@inference-gateway/cli 0.187.0 → 0.189.0
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.
- package/README.md +18 -1
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -68,10 +68,11 @@ An agentic command-line assistant that writes code, understands project context,
|
|
|
68
68
|
- **Project Initialization**: Set up local project configurations
|
|
69
69
|
- **Tool Execution**: LLMs can execute allowed commands and tools - [See all tools →](docs/tools-reference.md)
|
|
70
70
|
- **Tool Approval System**: User approval workflow for sensitive operations with real-time diff visualization
|
|
71
|
-
- **Agent Modes**:
|
|
71
|
+
- **Agent Modes**: Four operational modes for different workflows:
|
|
72
72
|
- **Standard Mode** (default): Normal operation with all configured tools and approval checks
|
|
73
73
|
- **Plan Mode**: Read-only mode for planning and analysis without execution - [Learn more →](docs/plan-mode.md)
|
|
74
74
|
- **Auto-Accept Mode**: All tools auto-approved for rapid execution (YOLO mode)
|
|
75
|
+
- **Auto+Judge Mode**: No human approves tool calls - an LLM judge decides gated calls - [Learn more →](docs/judge-mode.md)
|
|
75
76
|
- Toggle between modes with **Shift+Tab**
|
|
76
77
|
- **Token Usage Tracking**: Accurate token counting with polyfill support for providers that don't return usage metrics
|
|
77
78
|
- **Cost Tracking**: Real-time cost calculation for API usage with per-model breakdown and configurable pricing
|
|
@@ -295,6 +296,21 @@ OPENAI_API_KEY=your_key_here
|
|
|
295
296
|
DEEPSEEK_API_KEY=your_key_here
|
|
296
297
|
```
|
|
297
298
|
|
|
299
|
+
Provider keys resolve in this order, first hit wins: the system environment, the
|
|
300
|
+
project `.env`, then the userspace fallback `~/.infer/auth.json` - a flat JSON
|
|
301
|
+
map of provider key env vars, so you can keep keys in one place across all
|
|
302
|
+
projects (or run `infer` outside any project):
|
|
303
|
+
|
|
304
|
+
```json
|
|
305
|
+
{
|
|
306
|
+
"ANTHROPIC_API_KEY": "sk-ant-...",
|
|
307
|
+
"OPENAI_API_KEY": "sk-..."
|
|
308
|
+
}
|
|
309
|
+
```
|
|
310
|
+
|
|
311
|
+
A missing `auth.json` changes nothing, and a malformed one is ignored with a
|
|
312
|
+
logged warning. Keep the file private (`chmod 600 ~/.infer/auth.json`).
|
|
313
|
+
|
|
298
314
|
3. **Start chatting**:
|
|
299
315
|
|
|
300
316
|
```bash
|
|
@@ -523,6 +539,7 @@ use the `gh` CLI through Bash (or the built-in `/scm` shortcuts) for GitHub oper
|
|
|
523
539
|
| **TodoWrite** | Create and manage task lists | No |
|
|
524
540
|
| **RequestPlanApproval** | Submit a plan for approval and persist it (plan mode) | No |
|
|
525
541
|
| **AskUserQuestion** | Ask the user multiple-choice questions (plan mode) | No |
|
|
542
|
+
| **RequestApproval** | Ask the user to override a judge rejection once (judge mode) | No |
|
|
526
543
|
|
|
527
544
|
**Web** (`WebSearch`/`WebFetch` need their respective config flag):
|
|
528
545
|
|