dao-ai 0.1.14__tar.gz → 0.1.16__tar.gz

{dao_ai-0.1.14 → dao_ai-0.1.16}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dao-ai
-Version: 0.1.14
+Version: 0.1.16
 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

{dao_ai-0.1.14 → dao_ai-0.1.16}/config/examples/02_mcp/managed_mcp.yaml

@@ -3,19 +3,19 @@
 variables:
   client_id: &client_id                          # Service principal client ID
     options:
-      - env: RETAIL_AI_DATABRICKS_CLIENT_ID
-      - scope: retail_ai
+      - scope: retail_consumer_goods
         secret: RETAIL_AI_DATABRICKS_CLIENT_ID
+      - env: RETAIL_AI_DATABRICKS_CLIENT_ID
   client_secret: &client_secret                  # Service principal secret
     options:
-      - env: RETAIL_AI_DATABRICKS_CLIENT_SECRET
-      - scope: retail_ai
+      - scope: retail_consumer_goods
         secret: RETAIL_AI_DATABRICKS_CLIENT_SECRET
+      - env: RETAIL_AI_DATABRICKS_CLIENT_SECRET
   workspace_host: &workspace_host                # Databricks workspace URL
     options:
-      - env: RETAIL_AI_DATABRICKS_HOST
-      - scope: retail_ai
+      - scope: retail_consumer_goods
         secret: RETAIL_AI_DATABRICKS_HOST
+      - env: RETAIL_AI_DATABRICKS_HOST
 
 schemas:
   retail_schema: &retail_schema                  # Unity Catalog schema configuration
@@ -112,6 +112,10 @@ app:
   registered_model:                              # MLflow registered model configuration
     schema: *retail_schema                       # Schema where model will be registered
     name: mcp_agent                              # Model name in MLflow registry
+  environment_vars:
+    RETAIL_AI_DATABRICKS_CLIENT_ID: *client_id
+    RETAIL_AI_DATABRICKS_CLIENT_SECRET: *client_secret
+    RETAIL_AI_DATABRICKS_HOST: *workspace_host
   agents:                                        # List of agents included in the system
     - *mcp_agent                                 # MCP agent
   orchestration:                                 # Agent orchestration configuration

{dao_ai-0.1.14 → dao_ai-0.1.16}/config/examples/15_complete_applications/quick_serve_restaurant.yaml

@@ -144,38 +144,7 @@ resources:
       description: "A warehouse for shared endpoints"  # Description
       warehouse_id: 148ccb90800933a1                # Databricks warehouse ID
 
-  # ---------------------------------------------------------------------------
-  # DATABASES
-  # ---------------------------------------------------------------------------
-  # Configure external databases (e.g., PostgreSQL for checkpoints and memory)
-  # Supports both traditional user/password auth and OAuth2 client credentials
-  databases:
-    # PostgreSQL database for agent memory and checkpoints
-    qsr_database: &qsr_database
-      name: "retail-consumer-goods"
-      description: "Database for agent memory and checkpoints" 
-      
-      # Database connection parameters
-      # These can be set via environment variables or Databricks secrets
-      host: *database_host_var
-      port: *port_var
-      database: *database_var
-      client_id: *client_id_var
-      client_secret: *client_secret_var
-      workspace_host: *workspace_host_var
-
-          
-      # Optional: Additional PostgreSQL connection parameters
-      # Uncomment and modify as needed for your specific setup
-      # connection_kwargs:                            # Additional connection parameters
-      #   autocommit: True                            # Enable autocommit mode
-      #   prepare_threshold: 0                        # Disable prepared statements
-      #   sslmode: require                            # Require SSL connection
-      #   connect_timeout: 10                         # Connection timeout in seconds
-      
-      # Optional: Connection pool configuration
-      # max_pool_size: 20                             # Maximum connections in pool
-      # timeout: 5                                    # Connection timeout in seconds
+
 
 # =============================================================================
 # RETRIEVERS CONFIGURATION

{dao_ai-0.1.14 → dao_ai-0.1.16}/databricks.yaml.template

@@ -98,22 +98,22 @@ resources:
               config-path: ${var.config_path}
           environment_key: dao-ai-env
           
-# Cloud-specific targets with appropriate node types
-# The CLI auto-selects the target based on workspace cloud detection
+# App-specific cloud targets - ensures each app has its own deployment identity per cloud
+# The CLI auto-detects cloud provider and selects the appropriate target (e.g., app_name-azure)
 targets:
-  azure:
+  __APP_NAME__-azure:
     mode: development
     variables:
       cloud: azure
       node_type: Standard_D4ads_v5
   
-  aws:
+  __APP_NAME__-aws:
     mode: development
     variables:
       cloud: aws
       node_type: i3.xlarge
   
-  gcp:
+  __APP_NAME__-gcp:
     mode: development
     variables:
       cloud: gcp

{dao_ai-0.1.14 → dao_ai-0.1.16}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "dao-ai"
-version = "0.1.14"
+version = "0.1.16"
 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-0.1.14 → dao_ai-0.1.16}/src/dao_ai/cli.py

@@ -63,16 +63,26 @@ def detect_cloud_provider(profile: Optional[str] = None) -> Optional[str]:
         Cloud provider string ('azure', 'aws', 'gcp') or None if detection fails
     """
     try:
+        import os
         from databricks.sdk import WorkspaceClient
 
+        # Check for environment variables that might override profile
+        if profile and os.environ.get("DATABRICKS_HOST"):
+            logger.warning(
+                f"DATABRICKS_HOST environment variable is set, which may override --profile {profile}"
+            )
+
         # Create workspace client with optional profile
         if profile:
+            logger.debug(f"Creating WorkspaceClient with profile: {profile}")
             w = WorkspaceClient(profile=profile)
         else:
+            logger.debug("Creating WorkspaceClient with default/ambient credentials")
             w = WorkspaceClient()
 
         # Get the workspace URL from config
         host = w.config.host
+        logger.debug(f"WorkspaceClient host: {host}, profile used: {profile}")
         if not host:
             logger.warning("Could not determine workspace URL for cloud detection")
             return None
@@ -1143,7 +1153,7 @@ def run_databricks_command(
     app_config: AppConfig = AppConfig.from_file(config_path) if config_path else None
     normalized_name: str = normalize_name(app_config.app.name) if app_config else None
 
-    # Auto-detect cloud provider if not specified
+    # Auto-detect cloud provider if not specified (used for node_type selection)
     if not cloud:
         cloud = detect_cloud_provider(profile)
         if cloud:
@@ -1156,10 +1166,12 @@ def run_databricks_command(
     if config_path and app_config:
         generate_bundle_from_template(config_path, normalized_name)
 
-    # Use cloud as target (azure, aws, gcp) - can be overridden with explicit --target
+    # Use app-specific cloud target: {app_name}-{cloud}
+    # This ensures each app has unique deployment identity while supporting cloud-specific settings
+    # Can be overridden with explicit --target
     if not target:
-        target = cloud
-        logger.debug(f"Using cloud-based target: {target}")
+        target = f"{normalized_name}-{cloud}"
+        logger.info(f"Using app-specific cloud target: {target}")
 
     # Build databricks command
     # --profile is a global flag, --target is a subcommand flag for 'bundle'

{dao_ai-0.1.14 → dao_ai-0.1.16}/src/dao_ai/config.py

@@ -373,11 +373,13 @@ class IsDatabricksResource(ABC, BaseModel):
         """
         from dao_ai.utils import normalize_host
 
+        logger.trace(f"workspace_client_from called", context=context, on_behalf_of_user=self.on_behalf_of_user)
+
         # Check if we have headers in context for OBO
         if context and context.headers and self.on_behalf_of_user:
             headers = context.headers
             # Try both lowercase and title-case header names (HTTP headers are case-insensitive)
-            forwarded_token = headers.get("x-forwarded-access-token") or headers.get(
+            forwarded_token: str = headers.get("x-forwarded-access-token") or headers.get(
                 "X-Forwarded-Access-Token"
             )
 
@@ -2088,9 +2090,10 @@ class McpFunctionModel(BaseFunctionModel, IsDatabricksResource):
         if self.sql:
             return f"{workspace_host}/api/2.0/mcp/sql"
 
-        # Databricks App
+        # Databricks App - MCP endpoint is at {app_url}/mcp
         if self.app:
-            return self.app.url
+            app_url = self.app.url.rstrip("/")
+            return f"{app_url}/mcp"
 
         # Vector Search
         if self.vector_search: