@inference-gateway/cli 0.183.4 → 0.184.0
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 +13 -0
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -94,6 +94,8 @@ An agentic command-line assistant that writes code, understands project context,
|
|
|
94
94
|
- **Remote Messaging Channels**: Control the agent from Telegram, WhatsApp, and other platforms via a pluggable channel system - [Learn more →](docs/channels.md)
|
|
95
95
|
- **Speech-to-Text (Whisper)**: Dictate into chat with `/voice` and transcribe inbound Telegram voice messages, locally and offline -
|
|
96
96
|
off by default - [Learn more →](docs/speech-to-text.md)
|
|
97
|
+
- **Text-to-Speech (Qwen3-TTS)**: Turn text into a spoken WAV locally and offline, with zero-shot voice cloning
|
|
98
|
+
from a short reference recording - off by default - [Learn more →](docs/text-to-speech.md)
|
|
97
99
|
- **Scheduled Tasks**: Ask the agent (over Telegram, etc.) to run a prompt on a cron schedule and deliver the result back through the same channel -
|
|
98
100
|
recurring ("send me a quote every morning") or one-off ("remind me at 6pm today") - [Learn more →](docs/scheduling.md)
|
|
99
101
|
- **Heartbeat (Periodic Wake-Up)**: Wake the agent on a fixed interval to check for pending todos and background work,
|
|
@@ -545,6 +547,15 @@ use the `gh` CLI through Bash (or the built-in `/scm` shortcuts) for GitHub oper
|
|
|
545
547
|
| **Computer** | Read the accessibility tree, press labelled controls, capture screenshots, and control mouse/keyboard | Configurable |
|
|
546
548
|
| **GetLatestFrame** | Read the latest frame from a named source (screen, camera directory) | No |
|
|
547
549
|
|
|
550
|
+
**Media** (each gated by its own flag; all output is written to disk, never played aloud):
|
|
551
|
+
|
|
552
|
+
| Tool | Purpose | Approval | Enabled by |
|
|
553
|
+
| ------ | --------- | ---------- | ------------ |
|
|
554
|
+
| **ImageGeneration** | Generate an image from a prompt into `.infer/artifacts/` | No | `tools.image_generation.enabled` |
|
|
555
|
+
| **ImageEdit** | Edit an existing image and save the result | No | `tools.image_edit.enabled` |
|
|
556
|
+
| **ImageVariation** | Produce a variation of an existing image | No | `tools.image_variation.enabled` |
|
|
557
|
+
| **TextToSpeech** | Synthesize speech to a WAV locally, optionally cloning a voice | No | `text_to_speech.enabled` |
|
|
558
|
+
|
|
548
559
|
**Memory, scheduling & A2A** (each gated by its own flag):
|
|
549
560
|
|
|
550
561
|
| Tool | Purpose | Approval | Enabled by |
|
|
@@ -829,6 +840,8 @@ approval**; override per tool with `tools.<name>.require_approval`.
|
|
|
829
840
|
| Wait | No | Passive utility - blocks until condition met, no side effects |
|
|
830
841
|
| Read, Grep, Tree | No | Read-only operations |
|
|
831
842
|
| Memory, TodoWrite | No | Local agent state (explicitly exempt) |
|
|
843
|
+
| Image tools | No | Output confined to `.infer/artifacts/` - override with `tools.<name>.require_approval` |
|
|
844
|
+
| TextToSpeech | No | Output confined to `text_to_speech.output_dir` - override with `text_to_speech.require_approval` |
|
|
832
845
|
| Computer-use tools | No | Run silently in the background |
|
|
833
846
|
| A2A_QueryAgent, A2A_QueryTask | No | Read-only A2A queries |
|
|
834
847
|
|