ur-agent 1.84.6 → 1.85.0

package/docs/AGENT_FEATURES.md

@@ -350,7 +350,7 @@ automatically changes the active provider.
 | Clean update checks | `ur upgrade`, `ur update`, `src/cli/update.ts` | Detects development/source checkouts and prints a short pull-or-install message instead of attempting self-mutation. npm-installed builds compare the local version with `ur-agent` on npm and print update, latest, registry failure, and malformed-response states without stale planning text. |
 | Bundled IDE extension install | `extensions/vscode-ur-inline-diffs/`, `src/utils/ide.ts`, `ur ide diff` | Public VS Code install now packages the repo's bundled inline-diffs extension as a local VSIX instead of trying an unpublished marketplace ID. The extension remains local-only and reviews `.ur/ide/diffs` bundles from the current workspace. |
 | Professional clarification dialogs | `AskUserQuestion`, `src/tools/AskUserQuestionTool/AskUserQuestionTool.tsx` | Mandatory for every question with concrete choices; plain text is reserved for genuinely open-ended answers. Prefers 2-8 focused options but preserves larger legitimate menus, infers labels from description-only objects, accepts prompt aliases, deduplicates equivalent labels, safely repairs single suggestions with a neutral rejection choice, and is loaded without ToolSearch preloading. |
-| NVIDIA agent/task split | `nvidiaHostedModels.ts`, `NvidiaNimTask`, `/model` | Positively audits hosted agent contracts and exposes a one-shot model only when the live account catalog returns it and a complete adapter exists (FLUX.1 Schnell, Stable Video Diffusion, or PaliGemma). Task selection shows purpose and never replaces the ongoing agent. |
+| NVIDIA Agentic/Special providers | live Build-card generator, `nvidiaHostedModels.ts`, `NvidiaSpecial`, `/model` | Audits 100 current Build cards and preserves every Free Endpoint card: 13 Agentic and 23 Special. Uses each card's exact HTTP/NVCF/gRPC route, method, function ID, request/response schema, input/output hints, Assets/async handling, and artifact decoding. Runtime errors never remove models; focused selection never replaces the ongoing agent. |
 | Documentation release sync | `README.md`, `docs/`, `documentation/`, `CHANGELOG.md` | Keeps the npm README, static documentation site, provider guide, usage guide, feature ledger, validation runbook, and release notes aligned with current release behavior. |
 
 ## v1.24.0 Additions

package/docs/AGENT_TRENDS.md

@@ -80,7 +80,7 @@ Inside an interactive session:
 
 | Trend | UR status | Current coverage | Professional next step |
 | --- | --- | --- | --- |
-| Provider-flexible, local-first runtime | Covered | Local Ollama; direct OpenAI, Anthropic, Gemini, OpenRouter, NVIDIA NIM, and OpenAI-compatible APIs; authenticated subscription-CLI adapters; explicit provider selection | Normalize capability discovery across providers and make automatic per-step routing opt-in |
+| Provider-flexible, local-first runtime | Covered | Local Ollama; direct OpenAI, Anthropic, Gemini, OpenRouter, NVIDIA Agentic/Special, and OpenAI-compatible APIs; authenticated subscription-CLI adapters; explicit provider selection | Normalize capability discovery across providers and make automatic per-step routing opt-in |
 | Model Context Protocol ecosystem | Covered | Stable TypeScript SDK v2 split client/server/core runtime; `ur mcp`, OAuth/XAA, fail-closed bounded tools, final `input_required` continuation, all workspace roots with change notifications, and the opt-in stateless web server | Broaden independent-client interoperability fixtures |
 | Protocol Tasks and Apps | Covered | Negotiated Tasks lifecycle, owner-isolated durable state, and a self-contained Apps resource through `ur mcp serve-web` | Broaden independent-client interoperability fixtures |
 | A2A / Agent Card interoperability | Covered | Stable official v1.1 SDK, native ProtoJSON JSON-RPC/HTTP+JSON, SSE streaming, task resubscription, authenticated push delivery with validated destinations, negotiated cards, tenant isolation, durable artifacts, and explicit v0.3 compatibility | Broaden independent-client/TCK fixtures; keep gRPC and extended cards unadvertised until deployed and tested |
@@ -168,7 +168,7 @@ compatibility transport rather than relabeling either wire schema.
 ## Model Runtime Position
 
 UR is local-first, not local-only. Ollama supports private on-device execution;
-direct adapters support OpenAI, Anthropic, Gemini, OpenRouter, NVIDIA NIM, and compatible
+direct adapters support OpenAI, Anthropic, Gemini, OpenRouter, NVIDIA Agentic/Special, and compatible
 endpoints; subscription adapters use the provider's authenticated CLI. Provider
 and model selection are explicit, credentials are resolved through the
 credential layer, and the optional fallback setting is diagnostic advice rather

package/docs/CONFIGURATION.md

@@ -88,7 +88,8 @@ receives general-purpose tools through this path.
 
 UR-Nexus supports official provider access paths only:
 
-- Explicit API providers: OpenAI, Anthropic, Gemini, OpenRouter, NVIDIA NIM, and
+- Explicit API providers: OpenAI, Anthropic, Gemini, OpenRouter, NVIDIA
+  Agentic/Special, and
   OpenAI-compatible endpoints.
 - Local/server providers: Ollama, LM Studio, llama.cpp, vLLM, and Unsloth OpenAI-compatible
   server mode.
@@ -133,6 +134,7 @@ ur config set provider anthropic-api
 ur config set provider gemini-api
 ur config set provider openrouter
 ur config set provider nvidia-nim
+ur config set provider nvidia-special
 ur config set provider openai-compatible
 ur config set provider unsloth
 ur provider doctor agy
@@ -188,7 +190,8 @@ When the active provider fails, `ur provider doctor` shows the configured
 recovery command; changing providers remains an explicit user action.
 
 Provider values accept canonical IDs and common aliases. Examples:
-`openai-api`, `anthropic-api`, `gemini-api`, `openrouter`, `nvidia-nim` (`NVIDIA Build`), `ollama`,
+`openai-api`, `anthropic-api`, `gemini-api`, `openrouter`, `nvidia-nim`
+(`NVIDIA Agentic`), `nvidia-special` (`NVIDIA Special`), `ollama`,
 `lmstudio`, `LM Studio`, `llama.cpp`, `vllm`, `unsloth` (`Unsloth Studio`), and the subscription CLI
 providers `codex-cli` (`chatgpt`), `claude-code-cli` (`claude`), `gemini-cli`
 (`gemini`), and `antigravity-cli` (`agy`). Values with spaces should be quoted
@@ -203,14 +206,14 @@ saved provider/model pair controls the runtime backend for the next agent
 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, Unsloth, or NVIDIA NIM address;
+active does not replace the saved Ollama, llama.cpp, Unsloth, or NVIDIA Agentic address;
 returning to any provider restores its own URL. Legacy `provider.baseUrl`
 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,
-Gemini, OpenRouter, and NVIDIA NIM) as well as local/server providers; built-in vendor URLs
+Gemini, OpenRouter, and NVIDIA Agentic) as well as local/server providers; built-in vendor URLs
 are fallbacks only. Discovery, doctor output, and request dispatch all resolve
 the same per-provider override. `/model` also opens an endpoint field when a
 disconnected local/server provider is selected.
@@ -280,27 +283,28 @@ VLLM_API_KEY=...               # optional when required by the endpoint
 UNSLOTH_API_KEY=...
 ```
 
-NVIDIA NIM defaults to `https://integrate.api.nvidia.com/v1`, discovers the
-connected account's models live, and accepts a provider-scoped override for an
-enterprise or self-hosted NIM. On NVIDIA's hosted endpoint, `/v1/models`
-establishes account availability and UR's audited positive contract registry
-establishes agent compatibility; only their intersection can become the
-ongoing model. It does not narrow hosted models using the separate NVCF
-deployment inventory; a configured NIM gateway uses its own model feed. Generic
+NVIDIA Agentic defaults to `https://integrate.api.nvidia.com/v1` and accepts a
+provider-scoped override for an enterprise or self-hosted NIM. Public Build
+models come from the current per-card Agentic contracts and are never filtered
+or removed by an account inventory or entitlement failure. A configured NIM
+gateway uses its own live model feed. Generic
 `openai-compatible` authentication is
 optional: `ur connect openai-compatible` or the picker's `K` key stores a
 credential when the chosen gateway needs one, without breaking anonymous
 local endpoints.
 
-The broader Build web page includes download-only NIMs; those are not valid
-hosted choices unless the authenticated `/v1/models` endpoint returns them.
-For the hosted service, UR focuses NVIDIA's documented fastest 30B agent model,
+Download-only Build cards are not hosted choices. For the public Agentic
+service, UR focuses NVIDIA's documented fastest 30B agent model,
 `nvidia/nemotron-3.5-lightning-30b-a3b`, first. Its thinking toggle maps to
 NVIDIA's model-specific `chat_template_kwargs.enable_thinking` field.
-The same key also authorizes the separately labelled one-shot FLUX.1 Schnell,
-Stable Video Diffusion, and PaliGemma adapters. Those use their exact
-`ai.api.nvidia.com` paths, never replace `provider.model`, and write generated
-media under `.ur/artifacts/nvidia/` unless an output path is supplied.
+The same key authorizes NVIDIA Special. The current generator audits 100 Build
+cards and preserves all 36 Free Endpoint entries across both providers: 13
+Agentic and 23 Special. Every executable entry uses that card's exact URL,
+HTTP/RPC method, function ID, and request/response schema. Twenty-two Special
+entries are executable through HTTP, direct NVCF, or five native gRPC services;
+the one unpublished protocol stays visible and labelled. Special selection
+never replaces `provider.model`; large inputs use NVIDIA Assets and returned
+artifacts are saved under `.ur/artifacts/nvidia/` unless a path is supplied.
 
 Unsloth is an inference-provider integration only. Start Unsloth Studio and
 load the model outside UR, connect its generated key with `ur connect unsloth`,

package/docs/TROUBLESHOOTING.md

@@ -207,19 +207,17 @@ ur provider doctor
 
 For an authenticated generic gateway, run `ur connect openai-compatible` or
 press `K` on its `/model` screen; the key is optional and stored separately
-from `OPENAI_API_KEY`. NVIDIA NIM uses `ur connect nvidia-nim` and keeps any
+from `OPENAI_API_KEY`. NVIDIA Agentic/Special use one key stored with
+`ur connect nvidia-nim` or `ur connect nvidia-special`; Agentic keeps any
 custom `base_url` scoped to that provider.
 
 ### NVIDIA lists a model but inference returns `Function … Not found for account`
 
-- Cause: NVIDIA's hosted `/v1/models` feed can change, or a listed model's
-  backing function can become unavailable for the connected account.
-- Fix: upgrade UR, run `ur provider doctor nvidia-nim`, then open `/model` and
-  press `Ctrl+R`. Hosted discovery intersects NVIDIA's live `/v1/models`
-  availability with UR's audited agent contracts. It does not intersect the
-  catalog with the separate NVCF deployment-function inventory. A definitive
-  runtime 404 removes only that model from the current endpoint-scoped session
-  catalog until the next explicit refresh.
+- Cause: the card is documented by NVIDIA, but its backing function is not
+  entitled or temporarily available for this API key/account.
+- Fix: verify the model card and key with `ur provider doctor nvidia-nim`, then
+  retry. UR uses the exact per-card endpoint and keeps the model visible. A 404
+  never removes it from the current or future catalog.
 - Privacy: UR does not display or retain the internal NVIDIA function UUID and
   account identifier from this error response.
 
@@ -227,17 +225,22 @@ If `chat_models` fails, reconnect a current build.nvidia.com key with
 `ur connect nvidia-nim`. A configured enterprise/self-hosted NIM endpoint is
 validated only against that gateway's own `/models` response.
 
-### An NVIDIA image/video/vision model is missing from `/model`
-
-- Ongoing models appear only when NVIDIA returns them live and their exact
-  documented contract supports UR's multi-turn streaming tool loop.
-- Dedicated models appear only in the `ONE-SHOT` section after UR implements
-  their endpoint, request, response, media constraints, and artifact handling.
-  The current set is FLUX.1 Schnell, Stable Video Diffusion, and PaliGemma.
-- Download-only Build cards and unadapted endpoints are intentionally absent;
-  UR does not present a model that it cannot execute correctly.
-- Stable Video Diffusion's hosted inline-image contract accepts JPEG/PNG files
-  smaller than 200 KB. Compress larger input before retrying.
+### An NVIDIA specialized model is missing from `/model`
+
+- Ongoing public models come from exact Build cards that advertise agent/tool
+  use; a configured enterprise NIM uses its own live `/models` feed.
+- Dedicated models appear under NVIDIA Special without relying on a chat
+  `/v1/models` response.
+  Run `bun run provider:nvidia-catalog` in a source checkout to refresh the
+  checked-in contracts from NVIDIA's current public reference.
+- Download-only cards are absent. Every Free Endpoint card is preserved. If a
+  card lacks a published invocation protocol, it remains visible with
+  `unpublished` status rather than receiving a guessed endpoint.
+- UR inlines small supported media and automatically uses NVIDIA's Asset API
+  for larger files or contracts that require an asset UUID/reference.
+- A task-specific entitlement failure never removes the model. Exact endpoint,
+  HTTP/RPC method, function ID, request/response schemas, and documentation are
+  available through the `NvidiaSpecial` describe action.
 
 ### A provider says the previous answer was empty after successful tool calls
 

package/docs/USAGE.md

@@ -240,7 +240,8 @@ Use `ur provider status` or `ur provider doctor <provider>` to see provider
 kind, external CLI usage, native tool/streaming support, and the boundary text.
 
 Provider values accept canonical IDs and common aliases. For example,
-`openai-api`, `anthropic-api`, `gemini-api`, `openrouter`, `nvidia-nim`, `ollama`,
+`openai-api`, `anthropic-api`, `gemini-api`, `openrouter`, `nvidia-nim`,
+`nvidia-special`, `ollama`,
 `lmstudio`, `llama.cpp`, `vllm`, and `unsloth` are UR-native runtime providers, and
 `codex-cli` (`chatgpt`), `claude-code-cli` (`claude`), `gemini-cli` (`gemini`),
 and `antigravity-cli` (`agy`) are subscription CLI providers.
@@ -257,7 +258,7 @@ 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, LM Studio, llama.cpp, vLLM, Unsloth, and NVIDIA NIM once, then switch providers without
+Ollama, LM Studio, llama.cpp, vLLM, Unsloth, and NVIDIA Agentic 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.
@@ -266,32 +267,30 @@ without making it active first. The `/model` picker offers the same endpoint
 entry flow for a disconnected local/server provider.
 
 Use `/model` in an interactive session to select provider first and model
-second. OpenAI API, Claude API, Gemini API, OpenRouter, NVIDIA NIM, Ollama, and
+second. OpenAI API, Claude API, Gemini API, OpenRouter, NVIDIA Agentic, Ollama, and
 OpenAI-compatible endpoints stay separate; a subscription login does not grant
 API-key access, and an API key does not grant subscription CLI access.
 
-NVIDIA NIM uses the build.nvidia.com key and hosted
+NVIDIA Agentic and NVIDIA Special share the build.nvidia.com key. Agentic uses
 `https://integrate.api.nvidia.com/v1` endpoint by default. Connect it with
-`ur connect nvidia-nim`; use `ur config set base_url nvidia-nim <url>` for a
-different NIM deployment. For the hosted endpoint, `/model` intersects the
-account's live `/v1/models` feed with exact NVIDIA-documented agent contracts.
-This excludes utility endpoints and dedicated single-use APIs from the ongoing
-agent list even when NVIDIA returns them. NVCF deployment functions are a
-separate API and do not narrow this hosted catalog. A custom NIM gateway
-retains its own independent catalog.
+`ur connect nvidia-nim` (or `ur connect nvidia-special`); use
+`ur config set base_url nvidia-nim <url>` for a
+different NIM deployment. Public Agentic entries come from exact per-card
+contracts and are not filtered or removed by NVIDIA account inventory errors.
+A custom NIM gateway retains its own independent live catalog.
 Download-only cards from the Build web catalog are not inserted into the
 hosted picker. NVIDIA's live `nemotron-3.5-lightning-30b-a3b` endpoint is
 focused first as its documented fastest 30B agent model; Left/Right controls
 that model's advertised on/off thinking switch.
-Verified specialized models returned by the connected account appear
-separately as `ONE-SHOT`, with their purpose visible before selection. FLUX.1
-Schnell generates a JPEG from text, Stable Video Diffusion generates an MP4
-from a sub-200-KB JPEG/PNG, and PaliGemma analyzes one image with one prompt.
-Selecting one leaves the ongoing agent unchanged; describe the task normally
-and UR uses `NvidiaNimTask` with the same stored NVIDIA key and exact model
-endpoint. Generated media defaults to `.ur/artifacts/nvidia/`. Other
-download-only, utility, and dedicated models remain hidden until UR has a
-complete executable adapter for their contract.
+NVIDIA Special appears as its own provider, with purpose and input/output hints
+before selection. The current Build audit preserves all 23 focused Free
+Endpoint cards. `NvidiaSpecial` describes or runs each card's exact inference
+URL, HTTP/RPC method, function ID, and request/response schema using the shared
+key. It supports HTTP, direct NVCF, async polling, NVIDIA Assets, and five
+documented Maxine/Riva gRPC services. Selecting one leaves the ongoing agent
+unchanged. Returned media/binary/JSON defaults to `.ur/artifacts/nvidia/`.
+Cards are never removed; an unpublished protocol remains visible and clearly
+cannot be invoked until NVIDIA publishes its contract.
 On the `/model` model screen, `K` adds or replaces a
 provider API key and `E` edits its endpoint. This also makes optional
 authentication practical for generic OpenAI-compatible gateways.

package/docs/VALIDATION.md

@@ -19,7 +19,7 @@ You need:
 
 ```sh
 ur --version
-# expected for this release: "1.84.6 (UR-Nexus)"
+# expected for this release: "1.85.0 (UR-Nexus)"
 ```
 
 ### 0.0 Redteam mode and Reverse Skills (1.81.0)
@@ -258,19 +258,18 @@ bun test test/bashCommandExecution.test.ts \
 Expected: macOS can execute `timeout 0.1 …` without GNU coreutils and reports
 124 when the deadline expires. Image-bearing tool results retain their text and
 image bytes across OpenAI Chat/Responses, Anthropic, Gemini, OpenRouter,
-NVIDIA NIM, Ollama, LM Studio, llama.cpp, vLLM, Unsloth, and generic OpenAI-compatible
+NVIDIA Agentic/Special, Ollama, LM Studio, llama.cpp, vLLM, Unsloth, and generic OpenAI-compatible
 request shapes.
 
-The NVIDIA fixture also verifies hosted/default and overridden endpoints,
-Bearer discovery from NVIDIA's live `/v1/models` endpoint, positive agent
-contract intersection, selected-model doctor diagnostics, redaction of
-internal NVIDIA account/function IDs, endpoint-scoped runtime invalidation,
-native dispatch, the preferred Lightning endpoint and its model-scoped
-`enable_thinking` switch, documented effort aliases, and no Ultra on an unknown model.
-`nvidiaTaskRuntime.test.ts` verifies the exact FLUX, Stable Video Diffusion,
-and PaliGemma endpoints and payloads; Bearer reuse; async request-ID polling;
-artifact decoding; media constraints; and rejection of every model without an
-implemented adapter. In
+The NVIDIA fixtures verify the 100-card/36-Free-Endpoint audit, the 13 Agentic
+and 23 Special split, shared credential ownership, exact per-card endpoint
+routing, public-catalog preservation after entitlement failures, enterprise
+gateway isolation, redaction of internal NVIDIA account/function IDs, native
+dispatch, Lightning thinking, documented effort aliases, and no Ultra on an
+unknown model. `nvidiaTaskRuntime.test.ts` verifies PaliGemma, Cosmos Transfer,
+Cosmos3 async polling, direct-function BEV multi-artifacts, embeddings,
+NVIDIA Asset upload/cleanup, generated-schema validation, and all five exact
+public gRPC service/method and streaming shapes. In
 `/model`, select `openai-compatible` and verify `K` can
 add or replace its optional key while `E` continues to edit only its endpoint.
 

package/docs/providers.md

@@ -37,7 +37,8 @@ multimodal input, external CLI boundary, and sandbox scope:
 | Claude API | API | UR-native | no | yes | yes | yes | UR Bash/File sandbox | `api:anthropic` | `ANTHROPIC_API_KEY` |
 | Gemini API | API | UR-native | no | yes | yes | yes | UR Bash/File sandbox | `api:gemini` | `GEMINI_API_KEY` |
 | OpenRouter | API/router | UR-native | no | yes | yes | yes | UR Bash/File sandbox | `api:openrouter` | `OPENROUTER_API_KEY` |
-| NVIDIA NIM | hosted/server API | UR-native | no | yes | yes | model-dependent | UR Bash/File sandbox | `api:nvidia-nim` | `NVIDIA_API_KEY`; configurable NIM endpoint |
+| NVIDIA Agentic | hosted/server API | UR-native | no | yes | yes | model-dependent | UR Bash/File sandbox | `api:nvidia-nim` | `NVIDIA_API_KEY`; public per-card endpoints or configurable NIM gateway |
+| NVIDIA Special | hosted/focused-task API | UR-native | no | task-specific | task-specific | task-specific | UR tool permission flow | `api:nvidia-special` | shared `NVIDIA_API_KEY`; exact HTTP/NVCF/gRPC contracts |
 | OpenAI-compatible | server/API | UR-native | no | yes | yes | endpoint-dependent | UR Bash/File sandbox | `openai-compatible` | optional `OPENAI_COMPATIBLE_API_KEY`; never reuses `OPENAI_API_KEY` |
 | Ollama | local/server | UR-native | no | yes | yes | yes* | UR Bash/File sandbox | `ollama` | configured local, LAN, or hosted endpoint; optional `OLLAMA_API_KEY` |
 | LM Studio | local/server | UR-native | no | yes | yes | yes | UR Bash/File sandbox | `openai-compatible:lmstudio` | configured endpoint; optional `LMSTUDIO_API_KEY` |
@@ -161,7 +162,7 @@ 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, OpenRouter, and NVIDIA NIM can each target a separate compatible gateway using
+Gemini API, OpenRouter, and NVIDIA Agentic can each target a separate compatible gateway using
 the same command. Their official URLs are defaults, not hardcoded dispatch
 destinations; model discovery and inference use the selected provider's saved
 URL. Subscription CLI providers remain vendor-managed and do not accept a base
@@ -212,15 +213,14 @@ or has unknown capability metadata. Arbitrary
 labels such as `deep` still require an explicit provider alias because UR
 cannot infer their rank.
 
-NVIDIA NIM is live-discovery first. UR enriches a discovered model only when
-NVIDIA's current model API reference documents that exact model's
-`reasoning_effort` values. Documented `none` appears as Minimal and `max`
-appears as Ultra while the request preserves NVIDIA's wire values. An unknown
-NIM model never inherits an invented graded ladder.
-Hosted discovery is also a positive agent-contract intersection: a row in the
-mixed NVIDIA `/v1/models` inventory is not sufficient by itself to enter the
-ongoing agent picker. Verified dedicated media/VLM endpoints are exposed only
-as one-shot task contracts and cannot pass provider/model validation.
+Public NVIDIA Agentic discovery comes from current Build Free Endpoint cards
+that advertise agent/tool use. NVIDIA's account inventory can enrich but never
+filter or remove those models. UR applies only model-specific documented
+reasoning ladders: `none` appears as Minimal and a documented `max` can map to
+Ultra while preserving NVIDIA's wire value. Unknown models never inherit a
+ladder. Focused media, analysis, embedding, safety, translation, and gRPC
+contracts are isolated in NVIDIA Special and cannot pass ongoing-agent model
+validation.
 
 For an unknown or newly released model, UR waits for provider-authored model
 metadata or a supported model-scoped probe before adding thinking parameters.
@@ -298,10 +298,10 @@ and [fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode)
 UR uses only provider-documented acceleration controls. OpenAI Responses
 already has native streaming and WebSocket continuation; Gemini 2.5+ implicit
 caching is automatic. Google's Priority tier requires the Interactions API and
-is not a valid `generateContent` option. NVIDIA NIM and local servers publish
+is not a valid `generateContent` option. NVIDIA Agentic and local servers publish
 no universal OpenRouter-style routing field, so UR does not invent one.
 API-key entry for
-OpenAI, Claude, Gemini, OpenRouter, NVIDIA NIM, and authenticated compatible
+OpenAI, Claude, Gemini, OpenRouter, NVIDIA Agentic/Special, and authenticated compatible
 endpoints is a single aligned masked row; the key is stored in the OS keychain
 flow and is never written to settings. On the model screen, `K` adds or
 replaces the selected HTTP provider's key and `E` edits its endpoint. Generic
@@ -313,7 +313,7 @@ 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. NVIDIA's hosted NIM API has no documented token-count route;
-NVIDIA NIM, Ollama, OpenRouter, LM Studio, Unsloth, and subscription CLIs use a
+NVIDIA Agentic, 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,
@@ -344,7 +344,7 @@ error, not a successful `Did 0 searches` result.
 When you select a UR-native provider and model, every agent request is routed
 through that provider's backend:
 
-- **API providers** make direct HTTP calls in each provider's native wire format: Anthropic uses `x-api-key` + `anthropic-version` against `/v1/messages`; OpenAI uses `Authorization: Bearer` against `/v1/chat/completions` by default or `/v1/responses` when explicitly selected; Gemini uses `x-goog-api-key` against `…:generateContent`; OpenRouter and NVIDIA NIM use their OpenAI-compatible chat endpoints.
+- **API providers** make direct calls in each provider's native wire format: Anthropic uses `x-api-key` + `anthropic-version` against `/v1/messages`; OpenAI uses `Authorization: Bearer` against `/v1/chat/completions` by default or `/v1/responses` when explicitly selected; Gemini uses `x-goog-api-key` against `…:generateContent`; OpenRouter and NVIDIA Agentic use documented chat endpoints; NVIDIA Special uses per-card HTTP, NVCF, or gRPC inference.
 - **Local/server providers** connect to the configured local or OpenAI-compatible endpoint (`/v1/chat/completions` for LM Studio, llama.cpp and vLLM; the native tags/chat API for Ollama)
 - **Subscription CLI providers** (Codex CLI, Claude Code, Gemini CLI,
   Antigravity) dispatch the turn through the vendor's official CLI using your
@@ -455,7 +455,8 @@ ur config set provider anthropic-api
 | --- | --- | --- |
 | API providers (openai-api, anthropic-api, gemini-api) | Live discovery from the provider's `/models` endpoint using your connected key (curated fallback until connected) | live |
 | OpenRouter | Live `/models` discovery with an endpoint-scoped five-minute cache; Ctrl+R forces a fresh request with no stale fallback | live/cache |
-| NVIDIA NIM | Hosted: live `/models` availability intersected with audited agent contracts, plus separately labelled one-shot models with implemented adapters. Configured NIM gateway: its own live `/models` catalog | live |
+| NVIDIA Agentic | Public Build: generated per-card agent contracts, never narrowed by account inventory. Configured NIM gateway: its own live `/models` catalog | live card contracts or gateway live |
+| NVIDIA Special | Generated from every current focused Free Endpoint card, including exact HTTP/NVCF/gRPC inference metadata | static generated contracts |
 | Local/server providers (ollama, lmstudio, llama.cpp, vllm, unsloth) | Dynamic discovery from the selected provider endpoint | live |
 | OpenAI-compatible | Dynamic discovery from configured endpoint | live |
 | Subscription CLIs (codex-cli, claude-code-cli, gemini-cli, antigravity-cli) | Curated list (the official CLIs expose no models API); first-class in `/model`, dispatched via the official CLI. External CLI behavior depends on the vendor CLI. Log in with `ur auth <provider>` | static |
@@ -482,7 +483,7 @@ provider's successful live catalog remains authoritative for that account.
 - `anthropic-api` — requires `ANTHROPIC_API_KEY`
 - `gemini-api` — requires `GEMINI_API_KEY`
 - `openrouter` — requires `OPENROUTER_API_KEY`
-- `nvidia-nim` — requires `NVIDIA_API_KEY` for build.nvidia.com; endpoint is configurable
+- `nvidia-nim` / `nvidia-special` — share `NVIDIA_API_KEY`; Agentic's enterprise endpoint is configurable, while Special routes each public model to its card-specific contract
 
 **Local/server providers** require local runtime or endpoint:
 - `ollama` — configurable local, LAN, or hosted Ollama server
@@ -616,6 +617,7 @@ Provider config and doctor commands accept canonical IDs and common aliases:
 | `gemini-api` | `gemini api`, `google gemini api` |
 | `openrouter` | `openrouter api` |
 | `nvidia-nim` | `nvidia`, `NVIDIA Build`, `nvidia api`, `nim` |
+| `nvidia-special` | `NVIDIA Special`, `nvidia task`, `nvidia one-shot` |
 | `openai-compatible` | `compatible`, `openai compatible` |
 | `ollama` | `ollama local` |
 | `lmstudio` | `LM Studio`, `lm-studio` |
@@ -680,36 +682,35 @@ The compatible provider's key is optional and provider-scoped. Add or replace
 it with `ur connect openai-compatible`, `/connect openai-compatible`, or `K`
 in the `/model` model screen. Anonymous endpoints continue to work without it.
 
-### NVIDIA NIM / build.nvidia.com
+### NVIDIA Agentic and NVIDIA Special / build.nvidia.com
 
-NVIDIA NIM is a UR-native, OpenAI-compatible provider with live discovery:
+NVIDIA is exposed through two UR-native providers sharing one stored key:
 
 ```sh
 echo "$NVIDIA_API_KEY" | ur connect nvidia-nim
 ur config set provider nvidia-nim
 ur provider doctor nvidia-nim
+# Focused inference uses the same key:
+ur config set provider nvidia-special
 # Optional self-hosted/enterprise gateway:
 ur config set base_url nvidia-nim https://nim-gateway.example/v1
 ```
 
-The default is `https://integrate.api.nvidia.com/v1`. NVIDIA's authenticated
-`/v1/models` response proves current account availability but mixes agents,
-utilities, VLMs, and generation functions. UR intersects it with a reviewed
-positive agent registry before allowing a model to own the multi-turn tool
-loop. It does not intersect the result with NVCF's separate deployment-function
-inventory. A custom enterprise or self-hosted NIM remains independent and uses
-only that configured gateway's `/models` response.
-
-The Build web catalog also contains download-only NIMs. UR does not add those
-cards to the hosted picker: only IDs returned by the authenticated hosted
-`/v1/models` endpoint can appear. UR focuses
+NVIDIA Agentic defaults to `https://integrate.api.nvidia.com/v1`. For the
+public service, UR generates its agent catalog from every current Free Endpoint
+card that explicitly advertises agent/tool use. `/v1/models` is not an
+allowlist: account entitlement failures are reported and never remove a model.
+A custom enterprise or self-hosted NIM remains independent and uses only that
+configured gateway's live `/models` response. Download-only cards never enter
+either hosted provider. UR focuses
 `nvidia/nemotron-3.5-lightning-30b-a3b` first because NVIDIA documents it as
 its fastest 30B model for long-running agents. Left/Right can turn that exact
 model's thinking off/on through NVIDIA's documented
 `chat_template_kwargs.enable_thinking`; other NIM models receive only their
 own advertised reasoning contract.
 
-UR calls `/models` and `/chat/completions`. It counts NVIDIA requests with a
+Agentic uses each generated card's documented chat endpoint (or the configured
+gateway). It counts NVIDIA requests with a
 provider-wire local estimate instead of first calling the unsupported hosted
 `/messages/count_tokens` route, and never launches a hidden completion.
 Streaming, standard tool calls, and image input use the
@@ -719,31 +720,29 @@ documented Nemotron coding-agent models, UR includes NVIDIA's
 [NIM LLM API reference](https://docs.api.nvidia.com/nim/reference/llm-apis)
 and [NIM endpoint guide](https://docs.nvidia.com/nim/large-language-models/latest/tutorials.html).
 
-NVIDIA's dedicated APIs are a separate one-shot surface. `/model` labels them
-`ONE-SHOT`, shows the task purpose, and keeps the current agent model when one
-is selected. `NvidiaNimTask` currently implements three exact contracts:
-
-- [FLUX.1 Schnell](https://docs.api.nvidia.com/nim/reference/black-forest-labs-flux_1-schnell-infer)
-  → text-to-JPEG at
-  `https://ai.api.nvidia.com/v1/genai/black-forest-labs/flux.1-schnell`.
-- [Stable Video Diffusion](https://docs.api.nvidia.com/nim/reference/stabilityai-stable-video-diffusion-infer)
-  → JPEG/PNG-to-MP4 at
-  `https://ai.api.nvidia.com/v1/genai/stabilityai/stable-video-diffusion`;
-  NVIDIA's inline input contract requires a source smaller than 200 KB.
-- [PaliGemma](https://docs.api.nvidia.com/nim/reference/google-paligemma-infer)
-  → one-image visual analysis at
-  `https://ai.api.nvidia.com/v1/vlm/google/paligemma`.
-
-They reuse `NVIDIA_API_KEY`, poll documented asynchronous responses when
-necessary, save generated files under `.ur/artifacts/nvidia/` by default, and
-return only text/path metadata to the enclosing agent. Unsupported,
-download-only, and unadapted dedicated models never appear as usable choices.
-
-`ur provider doctor nvidia-nim` verifies the hosted catalog and selected model
-against the live `/v1/models` response. If NVIDIA rejects a listed model after
-selection, UR redacts NVIDIA's internal function/account IDs, removes that
-model from the current endpoint-scoped session catalog, and asks the user to
-select another model. `Ctrl+R` explicitly retries discovery.
+NVIDIA Special is a separate focused-task provider. Selecting a row stores a
+one-shot preference and keeps the current chat provider/model. The generator
+crawls all 100 current Build cards and preserves every card labelled Free
+Endpoint: 36 total, split into 13 Agentic and 23 Special. Thirty-five publish a
+complete executable contract; 22 are Special. The remaining VoiceChat card is
+kept visible with `unpublished` transport because NVIDIA currently provides no
+public request/response protocol.
+
+Every executable row records the purpose, input/output hints, exact endpoint,
+HTTP or RPC method, card-specific function ID, request and response schemas,
+documentation, and current NVIDIA availability flag. HTTP cards use their own
+`integrate.api.nvidia.com`, `ai.api.nvidia.com`, or direct
+`{function-id}.invocation.api.nvcf.nvidia.com` route. Five Maxine/Riva cards use
+their exact public service/method on `grpc.nvcf.nvidia.com:443`.
+
+`NvidiaSpecial` exposes `describe` for the full contract and `run` for
+convenience text/image/audio/video inputs or exact `payload_json` with
+JSON-pointer file bindings. UR inlines small media, uses NVIDIA Assets for
+larger inputs, polls documented asynchronous requests, decodes single or
+multiple returned artifacts, and saves output under `.ur/artifacts/nvidia/`
+unless the caller supplies a path. Both providers reuse `NVIDIA_API_KEY`.
+NVIDIA availability and entitlement errors are redacted and reported, but no
+model is ever removed from either generated catalog.
 
 Local/server providers use their normal endpoints:
 
@@ -801,7 +800,7 @@ Required variables:
 | --- | --- | --- |
 | 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`) |
-| NVIDIA NIM | `NVIDIA_API_KEY`, `NVIDIA_MODEL` | `NVIDIA_BASE_URL` (defaults to `https://integrate.api.nvidia.com/v1`) |
+| NVIDIA Agentic | `NVIDIA_API_KEY`, `NVIDIA_MODEL` | `NVIDIA_BASE_URL` (defaults to `https://integrate.api.nvidia.com/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

@@ -68,8 +68,8 @@ const featureGroups = [
   {
     title: 'Providers and auth',
     tags: ['subscription', 'API', 'local', 'effort', 'status bar'],
-    text: 'UR-native API/local/OpenAI-compatible runtimes, provider-scoped endpoints, audited NVIDIA agent discovery plus exact one-shot image/video/vision adapters, provider-only Unsloth inference, optional compatible-gateway keys, 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 nvidia-nim', 'ur connect status', 'ur config set provider nvidia-nim', 'ur config set provider openai-api', 'ur config set provider ollama', 'ur config set base_url llama.cpp http://localhost:9931/v1', '/model', '/effort ultra', '/thinking on'],
+    text: 'UR-native API/local/OpenAI-compatible runtimes, provider-scoped endpoints, NVIDIA Agentic plus NVIDIA Special with all 36 current Build Free Endpoint cards and exact per-card HTTP/NVCF/gRPC inference contracts, provider-only Unsloth inference, optional compatible-gateway keys, capability-driven reasoning effort, responsive OpenRouter routing, first-class subscription CLI providers dispatched through 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 nvidia-nim', 'ur connect status', 'ur config set provider nvidia-nim', 'ur config set provider nvidia-special', 'ur config set provider openai-api', 'ur config set provider ollama', 'ur config set base_url llama.cpp http://localhost:9931/v1', '/model', '/effort ultra', '/thinking on'],
   },
   {
     title: 'Security and operations',

package/documentation/index.html

@@ -45,7 +45,7 @@
     <main id="content" class="content">
       <header class="topbar">
         <div>
-          <p class="eyebrow">Version 1.84.6</p>
+          <p class="eyebrow">Version 1.85.0</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>
@@ -166,6 +166,7 @@ ur provider doctor agy</code></pre>
             <pre><code>ur config set provider openai-compatible
 ur config set provider openai-api
 ur config set provider nvidia-nim
+ur config set provider nvidia-special
 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
@@ -174,7 +175,7 @@ ur config set provider.fallback ollama
 ur config set openai_transport responses
 ur config set responses.store false
 ur config set anthropic.speed fast</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. Each configurable provider keeps its own <code>base_url</code>, so switching among Ollama, LM Studio, llama.cpp, vLLM, Unsloth, NVIDIA NIM, and API gateways restores the matching address. OpenAI Responses is opt-in and privacy-first; Chat Completions remains the default. Direct Anthropic preserves prompt-cache breakpoints, streams tool inputs with its per-tool control, and enables the documented premium fast tier only when explicitly configured for a supported model. Unsloth is an authenticated inference provider only.</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, NVIDIA Agentic, and API gateways restores the matching address. OpenAI Responses is opt-in and privacy-first; Chat Completions remains the default. Direct Anthropic preserves prompt-cache breakpoints, streams tool inputs with its per-tool control, and enables the documented premium fast tier only when explicitly configured for a supported model. Unsloth is an authenticated inference provider only.</p>
           </article>
           <article>
             <h3>Capability-driven reasoning effort</h3>
@@ -191,12 +192,13 @@ ur --model kimi-k3:cloud --effort high
             <p>The endpoint-scoped model catalog is reused for five minutes, while forced refresh never substitutes stale data. Tool turns preserve OpenRouter Auto Exacto for live throughput and tool-call reliability; non-tool turns prefer end-to-end throughput. Stable session affinity keeps prompt caches warm, while configurable routing preferences and the <code>:nitro</code>, <code>:floor</code>, and <code>:exacto</code> variants remain authoritative.</p>
           </article>
           <article>
-            <h3>NVIDIA NIM and compatible API keys</h3>
+            <h3>NVIDIA Agentic, NVIDIA Special, and compatible API keys</h3>
             <pre><code>ur connect nvidia-nim
 ur config set provider nvidia-nim
+ur config set provider nvidia-special
 ur config set base_url nvidia-nim https://integrate.api.nvidia.com/v1
 /model  # K API key · E endpoint</code></pre>
-            <p>NVIDIA NIM separates ongoing agents from specialized one-shot models. Hosted agent discovery intersects the live <code>/v1/models</code> inventory with audited tool-loop contracts; download-only, utility, and unadapted models stay hidden. The separately labelled one-shot section shows a model only when the connected account returns it and UR has a complete adapter: FLUX.1 Schnell text-to-image, Stable Video Diffusion image-to-video, and PaliGemma image understanding use their exact documented endpoints and the same stored NVIDIA key. Their purpose appears before selection, generated media is saved under <code>.ur/artifacts/nvidia/</code>, and the ongoing agent never changes. Nemotron 3.5 Lightning retains its documented on/off thinking field; unknown models inherit no fabricated effort. Generic OpenAI-compatible endpoints can store an optional dedicated key, while anonymous endpoints remain valid.</p>
+            <p>NVIDIA is split into NVIDIA Agentic for the ongoing tool loop and NVIDIA Special for focused inference; both share one stored <code>NVIDIA_API_KEY</code>. UR audits all 100 current Build cards and preserves every Free Endpoint card: 13 Agentic and 23 Special. Thirty-five publish executable contracts; the one unpublished protocol stays visible and labelled. Each row shows purpose, input, and output, and uses that card's exact HTTP, direct NVCF, or gRPC endpoint, method, function ID, and request/response schema. NVIDIA Assets, asynchronous polling, five native Maxine/Riva gRPC services, and media/binary/JSON artifact saving are built in. Account errors never remove models, and choosing a Special task never changes the ongoing agent. Nemotron 3.5 Lightning retains its documented on/off thinking field; unknown models inherit no fabricated effort. Generic OpenAI-compatible endpoints can store an optional dedicated key, while anonymous endpoints remain valid.</p>
           </article>
           <article>
             <h3>Portable shell deadlines</h3>
@@ -207,7 +209,7 @@ ur config set base_url nvidia-nim https://integrate.api.nvidia.com/v1
           <article>
             <h3>Tool images across providers</h3>
             <pre><code>Computer screenshot → tool result → vision model</code></pre>
-            <p>Every UR-native provider preserves image-bearing tool output in its valid wire shape. OpenRouter, NVIDIA NIM, and other Chat-Completions backends keep the tool result textual and send the image in the next multimodal user turn; Gemini, OpenAI Responses, Anthropic, and Ollama use their native rich forms. Vision still depends on the selected model.</p>
+            <p>Every UR-native provider preserves image-bearing tool output in its valid wire shape. OpenRouter, NVIDIA Agentic, and other Chat-Completions backends keep the tool result textual and send the image in the next multimodal user turn; Gemini, OpenAI Responses, Anthropic, and Ollama use their native rich forms. Vision still depends on the selected model.</p>
           </article>
           <article>
             <h3>Status bar and updates</h3>