ur-agent 1.81.2 → 1.81.4

package/docs/CONFIGURATION.md

@@ -143,6 +143,12 @@ incompatible saved model instead of silently carrying it across providers. The
 saved provider/model pair controls the runtime backend for the next agent
 request; Ollama is only used when `ollama` is the selected provider.
 
+In the model step, Up/Down browses, Left/Right changes the focused model's
+supported effort level, Enter confirms, Ctrl+R refreshes the catalog, and Esc
+returns to providers. OpenRouter entries show pricing tier, context size,
+tool/reasoning capability, and live/cache catalog status. API-provider secret
+entry stays on one masked row and stores the value through the keychain flow.
+
 The same provider-first picker is mandatory on the first interactive run in a
 workspace with no model in `.ur/settings.json` or `.ur/settings.local.json`.
 The result is validated and written to the gitignored local settings file.

package/docs/VALIDATION.md

@@ -19,7 +19,7 @@ You need:
 
 ```sh
 ur --version
-# expected for this release: "1.81.2 (UR-Nexus)"
+# expected for this release: "1.81.4 (UR-Nexus)"
 ```
 
 ### 0.0 Redteam mode and Reverse Skills (1.81.0)
@@ -72,6 +72,28 @@ changes must remain blocked. The deterministic regressions are:
 bun test test/taskListGate.test.ts test/toolExecutionFinalInput.test.ts
 ```
 
+### 0.0.0 OpenRouter research routing and provider UI (1.81.3)
+
+Connect OpenRouter, run `/model`, select OpenRouter, and verify that its model
+step shows catalog freshness plus pricing/context/tool/reasoning details. Focus
+a reasoning model and press Left/Right; the displayed effort must change and
+the confirmed value must match the status line. Open the OpenAI API or Claude
+API connection flow and verify the masked `API key` label and entry remain on
+one horizontal row.
+
+Then ask UR to research a current topic with WebSearch and WebFetch. Expected:
+the auxiliary request stays on the active OpenRouter model, no `modelH` error
+appears, a real provider search count is shown, and a response that did not
+perform a search fails clearly instead of saying `Did 0 searches`.
+
+Deterministic coverage:
+
+```sh
+bun test test/providerPickerPresentation.test.ts \
+  test/secondaryModelFallback.test.ts test/providerToolCalls.test.ts \
+  test/usageAccounting.test.ts test/providerRouting.test.ts
+```
+
 ### 0.0.1 Unavailable Ollama tools recover (1.80.7)
 
 With an Ollama model, ask for research that mentions WebSearch. If WebSearch is

package/docs/providers.md

@@ -163,6 +163,24 @@ and active-work spinner all show the same applied UR effort level. Providers
 that cannot apply a requested level report the actual downgraded level instead
 of confirming a value they did not use.
 
+The provider-first `/model` picker supports the same control directly: use
+Left/Right to move through the effort levels advertised by the focused model,
+then Enter to apply the model and effort together. OpenRouter's live catalog
+shows pricing tier, context size, tool capability, reasoning capability, and
+whether the list came from the live endpoint or cache. API-key entry for
+OpenAI, Claude, Gemini, and OpenRouter is a single aligned masked row; the key
+is stored in the OS keychain flow and is never written to settings.
+
+### Provider-aware research calls
+
+WebFetch summarization and WebSearch use the active session provider/model pair
+unless `URHQ_SMALL_FAST_MODEL` explicitly selects a secondary model. This
+prevents an OpenRouter session from dispatching auxiliary research through an
+unavailable internal alias or a stale Ollama model. On OpenRouter, WebSearch is
+sent as the native `openrouter:web_search` server tool and the provider's
+reported search count is preserved. A response that performs no search is an
+error, not a successful `Did 0 searches` result.
+
 ## Runtime provider routing
 
 When you select a UR-native provider and model, every agent request is routed
@@ -210,8 +228,10 @@ You see all configured providers with:
 
 After selecting a provider:
 - Only models from that provider are shown
-- Each model shows its description
+- Each model shows its concise capabilities; OpenRouter includes pricing,
+  context size, tool support, and reasoning support
 - Model source is displayed: `live` (dynamic discovery), `cache` (fallback), or `static` (predefined)
+- Left/Right changes effort for the focused model; Up/Down browses and Enter confirms
 - Press Esc to go back and change provider
 
 **Confirmation**

package/documentation/index.html

@@ -45,7 +45,7 @@
     <main id="content" class="content">
       <header class="topbar">
         <div>
-          <p class="eyebrow">Version 1.81.2</p>
+          <p class="eyebrow">Version 1.81.4</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>

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

@@ -7,7 +7,7 @@ plugins {
 }
 
 group = "dev.urnexus"
-version = "1.81.2"
+version = "1.81.4"
 
 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": "1.81.2",
+  "version": "1.81.4",
   "publisher": "ur-nexus",
   "engines": {
     "vscode": "^1.92.0"

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ur-agent",
-  "version": "1.81.2",
+  "version": "1.81.4",
   "description": "UR-Nexus — autonomous engineering workflow engine (plan, execute, test, verify, document, benchmark, reproduce)",
   "type": "module",
   "packageManager": "bun@1.3.14",