@inference-gateway/cli 0.202.2 → 0.203.0

package/README.md

@@ -297,19 +297,17 @@ DEEPSEEK_API_KEY=your_key_here
 ```
 
 Provider keys resolve in this order, first hit wins: the system environment, the
-project `.env`, then the userspace fallback `~/.infer/auth.json` - a flat JSON
+project `.env`, then the userspace fallback `~/.infer/auth.yaml` - a flat YAML
 map of provider key env vars, so you can keep keys in one place across all
 projects (or run `infer` outside any project):
 
-```json
-{
-  "ANTHROPIC_API_KEY": "sk-ant-...",
-  "OPENAI_API_KEY": "sk-..."
-}
+```yaml
+ANTHROPIC_API_KEY: sk-ant-...
+OPENAI_API_KEY: sk-...
 ```
 
-A missing `auth.json` changes nothing, and a malformed one is ignored with a
-logged warning. Keep the file private (`chmod 600 ~/.infer/auth.json`).
+A missing `auth.yaml` changes nothing, and a malformed one is ignored with a
+logged warning. Keep the file private (`chmod 600 ~/.infer/auth.yaml`).
 
 3. **Start chatting**:
 
@@ -918,6 +916,12 @@ actions.
 
 - `/new [title]` - Start a new conversation (optionally titled)
 - `/clear` - Save the current conversation and start a new one
+- `/insights [since]` - Analyze past sessions for repeatable workflows worth a skill and recurring tool failures; saves a report to `~/.infer/insights/`
+- `/reset [insights|confirm]` - Wipe the local runtime state (conversations, plans, scratch, artifacts, history, backups, exports, logs) of
+  **every project on this machine** and start a fresh session.
+  `/reset insights` analyzes the sessions first and previews the wipe.
+  `/reset confirm` performs it, but only after a preview in the same session - a cold `/reset confirm` previews instead of deleting.
+  Config and saved insights are preserved, remote stores are skipped.
 - `/compact` - Save the conversation and start a new session seeded with a summary
 - `/conversations` - Open the conversation selection dropdown
 - `/context` - Show context-window usage
@@ -956,7 +960,6 @@ actions.
 
 - `/scm issues` - List GitHub issues
 - `/scm issue <number>` - Show issue details
-- `/scm pr-create [context]` - Generate AI-powered PR plan
 
 **Other Shortcuts** (created by `infer init`):
 
@@ -1409,8 +1412,8 @@ infer chat
 # - Make changes
 # - Run tests
 
-# Generate PR plan when ready
-/scm pr-create Fixes the authentication timeout issue
+# Ask the agent to open the PR when ready
+> Create a pull request for these changes - it fixes the authentication timeout issue
 ```
 
 ### Configuration Example

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@inference-gateway/cli",
-  "version": "0.202.2",
+  "version": "0.203.0",
   "description": "A Git-first CLI coding agent that turns ideas, issues, and tasks into real code changes.",
   "bin": {
     "infer": "bin/run.js"