ur-agent 1.81.5 → 1.81.8

package/docs/AGENT_FEATURES.md

@@ -9,6 +9,23 @@ reproducible autonomous software engineering agent: every substantial task can
 be driven as `spec -> plan -> patch -> test -> report -> rollback`, with the
 spec as the durable source of truth and command evidence as the success gate.
 
+## v1.81.6 Addition
+
+- File reads no longer inject a blanket instruction that blocks all code
+  improvements. Benign games, websites, applications, and developer tools can
+  be modified normally; UR continues to apply authorization, secret handling,
+  sandbox, destructive-action, and genuine malware safeguards based on actual
+  behavior and intent.
+- OpenRouter keeps compact catalog rows while repeating the focused model's
+  complete provider/model ID immediately below the list.
+- The welcome screen uses the original clean house mark without a shadow. The
+  full adaptive layout is the default at every terminal size; the small-house
+  condensed layout is explicit-only through
+  `UR_CODE_COMPACT_LOGO=1`.
+- The full welcome pane uses a 16-line UR wordmark in the active UR theme color
+  and automatically switches to compact and minimal marks as terminal width or
+  height decreases.
+
 ## v1.81.0 Addition
 
 - UR now provides an explicit `/mode redteam` for authorized researchers. A

package/docs/VALIDATION.md

@@ -19,7 +19,7 @@ You need:
 
 ```sh
 ur --version
-# expected for this release: "1.81.5 (UR-Nexus)"
+# expected for this release: "1.81.8 (UR-Nexus)"
 ```
 
 ### 0.0 Redteam mode and Reverse Skills (1.81.0)
@@ -77,7 +77,12 @@ bun test test/taskListGate.test.ts test/toolExecutionFinalInput.test.ts
 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
+the row must list only that model's provider-advertised levels. Move Up/Down
+between high-only, xhigh, and max models; the level list and selected ceiling
+must update immediately, and the confirmation must match `/effort status` and
+the request wire value. For llama.cpp, verify focus requests
+`/props?model=<focused-id>` and that a template reporting
+`supports_reasoning_effort: false` has no graded selector. Open the OpenAI API or Claude
 API connection flow and verify the masked `API key` label and entry remain on
 one horizontal row.
 
@@ -90,6 +95,7 @@ Deterministic coverage:
 
 ```sh
 bun test test/providerPickerPresentation.test.ts \
+  test/openRouterEffort.test.ts test/providerModelDiscovery.test.ts \
   test/secondaryModelFallback.test.ts test/providerToolCalls.test.ts \
   test/usageAccounting.test.ts test/providerRouting.test.ts
 ```

package/docs/providers.md

@@ -154,25 +154,35 @@ the previous provider.
 
 ### Reasoning effort
 
-Use `/effort low|medium|high|max|auto` inside UR. `max` is provider-neutral and
-means the selected model's highest reasoning capability. For OpenRouter, UR
-preserves the live `/models` reasoning metadata and sends the unified
-`reasoning.effort` request, translating `max` to the model's advertised wire
-value such as `xhigh` or `high`. The command confirmation, status indicator,
-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.
+Use `/effort minimal|low|medium|high|xhigh|max|auto` inside UR. UR normalizes
+the exact graded levels advertised for the active provider/model pair. `max`
+is provider-neutral and means the selected model's real ceiling: it therefore
+displays and sends `max`, `xhigh`, or `high` according to that model's contract.
+For OpenRouter, UR preserves the live `/models` reasoning metadata and sends
+the unified `reasoning.effort` request. OpenAI-compatible servers receive the
+resolved value as `reasoning_effort`. The command confirmation, status
+indicator, active-work spinner, SDK settings response, and provider request all
+use the same resolved value. If a provider advertises only boolean thinking,
+UR does not invent a graded effort selector.
 
 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
-the exact model ID for the focused entry. Opening the OpenRouter catalog always
-fetches the current `/models` endpoint and never substitutes a cached list when
-that refresh fails. API-key entry for
+the full, untruncated model ID immediately below the focused entry. Opening the
+OpenRouter catalog always fetches the current `/models` endpoint and never
+substitutes a cached list when that refresh fails. 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.
 
+For llama.cpp, `/v1/models` metadata is preserved when the server supplies it.
+Because stock llama.cpp exposes chat-template effort support per loaded model,
+UR also resolves the model currently under the Up/Down cursor through
+`/props?model=<id>`. Left/Right is enabled only after that focused template
+advertises `supports_reasoning_effort`; the selected value is then sent
+unchanged in `reasoning_effort`. This works with llama.cpp router/cluster mode
+and does not assume that port 8080 limits UR to one worker.
+
 ### Provider-aware research calls
 
 WebFetch summarization and WebSearch use the active session provider/model pair
@@ -236,7 +246,9 @@ After selecting a provider:
 - Model source is displayed: `live` (dynamic discovery), `cache` (fallback), or `static` (predefined)
 - OpenRouter is fresh-only in this picker: every opening fetches `/models`, and
   a failed refresh is reported instead of showing stale cached entries
-- Left/Right changes effort for the focused model; Up/Down browses and Enter confirms
+- Up/Down changes the focused model and immediately switches to that model's
+  provider-advertised effort list; Left/Right cycles only those exact levels;
+  Enter confirms both
 - 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 1.81.5</p>
+          <p class="eyebrow">Version 1.81.8</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 = "1.81.5"
+version = "1.81.8"
 
 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": "1.81.5",
+  "version": "1.81.8",
   "publisher": "ur-nexus",
   "engines": {
     "vscode": "^1.92.0"

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ur-agent",
-  "version": "1.81.5",
+  "version": "1.81.8",
   "description": "UR-Nexus — autonomous engineering workflow engine (plan, execute, test, verify, document, benchmark, reproduce)",
   "type": "module",
   "packageManager": "bun@1.3.14",