dao-ai 0.0.24__tar.gz → 0.0.25__tar.gz

{dao_ai-0.0.24 → dao_ai-0.0.25}/.gitignore

@@ -273,3 +273,6 @@ tags
 .databricks
 
 mlruns/
+
+# Generated bundle configurations (created from databricks.yaml.template at deployment time)
+databricks.yaml

{dao_ai-0.0.24 → dao_ai-0.0.25}/Makefile

@@ -64,7 +64,7 @@ schema: depends
 	@$(PYTHON) -c "from dao_ai.config import AppConfig; import json; print(json.dumps(AppConfig.model_json_schema(), indent=2))"
 
 test: 
-	$(PYTEST) $(TEST_DIR)
+	$(PYTEST) -ra --tb=short $(TEST_DIR)
 
 help:
 	$(info TOP_DIR: $(TOP_DIR))

{dao_ai-0.0.24 → dao_ai-0.0.25}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dao-ai
-Version: 0.0.24
+Version: 0.0.25
 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-0.0.24 → dao_ai-0.0.25}/config/quick_serve_restaurant/quick-serve-restaurant.yaml

@@ -261,51 +261,30 @@ tools:
       name: dao_ai.tools.current_time_tool
 
 
-# =============================================================================
-# MEMORY CONFIGURATION
-# =============================================================================
-# Configure persistent storage for agent conversations and context
-
-memory: &memory
-  # Conversation checkpointing for state persistence
-  checkpointer: 
-    name: default_checkpointer                      # Checkpointer identifier
-    #type: postgres                                    # Store type (memory or postgres)
-    type: memory
-    database: *qsr_database                     # Reference to database configuration
-
-  # Long-term memory store for agent context
-  store: 
-    name: default_store                             # Store identifier
-    #type: postgres                                    # Store type (memory or postgres)
-    type: memory
-    embedding_model: *embedding_model               # Model for semantic memory
-    dims: 1536                                      # Embedding dimensions
-    database: *qsr_database                      # Database for persistence (if needed)
-    namespace: "{user_id}"
-
-# =============================================================================
-# AGENTS CONFIGURATION
-# =============================================================================
-# Define specialized agents for different aspects of customer service
-# Each agent has specific tools, capabilities, and responsibilities
-
-agents:
+# ==============================================================================
+# PROMPTS CONFIGURATION
+# ==============================================================================
+# Define reusable prompts that can be stored in MLflow Prompt Registry
+# 
+# Prompts support:
+# - default_template: Fallback template when registry is unavailable
+# - description: Used as commit message when syncing to registry
+# - alias: Reference specific versions (e.g., "production", "staging")
+# - version: Pin to specific version number
+# - tags: Metadata and organization
+#
+# Priority: Registry > default_template (registry is source of truth)
+# ==============================================================================
+
+prompts:
   # ---------------------------------------------------------------------------
-  # BARISTA AGENT
+  # Barista Agent Prompt
   # ---------------------------------------------------------------------------
-  # Expert coffee shop agent specialized in menu inquiries, recommendations, ordering, and order history
-  barista: &barista
-    name: barista                                   # Agent identifier
-    description: "Expert coffee shop barista specializing in menu recommendations, coffee ordering, price inquiries, item descriptions, and order history. Can find products by description, match items within price ranges, process coffee orders, and retrieve historical order data."
-    model: *tool_calling_llm                       # Reference to LLM configuration
-    tools: 
-      - *insert_coffee_order_tool
-      - *match_item_by_description_and_price_tool
-      - *match_historical_item_order_by_date_tool
-      - *lookup_items_by_descriptions_tool
-      - *current_time_tool
-    prompt: |                                       # System prompt defining agent behavior
+  barista_prompt: &barista_prompt
+    schema: *qsr_schema
+    name: barista_prompt
+    description: "Expert coffee shop barista prompt for menu recommendations, ordering, and order history"
+    default_template: |
       ### User Information
       - **User Id**: {user_id}
       - **Session ID**: {thread_id}
@@ -352,6 +331,56 @@ agents:
       **Handle Ambiguity**: If a customer's request is unclear, use your tools to show options and let them choose.
 
       You are friendly, knowledgeable, and always ready to help customers find exactly what they're looking for!
+    tags:
+      environment: production
+      agent_name: barista
+
+# =============================================================================
+# MEMORY CONFIGURATION
+# =============================================================================
+# Configure persistent storage for agent conversations and context
+
+memory: &memory
+  # Conversation checkpointing for state persistence
+  checkpointer: 
+    name: default_checkpointer                      # Checkpointer identifier
+    #type: postgres                                    # Store type (memory or postgres)
+    type: memory
+    database: *qsr_database                     # Reference to database configuration
+
+  # Long-term memory store for agent context
+  store: 
+    name: default_store                             # Store identifier
+    #type: postgres                                    # Store type (memory or postgres)
+    type: memory
+    embedding_model: *embedding_model               # Model for semantic memory
+    dims: 1536                                      # Embedding dimensions
+    database: *qsr_database                      # Database for persistence (if needed)
+    namespace: "{user_id}"
+
+# =============================================================================
+# AGENTS CONFIGURATION
+# =============================================================================
+# Define specialized agents for different aspects of customer service
+# Each agent has specific tools, capabilities, and responsibilities
+
+agents:
+  # ---------------------------------------------------------------------------
+  # BARISTA AGENT (Using Prompt Reference - Recommended)
+  # ---------------------------------------------------------------------------
+  # Expert coffee shop agent specialized in menu inquiries, recommendations, ordering, and order history
+  # This example shows how to use a prompt reference from the prompts section
+  barista: &barista
+    name: barista                                   # Agent identifier
+    description: "Expert coffee shop barista specializing in menu recommendations, coffee ordering, price inquiries, item descriptions, and order history. Can find products by description, match items within price ranges, process coffee orders, and retrieve historical order data."
+    model: *tool_calling_llm                       # Reference to LLM configuration
+    tools: 
+      - *insert_coffee_order_tool
+      - *match_item_by_description_and_price_tool
+      - *match_historical_item_order_by_date_tool
+      - *lookup_items_by_descriptions_tool
+      - *current_time_tool
+    prompt: *barista_prompt                        # Reference to prompt (instead of inline)
     handoff_prompt: |                              
       Coffee shop inquiries including menu questions, item recommendations, price checks, coffee ordering, taste descriptions, and order history.
       Examples: "What coffee drinks do you have?", "I'd like a medium latte", "What's good for under $4?", "What did I order yesterday?", "Tell me about your cold brew", "Can you recommend something sweet?"

dao_ai-0.0.24/databricks.yaml → dao_ai-0.0.25/databricks.yaml.template

@@ -1,7 +1,7 @@
 # yaml-language-server: $schema=./schemas/bundle_config_schema.json
 
 bundle:
-  name: dao-ai-bundle
+  name: __APP_NAME__
 
 artifacts:
   default:
@@ -12,17 +12,19 @@ artifacts:
 variables:
   config_path:
     description: Path to the configuration file for the job.
-    default: ../config/model_config.yaml
   node_type: 
     description: The job compute node type
     default: Standard_D4ads_v5
-  app_name: 
-    description: The job name
 
 resources:
   jobs:
-    deploy-end-to-end:
-      name: ${var.app_name}
+    # The job name and bundle name are templated and replaced by CLI at deployment time
+    # This allows multiple apps to coexist with separate bundle identities
+    deploy_job:
+      name: __APP_NAME__-job
+      tags:
+        app_name: __APP_NAME__
+        config_path: ${var.config_path}
       job_clusters:
         - job_cluster_key: common-cluster
           new_cluster:
@@ -92,7 +94,7 @@ resources:
           environment_key: dao-ai-env
           
 targets:
-  dev:
+  __APP_NAME__:
     mode: development
     default: true
 

{dao_ai-0.0.24 → dao_ai-0.0.25}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "dao-ai"
-version = "0.0.24"
+version = "0.0.25"
 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-0.0.24 → dao_ai-0.0.25}/schemas/model_config_schema.json

@@ -548,14 +548,18 @@
           "title": "Messages"
         },
         "custom_inputs": {
-          "additionalProperties": true,
-          "title": "Custom Inputs",
-          "type": "object"
+          "anyOf": [
+            {
+              "additionalProperties": true,
+              "type": "object"
+            },
+            {
+              "type": "null"
+            }
+          ],
+          "title": "Custom Inputs"
         }
       },
-      "required": [
-        "custom_inputs"
-      ],
       "title": "ChatPayload",
       "type": "object"
     },

{dao_ai-0.0.24 → dao_ai-0.0.25}/src/dao_ai/cli.py

@@ -460,6 +460,49 @@ def setup_logging(verbosity: int) -> None:
     logger.add(sys.stderr, level=level)
 
 
+def generate_bundle_from_template(config_path: Path, app_name: str) -> Path:
+    """
+    Generate an app-specific databricks.yaml from databricks.yaml.template.
+
+    This function:
+    1. Reads databricks.yaml.template (permanent template file)
+    2. Replaces __APP_NAME__ with the actual app name
+    3. Writes to databricks.yaml (overwrites if exists)
+    4. Returns the path to the generated file
+
+    The generated databricks.yaml is overwritten on each deployment and is not tracked in git.
+    Schema reference remains pointing to ./schemas/bundle_config_schema.json.
+
+    Args:
+        config_path: Path to the app config file
+        app_name: Normalized app name
+
+    Returns:
+        Path to the generated databricks.yaml file
+    """
+    cwd = Path.cwd()
+    template_path = cwd / "databricks.yaml.template"
+    output_path = cwd / "databricks.yaml"
+
+    if not template_path.exists():
+        logger.error(f"Template file {template_path} does not exist.")
+        sys.exit(1)
+
+    # Read template
+    with open(template_path, "r") as f:
+        template_content = f.read()
+
+    # Replace template variables
+    bundle_content = template_content.replace("__APP_NAME__", app_name)
+
+    # Write generated databricks.yaml (overwrite if exists)
+    with open(output_path, "w") as f:
+        f.write(bundle_content)
+
+    logger.info(f"Generated bundle configuration at {output_path} from template")
+    return output_path
+
+
 def run_databricks_command(
     command: list[str],
     profile: Optional[str] = None,
@@ -467,44 +510,55 @@ def run_databricks_command(
     target: Optional[str] = None,
     dry_run: bool = False,
 ) -> None:
-    """Execute a databricks CLI command with optional profile."""
+    """Execute a databricks CLI command with optional profile and target."""
+    config_path = Path(config) if config else None
+
+    if config_path and not config_path.exists():
+        logger.error(f"Configuration file {config_path} does not exist.")
+        sys.exit(1)
+
+    # Load app config and generate bundle from template
+    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
+
+    # Generate app-specific bundle from template (overwrites databricks.yaml temporarily)
+    if config_path and app_config:
+        generate_bundle_from_template(config_path, normalized_name)
+
+    # Use app name as target if not explicitly provided
+    # This ensures each app gets its own Terraform state in .databricks/bundle/<app-name>/
+    if not target and normalized_name:
+        target = normalized_name
+        logger.debug(f"Using app-specific target: {target}")
+
+    # Build databricks command (no -c flag needed, uses databricks.yaml in current dir)
     cmd = ["databricks"]
     if profile:
         cmd.extend(["--profile", profile])
+
     if target:
         cmd.extend(["--target", target])
-    cmd.extend(command)
-    if config:
-        config_path = Path(config)
 
-        if not config_path.exists():
-            logger.error(f"Configuration file {config_path} does not exist.")
-            sys.exit(1)
-
-        app_config: AppConfig = AppConfig.from_file(config_path)
+    cmd.extend(command)
 
-        # Always convert to path relative to notebooks directory
-        # Get absolute path of config file and current working directory
+    # Add config_path variable for notebooks
+    if config_path and app_config:
+        # Calculate relative path from notebooks directory to config file
         config_abs = config_path.resolve()
         cwd = Path.cwd()
         notebooks_dir = cwd / "notebooks"
 
-        # Calculate relative path from notebooks directory to config file
         try:
             relative_config = config_abs.relative_to(notebooks_dir)
         except ValueError:
-            # Config file is outside notebooks directory, calculate relative path
-            # Use os.path.relpath to get the relative path from notebooks_dir to config file
             relative_config = Path(os.path.relpath(config_abs, notebooks_dir))
 
         cmd.append(f'--var="config_path={relative_config}"')
 
-        normalized_name: str = normalize_name(app_config.app.name)
-        cmd.append(f'--var="app_name={normalized_name}"')
-
     logger.debug(f"Executing command: {' '.join(cmd)}")
 
     if dry_run:
+        logger.info(f"[DRY RUN] Would execute: {' '.join(cmd)}")
         return
 
     try:
@@ -531,6 +585,9 @@ def run_databricks_command(
     except FileNotFoundError:
         logger.error("databricks CLI not found. Please install the Databricks CLI.")
         sys.exit(1)
+    except Exception as e:
+        logger.error(f"Command execution failed: {e}")
+        sys.exit(1)
 
 
 def handle_bundle_command(options: Namespace) -> None:
@@ -539,6 +596,7 @@ def handle_bundle_command(options: Namespace) -> None:
     config: Optional[str] = options.config
     target: Optional[str] = options.target
     dry_run: bool = options.dry_run
+
     if options.deploy:
         logger.info("Deploying DAO AI asset bundle...")
         run_databricks_command(
@@ -546,8 +604,9 @@ def handle_bundle_command(options: Namespace) -> None:
         )
     if options.run:
         logger.info("Running DAO AI system with current configuration...")
+        # Use static job resource key that matches databricks.yaml (resources.jobs.deploy_job)
         run_databricks_command(
-            ["bundle", "run", "deploy-end-to-end"],
+            ["bundle", "run", "deploy_job"],
             profile,
             config,
             target,

{dao_ai-0.0.24 → dao_ai-0.0.25}/src/dao_ai/config.py

@@ -1301,7 +1301,7 @@ class ChatPayload(BaseModel):
     model_config = ConfigDict(use_enum_values=True, extra="forbid")
     input: Optional[list[Message]] = None
     messages: Optional[list[Message]] = None
-    custom_inputs: dict
+    custom_inputs: Optional[dict] = Field(default_factory=dict)
 
     @model_validator(mode="after")
     def validate_mutual_exclusion_and_alias(self) -> "ChatPayload":

{dao_ai-0.0.24 → dao_ai-0.0.25}/tests/dao_ai/test_databricks.py

@@ -354,6 +354,7 @@ def test_database_model_capacity_validation():
 
 
 @pytest.mark.unit
+@pytest.mark.skipif(not has_databricks_env(), reason="Databricks env vars not set")
 def test_create_lakebase_new_database():
     """Test create_lakebase when database doesn't exist."""
     # Mock workspace client
@@ -393,6 +394,7 @@ def test_create_lakebase_new_database():
 
 
 @pytest.mark.unit
+@pytest.mark.skipif(not has_databricks_env(), reason="Databricks env vars not set")
 def test_create_lakebase_database_already_exists_available():
     """Test create_lakebase when database already exists and is AVAILABLE."""
     # Mock workspace client
@@ -430,6 +432,7 @@ def test_create_lakebase_database_already_exists_available():
 
 
 @pytest.mark.unit
+@pytest.mark.skipif(not has_databricks_env(), reason="Databricks env vars not set")
 def test_create_lakebase_database_starting_state():
     """Test create_lakebase when database is in STARTING state."""
     # Mock workspace client
@@ -475,6 +478,7 @@ def test_create_lakebase_database_starting_state():
 
 
 @pytest.mark.unit
+@pytest.mark.skipif(not has_databricks_env(), reason="Databricks env vars not set")
 def test_create_lakebase_database_updating_state():
     """Test create_lakebase when database is in UPDATING state."""
     # Mock workspace client
@@ -520,6 +524,7 @@ def test_create_lakebase_database_updating_state():
 
 
 @pytest.mark.unit
+@pytest.mark.skipif(not has_databricks_env(), reason="Databricks env vars not set")
 def test_create_lakebase_database_stopped_state():
     """Test create_lakebase when database is in STOPPED state."""
     # Mock workspace client
@@ -555,6 +560,7 @@ def test_create_lakebase_database_stopped_state():
 
 
 @pytest.mark.unit
+@pytest.mark.skipif(not has_databricks_env(), reason="Databricks env vars not set")
 def test_create_lakebase_database_deleting_state():
     """Test create_lakebase when database is in DELETING state."""
     # Mock workspace client
@@ -590,6 +596,7 @@ def test_create_lakebase_database_deleting_state():
 
 
 @pytest.mark.unit
+@pytest.mark.skipif(not has_databricks_env(), reason="Databricks env vars not set")
 def test_create_lakebase_concurrent_creation():
     """Test create_lakebase when database is created concurrently by another process."""
     # Mock workspace client
@@ -626,6 +633,7 @@ def test_create_lakebase_concurrent_creation():
 
 
 @pytest.mark.unit
+@pytest.mark.skipif(not has_databricks_env(), reason="Databricks env vars not set")
 def test_create_lakebase_unexpected_error():
     """Test create_lakebase handles unexpected errors appropriately."""
     # Mock workspace client
@@ -659,6 +667,7 @@ def test_create_lakebase_unexpected_error():
 
 
 @pytest.mark.unit
+@pytest.mark.skipif(not has_databricks_env(), reason="Databricks env vars not set")
 def test_create_lakebase_timeout_waiting_for_available():
     """Test create_lakebase handles timeout when waiting for AVAILABLE state."""
     # Mock workspace client
@@ -696,6 +705,7 @@ def test_create_lakebase_timeout_waiting_for_available():
 
 
 @pytest.mark.unit
+@pytest.mark.skipif(not has_databricks_env(), reason="Databricks env vars not set")
 def test_create_lakebase_default_values():
     """Test create_lakebase uses correct default values."""
     # Mock workspace client
@@ -729,6 +739,7 @@ def test_create_lakebase_default_values():
 
 
 @pytest.mark.unit
+@pytest.mark.skipif(not has_databricks_env(), reason="Databricks env vars not set")
 def test_create_lakebase_custom_capacity_cu1():
     """Test create_lakebase with custom capacity CU_1."""
     # Mock workspace client
@@ -763,6 +774,7 @@ def test_create_lakebase_custom_capacity_cu1():
 
 
 @pytest.mark.unit
+@pytest.mark.skipif(not has_databricks_env(), reason="Databricks env vars not set")
 def test_create_lakebase_database_disappears_during_wait():
     """Test create_lakebase when database disappears while waiting for AVAILABLE state."""
     # Mock workspace client
@@ -806,6 +818,7 @@ def test_create_lakebase_database_disappears_during_wait():
 
 
 @pytest.mark.unit
+@pytest.mark.skipif(not has_databricks_env(), reason="Databricks env vars not set")
 def test_create_lakebase_instance_role_success():
     """Test creating a lakebase instance role successfully."""
     # Mock workspace client
@@ -847,6 +860,7 @@ def test_create_lakebase_instance_role_success():
 
 
 @pytest.mark.unit
+@pytest.mark.skipif(not has_databricks_env(), reason="Databricks env vars not set")
 def test_create_lakebase_instance_role_already_exists():
     """Test when instance role already exists."""
     # Mock workspace client
@@ -881,6 +895,7 @@ def test_create_lakebase_instance_role_already_exists():
 
 
 @pytest.mark.unit
+@pytest.mark.skipif(not has_databricks_env(), reason="Databricks env vars not set")
 def test_create_lakebase_instance_role_missing_client_id():
     """Test that a warning is logged and method returns early when client_id is not provided."""
     # Mock workspace client
@@ -907,6 +922,7 @@ def test_create_lakebase_instance_role_missing_client_id():
 
 
 @pytest.mark.unit
+@pytest.mark.skipif(not has_databricks_env(), reason="Databricks env vars not set")
 def test_create_lakebase_instance_role_concurrent_creation():
     """Test when role is created concurrently by another process."""
     # Mock workspace client
@@ -940,6 +956,7 @@ def test_create_lakebase_instance_role_concurrent_creation():
 
 
 @pytest.mark.unit
+@pytest.mark.skipif(not has_databricks_env(), reason="Databricks env vars not set")
 def test_create_lakebase_instance_role_unexpected_error():
     """Test that unexpected errors are raised."""
     # Mock workspace client
@@ -970,6 +987,7 @@ def test_create_lakebase_instance_role_unexpected_error():
 
 
 @pytest.mark.unit
+@pytest.mark.skipif(not has_databricks_env(), reason="Databricks env vars not set")
 def test_create_lakebase_instance_role_with_composite_variable():
     """Test creating role when client_id is a CompositeVariableModel."""
     from dao_ai.config import CompositeVariableModel, EnvironmentVariableModel

{dao_ai-0.0.24 → dao_ai-0.0.25}/tests/dao_ai/test_genie_databricks_integration.py

@@ -22,6 +22,7 @@ The fix involved:
 from unittest.mock import Mock, patch
 
 import pytest
+from conftest import has_databricks_env
 from langchain_core.tools import StructuredTool
 
 from dao_ai.config import GenieRoomModel
@@ -208,6 +209,7 @@ class TestGenieDatabricksIntegration:
         assert hasattr(tool, "func")
         assert tool.func is not None
 
+    @pytest.mark.skipif(not has_databricks_env(), reason="Databricks env vars not set")
     def test_conversation_persistence_with_injected_state(self, mock_genie_tool):
         """
         Test that conversation persistence works correctly with injected state pattern.

{dao_ai-0.0.24 → dao_ai-0.0.25}/tests/dao_ai/test_inference_integration.py

@@ -5,7 +5,7 @@ import sys
 from pathlib import Path
 
 import pytest
-from conftest import has_postgres_env
+from conftest import has_databricks_env, has_postgres_env
 from mlflow.types.responses import ResponsesAgentRequest
 from mlflow.types.responses_helpers import Message
 
@@ -43,6 +43,7 @@ def app_config_postgres(supervisor_postgres_config_path: Path) -> AppConfig:
 
 
 @pytest.mark.integration
+@pytest.mark.skipif(not has_databricks_env(), reason="Databricks env vars not set")
 def test_load_config_and_create_responses_agent(
     app_config_supervisor: AppConfig,
 ) -> None:
@@ -373,6 +374,7 @@ def test_inference_with_postgres_memory(app_config_postgres: AppConfig) -> None:
 
 
 @pytest.mark.unit
+@pytest.mark.skipif(not has_databricks_env(), reason="Databricks env vars not set")
 def test_config_has_required_components_for_inference() -> None:
     """Unit test to verify config has required components for inference without actual inference."""
     config_path = (

{dao_ai-0.0.24 → dao_ai-0.0.25}/tests/dao_ai/test_postgres_integration.py

@@ -202,6 +202,7 @@ def test_postgres_memory_initialization(postgres_app_config: AppConfig) -> None:
 
 
 @pytest.mark.unit
+@pytest.mark.skipif(not has_postgres_env(), reason="PostgreSQL env vars not set")
 def test_load_postgres_config_without_env() -> None:
     """Test that PostgreSQL config loads without requiring environment variables."""
     config_path = (