ur-agent 1.84.5 → 1.84.6

package/docs/AGENT_FEATURES.md

@@ -349,7 +349,8 @@ automatically changes the active provider.
 | Provider-aware status bar | Interactive bottom status bar, `src/components/StatusLine.tsx`, `src/utils/statusBar.ts` | Shows only important runtime state: active provider, selected model, mode, git branch, active task state, checks/build state when known, and update availability. Hidden in CI, dumb terminals, and non-interactive mode; custom status-line hooks still override it. |
 | Clean update checks | `ur upgrade`, `ur update`, `src/cli/update.ts` | Detects development/source checkouts and prints a short pull-or-install message instead of attempting self-mutation. npm-installed builds compare the local version with `ur-agent` on npm and print update, latest, registry failure, and malformed-response states without stale planning text. |
 | Bundled IDE extension install | `extensions/vscode-ur-inline-diffs/`, `src/utils/ide.ts`, `ur ide diff` | Public VS Code install now packages the repo's bundled inline-diffs extension as a local VSIX instead of trying an unpublished marketplace ID. The extension remains local-only and reviews `.ur/ide/diffs` bundles from the current workspace. |
-| Professional clarification dialogs | `AskUserQuestion`, `src/tools/AskUserQuestionTool/AskUserQuestionTool.tsx` | Supports up to eight concrete options, infers labels from description-only option objects, accepts prompt aliases, deduplicates equivalent labels, safely repairs single-suggestion payloads with a neutral rejection choice, and is loaded without ToolSearch preloading so typed schemas are available before use. |
+| Professional clarification dialogs | `AskUserQuestion`, `src/tools/AskUserQuestionTool/AskUserQuestionTool.tsx` | Mandatory for every question with concrete choices; plain text is reserved for genuinely open-ended answers. Prefers 2-8 focused options but preserves larger legitimate menus, infers labels from description-only objects, accepts prompt aliases, deduplicates equivalent labels, safely repairs single suggestions with a neutral rejection choice, and is loaded without ToolSearch preloading. |
+| NVIDIA agent/task split | `nvidiaHostedModels.ts`, `NvidiaNimTask`, `/model` | Positively audits hosted agent contracts and exposes a one-shot model only when the live account catalog returns it and a complete adapter exists (FLUX.1 Schnell, Stable Video Diffusion, or PaliGemma). Task selection shows purpose and never replaces the ongoing agent. |
 | Documentation release sync | `README.md`, `docs/`, `documentation/`, `CHANGELOG.md` | Keeps the npm README, static documentation site, provider guide, usage guide, feature ledger, validation runbook, and release notes aligned with current release behavior. |
 
 ## v1.24.0 Additions

package/docs/CONFIGURATION.md

@@ -282,10 +282,11 @@ UNSLOTH_API_KEY=...
 
 NVIDIA NIM defaults to `https://integrate.api.nvidia.com/v1`, discovers the
 connected account's models live, and accepts a provider-scoped override for an
-enterprise or self-hosted NIM. On NVIDIA's hosted endpoint, UR treats the
-documented `/v1/models` response as authoritative and omits non-agent utility
-endpoints. It does not narrow hosted models using the separate NVCF deployment
-inventory; a configured NIM gateway uses its own model feed. Generic
+enterprise or self-hosted NIM. On NVIDIA's hosted endpoint, `/v1/models`
+establishes account availability and UR's audited positive contract registry
+establishes agent compatibility; only their intersection can become the
+ongoing model. It does not narrow hosted models using the separate NVCF
+deployment inventory; a configured NIM gateway uses its own model feed. Generic
 `openai-compatible` authentication is
 optional: `ur connect openai-compatible` or the picker's `K` key stores a
 credential when the chosen gateway needs one, without breaking anonymous
@@ -296,6 +297,10 @@ hosted choices unless the authenticated `/v1/models` endpoint returns them.
 For the hosted service, UR focuses NVIDIA's documented fastest 30B agent model,
 `nvidia/nemotron-3.5-lightning-30b-a3b`, first. Its thinking toggle maps to
 NVIDIA's model-specific `chat_template_kwargs.enable_thinking` field.
+The same key also authorizes the separately labelled one-shot FLUX.1 Schnell,
+Stable Video Diffusion, and PaliGemma adapters. Those use their exact
+`ai.api.nvidia.com` paths, never replace `provider.model`, and write generated
+media under `.ur/artifacts/nvidia/` unless an output path is supplied.
 
 Unsloth is an inference-provider integration only. Start Unsloth Studio and
 load the model outside UR, connect its generated key with `ur connect unsloth`,

package/docs/TROUBLESHOOTING.md

@@ -215,8 +215,8 @@ custom `base_url` scoped to that provider.
 - Cause: NVIDIA's hosted `/v1/models` feed can change, or a listed model's
   backing function can become unavailable for the connected account.
 - Fix: upgrade UR, run `ur provider doctor nvidia-nim`, then open `/model` and
-  press `Ctrl+R`. Hosted discovery uses NVIDIA's documented `/v1/models`
-  endpoint and excludes non-agent utility endpoints. It does not intersect the
+  press `Ctrl+R`. Hosted discovery intersects NVIDIA's live `/v1/models`
+  availability with UR's audited agent contracts. It does not intersect the
   catalog with the separate NVCF deployment-function inventory. A definitive
   runtime 404 removes only that model from the current endpoint-scoped session
   catalog until the next explicit refresh.
@@ -227,6 +227,18 @@ If `chat_models` fails, reconnect a current build.nvidia.com key with
 `ur connect nvidia-nim`. A configured enterprise/self-hosted NIM endpoint is
 validated only against that gateway's own `/models` response.
 
+### An NVIDIA image/video/vision model is missing from `/model`
+
+- Ongoing models appear only when NVIDIA returns them live and their exact
+  documented contract supports UR's multi-turn streaming tool loop.
+- Dedicated models appear only in the `ONE-SHOT` section after UR implements
+  their endpoint, request, response, media constraints, and artifact handling.
+  The current set is FLUX.1 Schnell, Stable Video Diffusion, and PaliGemma.
+- Download-only Build cards and unadapted endpoints are intentionally absent;
+  UR does not present a model that it cannot execute correctly.
+- Stable Video Diffusion's hosted inline-image contract accepts JPEG/PNG files
+  smaller than 200 KB. Compress larger input before retrying.
+
 ### A provider says the previous answer was empty after successful tool calls
 
 Some OpenAI-compatible models scope generated tool-call IDs to one response

package/docs/USAGE.md

@@ -56,8 +56,11 @@ macOS, Autodesk 3ds Max is expected to be missing because it is a Windows
 application. Use Blender locally, or run the 3ds Max project on a Windows host.
 
 When UR needs a focused clarification, it uses the `AskUserQuestion` dialog.
-Professional clarification prompts can provide up to eight concrete options;
-UR also accepts custom "Other" answers. If a model supplies only one concrete
+Every real question with two or more plausible concrete answers must use this
+dialog; plain text is reserved for genuinely open-ended questions where no
+meaningful choices can be formed. UR prefers 2-8 focused choices but preserves
+larger legitimate menus instead of rejecting or truncating them, and always
+accepts a custom "Other" answer. If a model supplies only one concrete
 suggestion, UR keeps it and adds a neutral `Different answer` rejection path
 instead of showing an internal validation error or inventing another choice.
 
@@ -270,15 +273,25 @@ API-key access, and an API key does not grant subscription CLI access.
 NVIDIA NIM uses the build.nvidia.com key and hosted
 `https://integrate.api.nvidia.com/v1` endpoint by default. Connect it with
 `ur connect nvidia-nim`; use `ur config set base_url nvidia-nim <url>` for a
-different NIM deployment. For the hosted endpoint, `/model` shows only models
-returned by NVIDIA's authoritative `/v1/models` feed, excluding non-agent
-utility endpoints such as embeddings, guards, and parsers. NVCF deployment
-functions are a separate API and do not narrow this hosted catalog. A custom
-NIM gateway retains its own independent catalog.
+different NIM deployment. For the hosted endpoint, `/model` intersects the
+account's live `/v1/models` feed with exact NVIDIA-documented agent contracts.
+This excludes utility endpoints and dedicated single-use APIs from the ongoing
+agent list even when NVIDIA returns them. NVCF deployment functions are a
+separate API and do not narrow this hosted catalog. A custom NIM gateway
+retains its own independent catalog.
 Download-only cards from the Build web catalog are not inserted into the
 hosted picker. NVIDIA's live `nemotron-3.5-lightning-30b-a3b` endpoint is
 focused first as its documented fastest 30B agent model; Left/Right controls
 that model's advertised on/off thinking switch.
+Verified specialized models returned by the connected account appear
+separately as `ONE-SHOT`, with their purpose visible before selection. FLUX.1
+Schnell generates a JPEG from text, Stable Video Diffusion generates an MP4
+from a sub-200-KB JPEG/PNG, and PaliGemma analyzes one image with one prompt.
+Selecting one leaves the ongoing agent unchanged; describe the task normally
+and UR uses `NvidiaNimTask` with the same stored NVIDIA key and exact model
+endpoint. Generated media defaults to `.ur/artifacts/nvidia/`. Other
+download-only, utility, and dedicated models remain hidden until UR has a
+complete executable adapter for their contract.
 On the `/model` model screen, `K` adds or replaces a
 provider API key and `E` edits its endpoint. This also makes optional
 authentication practical for generic OpenAI-compatible gateways.

package/docs/VALIDATION.md

@@ -19,7 +19,7 @@ You need:
 
 ```sh
 ur --version
-# expected for this release: "1.84.5 (UR-Nexus)"
+# expected for this release: "1.84.6 (UR-Nexus)"
 ```
 
 ### 0.0 Redteam mode and Reverse Skills (1.81.0)
@@ -249,6 +249,7 @@ Run the deterministic adapter and shell coverage:
 ```sh
 bun test test/bashCommandExecution.test.ts \
   test/providerNvidiaNim.test.ts \
+  test/nvidiaTaskRuntime.test.ts \
   test/providerMultimodal.test.ts \
   test/openaiResponses.test.ts \
   test/ollamaToolResultImages.test.ts
@@ -261,11 +262,15 @@ NVIDIA NIM, Ollama, LM Studio, llama.cpp, vLLM, Unsloth, and generic OpenAI-comp
 request shapes.
 
 The NVIDIA fixture also verifies hosted/default and overridden endpoints,
-Bearer discovery from NVIDIA's authoritative `/v1/models` endpoint, removal
-of non-agent utility models, selected-model doctor diagnostics, redaction of
+Bearer discovery from NVIDIA's live `/v1/models` endpoint, positive agent
+contract intersection, selected-model doctor diagnostics, redaction of
 internal NVIDIA account/function IDs, endpoint-scoped runtime invalidation,
 native dispatch, the preferred Lightning endpoint and its model-scoped
-`enable_thinking` switch, documented effort aliases, and no Ultra on an unknown model. In
+`enable_thinking` switch, documented effort aliases, and no Ultra on an unknown model.
+`nvidiaTaskRuntime.test.ts` verifies the exact FLUX, Stable Video Diffusion,
+and PaliGemma endpoints and payloads; Bearer reuse; async request-ID polling;
+artifact decoding; media constraints; and rejection of every model without an
+implemented adapter. In
 `/model`, select `openai-compatible` and verify `K` can
 add or replace its optional key while `E` continues to edit only its endpoint.
 

package/docs/providers.md

@@ -217,6 +217,10 @@ NVIDIA's current model API reference documents that exact model's
 `reasoning_effort` values. Documented `none` appears as Minimal and `max`
 appears as Ultra while the request preserves NVIDIA's wire values. An unknown
 NIM model never inherits an invented graded ladder.
+Hosted discovery is also a positive agent-contract intersection: a row in the
+mixed NVIDIA `/v1/models` inventory is not sufficient by itself to enter the
+ongoing agent picker. Verified dedicated media/VLM endpoints are exposed only
+as one-shot task contracts and cannot pass provider/model validation.
 
 For an unknown or newly released model, UR waits for provider-authored model
 metadata or a supported model-scoped probe before adding thinking parameters.
@@ -451,7 +455,7 @@ ur config set provider anthropic-api
 | --- | --- | --- |
 | API providers (openai-api, anthropic-api, gemini-api) | Live discovery from the provider's `/models` endpoint using your connected key (curated fallback until connected) | live |
 | OpenRouter | Live `/models` discovery with an endpoint-scoped five-minute cache; Ctrl+R forces a fresh request with no stale fallback | live/cache |
-| NVIDIA NIM | Hosted: authoritative live `/models`, restricted to agent/chat endpoints. Configured NIM gateway: its own live `/models` catalog | live |
+| NVIDIA NIM | Hosted: live `/models` availability intersected with audited agent contracts, plus separately labelled one-shot models with implemented adapters. Configured NIM gateway: its own live `/models` catalog | live |
 | Local/server providers (ollama, lmstudio, llama.cpp, vllm, unsloth) | Dynamic discovery from the selected provider endpoint | live |
 | OpenAI-compatible | Dynamic discovery from configured endpoint | live |
 | Subscription CLIs (codex-cli, claude-code-cli, gemini-cli, antigravity-cli) | Curated list (the official CLIs expose no models API); first-class in `/model`, dispatched via the official CLI. External CLI behavior depends on the vendor CLI. Log in with `ur auth <provider>` | static |
@@ -688,11 +692,11 @@ ur provider doctor nvidia-nim
 ur config set base_url nvidia-nim https://nim-gateway.example/v1
 ```
 
-The default is `https://integrate.api.nvidia.com/v1`. NVIDIA documents
-`/v1/models` as the management endpoint for models available for inference, so
-UR uses that authenticated response as the live hosted catalog. It removes
-embedding, guard, parser, translation, reward, and similar non-agent endpoints,
-but does not intersect the result with NVCF's separate deployment-function
+The default is `https://integrate.api.nvidia.com/v1`. NVIDIA's authenticated
+`/v1/models` response proves current account availability but mixes agents,
+utilities, VLMs, and generation functions. UR intersects it with a reviewed
+positive agent registry before allowing a model to own the multi-turn tool
+loop. It does not intersect the result with NVCF's separate deployment-function
 inventory. A custom enterprise or self-hosted NIM remains independent and uses
 only that configured gateway's `/models` response.
 
@@ -715,6 +719,26 @@ documented Nemotron coding-agent models, UR includes NVIDIA's
 [NIM LLM API reference](https://docs.api.nvidia.com/nim/reference/llm-apis)
 and [NIM endpoint guide](https://docs.nvidia.com/nim/large-language-models/latest/tutorials.html).
 
+NVIDIA's dedicated APIs are a separate one-shot surface. `/model` labels them
+`ONE-SHOT`, shows the task purpose, and keeps the current agent model when one
+is selected. `NvidiaNimTask` currently implements three exact contracts:
+
+- [FLUX.1 Schnell](https://docs.api.nvidia.com/nim/reference/black-forest-labs-flux_1-schnell-infer)
+  → text-to-JPEG at
+  `https://ai.api.nvidia.com/v1/genai/black-forest-labs/flux.1-schnell`.
+- [Stable Video Diffusion](https://docs.api.nvidia.com/nim/reference/stabilityai-stable-video-diffusion-infer)
+  → JPEG/PNG-to-MP4 at
+  `https://ai.api.nvidia.com/v1/genai/stabilityai/stable-video-diffusion`;
+  NVIDIA's inline input contract requires a source smaller than 200 KB.
+- [PaliGemma](https://docs.api.nvidia.com/nim/reference/google-paligemma-infer)
+  → one-image visual analysis at
+  `https://ai.api.nvidia.com/v1/vlm/google/paligemma`.
+
+They reuse `NVIDIA_API_KEY`, poll documented asynchronous responses when
+necessary, save generated files under `.ur/artifacts/nvidia/` by default, and
+return only text/path metadata to the enclosing agent. Unsupported,
+download-only, and unadapted dedicated models never appear as usable choices.
+
 `ur provider doctor nvidia-nim` verifies the hosted catalog and selected model
 against the live `/v1/models` response. If NVIDIA rejects a listed model after
 selection, UR redacts NVIDIA's internal function/account IDs, removes that

package/documentation/app.js

@@ -68,8 +68,8 @@ const featureGroups = [
   {
     title: 'Providers and auth',
     tags: ['subscription', 'API', 'local', 'effort', 'status bar'],
-    text: 'UR-native API/local/OpenAI-compatible runtimes, provider-scoped endpoints, live NVIDIA NIM and provider-only Unsloth inference, optional compatible-gateway keys, capability-driven reasoning effort, responsive OpenRouter routing, first-class subscription CLI providers dispatched through the official vendor CLIs, provider doctor checks, secure API-key connect, non-secret config, fallback hints, and provider-aware status-bar output.',
-    commands: ['ur provider list', 'ur provider status', 'ur provider doctor agy', 'ur connect status', 'ur config set provider nvidia-nim', 'ur config set provider openai-api', 'ur config set provider ollama', 'ur config set base_url llama.cpp http://localhost:9931/v1', '/effort ultra', '/thinking on'],
+    text: 'UR-native API/local/OpenAI-compatible runtimes, provider-scoped endpoints, audited NVIDIA agent discovery plus exact one-shot image/video/vision adapters, provider-only Unsloth inference, optional compatible-gateway keys, capability-driven reasoning effort, responsive OpenRouter routing, first-class subscription CLI providers dispatched through the official vendor CLIs, provider doctor checks, secure API-key connect, non-secret config, fallback hints, and provider-aware status-bar output.',
+    commands: ['ur provider list', 'ur provider status', 'ur provider doctor nvidia-nim', 'ur connect status', 'ur config set provider nvidia-nim', 'ur config set provider openai-api', 'ur config set provider ollama', 'ur config set base_url llama.cpp http://localhost:9931/v1', '/model', '/effort ultra', '/thinking on'],
   },
   {
     title: 'Security and operations',

package/documentation/index.html

@@ -45,7 +45,7 @@
     <main id="content" class="content">
       <header class="topbar">
         <div>
-          <p class="eyebrow">Version 1.84.5</p>
+          <p class="eyebrow">Version 1.84.6</p>
           <h1>UR-Nexus Documentation</h1>
           <p class="lead">A practical, tutorial-style reference for installing, configuring, automating, extending, and operating UR-Nexus.</p>
         </div>
@@ -196,7 +196,7 @@ ur --model kimi-k3:cloud --effort high
 ur config set provider nvidia-nim
 ur config set base_url nvidia-nim https://integrate.api.nvidia.com/v1
 /model  # K API key · E endpoint</code></pre>
-            <p>NVIDIA NIM is a UR-native provider with live models, streaming, tools, images, configurable endpoints, and only NVIDIA-documented effort ladders. Its authenticated hosted <code>/v1/models</code> response is authoritative: UR filters utility endpoints but does not narrow the catalog through the unrelated NVCF deployment inventory, and download-only Build cards are not presented as hosted endpoints. Nemotron 3.5 Lightning is preferred when live and receives its documented on/off thinking field; unknown models inherit no fabricated effort. Generic OpenAI-compatible endpoints can store an optional dedicated key, while anonymous endpoints remain valid.</p>
+            <p>NVIDIA NIM separates ongoing agents from specialized one-shot models. Hosted agent discovery intersects the live <code>/v1/models</code> inventory with audited tool-loop contracts; download-only, utility, and unadapted models stay hidden. The separately labelled one-shot section shows a model only when the connected account returns it and UR has a complete adapter: FLUX.1 Schnell text-to-image, Stable Video Diffusion image-to-video, and PaliGemma image understanding use their exact documented endpoints and the same stored NVIDIA key. Their purpose appears before selection, generated media is saved under <code>.ur/artifacts/nvidia/</code>, and the ongoing agent never changes. Nemotron 3.5 Lightning retains its documented on/off thinking field; unknown models inherit no fabricated effort. Generic OpenAI-compatible endpoints can store an optional dedicated key, while anonymous endpoints remain valid.</p>
           </article>
           <article>
             <h3>Portable shell deadlines</h3>

package/extensions/jetbrains-ur/build.gradle.kts

@@ -7,7 +7,7 @@ plugins {
 }
 
 group = "dev.urnexus"
-version = "1.84.5"
+version = "1.84.6"
 
 repositories {
     mavenCentral()

package/extensions/vscode-ur-inline-diffs/package.json

@@ -2,7 +2,7 @@
   "name": "ur-inline-diffs",
   "displayName": "UR Inline Diffs",
   "description": "Review, apply, and reject UR inline diff bundles from .ur/ide/diffs inside VS Code.",
-  "version": "1.84.5",
+  "version": "1.84.6",
   "publisher": "ur-nexus",
   "engines": {
     "vscode": "^1.92.0"

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ur-agent",
-  "version": "1.84.5",
+  "version": "1.84.6",
   "description": "UR-Nexus — autonomous engineering workflow engine (plan, execute, test, verify, document, benchmark, reproduce)",
   "type": "module",
   "packageManager": "bun@1.3.14",