ur-agent 1.27.6 → 1.28.0
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/CHANGELOG.md +21 -0
- package/dist/cli.js +1862 -1686
- package/docs/providers.md +6 -3
- package/package.json +1 -1
package/docs/providers.md
CHANGED
|
@@ -68,9 +68,9 @@ UR-AGENT shows providers first, then only models available for the selected prov
|
|
|
68
68
|
When you select a provider and model, every agent request is routed through that
|
|
69
69
|
provider's backend:
|
|
70
70
|
|
|
71
|
-
- **Subscription providers** spawn the official CLI command
|
|
72
|
-
- **API providers** make direct HTTP
|
|
73
|
-
- **Local/server providers** connect to the configured local or OpenAI-compatible endpoint
|
|
71
|
+
- **Subscription providers** spawn the official CLI command (e.g. `codex`, `claude`, `gemini`) in non-interactive mode, pass the prompt and the provider-scoped model, and map its stdout to the response. A non-zero exit or empty output fails clearly — it is never replaced with placeholder text.
|
|
72
|
+
- **API providers** make direct HTTP calls in each provider's native wire format: Anthropic uses `x-api-key` + `anthropic-version` against `/v1/messages`; OpenAI uses `Authorization: Bearer` against `/v1/chat/completions`; Gemini uses `x-goog-api-key` against `…:generateContent`; OpenRouter uses its OpenAI-compatible chat endpoint.
|
|
73
|
+
- **Local/server providers** connect to the configured local or OpenAI-compatible endpoint (`/v1/chat/completions` for LM Studio, llama.cpp and vLLM; the native tags/chat API for Ollama)
|
|
74
74
|
|
|
75
75
|
The selected provider determines:
|
|
76
76
|
- Which backend receives your requests
|
|
@@ -246,6 +246,9 @@ ur provider status
|
|
|
246
246
|
- OpenAI-compatible: verify base_url and API key (if required)
|
|
247
247
|
- Fallback only to same provider's cached models (never other providers)
|
|
248
248
|
|
|
249
|
+
**Saved local/server model rejected after restart:**
|
|
250
|
+
- A model saved via `/model` for a live-discovery provider (`ollama`, `lmstudio`, `llama.cpp`, `vllm`, `openai-compatible`) is accepted on a fresh process even before discovery has repopulated the in-memory model cache. The endpoint is the source of truth, so a saved model is not rejected pre-discovery. Static providers (API/subscription) remain strictly validated against their model list.
|
|
251
|
+
|
|
249
252
|
**Debug active runtime backend:**
|
|
250
253
|
```sh
|
|
251
254
|
ur provider status
|
package/package.json
CHANGED