ur-agent 1.85.0 → 1.85.2

package/CHANGELOG.md

@@ -1,5 +1,49 @@
 # Changelog
 
+## 1.85.2
+
+- Made NVIDIA Special selections directly executable from the next prompt. UR
+  now sends focused image, video, audio, vision, retrieval, and other one-shot
+  jobs through the selected model's exact NVIDIA inference contract without
+  invoking or depending on the ongoing Anthropic, OpenAI, Ollama, or other
+  conversation provider. Structured prompt, file, passage, output-path, and
+  exact-JSON inputs are accepted, and missing required media produces targeted
+  guidance instead of an unrelated provider error.
+- Restored reliable model switching across providers. Provider and model now
+  change atomically, selecting an ordinary model exits NVIDIA Special mode,
+  provider-scoped models take precedence over stale legacy global settings,
+  and a saved model from one backend can no longer be paired accidentally with
+  another backend.
+- Added NVIDIA Special to first-run and new-folder provider selection while
+  keeping a normal agent model available for the conversation, and made the
+  active focused-task model visible in the status line. Updated public,
+  troubleshooting, provider, validation, and technical documentation, with
+  end-to-end regression coverage proving focused tasks bypass the conversation
+  provider and stale provider/model pairs recover correctly.
+- Refreshed the locked `fast-uri` dependency to its compatible 3.1.6 release so
+  the production dependency audit remains clean without changing runtime policy.
+
+## 1.85.1
+
+- Added complete Anthropic workspace routing for identity-linked Claude API
+  keys. A validated workspace ID can be configured with
+  `anthropic.workspace_id`, `ANTHROPIC_WORKSPACE_ID`, or
+  `ur connect anthropic-api --workspace-id`; UR applies the matching header to
+  model discovery, diagnostics, streaming and non-streaming Messages requests,
+  and token counting while leaving workspace-scoped keys unchanged.
+- Preserved Anthropic's real missing-workspace response and replaced the
+  misleading provider/model compatibility failure with an actionable setup
+  instruction. Live model caches are partitioned by workspace so one workspace
+  cannot reuse another workspace's catalog.
+- Made OpenAI permanent account failures fail immediately instead of looking
+  like slow inference. Streaming HTTP error bodies are decoded safely, exact
+  provider error codes such as `billing_not_active` and `insufficient_quota`
+  are treated as non-retryable, and genuine transient rate limits continue to
+  use retry and backoff behavior.
+- Isolated provider-discovery tests from live keychain credentials and updated
+  public, configuration, troubleshooting, validation, provider, and technical
+  documentation for both behaviors.
+
 ## 1.85.0
 
 - Split NVIDIA Build into two truthful provider surfaces backed by one saved

package/README.md

@@ -299,6 +299,7 @@ ur config set provider.fallback ollama
 ur config set openrouter.routing auto
 ur config set openrouter.preferred_min_throughput 40
 ur config set openrouter.preferred_max_latency 3
+ur config set anthropic.workspace_id wrkspc_...
 ```
 
 `provider.fallback` records a recovery provider for `ur provider doctor`
@@ -332,6 +333,11 @@ store records identifiers and status only. Compacted context is persisted only
 when `UR_OPENAI_RESPONSES_STATE_KEY` contains a 32-byte encryption key. Return
 to the default with `ur config set openai_transport chat-completions`.
 
+Both OpenAI transports retry genuine temporary rate limits. Permanent
+machine-coded account or billing responses such as `billing_not_active` and
+`insufficient_quota` are reported immediately, so an inactive project does not
+look like minute-long model latency.
+
 OpenRouter `auto` routing leaves tool turns to Auto Exacto and optimizes
 non-tool turns for end-to-end throughput. The routing, fallback,
 strict-parameter, rolling performance preference, service-tier, and supported
@@ -351,6 +357,21 @@ ur config set openrouter.speed fast            # standard | fast
 Direct Anthropic requests automatically preserve UR's prompt-cache
 breakpoints and enable per-tool fine-grained input streaming, reducing repeat
 prefill work and exposing large tool arguments as Claude generates them.
+Anthropic identity-linked keys that can act across workspaces also require a
+workspace on discovery, inference, streaming, and token-count calls. Configure
+the Console workspace ID once (it is not a secret):
+
+```sh
+ur config set anthropic.workspace_id wrkspc_...
+# or for one environment:
+export ANTHROPIC_WORKSPACE_ID=wrkspc_...
+```
+
+UR sends `anthropic-workspace-id` only when configured. Workspace-scoped keys
+continue to work without it. Use `auto` to clear the saved selection. If the
+key and workspace are being connected together, `ur connect anthropic-api
+--workspace-id wrkspc_...` accepts the same value.
+
 Anthropic's premium research-preview fast tier is opt-in and is sent only for
 Claude Opus 5 or Opus 4.8:
 
@@ -380,7 +401,7 @@ ur connect logout openai-api          # clear a stored key
 | Provider | Access type | Runtime kind | Legal path |
 | --- | --- | --- | --- |
 | OpenAI API | API key | UR-native | `OPENAI_API_KEY` or `ur connect openai-api` |
-| Claude API | API key | UR-native | `ANTHROPIC_API_KEY` or `ur connect anthropic-api` |
+| Claude API | API key | UR-native | `ANTHROPIC_API_KEY` or `ur connect anthropic-api`; identity-linked keys also use `ANTHROPIC_WORKSPACE_ID` or `anthropic.workspace_id` |
 | Gemini API | API key | UR-native | `GEMINI_API_KEY` or `ur connect gemini-api` |
 | OpenRouter | API/router | UR-native | `OPENROUTER_API_KEY` or `ur connect openrouter` |
 | NVIDIA Agentic | hosted/server API | UR-native | `NVIDIA_API_KEY` or `ur connect nvidia-nim`; configurable `base_url` |
@@ -431,6 +452,13 @@ In the interactive app, `/model` is a two-step, provider-first picker:
    UR supports direct HTTP, model-specific NVCF invocation, NVIDIA Assets,
    asynchronous polling, and the five documented Maxine/Riva gRPC services;
    artifacts are written under `.ur/artifacts/nvidia/` unless a path is supplied.
+   Selecting a Special row activates a real task mode: the next non-command
+   prompt goes directly to that card's inference endpoint and never passes
+   through the ongoing Anthropic, OpenAI, Ollama, or other chat provider. Plain
+   text becomes `prompt`. Models requiring media accept newline fields such as
+   `video_path: /path/source.mp4` or `image_path: /path/image.png`; exact JSON is
+   also accepted. First-workspace setup shows NVIDIA Special too, then returns
+   to the provider list so an ordinary agent model can be chosen for other work.
 
    In the model catalog, use **Up/Down** to browse. For graded models, the effort row updates to
    the focused model's capability-backed selectors; use **Left/Right** to cycle
@@ -502,7 +530,9 @@ identity line in the system prompt reflects it too:
   documented hosted chat endpoint or a user-selected compatible NIM gateway.
   NVIDIA Special uses each card's documented HTTP, direct NVCF, or gRPC
   endpoint with the same stored `NVIDIA_API_KEY`; asynchronous jobs are polled
-  through NVIDIA's request ID until completion or user cancellation.
+  through NVIDIA's request ID until completion or user cancellation. While a
+  Special task is selected, the next plain prompt is dispatched directly and
+  does not require the ongoing agent provider to be connected.
 - **Local/server** providers call the configured endpoint (`/v1/chat/completions`
   for LM Studio/llama.cpp/vLLM/Unsloth; the native API for Ollama). Unsloth is
   provider-only: UR never starts, installs, updates, trains, or loads models in