vrr/openclaw
2
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-07-09 15:59:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 22

feat(cohere): add current Command models (#102563)

Browse source 
* feat(cohere): add current Command models

* docs: keep release notes out of PR
This commit is contained in:
Peter Steinberger 2026-07-09 11:07:50 +01:00 • committed by GitHub
parent 5cb5f38144
commit fc5a4defaf
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
13 changed files with 223 additions and 28 deletions
Download patch file Download diff file Expand all files Collapse all files

4
docs/concepts/model-providers.md
View file

@ -205,7 +205,7 @@ Claude CLI reuse (`claude -p`) is a sanctioned OpenClaw integration path. Anthro
- Provider: `google`
- Auth: `GEMINI_API_KEY`
- Optional rotation: `GEMINI_API_KEYS`, `GEMINI_API_KEY_1`, `GEMINI_API_KEY_2`, `GOOGLE_API_KEY` fallback, and `OPENCLAW_LIVE_GEMINI_KEY` (single override)
- Example models: `google/gemini-3.1-pro-preview`, `google/gemini-3-flash-preview`
- Example models: `google/gemini-3.1-pro-preview`, `google/gemini-3.5-flash`
- Compatibility: legacy OpenClaw config using `google/gemini-3.1-flash-preview` is normalized to `google/gemini-3-flash-preview`
- Alias: `google/gemini-3.1-pro` is accepted and normalized to Google's live Gemini API id, `google/gemini-3.1-pro-preview`
- CLI: `openclaw onboard --auth-choice gemini-api-key`
@ -285,7 +285,7 @@ messages and normalizes `stats.cached` into `cacheRead`; legacy
| Cerebras | `cerebras` | `CEREBRAS_API_KEY` | `cerebras/zai-glm-4.7` |
| Chutes | `chutes` | `CHUTES_API_KEY` or `CHUTES_OAUTH_TOKEN` | `chutes/zai-org/GLM-4.7-TEE` |
| ClawRouter | `clawrouter` | `CLAWROUTER_API_KEY` | `clawrouter/anthropic/claude-sonnet-4-6` |
| Cohere | `cohere` | `COHERE_API_KEY` | `cohere/command-a-03-2025` |
| Cohere | `cohere` | `COHERE_API_KEY` | `cohere/command-a-plus-05-2026` |
| DeepInfra | `deepinfra` | `DEEPINFRA_API_KEY` | `deepinfra/deepseek-ai/DeepSeek-V4-Flash` |
| DeepSeek | `deepseek` | `DEEPSEEK_API_KEY` | `deepseek/deepseek-v4-flash` |
| Featherless AI | `featherless` | `FEATHERLESS_API_KEY` | `featherless/Qwen/Qwen3-32B` |

11
docs/help/testing-live.md
View file

@ -360,13 +360,13 @@ Narrow, explicit allowlists are fastest and least flaky:
- `OPENCLAW_LIVE_GATEWAY_MODELS="openai/gpt-5.5" pnpm test:live src/gateway/gateway-models.profiles.live.test.ts`
- Tool calling across several providers:
- `OPENCLAW_LIVE_GATEWAY_MODELS="openai/gpt-5.5,anthropic/claude-opus-4-6,google/gemini-3-flash-preview,deepseek/deepseek-v4-flash,zai/glm-5.1,minimax/MiniMax-M3" pnpm test:live src/gateway/gateway-models.profiles.live.test.ts`
- `OPENCLAW_LIVE_GATEWAY_MODELS="openai/gpt-5.5,anthropic/claude-opus-4-6,google/gemini-3.5-flash,deepseek/deepseek-v4-flash,zai/glm-5.1,minimax/MiniMax-M3" pnpm test:live src/gateway/gateway-models.profiles.live.test.ts`
- Z.AI Coding Plan GLM-5.2 direct smoke:
- `ZAI_CODING_LIVE_TEST=1 pnpm test:live src/agents/zai.live.test.ts`
- Google focus (Gemini API key + Antigravity):
- Gemini (API key): `OPENCLAW_LIVE_GATEWAY_MODELS="google/gemini-3-flash-preview" pnpm test:live src/gateway/gateway-models.profiles.live.test.ts`
- Gemini (API key): `OPENCLAW_LIVE_GATEWAY_MODELS="google/gemini-3.5-flash" pnpm test:live src/gateway/gateway-models.profiles.live.test.ts`
- Antigravity (OAuth): `OPENCLAW_LIVE_GATEWAY_MODELS="google-antigravity/claude-opus-4-6-thinking,google-antigravity/gemini-3-pro-high" pnpm test:live src/gateway/gateway-models.profiles.live.test.ts`
- Google adaptive thinking smoke (`qa manual` from the private QA CLI - requires `OPENCLAW_ENABLE_PRIVATE_QA_CLI=1` and a source checkout; see [QA overview](/concepts/qa-e2e-automation)):
@ -389,10 +389,12 @@ Live is opt-in, so there is no fixed "CI model list." `OPENCLAW_LIVE_MODELS=mode
| Provider/model | Notes |
| --------------------------------------------- | ---------- |
| `anthropic/claude-opus-4-8` | |
| `anthropic/claude-sonnet-5` | |
| `anthropic/claude-sonnet-4-6` | |
| `anthropic/claude-opus-4-7` | |
| `google/gemini-3.1-pro-preview` | Gemini API |
| `google/gemini-3-flash-preview` | Gemini API |
| `google/gemini-3.5-flash` | Gemini API |
| `cohere/command-a-plus-05-2026` | |
| `moonshot/kimi-k2.7-code` | |
| `anthropic/claude-opus-4-6` | |
| `deepseek/deepseek-v4-flash` | |
@ -404,6 +406,7 @@ Live is opt-in, so there is no fixed "CI model list." `OPENCLAW_LIVE_MODELS=mode
| `opencode-go/glm-5` | |
| `openrouter/ai21/jamba-large-1.7` | |
| `xai/grok-4.5` | |
| `xai/grok-4.20-0309-reasoning` | |
| `zai/glm-5.1` | |
| `fireworks/accounts/fireworks/models/glm-5p1` | |
| `minimax-portal/minimax-m3` | |
@ -430,7 +433,7 @@ Notes on the modern list:
Run gateway smoke with tools + image across a hand-picked cross-provider set:
```bash
OPENCLAW_LIVE_GATEWAY_MODELS="openai/gpt-5.5,anthropic/claude-opus-4-6,google/gemini-3.1-pro-preview,google/gemini-3-flash-preview,google-antigravity/claude-opus-4-6-thinking,deepseek/deepseek-v4-flash,zai/glm-5.1,minimax/MiniMax-M3" pnpm test:live src/gateway/gateway-models.profiles.live.test.ts
OPENCLAW_LIVE_GATEWAY_MODELS="openai/gpt-5.5,anthropic/claude-opus-4-6,google/gemini-3.1-pro-preview,google/gemini-3.5-flash,google-antigravity/claude-opus-4-6-thinking,deepseek/deepseek-v4-flash,zai/glm-5.1,minimax/MiniMax-M3" pnpm test:live src/gateway/gateway-models.profiles.live.test.ts
```
Optional additional coverage outside the curated lists (nice to have, pick a "tools"-capable model you have enabled):

19
docs/providers/cohere.md
View file

@ -17,17 +17,20 @@ read_when:
| Direct CLI flag | `--cohere-api-key <key>` |
| API | OpenAI-compatible (`openai-completions`) |
| Base URL | `https://api.cohere.ai/compatibility/v1` |
| Default model | `cohere/command-a-03-2025` |
| Context window | 256,000 tokens |
| Default model | `cohere/command-a-plus-05-2026` |
| Context window | 128,000 tokens |
## Built-in catalog
| Model ref | Input | Context | Max output | Notes |
| ---------------------------- | ----------- | ------- | ---------- | -------------------------------------- |
| `cohere/command-a-03-2025` | text | 256,000 | 8,000 | Default model |
| `cohere/north-mini-code-1-0` | text, image | 256,000 | 64,000 | Agentic coding; reasoning; free limits |
| Model ref | Input | Context | Max output | Notes |
| ------------------------------------ | ----------- | ------- | ---------- | --------------------------------------------- |
| `cohere/command-a-plus-05-2026` | text, image | 128,000 | 64,000 | Default; flagship agentic and reasoning model |
| `cohere/command-a-03-2025` | text | 256,000 | 8,000 | Previous Command A model |
| `cohere/command-a-reasoning-08-2025` | text | 256,000 | 32,000 | Agentic reasoning and tool use |
| `cohere/command-a-vision-07-2025` | text, image | 128,000 | 8,000 | Vision and document analysis; no tool use |
| `cohere/north-mini-code-1-0` | text, image | 256,000 | 64,000 | Agentic coding; reasoning; free limits |
North Mini Code supports Cohere's two Compatibility API reasoning modes. OpenClaw maps **off** to `none` and every enabled thinking level to `high`.
Reasoning-capable Cohere models support two Compatibility API reasoning modes. OpenClaw maps **off** to `none` and every enabled thinking level to `high`. Command A Vision does not support tool use, so OpenClaw keeps agent tools disabled for that model.
## Get started
@ -63,7 +66,7 @@ Make `COHERE_API_KEY` available to the Gateway process, then select the Cohere m
{
agents: {
defaults: {
model: { primary: "cohere/command-a-03-2025" },
model: { primary: "cohere/command-a-plus-05-2026" },
},
},
}