ur-agent 1.84.7 → 1.85.1

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| Public VS Code install now packages the repo's bundled inline-diffs extension as a local VSIX instead of trying an unpublished marketplace ID.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 | generated NVIDIA OpenAPI catalog, `nvidiaHostedModels.ts`, `NvidiaNimTask`, `/model` | Intersects live chat inventory with positive agent contracts and exposes 92 public hosted one-shot contracts across NVIDIA's AI, retrieval, health, optimization, and climate APIs. Task selection shows purpose, validates the documented schema, supports NVIDIA Assets and asynchronous/binary results, 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
@@ -170,6 +172,22 @@ Anthropic's supported cache-control shape. Streaming requests also set
 arrive as Claude generates them instead of waiting for server-side buffering.
 Both behaviors use Anthropic's documented native fields and require no setting.
 
+An Anthropic identity-linked API key can act across more than one workspace and
+requires `anthropic-workspace-id` on every API call. Set its non-secret Console
+workspace ID once:
+
+```sh
+ur config set anthropic.workspace_id wrkspc_...
+# environment-only alternative
+export ANTHROPIC_WORKSPACE_ID=wrkspc_...
+```
+
+The selected ID is applied consistently to `/v1/models`, `/v1/messages`,
+streaming messages, `/v1/messages/count_tokens`, and provider diagnostics.
+Workspace-scoped keys need no extra setting. Clear the saved value with
+`ur config set anthropic.workspace_id auto`. When adding a key and workspace
+together, use `ur connect anthropic-api --workspace-id wrkspc_...`.
+
 Anthropic fast mode is a separate, premium research-preview tier. It is off by
 default and can be requested explicitly:
 
@@ -188,7 +206,8 @@ 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 +222,14 @@ 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.
@@ -270,6 +289,7 @@ it in the environment when you explicitly choose API mode:
 OPENAI_API_KEY=...
 OPENAI_COMPATIBLE_API_KEY=...
 ANTHROPIC_API_KEY=...
+ANTHROPIC_WORKSPACE_ID=wrkspc_... # identity-linked Anthropic keys only
 GEMINI_API_KEY=...
 OPENROUTER_API_KEY=...
 NVIDIA_API_KEY=...
@@ -280,29 +300,28 @@ 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 authorizes the separately labelled one-shot catalog generated from
-NVIDIA's public OpenAPI reference. Its 92 task contracts use the exact
-`integrate.api`, `ai.api`, `health.api`, `optimize.api`, or `climate.api`
-NVIDIA path for each model. They never replace `provider.model`; large inputs
-use NVIDIA Assets and binary or large JSON output is saved 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`,
@@ -333,6 +352,11 @@ opaque compacted window, set `UR_OPENAI_RESPONSES_STATE_KEY` to exactly 32
 bytes encoded as 64 hexadecimal characters or base64. Without that key UR
 refuses to persist compacted context.
 
+HTTP 429 remains retryable for real transient rate limits. Machine-readable
+account, billing, and exhausted-quota failures such as `billing_not_active` and
+`insufficient_quota` are permanent for the unchanged request, so UR reports
+them immediately instead of spending the retry window in `requesting`.
+
 ### Reconfiguring the Ollama host
 
 The endpoint can be changed from UR in four ways, in order of precedence:

package/docs/TROUBLESHOOTING.md

@@ -207,19 +207,46 @@ 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.
 
+### Anthropic says `anthropic-workspace-id is required`
+
+- Cause: the API key is identity-linked and can act across workspaces. Anthropic
+  requires the target workspace on model discovery and every runtime request.
+- Fix: copy the `wrkspc_...` ID from Claude Console → Settings → Workspaces,
+  then configure it and re-run doctor. The workspace ID is not the API key.
+
+```sh
+ur config set anthropic.workspace_id wrkspc_...
+ur provider doctor anthropic-api
+```
+
+`ANTHROPIC_WORKSPACE_ID` is the environment-only alternative. If the key was
+created inside one workspace and is already workspace-scoped, no header is
+needed. `auto` clears an incorrect saved selection. UR cannot safely infer the
+Default Workspace ID because Anthropic omits that workspace from its list API.
+
+### OpenAI stays on `requesting` and then reports a billing 429
+
+- Cause: older retry classification treated every HTTP 429 as a temporary rate
+  limit. OpenAI also uses 429 for permanent request-state failures such as
+  `billing_not_active` and `insufficient_quota`.
+- Current behavior: UR reads the machine error code, reports permanent account
+  or billing failures immediately, and still retries genuine transient rate
+  limits. The same rule applies to Chat Completions and Responses.
+- Fix for `billing_not_active`: activate API billing for the project/account or
+  connect a key belonging to an active billed project. Changing models or
+  transports cannot activate the account.
+
 ### 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.
 
@@ -229,19 +256,20 @@ validated only against that gateway's own `/models` response.
 
 ### An NVIDIA specialized 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 come from UR's generated NVIDIA OpenAPI catalog and appear
-  in the `ONE-SHOT` section without relying on the chat `/v1/models` response.
+- 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, status-only routes, staging URLs, broken documentation,
-  and operations without a public hosted POST contract are intentionally absent.
+- 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 removes only that model until `Ctrl+R`;
-  the exact endpoint and documentation link are available through the
-  `NvidiaNimTask` describe action.
+- 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

@@ -186,6 +186,7 @@ ur config set openrouter.preferred_min_throughput 40
 ur config set openrouter.preferred_max_latency 3
 ur config set openrouter.service_tier priority
 ur config set openrouter.speed fast
+ur config set anthropic.workspace_id wrkspc_...
 ```
 
 `auto` is the recommended default. `priority`/`fast` are optional paid upstream
@@ -195,6 +196,17 @@ throughput-, price-, or tool-quality-first virtual route.
 
 Direct Anthropic sessions preserve prompt-cache breakpoints and stream large
 tool arguments with Anthropic's per-tool `eager_input_streaming` control.
+If Anthropic identifies the key as identity-linked, select the Console
+workspace before refreshing models or sending a turn:
+
+```sh
+ur config set anthropic.workspace_id wrkspc_...
+# or: export ANTHROPIC_WORKSPACE_ID=wrkspc_...
+```
+
+The selection is shared by discovery, doctor, inference, streaming, and token
+counting. Workspace-scoped keys require no extra value; use
+`ur config set anthropic.workspace_id auto` to clear it.
 Accounts admitted to Anthropic's premium fast-mode research preview can opt in
 for its supported Opus models:
 
@@ -216,6 +228,9 @@ background/poll/cancel support, WebSocket continuation, server compaction, and
 deferred tool search. Remote storage is off by default. Local state contains
 only bounded identifiers/status/cursors unless a 32-byte
 `UR_OPENAI_RESPONSES_STATE_KEY` is supplied for AES-256-GCM compacted context.
+Permanent billing/account 429s are shown immediately on both OpenAI transports;
+UR retries only responses that can plausibly succeed without configuration or
+billing changes.
 
 In the interactive app, `/model` chooses a provider first and then a model from
 that provider only. The saved pair controls the runtime backend for the next
@@ -240,7 +255,8 @@ 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.
@@ -248,7 +264,9 @@ 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`,
-`OPENROUTER_API_KEY`, `NVIDIA_API_KEY`, and `UNSLOTH_API_KEY`. Subscription CLIs are optional, never required
+`OPENROUTER_API_KEY`, `NVIDIA_API_KEY`, and `UNSLOTH_API_KEY`.
+`ANTHROPIC_WORKSPACE_ID` selects a workspace for identity-linked Anthropic
+keys. 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.
 OpenAI-compatible local or cloud endpoints use `base_url` plus `model`.
@@ -257,7 +275,7 @@ 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.
@@ -266,34 +284,30 @@ 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.
-Specialized public hosted contracts appear separately as `ONE-SHOT`, with
-their purpose visible before selection. The catalog is generated from
-NVIDIA's official OpenAPI indexes and currently covers 92 task models across
-generation, vision, retrieval, safety, translation, biology, molecular and
-medical inference, optimization, and climate APIs. 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. For
-advanced schemas the tool can describe required fields before running exact
-JSON and file bindings. Large inputs use NVIDIA Assets; binary or large JSON
-output defaults to `.ur/artifacts/nvidia/`. Download-only and non-executable
-cards remain hidden.
+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: "1.84.7 (UR-Nexus)"
+# expected for this release: "1.85.1 (UR-Nexus)"
 ```
 
 ### 0.0 Redteam mode and Reverse Skills (1.81.0)
@@ -136,6 +136,18 @@ Opus 5/4.8 must receive `speed="fast"` and
 Opus versions must receive neither. A non-stream response must retain
 `usage.speed`.
 
+With an identity-linked test key, first omit the workspace. Discovery and
+doctor must preserve Anthropic's `anthropic-workspace-id is required` detail
+and show the `anthropic.workspace_id` fix. Then configure a `wrkspc_...` value
+and verify the same header on model pagination, streaming/non-streaming
+Messages, and token counting. A workspace-scoped key must remain valid with no
+workspace setting.
+
+For OpenAI retry classification, mock a 429 `billing_not_active` streaming body
+and verify exactly one transport call plus the provider's actionable message.
+A 429 `rate_limit_exceeded` fixture must remain retryable. The deterministic
+coverage is in `test/providerReliability.test.ts`.
+
 Deterministic coverage:
 
 ```sh
@@ -258,20 +270,18 @@ 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 exact AI, retrieval, and healthcare
-endpoint routing; generated-schema defaults and validation; FLUX, Stable Video
-Diffusion, and PaliGemma conveniences; Bearer reuse; NVIDIA Asset upload and
-cleanup; async request-ID polling; artifact decoding; and rejection of models
-without a generated public hosted contract. 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.