dao-ai 0.1.11__tar.gz → 0.1.13__tar.gz

{dao_ai-0.1.11 → dao_ai-0.1.13}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dao-ai
-Version: 0.1.11
+Version: 0.1.13
 Summary: DAO AI: A modular, multi-agent orchestration framework for complex AI workflows. Supports agent handoff, tool integration, and dynamic configuration via YAML.
 Project-URL: Homepage, https://github.com/natefleming/dao-ai
 Project-URL: Documentation, https://natefleming.github.io/dao-ai
@@ -125,7 +125,7 @@ DAO AI Builder generates valid YAML configurations that work seamlessly with thi
 - **[Architecture](docs/architecture.md)** - Understand how DAO works under the hood
 
 ### Core Concepts
-- **[Key Capabilities](docs/key-capabilities.md)** - Explore 14 powerful features for production agents
+- **[Key Capabilities](docs/key-capabilities.md)** - Explore 15 powerful features for production agents
 - **[Configuration Reference](docs/configuration-reference.md)** - Complete YAML configuration guide
 - **[Examples](docs/examples.md)** - Ready-to-use example configurations
 
@@ -148,7 +148,7 @@ Before you begin, you'll need:
 - **Python 3.11 or newer** installed on your computer ([download here](https://www.python.org/downloads/))
 - **A Databricks workspace** (ask your IT team or see [Databricks docs](https://docs.databricks.com/))
   - Access to **Unity Catalog** (your organization's data catalog)
-  - **Model Serving** enabled (for deploying AI agents)
+  - **Model Serving** or **Databricks Apps** enabled (for deploying AI agents)
   - *Optional*: Vector Search, Genie (for advanced features)
 
 **Not sure if you have access?** Your Databricks administrator can grant you permissions.
@@ -345,6 +345,7 @@ DAO provides powerful capabilities for building production-ready AI agents:
 
 | Feature | Description |
 |---------|-------------|
+| **Dual Deployment Targets** | Deploy to Databricks Model Serving or Databricks Apps with a single config |
 | **Multi-Tool Support** | Python functions, Unity Catalog, MCP, Agent Endpoints |
 | **On-Behalf-Of User** | Per-user permissions and governance |
 | **Advanced Caching** | Two-tier (LRU + Semantic) caching for cost optimization |

{dao_ai-0.1.11 → dao_ai-0.1.13}/README.md

@@ -46,7 +46,7 @@ DAO AI Builder generates valid YAML configurations that work seamlessly with thi
 - **[Architecture](docs/architecture.md)** - Understand how DAO works under the hood
 
 ### Core Concepts
-- **[Key Capabilities](docs/key-capabilities.md)** - Explore 14 powerful features for production agents
+- **[Key Capabilities](docs/key-capabilities.md)** - Explore 15 powerful features for production agents
 - **[Configuration Reference](docs/configuration-reference.md)** - Complete YAML configuration guide
 - **[Examples](docs/examples.md)** - Ready-to-use example configurations
 
@@ -69,7 +69,7 @@ Before you begin, you'll need:
 - **Python 3.11 or newer** installed on your computer ([download here](https://www.python.org/downloads/))
 - **A Databricks workspace** (ask your IT team or see [Databricks docs](https://docs.databricks.com/))
   - Access to **Unity Catalog** (your organization's data catalog)
-  - **Model Serving** enabled (for deploying AI agents)
+  - **Model Serving** or **Databricks Apps** enabled (for deploying AI agents)
   - *Optional*: Vector Search, Genie (for advanced features)
 
 **Not sure if you have access?** Your Databricks administrator can grant you permissions.
@@ -266,6 +266,7 @@ DAO provides powerful capabilities for building production-ready AI agents:
 
 | Feature | Description |
 |---------|-------------|
+| **Dual Deployment Targets** | Deploy to Databricks Model Serving or Databricks Apps with a single config |
 | **Multi-Tool Support** | Python functions, Unity Catalog, MCP, Agent Endpoints |
 | **On-Behalf-Of User** | Per-user permissions and governance |
 | **Advanced Caching** | Two-tier (LRU + Semantic) caching for cost optimization |

{dao_ai-0.1.11 → dao_ai-0.1.13}/config/examples/07_human_in_the_loop/human_in_the_loop.yaml

@@ -26,6 +26,18 @@
   # - Composite: { type: composite, options: [${VAR1}, ${VAR2}, default] }
   # - Primitives: Just use the value directly
 
+variables:
+  client_id: &client_id
+    options:
+      - env: RETAIL_AI_DATABRICKS_CLIENT_ID      # Service principal client ID
+      - scope: retail_consumer_goods
+        secret: RETAIL_AI_DATABRICKS_CLIENT_ID
+  client_secret: &client_secret
+    options:
+      - env: RETAIL_AI_DATABRICKS_CLIENT_SECRET  # Service principal secret
+      - scope: retail_consumer_goods
+        secret: RETAIL_AI_DATABRICKS_CLIENT_SECRET
+
 schemas:
   retail_schema: &retail_schema
     catalog_name: nfleming                    
@@ -42,6 +54,8 @@ resources:
     lakebase_db: &lakebase_db
       name: retail-consumer-goods
       instance_name: retail-consumer-goods
+      client_id: *client_id
+      client_secret: *client_secret
 
 # =============================================================================
 # TOOLS WITH HUMAN-IN-THE-LOOP CONFIGURATIONS

{dao_ai-0.1.11 → dao_ai-0.1.13}/config/examples/15_complete_applications/hardware_store_lakebase.yaml

@@ -15,14 +15,15 @@
 variables:
   client_id: &client_id
     options:
-      - env: RETAIL_AI_DATABRICKS_CLIENT_ID      # Service principal client ID
       - scope: retail_consumer_goods
         secret: RETAIL_AI_DATABRICKS_CLIENT_ID
+      - env: RETAIL_AI_DATABRICKS_CLIENT_ID      # Service principal client ID
+
   client_secret: &client_secret
     options:
-      - env: RETAIL_AI_DATABRICKS_CLIENT_SECRET  # Service principal secret
       - scope: retail_consumer_goods
         secret: RETAIL_AI_DATABRICKS_CLIENT_SECRET
+      - env: RETAIL_AI_DATABRICKS_CLIENT_SECRET  # Service principal secret
 
 schemas:
   retail_schema: &retail_schema

{dao_ai-0.1.11 → dao_ai-0.1.13}/docs/key-capabilities.md

@@ -2,7 +2,62 @@
 
 These are the powerful features that make DAO production-ready. Don't worry if some seem complex — you can start simple and add these capabilities as you need them.
 
-## 1. Multi-Tool Support
+## 1. Dual Deployment Targets
+
+**What is this?** DAO agents can be deployed to either **Databricks Model Serving** or **Databricks Apps** using the same configuration, giving you flexibility in how you expose your agent.
+
+**Why this matters:**
+- **Model Serving**: Traditional endpoint for inference workloads, autoscaling, pay-per-token pricing
+- **Databricks Apps**: Full web applications with custom UI, background jobs, and richer integrations
+- **Single Configuration**: Switch deployment targets with one line change — no code rewrite needed
+- **Environment Consistency**: Same YAML config works in both environments
+
+**Comparison:**
+
+| Feature | Model Serving | Databricks Apps |
+|---------|--------------|-----------------|
+| **Use Case** | Inference API endpoint | Full web application |
+| **Scaling** | Auto-scales based on load | Manual scaling configuration |
+| **UI** | API only | Custom web UI possible |
+| **Pricing** | Pay per token/request | Compute-based |
+| **Deployment Speed** | ~2-5 minutes | ~2-5 minutes |
+| **Best For** | API integrations, high throughput | Interactive apps, custom UX |
+
+**How to configure:**
+
+```yaml
+app:
+  name: my_agent
+  deployment_target: model_serving  # or 'apps'
+  
+  # Model Serving specific options (only used when deployment_target: model_serving)
+  endpoint_name: my_agent_endpoint
+  workload_size: Small
+  scale_to_zero: true
+  
+  agents:
+    - *my_agent
+```
+
+**Deploy to Model Serving:**
+```bash
+dao-ai deploy -c config.yaml --target model_serving
+```
+
+**Deploy to Databricks Apps:**
+```bash
+dao-ai deploy -c config.yaml --target apps
+```
+
+**CLI override:** The `--target` flag always takes precedence over the YAML config, making it easy to deploy the same config to different environments.
+
+**Behind the scenes:**
+- Model Serving deployments create an MLflow model and serving endpoint
+- Apps deployments create a Databricks App with MLflow experiment tracking
+- Both share the same agent code, tools, and orchestration logic
+- Environment variables and secrets are automatically configured for each platform
+
+## 2. Multi-Tool Support
 
 **What are tools?** Tools are actions an agent can perform — like querying a database, calling an API, or running custom code.
 
@@ -57,7 +112,7 @@ tools:
       connection: *github_connection
 ```
 
-## 2. On-Behalf-Of User Support
+## 3. On-Behalf-Of User Support
 
 **What is this?** Many Databricks resources (like SQL warehouses, Genie spaces, and LLMs) can operate "on behalf of" the end user, using their permissions instead of the agent's service account credentials.
 
@@ -104,7 +159,7 @@ The same agent code enforces different permissions for each user automatically.
 - The user must have the necessary permissions on the underlying resources
 - Not all Databricks resources support on-behalf-of functionality
 
-## 3. Advanced Caching (Genie Queries)
+## 4. Advanced Caching (Genie Queries)
 
 **Why caching matters:** When users ask similar questions repeatedly, you don't want to pay for the same AI processing over and over. Caching stores results so you can reuse them.
 
@@ -234,7 +289,7 @@ This works by embedding both the current question *and* recent conversation turn
 
 For more details on semantic cache configuration, see [docs/semantic_cache_weight_configuration.md](semantic_cache_weight_configuration.md).
 
-## 4. Vector Search Reranking
+## 5. Vector Search Reranking
 
 **The problem:** Vector search (semantic similarity) is fast but sometimes returns loosely related results. It's like a librarian who quickly grabs 50 books that *might* be relevant.
 
@@ -321,7 +376,7 @@ rerank:
 
 **Note:** Model weights are downloaded automatically on first use (~34MB for MiniLM-L-12-v2).
 
-## 5. Human-in-the-Loop Approvals
+## 6. Human-in-the-Loop Approvals
 
 **Why this matters:** Some actions are too important to automate completely. For example, you might want human approval before an agent:
 - Deletes data
@@ -343,7 +398,7 @@ tools:
         review_prompt: "This operation will modify production data. Approve?"
 ```
 
-## 6. Memory & State Persistence
+## 7. Memory & State Persistence
 
 **What is memory?** Your agent needs to remember past conversations. When a user asks "What about size XL?" the agent should remember they were talking about shirts.
 
@@ -395,7 +450,7 @@ memory:
 - **PostgreSQL**: When you need external database features or already have PostgreSQL infrastructure
 - **Lakebase**: When you want Databricks-native persistence with Unity Catalog governance
 
-## 7. MLflow Prompt Registry Integration
+## 8. MLflow Prompt Registry Integration
 
 **The problem:** Prompts (instructions you give to AI models) need constant refinement. Hardcoding them in YAML means every change requires redeployment.
 
@@ -427,7 +482,7 @@ agents:
     prompt: *product_expert_prompt  # Loaded from MLflow registry
 ```
 
-## 8. Automated Prompt Optimization
+## 9. Automated Prompt Optimization
 
 **What is this?** Instead of manually tweaking prompts through trial and error, DAO can automatically test variations and find the best one.
 
@@ -452,7 +507,7 @@ optimizations:
       num_candidates: 5
 ```
 
-## 9. Guardrails & Response Quality Middleware
+## 10. Guardrails & Response Quality Middleware
 
 **What are guardrails?** Safety and quality controls that validate agent responses before they reach users. Think of them as quality assurance checkpoints.
 
@@ -670,7 +725,7 @@ agents:
         prompt: *professional_tone_prompt
 ```
 
-## 10. Conversation Summarization
+## 11. Conversation Summarization
 
 **The problem:** AI models have a maximum amount of text they can process (the "context window"). Long conversations eventually exceed this limit.
 
@@ -697,7 +752,7 @@ The `LoggingSummarizationMiddleware` provides detailed observability:
 INFO | Summarization: BEFORE 25 messages (~12500 tokens) → AFTER 3 messages (~2100 tokens) | Reduced by ~10400 tokens
 ```
 
-## 11. Structured Output (Response Format)
+## 12. Structured Output (Response Format)
 
 **What is this?** A way to force your agent to return data in a specific JSON structure, making responses machine-readable and predictable.
 
@@ -749,7 +804,7 @@ See `config/examples/09_structured_output/structured_output.yaml` for a complete
 
 ---
 
-## 12. Custom Input & Custom Output Support
+## 13. Custom Input & Custom Output Support
 
 **What is this?** A flexible system for passing custom configuration values to your agents and receiving enriched output with runtime state.
 
@@ -829,7 +884,7 @@ When invoked with the `custom_inputs` above, the prompt automatically populates:
 - `session` state is automatically maintained and returned in `custom_outputs`
 - Backward compatible with legacy flat custom_inputs format
 
-## 13. Middleware (Input Validation, Logging, Monitoring)
+## 14. Middleware (Input Validation, Logging, Monitoring)
 
 **What is middleware?** Middleware are functions that wrap around agent execution to add cross-cutting concerns like validation, logging, authentication, and monitoring. They run before and after the agent processes requests.
 
@@ -1049,7 +1104,7 @@ agents:
 
 ---
 
-## 14. Hook System
+## 15. Hook System
 
 **What are hooks?** Hooks let you run custom code at specific moments in your agent's lifecycle — like "before starting" or "when shutting down".
 

{dao_ai-0.1.11 → dao_ai-0.1.13}/notebooks/07_run_evaluation.py

@@ -225,6 +225,8 @@ def tool_call_efficiency(trace: Trace) -> Feedback:
         value=True,
         rationale=f"Efficient tool usage: {len(tool_calls)} successful calls"
     )
+    
+
 
 # COMMAND ----------
 

{dao_ai-0.1.11 → dao_ai-0.1.13}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "dao-ai"
-version = "0.1.11"
+version = "0.1.13"
 description = "DAO AI: A modular, multi-agent orchestration framework for complex AI workflows. Supports agent handoff, tool integration, and dynamic configuration via YAML."
 readme = "README.md"
 license = { text = "MIT" }

{dao_ai-0.1.11 → dao_ai-0.1.13}/src/dao_ai/apps/handlers.py

@@ -34,7 +34,7 @@ mlflow.set_tracking_uri("databricks")
 mlflow.langchain.autolog()
 
 # Get config path from environment or use default
-config_path: str = os.environ.get("DAO_AI_CONFIG_PATH", "model_config.yaml")
+config_path: str = os.environ.get("DAO_AI_CONFIG_PATH", "dao_ai.yaml")
 
 # Load configuration using AppConfig.from_file (consistent with CLI, notebook, builder)
 config: AppConfig = AppConfig.from_file(config_path)

{dao_ai-0.1.11 → dao_ai-0.1.13}/src/dao_ai/apps/resources.py

@@ -310,6 +310,25 @@ def _extract_secrets_from_config(config: AppConfig) -> list[dict[str, Any]]:
         A list of secret resource dictionaries with unique scope/key pairs
     """
     secrets: dict[tuple[str, str], dict[str, Any]] = {}
+    used_names: set[str] = set()
+
+    def get_unique_resource_name(base_name: str) -> str:
+        """Generate a unique resource name, adding suffix if needed."""
+        sanitized = _sanitize_resource_name(base_name)
+        if sanitized not in used_names:
+            used_names.add(sanitized)
+            return sanitized
+        # Name collision - add numeric suffix
+        counter = 1
+        while True:
+            # Leave room for suffix (e.g., "_1", "_2", etc.)
+            suffix = f"_{counter}"
+            max_base_len = 30 - len(suffix)
+            candidate = sanitized[:max_base_len] + suffix
+            if candidate not in used_names:
+                used_names.add(candidate)
+                return candidate
+            counter += 1
 
     def extract_from_value(value: Any, path: str = "") -> None:
         """Recursively extract secrets from any value."""
@@ -317,9 +336,10 @@ def _extract_secrets_from_config(config: AppConfig) -> list[dict[str, Any]]:
             secret_key = (value.scope, value.secret)
             if secret_key not in secrets:
                 # Create a unique name for the secret resource
-                resource_name = f"{value.scope}_{value.secret}".replace(
-                    "-", "_"
-                ).replace("/", "_")
+                base_name = f"{value.scope}_{value.secret}".replace("-", "_").replace(
+                    "/", "_"
+                )
+                resource_name = get_unique_resource_name(base_name)
                 secrets[secret_key] = {
                     "name": resource_name,
                     "type": "secret",
@@ -327,7 +347,9 @@ def _extract_secrets_from_config(config: AppConfig) -> list[dict[str, Any]]:
                     "key": value.secret,
                     "permissions": [{"level": "READ"}],
                 }
-                logger.debug(f"Found secret: {value.scope}/{value.secret} at {path}")
+                logger.debug(
+                    f"Found secret: {value.scope}/{value.secret} at {path} -> resource: {resource_name}"
+                )
         elif isinstance(value, dict):
             for k, v in value.items():
                 extract_from_value(v, f"{path}.{k}" if path else k)
@@ -742,6 +764,25 @@ def _extract_sdk_secrets_from_config(config: AppConfig) -> list[AppResource]:
         A list of AppResource objects for secrets
     """
     secrets: dict[tuple[str, str], AppResource] = {}
+    used_names: set[str] = set()
+
+    def get_unique_resource_name(base_name: str) -> str:
+        """Generate a unique resource name, adding suffix if needed."""
+        sanitized = _sanitize_resource_name(base_name)
+        if sanitized not in used_names:
+            used_names.add(sanitized)
+            return sanitized
+        # Name collision - add numeric suffix
+        counter = 1
+        while True:
+            # Leave room for suffix (e.g., "_1", "_2", etc.)
+            suffix = f"_{counter}"
+            max_base_len = 30 - len(suffix)
+            candidate = sanitized[:max_base_len] + suffix
+            if candidate not in used_names:
+                used_names.add(candidate)
+                return candidate
+            counter += 1
 
     def extract_from_value(value: Any) -> None:
         """Recursively extract secrets from any value."""
@@ -749,10 +790,10 @@ def _extract_sdk_secrets_from_config(config: AppConfig) -> list[AppResource]:
             secret_key = (value.scope, value.secret)
             if secret_key not in secrets:
                 # Create a unique name for the secret resource
-                resource_name = f"{value.scope}_{value.secret}".replace(
-                    "-", "_"
-                ).replace("/", "_")
-                resource_name = _sanitize_resource_name(resource_name)
+                base_name = f"{value.scope}_{value.secret}".replace("-", "_").replace(
+                    "/", "_"
+                )
+                resource_name = get_unique_resource_name(base_name)
 
                 resource = AppResource(
                     name=resource_name,
@@ -764,7 +805,7 @@ def _extract_sdk_secrets_from_config(config: AppConfig) -> list[AppResource]:
                 )
                 secrets[secret_key] = resource
                 logger.debug(
-                    f"Found secret for SDK resource: {value.scope}/{value.secret}"
+                    f"Found secret for SDK resource: {value.scope}/{value.secret} -> resource: {resource_name}"
                 )
         elif isinstance(value, dict):
             for v in value.values():
@@ -969,12 +1010,21 @@ def generate_app_yaml(
         {"name": "MLFLOW_TRACKING_URI", "value": "databricks"},
         {"name": "MLFLOW_REGISTRY_URI", "value": "databricks-uc"},
         {"name": "MLFLOW_EXPERIMENT_ID", "valueFrom": "experiment"},
-        {"name": "DAO_AI_CONFIG_PATH", "value": "model_config.yaml"},
+        {"name": "DAO_AI_CONFIG_PATH", "value": "dao_ai.yaml"},
     ]
 
     # Extract environment variables from config.app.environment_vars
     config_env_vars = _extract_env_vars_from_config(config)
 
+    # Environment variables that are automatically provided by Databricks Apps
+    # and should not be included in app.yaml
+    platform_provided_env_vars = {"DATABRICKS_HOST"}
+
+    # Filter out platform-provided env vars from config
+    config_env_vars = [
+        e for e in config_env_vars if e["name"] not in platform_provided_env_vars
+    ]
+
     # Merge config env vars, avoiding duplicates (config takes precedence)
     base_env_names = {e["name"] for e in env_vars}
     for config_env in config_env_vars:

{dao_ai-0.1.11 → dao_ai-0.1.13}/src/dao_ai/apps/server.py

@@ -7,13 +7,13 @@ uses the AgentServer for the Databricks Apps runtime.
 
 Configuration Loading:
     The config path is specified via the DAO_AI_CONFIG_PATH environment variable,
-    or defaults to model_config.yaml in the current directory.
+    or defaults to dao_ai.yaml in the current directory.
 
 Usage:
     # With environment variable
     DAO_AI_CONFIG_PATH=/path/to/config.yaml python -m dao_ai.apps.server
 
-    # With default model_config.yaml in current directory
+    # With default dao_ai.yaml in current directory
     python -m dao_ai.apps.server
 """
 

{dao_ai-0.1.11 → dao_ai-0.1.13}/src/dao_ai/config.py

@@ -294,36 +294,37 @@ class IsDatabricksResource(ABC, BaseModel):
 
         # Check for OBO first (highest priority)
         if self.on_behalf_of_user:
-            # NEW: In Databricks Apps, use forwarded headers for per-user auth
-            try:
-                from mlflow.genai.agent_server import get_request_headers
-
-                headers = get_request_headers()
-                forwarded_token = headers.get("x-forwarded-access-token")
+            # In Databricks Apps, use forwarded headers for per-user auth
+            from mlflow.genai.agent_server import get_request_headers
+
+            headers = get_request_headers()
+            logger.debug(f"Headers received: {list(headers.keys())}")
+            # Try both lowercase and title-case header names (HTTP headers are case-insensitive)
+            forwarded_token = headers.get("x-forwarded-access-token") or headers.get(
+                "X-Forwarded-Access-Token"
+            )
 
-                if forwarded_token:
-                    forwarded_user = headers.get("x-forwarded-user", "unknown")
-                    logger.debug(
-                        f"Creating WorkspaceClient for {self.__class__.__name__} "
-                        f"with OBO using forwarded token from Databricks Apps",
-                        forwarded_user=forwarded_user,
-                    )
-                    # Use workspace_host if configured, otherwise SDK will auto-detect
-                    workspace_host_value: str | None = (
-                        normalize_host(value_of(self.workspace_host))
-                        if self.workspace_host
-                        else None
-                    )
-                    return WorkspaceClient(
-                        host=workspace_host_value,
-                        token=forwarded_token,
-                        auth_type="pat",
-                    )
-            except (ImportError, LookupError):
-                # mlflow not available or headers not set - fall through to Model Serving
-                pass
+            if forwarded_token:
+                forwarded_user = headers.get("x-forwarded-user") or headers.get(
+                    "X-Forwarded-User", "unknown"
+                )
+                logger.debug(
+                    f"Creating WorkspaceClient for {self.__class__.__name__} "
+                    f"with OBO using forwarded token from Databricks Apps",
+                    forwarded_user=forwarded_user,
+                )
+                # Use workspace_host if configured, otherwise SDK will auto-detect
+                workspace_host_value: str | None = (
+                    normalize_host(value_of(self.workspace_host))
+                    if self.workspace_host
+                    else None
+                )
+                return WorkspaceClient(
+                    host=workspace_host_value,
+                    token=forwarded_token,
+                    auth_type="pat",
+                )
 
-            # Fall back to Model Serving OBO (existing behavior)
             credentials_strategy: CredentialsStrategy = ModelServingUserCredentials()
             logger.debug(
                 f"Creating WorkspaceClient for {self.__class__.__name__} "

{dao_ai-0.1.11 → dao_ai-0.1.13}/src/dao_ai/providers/databricks.py

@@ -152,25 +152,77 @@ class DatabricksProvider(ServiceProvider):
         client_secret: str | None = None,
         workspace_host: str | None = None,
     ) -> None:
-        if w is None:
-            w = _workspace_client(
-                pat=pat,
-                client_id=client_id,
-                client_secret=client_secret,
-                workspace_host=workspace_host,
+        # Store credentials for lazy initialization
+        self._pat = pat
+        self._client_id = client_id
+        self._client_secret = client_secret
+        self._workspace_host = workspace_host
+
+        # Lazy initialization for WorkspaceClient
+        self._w: WorkspaceClient | None = w
+        self._w_initialized = w is not None
+
+        # Lazy initialization for VectorSearchClient - only create when needed
+        # This avoids authentication errors in Databricks Apps where VSC
+        # requires explicit credentials but the platform uses ambient auth
+        self._vsc: VectorSearchClient | None = vsc
+        self._vsc_initialized = vsc is not None
+
+        # Lazy initialization for DatabricksFunctionClient
+        self._dfs: DatabricksFunctionClient | None = dfs
+        self._dfs_initialized = dfs is not None
+
+    @property
+    def w(self) -> WorkspaceClient:
+        """Lazy initialization of WorkspaceClient."""
+        if not self._w_initialized:
+            self._w = _workspace_client(
+                pat=self._pat,
+                client_id=self._client_id,
+                client_secret=self._client_secret,
+                workspace_host=self._workspace_host,
             )
-        if vsc is None:
-            vsc = _vector_search_client(
-                pat=pat,
-                client_id=client_id,
-                client_secret=client_secret,
-                workspace_host=workspace_host,
+            self._w_initialized = True
+        return self._w  # type: ignore[return-value]
+
+    @w.setter
+    def w(self, value: WorkspaceClient) -> None:
+        """Set WorkspaceClient and mark as initialized."""
+        self._w = value
+        self._w_initialized = True
+
+    @property
+    def vsc(self) -> VectorSearchClient:
+        """Lazy initialization of VectorSearchClient."""
+        if not self._vsc_initialized:
+            self._vsc = _vector_search_client(
+                pat=self._pat,
+                client_id=self._client_id,
+                client_secret=self._client_secret,
+                workspace_host=self._workspace_host,
             )
-        if dfs is None:
-            dfs = _function_client(w=w)
-        self.w = w
-        self.vsc = vsc
-        self.dfs = dfs
+            self._vsc_initialized = True
+        return self._vsc  # type: ignore[return-value]
+
+    @vsc.setter
+    def vsc(self, value: VectorSearchClient) -> None:
+        """Set VectorSearchClient and mark as initialized."""
+        self._vsc = value
+        self._vsc_initialized = True
+
+    @property
+    def dfs(self) -> DatabricksFunctionClient:
+        """Lazy initialization of DatabricksFunctionClient."""
+        if not self._dfs_initialized:
+            self._dfs = _function_client(w=self.w)
+            self._dfs_initialized = True
+        return self._dfs  # type: ignore[return-value]
+
+    @dfs.setter
+    def dfs(self, value: DatabricksFunctionClient) -> None:
+        """Set DatabricksFunctionClient and mark as initialized."""
+        self._dfs = value
+        self._dfs_initialized = True
 
     def experiment_name(self, config: AppConfig) -> str:
         current_user: User = self.w.current_user.me()
@@ -572,7 +624,7 @@ class DatabricksProvider(ServiceProvider):
         source_config_path: str | None = config.source_config_path
         if source_config_path:
             # Read the config file and upload to workspace
-            config_file_name: str = "model_config.yaml"
+            config_file_name: str = "dao_ai.yaml"
             workspace_config_path: str = f"{source_path}/{config_file_name}"
 
             logger.info(
@@ -603,7 +655,7 @@ class DatabricksProvider(ServiceProvider):
             logger.warning(
                 "No source config path available. "
                 "Ensure DAO_AI_CONFIG_PATH is set in the app environment or "
-                "model_config.yaml exists in the app source directory."
+                "dao_ai.yaml exists in the app source directory."
             )
 
         # Generate and upload app.yaml with dynamically discovered resources
@@ -634,7 +686,9 @@ class DatabricksProvider(ServiceProvider):
             generate_user_api_scopes,
         )
 
-        sdk_resources = generate_sdk_resources(config, experiment_id=experiment.experiment_id)
+        sdk_resources = generate_sdk_resources(
+            config, experiment_id=experiment.experiment_id
+        )
         if sdk_resources:
             logger.info(
                 "Discovered app resources from config",