omnius 1.0.850 → 1.0.852

package/docs/DISCOVERY.json

@@ -33264,6 +33264,148 @@
         }
       ]
     },
+    {
+      "id": "guide.work-orders-evidence-public-review-after-20261012",
+      "kind": "guide",
+      "title": "Public Review After 20261012",
+      "summary": "Bundled Omnius documentation artifact: docs/work-orders/evidence/public-review-after-20261012.json.",
+      "keywords": [
+        "work",
+        "orders",
+        "evidence",
+        "public",
+        "review",
+        "after",
+        "20261012",
+        "json"
+      ],
+      "maturity": "internal",
+      "audiences": [
+        "maintainer",
+        "large-context-agent"
+      ],
+      "layer": "documentation",
+      "interfaces": [
+        {
+          "type": "file",
+          "target": "docs/work-orders/evidence/public-review-after-20261012.json"
+        }
+      ],
+      "references": [
+        {
+          "type": "documentation",
+          "target": "docs/work-orders/evidence/public-review-after-20261012.json",
+          "relation": "canonical-artifact"
+        }
+      ]
+    },
+    {
+      "id": "guide.work-orders-evidence-public-review-before-20261012",
+      "kind": "guide",
+      "title": "Public Review Before 20261012",
+      "summary": "Bundled Omnius documentation artifact: docs/work-orders/evidence/public-review-before-20261012.json.",
+      "keywords": [
+        "work",
+        "orders",
+        "evidence",
+        "public",
+        "review",
+        "before",
+        "20261012",
+        "json"
+      ],
+      "maturity": "internal",
+      "audiences": [
+        "maintainer",
+        "large-context-agent"
+      ],
+      "layer": "documentation",
+      "interfaces": [
+        {
+          "type": "file",
+          "target": "docs/work-orders/evidence/public-review-before-20261012.json"
+        }
+      ],
+      "references": [
+        {
+          "type": "documentation",
+          "target": "docs/work-orders/evidence/public-review-before-20261012.json",
+          "relation": "canonical-artifact"
+        }
+      ]
+    },
+    {
+      "id": "guide.work-orders-evidence-telegram-all-free-live-20261013",
+      "kind": "guide",
+      "title": "Telegram All Free Live 20261013",
+      "summary": "Bundled Omnius documentation artifact: docs/work-orders/evidence/telegram-all-free-live-20261013.json.",
+      "keywords": [
+        "work",
+        "orders",
+        "evidence",
+        "telegram",
+        "all",
+        "free",
+        "live",
+        "20261013",
+        "json"
+      ],
+      "maturity": "internal",
+      "audiences": [
+        "maintainer",
+        "large-context-agent"
+      ],
+      "layer": "documentation",
+      "interfaces": [
+        {
+          "type": "file",
+          "target": "docs/work-orders/evidence/telegram-all-free-live-20261013.json"
+        }
+      ],
+      "references": [
+        {
+          "type": "documentation",
+          "target": "docs/work-orders/evidence/telegram-all-free-live-20261013.json",
+          "relation": "canonical-artifact"
+        }
+      ]
+    },
+    {
+      "id": "guide.work-orders-evidence-telegram-native-planning-live-20261013",
+      "kind": "guide",
+      "title": "Telegram Native Planning Live 20261013",
+      "summary": "Bundled Omnius documentation artifact: docs/work-orders/evidence/telegram-native-planning-live-20261013.json.",
+      "keywords": [
+        "work",
+        "orders",
+        "evidence",
+        "telegram",
+        "native",
+        "planning",
+        "live",
+        "20261013",
+        "json"
+      ],
+      "maturity": "internal",
+      "audiences": [
+        "maintainer",
+        "large-context-agent"
+      ],
+      "layer": "documentation",
+      "interfaces": [
+        {
+          "type": "file",
+          "target": "docs/work-orders/evidence/telegram-native-planning-live-20261013.json"
+        }
+      ],
+      "references": [
+        {
+          "type": "documentation",
+          "target": "docs/work-orders/evidence/telegram-native-planning-live-20261013.json",
+          "relation": "canonical-artifact"
+        }
+      ]
+    },
     {
       "id": "guide.work-orders-evidence-terminal-review-contract-probe-20261012",
       "kind": "guide",
@@ -38045,6 +38187,43 @@
         }
       ]
     },
+    {
+      "id": "guide.work-orders-wo-built-in-free-model-startup-20261012-uppercase",
+      "kind": "guide",
+      "title": "Built-in free inference and clean Telegram settlement",
+      "summary": "Status: implemented, tested and committed. Live service limits are recorded below rather than claimed as model availability. Publication and bot restart remain operator-owned.",
+      "keywords": [
+        "work",
+        "orders",
+        "WO",
+        "built",
+        "in",
+        "free",
+        "model",
+        "startup",
+        "20261012",
+        "md"
+      ],
+      "maturity": "internal",
+      "audiences": [
+        "maintainer",
+        "large-context-agent"
+      ],
+      "layer": "documentation",
+      "interfaces": [
+        {
+          "type": "file",
+          "target": "docs/work-orders/WO-built-in-free-model-startup-20261012.md"
+        }
+      ],
+      "references": [
+        {
+          "type": "documentation",
+          "target": "docs/work-orders/WO-built-in-free-model-startup-20261012.md",
+          "relation": "canonical-artifact"
+        }
+      ]
+    },
     {
       "id": "guide.work-orders-wo-fallback-quality-order-20261012-uppercase",
       "kind": "guide",
@@ -38184,6 +38363,43 @@
         }
       ]
     },
+    {
+      "id": "guide.work-orders-wo-live-native-cascade-ui-freeze-20261013-uppercase",
+      "kind": "guide",
+      "title": "Live native-planning cascade and TUI responsiveness",
+      "summary": "Status: implementation and live packaged acceptance complete; operator publication/restart pending. Follow-up to the operator’s live 1.0.851 report after the built-in free-model integration; do not substitute another ping-only check.",
+      "keywords": [
+        "work",
+        "orders",
+        "WO",
+        "live",
+        "native",
+        "cascade",
+        "ui",
+        "freeze",
+        "20261013",
+        "md"
+      ],
+      "maturity": "internal",
+      "audiences": [
+        "maintainer",
+        "large-context-agent"
+      ],
+      "layer": "documentation",
+      "interfaces": [
+        {
+          "type": "file",
+          "target": "docs/work-orders/WO-live-native-cascade-ui-freeze-20261013.md"
+        }
+      ],
+      "references": [
+        {
+          "type": "documentation",
+          "target": "docs/work-orders/WO-live-native-cascade-ui-freeze-20261013.md",
+          "relation": "canonical-artifact"
+        }
+      ]
+    },
     {
       "id": "guide.work-orders-wo-native-transport-fresh-install-20261012-uppercase",
       "kind": "guide",
@@ -38327,6 +38543,42 @@
         }
       ]
     },
+    {
+      "id": "guide.work-orders-wo-public-review-schema-compatibility-20261012-uppercase",
+      "kind": "guide",
+      "title": "Public reply-review schema compatibility",
+      "summary": "Status: repaired and verified; broader built-in-model/startup/lifecycle work is tracked in WO-built-in-free-model-startup-20261012.md.",
+      "keywords": [
+        "work",
+        "orders",
+        "WO",
+        "public",
+        "review",
+        "schema",
+        "compatibility",
+        "20261012",
+        "md"
+      ],
+      "maturity": "internal",
+      "audiences": [
+        "maintainer",
+        "large-context-agent"
+      ],
+      "layer": "documentation",
+      "interfaces": [
+        {
+          "type": "file",
+          "target": "docs/work-orders/WO-public-review-schema-compatibility-20261012.md"
+        }
+      ],
+      "references": [
+        {
+          "type": "documentation",
+          "target": "docs/work-orders/WO-public-review-schema-compatibility-20261012.md",
+          "relation": "canonical-artifact"
+        }
+      ]
+    },
     {
       "id": "guide.work-orders-wo-telegram-fallback-20261012-uppercase",
       "kind": "guide",
@@ -38434,6 +38686,41 @@
         }
       ]
     },
+    {
+      "id": "guide.work-orders-wo-telegram-reply-lifecycle-20261013-uppercase",
+      "kind": "guide",
+      "title": "Telegram reply lifecycle",
+      "summary": "Status: implemented and verified. The built-in-model/startup and multi-model live acceptance work continues under WO-built-in-free-model-startup-20261012.md.",
+      "keywords": [
+        "work",
+        "orders",
+        "WO",
+        "telegram",
+        "reply",
+        "lifecycle",
+        "20261013",
+        "md"
+      ],
+      "maturity": "internal",
+      "audiences": [
+        "maintainer",
+        "large-context-agent"
+      ],
+      "layer": "documentation",
+      "interfaces": [
+        {
+          "type": "file",
+          "target": "docs/work-orders/WO-telegram-reply-lifecycle-20261013.md"
+        }
+      ],
+      "references": [
+        {
+          "type": "documentation",
+          "target": "docs/work-orders/WO-telegram-reply-lifecycle-20261013.md",
+          "relation": "canonical-artifact"
+        }
+      ]
+    },
     {
       "id": "guide.work-orders-wo-telegram-unavailable-review-presentation-20261012-uppercase",
       "kind": "guide",
@@ -40382,6 +40669,47 @@
         "config.provider-protocol"
       ]
     },
+    {
+      "id": "provider.builtin-free",
+      "kind": "provider",
+      "title": "Built-in free",
+      "summary": "Built-in free inference through openai-chat.",
+      "aliases": [],
+      "keywords": [
+        "provider",
+        "inference",
+        "api key",
+        "openai-chat"
+      ],
+      "interfaces": [
+        {
+          "type": "provider-protocol",
+          "target": "openai-chat"
+        },
+        {
+          "type": "endpoint",
+          "target": "https://opencode.ai/inference/v1"
+        }
+      ],
+      "capabilities": [
+        "chat",
+        "streaming",
+        "models",
+        "tools",
+        "structured-output"
+      ],
+      "auth": {
+        "strategy": "none",
+        "required": false,
+        "staticHeaders": {
+          "Authorization": "Bearer public"
+        }
+      },
+      "paths": {
+        "chat": "/inference/v1/chat/completions",
+        "models": "/inference/v1/models"
+      }
+    },
     {
       "id": "provider.cerebras",
       "kind": "provider",

package/docs/DISCOVERY.md

@@ -541,6 +541,10 @@ Daemon equivalents are `GET /v1/discovery/bootstrap`, `GET /v1/discovery?q=<inte
 | `guide.work-orders-evidence-opencode-step-rate-limited-diagnostic-20261012` | Opencode Step Rate Limited Diagnostic 20261012 | Bundled Omnius documentation artifact: docs/work-orders/evidence/opencode-step-rate-limited-diagnostic-20261012.json. |
 | `guide.work-orders-evidence-ovh-production-compatibility-20261012` | Ovh Production Compatibility 20261012 | Bundled Omnius documentation artifact: docs/work-orders/evidence/ovh-production-compatibility-20261012.json. |
 | `guide.work-orders-evidence-ovh-structured-context-compatibility-20261012` | Ovh Structured Context Compatibility 20261012 | Bundled Omnius documentation artifact: docs/work-orders/evidence/ovh-structured-context-compatibility-20261012.json. |
+| `guide.work-orders-evidence-public-review-after-20261012` | Public Review After 20261012 | Bundled Omnius documentation artifact: docs/work-orders/evidence/public-review-after-20261012.json. |
+| `guide.work-orders-evidence-public-review-before-20261012` | Public Review Before 20261012 | Bundled Omnius documentation artifact: docs/work-orders/evidence/public-review-before-20261012.json. |
+| `guide.work-orders-evidence-telegram-all-free-live-20261013` | Telegram All Free Live 20261013 | Bundled Omnius documentation artifact: docs/work-orders/evidence/telegram-all-free-live-20261013.json. |
+| `guide.work-orders-evidence-telegram-native-planning-live-20261013` | Telegram Native Planning Live 20261013 | Bundled Omnius documentation artifact: docs/work-orders/evidence/telegram-native-planning-live-20261013.json. |
 | `guide.work-orders-evidence-terminal-review-contract-probe-20261012` | Terminal Review Contract Probe 20261012 | Bundled Omnius documentation artifact: docs/work-orders/evidence/terminal-review-contract-probe-20261012.json. |
 | `guide.work-orders-evidence-terminal-review-error-probe-20261012` | Terminal Review Error Probe 20261012 | Bundled Omnius documentation artifact: docs/work-orders/evidence/terminal-review-error-probe-20261012.json. |
 | `guide.work-orders-evidence-terminal-review-schema-repair-probe-20261012` | Terminal Review Schema Repair Probe 20261012 | Bundled Omnius documentation artifact: docs/work-orders/evidence/terminal-review-schema-repair-probe-20261012.json. |
@@ -667,17 +671,21 @@ Daemon equivalents are `GET /v1/discovery/bootstrap`, `GET /v1/discovery?q=<inte
 | `guide.work-orders-telegram-reliability-consolidation-2026-09-28` | Telegram Reliability Consolidation — 2026-09-28 | Rule: check a box only after the named behavior is implemented and its listed verification passes. A parent box stays open until every child box is checked. |
 | `guide.work-orders-wo-active-inference-route-and-telegram-review-20261012-uppercase` | Active inference route and Telegram completion review | Status: implementation complete and verified. Publication remains with the user. |
 | `guide.work-orders-wo-am-gaps-uppercase` | Associative Memory Gap Work Orders | Generated: 2026-04-13 Source: Deep audit of multimodal associative memory systems Status: READY FOR IMPLEMENTATION |
+| `guide.work-orders-wo-built-in-free-model-startup-20261012-uppercase` | Built-in free inference and clean Telegram settlement | Status: implemented, tested and committed. Live service limits are recorded below rather than claimed as model availability. Publication and bot restart remain operator-owned. |
 | `guide.work-orders-wo-fallback-quality-order-20261012-uppercase` | Benchmark-informed fallback cascade | Status: implemented and verified. Publication and active runtime replacement remain with the user. Telegram progress presentation stays deferred. |
 | `guide.work-orders-wo-fallback-reply-contracts-20261012-uppercase` | Fallback reply contracts and live Telegram regressions | Status: implemented and verified in source and the freshly installed package. Publishing and restarting the active bot remain user-owned. The subsequent OpenCode-first capability ordering is tracked in its work order; Telegram progress presentation remains explicitly deferred. |
 | `guide.work-orders-wo-inference-fallback-20261012-uppercase` | Local inference outage fallback | Status: source implementation complete and verified. Installed-runtime activation is separate; the running daemon has not been upgraded or restarted. |
 | `guide.work-orders-wo-keyless-fallback-coverage-20261012-uppercase` | Keyless automatic fallback coverage and compatibility | Status: implemented and verified. Publication and replacement of the running bot remain user-owned; the running bot has not been restarted by this work. |
+| `guide.work-orders-wo-live-native-cascade-ui-freeze-20261013-uppercase` | Live native-planning cascade and TUI responsiveness | Status: implementation and live packaged acceptance complete; operator publication/restart pending. Follow-up to the operator’s live 1.0.851 report after the built-in free-model integration; do not substitute another ping-only check. |
 | `guide.work-orders-wo-native-transport-fresh-install-20261012-uppercase` | Native transport failure in the fresh npm installation gate | Status: implemented and verified. Publication remains with the user. |
 | `guide.work-orders-wo-opencode-all-free-models-20261012-uppercase` | All OpenCode free models in the fallback cascade | Status: implemented and verified. Publication and runtime replacement remain with the user. The subsequent live-reply fixes are tracked separately in fallback reply contracts. The original preferred-first/provider-fairness ordering recorded below has been superseded by benchmark-informed priority at the user's subsequent request. |
 | `guide.work-orders-wo-opencode-production-compatibility-20261012-uppercase` | OpenCode production request compatibility | Status: implemented and verified. Telegram presentation is also completed. Publication and active-runtime restart remain with the operator. Step's native attention-format compatibility remains unverified after a provider limit; the working cascade can continue to other compatible models. |
 | `guide.work-orders-wo-primary-checkout-fallback-delivery-20261012-uppercase` | Primary checkout delivery and remote output capacity | Status: implementation complete and verified in the primary checkout. Publication remains with the user. |
+| `guide.work-orders-wo-public-review-schema-compatibility-20261012-uppercase` | Public reply-review schema compatibility | Status: repaired and verified; broader built-in-model/startup/lifecycle work is tracked in WO-built-in-free-model-startup-20261012.md. |
 | `guide.work-orders-wo-telegram-fallback-20261012-uppercase` | Telegram outage fallback and user-selected approval mode | Status: implementation complete; distributable verification recorded below. Publication and runtime installation are reserved for the user. |
 | `guide.work-orders-wo-telegram-plain-answer-and-provider-catalog-20261012-uppercase` | Preserve native Telegram answers and use compatible free inference routes | Status: implemented and verified. The user owns publication and runtime replacement. |
 | `guide.work-orders-wo-telegram-progress-presentation-20261012-uppercase` | Telegram progress presentation | Status: implemented and verified, resumed by the user with instructions to complete, commit and push. The evidenced OpenCode compatibility failure is handled in the current repair order. |
+| `guide.work-orders-wo-telegram-reply-lifecycle-20261013-uppercase` | Telegram reply lifecycle | Status: implemented and verified. The built-in-model/startup and multi-model live acceptance work continues under WO-built-in-free-model-startup-20261012.md. |
 | `guide.work-orders-wo-telegram-unavailable-review-presentation-20261012-uppercase` | Telegram reply presentation when an auxiliary review is unavailable | Status: implemented and verified. Publication and runtime replacement remain with the user. |
 | `guide.work-orders-world-class-memory-compiler-readme-uppercase` | World-Class Memory Compiler Program | Status: active implementation program Owner: Omnius orchestration and memory packages Last updated: 2026-07-13 |
 | `guide.work-orders-world-class-memory-compiler-tracker-uppercase` | Memory Compiler Implementation Tracker | Last reconciled: 2026-07-13 Authority: This file is the granular program tracker. The work-order documents define the contract and acceptance criteria; neither test output nor a model claim may check an item without the named evidence. |
@@ -741,6 +749,7 @@ Daemon equivalents are `GET /v1/discovery/bootstrap`, `GET /v1/discovery?q=<inte
 | ID | Title | Summary |
 | --- | --- | --- |
 | `provider.anthropic` | Anthropic Claude | Claude through Anthropic's native Messages API with system, tool, streaming, stop-reason, and usage translation. |
+| `provider.builtin-free` | Built-in free | Built-in free inference through openai-chat. |
 | `provider.cerebras` | Cerebras | Cerebras inference through its OpenAI-compatible API. |
 | `provider.chutes` | Chutes | Chutes hosted models through an OpenAI-compatible API. |
 | `provider.custom` | Custom inference endpoint | A user-supplied endpoint that remains disabled until its protocol is declared explicitly. |

package/docs/getting-started/first-run.md

@@ -2,32 +2,42 @@
 
 The setup flow is responsible for choosing a usable model path without assuming local Ollama is the only option.
 
-## Guided Cloud Setup
-
-When no endpoint has been selected, terminal startup opens a lightweight helper
-before loading the normal agent, MCP plugins, memory, or local model services.
-It uses anonymous public inference discovered from
-[the free inference directory](https://robit-man.github.io/inference/), checking
-the catalog and a small synthetic readiness request before using a route.
-Unavailable routes fail over; rate limits retain their retry cooldown.
-
-Ask a setup question or use `/key openrouter`, `/key openai`, or `/key anthropic`.
-All setup input is hidden. The host captures credentials locally and substitutes
-opaque references before public inference. Only provider-specific local tools
-can resolve a reference, and only for that provider's pinned official endpoint.
-Redirects are refused. The helper cannot read files, environment variables,
-project conversations, or the vault's raw values.
-
-The host lists models, tests the chosen model, and saves the exact tested
-connection privately before starting the normal agent. The free route is
-temporary and is not saved as the normal endpoint. If free inference is
-unavailable, local setup tools can still complete cloud setup from an explicitly
-provider-bound key. Existing configured endpoints bypass the helper even when
-temporarily offline. Piped input is never sent to public setup inference.
-
-Use `/setup` to reopen guided setup, `/setup local` or the helper's `/local` for
-explicit local model setup, and `/exit` to leave without selecting an endpoint.
-Local inference tests require the normal hardware preflight.
+## Built-in Free Start
+
+An unconfigured installation starts with **Built-in free** inference without an
+API key, a local model download, or a setup conversation. Omnius selects the
+highest-ranked compatible model from its discovered free catalog. Muse Spark
+1.3 is the bundled default when current catalog discovery is unavailable.
+Saved local and cloud profiles keep their selected endpoint and model, even
+when that endpoint is temporarily offline.
+
+Use `/model` to browse the **Built-in free** section alongside your configured
+endpoint's models. Known bundled choices remain visible when catalog discovery
+fails. `Saved catalog; availability unverified` and `Not currently listed`
+describe catalog state; listing a model does not prove that it will answer.
+Live catalog pricing and retirement status still control free eligibility.
+
+With `/fallback auto`, the default, a failed selected route can fall back to
+compatible alternatives. Attempts respect time limits, rate-limit cooldowns,
+and the original response contract. `/fallback manual` asks before using an
+alternative. If all eligible services fail, Omnius reports that inference could
+not complete; free access does not guarantee an answer to every request.
+
+## Optional Provider Setup
+
+Use `/setup` to ask about providers or commands. Inside setup, `/free` selects
+built-in free inference without asking for credentials. Use `/key openrouter`,
+`/key openai`, or another `/key <provider>` only when choosing a provider that
+requires a key. Setup input is hidden. Credentials are captured locally and
+replaced with opaque references before the setup helper sees them; only the
+chosen provider's pinned endpoint receives its key. The helper cannot read
+project files, environment variables, project conversations, or raw vault values.
+
+Keyed-provider setup lists models, checks the chosen model, and saves the exact
+tested connection privately. `/setup local`, or `/local` inside setup, opens
+explicit local model setup. Local inference tests require the normal hardware
+preflight. `/exit` leaves optional setup without changing inference. Piped task
+input follows the normal runtime and never becomes a setup conversation.
 
 ## What Setup Probes
 
@@ -42,7 +52,11 @@ Setup can inspect:
 
 ## Model And Endpoint Choice
 
-The model picker should show the union of enabled endpoints. If a sponsor endpoint, OpenRouter endpoint, or other external endpoint is selected, the next model step must list models from that endpoint as well as other toggled enabled endpoints.
+The model picker includes built-in free choices independently of the configured
+endpoint's availability. Selecting a free entry switches the complete model and
+transport profile without inheriting the previous endpoint's keys. Selecting
+another endpoint with `/endpoint` keeps its provider-specific model choices
+available through `/model`.
 
 The setup flow should not silently fall back to local Ollama when an external endpoint was selected.
 
@@ -62,4 +76,4 @@ After first run:
 - a model is selected
 - `.omnius/settings.json` exists if settings were persisted
 - `.omnius/` is ignored by git
-- the TUI can submit a prompt without re-entering setup
+- the TUI can submit a prompt without re-entering setup; remote service availability still applies

package/docs/getting-started/model-providers.md

@@ -6,6 +6,7 @@ Omnius routes model requests through a provider abstraction instead of treating
 
 Supported endpoint patterns include:
 
+- built-in free inference, available without user credentials
 - local Ollama
 - Omnius-managed Ollama pool
 - vLLM
@@ -20,6 +21,26 @@ Supported endpoint patterns include:
 - sponsor endpoints discovered through Nexus
 - COHERE distributed inference peers
 
+## Built-in Free Models
+
+An installation without a selected profile defaults to **Built-in free**
+inference. `/model` lists discovered free models by name in that category,
+alongside the configured endpoint's models. Current catalog eligibility and
+model capabilities determine the choices; known bundled choices remain visible
+when discovery is offline and are marked as unverified. Existing local and
+keyed-provider profiles are preserved.
+
+Choosing a built-in free model switches its whole transport profile and clears
+unrelated endpoint keys. Model-specific adapters handle Chat or Responses
+framing while retaining the original host validation. Inference diagnostics
+continue to identify the actual provider and model used.
+
+Free services have availability and quota limits. Automatic fallback is enabled
+by default and tries compatible alternatives within bounded deadlines and
+rate-limit cooldowns. It does not guarantee that every request succeeds. Use
+`/fallback manual` to require a choice before moving to an alternative after
+the selected route fails; `/fallback auto` restores automatic selection.
+
 ## Endpoint Selection
 
 Use:
@@ -28,10 +49,16 @@ Use:
 /endpoint
 /endpoint sponsor
 /model
+/setup
+/setup local
 ```
 
 Endpoint history records recently used URLs and auth metadata so users can return to external routers without retyping them.
 
+Setup is optional. Inside `/setup`, use `/free` for credentialless inference or
+`/key <provider>` only after choosing a provider that requires a key. Local
+model setup is explicit and retains its hardware preflight requirements.
+
 For the complete protocol, authentication, and fail-closed behavior, read
 [Bring Your Own Inference](../guides/bring-your-own-inference.md). The important
 distinction is that provider names are not cosmetic: