Merge remote-tracking branch 'origin/main' into codex/pr6160-fixes

Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>

Author: franciscojavierarceo

README.md

@@ -60,10 +60,10 @@ Install and run a OGX server:
 curl -LsSf https://github.com/ogx-ai/ogx/raw/main/scripts/install.sh | bash
 
 # Or install via uv
-uv pip install ogx[starter]
+uv pip install ogx
 
-# Start the server (uses the starter distribution with Ollama)
-uv run ogx run starter
+# Start the server (auto-detects providers from the environment)
+uv run ogx go
 ```
 
 Then connect with any OpenAI, Anthropic, or Google GenAI client — [Python](https://github.com/openai/openai-python), [TypeScript](https://github.com/openai/openai-node), [curl](https://platform.openai.com/docs/api-reference), or any framework that speaks these APIs.

docs/docs/api-openai/provider_matrix.md

@@ -21,7 +21,7 @@ inference provider, based on integration test results.
 |----------|--------|---------|---------|----------|
 | azure | 111 | 111 | 0 | 82% |
 | bedrock | 27 | 27 | 0 | 20% |
-| ollama | 2 | 2 | 0 | 2% |
+| ollama | 3 | 3 | 0 | 2% |
 | openai | 136 | 136 | 0 | 100% |
 | vertexai | 70 | 70 | 0 | 52% |
 | vllm | 3 | 3 | 0 | 2% |
@@ -35,10 +35,10 @@ Models, endpoints, and versions used during test recordings.
 |----------|----------|----------|--------------|
 | azure | gpt-4o | llama-stack-test.openai.azure.com, lls-test.openai.azure.com, ogx-test.openai.azure.com | openai sdk: 2.43.0 |
 | bedrock | openai.gpt-oss-20b-1:0 | bedrock-runtime.us-west-2.amazonaws.com | openai sdk: 2.30.0 |
-| ollama | deepseek-r1:1.5b | — | openai sdk: 2.30.0 |
+| ollama | deepseek-r1:1.5b | — | openai sdk: 2.43.0 |
 | openai | gpt-4o, o4-mini, text-embedding-3-small | api.openai.com | openai sdk: 2.43.0 |
 | vertexai | publishers/google/models/gemini-2.0-flash | — | openai sdk: 2.5.0, provider: vertexai |
-| vllm | Qwen/Qwen3-0.6B | — | openai sdk: 2.5.0, vllm server: 0.18.1rc1.dev197+g0e9358c11 |
+| vllm | Qwen/Qwen3-0.6B | — | openai sdk: 2.5.0, vllm server: 0.17.2rc1.dev79+g5ce2d10e4 |
 | watsonx | meta-llama/llama-3-3-70b-instruct | us-south.ml.cloud.ibm.com | openai sdk: 2.5.0 |
 
 ## Basic Responses
@@ -165,7 +165,7 @@ Models, endpoints, and versions used during test recordings.
 
 | Feature | azure | bedrock | ollama | openai | vertexai | vllm | watsonx |
 | --- | --- | --- | --- | --- | --- | --- | --- |
-| reasoning basic streaming | ✅ | ✅ | ⏭️ | ✅ | ✅ | ✅ | ✅ |
+| reasoning basic streaming | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
 | reasoning multi turn passthrough | ⏭️ | ✅ | ✅ | ✅ | ⏭️ | ✅ | ✅ |
 | reasoning no summary without request | ⏭️ | ⏭️ | ⏭️ | ✅ | ⏭️ | ⏭️ | ✅ |
 | reasoning non streaming | ⏭️ | ✅ | ✅ | ✅ | ⏭️ | ✅ | ✅ |

docs/docs/distributions/self_hosted_distro/passthrough.md

@@ -19,16 +19,15 @@ Install [Ollama](https://ollama.com/download), then pull a model and start the s
 
 ```bash
 ollama pull llama3.2:3b
-export OLLAMA_URL=http://localhost:11434/v1
-uvx --from 'ogx[starter]' ogx run starter
+uvx ogx go
 ```
 
 </TabItem>
 <TabItem value="openai" label="OpenAI">
 
 ```bash
 export OPENAI_API_KEY=sk-xxx
-uvx --from 'ogx[starter]' ogx run starter
+uvx ogx go
 ```
 
 </TabItem>
@@ -52,13 +51,14 @@ The `uvx` command above is great for trying things out. For a real project, inst
 
 ```bash
 uv init my-ai-app && cd my-ai-app
-uv add 'ogx[starter]' openai
-export OLLAMA_URL=http://localhost:11434/v1
-uv run ogx run starter
+uv add ogx openai
+uv run ogx go
 ```
 :::
 
-The server is now running at `http://localhost:8321`. You can use any OpenAI-compatible client.
+The server is now running at `https://localhost:8321`. You can use any OpenAI-compatible client.
+
+OGX is secure by default and listens on https. Passing `--insecure` forces the server to listen on http.
 
 ## Verify it works
 
@@ -68,16 +68,17 @@ Before writing any code, confirm the server is healthy and models are registered
 <TabItem value="curl" label="curl" default>
 
 ```bash
-curl -s http://localhost:8321/v1/models | python -m json.tool
+curl -k -s https://localhost:8321/v1/models | python -m json.tool
 ```
 
 </TabItem>
 <TabItem value="python" label="Python">
 
 ```python
+import httpx
 from openai import OpenAI
 
-client = OpenAI(base_url="http://localhost:8321/v1", api_key="fake")
+client = OpenAI(base_url="http://localhost:8321/v1", api_key="fake", http_client=httpx.Client(verify=False))
 
 for model in client.models.list():
     print(model.id)
@@ -108,9 +109,10 @@ If the list is empty or the command fails, check the [Troubleshooting](#troubles
 Open a new terminal and run:
 
 ```python title="app.py"
+import httpx
 from openai import OpenAI
 
-client = OpenAI(base_url="http://localhost:8321/v1", api_key="fake")
+client = OpenAI(base_url="https://localhost:8321/v1", api_key="fake", http_client=httpx.Client(verify=False))
 
 response = client.responses.create(
     model="ollama/llama3.2:3b",
@@ -128,9 +130,10 @@ pip install openai && python app.py
 Upload a file, create a vector store, and ask questions about it:
 
 ```python
+import httpx
 from openai import OpenAI
 
-client = OpenAI(base_url="http://localhost:8321/v1", api_key="fake")
+client = OpenAI(base_url="http://localhost:8321/v1", api_key="fake", http_client=httpx.Client(verify=False))
 
 # Upload a document
 file = client.files.create(
@@ -166,7 +169,7 @@ That's it. Same OpenAI SDK, local model, your own vector store.
 If you see `Address already in use`, another process is using port 8321. Either stop it or run on a different port:
 
 ```bash
-uvx --from 'ogx[starter]' ogx run starter --port 8322
+uvx ogx go --port 8322
 ```
 
 </details>

docs/docs/getting_started/quickstart.mdx

@@ -113,11 +113,13 @@ curl -LsSf https://github.com/ogx-ai/ogx/raw/main/scripts/install.sh | bash
 pip install ogx
 
 # Start the server
-ogx stack run
+uv run ogx go --insecure
 ```
 
 :::tip
 OGX works with any OpenAI-compatible client. Point your existing code at `http://localhost:8321/v1` and you're ready to go.
+
+OGX is secure by default. `--insecure` forces the server to listen on http. By default it runs on https with a self-signed cert. You'll have to skip cert verification or trust the automatically generated cert.
 :::
 
 [Quick Start Guide](/docs/getting_started/quickstart) | [OpenAI API Compatibility](./api-openai) | [GitHub](https://github.com/ogx-ai/ogx)

docs/docs/index.mdx

@@ -4,15 +4,11 @@ import styles from './styles.module.css';
 const EXAMPLES = [
   {
     label: 'Server',
-    command: "uvx --from 'ogx[starter]' ogx run starter",
+    command: "uvx ogx go",
     tokens: [
       { text: 'uvx', style: 'tokenBinary' },
-      { text: '--from', style: 'tokenFlag' },
-      { text: "'ogx[starter]'", style: 'tokenPackage' },
       { text: 'ogx', style: 'tokenCommand' },
-      { text: 'stack', style: 'tokenSub' },
-      { text: 'run', style: 'tokenSub' },
-      { text: 'starter', style: 'tokenAccent' },
+      { text: 'go', style: 'tokenSub' },
     ],
   },
   {

docs/docs/providers/inference/remote_passthrough.mdx

@@ -74,7 +74,6 @@
     "meta",
     "nvidia",
     "oci",
-    "passthrough",
     "runpod",
     "sambanova",
 }

docs/src/components/InstallBlock/index.jsx

@@ -5,6 +5,7 @@
 # the root directory of this source tree.
 
 import argparse
+import warnings
 from typing import Any
 
 from ogx.cli.stack.lets_go import add_letsgo_arguments, run_letsgo_cmd
@@ -14,12 +15,33 @@
 class LetsGo(Subcommand):
     """Auto-detect providers, generate runtime config, and start the stack."""
 
+    def __init__(self, subparsers: Any) -> None:
+        super().__init__()
+        self.parser = subparsers.add_parser(
+            "go",
+            prog="ogx go",
+            description="Auto-detect providers and start the stack",
+            formatter_class=argparse.ArgumentDefaultsHelpFormatter,
+        )
+        self._add_arguments()
+        self.parser.set_defaults(func=self._run_cmd)
+
+    def _add_arguments(self) -> None:
+        add_letsgo_arguments(self.parser)
+
+    def _run_cmd(self, args: argparse.Namespace) -> None:
+        run_letsgo_cmd(args, self.parser)
+
+
+class LetsGoDeprecated(Subcommand):
+    """Backward-compatible alias for 'ogx go' (deprecated)."""
+
     def __init__(self, subparsers: Any) -> None:
         super().__init__()
         self.parser = subparsers.add_parser(
             "letsgo",
             prog="ogx letsgo",
-            description="Auto-detect providers and start the stack",
+            description="Auto-detect providers and start the stack (deprecated, use 'ogx go' instead)",
             formatter_class=argparse.ArgumentDefaultsHelpFormatter,
         )
         self._add_arguments()
@@ -29,4 +51,9 @@ def _add_arguments(self) -> None:
         add_letsgo_arguments(self.parser)
 
     def _run_cmd(self, args: argparse.Namespace) -> None:
+        warnings.warn(
+            "'ogx letsgo' is deprecated and will be removed in a future release. Use 'ogx go' instead.",
+            FutureWarning,
+            stacklevel=1,
+        )
         run_letsgo_cmd(args, self.parser)

scripts/generate_target_models_docs.py

@@ -13,7 +13,7 @@
 setup_logging()
 
 from .connect import ConnectParser  # type: ignore[attr-defined]
-from .letsgo import LetsGo
+from .letsgo import LetsGo, LetsGoDeprecated
 from .run import Run
 from .stack import StackParser  # type: ignore[attr-defined]
 from .stack.utils import print_subcommand_description
@@ -37,6 +37,7 @@ def __init__(self) -> None:
 
         # Add sub-commands
         LetsGo.create(subparsers)
+        LetsGoDeprecated.create(subparsers)
         Run.create(subparsers)
         StackParser.create(subparsers)
         ConnectParser.create(subparsers)