docs(hosted-agents): collapse Foundry Toolkit section and neutralize azd recommendations (#585)

* docs(hosted-agents): collapse Foundry Toolkit section and neutralize azd recs

Minimal README updates across the python and csharp hosted-agents samples: collapse the 'Using the Foundry Toolkit VS Code Extension' section into a <details> block, drop azd 'Recommended'/'recommended' qualifiers, and rename 'Without azd' to 'Manual setup' (with anchor fixes). H1 headers, descriptions, and other section content are left unchanged.

* docs(hosted-agents): revert Python overview README

Author: huimiu

.github/CODEOWNERS

@@ -11,6 +11,18 @@
 /samples/python/foundry-local/     @microsoft-foundry/foundry-local
 /samples/rust/foundry-local/       @microsoft-foundry/foundry-local
 
+#### Partner / external collaborator sample areas #######################################################
+# Partners are outside collaborators (not org members). Each entry is the source of truth for that
+# partner. Update alongside step 3 of the onboarding process in docs/external-contributions.md.
+#
+# Format:
+# # <Partner name> — onboarded: YYYY-MM-DD — partner: @<partner-github> — dri: @<dri-github>
+# /samples/<language>/<partner-area>/  @<dri-github>
+#
+# Mistral AI — add entry here once DRI and sample paths are confirmed:
+# # Mistral AI — onboarded: 2026-06-22 — partner: @peymanmohajerian — dri: @truptiparkar7
+# /samples/python/mistral/  @FILL_IN
+
 #### files referenced in docs (DO NOT EDIT, except for Docs team!!!) ##########################################
 /infrastructure/infrastructure-setup-bicep/01-connections/connection-key-vault.bicep @microsoft-foundry/AI-Platform-Docs
 /infrastructure/infrastructure-setup-bicep/05-custom-policy-definitions/deny-disallowed-connections.json @microsoft-foundry/AI-Platform-Docs

samples/csharp/hosted-agents/README.md

@@ -222,7 +222,8 @@ azd up
 azd down
 ```
 
-### Using the Foundry Toolkit VS Code Extension
+<details>
+<summary><h3>Using the Foundry Toolkit VS Code Extension</h3></summary>
 
 The [Foundry Toolkit VS Code extension](https://learn.microsoft.com/en-us/azure/foundry/agents/quickstarts/quickstart-hosted-agent?view=foundry&pivots=vscode) has a built-in sample gallery. You can open any sample directly from the extension without cloning this repository, it scaffolds the project into a new workspace, generates `agent.yaml`, `.env`, and `.vscode/tasks.json` + `launch.json` automatically, and configures a one-click **F5** debug experience.
 
@@ -238,6 +239,8 @@ Or, if you've already cloned this repository:
 
    The extension builds the container image in ACR (or uploads the ZIP), creates the agent version, and assigns required RBAC roles automatically.
 
+</details>
+
 ### Other ways to invoke your agent
 
 | Method | When to use |

samples/csharp/hosted-agents/agent-framework/README.md

@@ -130,7 +130,8 @@ Or in PowerShell:
 (Invoke-WebRequest -Uri http://localhost:8088/responses -Method POST -ContentType "application/json" -Body '{"input": "Hello!"}').Content
 ```
 
-### Using the Foundry Toolkit VS Code Extension
+<details>
+<summary><h3>Using the Foundry Toolkit VS Code Extension</h3></summary>
 
 The [Foundry Toolkit VS Code extension](https://learn.microsoft.com/en-us/azure/foundry/agents/quickstarts/quickstart-hosted-agent?view=foundry&pivots=vscode) has a built-in sample gallery. You can open this sample directly from the extension without cloning the repository, it scaffolds the project into a new workspace, generates `agent.yaml`, `.env`, and `.vscode/tasks.json` + `launch.json` automatically, and configures a one-click **F5** debug experience.
 
@@ -149,6 +150,8 @@ With the agent running on `http://localhost:8088/`:
 2. The Inspector auto-connects to the running agent.
 3. Send messages from the Inspector to chat with the agent and watch the streamed responses.
 
+</details>
+
 ### Using `dotnet run`
 
 #### Prerequisites

samples/csharp/hosted-agents/agent-framework/agent-skills/README.md

@@ -50,7 +50,7 @@ See [Program.cs](Program.cs) for the full implementation.
 
 Before running this sample, ensure you have:
 
-1. **Azure Developer CLI (`azd`)** (recommended)
+1. **Azure Developer CLI (`azd`)**
    - [Install azd](https://learn.microsoft.com/en-us/azure/developer/azure-developer-cli/install-azd) (1.25 or later) and the unified Foundry CLI extension: `azd ext install microsoft.foundry`
    - Authenticated: `azd auth login`
 
@@ -62,7 +62,7 @@ Before running this sample, ensure you have:
    - Download from [https://dotnet.microsoft.com/download](https://dotnet.microsoft.com/download)
 
 > [!NOTE]
-> You do **not** need an existing [Microsoft Foundry](https://learn.microsoft.com/en-us/azure/ai-foundry/what-is-foundry?view=foundry) project or model deployment to get started — `azd provision` creates them for you. If you already have a project, see the [note below](#using-azd-recommended-for-cli-workflows) on how to target it.
+> You do **not** need an existing [Microsoft Foundry](https://learn.microsoft.com/en-us/azure/ai-foundry/what-is-foundry?view=foundry) project or model deployment to get started — `azd provision` creates them for you. If you already have a project, see the [note below](#using-azd) on how to target it.
 
 ### Required RBAC
 
@@ -102,15 +102,18 @@ dotnet restore
 
 ### Running the Sample
 
-The recommended way to run and test hosted agents locally is with the Azure Developer CLI (`azd`) or the Foundry VS Code extension.
+Run and test hosted agents locally with the Azure Developer CLI (`azd`) or the Foundry VS Code extension.
 
-#### Using the Foundry VS Code Extension
+<details>
+<summary><h4>Using the Foundry VS Code Extension</h4></summary>
 
 The [Foundry VS Code extension](https://learn.microsoft.com/en-us/azure/foundry/agents/quickstarts/quickstart-hosted-agent?view=foundry&pivots=vscode) has a built-in sample gallery. You can open this sample directly from the extension without cloning the repository — it scaffolds the project into a new workspace, generates `agent.yaml`, `.env`, and `.vscode/tasks.json` + `launch.json` automatically, and configures a one-click **F5** debug experience.
 
 Follow the [VS Code quickstart](https://learn.microsoft.com/en-us/azure/foundry/agents/quickstarts/quickstart-hosted-agent?view=foundry&pivots=vscode) for a full step-by-step walkthrough.
 
-#### Using [`azd`](https://learn.microsoft.com/en-us/azure/foundry/agents/quickstarts/quickstart-hosted-agent?view=foundry&pivots=azd) (recommended for CLI workflows)
+</details>
+
+#### Using [`azd`](https://learn.microsoft.com/en-us/azure/foundry/agents/quickstarts/quickstart-hosted-agent?view=foundry&pivots=azd)
 
 No cloning required. Create a new folder, point `azd` at the manifest on GitHub, and it sets up the sample and generates Bicep infrastructure, `agent.yaml`, and env config automatically:
 
@@ -169,7 +172,7 @@ curl -sS -X POST http://localhost:8088/responses \
 
 Because skills are loaded on demand, the canary token in a response also proves the model actually invoked `load_skill` for the matching skill — not just saw its name in the advertised list.
 
-#### Without `azd`
+#### Manual setup
 
 If running without `azd`, set environment variables manually (see [Environment Variables](#environment-variables)), then:
 
@@ -212,7 +215,7 @@ For the full deployment guide, see [Azure AI Foundry hosted agents](https://aka.
 
 ### Images built on Apple Silicon or other ARM64 machines do not work on our service
 
-We **recommend deploying with `azd deploy`**, which uses ACR remote build and always produces images with the correct architecture.
+**Deploy with `azd deploy`**, which uses ACR remote build and always produces images with the correct architecture.
 
 If you choose to **build locally**, and your machine is **not `linux/amd64`** (for example, an Apple Silicon Mac), the image will **not be compatible with our service**, causing runtime failures.
 

samples/csharp/hosted-agents/agent-framework/azure-search-rag/README.md

@@ -23,7 +23,7 @@ See [Program.cs](Program.cs) for the full implementation.
 
 Before running this sample, ensure you have:
 
-1. **Azure Developer CLI (`azd`)** (recommended)
+1. **Azure Developer CLI (`azd`)**
    - [Install azd](https://learn.microsoft.com/en-us/azure/developer/azure-developer-cli/install-azd) (1.25 or later) and the unified Foundry CLI extension: `azd ext install microsoft.foundry`
    - Authenticated: `azd auth login`
 
@@ -35,7 +35,7 @@ Before running this sample, ensure you have:
    - Download from [https://dotnet.microsoft.com/download](https://dotnet.microsoft.com/download)
 
 > [!NOTE]
-> You do **not** need an existing [Microsoft Foundry](https://learn.microsoft.com/en-us/azure/ai-foundry/what-is-foundry?view=foundry) project, model deployment, or Azure AI Search service to get started, `azd provision` creates them all for you. If you already have some of these, see the [note below](#using-azd-recommended-for-cli-workflows) on how to target them.
+> You do **not** need an existing [Microsoft Foundry](https://learn.microsoft.com/en-us/azure/ai-foundry/what-is-foundry?view=foundry) project, model deployment, or Azure AI Search service to get started, `azd provision` creates them all for you. If you already have some of these, see the [note below](#using-azd) on how to target them.
 
 ### Environment Variables
 
@@ -73,19 +73,22 @@ dotnet restore
 
 ### Running the Sample
 
-The recommended way to run and test hosted agents locally is with the Azure Developer CLI (`azd`) or the Foundry Toolkit VS Code extension.
+Run and test hosted agents locally with the Azure Developer CLI (`azd`) or the Foundry Toolkit VS Code extension.
 
-#### Using the Foundry Toolkit VS Code Extension
+<details>
+<summary><h4>Using the Foundry Toolkit VS Code Extension</h4></summary>
 
 The [Foundry Toolkit VS Code extension](https://learn.microsoft.com/en-us/azure/foundry/agents/quickstarts/quickstart-hosted-agent?view=foundry&pivots=vscode) has a built-in sample gallery. You can open this sample directly from the extension without cloning the repository, it scaffolds the project into a new workspace, generates `agent.yaml`, `.env`, and `.vscode/tasks.json` + `launch.json` automatically, and configures a one-click **F5** debug experience.
 
 Chat with a running agent using the **Agent Inspector**:
 
-1. Start the agent locally first using **Using `azd`** or **Without `azd`** above. The agent listens on `http://localhost:8088/`.
+1. Start the agent locally first using **Using `azd`** or **Manual setup** above. The agent listens on `http://localhost:8088/`.
 2. Open the Command Palette (`Ctrl+Shift+P`) and run **Foundry Toolkit: Open Agent Inspector**.
 3. The Inspector auto-connects to the running agent. Send messages to chat with the agent and watch the streamed responses.
 
-#### Using [`azd`](https://learn.microsoft.com/en-us/azure/foundry/agents/quickstarts/quickstart-hosted-agent?view=foundry&pivots=azd) (recommended for CLI workflows)
+</details>
+
+#### Using [`azd`](https://learn.microsoft.com/en-us/azure/foundry/agents/quickstarts/quickstart-hosted-agent?view=foundry&pivots=azd)
 
 No cloning required. Create a new folder, point `azd` at the manifest on GitHub, and it sets up the sample, generates Bicep infrastructure, `agent.yaml`, and env config:
 
@@ -128,7 +131,7 @@ Tracking issue: [Azure-Samples/azd-ai-starter-basic — make storage optional in
 > `azd ai agent init -m <path-to-repo>/samples/csharp/hosted-agents/agent-framework/azure-search-rag/agent.manifest.yaml`
 
 > [!NOTE]
-> If you already have a Foundry project, model deployment, and Azure AI Search service, add `-p <project-id> -d <deployment-name>` to `azd ai agent init` to target existing resources. You can also skip provisioning entirely and configure env vars manually, see [Without `azd`](#without-azd).
+> If you already have a Foundry project, model deployment, and Azure AI Search service, add `-p <project-id> -d <deployment-name>` to `azd ai agent init` to target existing resources. You can also skip provisioning entirely and configure env vars manually, see [Manual setup](#manual-setup).
 
 The agent starts on `http://localhost:8088/`. To invoke it:
 
@@ -152,7 +155,7 @@ curl -sS -X POST http://localhost:8088/responses \
   -d '{"input": "How do I clean my tent?", "stream": false}' | jq .
 ```
 
-#### Without `azd`
+#### Manual setup
 
 If running without `azd`, set environment variables manually (see [Environment Variables](#environment-variables)), then:
 
@@ -335,7 +338,7 @@ Wait ~3 minutes for AAD propagation before invoking the agent.
 
 ### Images built on Apple Silicon or other ARM64 machines do not work on our service
 
-We **recommend deploying with `azd deploy`**, which uses ACR remote build and always produces images with the correct architecture.
+**Deploy with `azd deploy`**, which uses ACR remote build and always produces images with the correct architecture.
 
 If you choose to **build locally**, and your machine is **not `linux/amd64`** (for example, an Apple Silicon Mac), the image will **not be compatible with our service**, causing runtime failures.
 

samples/csharp/hosted-agents/agent-framework/file-tools/README.md

@@ -32,7 +32,7 @@ See [Program.cs](Program.cs) for the full implementation.
 
 Before running this sample, ensure you have:
 
-1. **Azure Developer CLI (`azd`)** (recommended)
+1. **Azure Developer CLI (`azd`)**
    - [Install azd](https://learn.microsoft.com/en-us/azure/developer/azure-developer-cli/install-azd) (1.25 or later) and the unified Foundry CLI extension: `azd ext install microsoft.foundry`
    - Authenticated: `azd auth login`
 
@@ -44,7 +44,7 @@ Before running this sample, ensure you have:
    - Download from [https://dotnet.microsoft.com/download](https://dotnet.microsoft.com/download)
 
 > [!NOTE]
-> You do **not** need an existing [Microsoft Foundry](https://learn.microsoft.com/en-us/azure/ai-foundry/what-is-foundry?view=foundry) project or model deployment to get started — `azd provision` creates them for you. If you already have a project, see the [note below](#using-azd-recommended-for-cli-workflows) on how to target it.
+> You do **not** need an existing [Microsoft Foundry](https://learn.microsoft.com/en-us/azure/ai-foundry/what-is-foundry?view=foundry) project or model deployment to get started — `azd provision` creates them for you. If you already have a project, see the [note below](#using-azd) on how to target it.
 
 ### Environment Variables
 
@@ -80,19 +80,22 @@ dotnet restore
 
 ### Running the Sample
 
-The recommended way to run and test hosted agents locally is with the Azure Developer CLI (`azd`) or the Foundry Toolkit VS Code extension.
+Run and test hosted agents locally with the Azure Developer CLI (`azd`) or the Foundry Toolkit VS Code extension.
 
-#### Using the Foundry Toolkit VS Code Extension
+<details>
+<summary><h4>Using the Foundry Toolkit VS Code Extension</h4></summary>
 
 The [Foundry Toolkit VS Code extension](https://learn.microsoft.com/en-us/azure/foundry/agents/quickstarts/quickstart-hosted-agent?view=foundry&pivots=vscode) has a built-in sample gallery. You can open this sample directly from the extension without cloning the repository, it scaffolds the project into a new workspace, generates `agent.yaml`, `.env`, and `.vscode/tasks.json` + `launch.json` automatically, and configures a one-click **F5** debug experience.
 
 Chat with a running agent using the **Agent Inspector**:
 
-1. Start the agent locally first using **Using `azd`** or **Without `azd`** above. The agent listens on `http://localhost:8088/`.
+1. Start the agent locally first using **Using `azd`** or **Manual setup** above. The agent listens on `http://localhost:8088/`.
 2. Open the Command Palette (`Ctrl+Shift+P`) and run **Foundry Toolkit: Open Agent Inspector**.
 3. The Inspector auto-connects to the running agent. Send messages to chat with the agent and watch the streamed responses.
 
-#### Using [`azd`](https://learn.microsoft.com/en-us/azure/foundry/agents/quickstarts/quickstart-hosted-agent?view=foundry&pivots=azd) (recommended for CLI workflows)
+</details>
+
+#### Using [`azd`](https://learn.microsoft.com/en-us/azure/foundry/agents/quickstarts/quickstart-hosted-agent?view=foundry&pivots=azd)
 
 No cloning required. Create a new folder, point `azd` at the manifest on GitHub, and it sets up the sample and generates Bicep infrastructure, `agent.yaml`, and env config automatically:
 
@@ -116,7 +119,7 @@ azd ai agent run
 > `azd ai agent init -m <path-to-repo>/samples/csharp/hosted-agents/agent-framework/file-tools/agent.manifest.yaml`
 
 > [!NOTE]
-> If you already have a Foundry project and model deployment, add `-p <project-id> -d <deployment-name>` to `azd ai agent init` to target existing resources. You can also skip provisioning entirely and configure env vars manually — see [Without `azd`](#without-azd).
+> If you already have a Foundry project and model deployment, add `-p <project-id> -d <deployment-name>` to `azd ai agent init` to target existing resources. You can also skip provisioning entirely and configure env vars manually — see [Manual setup](#manual-setup).
 
 The agent starts on `http://localhost:8088/`.
 
@@ -147,7 +150,7 @@ azd ai agent invoke --local "Read the file at the path '../../../etc/passwd' fro
 
 The agent's tool schema only accepts a `fileName` (no `path`), and the `Path.GetFileName` + `StartsWith(root)` defence in depth rejects anything that resolves outside the tool's root. The agent will refuse and explain that only the bundled files are available.
 
-#### Without `azd`
+#### Manual setup
 
 If running without `azd`, set environment variables manually (see [Environment Variables](#environment-variables)), then:
 
@@ -208,7 +211,7 @@ Drop additional text files into [`resources/`](./resources/). The csproj `<Conte
 
 ### Images built on Apple Silicon or other ARM64 machines do not work on our service
 
-We **recommend deploying with `azd deploy`**, which uses ACR remote build and always produces images with the correct architecture.
+**Deploy with `azd deploy`**, which uses ACR remote build and always produces images with the correct architecture.
 
 If you choose to **build locally**, and your machine is **not `linux/amd64`** (for example, an Apple Silicon Mac), the image will **not be compatible with our service**, causing runtime failures.