@ours.network/mcp 0.14.1 → 0.15.0

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 CHANGED
@@ -30,13 +30,16 @@ Voice transcription is off until a provider and key (plus provider-required fiel
30
30
  configured. Check readiness without exposing credentials:
31
31
 
32
32
  ```sh
33
+ ours-mcp voice-setup
33
34
  ours-mcp voice-status --json
34
35
  ```
35
36
 
36
- Run `ours-install` interactively for guided, masked setup. It writes the config atomically
37
- with mode `0600` and rolls back if the daemon cannot reload it. For environment-only service
38
- configuration use `OURS_STT_PROVIDER`, `OURS_STT_API_KEY`, `OURS_STT_MODEL`,
39
- `OURS_STT_BASE_URL`, and `OURS_STT_LANGUAGE`; environment values override file fields.
37
+ `voice-setup` presents a keyboard-driven single-choice provider selector and reads the
38
+ provider key with hidden input. It writes config atomically with mode `0600`, preserves
39
+ unrelated fields, and rolls back if the managed daemon cannot restart and report ready.
40
+ It never accepts a key in command arguments. For environment-only service configuration
41
+ use `OURS_STT_PROVIDER`, `OURS_STT_API_KEY`, `OURS_STT_MODEL`, `OURS_STT_BASE_URL`, and
42
+ `OURS_STT_LANGUAGE`; environment values override file fields.
40
43
 
41
44
  The supported providers are `openai-compatible` (explicit base URL + model),
42
45
  `elevenlabs` (model), `deepgram`, and `custom` (`stt.custom.url`). Incoming voice remains