chore: point default models at the refreshed hosted catalog (#585)

* chore: point default models at the refreshed hosted catalog

The hosted catalog replaces GPT-5.6 Sol and Luna with GPT-6 Sol and
Luna and Claude Opus 5 with Claude Opus 5.5. Reconciliation removes
superseded models that no agent or profile references, so references to
them stop resolving.

Prefer GPT-6 Sol as the console's default model for new agents and
templates. Update the README, docs, and examples that name
omnara-openrouter models, including the Claude Fable 5 references left
behind when Fable 5.1 replaced it.

Remove default-model-provider-example.yaml. Nothing loads it, it had
drifted from the hosted catalog, and a template requires an operator
credential service, so the hosted catalog is the only one maintained.
The self-hosting configuration docs now show the template format inline.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

* chore: use current OpenAI models in provider examples

The bring-your-own OpenAI docs, the SharePoint example, and the model
name placeholders named GPT-5.6, GPT-5.5, and gpt-5.6-mini, which is not
an OpenAI model. Use gpt-6-sol and gpt-6-luna, and give the configured
model example GPT-6 Sol's published 1,050,000-token context window and
128,000-token output limit.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

Author: ksarangmath

.env.example

@@ -87,7 +87,7 @@ OMNARA_EMAIL_FROM=
 # OMNARA_UNIKRAFT_DEFAULT_POOL_TOKEN=
 
 # Optional operator-provisioned model provider for new organizations.
-# OMNARA_DEFAULT_MODEL_PROVIDER_TEMPLATE=default-model-provider-example.yaml
+# OMNARA_DEFAULT_MODEL_PROVIDER_TEMPLATE=
 # OMNARA_HOSTED_API_URL=https://operator.example.com/internal
 # OMNARA_HOSTED_API_TOKEN=
 

README.md

@@ -26,11 +26,11 @@ interact with each agent.
 1. Create your agent
 ```yaml agent.yaml
 instruction: |
-  You are a coding agent running gpt-5.6-sol. Use the tools
+  You are a coding agent running gpt-6-sol. Use the tools
   you have available to solve coding problems for the user.
 model:
   provider_config: omnara-openrouter
-  name: openai/gpt-5.6-sol
+  name: openai/gpt-6-sol
 # ...
 # add more tools, sandboxes, mcps
 ```

default-model-provider-example.yaml

@@ -25,7 +25,7 @@ instruction: |
   Run read-only commands freely; ask before anything destructive.
 model:
   provider_config: openai-prod
-  name: gpt-5.6
+  name: gpt-6-sol
   reasoning:
     effort: high
 tools:
@@ -88,7 +88,7 @@ max_depth: 2
 ```yaml
 model:
   provider_config: openai-prod
-  name: gpt-5.6
+  name: gpt-6-sol
   cache_retention: short
   reasoning:
     effort: high
@@ -213,7 +213,7 @@ subagents:
     description: Read-only codebase investigation.
     model:
       provider_config: openai-prod
-      name: gpt-5.6-mini
+      name: gpt-6-luna
     instruction:
       append: Report findings as a bullet list.
     max_instances: 4

docs/agents/configuration.mdx

@@ -51,7 +51,7 @@ instruction: |
   before making destructive changes.
 model:
   provider_config: openai-prod
-  name: gpt-5.6
+  name: gpt-6-sol
 machine_sources:
   - machine_name: sharepoint-docs    # the name from Connect machine
     cwd: /mnt/sharepoint

docs/examples/mounted-storage.mdx

@@ -25,7 +25,7 @@ instruction: |
   commands. Ask a question when a task is not clear.
 model:
   provider_config: omnara-openrouter
-  name: anthropic/claude-fable-5
+  name: anthropic/claude-fable-5.1
 tools:
   run_command: {}
   web_search: {}

docs/introduction.mdx

@@ -121,7 +121,7 @@ With the chain complete, this config can now be created in the project:
 ```yaml
 model:
   provider_config: openai-prod
-  name: gpt-5.6
+  name: gpt-6-sol
 ```
 
 When you create the config, Omnara checks the provider, model, and project grant. If something is missing, the validation error tells you what to fix.

docs/organization/model-providers.mdx

@@ -16,7 +16,7 @@ Launch your first agent with Omnara via the **dashboard**, or programmatically w
 
 Sign in at [app.omnara.com](https://app.omnara.com). When you sign in the first time, Omnara creates your first organization and project, plus two default resources this guide uses:
 
-- **`omnara-openrouter`** — a model provider with frontier models such as `anthropic/claude-fable-5` and `openai/gpt-5.6-sol`.
+- **`omnara-openrouter`** — a model provider with frontier models such as `anthropic/claude-fable-5.1` and `openai/gpt-6-sol`.
 - **`default-pool`** — a pool of Omnara-managed sandboxes.
 
 ## Setup with a Skill

docs/quickstart.mdx

@@ -159,10 +159,34 @@ organization owners configure providers themselves.
 
 | Variable | Purpose | Default | Required |
 | --- | --- | --- | --- |
-| `OMNARA_DEFAULT_MODEL_PROVIDER_TEMPLATE` | Path to the provider and model template on the API and maintenance. See `default-model-provider-example.yaml`. | — | No |
+| `OMNARA_DEFAULT_MODEL_PROVIDER_TEMPLATE` | Path to the provider and model template on the API and maintenance. | — | No |
 | `OMNARA_HOSTED_API_URL` | Base URL of the operator credential service. Used by the API and maintenance. | — | With a default provider template |
 | `OMNARA_HOSTED_API_TOKEN` | Bearer token shared with the operator credential service; at least 32 bytes. Used by the API and maintenance. | — | With a default provider template |
 
+A template names the provider and lists the models each organization receives:
+
+```yaml
+provisioner: openrouter
+name: omnara-openrouter
+credential_secret_name: omnara-openrouter-key
+api_format: openai-chat-completions
+api_variant: openrouter
+base_url: https://openrouter.ai/api/v1
+endpoint_path: /chat/completions
+auth_kind: bearer_token
+models:
+  - name: openai/gpt-6-sol
+    provider_model_slug: openai/gpt-6-sol
+    context_window_tokens: 1050000
+    max_output_tokens: 128000
+    supports_tools: true
+    supports_reasoning: true
+    default_reasoning_effort: medium
+    supported_reasoning_efforts: [max, xhigh, high, medium, low, none]
+    input_modalities: [file, image, text]
+    output_modalities: [text]
+```
+
 Templates support the [token settings and timeouts](/organization/model-providers)
 described for model providers.
 

docs/self-hosting/configuration.mdx

@@ -45,7 +45,7 @@ const provider = await sdk.createModelProviderConfig({
   "model_catalog": {
     "status": "ok",
     "models": [
-      { "slug": "gpt-5.6", "display_name": "GPT-5.6" }
+      { "slug": "gpt-6-sol", "display_name": "GPT-6 Sol" }
     ]
   }
 }