savant-code 0.0.21 → 0.0.22
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 +11 -8
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -45,14 +45,17 @@ Or select one of the supported gateway providers directly:
|
|
|
45
45
|
|
|
46
46
|
| Provider | Selection | Environment variable | Notes |
|
|
47
47
|
| --- | --- | --- | --- |
|
|
48
|
-
|
|
49
|
-
| OpenRouter | `/provider openrouter` or `DIRECT_PROVIDER=openrouter` | `OR_MASTER_KEY`, `OPENROUTER_API_KEY`, or `INFERENCE_API_KEY` | Default provider; free tier (`openrouter/free`) is the boot default; direct mode without the Savant backend |
|
|
50
|
-
|
|
|
51
|
-
|
|
|
52
|
-
|
|
|
53
|
-
|
|
|
54
|
-
| CommandCode | `/provider commandcode` | `COMMAND_CODE_API_KEY` | OpenAI-compatible hosted inference |
|
|
55
|
-
|
|
|
48
|
+
<!-- GENERATED:provider-table-start -->
|
|
49
|
+
| OpenRouter | `/provider openrouter` or `DIRECT_PROVIDER=openrouter` | `OR_MASTER_KEY`, `OPENROUTER_API_KEY`, or `INFERENCE_API_KEY` | Default provider; free tier (`openrouter/free`) is the boot default; direct mode without the Savant backend |
|
|
50
|
+
| TokenRouter | `/provider tokenrouter` or `DIRECT_PROVIDER=tokenrouter` | `TOKENROUTER_API_KEY` | Multi-provider gateway |
|
|
51
|
+
| NVIDIA NIM | `/provider nvidia` or `DIRECT_PROVIDER=nvidia` | `NVIDIA_API_KEY` | NVIDIA-hosted inference |
|
|
52
|
+
| OpenCode Go | `/provider opencode-go` or `DIRECT_PROVIDER=opencode-go` | `OPENCODE_GO_API_KEY` | Hosted gateway (dual-protocol) |
|
|
53
|
+
| Cloudflare | Environment configuration | `CLOUDFLARE_API_TOKEN` + `CLOUDFLARE_ACCOUNT_ID` | Env-only — not in the `/provider` picker; requires the account id too |
|
|
54
|
+
| CommandCode | `/provider commandcode` or `DIRECT_PROVIDER=commandcode` | `COMMAND_CODE_API_KEY` | OpenAI-compatible hosted inference (dual-protocol) |
|
|
55
|
+
| Ollama | Automatic detection | `OLLAMA_HOST` (optional) | Local inference; no API key required |
|
|
56
|
+
| TokenHarbor | `/provider tokenharbor` or `DIRECT_PROVIDER=tokenharbor` | `TOKENHARBOR_API_KEY` | OpenAI-compatible hosted gateway |
|
|
57
|
+
| Custom endpoint | Environment configuration | `INFERENCE_BASE_URL`, `INFERENCE_API_KEY` | Advanced OpenAI-compatible endpoint |
|
|
58
|
+
<!-- GENERATED:provider-table-end -->
|
|
56
59
|
|
|
57
60
|
The interactive key prompt is masked. Saved provider credentials are stored in the user configuration directory and are not added to chat history:
|
|
58
61
|
|