ur-agent 1.81.5 → 1.81.8

package/CHANGELOG.md

@@ -1,5 +1,55 @@
 # Changelog
 
+## 1.81.8
+
+- Made reasoning effort provider- and model-accurate across the model picker,
+  `/effort`, the status bar, SDK, and outbound API requests. Up/Down now loads
+  the focused model's exact levels, Left/Right cycles only those levels, and
+  `max` resolves to the model's real `high`, `xhigh`, or `max` ceiling.
+- Added model-scoped llama.cpp reasoning discovery through `/props`, preserved
+  rich OpenAI-compatible capability metadata, and stopped presenting invented
+  graded levels when a provider does not advertise them.
+- Regenerated version-matched smoke and regression benchmark evidence (6/6 and
+  20/20 passed) so the release-readiness gate rejects no stale prior-release
+  artifacts.
+
+## 1.81.7
+
+- Made reasoning effort a real provider/model capability instead of a cosmetic
+  selector. UR now preserves exact `minimal`, `low`, `medium`, `high`, `xhigh`,
+  and `max` levels advertised by the provider and sends the selected value on
+  the provider request.
+- Made `/effort max` resolve to the selected model's actual ceiling. A
+  high-only model receives `high`, an xhigh model receives `xhigh`, and a model
+  with native max support receives `max`; `/effort status` and the status bar
+  report that same applied value.
+- Updated both model pickers so Up/Down refreshes the focused model's exact
+  effort list and Left/Right cycles only through supported levels. Models that
+  do not advertise graded reasoning no longer receive invented capabilities.
+- Added model-scoped llama.cpp reasoning discovery through `/props`, retained
+  rich OpenAI-compatible model metadata, and cached the result per endpoint and
+  model so clustered local deployments use their real capabilities.
+- Extended the CLI, SDK schemas, documentation, and regression coverage for
+  exact effort levels and provider wire serialization.
+
+## 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

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
@@ -353,11 +359,17 @@ In the interactive app, `/model` is a two-step, provider-first picker:
    their curated model list because the official CLIs expose no models API. The
    generic `subscription` entry is an internal placeholder hidden from listings.
 
-   In the model catalog, use **Up/Down** to browse and **Left/Right** to change
-   the focused model's effort before pressing Enter. OpenRouter additionally
+   In the model catalog, use **Up/Down** to browse. The effort row updates to
+   the focused model's exact provider-advertised levels; use **Left/Right** to
+   cycle only those levels before pressing Enter. A generic `max` request is
+   resolved visibly to that model's actual `max`, `xhigh`, or `high` ceiling,
+   and the resolved value is the value sent to the provider. llama.cpp models
+   are checked lazily through their model-scoped `/props` capability while the
+   cursor moves. OpenRouter additionally
    shows compact model names, FREE/PAID tier, context size, tool/reasoning
-   support, and the exact ID for the focused entry. Its catalog is fetched
-   fresh every time it opens and never falls back to a stale cached list.
+   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.