ur-agent 1.83.1 → 1.84.0

package/CHANGELOG.md

@@ -1,5 +1,62 @@
 # Changelog
 
+## 1.84.0
+
+- Added production npm marketplace sources with scoped-package and version
+  selectors, custom registries, isolated installation, atomic cache promotion
+  and rollback, actionable failures, and complete installed-plugin cache
+  invalidation. Public and technical plugin documentation now describes the
+  same executable contract.
+- Made input-token accounting provider-aware. OpenAI Responses, Anthropic,
+  Gemini, llama.cpp, and vLLM use native non-generating count paths where
+  available; Ollama, OpenRouter, LM Studio, Unsloth, and compatible endpoints
+  use request-shaped local estimation without reusing another provider's
+  fixture or carrying unreachable Bedrock/Vertex branches.
+- Corrected reasoning controls across dynamic providers. Ollama capability
+  discovery now treats ordinary thinking models as native boolean `think`
+  models and sends strings only for explicitly advertised graded ladders or
+  aliases. Added `/thinking on|off|toggle|status`; boolean-capable model pickers
+  use Left for off and Right for on only when the runtime has a real two-state
+  transport. `/effort` never claims a fabricated level, and Ultra remains
+  limited to an explicit provider-advertised beyond-high value. OpenRouter
+  provider selection now reuses its endpoint-scoped live catalogue instead of
+  forcing a slow refresh each time.
+- Replaced incomplete runtime scaffolding with working implementations: a
+  validated tmux-backed Tungsten tool and live monitor; a buildable KAIROS
+  assistant/proactive runtime with transcript persistence, dream lifecycle,
+  scheduling, and communication tools; complete tool output/permission
+  contracts; and a non-React MCP desired-state controller that handles
+  reconnect, authentication, partial failure, and late-connection races.
+- Completed the keybinding and SDK migrations. Shortcut labels now come from
+  the typed registry with correct last-write and Alt/Meta behavior, feature
+  gates hide unavailable bindings, remote tools receive a full fallback
+  contract, and SDK initialization emits canonical `Agent` names while
+  retaining compatibility only at the input boundary.
+- Fixed production-shell and test-isolation defects: `getCwd` is always bound,
+  spawned zsh sessions pass unmatched globs through instead of aborting,
+  missing grep/rg targets become precise model-facing recovery guidance, and
+  secondary-model tests no longer inherit cached live provider settings.
+- Synchronized the slash-command reference from the shipped registry, separated
+  commands from bundled skills and feature-gated internals, expanded KAIROS and
+  provider technical coverage, ignored only runtime-owned `.ur/` state, and
+  added pre-build version consistency enforcement across npm, documentation,
+  IDE extensions, source fallbacks, and the generated CLI.
+
+## 1.83.2
+
+- Synchronized the public guides, static documentation site, examples, and
+  source-derived technical specifications with the shipped capability-backed
+  effort contract. The docs now cover the complete selector ladder, `/effort`
+  and `--effort`, Left/Right model-picker control, provider-neutral `max`, and
+  exact Ultra mappings such as `ultra→max`, while clearly excluding models that
+  top out at `high`, Boolean-thinking models, and unknown capabilities.
+- Corrected adjacent provider documentation: provider-scoped `base_url`
+  persistence, Unsloth's provider-only inference boundary, LM Studio's enabled
+  status, and OpenRouter's five-minute endpoint cache and latency-oriented
+  request routing. Added regression coverage to keep public and technical
+  effort documentation synchronized. This release changes documentation and
+  source comments only; runtime behavior remains the 1.83.1 contract.
+
 ## 1.83.1
 
 - Made Ultra a capability-driven, visible ceiling selector without inventing a

package/README.md

@@ -263,7 +263,8 @@ not fall back to Ollama unless `ollama` is the selected provider.
 ### Legal Provider Auth
 
 UR-Nexus stores only safe provider preferences: provider name, model name,
-base URL, fallback preference, and non-secret settings. API keys must stay in
+base URL, fallback preference, and non-secret settings. API keys stay out of
+plaintext settings and are read from the OS keychain after `ur connect` or from
 environment variables. API, local, and OpenAI-compatible server providers are
 UR-native runtimes and behave like Ollama: UR owns the conversation loop, tool
 loop, errors, and output.
@@ -290,7 +291,7 @@ ur config set provider openrouter
 ur config set provider unsloth
 ur config set model qwen2.5-coder:7b
 ur provider select-model ollama qwen2.5-coder:7b --json
-ur config set base_url http://localhost:11434
+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
 ```
@@ -305,7 +306,8 @@ provider before the URL to configure it without switching first, for example
 provider's address independently, so switching among Ollama, LM Studio,
 llama.cpp, vLLM, Unsloth, or another compatible endpoint restores that
 provider's last URL automatically. Existing single-URL settings are migrated
-to the previously active provider on the first switch.
+to the previously active provider on the first provider switch or scoped
+base-URL write.
 
 OpenAI API traffic uses Chat Completions by default. The Responses transport is
 an explicit, provider-scoped opt-in with privacy-conscious defaults:
@@ -374,19 +376,28 @@ 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. The effort row updates to
-   the focused model's exact provider-advertised levels; use **Left/Right** to
-   cycle only those levels before pressing Enter. `ultra` is UR's visible
+   In the model catalog, use **Up/Down** to browse. For graded models, the effort row updates to
+   the focused model's capability-backed selectors; use **Left/Right** to cycle
+   only values UR can map to provider-native levels before pressing Enter. For
+   boolean-thinking models on runtimes with a native two-state mapping (currently
+   Ollama and direct Anthropic), Left selects off, Right selects on, and `t`
+   toggles. The same state is available directly through `/thinking on|off`.
+   Generic OpenAI-compatible runtimes never receive an invented boolean field.
+   `ultra` is UR's visible
    beyond-high ceiling selector. It appears only when the provider/model
    advertises `ultra`, `max`, `xhigh`, or an explicit equivalent, and the row
-   shows the exact mapping (for example, `ultra→max`). High-only and
-   boolean-thinking models do not get Ultra. 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
+   shows the exact mapping (for example, `ultra→max`). Models whose graded
+   ladder tops out at `high`, plus boolean-thinking models, do not get Ultra. A generic
+   `max` request resolves visibly to that model's highest supported non-Ultra tier
+   (commonly `max`, `xhigh`, or `high`), and that resolved value is sent to the provider. llama.cpp models
    are checked lazily through their model-scoped `/props` capability while the
-   cursor moves. Ollama models are checked through `/api/show`; Kimi K3 exposes
-   `low`, `high`, and `max`, and the chosen level is sent through Ollama's
-   native `think` field; Ultra maps to Kimi's advertised `max`. OpenRouter additionally
+   cursor moves. Ollama models are checked through `/api/show`; its `thinking`
+   capability enables boolean thinking without inventing a graded ladder.
+   If `/effort max` or another graded request is used for a boolean-only model,
+   UR enables thinking but reports that no graded level was sent.
+   GPT-OSS uses its documented `low|medium|high` values, while any other graded
+   values or Ultra aliases must be explicitly present in provider metadata.
+   The resolved value is sent through Ollama's native `think` field. OpenRouter additionally
    shows compact model names, FREE/PAID tier, context size, tool/reasoning
    support, and the full untruncated ID immediately below the focused entry.
    Its endpoint-scoped catalog is reused for five minutes; Ctrl+R forces an
@@ -613,6 +624,7 @@ validator, and Markdown language-adapter metadata.
 
 ```sh
 ur plugin list
+ur plugin marketplace add npm:@acme/ur-marketplace@latest
 ur plugin search git
 ur plugin search --capability skills --json
 ur plugin show github@ur-plugins-official
@@ -634,6 +646,13 @@ installed, project, and bundled plugin manifest and reports its declared
 components and capability surface, so you can review what a plugin touches
 before enabling it.
 
+Marketplace catalogs can come from GitHub/Git, direct URLs, npm packages,
+local files/directories, or inline settings. npm sources use
+`npm:<package>[@<version-range-or-dist-tag>]`, respect the user's npm registry
+and authentication configuration, and must ship `.ur-plugin/marketplace.json`.
+See the [Plugin Guide](docs/plugins.md) for private-registry configuration and
+refresh behavior.
+
 The npm package includes `README.md`, `QUALITY.md`, `docs/`, `documentation/`,
 and `plugins/`, so the npm package page and installed artifact both carry the
 marketplace documentation, core plugins, community staging directory, and