tests (batch d046) (#159181 )

2026-09-26 21:51:57 +00:00

index.ts

refactor(providers): deslop small provider plugins (#158437 )

2026-09-26 00:32:31 -07:00

kimi-coding.live.test.ts

refactor(models): preserve selected identities and centralize thinking policy (#150509 )

2026-09-16 20:18:50 -07:00

onboard.test.ts

test(plugins,net-policy): remove low-value tests (batch d046) (#159181 )

2026-09-26 21:51:57 +00:00

onboard.ts

refactor(providers): deslop small provider plugins (#158437 )

2026-09-26 00:32:31 -07:00

openclaw.plugin.json

feat(models): use the v2 catalog and price each route by who bills it (#156535 )

2026-09-24 21:20:57 +05:30

package.json

chore(release): close out 2026.9.6 on main (#156869 )

2026-09-23 23:02:54 -07:00

provider-catalog.test.ts

test(plugins,net-policy): remove low-value tests (batch d046) (#159181 )

2026-09-26 21:51:57 +00:00

provider-catalog.ts

fix(kimi): normalize legacy model IDs from manifest metadata (#146261 )

2026-09-12 11:00:50 -07:00

provider-policy-api.ts

fix(kimi): refresh K3 catalog and add 256K variant (#113918 )

2026-07-25 20:57:26 -07:00

README.md

fix(kimi): stop treating quota exhaustion as authentication failure (#142656 )

2026-09-09 08:16:50 +05:30

replay-policy.test.ts

…

replay-policy.ts

…

stream.test.ts

test(plugins,net-policy): remove low-value tests (batch d046) (#159181 )

2026-09-26 21:51:57 +00:00

stream.ts

fix: preserve thinking choices across models and runtimes (#150106 )

2026-09-16 10:56:40 -07:00

tsconfig.json

refactor(plugins): inherit shared package boundary settings (#117474 )

2026-08-01 09:11:09 -07:00

README.md

OpenClaw Kimi Coding Provider

Official OpenClaw provider plugin for Kimi Coding.

Install from OpenClaw:

openclaw plugins install @openclaw/kimi-provider
openclaw gateway restart

See https://docs.openclaw.ai/providers/moonshot for setup and configuration.

Quota errors

Kimi can return HTTP 403 when a weekly usage limit is exhausted. OpenClaw treats explicit weekly, seven-day, or quota-reset errors as rate limits. Wait for the provider's quota window to reset or use another configured provider; replacing a valid API key does not restore quota. Invalid keys and access restrictions keep their authentication error handling.

Catalog notes

Model rows live in openclaw.plugin.json under modelCatalog.providers.kimi.

k3 serves up to 1M context, tier-gated server-side; k3-256k is the cheaper 256K variant of the same weights. Both point at moonshot/kimi-k3 through upstreamModel, which keeps their compat capability tiers aligned with the moonshot catalog for the same model.
Legacy k3[1m] was retired upstream and normalizes to k3 for shipped configurations.
KIMI_K3_MODEL_IDS in provider-policy-api.ts must cover exactly the catalog rows that carry a K3 thinkingLevelMap; provider-catalog.test.ts asserts it.