ur-agent 1.85.1 → 1.85.2

package/docs/AGENT_FEATURES.md

@@ -350,7 +350,7 @@ automatically changes the active provider.
 | 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| Public VS Code install now packages the repo's bundled inline-diffs extension as a local VSIX instead of trying an unpublished marketplace ID.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` | 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 Agentic/Special providers | live Build-card generator, `nvidiaHostedModels.ts`, `NvidiaSpecial`, `/model` | Audits 100 current Build cards and preserves every Free Endpoint card: 13 Agentic and 23 Special. Uses each card's exact HTTP/NVCF/gRPC route, method, function ID, request/response schema, input/output hints, Assets/async handling, and artifact decoding. Runtime errors never remove models; focused selection never replaces the ongoing agent. |
+| NVIDIA Agentic/Special providers | live Build-card generator, `nvidiaHostedModels.ts`, `NvidiaSpecial`, `/model`, first-workspace setup | Audits 100 current Build cards and preserves every Free Endpoint card: 13 Agentic and 23 Special. Uses each card's exact HTTP/NVCF/gRPC route, method, function ID, request/response schema, input/output hints, Assets/async handling, and artifact decoding. Runtime errors never remove models; focused selection never replaces the ongoing agent, appears during setup, and directly owns the next non-command prompt without depending on that agent provider. |
 | 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/TROUBLESHOOTING.md

@@ -211,6 +211,16 @@ from `OPENAI_API_KEY`. NVIDIA Agentic/Special use one key stored with
 `ur connect nvidia-nim` or `ur connect nvidia-special`; Agentic keeps any
 custom `base_url` scoped to that provider.
 
+When NVIDIA Special is selected, plain prompts are sent directly to its exact
+model-card endpoint. They must not produce Anthropic/Ollama connection or
+provider-model errors. If a contract needs media, provide its required field,
+for example:
+
+```text
+prompt: Turn this source into an 8mm-film scene.
+video_path: /absolute/path/source.mp4
+```
+
 ### Anthropic says `anthropic-workspace-id is required`
 
 - Cause: the API key is identity-linked and can act across workspaces. Anthropic

package/docs/USAGE.md

@@ -300,12 +300,18 @@ 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.
 NVIDIA Special appears as its own provider, with purpose and input/output hints
-before selection. The current Build audit preserves all 23 focused Free
+before selection, including during first-workspace setup. Setup returns to the
+provider list after a Special selection so the session also has an ordinary
+agent model. The current Build audit preserves all 23 focused Free
 Endpoint cards. `NvidiaSpecial` describes or runs each card's exact inference
 URL, HTTP/RPC method, function ID, and request/response schema using the shared
 key. It supports HTTP, direct NVCF, async polling, NVIDIA Assets, and five
 documented Maxine/Riva gRPC services. Selecting one leaves the ongoing agent
-unchanged. Returned media/binary/JSON defaults to `.ur/artifacts/nvidia/`.
+unchanged and activates direct task mode: the next non-command prompt calls
+NVIDIA without first calling that agent. Plain prompts supply `prompt`; use
+newline inputs such as `video_path: /path/source.mp4` or exact JSON when the
+selected contract requires media or specialized fields. Returned
+media/binary/JSON defaults to `.ur/artifacts/nvidia/`.
 Cards are never removed; an unpublished protocol remains visible and clearly
 cannot be invoked until NVIDIA publishes its contract.
 On the `/model` model screen, `K` adds or replaces a

package/docs/VALIDATION.md

@@ -19,7 +19,7 @@ You need:
 
 ```sh
 ur --version
-# expected for this release: "1.85.1 (UR-Nexus)"
+# expected for this release: "1.85.2 (UR-Nexus)"
 ```
 
 ### 0.0 Redteam mode and Reverse Skills (1.81.0)

package/docs/providers.md

@@ -738,7 +738,13 @@ documented Nemotron coding-agent models, UR includes NVIDIA's
 and [NIM endpoint guide](https://docs.nvidia.com/nim/large-language-models/latest/tutorials.html).
 
 NVIDIA Special is a separate focused-task provider. Selecting a row stores a
-one-shot preference and keeps the current chat provider/model. The generator
+task-mode selection and keeps the current chat provider/model. The next
+non-command prompt is dispatched directly to NVIDIA, so an unavailable or
+misconfigured chat provider cannot intercept the task. Plain text maps to the
+contract's `prompt`; newline convenience fields (`video_path`, `image_path`,
+`audio_path`, `output_path`, and generation options) or exact JSON cover richer
+contracts. NVIDIA Special is also visible during first-workspace setup; after a
+task is chosen, setup returns to the ordinary provider/model picker. The generator
 crawls all 100 current Build cards and preserves every card labelled Free
 Endpoint: 36 total, split into 13 Agentic and 23 Special. Thirty-five publish a
 complete executable contract; 22 are Special. The remaining VoiceChat card is

package/documentation/app.js

@@ -68,7 +68,7 @@ const featureGroups = [
   {
     title: 'Providers and auth',
     tags: ['subscription', 'API', 'local', 'effort', 'status bar'],
-    text: 'UR-native API/local/OpenAI-compatible runtimes, provider-scoped endpoints, NVIDIA Agentic plus NVIDIA Special with all 36 current Build Free Endpoint cards and exact per-card HTTP/NVCF/gRPC inference contracts, provider-only Unsloth inference, optional compatible-gateway keys, capability-driven reasoning effort, responsive OpenRouter routing, first-class subscription CLI providers dispatched through official vendor CLIs, provider doctor checks, secure API-key connect, non-secret config, fallback hints, and provider-aware status-bar output.',
+    text: 'UR-native API/local/OpenAI-compatible runtimes, provider-scoped endpoints, NVIDIA Agentic plus directly dispatched NVIDIA Special task mode with all 36 current Build Free Endpoint cards and exact per-card HTTP/NVCF/gRPC inference contracts, provider-only Unsloth inference, optional compatible-gateway keys, capability-driven reasoning effort, responsive OpenRouter routing, first-class subscription CLI providers dispatched through 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 nvidia-special', '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'],
   },
   {

package/documentation/index.html

@@ -45,7 +45,7 @@
     <main id="content" class="content">
       <header class="topbar">
         <div>
-          <p class="eyebrow">Version 1.85.1</p>
+          <p class="eyebrow">Version 1.85.2</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>
@@ -198,7 +198,7 @@ ur config set provider nvidia-nim
 ur config set provider nvidia-special
 ur config set base_url nvidia-nim https://integrate.api.nvidia.com/v1
 /model  # K API key · E endpoint</code></pre>
-            <p>NVIDIA is split into NVIDIA Agentic for the ongoing tool loop and NVIDIA Special for focused inference; both share one stored <code>NVIDIA_API_KEY</code>. UR audits all 100 current Build cards and preserves every Free Endpoint card: 13 Agentic and 23 Special. Thirty-five publish executable contracts; the one unpublished protocol stays visible and labelled. Each row shows purpose, input, and output, and uses that card's exact HTTP, direct NVCF, or gRPC endpoint, method, function ID, and request/response schema. NVIDIA Assets, asynchronous polling, five native Maxine/Riva gRPC services, and media/binary/JSON artifact saving are built in. Account errors never remove models, and choosing a Special task never changes the ongoing agent. 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>
+            <p>NVIDIA is split into NVIDIA Agentic for the ongoing tool loop and NVIDIA Special for focused inference; both share one stored <code>NVIDIA_API_KEY</code>. UR audits all 100 current Build cards and preserves every Free Endpoint card: 13 Agentic and 23 Special. Thirty-five publish executable contracts; the one unpublished protocol stays visible and labelled. Each row shows purpose, input, and output, and uses that card's exact HTTP, direct NVCF, or gRPC endpoint, method, function ID, and request/response schema. Selecting Special activates a visible task mode: the next plain prompt goes directly to NVIDIA without depending on the ongoing chat provider. Plain text supplies the prompt, while fields such as <code>video_path</code> and exact JSON cover specialized inputs. Special is also available during first-workspace setup before the ordinary agent model is chosen. NVIDIA Assets, asynchronous polling, five native Maxine/Riva gRPC services, and media/binary/JSON artifact saving are built in. Account errors never remove models, and choosing a Special task never changes the ongoing agent. 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 = "1.85.1"
+version = "1.85.2"
 
 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": "1.85.1",
+  "version": "1.85.2",
   "publisher": "ur-nexus",
   "engines": {
     "vscode": "^1.92.0"

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ur-agent",
-  "version": "1.85.1",
+  "version": "1.85.2",
   "description": "UR-Nexus — autonomous engineering workflow engine (plan, execute, test, verify, document, benchmark, reproduce)",
   "type": "module",
   "packageManager": "bun@1.3.14",
@@ -75,7 +75,7 @@
   "overrides": {
     "@hono/node-server": "2.0.12",
     "body-parser": "2.3.0",
-    "fast-uri": "3.1.5",
+    "fast-uri": "3.1.6",
     "form-data": "4.0.6",
     "hono": "4.13.0",
     "ip-address": "10.4.0",