ur-agent 1.81.4 → 1.81.6

package/CHANGELOG.md

@@ -1,5 +1,40 @@
 # Changelog
 
+## 1.81.6
+
+- Restored the original clean welcome house without a shadow. The full adaptive
+  startup UI is now the default at every terminal size; its responsive stacking
+  and wordmark fallbacks handle resizing. The small-house condensed UI appears
+  only when explicitly requested with `UR_CODE_COMPACT_LOGO=1`.
+- Replaced the large UR wordmark with the supplied 16-line letterform in UR's
+  existing theme-aware brand color. It responds to terminal width and height,
+  falling back to the prior compact mark and then plain `UR` so resized or
+  narrow windows never overflow.
+- Kept OpenRouter catalog rows concise while showing the focused model's full,
+  untruncated provider/model ID immediately below the list on both picker
+  surfaces. Request routing continues to use that exact ID.
+- Removed the blanket file-read system reminder that told models to refuse all
+  code improvements. Reading ordinary games, websites, applications, and tools
+  no longer blocks requested edits; UR's normal authorization, malware, secret,
+  sandbox, and destructive-action safeguards remain enforced where relevant.
+
+## 1.81.5
+
+- Matched the UR welcome wordmark to the house and frame's bright, theme-aware
+  accent by applying the brand color directly to each rendered row. Added a
+  restrained dim drop shadow around the large house without changing its
+  established geometry or screen-reader output.
+- Made OpenRouter model discovery fresh-only whenever the model catalog opens.
+  UR now fetches the current catalog on every visit and reports refresh errors
+  instead of silently showing stale cached entries.
+- Shortened OpenRouter model labels and startup model chrome to their useful
+  model names while preserving the complete provider/model ID for requests and
+  showing it on the focused catalog entry. Duplicate short names retain a clear
+  vendor suffix.
+- Stabilized the production-shell recovery regression under concurrent test
+  execution while continuing to verify that reclaimed task-output directories
+  are recreated without restarting UR.
+
 ## 1.81.4
 
 - Unified the welcome-screen UR wordmark, outlined depth, decorative marks,

package/README.md

@@ -114,6 +114,12 @@ available, and the approval decision in task evidence. Security-research prompts
 need scoped targets and authorization confirmation; local/lab/test targets are
 preferred unless the user confirms authorized external scope.
 
+Reading source code does not attach a blanket modification refusal. UR evaluates
+the actual behavior and requested intent, so ordinary games, websites, apps,
+and developer tools can be analyzed and improved normally. Genuine malicious
+or unauthorized activity remains subject to UR's security and operational
+boundaries.
+
 Authorized researchers can explicitly activate `/mode redteam`. The first use
 shows a mandatory risk warning; `/mode redteam --accept-risk` acknowledges it
 and enables UR's unrestricted security-research prompt policy for the current
@@ -355,9 +361,12 @@ In the interactive app, `/model` is a two-step, provider-first picker:
 
    In the model catalog, use **Up/Down** to browse and **Left/Right** to change
    the focused model's effort before pressing Enter. OpenRouter additionally
-   shows FREE/PAID tier, context size, tool/reasoning support, and whether its
-   catalog is live or cached. API-key entry is masked, aligned on one row, and
-   stored through the OS keychain flow.
+   shows compact model names, FREE/PAID tier, context size, tool/reasoning
+   support, and the full untruncated ID immediately below the focused entry.
+   Its catalog is fetched fresh every time it opens and never falls back to a
+   stale cached list.
+   API-key entry is masked, aligned on one row, and stored through the OS
+   keychain flow.
 
 Model lists never cross providers: OpenAI API, Claude API, Gemini API,
 OpenRouter, Ollama, and OpenAI-compatible local/server endpoints are separate