@rayu-dev/rayu-cli 1.5.12 → 1.5.14

package/README.md

@@ -51,6 +51,51 @@ Or reinstall the latest directly:
 npm install -g @rayu-dev/rayu-cli
 ```
 
+Prefer `rayu update`: it resolves the latest version once, installs that **exact**
+version, and then verifies what actually landed on disk. A plain
+`npm install -g @rayu-dev/rayu-cli@latest` resolves the mutable `latest` tag a
+second time and can silently reinstall the version you already have when npm
+serves cached registry metadata (packuments are cached for 5 minutes), which
+looks like a successful update that changed nothing.
+
+When a newer version is published, Rayu shows a one-line notice above the prompt
+and in the welcome box at launch, with a link to
+[the changelog](https://rayucode.com/changelog). Nothing is installed until you
+run `rayu update` yourself.
+
+### Automatic updates (opt-in)
+
+Auto-updates are **off by default**. Rayu tells you an update exists but never
+replaces your install behind your back. To turn them on, set `autoUpdates` in
+`~/.rayu/config.json`:
+
+```json
+{
+  "autoUpdates": true
+}
+```
+
+To silence update checks and notices entirely:
+
+```bash
+export DISABLE_AUTOUPDATER=1
+```
+
+Two things to know before enabling automatic updates:
+
+- **Node version.** Rayu requires **Node.js 18 or newer**. npm only *warns* when
+  a package's `engines` requirement isn't met, so if a future release raises that
+  floor, an automatic update could replace a working install with one that
+  refuses to start until you upgrade Node. `rayu update` has the same
+  constraint, but you choose when it happens.
+- **Duplicate installs.** If Rayu is installed under two different npm prefixes
+  (for example once with `sudo`, landing in `/usr/local`, and once without,
+  landing in `~/.npm-global`), an update writes to whichever prefix npm is
+  configured for — which may not be the copy your shell actually runs. The result
+  is a "successful" update where `rayu --version` never changes. `rayu update`
+  detects this and tells you which copy is shadowing which; the automatic updater
+  does not. Run `which -a rayu` to check, and remove the copy you don't want.
+
 ---
 
 ## Uninstall
@@ -127,15 +172,27 @@ rayu --print --output-format json "list top-level folders" | jq .result
 
 ## Providers
 
-Rayu supports five provider types:
-
-| Provider | SDK / Method | Key env var |
-|----------|-------------|-------------|
-| **`anthropic`** | Anthropic SDK (`@anthropic-ai/sdk`) | `ANTHROPIC_API_KEY` |
-| **`openai-compatible`** | OpenAI SDK — NVIDIA, DeepSeek, Kimi, OpenRouter, Ollama, LM Studio, etc. | `RAYU_OPENAI_API_KEY` |
-| **`bedrock`** | AWS Bedrock SDK v3 | `AWS_BEARER_TOKEN_BEDROCK` or default AWS creds |
-| **`vertex`** | Google Gemini API via `@google/genai` | Google OAuth / ADC |
-| **`rayu-hosted`** | Proxied through rayu-gateway (requires RAYU OAuth login) | N/A (uses JWT auth) |
+Rayu speaks **four wire formats**, so one provider entry can serve models that use
+different protocols. Which format a request uses is decided per **model**, not per
+provider:
+
+| Provider | Models it serves | Wire format(s) | Auth |
+|----------|------------------|----------------|------|
+| **Anthropic** | Claude | Anthropic Messages | `ANTHROPIC_API_KEY` |
+| **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) |
+| **Microsoft Azure** | Claude **and** GPT deployments | Anthropic Messages for Claude, OpenAI Responses for the rest | `ANTHROPIC_FOUNDRY_API_KEY` / `AZURE_OPENAI_API_KEY` |
+| **Google Vertex AI** | Gemini, Claude, **and** Llama / Mistral / Qwen (MaaS) | GenAI, Anthropic Messages, OpenAI Chat | Google OAuth / ADC |
+| **OpenAI-compatible** | NVIDIA, DeepSeek, Kimi, OpenRouter, GLM, Ollama, LM Studio, … | OpenAI Chat | `RAYU_OPENAI_API_KEY` or per-provider key |
+| **Anthropic-compatible** | LongCat, Ollama Cloud | Anthropic Messages | Bearer key |
+| **GitHub Copilot** | Copilot models | OpenAI Chat | GitHub OAuth device flow |
+| **Kiro** | Claude via AWS CodeWhisperer | CodeWhisperer event-stream | API key or `kiro-cli` login |
+| **Rayu (hosted)** | Curated hosted models | Anthropic Messages | Your Rayu account (JWT) |
+| **Custom** | Anything you declare | **you pick**: OpenAI Chat, OpenAI Responses, or Anthropic Messages | your key |
+
+**Custom providers need no code change.** Run `/connect` → *Custom provider*, give
+it a name, pick the API format its endpoint speaks, enter the base URL, the model
+ids and your key. Declare whether it supports reasoning and images so Rayu never
+sends a parameter your endpoint would reject.
 
 **Google Gemini** is available three ways:
 1. **Gemini API key** (`GEMINI_API_KEY`) via the OpenAI-compatible endpoint