@rayu-dev/rayu-cli 1.5.13 → 1.5.14

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (4) hide show
  1. package/README.md +21 -9
  2. package/dist/rayu.js +56930 -51786
  3. package/package.json +1 -1
  4. package/scripts/postinstall.cjs +15 -0
package/README.md CHANGED
@@ -172,15 +172,27 @@ rayu --print --output-format json "list top-level folders" | jq .result
172
172
 
173
173
  ## Providers
174
174
 
175
- Rayu supports five provider types:
176
-
177
- | Provider | SDK / Method | Key env var |
178
- |----------|-------------|-------------|
179
- | **`anthropic`** | Anthropic SDK (`@anthropic-ai/sdk`) | `ANTHROPIC_API_KEY` |
180
- | **`openai-compatible`** | OpenAI SDK — NVIDIA, DeepSeek, Kimi, OpenRouter, Ollama, LM Studio, etc. | `RAYU_OPENAI_API_KEY` |
181
- | **`bedrock`** | AWS Bedrock SDK v3 | `AWS_BEARER_TOKEN_BEDROCK` or default AWS creds |
182
- | **`vertex`** | Google Gemini API via `@google/genai` | Google OAuth / ADC |
183
- | **`rayu-hosted`** | Proxied through rayu-gateway (requires RAYU OAuth login) | N/A (uses JWT auth) |
175
+ Rayu speaks **four wire formats**, so one provider entry can serve models that use
176
+ different protocols. Which format a request uses is decided per **model**, not per
177
+ provider:
178
+
179
+ | Provider | Models it serves | Wire format(s) | Auth |
180
+ |----------|------------------|----------------|------|
181
+ | **Anthropic** | Claude | Anthropic Messages | `ANTHROPIC_API_KEY` |
182
+ | **AWS Bedrock** | Claude **and** gpt-oss / qwen / deepseek / mistral / … | Anthropic Messages for Claude, OpenAI Chat for the rest | `AWS_BEARER_TOKEN_BEDROCK` (Bedrock API key) |
183
+ | **Microsoft Azure** | Claude **and** GPT deployments | Anthropic Messages for Claude, OpenAI Responses for the rest | `ANTHROPIC_FOUNDRY_API_KEY` / `AZURE_OPENAI_API_KEY` |
184
+ | **Google Vertex AI** | Gemini, Claude, **and** Llama / Mistral / Qwen (MaaS) | GenAI, Anthropic Messages, OpenAI Chat | Google OAuth / ADC |
185
+ | **OpenAI-compatible** | NVIDIA, DeepSeek, Kimi, OpenRouter, GLM, Ollama, LM Studio, … | OpenAI Chat | `RAYU_OPENAI_API_KEY` or per-provider key |
186
+ | **Anthropic-compatible** | LongCat, Ollama Cloud | Anthropic Messages | Bearer key |
187
+ | **GitHub Copilot** | Copilot models | OpenAI Chat | GitHub OAuth device flow |
188
+ | **Kiro** | Claude via AWS CodeWhisperer | CodeWhisperer event-stream | API key or `kiro-cli` login |
189
+ | **Rayu (hosted)** | Curated hosted models | Anthropic Messages | Your Rayu account (JWT) |
190
+ | **Custom** | Anything you declare | **you pick**: OpenAI Chat, OpenAI Responses, or Anthropic Messages | your key |
191
+
192
+ **Custom providers need no code change.** Run `/connect` → *Custom provider*, give
193
+ it a name, pick the API format its endpoint speaks, enter the base URL, the model
194
+ ids and your key. Declare whether it supports reasoning and images so Rayu never
195
+ sends a parameter your endpoint would reject.
184
196
 
185
197
  **Google Gemini** is available three ways:
186
198
  1. **Gemini API key** (`GEMINI_API_KEY`) via the OpenAI-compatible endpoint