azurefunctions-agents-runtime 0.0.0.dev6__tar.gz → 0.1.0b3__tar.gz

{azurefunctions_agents_runtime-0.0.0.dev6 → azurefunctions_agents_runtime-0.1.0b3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: azurefunctions-agents-runtime
-Version: 0.0.0.dev6
+Version: 0.1.0b3
 Summary: A markdown-first programming model for building AI agents on Azure Functions, powered by the Microsoft Agent Framework.
 License: MIT
 Requires-Python: >=3.13
@@ -58,21 +58,17 @@ azurefunctions-agents-runtime
 
 ## Model Provider Configuration
 
-The runtime uses Microsoft Agent Framework, which supports OpenAI, Azure OpenAI, and Microsoft Foundry as inference back-ends. Auto-detection picks the first provider whose env vars are set, in this order:
+The runtime uses Microsoft Agent Framework, which supports Microsoft Foundry, Azure OpenAI, and OpenAI as inference back-ends. The public preview quickstart and samples use **Microsoft Foundry** as the primary path, pinned with `AZURE_FUNCTIONS_AGENTS_PROVIDER=foundry`.
 
-1. `AZURE_OPENAI_ENDPOINT` → Azure OpenAI
-2. `FOUNDRY_PROJECT_ENDPOINT` → Microsoft Foundry
-3. `OPENAI_API_KEY` → OpenAI
+| Provider | `AZURE_FUNCTIONS_AGENTS_PROVIDER` | Required env vars | Notes |
+| --- | --- | --- | --- |
+| Microsoft Foundry | `foundry` | `FOUNDRY_PROJECT_ENDPOINT`, `FOUNDRY_MODEL` | Recommended quickstart/sample path. Uses `DefaultAzureCredential`; run `az login` locally and set `AZURE_CLIENT_ID` in multi-identity Function Apps. |
+| Azure OpenAI | `azure_openai` | `AZURE_OPENAI_ENDPOINT`, `AZURE_OPENAI_DEPLOYMENT`, optional `AZURE_OPENAI_API_VERSION` | Alternative Azure-hosted provider. `AZURE_OPENAI_DEPLOYMENT` takes precedence over `AZURE_FUNCTIONS_AGENTS_MODEL`. If `AZURE_OPENAI_API_KEY` is omitted the SDK uses `DefaultAzureCredential` (AAD). |
+| OpenAI | `openai` | `OPENAI_API_KEY`, optional `AZURE_FUNCTIONS_AGENTS_MODEL` (default `gpt-4o-mini`) | Alternative non-Azure provider. `AZURE_FUNCTIONS_AGENTS_MODEL` applies directly for OpenAI. |
 
-You can pin the provider explicitly with `MAF_PROVIDER=openai|azure_openai|foundry`.
+If `AZURE_FUNCTIONS_AGENTS_PROVIDER` is unset, auto-detection picks the first provider whose env vars are set, in this order: `AZURE_OPENAI_ENDPOINT` → `FOUNDRY_PROJECT_ENDPOINT` → `OPENAI_API_KEY`. Set `AZURE_FUNCTIONS_AGENTS_PROVIDER` to make the provider choice intentional.
 
-| Provider          | Required env vars                                                                            | Notes                                                                                                                                 |
-| ----------------- | -------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------- |
-| OpenAI            | `OPENAI_API_KEY`, optional `MAF_MODEL` (default `gpt-4o-mini`)                               | `MAF_MODEL` applies directly for OpenAI.                                                                                              |
-| Azure OpenAI      | `AZURE_OPENAI_ENDPOINT`, `AZURE_OPENAI_DEPLOYMENT`, optional `AZURE_OPENAI_API_VERSION`      | `AZURE_OPENAI_DEPLOYMENT` takes precedence over `MAF_MODEL`. If `AZURE_OPENAI_API_KEY` is omitted the SDK uses `DefaultAzureCredential` (AAD); set `AZURE_CLIENT_ID` in multi-identity Function Apps. |
-| Microsoft Foundry | `FOUNDRY_PROJECT_ENDPOINT`, optional `FOUNDRY_MODEL`                                         | `FOUNDRY_MODEL` takes precedence over `MAF_MODEL`. Uses `DefaultAzureCredential`; set `AZURE_CLIENT_ID` in multi-identity Function Apps. |
-
-Model resolution precedence is: explicit requested model > provider-specific env (`AZURE_OPENAI_DEPLOYMENT` for Azure OpenAI, `FOUNDRY_MODEL` for Foundry) > `MAF_MODEL` > provider default.
+Model resolution precedence is: explicit requested model > provider-specific env (`FOUNDRY_MODEL` for Foundry, `AZURE_OPENAI_DEPLOYMENT` for Azure OpenAI) > `AZURE_FUNCTIONS_AGENTS_MODEL` > provider default.
 
 ## Quick Start
 
@@ -84,6 +80,8 @@ Create `main.agent.md`:
 ---
 name: My Agent
 description: A helpful assistant
+
+builtin_endpoints: true
 ---
 
 You are a helpful assistant. Answer questions concisely.
@@ -101,7 +99,15 @@ app = create_function_app()
 
 > The app root is auto-detected from `AzureWebJobsScriptRoot` (set by `func start` and the Azure Functions host). You can override it with `create_function_app(app_root=Path(__file__).parent)` or the `AZURE_FUNCTIONS_AGENTS_APP_ROOT` env var.
 
-### 3. Create `host.json`
+### 3. Create `agents.config.yaml`
+
+```yaml
+# Default runtime configuration
+model: $FOUNDRY_MODEL
+timeout: 900
+```
+
+### 4. Create `host.json`
 
 ```json
 {
@@ -118,7 +124,7 @@ app = create_function_app()
 }
 ```
 
-### 4. Create `requirements.txt`
+### 5. Create `requirements.txt`
 
 ```
 azurefunctions-agents-runtime
@@ -126,9 +132,9 @@ azurefunctions-agents-runtime
 
 Connector-backed tools are exposed through MCP servers in `mcp.json`, and connector-triggered apps use the Azure Functions Connector Extension through the Functions extension bundle. No package extra is required.
 
-### 5. Set the model provider
+### 6. Set the model provider
 
-For local development with OpenAI:
+For local development with Microsoft Foundry, sign in with `az login`, then create `local.settings.json`:
 
 ```json
 {
@@ -136,13 +142,14 @@ For local development with OpenAI:
   "Values": {
     "FUNCTIONS_WORKER_RUNTIME": "python",
     "AzureWebJobsStorage": "UseDevelopmentStorage=true",
-    "OPENAI_API_KEY": "sk-...",
-    "MAF_MODEL": "gpt-4o-mini"
+    "AZURE_FUNCTIONS_AGENTS_PROVIDER": "foundry",
+    "FOUNDRY_PROJECT_ENDPOINT": "https://<project-name>.<region>.services.ai.azure.com/api/projects/<project-name>",
+    "FOUNDRY_MODEL": "gpt-5.4"
   }
 }
 ```
 
-### 6. Start Azurite (local storage emulator)
+### 7. Start Azurite (local storage emulator)
 
 The MCP server endpoint and non-HTTP triggers (timer, queue, blob, etc.) require a storage account. Locally, use [Azurite](https://learn.microsoft.com/azure/storage/common/storage-use-azurite) via Docker:
 
@@ -152,28 +159,28 @@ docker run -d --name azurite -p 10000:10000 -p 10001:10001 -p 10002:10002 \
   azurite --skipApiVersionCheck --blobHost 0.0.0.0 --queueHost 0.0.0.0 --tableHost 0.0.0.0
 ```
 
-### 7. Run locally
+### 8. Run locally
 
 ```bash
 func start
 ```
 
-Your agent is now running at `http://localhost:7071/` with a built-in chat UI, HTTP API (`/agent/chat`, `/agent/chatstream`), and MCP server (`/runtime/webhooks/mcp`).
+Your agent is now running at `http://localhost:7071/agents/main/` with a built-in chat UI, HTTP API (`/agents/main/chat`, `/agents/main/chatstream`), and MCP tool exposed through the Functions MCP endpoint (`/runtime/webhooks/mcp`).
 
 ## Features
 
 **Architecture overview:** see [`docs/architecture.md`](docs/architecture.md) for the module map and data flow pipeline.
 
-### `main.agent.md`
+### Built-in endpoints
 
-Define an agent with a markdown file. When `main.agent.md` is present, the runtime automatically registers:
+Any `.agent.md` file can opt into built-in endpoints with `builtin_endpoints`. The route slug comes from the `.agent.md` filename after sanitization, not from the display `name:` field.
 
-- **Chat UI** — built-in single-page web interface at the app root
-- **HTTP APIs** — `POST /agent/chat` (JSON) and `POST /agent/chatstream` (SSE)
-- **MCP server** — `/runtime/webhooks/mcp` for VS Code, Claude Desktop, etc.
+- **Debug chat UI** — built-in single-page web interface at `/agents/{slug}/`
+- **HTTP APIs** — `POST /agents/{slug}/chat` (JSON) and `POST /agents/{slug}/chatstream` (SSE)
+- **MCP tool** — optional tool exposed through `/runtime/webhooks/mcp` for VS Code, Claude Desktop, etc.
 - **Session persistence** — multi-turn conversations stored in Azure Blob Storage via the runtime's `BlobHistoryProvider`, reusing the function app's `AzureWebJobsStorage` account
 
-Non-main agents can also opt into their own chat UI and HTTP debug endpoints with `debug.chat: true` (or `debug: true`), served at `/agents/{slug}/`, `/agents/{slug}/chat`, and `/agents/{slug}/chatstream`, where `{slug}` is derived from the `.agent.md` filename (not the display `name:` field). See [`docs/front-matter-spec.md#function-name-resolution`](docs/front-matter-spec.md#function-name-resolution).
+If any built-in endpoint is enabled, `trigger` is optional. This allows endpoint-only agents as well as triggered agents that also expose a chat UI or API. `builtin_endpoints.debug_chat_ui: true` automatically enables the backing chat APIs. `builtin_endpoints: true` is shorthand for enabling all built-in endpoints, including the MCP tool. See [`docs/front-matter-spec.md#builtin_endpoints`](docs/front-matter-spec.md#builtin_endpoints).
 
 ### Event-driven agents (`<name>.agent.md`)
 
@@ -201,10 +208,10 @@ description: What this agent does
 
 # Optional: system tools (code execution)
 system_tools:
-  execute_in_sessions:
-    session_pool_management_endpoint: $ACA_SESSION_POOL_ENDPOINT
+  dynamic_sessions_code_interpreter:
+    endpoint: $ACA_SESSION_POOL_ENDPOINT
 
-# For triggered agents only (not `main.agent.md`):
+# Optional when builtin_endpoints is enabled; required otherwise:
 trigger:
   type: timer_trigger      # or queue_trigger, connector_trigger, etc.
   args:
@@ -228,8 +235,8 @@ Agent instructions in markdown...
 
 ### Multiple functions from markdown
 
-- **`main.agent.md`** — creates HTTP chat, MCP, and UI endpoints. No other triggers are supported in this file.
-- **`<name>.agent.md`** — creates an event-triggered Azure Function. Exactly one trigger per file. With `debug.chat: true` (or `debug: true`), it also serves `/agents/{slug}/`, `/agents/{slug}/chat`, and `/agents/{slug}/chatstream`. The sanitized filename stem becomes the base Azure Function name. If two agent files sanitize to the same name (for example, `daily-report.agent.md` and `daily_report.agent.md`), the runtime auto-suffixes both the Azure Function name and the non-main debug slug (`_2`, `_3`, ...), keeping them paired in practice (`daily_report_2` ↔ `/agents/daily_report_2/`). The frontmatter `name:` field is display-only. See [`docs/front-matter-spec.md#function-name-resolution`](docs/front-matter-spec.md#function-name-resolution) and [`docs/front-matter-spec.md#debug`](docs/front-matter-spec.md#debug).
+- **`*.agent.md` with `trigger`** — creates an event-triggered Azure Function. Exactly one trigger per file.
+- **`*.agent.md` with `builtin_endpoints`** — also serves `/agents/{slug}/`, `/agents/{slug}/chat`, and `/agents/{slug}/chatstream` when chat endpoints are enabled, and can expose an MCP tool when `builtin_endpoints: true` or `builtin_endpoints.mcp: true`. The sanitized filename stem becomes the base Azure Function name and endpoint slug. If two agent files sanitize to the same name (for example, `daily-report.agent.md` and `daily_report.agent.md`), the runtime auto-suffixes both the Azure Function name and the built-in endpoint slug (`_2`, `_3`, ...), keeping them paired in practice (`daily_report_2` ↔ `/agents/daily_report_2/`). The frontmatter `name:` field is display-only. See [`docs/front-matter-spec.md#function-name-resolution`](docs/front-matter-spec.md#function-name-resolution) and [`docs/front-matter-spec.md#builtin_endpoints`](docs/front-matter-spec.md#builtin_endpoints).
 
 When a triggered function runs, the agent's markdown body is used as the system instructions. The prompt sent to the agent includes the trigger type and the serialized binding data:
 
@@ -295,8 +302,8 @@ Variable references are resolved inline at load time anywhere string values are
 name: Notifier
 description: Sends updates to $TEAM_NAME
 system_tools:
-  execute_in_sessions:
-    session_pool_management_endpoint: "https://$HOST/api"
+  dynamic_sessions_code_interpreter:
+    endpoint: "https://$HOST/api"
 ---
 
 Send a daily summary email to $TO_EMAIL.
@@ -305,7 +312,7 @@ Post a message to the %TEAM_NAME% team's General channel.
 
 If `HOST=contoso.internal`, `TO_EMAIL=alice@example.com`, and `TEAM_NAME=Engineering` are set in the environment, those values resolve inline:
 
-> `session_pool_management_endpoint: "https://contoso.internal/api"`
+> `endpoint: "https://contoso.internal/api"`
 >
 > Send a daily summary email to alice@example.com.
 >
@@ -346,13 +353,13 @@ def reverse_string(text: str) -> str:
 
 `@tool` is re-exported from `agent_framework`. Functions can be sync or async; types in the signature feed MAF's automatic JSON-Schema generation. Tools that need richer schemas can be declared with `agent_framework.FunctionTool` directly.
 
-## What `main.agent.md` Enables
+## Built-in Endpoint Routes
 
-When a `main.agent.md` file exists in your app root, the runtime automatically registers:
+Built-in endpoints are explicit per agent. The filename stem determines `{slug}`; for example, `main.agent.md` uses `main` and `daily_azure_report.agent.md` uses `daily_azure_report`.
 
 ### Chat UI
 
-A built-in single-page chat interface served at `/` for the main agent, and at `/agents/{slug}/` for any non-main agent with `debug.chat: true` (or `debug: true`). For non-main agents, `{slug}` comes from the `.agent.md` filename after sanitization, not from the display `name:` field. No frontend code needed — just open `http://localhost:7071/` locally or `https://<your-app>.azurewebsites.net/` when deployed. See [`docs/front-matter-spec.md#function-name-resolution`](docs/front-matter-spec.md#function-name-resolution).
+A built-in single-page chat interface served at `/agents/{slug}/` when `builtin_endpoints.debug_chat_ui: true` (or `builtin_endpoints: true`). No frontend code needed — just open `http://localhost:7071/agents/main/` locally for `main.agent.md`, or `https://<your-app>.azurewebsites.net/agents/{slug}/` when deployed. See [`docs/front-matter-spec.md#function-name-resolution`](docs/front-matter-spec.md#function-name-resolution).
 
 On first load, you'll be prompted for the base URL and a function key (for deployed apps). These are stored in browser local storage and can be changed via the gear icon.
 
@@ -360,8 +367,7 @@ On first load, you'll be prompted for the base URL and a function key (for deplo
 
 POST endpoints for programmatic access:
 
-- **Main agent:** `POST /agent/chat` and `POST /agent/chatstream`
-- **Non-main agent with `debug.chat: true`:** `POST /agents/{slug}/chat` and `POST /agents/{slug}/chatstream` (`{slug}` comes from the `.agent.md` filename after sanitization)
+- **Any agent with `builtin_endpoints.chat_api: true`:** `POST /agents/{slug}/chat` and `POST /agents/{slug}/chatstream`
 
 The JSON endpoint returns `session_id`, `response`, and `tool_calls`. The streaming endpoint uses Server-Sent Events (SSE) with `session`, `delta`, `intermediate`, `tool_start`, `tool_end`, `done`, and `error` events.
 
@@ -369,11 +375,11 @@ Pass `x-ms-session-id` header to continue a conversation across requests. If omi
 
 ### MCP Server
 
-An MCP-compatible endpoint at `/runtime/webhooks/mcp` that any MCP client (VS Code, Claude Desktop, etc.) can connect to. Requires the MCP extension system key in the `x-functions-key` header when deployed.
+When `builtin_endpoints: true` or `builtin_endpoints.mcp: true`, the agent is exposed as an MCP tool named after its slug through the shared MCP-compatible endpoint at `/runtime/webhooks/mcp`. Requires the MCP extension system key in the `x-functions-key` header when deployed.
 
-### Without `main.agent.md`
+### Without built-in endpoints
 
-If there's no `main.agent.md`, the root (`/`) chat UI, `/agent/*` chat APIs, and `/runtime/webhooks/mcp` endpoint are disabled. The app still runs triggered functions, and non-main agents can still opt into per-agent chat surfaces with `debug.chat: true` (or `debug: true`). See [`docs/front-matter-spec.md#debug`](docs/front-matter-spec.md#debug).
+If no agent enables built-in endpoints, no chat UI, chat API, chatstream, or agent MCP tool is registered. The app still runs triggered functions. See [`docs/front-matter-spec.md#builtin_endpoints`](docs/front-matter-spec.md#builtin_endpoints).
 
 ## MCP Server Configuration
 
@@ -402,7 +408,6 @@ String values in `mcp.json` support inline environment-variable substitution wit
       "type": "http",
       "url": "$O365_MCP_SERVER_URL",
       "tools": ["office365_SendEmailV2"],
-      "load_prompts": false,
       "auth": {
         "scope": "https://apihub.azure.com/.default",
         "client_id": "$O365_MCP_CLIENT_ID"
@@ -418,10 +423,10 @@ Tools from configured MCP servers are automatically available to the agent at ru
 - **`url`** — the MCP server endpoint URL (required)
 - **`headers`** — optional HTTP headers (e.g. for authentication)
 - **`tools`** — optional array of tool name patterns to allow (default: `["*"]`)
-- **`load_tools`** — optional boolean controlling whether tools are loaded from the MCP server (default: `true`)
-- **`load_prompts`** — optional boolean controlling whether prompts are loaded from the MCP server (default: `true`). Set this to `false` for MCP servers that do not implement `prompts/list`.
 - **`auth`** — optional Azure Identity authentication configuration. Set `auth.scope` to the token scope required by the MCP server. The runtime uses `DefaultAzureCredential` to acquire the token.
 
+The runtime loads MCP tools and skips MCP prompts. This avoids startup/runtime failures from connector-backed MCP servers that support tools but reject `prompts/list`.
+
 By default, MCP auth follows the app-wide identity selection: `AZURE_CLIENT_ID` when set, otherwise the system-assigned identity/default Azure credential chain. To choose a user-assigned managed identity for a single MCP server without changing the app-wide identity, set `auth.client_id` in that server's `mcp.json` entry. If the configured client ID is empty or an unresolved placeholder, the runtime falls back to the app-wide identity selection.
 
 > **Note**: Entries without a `url`, with unresolved placeholders in `url`, or with a `type` other than `"http"` / `"streamable-http"`, are ignored with a warning. Use the remote HTTP transport instead.
@@ -445,7 +450,7 @@ Multi-turn conversations are persisted as JSON Lines, one record per message:
 - **Local dev fallback.** When neither `AzureWebJobsStorage` nor
   `AzureWebJobsStorage__blobServiceUri` is set, history falls back to MAF's
   `FileHistoryProvider` writing to
-  `{AZURE_FUNCTIONS_AGENTS_CONFIG_DIR}/agent-sessions/{session_id}.jsonl`,
+  `{AZURE_FUNCTIONS_AGENTS_SESSION_DIR}/agent-sessions/{session_id}.jsonl`,
   defaulting to `~/.azure-functions-agents/agent-sessions/`.
 
 Session ids must match `^[A-Za-z0-9._-]{1,128}$` — anything else is rejected at the API boundary.
@@ -465,20 +470,21 @@ See the [`samples/`](samples/) directory for complete, deployable example apps:
 
 ### Required Azure App Settings
 
-Set the model provider env vars described above (e.g. `OPENAI_API_KEY` and `MAF_MODEL`, `AZURE_OPENAI_ENDPOINT` + `AZURE_OPENAI_DEPLOYMENT`, or `FOUNDRY_PROJECT_ENDPOINT` + `FOUNDRY_MODEL`). For Azure OpenAI and Microsoft Foundry, the provider-specific deployment/model setting takes precedence over `MAF_MODEL`.
+Set the model provider env vars described above. The preview samples use Microsoft Foundry (`AZURE_FUNCTIONS_AGENTS_PROVIDER=foundry`, `FOUNDRY_PROJECT_ENDPOINT`, and `FOUNDRY_MODEL`). Azure OpenAI (`AZURE_OPENAI_ENDPOINT` + `AZURE_OPENAI_DEPLOYMENT`) and OpenAI (`OPENAI_API_KEY` and optionally `AZURE_FUNCTIONS_AGENTS_MODEL`) are supported alternatives. For Microsoft Foundry and Azure OpenAI, the provider-specific model/deployment setting takes precedence over `AZURE_FUNCTIONS_AGENTS_MODEL`.
 
-When the agent uses connector-backed MCP servers, connector triggers, or `execution_sandbox`, the function app's **system-assigned or user-assigned Managed Identity** must be enabled and granted access to the target resource — otherwise `DefaultAzureCredential` will fail to obtain a token. In multi-identity Function Apps, set `AZURE_CLIENT_ID` so the runtime uses the intended managed identity for Azure OpenAI, Foundry, blob-backed session storage, ACA Dynamic Sessions, and ARM/data-plane connector calls. For an individual MCP server, set `auth.client_id` in `mcp.json` to choose a different managed identity just for that server.
+When the agent uses connector-backed MCP servers, connector triggers, or `dynamic_sessions_code_interpreter`, the function app's **system-assigned or user-assigned Managed Identity** must be enabled and granted access to the target resource — otherwise `DefaultAzureCredential` will fail to obtain a token. In multi-identity Function Apps, set `AZURE_CLIENT_ID` so the runtime uses the intended managed identity for Azure OpenAI, Foundry, blob-backed session storage, ACA Dynamic Sessions, and ARM/data-plane connector calls. For an individual MCP server, set `auth.client_id` in `mcp.json` to choose a different managed identity just for that server. For an individual code interpreter pool, set `system_tools.dynamic_sessions_code_interpreter.client_id`.
 
 ### Optional config overrides
 
 | Setting | Purpose |
 |---|---|
 | `AZURE_FUNCTIONS_AGENTS_APP_ROOT` | Override the app root used to discover `*.agent.md`, `tools/`, `skills/`, and `mcp.json` |
-| `AZURE_FUNCTIONS_AGENTS_CONFIG_DIR` | Override the directory used for session storage |
-| `AGENT_TIMEOUT` | Per-call timeout in seconds (default `900`) |
-| `MAF_PROVIDER` | Pin the model provider (`openai`/`azure_openai`/`foundry`) and skip auto-detection |
-| `MAF_REASONING_EFFORT` | Reasoning effort for supported reasoning models (default `high`; valid values include `none`, `low`, `medium`, `high`, `xhigh`) |
-| `MAF_REASONING_SUMMARY` | Reasoning summary mode for supported reasoning models (default `concise`; valid values are `auto`, `concise`, `detailed`) |
+| `AZURE_FUNCTIONS_AGENTS_SESSION_DIR` | Override the directory used for local session storage |
+| `AZURE_FUNCTIONS_AGENTS_TIMEOUT_SECONDS` | Per-call timeout in seconds (default `900`) |
+| `AZURE_FUNCTIONS_AGENTS_PROVIDER` | Pin the model provider (`openai`/`azure_openai`/`foundry`) and skip auto-detection |
+| `AZURE_FUNCTIONS_AGENTS_MODEL` | Runtime-owned model fallback when no provider-specific model/deployment is set |
+| `AZURE_FUNCTIONS_AGENTS_REASONING_EFFORT` | Optional reasoning effort for supported reasoning models (valid values include `none`, `low`, `medium`, `high`, `xhigh`) |
+| `AZURE_FUNCTIONS_AGENTS_REASONING_SUMMARY` | Optional reasoning summary mode for supported reasoning models (valid values are `auto`, `concise`, `detailed`) |
 
 ## Development
 

{azurefunctions_agents_runtime-0.0.0.dev6 → azurefunctions_agents_runtime-0.1.0b3}/README.md

@@ -29,21 +29,17 @@ azurefunctions-agents-runtime
 
 ## Model Provider Configuration
 
-The runtime uses Microsoft Agent Framework, which supports OpenAI, Azure OpenAI, and Microsoft Foundry as inference back-ends. Auto-detection picks the first provider whose env vars are set, in this order:
+The runtime uses Microsoft Agent Framework, which supports Microsoft Foundry, Azure OpenAI, and OpenAI as inference back-ends. The public preview quickstart and samples use **Microsoft Foundry** as the primary path, pinned with `AZURE_FUNCTIONS_AGENTS_PROVIDER=foundry`.
 
-1. `AZURE_OPENAI_ENDPOINT` → Azure OpenAI
-2. `FOUNDRY_PROJECT_ENDPOINT` → Microsoft Foundry
-3. `OPENAI_API_KEY` → OpenAI
+| Provider | `AZURE_FUNCTIONS_AGENTS_PROVIDER` | Required env vars | Notes |
+| --- | --- | --- | --- |
+| Microsoft Foundry | `foundry` | `FOUNDRY_PROJECT_ENDPOINT`, `FOUNDRY_MODEL` | Recommended quickstart/sample path. Uses `DefaultAzureCredential`; run `az login` locally and set `AZURE_CLIENT_ID` in multi-identity Function Apps. |
+| Azure OpenAI | `azure_openai` | `AZURE_OPENAI_ENDPOINT`, `AZURE_OPENAI_DEPLOYMENT`, optional `AZURE_OPENAI_API_VERSION` | Alternative Azure-hosted provider. `AZURE_OPENAI_DEPLOYMENT` takes precedence over `AZURE_FUNCTIONS_AGENTS_MODEL`. If `AZURE_OPENAI_API_KEY` is omitted the SDK uses `DefaultAzureCredential` (AAD). |
+| OpenAI | `openai` | `OPENAI_API_KEY`, optional `AZURE_FUNCTIONS_AGENTS_MODEL` (default `gpt-4o-mini`) | Alternative non-Azure provider. `AZURE_FUNCTIONS_AGENTS_MODEL` applies directly for OpenAI. |
 
-You can pin the provider explicitly with `MAF_PROVIDER=openai|azure_openai|foundry`.
+If `AZURE_FUNCTIONS_AGENTS_PROVIDER` is unset, auto-detection picks the first provider whose env vars are set, in this order: `AZURE_OPENAI_ENDPOINT` → `FOUNDRY_PROJECT_ENDPOINT` → `OPENAI_API_KEY`. Set `AZURE_FUNCTIONS_AGENTS_PROVIDER` to make the provider choice intentional.
 
-| Provider          | Required env vars                                                                            | Notes                                                                                                                                 |
-| ----------------- | -------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------- |
-| OpenAI            | `OPENAI_API_KEY`, optional `MAF_MODEL` (default `gpt-4o-mini`)                               | `MAF_MODEL` applies directly for OpenAI.                                                                                              |
-| Azure OpenAI      | `AZURE_OPENAI_ENDPOINT`, `AZURE_OPENAI_DEPLOYMENT`, optional `AZURE_OPENAI_API_VERSION`      | `AZURE_OPENAI_DEPLOYMENT` takes precedence over `MAF_MODEL`. If `AZURE_OPENAI_API_KEY` is omitted the SDK uses `DefaultAzureCredential` (AAD); set `AZURE_CLIENT_ID` in multi-identity Function Apps. |
-| Microsoft Foundry | `FOUNDRY_PROJECT_ENDPOINT`, optional `FOUNDRY_MODEL`                                         | `FOUNDRY_MODEL` takes precedence over `MAF_MODEL`. Uses `DefaultAzureCredential`; set `AZURE_CLIENT_ID` in multi-identity Function Apps. |
-
-Model resolution precedence is: explicit requested model > provider-specific env (`AZURE_OPENAI_DEPLOYMENT` for Azure OpenAI, `FOUNDRY_MODEL` for Foundry) > `MAF_MODEL` > provider default.
+Model resolution precedence is: explicit requested model > provider-specific env (`FOUNDRY_MODEL` for Foundry, `AZURE_OPENAI_DEPLOYMENT` for Azure OpenAI) > `AZURE_FUNCTIONS_AGENTS_MODEL` > provider default.
 
 ## Quick Start
 
@@ -55,6 +51,8 @@ Create `main.agent.md`:
 ---
 name: My Agent
 description: A helpful assistant
+
+builtin_endpoints: true
 ---
 
 You are a helpful assistant. Answer questions concisely.
@@ -72,7 +70,15 @@ app = create_function_app()
 
 > The app root is auto-detected from `AzureWebJobsScriptRoot` (set by `func start` and the Azure Functions host). You can override it with `create_function_app(app_root=Path(__file__).parent)` or the `AZURE_FUNCTIONS_AGENTS_APP_ROOT` env var.
 
-### 3. Create `host.json`
+### 3. Create `agents.config.yaml`
+
+```yaml
+# Default runtime configuration
+model: $FOUNDRY_MODEL
+timeout: 900
+```
+
+### 4. Create `host.json`
 
 ```json
 {
@@ -89,7 +95,7 @@ app = create_function_app()
 }
 ```
 
-### 4. Create `requirements.txt`
+### 5. Create `requirements.txt`
 
 ```
 azurefunctions-agents-runtime
@@ -97,9 +103,9 @@ azurefunctions-agents-runtime
 
 Connector-backed tools are exposed through MCP servers in `mcp.json`, and connector-triggered apps use the Azure Functions Connector Extension through the Functions extension bundle. No package extra is required.
 
-### 5. Set the model provider
+### 6. Set the model provider
 
-For local development with OpenAI:
+For local development with Microsoft Foundry, sign in with `az login`, then create `local.settings.json`:
 
 ```json
 {
@@ -107,13 +113,14 @@ For local development with OpenAI:
   "Values": {
     "FUNCTIONS_WORKER_RUNTIME": "python",
     "AzureWebJobsStorage": "UseDevelopmentStorage=true",
-    "OPENAI_API_KEY": "sk-...",
-    "MAF_MODEL": "gpt-4o-mini"
+    "AZURE_FUNCTIONS_AGENTS_PROVIDER": "foundry",
+    "FOUNDRY_PROJECT_ENDPOINT": "https://<project-name>.<region>.services.ai.azure.com/api/projects/<project-name>",
+    "FOUNDRY_MODEL": "gpt-5.4"
   }
 }
 ```
 
-### 6. Start Azurite (local storage emulator)
+### 7. Start Azurite (local storage emulator)
 
 The MCP server endpoint and non-HTTP triggers (timer, queue, blob, etc.) require a storage account. Locally, use [Azurite](https://learn.microsoft.com/azure/storage/common/storage-use-azurite) via Docker:
 
@@ -123,28 +130,28 @@ docker run -d --name azurite -p 10000:10000 -p 10001:10001 -p 10002:10002 \
   azurite --skipApiVersionCheck --blobHost 0.0.0.0 --queueHost 0.0.0.0 --tableHost 0.0.0.0
 ```
 
-### 7. Run locally
+### 8. Run locally
 
 ```bash
 func start
 ```
 
-Your agent is now running at `http://localhost:7071/` with a built-in chat UI, HTTP API (`/agent/chat`, `/agent/chatstream`), and MCP server (`/runtime/webhooks/mcp`).
+Your agent is now running at `http://localhost:7071/agents/main/` with a built-in chat UI, HTTP API (`/agents/main/chat`, `/agents/main/chatstream`), and MCP tool exposed through the Functions MCP endpoint (`/runtime/webhooks/mcp`).
 
 ## Features
 
 **Architecture overview:** see [`docs/architecture.md`](docs/architecture.md) for the module map and data flow pipeline.
 
-### `main.agent.md`
+### Built-in endpoints
 
-Define an agent with a markdown file. When `main.agent.md` is present, the runtime automatically registers:
+Any `.agent.md` file can opt into built-in endpoints with `builtin_endpoints`. The route slug comes from the `.agent.md` filename after sanitization, not from the display `name:` field.
 
-- **Chat UI** — built-in single-page web interface at the app root
-- **HTTP APIs** — `POST /agent/chat` (JSON) and `POST /agent/chatstream` (SSE)
-- **MCP server** — `/runtime/webhooks/mcp` for VS Code, Claude Desktop, etc.
+- **Debug chat UI** — built-in single-page web interface at `/agents/{slug}/`
+- **HTTP APIs** — `POST /agents/{slug}/chat` (JSON) and `POST /agents/{slug}/chatstream` (SSE)
+- **MCP tool** — optional tool exposed through `/runtime/webhooks/mcp` for VS Code, Claude Desktop, etc.
 - **Session persistence** — multi-turn conversations stored in Azure Blob Storage via the runtime's `BlobHistoryProvider`, reusing the function app's `AzureWebJobsStorage` account
 
-Non-main agents can also opt into their own chat UI and HTTP debug endpoints with `debug.chat: true` (or `debug: true`), served at `/agents/{slug}/`, `/agents/{slug}/chat`, and `/agents/{slug}/chatstream`, where `{slug}` is derived from the `.agent.md` filename (not the display `name:` field). See [`docs/front-matter-spec.md#function-name-resolution`](docs/front-matter-spec.md#function-name-resolution).
+If any built-in endpoint is enabled, `trigger` is optional. This allows endpoint-only agents as well as triggered agents that also expose a chat UI or API. `builtin_endpoints.debug_chat_ui: true` automatically enables the backing chat APIs. `builtin_endpoints: true` is shorthand for enabling all built-in endpoints, including the MCP tool. See [`docs/front-matter-spec.md#builtin_endpoints`](docs/front-matter-spec.md#builtin_endpoints).
 
 ### Event-driven agents (`<name>.agent.md`)
 
@@ -172,10 +179,10 @@ description: What this agent does
 
 # Optional: system tools (code execution)
 system_tools:
-  execute_in_sessions:
-    session_pool_management_endpoint: $ACA_SESSION_POOL_ENDPOINT
+  dynamic_sessions_code_interpreter:
+    endpoint: $ACA_SESSION_POOL_ENDPOINT
 
-# For triggered agents only (not `main.agent.md`):
+# Optional when builtin_endpoints is enabled; required otherwise:
 trigger:
   type: timer_trigger      # or queue_trigger, connector_trigger, etc.
   args:
@@ -199,8 +206,8 @@ Agent instructions in markdown...
 
 ### Multiple functions from markdown
 
-- **`main.agent.md`** — creates HTTP chat, MCP, and UI endpoints. No other triggers are supported in this file.
-- **`<name>.agent.md`** — creates an event-triggered Azure Function. Exactly one trigger per file. With `debug.chat: true` (or `debug: true`), it also serves `/agents/{slug}/`, `/agents/{slug}/chat`, and `/agents/{slug}/chatstream`. The sanitized filename stem becomes the base Azure Function name. If two agent files sanitize to the same name (for example, `daily-report.agent.md` and `daily_report.agent.md`), the runtime auto-suffixes both the Azure Function name and the non-main debug slug (`_2`, `_3`, ...), keeping them paired in practice (`daily_report_2` ↔ `/agents/daily_report_2/`). The frontmatter `name:` field is display-only. See [`docs/front-matter-spec.md#function-name-resolution`](docs/front-matter-spec.md#function-name-resolution) and [`docs/front-matter-spec.md#debug`](docs/front-matter-spec.md#debug).
+- **`*.agent.md` with `trigger`** — creates an event-triggered Azure Function. Exactly one trigger per file.
+- **`*.agent.md` with `builtin_endpoints`** — also serves `/agents/{slug}/`, `/agents/{slug}/chat`, and `/agents/{slug}/chatstream` when chat endpoints are enabled, and can expose an MCP tool when `builtin_endpoints: true` or `builtin_endpoints.mcp: true`. The sanitized filename stem becomes the base Azure Function name and endpoint slug. If two agent files sanitize to the same name (for example, `daily-report.agent.md` and `daily_report.agent.md`), the runtime auto-suffixes both the Azure Function name and the built-in endpoint slug (`_2`, `_3`, ...), keeping them paired in practice (`daily_report_2` ↔ `/agents/daily_report_2/`). The frontmatter `name:` field is display-only. See [`docs/front-matter-spec.md#function-name-resolution`](docs/front-matter-spec.md#function-name-resolution) and [`docs/front-matter-spec.md#builtin_endpoints`](docs/front-matter-spec.md#builtin_endpoints).
 
 When a triggered function runs, the agent's markdown body is used as the system instructions. The prompt sent to the agent includes the trigger type and the serialized binding data:
 
@@ -266,8 +273,8 @@ Variable references are resolved inline at load time anywhere string values are
 name: Notifier
 description: Sends updates to $TEAM_NAME
 system_tools:
-  execute_in_sessions:
-    session_pool_management_endpoint: "https://$HOST/api"
+  dynamic_sessions_code_interpreter:
+    endpoint: "https://$HOST/api"
 ---
 
 Send a daily summary email to $TO_EMAIL.
@@ -276,7 +283,7 @@ Post a message to the %TEAM_NAME% team's General channel.
 
 If `HOST=contoso.internal`, `TO_EMAIL=alice@example.com`, and `TEAM_NAME=Engineering` are set in the environment, those values resolve inline:
 
-> `session_pool_management_endpoint: "https://contoso.internal/api"`
+> `endpoint: "https://contoso.internal/api"`
 >
 > Send a daily summary email to alice@example.com.
 >
@@ -317,13 +324,13 @@ def reverse_string(text: str) -> str:
 
 `@tool` is re-exported from `agent_framework`. Functions can be sync or async; types in the signature feed MAF's automatic JSON-Schema generation. Tools that need richer schemas can be declared with `agent_framework.FunctionTool` directly.
 
-## What `main.agent.md` Enables
+## Built-in Endpoint Routes
 
-When a `main.agent.md` file exists in your app root, the runtime automatically registers:
+Built-in endpoints are explicit per agent. The filename stem determines `{slug}`; for example, `main.agent.md` uses `main` and `daily_azure_report.agent.md` uses `daily_azure_report`.
 
 ### Chat UI
 
-A built-in single-page chat interface served at `/` for the main agent, and at `/agents/{slug}/` for any non-main agent with `debug.chat: true` (or `debug: true`). For non-main agents, `{slug}` comes from the `.agent.md` filename after sanitization, not from the display `name:` field. No frontend code needed — just open `http://localhost:7071/` locally or `https://<your-app>.azurewebsites.net/` when deployed. See [`docs/front-matter-spec.md#function-name-resolution`](docs/front-matter-spec.md#function-name-resolution).
+A built-in single-page chat interface served at `/agents/{slug}/` when `builtin_endpoints.debug_chat_ui: true` (or `builtin_endpoints: true`). No frontend code needed — just open `http://localhost:7071/agents/main/` locally for `main.agent.md`, or `https://<your-app>.azurewebsites.net/agents/{slug}/` when deployed. See [`docs/front-matter-spec.md#function-name-resolution`](docs/front-matter-spec.md#function-name-resolution).
 
 On first load, you'll be prompted for the base URL and a function key (for deployed apps). These are stored in browser local storage and can be changed via the gear icon.
 
@@ -331,8 +338,7 @@ On first load, you'll be prompted for the base URL and a function key (for deplo
 
 POST endpoints for programmatic access:
 
-- **Main agent:** `POST /agent/chat` and `POST /agent/chatstream`
-- **Non-main agent with `debug.chat: true`:** `POST /agents/{slug}/chat` and `POST /agents/{slug}/chatstream` (`{slug}` comes from the `.agent.md` filename after sanitization)
+- **Any agent with `builtin_endpoints.chat_api: true`:** `POST /agents/{slug}/chat` and `POST /agents/{slug}/chatstream`
 
 The JSON endpoint returns `session_id`, `response`, and `tool_calls`. The streaming endpoint uses Server-Sent Events (SSE) with `session`, `delta`, `intermediate`, `tool_start`, `tool_end`, `done`, and `error` events.
 
@@ -340,11 +346,11 @@ Pass `x-ms-session-id` header to continue a conversation across requests. If omi
 
 ### MCP Server
 
-An MCP-compatible endpoint at `/runtime/webhooks/mcp` that any MCP client (VS Code, Claude Desktop, etc.) can connect to. Requires the MCP extension system key in the `x-functions-key` header when deployed.
+When `builtin_endpoints: true` or `builtin_endpoints.mcp: true`, the agent is exposed as an MCP tool named after its slug through the shared MCP-compatible endpoint at `/runtime/webhooks/mcp`. Requires the MCP extension system key in the `x-functions-key` header when deployed.
 
-### Without `main.agent.md`
+### Without built-in endpoints
 
-If there's no `main.agent.md`, the root (`/`) chat UI, `/agent/*` chat APIs, and `/runtime/webhooks/mcp` endpoint are disabled. The app still runs triggered functions, and non-main agents can still opt into per-agent chat surfaces with `debug.chat: true` (or `debug: true`). See [`docs/front-matter-spec.md#debug`](docs/front-matter-spec.md#debug).
+If no agent enables built-in endpoints, no chat UI, chat API, chatstream, or agent MCP tool is registered. The app still runs triggered functions. See [`docs/front-matter-spec.md#builtin_endpoints`](docs/front-matter-spec.md#builtin_endpoints).
 
 ## MCP Server Configuration
 
@@ -373,7 +379,6 @@ String values in `mcp.json` support inline environment-variable substitution wit
       "type": "http",
       "url": "$O365_MCP_SERVER_URL",
       "tools": ["office365_SendEmailV2"],
-      "load_prompts": false,
       "auth": {
         "scope": "https://apihub.azure.com/.default",
         "client_id": "$O365_MCP_CLIENT_ID"
@@ -389,10 +394,10 @@ Tools from configured MCP servers are automatically available to the agent at ru
 - **`url`** — the MCP server endpoint URL (required)
 - **`headers`** — optional HTTP headers (e.g. for authentication)
 - **`tools`** — optional array of tool name patterns to allow (default: `["*"]`)
-- **`load_tools`** — optional boolean controlling whether tools are loaded from the MCP server (default: `true`)
-- **`load_prompts`** — optional boolean controlling whether prompts are loaded from the MCP server (default: `true`). Set this to `false` for MCP servers that do not implement `prompts/list`.
 - **`auth`** — optional Azure Identity authentication configuration. Set `auth.scope` to the token scope required by the MCP server. The runtime uses `DefaultAzureCredential` to acquire the token.
 
+The runtime loads MCP tools and skips MCP prompts. This avoids startup/runtime failures from connector-backed MCP servers that support tools but reject `prompts/list`.
+
 By default, MCP auth follows the app-wide identity selection: `AZURE_CLIENT_ID` when set, otherwise the system-assigned identity/default Azure credential chain. To choose a user-assigned managed identity for a single MCP server without changing the app-wide identity, set `auth.client_id` in that server's `mcp.json` entry. If the configured client ID is empty or an unresolved placeholder, the runtime falls back to the app-wide identity selection.
 
 > **Note**: Entries without a `url`, with unresolved placeholders in `url`, or with a `type` other than `"http"` / `"streamable-http"`, are ignored with a warning. Use the remote HTTP transport instead.
@@ -416,7 +421,7 @@ Multi-turn conversations are persisted as JSON Lines, one record per message:
 - **Local dev fallback.** When neither `AzureWebJobsStorage` nor
   `AzureWebJobsStorage__blobServiceUri` is set, history falls back to MAF's
   `FileHistoryProvider` writing to
-  `{AZURE_FUNCTIONS_AGENTS_CONFIG_DIR}/agent-sessions/{session_id}.jsonl`,
+  `{AZURE_FUNCTIONS_AGENTS_SESSION_DIR}/agent-sessions/{session_id}.jsonl`,
   defaulting to `~/.azure-functions-agents/agent-sessions/`.
 
 Session ids must match `^[A-Za-z0-9._-]{1,128}$` — anything else is rejected at the API boundary.
@@ -436,20 +441,21 @@ See the [`samples/`](samples/) directory for complete, deployable example apps:
 
 ### Required Azure App Settings
 
-Set the model provider env vars described above (e.g. `OPENAI_API_KEY` and `MAF_MODEL`, `AZURE_OPENAI_ENDPOINT` + `AZURE_OPENAI_DEPLOYMENT`, or `FOUNDRY_PROJECT_ENDPOINT` + `FOUNDRY_MODEL`). For Azure OpenAI and Microsoft Foundry, the provider-specific deployment/model setting takes precedence over `MAF_MODEL`.
+Set the model provider env vars described above. The preview samples use Microsoft Foundry (`AZURE_FUNCTIONS_AGENTS_PROVIDER=foundry`, `FOUNDRY_PROJECT_ENDPOINT`, and `FOUNDRY_MODEL`). Azure OpenAI (`AZURE_OPENAI_ENDPOINT` + `AZURE_OPENAI_DEPLOYMENT`) and OpenAI (`OPENAI_API_KEY` and optionally `AZURE_FUNCTIONS_AGENTS_MODEL`) are supported alternatives. For Microsoft Foundry and Azure OpenAI, the provider-specific model/deployment setting takes precedence over `AZURE_FUNCTIONS_AGENTS_MODEL`.
 
-When the agent uses connector-backed MCP servers, connector triggers, or `execution_sandbox`, the function app's **system-assigned or user-assigned Managed Identity** must be enabled and granted access to the target resource — otherwise `DefaultAzureCredential` will fail to obtain a token. In multi-identity Function Apps, set `AZURE_CLIENT_ID` so the runtime uses the intended managed identity for Azure OpenAI, Foundry, blob-backed session storage, ACA Dynamic Sessions, and ARM/data-plane connector calls. For an individual MCP server, set `auth.client_id` in `mcp.json` to choose a different managed identity just for that server.
+When the agent uses connector-backed MCP servers, connector triggers, or `dynamic_sessions_code_interpreter`, the function app's **system-assigned or user-assigned Managed Identity** must be enabled and granted access to the target resource — otherwise `DefaultAzureCredential` will fail to obtain a token. In multi-identity Function Apps, set `AZURE_CLIENT_ID` so the runtime uses the intended managed identity for Azure OpenAI, Foundry, blob-backed session storage, ACA Dynamic Sessions, and ARM/data-plane connector calls. For an individual MCP server, set `auth.client_id` in `mcp.json` to choose a different managed identity just for that server. For an individual code interpreter pool, set `system_tools.dynamic_sessions_code_interpreter.client_id`.
 
 ### Optional config overrides
 
 | Setting | Purpose |
 |---|---|
 | `AZURE_FUNCTIONS_AGENTS_APP_ROOT` | Override the app root used to discover `*.agent.md`, `tools/`, `skills/`, and `mcp.json` |
-| `AZURE_FUNCTIONS_AGENTS_CONFIG_DIR` | Override the directory used for session storage |
-| `AGENT_TIMEOUT` | Per-call timeout in seconds (default `900`) |
-| `MAF_PROVIDER` | Pin the model provider (`openai`/`azure_openai`/`foundry`) and skip auto-detection |
-| `MAF_REASONING_EFFORT` | Reasoning effort for supported reasoning models (default `high`; valid values include `none`, `low`, `medium`, `high`, `xhigh`) |
-| `MAF_REASONING_SUMMARY` | Reasoning summary mode for supported reasoning models (default `concise`; valid values are `auto`, `concise`, `detailed`) |
+| `AZURE_FUNCTIONS_AGENTS_SESSION_DIR` | Override the directory used for local session storage |
+| `AZURE_FUNCTIONS_AGENTS_TIMEOUT_SECONDS` | Per-call timeout in seconds (default `900`) |
+| `AZURE_FUNCTIONS_AGENTS_PROVIDER` | Pin the model provider (`openai`/`azure_openai`/`foundry`) and skip auto-detection |
+| `AZURE_FUNCTIONS_AGENTS_MODEL` | Runtime-owned model fallback when no provider-specific model/deployment is set |
+| `AZURE_FUNCTIONS_AGENTS_REASONING_EFFORT` | Optional reasoning effort for supported reasoning models (valid values include `none`, `low`, `medium`, `high`, `xhigh`) |
+| `AZURE_FUNCTIONS_AGENTS_REASONING_SUMMARY` | Optional reasoning summary mode for supported reasoning models (valid values are `auto`, `concise`, `detailed`) |
 
 ## Development
 

{azurefunctions_agents_runtime-0.0.0.dev6 → azurefunctions_agents_runtime-0.1.0b3}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "azurefunctions-agents-runtime"
-version = "0.0.0dev6"
+dynamic = ["version"]
 description = "A markdown-first programming model for building AI agents on Azure Functions, powered by the Microsoft Agent Framework."
 readme = "README.md"
 license = {text = "MIT"}
@@ -37,6 +37,9 @@ dev = [
 [tool.setuptools.packages.find]
 where = ["src"]
 
+[tool.setuptools.dynamic]
+version = {attr = "azure_functions_agents.__version__"}
+
 [tool.setuptools.package-data]
 azure_functions_agents = ["public/**"]