ur-agent 1.83.1 → 1.84.0

package/docs/AGENT_FEATURES.md

@@ -314,7 +314,7 @@ ur auth antigravity
 ur config set provider ollama
 ur config set provider openai-compatible
 ur config set model qwen2.5-coder:7b
-ur config set base_url http://localhost:11434/v1
+ur config set base_url openai-compatible http://localhost:11434/v1
 ur config set provider.fallback ollama
 ur upgrade
 ```

package/docs/CONFIGURATION.md

@@ -164,7 +164,8 @@ request; Ollama is only used when `ollama` is the selected provider.
 The configured `base_url` is provider-scoped. Setting an address while vLLM is
 active does not replace the saved Ollama, llama.cpp, or Unsloth address;
 returning to any provider restores its own URL. Legacy `provider.baseUrl`
-settings are migrated to the old active provider when the first switch occurs.
+settings are migrated to the old active provider on the first provider switch
+or scoped base-URL write.
 To configure a provider that is not active, use
 `ur config set base_url <provider> <url>`; the success message names the target
 provider. This applies to direct API providers and gateways (OpenAI, Anthropic,
@@ -185,6 +186,18 @@ Ollama and llama.cpp capabilities are loaded lazily for the focused model from
 `/api/show` and `/props`, respectively, so the arrow selector reflects the
 actual model rather than a provider-wide guess.
 
+The effort row contains only capability-backed selectors UR can map to native
+provider values. Ultra appears only when metadata advertises `ultra`, `max`,
+`xhigh`, or an explicit alias; mappings such as `ultra→max` are shown and sent
+exactly. Models that top out at `high`, boolean-thinking models, and unknown
+capabilities omit Ultra. See [Reasoning effort](providers.md#reasoning-effort).
+
+Boolean-thinking models on runtimes with a native toggle expose a two-state
+control instead: Left selects off, Right selects on, and `t` toggles in
+`/model`; `/thinking on|off|status` is the direct command. This updates the live
+session and `alwaysThinkingEnabled`. Generic OpenAI-compatible transports do
+not receive an invented boolean field.
+
 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.
@@ -223,7 +236,7 @@ UNSLOTH_API_KEY=...
 Unsloth is an inference-provider integration only. Start Unsloth Studio and
 load the model outside UR, connect its generated key with `ur connect unsloth`,
 then select a model discovered from `http://localhost:8888/v1` (or your
-configured `base_url`). UR always sends `enable_tools: false`; standard model
+configured `base_url`). UR sends `enable_tools: false` on every inference request; standard model
 function calls continue through UR's normal native tool flow, while Unsloth's
 server-side tools remain disabled so the integration stays provider-only.
 
@@ -712,6 +725,7 @@ Plugins can add commands, tools, and skills:
 
 ```sh
 ur plugin list
+ur plugin marketplace add npm:@scope/catalog@latest
 ur plugin search [query] [--capability <name>] [--marketplace <name>] [--installed] [--json]
 ur plugin show <name-or-name@marketplace> [--json]
 ur plugin install <plugin>

package/docs/TROUBLESHOOTING.md

@@ -228,8 +228,8 @@ tool loop.
 - Fix: point UR at the right endpoint.
 
 ```sh
-ur config set base_url http://localhost:11434
-ur provider doctor
+ur config set base_url ollama http://localhost:11434
+ur provider doctor ollama
 ```
 
 Addresses are saved per provider. If the doctor probes an unexpected URL,

package/docs/USAGE.md

@@ -214,7 +214,7 @@ and `antigravity-cli` (`agy`) are subscription CLI providers.
 
 API modes are explicit. Keys are read from a key stored via
 `ur connect <provider>` (OS keychain) or from the environment variables
-`OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, `GEMINI_API_KEY`, and
+`OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, `GEMINI_API_KEY`,
 `OPENROUTER_API_KEY`, and `UNSLOTH_API_KEY`. Subscription CLIs are optional, never required
 dependencies, and never used as a silent fallback. UR-Nexus never scrapes
 browser sessions, extracts OAuth tokens, or bypasses provider restrictions.
@@ -224,9 +224,10 @@ and is inference-only: UR does not manage Unsloth and disables its server-side
 tools while retaining standard function calls inside UR's guarded tool loop.
 
 UR stores `base_url` per provider. You can set different addresses for
-Ollama, llama.cpp, vLLM, and Unsloth once, then switch providers without
-re-entering any of them. `ur config get base_url` always reports the address
-for the currently active provider.
+Ollama, LM Studio, llama.cpp, vLLM, and Unsloth once, then switch providers without
+re-entering any of them. `ur config get base_url` reports the active provider's
+saved scoped override when one exists; use `ur provider status` or
+`ur provider doctor <provider>` to inspect the effective endpoint.
 Use `ur config set base_url <provider> <url>` to change one provider's address
 without making it active first. The `/model` picker offers the same endpoint
 entry flow for a disconnected local/server provider.
@@ -348,6 +349,10 @@ UR includes slash commands and CLI subcommands for common workflows:
   `ur plugin search [query]` for ranked cross-catalog discovery and
   `ur plugin show <name@marketplace>` to inspect provenance and capabilities
   before installation.
+  Add an npm-hosted catalog with
+  `ur plugin marketplace add npm:@scope/catalog@latest`; npm sources respect
+  the user's registry/authentication configuration and are refreshed with the
+  normal marketplace update command.
 - `ur agents` to list configured agents
 - `ur agent-trends` to inspect coverage for current agent technology trends
 - `ur a2a card` to print legacy Agent Card metadata, or

package/docs/VALIDATION.md

@@ -19,7 +19,7 @@ You need:
 
 ```sh
 ur --version
-# expected for this release: "1.83.1 (UR-Nexus)"
+# expected for this release: "1.84.0 (UR-Nexus)"
 ```
 
 ### 0.0 Redteam mode and Reverse Skills (1.81.0)
@@ -72,16 +72,20 @@ 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)
+### 0.0.0 OpenRouter research routing and provider UI (1.81.3; Ultra mapping updated 1.83.1)
 
 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 row must list only that model's provider-advertised levels. Move Up/Down
-between high-only, xhigh, max, and native-ultra models; the level list and
-selected ceiling must update immediately. High-only must omit Ultra, while
+the row must list only capability-backed selectors that map to that model's native levels. Move Up/Down
+between models that top out at high, xhigh, max, and native-ultra models; the level list and
+selected ceiling must update immediately. Models that top out at high must omit Ultra, while
 xhigh/max entries must show `ultra→xhigh` or `ultra→max`, and the
 confirmation must match `/effort status` and the request wire value. For
+an Ollama model that advertises boolean thinking without a ladder, verify that
+Left selects off, Right selects on, `t` toggles, and `/effort max` reports that
+max was not sent while enabling `think: true`; `/thinking off` must produce
+`think: false`. 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

package/docs/plugins.md

@@ -51,6 +51,50 @@ ur --plugin-dir ./plugins/community/my-plugin
 Plugins are loaded from local UR-Nexus paths first. Network marketplace installs
 remain explicit user actions and are subject to plugin policy checks.
 
+## Marketplace sources
+
+UR accepts GitHub shorthand, Git URLs, direct marketplace JSON URLs, npm
+packages, local files/directories, and inline settings manifests. Add an npm
+marketplace with the explicit `npm:` prefix:
+
+```sh
+ur plugin marketplace add npm:acme-ur-marketplace
+ur plugin marketplace add npm:@acme/ur-marketplace@latest
+ur plugin marketplace add npm:@acme/ur-marketplace@^2.0.0
+ur plugin marketplace update <marketplace-name>
+```
+
+The package must ship `.ur-plugin/marketplace.json`. An omitted version follows
+the registry's `latest` dist-tag; a version, semver range, or another dist-tag
+can be supplied after the package name, using npm's
+[package-spec syntax](https://docs.npmjs.com/cli/v11/using-npm/package-spec/).
+Refreshing the marketplace re-resolves
+that selector. UR uses the installed npm client, so standard `.npmrc`
+authentication, scoped registries, proxies, and registry settings continue to
+work. Package lifecycle scripts are disabled during marketplace download, and
+only the requested package—not its staging dependency tree—is retained.
+
+For a private registry selected in project or user settings:
+
+```json
+{
+  "extraKnownMarketplaces": {
+    "acme": {
+      "source": {
+        "source": "npm",
+        "package": "@acme/ur-marketplace",
+        "version": "^2.0.0",
+        "registry": "https://registry.example.com"
+      }
+    }
+  }
+}
+```
+
+After an install, removal, or external registry-file change,
+`/reload-plugins` clears both plugin discovery caches and the installed-plugin
+snapshot before reloading.
+
 ## Manifest reference
 
 A plugin is a directory containing `.ur-plugin/plugin.json`. UR uses a

package/docs/providers.md

@@ -21,8 +21,9 @@ UR-Nexus never:
 - claims provider support unless the official CLI/API path works
 
 UR-Nexus stores only safe config: provider name, model name, base URL, fallback
-preference, and non-secret preferences. API keys are read from environment
-variables only when the user explicitly selects API mode.
+preference, and non-secret preferences. API keys stay out of plaintext settings
+and are read from the OS keychain after `ur connect` or from environment
+variables when the user explicitly selects API mode.
 
 ## Provider matrix
 
@@ -144,7 +145,8 @@ form `ur config set base_url <provider> <url>` configures a named provider
 without switching first, and the confirmation names that provider. Each
 provider retains its own address across `/provider`, `/model`, and CLI
 switches. The legacy single `provider.baseUrl` field remains readable and is
-migrated to the previously active provider on the first switch.
+migrated to the previously active provider on the first provider switch or
+scoped base-URL write.
 
 The override is not limited to local runtimes. OpenAI API, Anthropic API,
 Gemini API, and OpenRouter can each target a separate compatible gateway using
@@ -171,29 +173,46 @@ the previous provider.
 
 ### Reasoning effort
 
-Use `/effort minimal|low|medium|high|xhigh|max|ultra|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.
+Use `/effort minimal|low|medium|high|xhigh|max|ultra|auto` inside UR. UR builds a
+capability-backed selector set from the native graded levels advertised for the active
+provider/model pair. `max` is provider-neutral and means the selected model's
+highest supported non-Ultra tier: it displays and sends the matching native
+value (commonly `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.
+use the same resolved value. If a provider advertises only boolean thinking and
+its runtime has a real native on/off mapping, UR does not invent a graded effort
+selector. Use `/thinking on|off` directly;
+in `/model`, Left selects off, Right selects on, and `t` toggles. A graded
+`/effort` request on that model enables boolean thinking while clearly reporting
+that the requested level was not sent.
+Generic OpenAI-compatible endpoints have no universal boolean thinking field,
+so metadata alone does not make this toggle appear and UR sends no invented parameter.
 `ultra` is UR's visible beyond-high ceiling selector. It is selectable only
 when the provider/model advertises `ultra`, `max`, `xhigh`, or an explicit
 provider-authored equivalent. UR shows the native mapping (for example,
-`ultra→max`) and sends that exact wire value; it never enables Ultra for a
-high-only model, boolean thinking, or unknown capability metadata. Arbitrary
+`ultra→max`) and sends that exact wire value; it never enables Ultra for a model
+whose graded ladder tops out at `high`, boolean thinking, or unknown capability metadata. Arbitrary
 labels such as `deep` still require an explicit provider alias because UR
 cannot infer their rank.
 
+For an unknown or newly released model, UR waits for provider-authored model
+metadata or a supported model-scoped probe before adding thinking parameters.
+If the provider does not establish support, thinking stays off for request
+shaping; UR does not optimistically send an unknown parameter and treat an API
+error as capability discovery. Boolean thinking metadata enables the thinking
+toggle only and never invents a graded effort ladder. On OpenRouter, UR sends
+the provider-default `reasoning.enabled` control, or the exact token budget when
+the model advertises `supports_max_tokens`.
+
 For Ollama, UR lazily reads the focused model's `/api/show` capabilities and
-sends the selected level through native `think`. Kimi K3 uses
-`low|high|max` and therefore exposes Ultra as `ultra→max`; GPT-OSS uses
-`low|medium|high` and does not expose Ultra; other models advertising
-`thinking` use Ollama's current `low|medium|high|max` contract. Direct OpenAI,
+sends the resolved control through native `think`. A generic `thinking`
+capability means boolean thinking only. GPT-OSS uses Ollama's documented
+`low|medium|high` ladder and does not expose Ultra. Other graded ladders and
+Ultra aliases are used only when the endpoint explicitly returns them in model
+reasoning metadata. Direct OpenAI,
 Anthropic, and Gemini models use curated model-specific ladders from their
 official documentation; live discovery rows are merged with those contracts.
 See [Ollama thinking](https://docs.ollama.com/capabilities/thinking),
@@ -202,8 +221,10 @@ See [Ollama thinking](https://docs.ollama.com/capabilities/thinking),
 and [Gemini thinking](https://ai.google.dev/gemini-api/docs/thinking).
 
 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
+Left/Right to move through the capability-backed selectors UR can map to a
+graded model's native levels, or to choose off/on for a boolean-thinking model
+when its runtime has a native two-state mapping, then Enter to apply the model
+and reasoning control together. OpenRouter's live catalog
 shows pricing tier, context size, tool capability, reasoning capability, and
 the full, untruncated model ID immediately below the focused entry. Opening the
 OpenRouter catalog reuses its endpoint-scoped five-minute cache; Ctrl+R forces
@@ -215,6 +236,18 @@ provider prompt-cache markers. Explicit routing preferences and the `:nitro`,
 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.
 
+### Token counting
+
+UR uses each provider's non-generating count endpoint when one covers the full
+request: OpenAI Responses input tokens, Anthropic Messages token counting,
+Gemini `countTokens`, llama.cpp chat input tokens, and vLLM Messages token
+counting. Ollama, OpenRouter, LM Studio, Unsloth, and subscription CLIs use a
+provider-wire local estimate because those runtimes do not share a dependable
+preflight tokenizer for complete chat history plus tools. UR never launches a
+hidden completion for token counting. If a native count call is unavailable,
+file and MCP size checks retain the local estimate rather than disabling their
+limits.
+
 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
@@ -283,12 +316,12 @@ After selecting a provider:
 - Each model shows its concise capabilities; OpenRouter includes pricing,
   context size, tool support, and reasoning support. Its list uses compact
   model names; focus an entry to see the exact provider/model ID
-- 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
+- Model source is displayed: `live` (dynamic discovery), `cache` (recent endpoint result), or `static` (predefined)
+- OpenRouter reuses an endpoint-scoped `/models` result for five minutes; Ctrl+R
+  forces a live refresh, and a failed forced refresh never substitutes stale data
 - 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
+  capability-backed effort selectors; Left/Right cycles only values UR can map
+  to provider-native levels, and Enter confirms both
 - Press Esc to go back and change provider
 
 **Confirmation**
@@ -591,7 +624,7 @@ ur provider models unsloth --json
 
 The default endpoint is `http://localhost:8888/v1`; override it with
 `ur config set base_url unsloth <url>`. Authentication is mandatory. Every Unsloth
-request sets `enable_tools: false`, including streaming requests. The model may
+inference request sets `enable_tools: false`, including streaming requests. The model may
 still return standard OpenAI function calls; UR handles those through the same
 native tool flow used by its other providers. This keeps Unsloth provider-only
 and avoids running a second tool loop inside Studio. See the official
@@ -621,6 +654,7 @@ Required variables:
 | Provider | Required env vars | Optional env vars |
 | --- | --- | --- |
 | OpenAI-compatible | `OPENAI_COMPATIBLE_BASE_URL`, `OPENAI_COMPATIBLE_MODEL` | `OPENAI_COMPATIBLE_API_KEY` |
+| Unsloth | `UNSLOTH_API_KEY`, `UNSLOTH_MODEL` | `UNSLOTH_BASE_URL` (defaults to `http://localhost:8888/v1`) |
 | OpenAI | `OPENAI_API_KEY`, `OPENAI_MODEL` | `OPENAI_BASE_URL` |
 | OpenRouter | `OPENROUTER_API_KEY`, `OPENROUTER_MODEL` | `OPENROUTER_BASE_URL` |
 | Anthropic | `ANTHROPIC_API_KEY`, `ANTHROPIC_MODEL` | `ANTHROPIC_BASE_URL` |

package/documentation/app.js

@@ -67,9 +67,9 @@ const featureGroups = [
   },
   {
     title: 'Providers and auth',
-    tags: ['subscription', 'API', 'local', 'status bar'],
-    text: 'UR-native API/local/OpenAI-compatible runtimes, first-class subscription CLI providers dispatched through the 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 agy', 'ur connect status', 'ur config set provider openai-api', 'ur config set provider ollama'],
+    tags: ['subscription', 'API', 'local', 'effort', 'status bar'],
+    text: 'UR-native API/local/OpenAI-compatible runtimes, provider-scoped endpoints, provider-only Unsloth inference, capability-driven reasoning effort, responsive OpenRouter routing, first-class subscription CLI providers dispatched through the 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 agy', 'ur connect status', 'ur config set provider openai-api', 'ur config set provider ollama', 'ur config set base_url llama.cpp http://localhost:9931/v1', '/effort ultra', '/thinking on'],
   },
   {
     title: 'Security and operations',
@@ -85,7 +85,7 @@ const commands = [
     category: 'Core',
     aliases: [],
     summary: 'Start an interactive session; a fresh workspace must choose and locally persist a validated provider/model pair first.',
-    examples: ['ur', 'ur --model qwen3-coder:480b-cloud', 'ur --continue', 'ur --resume'],
+    examples: ['ur', 'ur --model gpt-5.6-sol --effort ultra', 'ur --continue', 'ur --resume'],
   },
   {
     name: 'ur -p',
@@ -225,7 +225,7 @@ const commands = [
     category: 'Ops',
     aliases: ['settings'],
     summary: 'Open the config panel or persist safe non-secret provider settings.',
-    examples: ['ur config', 'ur config set provider ollama', 'ur config set provider openai-api', 'ur config set provider anthropic-api', 'ur config set model qwen3-coder:480b-cloud', 'ur config set base_url http://localhost:11434/v1', 'ur config set provider.fallback ollama'],
+    examples: ['ur config', 'ur config set provider ollama', 'ur config set provider openai-api', 'ur config set provider anthropic-api', 'ur config set model qwen3-coder:480b-cloud', 'ur config set base_url ollama http://localhost:11434', 'ur config set base_url llama.cpp http://localhost:9931/v1', 'ur config set provider.fallback ollama'],
   },
   {
     name: 'test-first',
@@ -378,8 +378,8 @@ const commands = [
     name: 'plugin',
     category: 'Interop',
     aliases: ['plugins'],
-    summary: 'Manage UR plugins and marketplaces for MCP tools, skills, templates, validators, language adapters, LSP servers, agents, hooks, output styles, and commands.',
-    examples: ['ur plugin search git', 'ur plugin search --capability skills --json', 'ur plugin show github@ur-plugins-official', 'ur plugin list', 'ur plugin install hello@ur-plugins-official', 'ur plugin update <plugin>'],
+    summary: 'Manage UR plugins and GitHub, Git, URL, npm, local, or settings-backed marketplaces for MCP tools, skills, templates, validators, language adapters, LSP servers, agents, hooks, output styles, and commands.',
+    examples: ['ur plugin marketplace add npm:@scope/catalog@latest', 'ur plugin search git', 'ur plugin search --capability skills --json', 'ur plugin show github@ur-plugins-official', 'ur plugin list', 'ur plugin install hello@ur-plugins-official', 'ur plugin update <plugin>'],
   },
   {
     name: 'provider',
@@ -547,8 +547,8 @@ const slashGroups = [
   },
   {
     title: 'Models, tools, and interop',
-    items: ['/model', '/model-doctor', '/model-route', '/escalate', '/mcp', '/plugin', '/skills', '/skill', '/sdk', '/a2a-card'],
-    text: 'Pick models, inspect capabilities, manage MCP/plugin extensions, browse prompt skills with /skills, run executable workflows with /skill, and expose interop surfaces.',
+    items: ['/model', '/provider', '/effort', '/thinking', '/fast', '/model-doctor', '/model-route', '/escalate', '/mcp', '/plugin', '/skills', '/skill', '/sdk', '/a2a-card'],
+    text: 'Pick providers and models, cycle only capability-backed effort selectors or provider-native boolean thinking, inspect capabilities, manage MCP/plugin extensions, browse prompt skills with /skills, run executable workflows with /skill, and expose interop surfaces.',
   },
   {
     title: 'Security operations',

package/documentation/index.html

@@ -45,7 +45,7 @@
     <main id="content" class="content">
       <header class="topbar">
         <div>
-          <p class="eyebrow">Version 1.83.1</p>
+          <p class="eyebrow">Version 1.84.0</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>
@@ -76,7 +76,7 @@
           </article>
           <article>
             <strong>Plugin marketplace</strong>
-            <span>Plugins can add MCP tools, skills, templates, validators, language adapters, LSP servers, agents, hooks, and output styles.</span>
+            <span>GitHub, Git, URL, npm, local, and settings-backed catalogs can add MCP tools, skills, templates, validators, language adapters, LSP servers, agents, hooks, and output styles.</span>
           </article>
           <article>
             <strong>Legal provider routing</strong>
@@ -100,7 +100,7 @@
           </article>
           <article>
             <strong>Deterministic commands</strong>
-            <span>The external runtime exposes 172 commands and 253 unique slash tokens; registry tests reject ambiguous names, broken loaders, and undocumented visible commands.</span>
+            <span>The external runtime exposes a source-derived command catalog; registry tests reject ambiguous names, broken loaders, undocumented visible aliases, and documented commands without implementations.</span>
           </article>
           <article>
             <strong>Safety and context</strong>
@@ -165,16 +165,32 @@ ur provider doctor agy</code></pre>
             <h3>API and local providers</h3>
             <pre><code>ur config set provider openai-compatible
 ur config set provider openai-api
-ur config set base_url http://localhost:11434/v1
+ur config set base_url ollama http://localhost:11434
+ur config set base_url llama.cpp http://localhost:9931/v1
+ur config set provider unsloth
 ur config set model qwen3-coder:480b-cloud
 ur config set provider.fallback ollama
 ur config set openai_transport responses
 ur config set responses.store false</code></pre>
-            <p>API providers require explicit selection and read keys from a key stored via <code>ur connect</code> (OS keychain) or from environment variables. OpenAI Responses is opt-in and privacy-first; Chat Completions remains the default. Local providers include Ollama, LM Studio, llama.cpp, and vLLM.</p>
+            <p>API providers require explicit selection and read keys from a key stored via <code>ur connect</code> (OS keychain) or from environment variables. Each configurable provider keeps its own <code>base_url</code>, so switching among Ollama, LM Studio, llama.cpp, vLLM, Unsloth, and API gateways restores the matching address. OpenAI Responses is opt-in and privacy-first; Chat Completions remains the default. Unsloth is an authenticated inference provider only.</p>
+          </article>
+          <article>
+            <h3>Capability-driven reasoning effort</h3>
+            <pre><code>/effort ultra
+/thinking on
+ur --model kimi-k3:cloud --effort high
+/model  # Up/Down model · Left/Right effort or boolean thinking · Enter apply</code></pre>
+            <p>The normalized vocabulary is <code>minimal</code>, <code>low</code>, <code>medium</code>, <code>high</code>, <code>xhigh</code>, <code>max</code>, and <code>ultra</code>; <code>/effort auto</code> clears an explicit choice. UR lists only capability-backed selectors it can map to the focused model's provider-native levels. <code>max</code> resolves to the highest supported non-Ultra tier. Ultra appears only for native <code>ultra</code>, advertised <code>max</code>/<code>xhigh</code>, or an explicit provider alias; the picker shows translations such as <code>ultra→max</code> and sends that exact provider value. Models that top out at <code>high</code>, boolean-thinking models, and unknown capabilities do not get Ultra. For boolean-thinking models on runtimes with a native toggle, Left selects off, Right selects on, and <code>t</code> toggles; <code>/thinking on|off</code> is the direct control. A graded <code>/effort</code> request on such a model enables thinking while reporting that no graded value was sent. Generic OpenAI-compatible runtimes receive no invented boolean field.</p>
+          </article>
+          <article>
+            <h3>OpenRouter responsive routing</h3>
+            <pre><code>ur config set provider openrouter
+/model  # cached catalog; Ctrl+R forces live refresh</code></pre>
+            <p>The endpoint-scoped model catalog is reused for five minutes, while forced refresh never substitutes stale data. Interactive requests prefer OpenRouter latency routing, a stable session ID, and provider-authored prompt-cache markers; explicit routing preferences and model variants still win.</p>
           </article>
           <article>
             <h3>Status bar and updates</h3>
-            <pre><code>Ollama | llama3 | ask | main | update 1.48.0 available</code></pre>
+            <pre><code>Ollama | llama3 | ask | main | update available</code></pre>
             <p>The interactive status bar shows only important runtime state: provider, model, mode, branch, active tasks, checks status when known, and update availability. It is hidden in CI, dumb terminals, and print mode.</p>
           </article>
           <article>

package/examples/provider_selection.md

@@ -38,7 +38,11 @@ ur config set provider codex-cli
 ```
 
 Inside a session, `/model` gives the same flow interactively: provider first,
-then only that provider's models. Verify the active pair any time:
+then only that provider's models. Use Up/Down to focus a model and Left/Right to
+cycle its capability-backed effort selectors before pressing Enter. Ultra is
+shown only when UR can map it to an advertised native `ultra`, `max`, `xhigh`,
+or explicit alias; the picker displays the exact mapping, such as
+`ultra→max`. Verify the active pair any time:
 
 ```sh
 ur provider status

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

@@ -7,7 +7,7 @@ plugins {
 }
 
 group = "dev.urnexus"
-version = "1.83.1"
+version = "1.84.0"
 
 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": "1.83.1",
+  "version": "1.84.0",
   "publisher": "ur-nexus",
   "engines": {
     "vscode": "^1.92.0"

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ur-agent",
-  "version": "1.83.1",
+  "version": "1.84.0",
   "description": "UR-Nexus — autonomous engineering workflow engine (plan, execute, test, verify, document, benchmark, reproduce)",
   "type": "module",
   "packageManager": "bun@1.3.14",