apunkt/dograh
1
0
Fork 0
mirror of https://github.com/dograh-hq/dograh.git synced 2026-06-07 07:55:16 +02:00
Code Issues Projects Releases Packages Wiki Activity

feat: add Tuner Integration to Dograh (#311)

Browse source 
* Add tuner integration

* bump pipecat version

* chore: update pipecat submodule to match upstream and use tuner-pipecat-sdk 0.2.0

Update pipecat submodule from 0.0.109.dev23 to 13e98d0d9 (the exact commit
upstream dograh-hq/dograh uses after v1.30.1). This installs pipecat-ai as
1.1.0.post277 via setuptools_scm, satisfying tuner-pipecat-sdk 0.2.0's
pipecat-ai>=1.0.0 requirement.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* wire tuner

* feat: refactor integrations into self contained packages

* chore: simplify ensure_public_access_token

* fix: remove NodeSpec and make DTOs the source of truth

* feat: send relevant signal to mcp using to_mcp_dict

* fix: fix tests

* cleanup: remove nango integrations

* feat: add agents.md for integrations

---------

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: Abhishek Kumar <abhishek@a6k.me>
This commit is contained in:
Mohamed-Mamdouh 2026-05-20 10:07:33 +01:00 • committed by GitHub
parent afa78fe859
commit 5f28c1b2a9
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
93 changed files with 3388 additions and 3414 deletions
Download patch file Download diff file Expand all files Collapse all files

2
api/constants.py
View file

@ -142,3 +142,5 @@ FORCE_TURN_RELAY = os.getenv("FORCE_TURN_RELAY", "false").lower() == "true"
# OSS Email/Password Auth
OSS_JWT_SECRET = os.getenv("OSS_JWT_SECRET", "change-me-in-production")
OSS_JWT_EXPIRY_HOURS = int(os.getenv("OSS_JWT_EXPIRY_HOURS", "720")) # 30 days
TUNER_BASE_URL = os.getenv("TUNER_BASE_URL", "https://api.usetuner.ai")

8
api/db/models.py
View file

@ -292,7 +292,9 @@ class IntegrationModel(Base):
__tablename__ = "integrations"
id = Column(Integer, primary_key=True, index=True)
integration_id = Column(String, nullable=False, index=True) # Nango Connection ID
integration_id = Column(
String, nullable=False, index=True
) # External connection ID
organization_id = Column(Integer, ForeignKey("organizations.id"), nullable=False)
provider = Column(String, nullable=False)
created_by = Column(Integer, ForeignKey("users.id"))
@ -555,8 +557,8 @@ class CampaignModel(Base):
)
# Source configuration
source_type = Column(String, nullable=False, default="google-sheet")
source_id = Column(String, nullable=False) # Sheet URL
source_type = Column(String, nullable=False, default="csv")
source_id = Column(String, nullable=False) # CSV file key
# State management
state = Column(

14
api/mcp_server/tools/node_types.py
View file

@ -40,15 +40,17 @@ async def list_node_types() -> dict:
@traced_tool
async def get_node_type(name: str) -> dict:
"""Fetch the full schema for a node type, including every property's
type, default, conditional visibility rules, and LLM-readable
description, plus worked examples.
"""Fetch the authoring schema for a node type: each property's name,
type, default, requiredness, enum options, validation bounds, and
LLM-readable description, plus worked examples and graph constraints.
Use the property `description` and the `examples` list to understand
semantics — types alone are not enough.
UI-only metadata (display labels, placeholders, conditional visibility
rules, renderer hints) is intentionally omitted — set only the fields
you need. Use the property `description`/`llm_hint` and the `examples`
list to understand semantics; types alone are not enough.
"""
await authenticate_mcp_request()
spec = get_spec(name)
if spec is None:
raise HTTPException(status_code=404, detail=f"Unknown node type: {name!r}")
return spec.model_dump(mode="json")
return spec.to_mcp_dict()

1
api/requirements.txt
View file

@ -18,4 +18,5 @@ bcrypt==5.0.0
email-validator==2.3.0
posthog==7.11.1
fastmcp==3.2.4
tuner-pipecat-sdk==0.2.0
PyNaCl==1.6.2

6
api/routes/campaign.py
View file

@ -152,8 +152,8 @@ class CircuitBreakerConfigResponse(BaseModel):
class CreateCampaignRequest(BaseModel):
name: str = Field(..., min_length=1, max_length=255)
workflow_id: int
source_type: str = Field(..., pattern="^(google-sheet|csv)$")
source_id: str # Google Sheet URL or CSV file key
source_type: str = Field(..., pattern="^csv$")
source_id: str # CSV file key
# Optional during the legacy → multi-config migration window. Required in
# a follow-up. When omitted, the dispatcher falls back to the org's
# default config.
@ -929,8 +929,6 @@ async def get_campaign_source_download_url(
user: UserModel = Depends(get_user),
) -> CampaignSourceDownloadResponse:
"""Get presigned download URL for campaign CSV source file
Only works for CSV source type. For Google Sheets, use the source_id directly.
Validates that the campaign belongs to the user's organization for security.
"""
# Verify campaign exists and belongs to organization

266
api/routes/integration.py
View file

@ -1,266 +0,0 @@
"""
Route for 3rd party integrations. Currently being backed by nango.
"""
from dataclasses import dataclass
from typing import Any, Dict, List, Optional, TypedDict
from fastapi import APIRouter, Depends, HTTPException, Request
from loguru import logger
from pydantic import BaseModel
from api.db import db_client
from api.db.models import UserModel
from api.services.auth.depends import get_user
from api.services.integrations.nango import nango_service
router = APIRouter(prefix="/integration")
@dataclass
class IntegrationResponse:
id: int
integration_id: str
organization_id: int
created_by: Optional[int]
provider: str
is_active: bool
created_at: str
action: str
provider_data: dict
class SessionResponse(TypedDict):
session_token: str
expires_at: str
class WebhookResponse(TypedDict):
status: str
message: str
class UpdateIntegrationRequest(BaseModel):
selected_files: List[Dict[str, Any]]
class AccessTokenResponse(BaseModel):
access_token: Optional[str]
refresh_token: Optional[str]
expires_at: Optional[str]
connection_id: str
def build_integration_response(integration) -> IntegrationResponse:
"""Build a standardized integration response with provider-specific data."""
provider_data = {}
if integration.provider == "google-sheet":
# For Google Sheets, include selected_files
provider_data["selected_files"] = integration.connection_details.get(
"selected_files", []
)
elif integration.provider == "slack":
# For Slack, include channel information
channel = integration.connection_details.get("connection_config", {}).get(
"incoming_webhook.channel"
)
if channel:
provider_data["channel"] = channel
return IntegrationResponse(
id=integration.id,
integration_id=integration.integration_id,
organization_id=integration.organization_id,
created_by=integration.created_by,
provider=integration.provider,
is_active=integration.is_active,
created_at=integration.created_at.isoformat(),
action=integration.action,
provider_data=provider_data,
)
@router.get("/")
async def get_integrations(
user: UserModel = Depends(get_user),
) -> list[IntegrationResponse]:
"""
Get all integrations for the user's selected organization.
Returns:
List of integrations associated with the user's selected organization
"""
if not user.selected_organization_id:
raise HTTPException(
status_code=400, detail="No organization selected for the user"
)
integrations = await db_client.get_integrations_by_organization_id(
user.selected_organization_id
)
return [build_integration_response(integration) for integration in integrations]
@router.post("/session")
async def create_session(
user: UserModel = Depends(get_user),
) -> SessionResponse:
"""
Create a Nango session for the user's selected organization.
Returns:
Session token and ID for the created session
"""
if not user.selected_organization_id:
raise HTTPException(
status_code=400, detail="No organization selected for the user"
)
try:
session_data = await nango_service.create_session(
user_id=str(user.id), organization_id=user.selected_organization_id
)
return {
"session_token": session_data["data"]["token"],
"expires_at": session_data["data"]["expires_at"],
}
except ValueError as e:
raise HTTPException(status_code=500, detail=str(e))
except Exception as e:
raise HTTPException(
status_code=500, detail=f"Failed to create session: {str(e)}"
)
@router.put("/{integration_id}")
async def update_integration(
integration_id: int,
request: UpdateIntegrationRequest,
user: UserModel = Depends(get_user),
) -> IntegrationResponse:
"""
Update an integration's selected files (for Google Sheets).
Args:
integration_id: The ID of the integration to update
request: The update request containing selected files
user: The authenticated user
Returns:
Updated integration details
"""
if not user.selected_organization_id:
raise HTTPException(
status_code=400, detail="No organization selected for the user"
)
# Get the integration first to verify ownership
integrations = await db_client.get_integrations_by_organization_id(
user.selected_organization_id
)
integration = next((i for i in integrations if i.id == integration_id), None)
if not integration:
raise HTTPException(status_code=404, detail="Integration not found")
# Only allow updating selected_files for google-sheet provider
if integration.provider != "google-sheet":
raise HTTPException(
status_code=400,
detail="This endpoint only supports updating Google Sheet integrations",
)
# Update the connection_details with the new selected_files
updated_connection_details = integration.connection_details.copy()
updated_connection_details["selected_files"] = request.selected_files
# Update the integration
updated_integration = await db_client.update_integration_connection_details(
integration_id=integration_id, connection_details=updated_connection_details
)
if not updated_integration:
raise HTTPException(status_code=500, detail="Failed to update integration")
return build_integration_response(updated_integration)
@router.get("/{integration_id}/access-token")
async def get_integration_access_token(
integration_id: int,
user: UserModel = Depends(get_user),
) -> AccessTokenResponse:
"""
Get the latest access token for an integration from Nango.
Args:
integration_id: The ID of the integration
user: The authenticated user
Returns:
Dict containing access token and expiration info
"""
if not user.selected_organization_id:
raise HTTPException(
status_code=400, detail="No organization selected for the user"
)
# Get the integration to verify ownership and get connection details
integrations = await db_client.get_integrations_by_organization_id(
user.selected_organization_id
)
integration = next((i for i in integrations if i.id == integration_id), None)
if not integration:
raise HTTPException(status_code=404, detail="Integration not found")
try:
# Fetch the latest access token from Nango
token_data = await nango_service.get_access_token(
connection_id=integration.integration_id,
provider_config_key=integration.provider,
)
# Extract relevant fields
return AccessTokenResponse(
access_token=token_data.get("credentials", {}).get("access_token"),
refresh_token=token_data.get("credentials", {}).get("refresh_token"),
expires_at=token_data.get("credentials", {}).get("expires_at"),
connection_id=integration.integration_id,
)
except Exception as e:
logger.error(f"Failed to get access token: {str(e)}")
raise HTTPException(
status_code=500, detail=f"Failed to fetch access token: {str(e)}"
)
@router.post("/webhook", include_in_schema=False)
async def handle_nango_webhook(
request: Request,
) -> WebhookResponse:
"""
Handle Nango integration webhook requests.
Processes webhook events from Nango when integrations are created/updated
and stores the integration details in the database.
Args:
request: The raw FastAPI request object
Returns:
WebhookResponse with status and message
"""
raw_body = await request.body()
# Get signature from headers (you may need to adjust the header name)
signature = request.headers.get("X-Nango-Signature")
# Use the nango service to process the webhook
result = await nango_service.process_webhook(raw_body, signature)
return result

6
api/routes/main.py
View file

@ -6,7 +6,6 @@ from api.routes.agent_stream import router as agent_stream_router
from api.routes.auth import router as auth_router
from api.routes.campaign import router as campaign_router
from api.routes.credentials import router as credentials_router
from api.routes.integration import router as integration_router
from api.routes.knowledge_base import router as knowledge_base_router
from api.routes.node_types import router as node_types_router
from api.routes.organization import router as organization_router
@ -26,6 +25,7 @@ from api.routes.webrtc_signaling import router as webrtc_signaling_router
from api.routes.workflow import router as workflow_router
from api.routes.workflow_embed import router as workflow_embed_router
from api.routes.workflow_recording import router as workflow_recording_router
from api.services.integrations import all_routers
router = APIRouter(
tags=["main"],
@ -39,7 +39,6 @@ router.include_router(user_router)
router.include_router(campaign_router)
router.include_router(credentials_router)
router.include_router(tool_router)
router.include_router(integration_router)
router.include_router(organization_router)
router.include_router(s3_router)
router.include_router(service_keys_router)
@ -57,6 +56,9 @@ router.include_router(auth_router)
router.include_router(node_types_router)
router.include_router(agent_stream_router)
for _integration_router in all_routers():
router.include_router(_integration_router)
class HealthResponse(BaseModel):
status: str

5
api/routes/public_download.py
View file

@ -1,8 +1,9 @@
"""Public download endpoints for workflow recordings and transcripts.
These endpoints provide secure, token-based public access to workflow artifacts
without requiring authentication. Tokens are generated on-demand when webhooks
are executed and included in the webhook payload.
without requiring authentication. Tokens are generated on-demand during
post-call processing for runs that execute integrations, QA, or campaign
reporting.
"""
from typing import Literal

4
api/services/campaign/source_sync.py
View file

@ -183,9 +183,7 @@ class CampaignSourceSyncService(ABC):
async def get_source_credentials(
self, organization_id: int, source_type: str
) -> Dict[str, Any]:
"""Gets OAuth tokens or API credentials via Nango"""
# This would be implemented to work with Nango service
# For now, returning placeholder
"""Gets source credentials when a sync service requires them."""
logger.info(
f"Getting credentials for org {organization_id}, source {source_type}"
)

3
api/services/campaign/source_sync_factory.py
View file

@ -1,15 +1,12 @@
from api.services.campaign.source_sync import CampaignSourceSyncService
from api.services.campaign.sources.csv import CSVSyncService
from api.services.campaign.sources.google_sheets import GoogleSheetsSyncService
def get_sync_service(source_type: str) -> CampaignSourceSyncService:
"""Returns appropriate sync service based on source type"""
services = {
"google-sheet": GoogleSheetsSyncService,
"csv": CSVSyncService,
# Add more as needed: "hubspot": HubSpotSyncService,
}
service_class = services.get(source_type)

4
api/services/campaign/sources/__init__.py
View file

@ -1,5 +1,3 @@
"""Campaign source sync services"""
from .google_sheets import GoogleSheetsSyncService
__all__ = ["GoogleSheetsSyncService"]
__all__: list[str] = []

224
api/services/campaign/sources/google_sheets.py
View file

@ -1,224 +0,0 @@
import re
from typing import Any, Dict, List, Optional
import httpx
from loguru import logger
from api.db import db_client
from api.services.campaign.source_sync import (
CampaignSourceSyncService,
ValidationError,
ValidationResult,
)
from api.services.integrations.nango import NangoService
class GoogleSheetsSyncService(CampaignSourceSyncService):
"""Implementation for Google Sheets synchronization"""
def __init__(self):
self.nango_service = NangoService()
self.sheets_api_base = "https://sheets.googleapis.com/v4/spreadsheets"
async def _get_access_token(self, organization_id: int) -> str:
"""Get OAuth access token for Google Sheets via Nango."""
integrations = await db_client.get_integrations_by_organization_id(
organization_id
)
integration = None
for intg in integrations:
if intg.provider == "google-sheet" and intg.is_active:
integration = intg
break
if not integration:
raise ValueError("Google Sheets integration not found or inactive")
token_data = await self.nango_service.get_access_token(
connection_id=integration.integration_id, provider_config_key="google-sheet"
)
return token_data["credentials"]["access_token"]
async def _fetch_all_sheet_data(
self, sheet_url: str, organization_id: int
) -> List[List[str]]:
"""Fetch all data from a Google Sheet. Returns all rows including header."""
access_token = await self._get_access_token(organization_id)
sheet_id = self._extract_sheet_id(sheet_url)
metadata = await self._get_sheet_metadata(sheet_id, access_token)
if not metadata.get("sheets"):
raise ValueError("No sheets found in the spreadsheet")
sheet_name = metadata["sheets"][0]["properties"]["title"]
return await self._fetch_sheet_data(sheet_id, f"{sheet_name}!A:Z", access_token)
async def validate_source(
self, source_id: str, organization_id: Optional[int] = None
) -> ValidationResult:
"""Validate a Google Sheet source for campaign creation."""
if organization_id is None:
return ValidationResult(
is_valid=False,
error=ValidationError(
message="Organization ID is required for Google Sheets validation"
),
)
# Validate URL format first
pattern = r"/spreadsheets/d/([a-zA-Z0-9-_]+)"
if not re.search(pattern, source_id):
return ValidationResult(
is_valid=False,
error=ValidationError(
message=f"Invalid Google Sheets URL: {source_id}"
),
)
try:
rows = await self._fetch_all_sheet_data(source_id, organization_id)
except ValueError as e:
return ValidationResult(
is_valid=False,
error=ValidationError(message=str(e)),
)
except httpx.HTTPStatusError as e:
logger.error(f"HTTP error fetching Google Sheet: {e.response.status_code}")
return ValidationResult(
is_valid=False,
error=ValidationError(
message=f"Failed to fetch Google Sheet data: {e.response.status_code}"
),
)
except Exception as e:
logger.error(f"Error fetching Google Sheet: {e}")
return ValidationResult(
is_valid=False,
error=ValidationError(message="Failed to fetch Google Sheet data"),
)
if not rows or len(rows) < 2:
return ValidationResult(
is_valid=False,
error=ValidationError(
message="Google Sheet must have a header row and at least one data row"
),
)
headers = rows[0]
data_rows = rows[1:]
return self.validate_source_data(headers, data_rows)
async def sync_source_data(self, campaign_id: int) -> int:
"""
Fetches data from Google Sheets and creates queued_runs
"""
# Get campaign
campaign = await db_client.get_campaign_by_id(campaign_id)
if not campaign:
raise ValueError(f"Campaign {campaign_id} not found")
rows = await self._fetch_all_sheet_data(
campaign.source_id, campaign.organization_id
)
if not rows or len(rows) < 2:
logger.warning(f"No data found in sheet for campaign {campaign_id}")
return 0
headers = self.normalize_headers(rows[0])
data_rows = rows[1:]
sheet_id = self._extract_sheet_id(campaign.source_id)
queued_runs = []
for idx, row_values in enumerate(data_rows, 1):
# Pad row to match headers length
padded_row = row_values + [""] * (len(headers) - len(row_values))
# Create context variables dict
context_vars = dict(zip(headers, padded_row))
# Skip if no phone number
if not context_vars.get("phone_number"):
logger.debug(f"Skipping row {idx}: no phone_number")
continue
# Generate unique source UUID
source_uuid = f"sheet_{sheet_id}_row_{idx}"
queued_runs.append(
{
"campaign_id": campaign_id,
"source_uuid": source_uuid,
"context_variables": context_vars,
"state": "queued",
}
)
# Bulk insert
if queued_runs:
await db_client.bulk_create_queued_runs(queued_runs)
logger.info(
f"Created {len(queued_runs)} queued runs for campaign {campaign_id}"
)
# Update campaign total_rows
await db_client.update_campaign(
campaign_id=campaign_id,
total_rows=len(queued_runs),
source_sync_status="completed",
)
return len(queued_runs)
async def _fetch_sheet_data(
self, sheet_id: str, range: str, access_token: str
) -> List[List[str]]:
"""Fetch data from Google Sheets API"""
url = f"{self.sheets_api_base}/{sheet_id}/values/{range}"
headers = {"Authorization": f"Bearer {access_token}"}
async with httpx.AsyncClient() as client:
response = await client.get(url, headers=headers)
response.raise_for_status()
data = response.json()
return data.get("values", [])
async def _get_sheet_metadata(
self, sheet_id: str, access_token: str
) -> Dict[str, Any]:
"""Get sheet metadata including sheet names"""
url = f"{self.sheets_api_base}/{sheet_id}"
headers = {"Authorization": f"Bearer {access_token}"}
logger.debug(f"Fetching sheet metadata from URL: {url}")
logger.debug(f"Using sheet_id: {sheet_id}")
async with httpx.AsyncClient() as client:
try:
response = await client.get(url, headers=headers)
response.raise_for_status()
return response.json()
except httpx.HTTPStatusError as e:
logger.error(f"HTTP error {e.response.status_code} for URL: {url}")
logger.error(f"Response body: {e.response.text}")
raise
except Exception as e:
logger.error(f"Error fetching sheet metadata: {e}")
raise
def _extract_sheet_id(self, sheet_url: str) -> str:
"""
Extract sheet ID from various Google Sheets URL formats:
- https://docs.google.com/spreadsheets/d/{id}/edit
- https://docs.google.com/spreadsheets/d/{id}/edit#gid=0
"""
pattern = r"/spreadsheets/d/([a-zA-Z0-9-_]+)"
match = re.search(pattern, sheet_url)
if match:
return match.group(1)
raise ValueError(f"Invalid Google Sheets URL: {sheet_url}")

58
api/services/configuration/masking.py
View file

@ -13,6 +13,7 @@ from typing import Any, Dict, Optional
from api.schemas.user_configuration import UserConfiguration
from api.services.configuration.registry import ServiceConfig
from api.services.integrations import get_node_secret_fields
VISIBLE_CHARS = 4 # number of trailing characters to reveal
MASK_CHAR = "*"
@ -129,14 +130,22 @@ def mask_user_config(config: UserConfiguration) -> Dict[str, Any]:
# ---------------------------------------------------------------------------
# Workflow definition helpers – mask / merge QA-node API keys
# Workflow definition helpers – mask / merge node API keys
# ---------------------------------------------------------------------------
_QA_API_KEY_FIELD = "qa_api_key"
_NODE_SECRET_FIELDS: dict[str, tuple[str, ...]] = {
"qa": ("qa_api_key",),
}
def _secret_fields_for_node_type(node_type: str | None) -> tuple[str, ...]:
if not node_type:
return ()
return _NODE_SECRET_FIELDS.get(node_type, ()) or get_node_secret_fields(node_type)
def mask_workflow_definition(workflow_definition: Optional[Dict]) -> Optional[Dict]:
"""Return a *shallow copy* of *workflow_definition* with QA-node API keys masked."""
"""Return a copy of *workflow_definition* with node secret fields masked."""
if not workflow_definition:
return workflow_definition
@ -144,47 +153,46 @@ def mask_workflow_definition(workflow_definition: Optional[Dict]) -> Optional[Di
masked = copy.deepcopy(workflow_definition)
for node in masked.get("nodes", []):
if node.get("type") != "qa":
secret_fields = _secret_fields_for_node_type(node.get("type"))
if not secret_fields:
continue
data = node.get("data", {})
raw_key = data.get(_QA_API_KEY_FIELD)
if raw_key:
data[_QA_API_KEY_FIELD] = mask_key(raw_key)
for field in secret_fields:
raw_key = data.get(field)
if raw_key:
data[field] = mask_key(raw_key)
return masked
def merge_workflow_api_keys(
incoming_definition: Optional[Dict], existing_definition: Optional[Dict]
) -> Optional[Dict]:
"""Preserve real QA-node API keys when the incoming value is a masked placeholder.
For each QA node in *incoming_definition*, if its ``qa_api_key`` equals
the masked form of the corresponding node in *existing_definition*, the
real key is restored so it is never lost.
"""
"""Preserve real node secret fields when the incoming value is masked."""
if not incoming_definition or not existing_definition:
return incoming_definition
# Build lookup: node-id → data for existing QA nodes
existing_qa: Dict[str, Dict] = {}
existing_nodes: Dict[str, Dict] = {}
for node in existing_definition.get("nodes", []):
if node.get("type") == "qa":
existing_qa[node["id"]] = node.get("data", {})
if _secret_fields_for_node_type(node.get("type")):
existing_nodes[node["id"]] = node.get("data", {})
for node in incoming_definition.get("nodes", []):
if node.get("type") != "qa":
secret_fields = _secret_fields_for_node_type(node.get("type"))
if not secret_fields:
continue
data = node.get("data", {})
incoming_key = data.get(_QA_API_KEY_FIELD)
if not incoming_key:
continue
old_data = existing_qa.get(node["id"])
old_data = existing_nodes.get(node["id"])
if not old_data:
continue
old_key = old_data.get(_QA_API_KEY_FIELD, "")
if old_key and is_mask_of(incoming_key, old_key):
data[_QA_API_KEY_FIELD] = old_key
for field in secret_fields:
incoming_key = data.get(field)
if not incoming_key:
continue
old_key = old_data.get(field, "")
if old_key and is_mask_of(incoming_key, old_key):
data[field] = old_key
return incoming_definition

239
api/services/integrations/AGENTS.md Normal file
View file

@ -0,0 +1,239 @@
# Integrations - Plugin Contract
`api/services/integrations/` is the extension seam for third-party integrations.
New integrations should be self-contained here. Do not bleed integration-specific
logic into `workflow/dto.py`, `workflow/node_specs/`, `run_pipeline.py`,
`event_handlers.py`, or `run_integrations.py` unless you are changing the generic
framework itself.
## Golden Path
Create a package:
```text
api/services/integrations/<name>/
├── __init__.py
├── node.py
├── runtime.py # optional
├── completion.py # optional
├── routes.py # optional
└── client.py # optional
```
The package self-registers on import via `register_package(...)`. Discovery is
automatic: `api/services/integrations/loader.py` imports every submodule under
`api.services.integrations` except the reserved internal names `base`, `loader`,
and `registry`.
## Registration Pattern
`__init__.py` should register one `IntegrationPackageSpec`, following the
existing integration packages in this directory.
Use:
```python
PACKAGE = register_package(
IntegrationPackageSpec(
name="<package_name>",
nodes=(NODE,),
create_runtime_sessions=create_runtime_sessions, # optional
run_completion=run_completion, # optional
routers=(router,), # optional
)
)
```
The package name is the registry key. The node `type_name` is the workflow node
type string and must stay stable once exposed.
## Node Model + Spec
For integration nodes, the Pydantic model is the source of truth. The serialized
`NodeSpec` is derived from it.
Refer to an existing integration node for the overall structure:
- Define one Pydantic model per node, inheriting
`api/services/workflow/node_data.py:BaseNodeData`.
- Annotate it with `@node_spec(...)`.
- Define fields with `spec_field(...)`.
- Generate the external spec with `SPEC = build_spec(ModelClass)`.
- Register the node with `IntegrationNodeRegistration(...)`.
Important rules:
- Put runtime validation in the model, not in the generated spec.
Example: conditional requiredness belongs in `@model_validator(mode="after")`.
- Keep `@node_spec(name=...)` and `IntegrationNodeRegistration.type_name`
identical. They are the same workflow node type string.
- Put wire constraints in the field itself where possible.
Example: `gt=0`, `min_length=1`, `pattern=...`.
- Put UI/export-only differences in `field_overrides`.
Use this for `display_name`, `description`, `required`, `spec_default`,
`display_options`, or property ordering.
- Use `spec_exclude=True` for internal fields that must exist in persisted data
but must not show up in `/api/v1/node-types`.
- Set `property_order=(...)` in `@node_spec(...)` when the editor field order
must remain stable.
Typical workflow graph constraints for configuration-only integration nodes:
```python
GraphConstraints(min_incoming=0, max_incoming=0, min_outgoing=0, max_outgoing=0)
```
These constraints control how the node can be connected in the workflow graph.
Use them for configuration nodes that are not conversational graph steps.
## Secret Fields
If the node stores secrets, register them in
`IntegrationNodeRegistration.sensitive_fields`.
That is enough for generic masking / masked round-trip preservation via
`api/services/configuration/masking.py`. Do not add new integration-specific
masking branches unless you are changing the shared masking framework.
## No Central DTO Edits
Do not add integration node classes to `api/services/workflow/dto.py`.
Integration nodes are resolved dynamically through:
- `get_node_data_model()` in `workflow/dto.py`
- `get_node_spec()` / `all_node_specs()` in `services/integrations/registry.py`
`RFNodeDTO` validates integration nodes by `type` through the registry. That is
the intended extension path.
## Live Call Path
If the integration needs live call data, implement `create_runtime_sessions(...)`
in `runtime.py` and return `IntegrationRuntimeSession` objects.
The generic wiring is already in `api/services/pipecat/run_pipeline.py`:
- `create_runtime_sessions(IntegrationRuntimeContext(...))` is called before the
pipeline task starts.
- Each returned session gets `session.attach(task)` called.
Use this only for lightweight live collection:
- attach task observers
- read context messages
- capture timing / turn / tool events
- build an in-memory snapshot
Do not do outbound network I/O in the live path unless there is a very strong
reason. Prefer the standard pattern: collect live, deliver after the call.
`IntegrationRuntimeContext` gives you:
- `workflow_run_id`
- `workflow_run`
- `workflow_graph`
- `run_definition`
- `user_config`
- `is_realtime`
- `context_messages_provider`
Typical runtime pattern:
- scan `context.workflow_graph.nodes.values()` for enabled nodes of your type
- if none are enabled, return `[]`
- build one collector/session per workflow run, not per node, unless the
integration truly needs multiple independent collectors
## Call-Finish Snapshot Path
`api/services/pipecat/event_handlers.py` finalizes runtime sessions before the
engine is cleaned up.
The generic flow:
1. `on_pipeline_finished` builds `gathered_context`
2. each runtime session gets `await session.on_call_finished(...)`
3. returned dicts are merged into `integration_logs`
4. those logs are persisted into `workflow_run.logs`
Use `on_call_finished(...)` to emit a compact, serializable snapshot that the
post-call completion handler can consume later. Return `None` if there is nothing
to persist.
This is the handoff between the live call path and the post-call task path.
## Post-Call Completion Path
If the integration needs durable artifacts, public URLs, retries, or external
delivery, implement `run_completion(nodes, context)` in `completion.py`.
The generic orchestration is already in `api/tasks/run_integrations.py`:
1. load the pinned workflow definition from the workflow run
2. create a public token if post-call work exists
3. run QA nodes first
4. run registered integration completion handlers
5. run webhook nodes last
Your handler receives:
- `nodes`: raw workflow node dicts for your node types only
- `IntegrationCompletionContext`:
- `workflow_run_id`
- `workflow_run`
- `workflow_definition`
- `definition_id`
- `organization_id`
- `public_token`
Expected completion handler pattern:
- validate each node with `YourNodeData.model_validate(node.get("data", {}))`
- skip disabled nodes
- read any runtime snapshot from `context.workflow_run.logs`
- build durable URLs using `public_token` when appropriate
- perform external delivery
- return a result dict keyed per node, usually with `node_id` embedded
Returned data is merged into `workflow_run.annotations`.
Do not assume completion runs inside the live pipeline process. Treat it as a
separate post-call worker step.
## Optional Routes
If an integration exposes HTTP routes, put them in `routes.py` and include the
router in `IntegrationPackageSpec.routers`.
Routers are mounted automatically by `api/routes/main.py` through `all_routers()`.
Do not edit `routes/main.py` for per-integration route wiring.
## Import Discipline
Keep package import side effects light.
The integration loader runs during:
- node-type/spec enumeration
- tests
- route startup
- registry access
So avoid top-level imports that require environment variables, network access,
or heavyweight initialization when possible. Prefer lazy imports inside
`run_completion()` / `create_runtime_sessions()` if the dependency is optional or
environment-sensitive.
## Testing Expectations
At minimum, new integrations should add coverage for:
- node model validation
- generated spec/example validity
- secret masking + masked round-trip preservation if secrets exist
- runtime snapshot creation if live collectors exist
- completion handler happy path and disabled-node skip path
If you change shared integration machinery, test the framework in the generic
code path, not only the concrete integration.

39
api/services/integrations/__init__.py
View file

@ -0,0 +1,39 @@
from api.services.integrations.base import (
IntegrationCompletionContext,
IntegrationNodeRegistration,
IntegrationPackageSpec,
IntegrationRuntimeContext,
IntegrationRuntimeSession,
)
from api.services.integrations.registry import (
all_node_specs,
all_packages,
all_routers,
create_runtime_sessions,
get_node_data_model,
get_node_registration,
get_node_secret_fields,
get_node_spec,
has_completion_handlers,
register_package,
run_completion_handlers,
)
__all__ = [
"IntegrationCompletionContext",
"IntegrationNodeRegistration",
"IntegrationPackageSpec",
"IntegrationRuntimeContext",
"IntegrationRuntimeSession",
"all_node_specs",
"all_packages",
"all_routers",
"create_runtime_sessions",
"get_node_data_model",
"get_node_registration",
"get_node_secret_fields",
"get_node_spec",
"has_completion_handlers",
"register_package",
"run_completion_handlers",
]

69
api/services/integrations/base.py Normal file
View file

@ -0,0 +1,69 @@
from __future__ import annotations
from dataclasses import dataclass
from typing import Any, Awaitable, Callable, Protocol
from fastapi import APIRouter
from api.services.workflow.node_data import BaseNodeData
from api.services.workflow.node_specs._base import NodeSpec
class IntegrationRuntimeSession(Protocol):
name: str
def attach(self, task: Any) -> None: ...
async def on_call_finished(
self,
*,
gathered_context: dict[str, Any],
) -> dict[str, Any] | None: ...
@dataclass(frozen=True)
class IntegrationRuntimeContext:
workflow_run_id: int
workflow_run: Any
workflow_graph: Any
run_definition: Any
user_config: Any
is_realtime: bool
context_messages_provider: Callable[[], list[dict[str, Any]]]
@dataclass(frozen=True)
class IntegrationCompletionContext:
workflow_run_id: int
workflow_run: Any
workflow_definition: dict[str, Any]
definition_id: int | None
organization_id: int
public_token: str | None
RuntimeFactory = Callable[
[IntegrationRuntimeContext],
list[IntegrationRuntimeSession],
]
CompletionHandler = Callable[
[list[dict[str, Any]], IntegrationCompletionContext],
Awaitable[dict[str, Any]],
]
@dataclass(frozen=True)
class IntegrationNodeRegistration:
type_name: str
data_model: type[BaseNodeData]
node_spec: NodeSpec
sensitive_fields: tuple[str, ...] = ()
@dataclass(frozen=True)
class IntegrationPackageSpec:
name: str
nodes: tuple[IntegrationNodeRegistration, ...] = ()
routers: tuple[APIRouter, ...] = ()
create_runtime_sessions: RuntimeFactory | None = None
run_completion: CompletionHandler | None = None

21
api/services/integrations/loader.py Normal file
View file

@ -0,0 +1,21 @@
from __future__ import annotations
import importlib
import pkgutil
_INTERNAL_MODULES = {"base", "loader", "registry"}
_loaded = False
def ensure_integrations_loaded() -> None:
global _loaded
if _loaded:
return
package = importlib.import_module("api.services.integrations")
for module_info in pkgutil.iter_modules(package.__path__):
if module_info.name in _INTERNAL_MODULES:
continue
importlib.import_module(f"{package.__name__}.{module_info.name}")
_loaded = True

253
api/services/integrations/nango.py
View file

@ -1,253 +0,0 @@
import hashlib
import json
import os
from typing import Any, Dict
import httpx
from fastapi import HTTPException
from loguru import logger
from pydantic import BaseModel
from api.db import db_client
NANGO_ALLOWED_INTEGRATIONS = [
i.strip() for i in os.environ.get("NANGO_ALLOWED_INTEGRATIONS", "slack").split(",")
]
class NangoWebhookRequest(BaseModel):
type: str
connectionId: str
providerConfigKey: str
authMode: str
provider: str
environment: str
operation: str
endUser: dict # Contains endUserId and organizationId
success: bool
class NangoService:
def __init__(self):
self.base_url = "https://api.nango.dev"
self.secret_key = os.getenv("NANGO_API_KEY")
def _verify_webhook_signature(
self, request_body: str, signature: str = None
) -> bool:
"""
Verify the webhook signature using SHA256 hash.
Args:
request_body: The raw request body as string
signature: The signature from request headers (optional for now)
Returns:
True if signature is valid
"""
expected_signature = self.secret_key + request_body
expected_hash = hashlib.sha256(expected_signature.encode("utf-8")).hexdigest()
return expected_hash == signature
async def create_session(
self, user_id: str, organization_id: int
) -> Dict[str, Any]:
"""
Create a Nango session for the given user and organization.
Args:
user_id: The end user ID
organization_id: The organization ID
Returns:
Response from Nango API
"""
if not self.secret_key:
raise ValueError("NANGO_SECRET_KEY environment variable is not set")
headers = {
"Authorization": f"Bearer {self.secret_key}",
"Content-Type": "application/json",
}
payload = {
"end_user": {"id": user_id},
"organization": {"id": str(organization_id)},
"allowed_integrations": NANGO_ALLOWED_INTEGRATIONS,
}
async with httpx.AsyncClient() as client:
response = await client.post(
f"{self.base_url}/connect/sessions", headers=headers, json=payload
)
if response.status_code != 201:
raise httpx.HTTPStatusError(
f"Nango API error: {response.status_code}",
request=response.request,
response=response,
)
return response.json()
async def process_webhook(
self, raw_body: bytes, signature: str = None
) -> Dict[str, str]:
"""
Process incoming Nango webhook request.
Args:
raw_body: The raw request body as bytes
signature: Optional signature from request headers
Returns:
Dict with status and message
"""
# Decode and parse the request body
try:
body_text = raw_body.decode("utf-8")
webhook_json = json.loads(body_text) if body_text else {}
logger.debug(f"received webhook from nango: {webhook_json}")
except json.JSONDecodeError as e:
logger.error(f"JSON decode error: {e} body_text: {body_text}")
raise HTTPException(status_code=400, detail=f"Invalid JSON: {str(e)}")
# Verify webhook signature
if not self._verify_webhook_signature(body_text, signature):
raise HTTPException(status_code=401, detail="Invalid webhook signature")
# Parse webhook data
try:
webhook_data = NangoWebhookRequest(**webhook_json)
except Exception as e:
logger.error(f"Failed to parse webhook data: {e}")
raise HTTPException(
status_code=400, detail=f"Invalid webhook format: {str(e)}"
)
# Extract user and organization IDs from the webhook payload
end_user = webhook_data.endUser
if (
not end_user
or "endUserId" not in end_user
or "organizationId" not in end_user
):
raise HTTPException(
status_code=400, detail="Missing endUser information in webhook payload"
)
user_id = int(end_user["endUserId"])
organization_id = int(end_user["organizationId"])
# Use the connectionId as the integration_id since it's unique per integration
integration_id = webhook_data.connectionId
# Initialize connection_details
connection_details = {}
# Fetch connection details if type is auth and provider is slack
if webhook_data.type == "auth":
connection_details = await self._fetch_connection_details(
integration_id, webhook_data.provider
)
# Create the integration in the database
integration = await db_client.create_integration(
integration_id=integration_id,
organization_id=organization_id,
provider=webhook_data.provider,
created_by=user_id,
is_active=True,
connection_details=connection_details,
)
return {
"status": "success",
"message": f"Integration created successfully with ID: {integration.id}",
}
async def _fetch_connection_details(
self, connection_id: str, provider_key: str
) -> Dict[str, Any]:
"""
Fetch connection details from Nango API for a given connection ID.
Args:
connection_id: The connection ID from the webhook
Returns:
Connection details as a dictionary
"""
headers = {
"Authorization": f"Bearer {self.secret_key}",
"Content-Type": "application/json",
}
url = f"{self.base_url}/connection/{connection_id}/?provider_config_key={provider_key}"
async with httpx.AsyncClient() as client:
try:
response = await client.get(url, headers=headers)
if response.status_code != 200:
logger.error(
f"Failed to fetch connection details: {response.status_code} - {response.text}"
)
raise httpx.HTTPStatusError(
f"Nango API error while fetching connection: {response.status_code}",
request=response.request,
response=response,
)
connection_details = response.json()
return connection_details
except httpx.HTTPError as e:
logger.error(f"HTTP error while fetching connection details: {e}")
# Return empty dict if API call fails, but log the error
return {}
async def get_access_token(
self, connection_id: str, provider_config_key: str
) -> Dict[str, Any]:
"""
Get the latest access token for a connection from Nango.
Args:
connection_id: The connection ID
provider_config_key: The provider config key (e.g., 'google-sheet')
Returns:
Dict containing access token and other connection details
"""
headers = {
"Authorization": f"Bearer {self.secret_key}",
"Content-Type": "application/json",
}
url = f"{self.base_url}/connection/{connection_id}?provider_config_key={provider_config_key}"
async with httpx.AsyncClient() as client:
try:
response = await client.get(url, headers=headers)
if response.status_code != 200:
logger.error(
f"Failed to get access token: {response.status_code} - {response.text}"
)
raise httpx.HTTPStatusError(
f"Nango API error: {response.status_code}",
request=response.request,
response=response,
)
return response.json()
except httpx.HTTPError as e:
logger.error(f"HTTP error while getting access token: {e}")
raise
# Create a singleton instance
nango_service = NangoService()

128
api/services/integrations/registry.py Normal file
View file

@ -0,0 +1,128 @@
from __future__ import annotations
from typing import Any
from api.services.integrations.base import (
IntegrationCompletionContext,
IntegrationNodeRegistration,
IntegrationPackageSpec,
IntegrationRuntimeContext,
)
from api.services.workflow.node_data import BaseNodeData
_PACKAGE_REGISTRY: dict[str, IntegrationPackageSpec] = {}
def register_package(spec: IntegrationPackageSpec) -> IntegrationPackageSpec:
existing = _PACKAGE_REGISTRY.get(spec.name)
if existing is not None and existing is not spec:
raise ValueError(
f"Duplicate integration package registration for {spec.name!r}"
)
_PACKAGE_REGISTRY[spec.name] = spec
return spec
def _ensure_loaded() -> None:
from api.services.integrations.loader import ensure_integrations_loaded
ensure_integrations_loaded()
def all_packages() -> list[IntegrationPackageSpec]:
_ensure_loaded()
return [_PACKAGE_REGISTRY[name] for name in sorted(_PACKAGE_REGISTRY)]
def get_package(name: str) -> IntegrationPackageSpec | None:
_ensure_loaded()
return _PACKAGE_REGISTRY.get(name)
def get_node_registration(type_name: str) -> IntegrationNodeRegistration | None:
_ensure_loaded()
for package in _PACKAGE_REGISTRY.values():
for node in package.nodes:
if node.type_name == type_name:
return node
return None
def get_node_data_model(type_name: str) -> type[BaseNodeData] | None:
registration = get_node_registration(type_name)
return registration.data_model if registration else None
def get_node_spec(type_name: str):
registration = get_node_registration(type_name)
return registration.node_spec if registration else None
def get_node_secret_fields(type_name: str) -> tuple[str, ...]:
registration = get_node_registration(type_name)
return registration.sensitive_fields if registration else ()
def all_node_specs():
_ensure_loaded()
specs = []
for package in all_packages():
specs.extend(node.node_spec for node in package.nodes)
return specs
def all_routers():
_ensure_loaded()
routers = []
for package in all_packages():
routers.extend(package.routers)
return routers
def create_runtime_sessions(
context: IntegrationRuntimeContext,
):
_ensure_loaded()
sessions = []
for package in all_packages():
if package.create_runtime_sessions is None:
continue
sessions.extend(package.create_runtime_sessions(context))
return sessions
def iter_completion_packages(
workflow_definition: dict[str, Any],
):
_ensure_loaded()
nodes = workflow_definition.get("nodes", []) if workflow_definition else []
for package in all_packages():
node_types = {node.type_name for node in package.nodes}
package_nodes = [
node
for node in nodes
if isinstance(node, dict) and node.get("type") in node_types
]
if package_nodes:
yield package, package_nodes
def has_completion_handlers(workflow_definition: dict[str, Any]) -> bool:
return any(
package.run_completion is not None
for package, _nodes in iter_completion_packages(workflow_definition)
)
async def run_completion_handlers(
*,
context: IntegrationCompletionContext,
) -> dict[str, Any]:
results: dict[str, Any] = {}
for package, nodes in iter_completion_packages(context.workflow_definition):
if package.run_completion is None:
continue
package_result = await package.run_completion(nodes, context)
if package_result:
results.update(package_result)
return results

19
api/services/integrations/tuner/__init__.py Normal file
View file

@ -0,0 +1,19 @@
from __future__ import annotations
from api.services.integrations.base import IntegrationPackageSpec
from api.services.integrations.registry import register_package
from .completion import run_completion
from .node import NODE
from .runtime import create_runtime_sessions
PACKAGE = register_package(
IntegrationPackageSpec(
name="tuner",
nodes=(NODE,),
create_runtime_sessions=create_runtime_sessions,
run_completion=run_completion,
)
)
__all__ = ["PACKAGE"]

71
api/services/integrations/tuner/client.py Normal file
View file

@ -0,0 +1,71 @@
from __future__ import annotations
from typing import Any
import httpx
from loguru import logger
from pydantic import BaseModel, field_validator
class TunerDeliveryConfig(BaseModel):
base_url: str
api_key: str
workspace_id: int
agent_id: str
@field_validator("api_key", "agent_id")
@classmethod
def _must_not_be_empty(cls, value: str) -> str:
if not value or not value.strip():
raise ValueError("must not be empty")
return value
@field_validator("workspace_id")
@classmethod
def _workspace_must_be_positive(cls, value: int) -> int:
if value <= 0:
raise ValueError("must be a positive integer")
return value
async def post_call(
config: TunerDeliveryConfig,
payload: dict[str, Any],
) -> dict[str, Any]:
url = (
f"{config.base_url}/api/v1/public/call"
f"?workspace_id={config.workspace_id}"
f"&agent_remote_identifier={config.agent_id}"
)
headers = {"Authorization": f"Bearer {config.api_key}"}
logger.info(
"[tuner] posting completed call {} to workspace {} / agent {}",
payload.get("call_id"),
config.workspace_id,
config.agent_id,
)
async with httpx.AsyncClient(timeout=10) as client:
response = await client.post(url, json=payload, headers=headers)
if response.status_code == 409:
logger.info("[tuner] call {} already exists in tuner", payload.get("call_id"))
return {"status": "duplicate", "status_code": response.status_code}
if response.status_code >= 400:
logger.error(
"[tuner] POST failed for call {} with status {}: {}",
payload.get("call_id"),
response.status_code,
response.text[:200],
)
response.raise_for_status()
logger.info(
"[tuner] POST succeeded for call {} with status {}",
payload.get("call_id"),
response.status_code,
)
return {"status": "delivered", "status_code": response.status_code}

182
api/services/integrations/tuner/collector.py Normal file
View file

@ -0,0 +1,182 @@
from __future__ import annotations
import time
from collections import deque
from dataclasses import dataclass
from typing import Any, Callable
from loguru import logger
from pipecat.frames.frames import (
BotStartedSpeakingFrame,
BotStoppedSpeakingFrame,
CancelFrame,
EndFrame,
FunctionCallInProgressFrame,
FunctionCallResultFrame,
MetricsFrame,
StartFrame,
UserStartedSpeakingFrame,
UserStoppedSpeakingFrame,
VADUserStoppedSpeakingFrame,
)
from pipecat.observers.base_observer import BaseObserver, FramePushed
from pipecat.observers.turn_tracking_observer import TurnTrackingObserver
from pipecat.observers.user_bot_latency_observer import UserBotLatencyObserver
from pipecat.processors.frame_processor import FrameDirection
from tuner_pipecat_sdk.accumulator import CallAccumulator
from tuner_pipecat_sdk.payload_builder import build_payload
from api.enums import WorkflowRunMode
TUNER_RECORDING_PLACEHOLDER = "pipecat://no-recording"
@dataclass(frozen=True)
class _PayloadConfig:
call_id: str
call_type: str
recording_url: str
asr_model: str
llm_model: str
tts_model: str
sip_call_id: str | None = None
sip_headers: dict[str, str] | None = None
agent_version: int | None = None
def mode_to_tuner_call_type(mode: str | None) -> str:
if mode in {
WorkflowRunMode.WEBRTC.value,
WorkflowRunMode.SMALLWEBRTC.value,
}:
return "web_call"
return "phone_call"
class TunerCollector(BaseObserver):
"""Collect runtime call metadata and build a deferred Tuner payload."""
def __init__(
self,
*,
workflow_run_id: int,
call_type: str,
asr_model: str = "",
llm_model: str = "",
tts_model: str = "",
agent_version: int | None = None,
max_frames: int = 500,
) -> None:
super().__init__()
self._call_id = str(workflow_run_id)
self._call_type = call_type
self._asr_model = asr_model
self._llm_model = llm_model
self._tts_model = tts_model
self._agent_version = agent_version
self._acc = CallAccumulator()
self._acc.call_start_abs_ns = time.time_ns()
self._context_provider: Callable[[], list[dict[str, Any]]] | None = None
self._processed_frames: set[int] = set()
self._frame_history: deque[int] = deque(maxlen=max_frames)
def attach_context(self, provider: Callable[[], list[dict[str, Any]]]) -> None:
self._context_provider = provider
def set_disconnection_reason(self, reason: str | None) -> None:
if reason:
self._acc.set_disconnection_reason(reason)
def attach_turn_tracking_observer(
self, turn_tracker: TurnTrackingObserver | None
) -> None:
if turn_tracker is None:
return
@turn_tracker.event_handler("on_turn_started")
async def _on_turn_started(_tracker: Any, turn_number: int) -> None:
self._acc.on_turn_started(turn_number, time.time_ns())
@turn_tracker.event_handler("on_turn_ended")
async def _on_turn_ended(
_tracker: Any, turn_number: int, _duration: float, was_interrupted: bool
) -> None:
self._acc.on_turn_ended(turn_number, was_interrupted)
def attach_latency_observer(
self, latency_observer: UserBotLatencyObserver | None
) -> None:
if latency_observer is None:
return
@latency_observer.event_handler("on_latency_measured")
async def _on_latency_measured(_observer: Any, latency: float) -> None:
self._acc.on_latency_measured(latency)
@latency_observer.event_handler("on_latency_breakdown")
async def _on_latency_breakdown(_observer: Any, breakdown: Any) -> None:
self._acc.on_latency_breakdown(breakdown)
async def on_push_frame(self, data: FramePushed):
if data.direction != FrameDirection.DOWNSTREAM:
return
if data.frame.id in self._processed_frames:
return
self._processed_frames.add(data.frame.id)
self._frame_history.append(data.frame.id)
if len(self._processed_frames) > len(self._frame_history):
self._processed_frames = set(self._frame_history)
frame = data.frame
timestamp_ns = data.timestamp
if isinstance(frame, StartFrame):
self._acc.on_start(timestamp_ns)
elif isinstance(frame, FunctionCallInProgressFrame):
self._acc.on_function_call_in_progress(frame, timestamp_ns)
elif isinstance(frame, FunctionCallResultFrame):
self._acc.on_function_call_result(frame.tool_call_id, timestamp_ns)
elif isinstance(frame, MetricsFrame):
self._acc.on_metrics_frame(frame)
elif isinstance(frame, UserStartedSpeakingFrame):
self._acc.on_user_started_speaking(timestamp_ns)
elif isinstance(frame, UserStoppedSpeakingFrame):
self._acc.on_user_stopped_speaking(timestamp_ns)
self._acc.on_user_turn_stopped(timestamp_ns)
elif isinstance(frame, BotStartedSpeakingFrame):
self._acc.on_bot_started_speaking(timestamp_ns)
elif isinstance(frame, BotStoppedSpeakingFrame):
self._acc.on_bot_stopped(timestamp_ns)
elif isinstance(frame, VADUserStoppedSpeakingFrame):
self._acc.on_vad_stopped(timestamp_ns)
elif isinstance(frame, (CancelFrame, EndFrame)):
self._acc.on_call_end(timestamp_ns)
def build_payload_snapshot(
self,
*,
recording_url: str = TUNER_RECORDING_PLACEHOLDER,
) -> dict[str, Any] | None:
if self._context_provider is None:
logger.warning(
"[tuner] no context provider attached; skipping payload snapshot"
)
return None
transcript = list(self._context_provider())
payload = build_payload(
self._acc,
_PayloadConfig(
call_id=self._call_id,
call_type=self._call_type,
recording_url=recording_url,
asr_model=self._asr_model,
llm_model=self._llm_model,
tts_model=self._tts_model,
agent_version=self._agent_version,
),
transcript,
)
return payload.to_dict()

76
api/services/integrations/tuner/completion.py Normal file
View file

@ -0,0 +1,76 @@
from __future__ import annotations
import copy
from datetime import UTC, datetime
from typing import Any
from loguru import logger
from api.constants import BACKEND_API_ENDPOINT, TUNER_BASE_URL
from api.services.integrations.base import IntegrationCompletionContext
from .client import TunerDeliveryConfig, post_call
from .collector import TUNER_RECORDING_PLACEHOLDER
from .node import TunerNodeData
def _build_recording_url(
context: IntegrationCompletionContext,
) -> str | None:
workflow_run = context.workflow_run
if context.public_token:
base_url = f"{BACKEND_API_ENDPOINT}/api/v1/public/download/workflow/{context.public_token}"
return f"{base_url}/recording" if workflow_run.recording_url else None
return workflow_run.recording_url
async def run_completion(
nodes: list[dict[str, Any]],
context: IntegrationCompletionContext,
) -> dict[str, Any]:
results: dict[str, Any] = {}
payload_snapshot = (context.workflow_run.logs or {}).get("tuner_payload")
recording_url = _build_recording_url(context) or TUNER_RECORDING_PLACEHOLDER
for node in nodes:
node_id = node.get("id", "unknown")
try:
tuner_data = TunerNodeData.model_validate(node.get("data", {}))
except Exception as exc:
logger.warning(f"Tuner node #{node_id} failed validation, skipping: {exc}")
results[f"tuner_{node_id}"] = {"error": "validation_failed"}
continue
if not tuner_data.tuner_enabled:
logger.debug(f"Tuner node '{tuner_data.name}' is disabled, skipping")
continue
if not payload_snapshot:
logger.warning(
f"Tuner payload snapshot missing for node '{tuner_data.name}' (#{node_id})"
)
results[f"tuner_{node_id}"] = {"error": "missing_payload_snapshot"}
continue
payload = copy.deepcopy(payload_snapshot)
payload["recording_url"] = recording_url
try:
config = TunerDeliveryConfig(
base_url=TUNER_BASE_URL,
api_key=tuner_data.tuner_api_key or "",
workspace_id=tuner_data.tuner_workspace_id or 0,
agent_id=tuner_data.tuner_agent_id or "",
)
delivery = await post_call(config, payload)
results[f"tuner_{node_id}"] = {
**delivery,
"workspace_id": tuner_data.tuner_workspace_id,
"agent_id": tuner_data.tuner_agent_id,
"exported_at": datetime.now(UTC).isoformat(),
}
except Exception as exc:
logger.error(f"Tuner export failed for node '{tuner_data.name}': {exc}")
results[f"tuner_{node_id}"] = {"error": str(exc)}
return results

139
api/services/integrations/tuner/node.py Normal file
View file

@ -0,0 +1,139 @@
from __future__ import annotations
from pydantic import model_validator
from api.services.integrations.base import IntegrationNodeRegistration
from api.services.workflow.node_data import BaseNodeData
from api.services.workflow.node_specs._base import (
GraphConstraints,
NodeCategory,
NodeExample,
PropertyType,
)
from api.services.workflow.node_specs.model_spec import (
build_spec,
node_spec,
spec_field,
)
@node_spec(
name="tuner",
display_name="Tuner",
description="Export the completed call to Tuner for Agent Observability",
llm_hint=(
"Tuner is a post-call observability export. It does not participate in the "
"conversation graph and should not be connected to other nodes."
),
category=NodeCategory.integration,
icon="Activity",
examples=[
NodeExample(
name="tuner_export",
data={
"name": "Primary Tuner Export",
"tuner_enabled": True,
"tuner_agent_id": "sales-bot-prod",
"tuner_workspace_id": 42,
"tuner_api_key": "tuner_live_xxxxxxxx",
},
)
],
graph_constraints=GraphConstraints(
min_incoming=0,
max_incoming=0,
min_outgoing=0,
max_outgoing=0,
),
property_order=(
"name",
"tuner_enabled",
"tuner_agent_id",
"tuner_workspace_id",
"tuner_api_key",
),
field_overrides={
"name": {
"spec_default": "Tuner",
"description": "Short identifier for this Tuner export configuration.",
},
"tuner_enabled": {
"display_name": "Enabled",
"description": "When false, Dograh skips exporting this call to Tuner.",
},
"tuner_agent_id": {
"display_name": "Tuner Agent ID",
"description": "The agent identifier registered in your Tuner workspace.",
"required": True,
},
"tuner_workspace_id": {
"display_name": "Tuner Workspace ID",
"description": "Your numeric Tuner workspace ID.",
"required": True,
"min_value": 1,
},
"tuner_api_key": {
"display_name": "Tuner API Key",
"description": "Bearer token used when posting completed calls to Tuner.",
"required": True,
},
},
)
class TunerNodeData(BaseNodeData):
tuner_enabled: bool = spec_field(
default=True,
ui_type=PropertyType.boolean,
display_name="Enabled",
description="When false, Dograh skips exporting this call to Tuner.",
)
tuner_agent_id: str | None = spec_field(
default=None,
ui_type=PropertyType.string,
display_name="Tuner Agent ID",
description="The agent identifier registered in your Tuner workspace.",
)
tuner_workspace_id: int | None = spec_field(
default=None,
gt=0,
ui_type=PropertyType.number,
display_name="Tuner Workspace ID",
description="Your numeric Tuner workspace ID.",
)
tuner_api_key: str | None = spec_field(
default=None,
ui_type=PropertyType.string,
display_name="Tuner API Key",
description="Bearer token used when posting completed calls to Tuner.",
)
@model_validator(mode="after")
def _validate_enabled_config(self):
if not self.tuner_enabled:
return self
missing: list[str] = []
if not self.tuner_agent_id or not self.tuner_agent_id.strip():
missing.append("tuner_agent_id")
if self.tuner_workspace_id is None:
missing.append("tuner_workspace_id")
if not self.tuner_api_key or not self.tuner_api_key.strip():
missing.append("tuner_api_key")
if missing:
fields = ", ".join(missing)
raise ValueError(
f"Tuner node is enabled but missing required fields: {fields}"
)
return self
SPEC = build_spec(TunerNodeData)
NODE = IntegrationNodeRegistration(
type_name="tuner",
data_model=TunerNodeData,
node_spec=SPEC,
sensitive_fields=("tuner_api_key",),
)

101
api/services/integrations/tuner/runtime.py Normal file
View file

@ -0,0 +1,101 @@
from __future__ import annotations
from typing import Any
from api.services.configuration.registry import ServiceProviders
from api.services.integrations.base import (
IntegrationRuntimeContext,
IntegrationRuntimeSession,
)
from .collector import TunerCollector, mode_to_tuner_call_type
def _format_model_label(provider: str | None, model: str | None) -> str:
if provider and model:
return f"{provider}/{model}"
if model:
return model
return provider or ""
def _resolve_model_labels(context: IntegrationRuntimeContext) -> tuple[str, str, str]:
user_config = context.user_config
if context.is_realtime and user_config.realtime:
realtime_provider = user_config.realtime.provider
realtime_model = user_config.realtime.model
llm_model = _format_model_label(realtime_provider, realtime_model)
if realtime_provider in {
ServiceProviders.GOOGLE_REALTIME.value,
ServiceProviders.GOOGLE_VERTEX_REALTIME.value,
ServiceProviders.OPENAI_REALTIME.value,
}:
return "", llm_model, ""
return "", llm_model, ""
return (
_format_model_label(
getattr(user_config.stt, "provider", None),
getattr(user_config.stt, "model", None),
),
_format_model_label(
getattr(user_config.llm, "provider", None),
getattr(user_config.llm, "model", None),
),
_format_model_label(
getattr(user_config.tts, "provider", None),
getattr(user_config.tts, "model", None),
),
)
class TunerRuntimeSession(IntegrationRuntimeSession):
name = "tuner"
def __init__(self, collector: TunerCollector) -> None:
self._collector = collector
def attach(self, task: Any) -> None:
self._collector.attach_turn_tracking_observer(task.turn_tracking_observer)
self._collector.attach_latency_observer(task.user_bot_latency_observer)
task.add_observer(self._collector)
async def on_call_finished(
self,
*,
gathered_context: dict[str, Any],
) -> dict[str, Any] | None:
self._collector.set_disconnection_reason(
gathered_context.get("call_disposition")
)
payload = self._collector.build_payload_snapshot()
if payload is None:
return None
return {"tuner_payload": payload}
def create_runtime_sessions(
context: IntegrationRuntimeContext,
) -> list[IntegrationRuntimeSession]:
tuner_nodes = [
node
for node in context.workflow_graph.nodes.values()
if node.node_type == "tuner" and getattr(node.data, "tuner_enabled", True)
]
if not tuner_nodes:
return []
asr_model, llm_model, tts_model = _resolve_model_labels(context)
collector = TunerCollector(
workflow_run_id=context.workflow_run_id,
call_type=mode_to_tuner_call_type(context.workflow_run.mode),
asr_model=asr_model,
llm_model=llm_model,
tts_model=tts_model,
agent_version=getattr(context.run_definition, "version_number", None),
)
collector.attach_context(context.context_messages_provider)
return [TunerRuntimeSession(collector)]

34
api/services/pipecat/event_handlers.py
View file

@ -5,6 +5,7 @@ from loguru import logger
from api.db import db_client
from api.enums import PostHogEvent, WorkflowRunState
from api.services.campaign.circuit_breaker import circuit_breaker
from api.services.integrations import IntegrationRuntimeSession
from api.services.pipecat.audio_config import AudioConfig
from api.services.pipecat.audio_playback import play_audio, play_audio_loop
from api.services.pipecat.in_memory_buffers import (
@ -70,6 +71,7 @@ def register_event_handlers(
pre_call_fetch_task: asyncio.Task | None = None,
fetch_recording_audio=None,
user_provider_id: str | None = None,
integration_runtime_sessions: list[IntegrationRuntimeSession] | None = None,
):
"""Register all event handlers for transport and task events.
@ -319,6 +321,20 @@ def register_event_handlers(
)
# Clean up engine resources (including voicemail detector)
integration_logs: dict[str, object] = {}
for runtime_session in integration_runtime_sessions or []:
try:
session_logs = await runtime_session.on_call_finished(
gathered_context=gathered_context
)
if session_logs:
integration_logs.update(session_logs)
except Exception as e:
logger.error(
f"Error finalizing integration runtime session '{runtime_session.name}': {e}",
exc_info=True,
)
await engine.cleanup()
# ------------------------------------------------------------------
@ -368,14 +384,11 @@ def register_event_handlers(
)
)
# Save real-time feedback logs to workflow run
logs_update: dict[str, object] = {}
if not in_memory_logs_buffer.is_empty:
try:
feedback_events = in_memory_logs_buffer.get_events()
await db_client.update_workflow_run(
run_id=workflow_run_id,
logs={"realtime_feedback_events": feedback_events},
)
logs_update["realtime_feedback_events"] = feedback_events
logger.debug(
f"Saved {len(feedback_events)} feedback events to workflow run logs"
)
@ -384,6 +397,17 @@ def register_event_handlers(
else:
logger.debug("Logs buffer is empty, skipping save")
logs_update.update(integration_logs)
if logs_update:
try:
await db_client.update_workflow_run(
run_id=workflow_run_id,
logs=logs_update,
)
except Exception as e:
logger.error(f"Error saving workflow run logs: {e}", exc_info=True)
# Write buffers to temp files and enqueue combined processing task
audio_temp_path = None
transcript_temp_path = None

25
api/services/pipecat/run_pipeline.py
View file

@ -7,6 +7,10 @@ from loguru import logger
from api.db import db_client
from api.enums import WorkflowRunMode
from api.services.configuration.registry import ServiceProviders
from api.services.integrations import (
IntegrationRuntimeContext,
create_runtime_sessions,
)
from api.services.pipecat.audio_config import AudioConfig, create_audio_config
from api.services.pipecat.event_handlers import (
register_audio_data_handler,
@ -525,6 +529,18 @@ async def _run_pipeline(
# Create pipeline components
audio_buffer, context = create_pipeline_components(audio_config)
integration_runtime_sessions = create_runtime_sessions(
IntegrationRuntimeContext(
workflow_run_id=workflow_run_id,
workflow_run=workflow_run,
workflow_graph=workflow_graph,
run_definition=run_definition,
user_config=user_config,
is_realtime=is_realtime,
context_messages_provider=lambda: context.messages,
)
)
# Set the context, audio_config, and audio_buffer after creation
engine.set_context(context)
engine.set_audio_config(audio_config)
@ -717,6 +733,14 @@ async def _run_pipeline(
# Create pipeline task with audio configuration
task = create_pipeline_task(pipeline, workflow_run_id, audio_config)
for runtime_session in integration_runtime_sessions:
runtime_session.attach(task)
logger.info(
"[integrations] attached runtime session '{}' for workflow run {}",
runtime_session.name,
workflow_run_id,
)
# Now set the task and transport output on the engine
engine.set_task(task)
engine.set_transport_output(transport.output())
@ -781,6 +805,7 @@ async def _run_pipeline(
pre_call_fetch_task=pre_call_fetch_task,
fetch_recording_audio=fetch_audio,
user_provider_id=user_provider_id,
integration_runtime_sessions=integration_runtime_sessions,
)
register_audio_data_handler(audio_buffer, workflow_run_id, in_memory_audio_buffer)

8
api/services/workflow/audit.py
View file

@ -7,7 +7,7 @@ script in `api/services/admin_utils/local_exec.py` is the production
consumer.
"""
from api.services.workflow.node_specs import REGISTRY
from api.services.workflow.node_specs import all_specs
def _build_type_rules() -> tuple[set[str], set[str]]:
@ -16,14 +16,14 @@ def _build_type_rules() -> tuple[set[str], set[str]]:
(max_incoming == 0)."""
src_forbidden: set[str] = set()
tgt_forbidden: set[str] = set()
for name, spec in REGISTRY.items():
for spec in all_specs():
gc = spec.graph_constraints
if gc is None:
continue
if gc.max_outgoing == 0:
src_forbidden.add(name)
src_forbidden.add(spec.name)
if gc.max_incoming == 0:
tgt_forbidden.add(name)
tgt_forbidden.add(spec.name)
return src_forbidden, tgt_forbidden

932
api/services/workflow/dto.py
View file

File diff suppressed because it is too large Load diff

19
api/services/workflow/node_data.py Normal file
View file

@ -0,0 +1,19 @@
from __future__ import annotations
from pydantic import BaseModel
from api.services.workflow.node_specs._base import PropertyType
from api.services.workflow.node_specs.model_spec import spec_field
class BaseNodeData(BaseModel):
name: str = spec_field(
...,
min_length=1,
ui_type=PropertyType.string,
display_name="Name",
description="Short identifier shown in the canvas and call logs.",
required=True,
)
is_start: bool = spec_field(default=False, spec_exclude=True)
is_end: bool = spec_field(default=False, spec_exclude=True)

51
api/services/workflow/node_specs/__init__.py
View file

@ -1,10 +1,8 @@
"""Node specification registry.
Adding a new node type:
1. Create a new module under this package, define a `SPEC: NodeSpec`.
2. Add it to the imports + REGISTRY below.
3. The Pydantic discriminated-union variant in dto.py must use the same
`name` value as `SPEC.name`.
Core node specs are generated from the workflow DTO models. Third-party
integration node specs live under `api.services.integrations/<name>/` and
register through the integration registry so they don't need edits here.
"""
from __future__ import annotations
@ -21,8 +19,10 @@ from api.services.workflow.node_specs._base import (
PropertyType,
evaluate_display_options,
)
from api.services.workflow.node_specs.model_spec import build_spec
REGISTRY: dict[str, NodeSpec] = {}
_CORE_SPECS_LOADED = False
def register(spec: NodeSpec) -> NodeSpec:
@ -38,12 +38,23 @@ def register(spec: NodeSpec) -> NodeSpec:
def get_spec(name: str) -> NodeSpec | None:
return REGISTRY.get(name)
_ensure_core_registered()
if name in REGISTRY:
return REGISTRY[name]
from api.services.integrations import get_node_spec
return get_node_spec(name)
def all_specs() -> list[NodeSpec]:
"""All registered specs, sorted by name for stable output."""
return [REGISTRY[name] for name in sorted(REGISTRY)]
_ensure_core_registered()
from api.services.integrations import all_node_specs
specs = {spec.name: spec for spec in REGISTRY.values()}
specs.update({spec.name: spec for spec in all_node_specs()})
return [specs[name] for name in sorted(specs)]
__all__ = [
@ -64,19 +75,15 @@ __all__ = [
]
# Side-effect imports — each module's `register(SPEC)` call populates REGISTRY.
# Keep at module bottom so the registry helpers are defined first.
from api.services.workflow.node_specs import ( # noqa: E402, F401
agent,
end_call,
global_node,
qa,
start_call,
trigger,
webhook,
)
def _ensure_core_registered() -> None:
global _CORE_SPECS_LOADED
if _CORE_SPECS_LOADED:
return
# Wire up registrations from the SPEC constants in each module.
for _module in (start_call, agent, end_call, global_node, trigger, webhook, qa):
register(_module.SPEC)
del _module
from api.services.workflow.dto import _CORE_NODE_DATA_CLASSES
for model_cls in _CORE_NODE_DATA_CLASSES.values():
if model_cls.__node_spec_metadata__.name in REGISTRY:
continue
register(build_spec(model_cls))
_CORE_SPECS_LOADED = True

85
api/services/workflow/node_specs/_base.py
View file

@ -1,9 +1,9 @@
"""Spec schema for node definitions.
A `NodeSpec` is the single source of truth for a node type. It drives:
- Pydantic validation (the per-type DTOs in dto.py mirror these property types)
- The generic UI renderer (frontend reads specs via /api/v1/node-types)
- The LLM SDK (constructors and JSON-Schema derived from these specs)
`NodeSpec` is the serialized contract exposed to the frontend, MCP tools, and
SDKs. Core workflow node specs are generated from the DTO models plus
model-attached metadata; integration packages may generate them the same way or
register a prebuilt spec object.
Every property's `description` is LLM-readable copy — treat it as production
documentation, not internal notes. Spec lint enforces non-empty descriptions
@ -122,6 +122,16 @@ class PropertyOption(BaseModel):
model_config = ConfigDict(extra="forbid")
def to_mcp_dict(self) -> dict[str, Any]:
"""Lean projection for `get_node_type`: the `value` an LLM writes in
code, plus a `description` when one carries real meaning. The UI
`label` is dropped — it's the option's display string, never used
when authoring."""
out: dict[str, Any] = {"value": self.value}
if self.description:
out["description"] = self.description
return out
class PropertySpec(BaseModel):
"""Single field on a node.
@ -175,6 +185,43 @@ class PropertySpec(BaseModel):
model_config = ConfigDict(extra="forbid")
def to_mcp_dict(self) -> dict[str, Any]:
"""Lean projection of this property for the `get_node_type` MCP tool.
Keeps only what an LLM needs to author a valid value: name, type,
description, llm_hint, requiredness, default, enum options, nested
row properties, and validation bounds. UI-rendering concerns
(`display_name`, `placeholder`, `display_options`, `editor`,
`extra`) and null/empty fields are omitted — they're noise in the
model's context and never appear in authored SDK code.
"""
out: dict[str, Any] = {
"name": self.name,
"type": self.type.value,
"description": self.description,
}
if self.llm_hint:
out["llm_hint"] = self.llm_hint
if self.required:
out["required"] = True
if self.default is not None:
out["default"] = self.default
if self.options:
out["options"] = [opt.to_mcp_dict() for opt in self.options]
if self.properties:
out["properties"] = [prop.to_mcp_dict() for prop in self.properties]
for constraint in (
"min_value",
"max_value",
"min_length",
"max_length",
"pattern",
):
value = getattr(self, constraint)
if value is not None:
out[constraint] = value
return out
PropertySpec.model_rebuild()
@ -222,3 +269,33 @@ class NodeSpec(BaseModel):
graph_constraints: Optional[GraphConstraints] = None
model_config = ConfigDict(extra="forbid")
def to_mcp_dict(self) -> dict[str, Any]:
"""Lean projection of this spec for the `get_node_type` MCP tool.
Drops node-level UI metadata (`display_name`, `category`, `icon`,
`version`) and the per-property rendering concerns trimmed by
`PropertySpec.to_mcp_dict`, leaving just the authoring-relevant
schema the LLM consumes when composing a workflow. The full spec is
still served verbatim to the frontend renderer (REST `node-types`
route) and the SDK codegen / TS validator (`ts_bridge`), which need
the dropped fields.
"""
out: dict[str, Any] = {
"name": self.name,
"description": self.description,
}
if self.llm_hint:
out["llm_hint"] = self.llm_hint
out["properties"] = [prop.to_mcp_dict() for prop in self.properties]
if self.examples:
out["examples"] = [
ex.model_dump(mode="json", exclude_none=True) for ex in self.examples
]
if self.graph_constraints:
constraints = self.graph_constraints.model_dump(
mode="json", exclude_none=True
)
if constraints:
out["graph_constraints"] = constraints
return out

168
api/services/workflow/node_specs/agent.py
View file

@ -1,168 +0,0 @@
"""Spec for the Agent node — the workhorse mid-call node where the LLM
executes a focused conversational step with optional tools and documents."""
from api.services.workflow.node_specs._base import (
DisplayOptions,
GraphConstraints,
NodeCategory,
NodeExample,
NodeSpec,
PropertyOption,
PropertySpec,
PropertyType,
)
SPEC = NodeSpec(
name="agentNode",
display_name="Agent Node",
description="Conversational step — the LLM runs one focused exchange.",
llm_hint=(
"Mid-call step executed by the LLM. Most workflows are a chain of "
"agent nodes connected by edges that describe transition conditions. "
"Each agent node can invoke tools and reference documents."
),
category=NodeCategory.call_node,
icon="Headset",
properties=[
PropertySpec(
name="name",
type=PropertyType.string,
display_name="Name",
description=(
"Short identifier for this step (e.g., 'Qualify Budget'). "
"Appears in call logs and edge transition tools."
),
required=True,
min_length=1,
default="Agent",
),
PropertySpec(
name="prompt",
type=PropertyType.mention_textarea,
display_name="Prompt",
description=(
"Agent system prompt for this step. Supports "
"{{template_variables}} from extraction or pre-call fetch."
),
required=True,
min_length=1,
placeholder="Ask the caller about their budget and timeline.",
),
PropertySpec(
name="allow_interrupt",
type=PropertyType.boolean,
display_name="Allow Interruption",
description=(
"When true, the user can interrupt the agent mid-utterance. "
"Set false for non-interruptible disclosures."
),
default=True,
),
PropertySpec(
name="add_global_prompt",
type=PropertyType.boolean,
display_name="Add Global Prompt",
description=(
"When true and a Global node exists, prepends the global "
"prompt to this node's prompt at runtime."
),
default=True,
),
PropertySpec(
name="extraction_enabled",
type=PropertyType.boolean,
display_name="Enable Variable Extraction",
description=(
"When true, runs an LLM extraction pass on transition out of "
"this node to capture variables from the conversation."
),
default=False,
),
PropertySpec(
name="extraction_prompt",
type=PropertyType.string,
display_name="Extraction Prompt",
description="Overall instructions guiding variable extraction.",
display_options=DisplayOptions(show={"extraction_enabled": [True]}),
editor="textarea",
),
PropertySpec(
name="extraction_variables",
type=PropertyType.fixed_collection,
display_name="Variables to Extract",
description=(
"Each entry declares one variable to capture from the "
"conversation, with its name, type, and per-variable hint."
),
display_options=DisplayOptions(show={"extraction_enabled": [True]}),
properties=[
PropertySpec(
name="name",
type=PropertyType.string,
display_name="Variable Name",
description="snake_case identifier used downstream.",
required=True,
),
PropertySpec(
name="type",
type=PropertyType.options,
display_name="Type",
description="Data type of the extracted value.",
required=True,
default="string",
options=[
PropertyOption(value="string", label="String"),
PropertyOption(value="number", label="Number"),
PropertyOption(value="boolean", label="Boolean"),
],
),
PropertySpec(
name="prompt",
type=PropertyType.string,
display_name="Extraction Hint",
description="Per-variable hint describing what to look for.",
editor="textarea",
),
],
),
PropertySpec(
name="tool_uuids",
type=PropertyType.tool_refs,
display_name="Tools",
description="Tools the agent can invoke during this step.",
llm_hint="List of tool UUIDs from `list_tools`.",
),
PropertySpec(
name="document_uuids",
type=PropertyType.document_refs,
display_name="Knowledge Base Documents",
description="Documents the agent can reference during this step.",
llm_hint="List of document UUIDs from `list_documents`.",
),
],
examples=[
NodeExample(
name="qualify_lead",
data={
"name": "Qualify Budget",
"prompt": "Ask about budget and timeline. Capture both before transitioning.",
"allow_interrupt": True,
"extraction_enabled": True,
"extraction_prompt": "Extract budget amount and rough timeline.",
"extraction_variables": [
{
"name": "budget_usd",
"type": "number",
"prompt": "Stated budget in USD",
},
{
"name": "timeline",
"type": "string",
"prompt": "When they want to start",
},
],
},
),
],
graph_constraints=GraphConstraints(min_incoming=1),
)

44
api/services/workflow/node_specs/constants.py Normal file
View file

@ -0,0 +1,44 @@
DEFAULT_QA_SYSTEM_PROMPT = """You are a QA analyst evaluating a specific segment of a voice AI conversation.
## Node Purpose
{{node_summary}}
## Previous Conversation Context (For start of conversation, previous conversation summary can be empty.)
{{previous_conversation_summary}}
## Tags to evaluate
Examine the conversation carefully and identify which of the following tags apply:
- UNCLEAR_CONVERSATION - The conversation is not coherent or clear, messages don't connect logically
- ASSISTANT_IN_LOOP - The assistant asks the same question multiple times or gets stuck repeating itself
- ASSISTANT_REPLY_IMPROPER - The assistant did not reply properly to the user's question/query or seems confused by what the user said
- USER_FRUSTRATED - The user seems angry, frustrated, or is complaining about something in the call
- USER_NOT_UNDERSTANDING - The user explicitly says they don't understand or repeatedly asks for clarification
- HEARING_ISSUES - Either party can't hear the other ("hello?", "are you there?", "can you hear me?")
- DEAD_AIR - Unusually long silences in the conversation (use the timestamps to judge)
- USER_REQUESTING_FEATURE - The user asks for something the assistant can't fulfill
- ASSISTANT_LACKS_EMPATHY - The assistant ignores the user's personal situation or emotional state and continues pitching or pushing the agenda.
- USER_DETECTS_AI - The user suspects or identifies that they are talking to an AI/robot/bot rather than a real human.
## Call metrics (pre-computed)
Use these alongside the transcript for your analysis:
{{metrics}}
## Output format
Return ONLY a valid JSON object (no markdown):
{
"tags": [
{
"tag": "TAG_NAME",
"reason": "Short reason with evidence from the transcript"
}
],
"overall_sentiment": "positive|neutral|negative",
"call_quality_score": <1-10>,
"summary": "1-2 sentence summary of this segment"
}
If no tags apply, return an empty tags list. Always provide sentiment, score, and summary."""

141
api/services/workflow/node_specs/end_call.py
View file

@ -1,141 +0,0 @@
"""Spec for the End Call node — terminal node that wraps up a conversation
and optionally extracts variables before hangup."""
from api.services.workflow.node_specs._base import (
DisplayOptions,
GraphConstraints,
NodeCategory,
NodeExample,
NodeSpec,
PropertyOption,
PropertySpec,
PropertyType,
)
SPEC = NodeSpec(
name="endCall",
display_name="End Call",
description="Closes the conversation and hangs up.",
llm_hint=(
"Terminal node that politely closes the conversation. Variable "
"extraction can run before hangup. A workflow can have multiple "
"endCall nodes reached via different edge conditions."
),
category=NodeCategory.call_node,
icon="OctagonX",
properties=[
PropertySpec(
name="name",
type=PropertyType.string,
display_name="Name",
description=(
"Short identifier shown in call logs. Should describe the "
"ending context (e.g., 'Successful close', 'Polite decline')."
),
required=True,
min_length=1,
default="End Call",
),
PropertySpec(
name="prompt",
type=PropertyType.mention_textarea,
display_name="Prompt",
description=(
"Agent system prompt for the closing exchange. Supports "
"{{template_variables}} from extraction or pre-call fetch."
),
required=True,
min_length=1,
placeholder="Thank the caller and confirm next steps before ending the call.",
),
PropertySpec(
name="add_global_prompt",
type=PropertyType.boolean,
display_name="Add Global Prompt",
description=(
"When true and a Global node exists, prepends the global "
"prompt to this node's prompt at runtime."
),
default=False,
),
PropertySpec(
name="extraction_enabled",
type=PropertyType.boolean,
display_name="Enable Variable Extraction",
description=(
"When true, runs an LLM extraction pass before hangup to "
"capture variables from the conversation."
),
default=False,
),
PropertySpec(
name="extraction_prompt",
type=PropertyType.string,
display_name="Extraction Prompt",
description=(
"Overall instructions guiding how variables should be "
"extracted from the conversation."
),
display_options=DisplayOptions(show={"extraction_enabled": [True]}),
editor="textarea",
),
PropertySpec(
name="extraction_variables",
type=PropertyType.fixed_collection,
display_name="Variables to Extract",
description=(
"Each entry declares one variable to capture from the "
"conversation, with its name, data type, and a per-variable "
"extraction hint."
),
display_options=DisplayOptions(show={"extraction_enabled": [True]}),
properties=[
PropertySpec(
name="name",
type=PropertyType.string,
display_name="Variable Name",
description="snake_case identifier used downstream.",
required=True,
),
PropertySpec(
name="type",
type=PropertyType.options,
display_name="Type",
description="The data type of the extracted value.",
required=True,
default="string",
options=[
PropertyOption(value="string", label="String"),
PropertyOption(value="number", label="Number"),
PropertyOption(value="boolean", label="Boolean"),
],
),
PropertySpec(
name="prompt",
type=PropertyType.string,
display_name="Extraction Hint",
description=(
"Per-variable hint describing what to look for in "
"the conversation."
),
editor="textarea",
),
],
),
],
examples=[
NodeExample(
name="successful_close",
data={
"name": "Successful Close",
"prompt": "Confirm the appointment time, thank the caller, and end the call.",
"add_global_prompt": False,
},
),
],
graph_constraints=GraphConstraints(
min_incoming=1,
min_outgoing=0,
max_outgoing=0,
),
)

77
api/services/workflow/node_specs/global_node.py
View file

@ -1,77 +0,0 @@
"""Spec for the Global node — system-level instructions appended to every
agent node that opts in via `add_global_prompt`."""
from api.services.workflow.node_specs._base import (
GraphConstraints,
NodeCategory,
NodeExample,
NodeSpec,
PropertySpec,
PropertyType,
)
SPEC = NodeSpec(
name="globalNode",
display_name="Global Node",
description="Persona/tone appended to every agent node's prompt.",
llm_hint=(
"System-level prompt appended to every prompted node whose "
"`add_global_prompt` is true. Use it for persona, tone, and shared "
"rules that apply across the entire conversation. At most one "
"global node per workflow."
),
category=NodeCategory.global_node,
icon="Globe",
properties=[
PropertySpec(
name="name",
type=PropertyType.string,
display_name="Name",
description=(
"Short identifier shown in the canvas and call logs. Has no "
"runtime effect."
),
required=True,
min_length=1,
default="Global Node",
),
PropertySpec(
name="prompt",
type=PropertyType.mention_textarea,
display_name="Global Prompt",
description=(
"Text appended to every prompted node's system prompt when "
"that node has `add_global_prompt=true`. Supports "
"{{template_variables}}."
),
required=True,
min_length=1,
placeholder="You are a friendly assistant calling on behalf of {{company_name}}.",
default=(
"You are a helpful assistant whose mode of interaction with "
"the user is voice. So don't use any special characters which "
"can not be pronounced. Use short sentences and simple language."
),
),
],
examples=[
NodeExample(
name="basic_persona",
description="Establishes a consistent persona across the call.",
data={
"name": "Persona",
"prompt": (
"You are Sarah, a polite and warm representative from "
"Acme Corp. Always thank the caller for their time and "
"speak in short conversational sentences."
),
},
),
],
graph_constraints=GraphConstraints(
min_incoming=0,
max_incoming=0,
min_outgoing=0,
max_outgoing=0,
),
)

404
api/services/workflow/node_specs/model_spec.py Normal file
View file

@ -0,0 +1,404 @@
from __future__ import annotations
from dataclasses import dataclass
from dataclasses import field as dataclass_field
from enum import Enum
from types import NoneType
from typing import Any, Callable, Literal, get_args, get_origin
from pydantic import BaseModel, Field
from pydantic.fields import FieldInfo, PydanticUndefined
from api.services.workflow.node_specs._base import (
DisplayOptions,
GraphConstraints,
NodeCategory,
NodeExample,
NodeSpec,
PropertyOption,
PropertySpec,
PropertyType,
)
_SPEC_FIELD_META_KEY = "__dograh_spec_field__"
_UNSET = object()
@dataclass(frozen=True)
class NodeSpecMetadata:
name: str
display_name: str
description: str
category: NodeCategory
icon: str
llm_hint: str | None = None
version: str = "1.0.0"
examples: tuple[NodeExample, ...] = ()
graph_constraints: GraphConstraints | None = None
property_order: tuple[str, ...] = ()
field_overrides: dict[str, dict[str, Any]] = dataclass_field(default_factory=dict)
def spec_field(
*field_args: Any,
ui_type: PropertyType | str | None = None,
display_name: str | None = None,
llm_hint: str | None = None,
required: bool | None = None,
spec_default: Any = _UNSET,
placeholder: str | None = None,
display_options: DisplayOptions | None = None,
options: list[PropertyOption] | None = None,
editor: str | None = None,
extra: dict[str, Any] | None = None,
spec_exclude: bool = False,
min_value: float | None = None,
max_value: float | None = None,
min_length: int | None = None,
max_length: int | None = None,
pattern: str | None = None,
**field_kwargs: Any,
):
json_schema_extra = dict(field_kwargs.pop("json_schema_extra", {}) or {})
json_schema_extra[_SPEC_FIELD_META_KEY] = {
"ui_type": ui_type.value if isinstance(ui_type, PropertyType) else ui_type,
"display_name": display_name,
"llm_hint": llm_hint,
"required": required,
"placeholder": placeholder,
"display_options": display_options,
"options": options,
"editor": editor,
"extra": extra or {},
"spec_exclude": spec_exclude,
"min_value": min_value,
"max_value": max_value,
"min_length": min_length,
"max_length": max_length,
"pattern": pattern,
}
if spec_default is not _UNSET:
json_schema_extra[_SPEC_FIELD_META_KEY]["spec_default"] = spec_default
return Field(*field_args, json_schema_extra=json_schema_extra, **field_kwargs)
def node_spec(
*,
name: str,
display_name: str,
description: str,
category: NodeCategory,
icon: str,
llm_hint: str | None = None,
version: str = "1.0.0",
examples: list[NodeExample] | tuple[NodeExample, ...] = (),
graph_constraints: GraphConstraints | None = None,
property_order: list[str] | tuple[str, ...] = (),
field_overrides: dict[str, dict[str, Any]] | None = None,
) -> Callable[[type[BaseModel]], type[BaseModel]]:
metadata = NodeSpecMetadata(
name=name,
display_name=display_name,
description=description,
category=category,
icon=icon,
llm_hint=llm_hint,
version=version,
examples=tuple(examples),
graph_constraints=graph_constraints,
property_order=tuple(property_order),
field_overrides=field_overrides or {},
)
def decorator(model_cls: type[BaseModel]) -> type[BaseModel]:
setattr(model_cls, "__node_spec_metadata__", metadata)
return model_cls
return decorator
def build_spec(model_cls: type[BaseModel]) -> NodeSpec:
metadata: NodeSpecMetadata | None = getattr(
model_cls, "__node_spec_metadata__", None
)
if metadata is None:
raise ValueError(f"{model_cls.__name__} is missing __node_spec_metadata__")
properties: list[PropertySpec] = []
for name, field in model_cls.model_fields.items():
prop = _build_property_spec(model_cls, name, field)
if prop is not None:
properties.append(prop)
properties = _sort_properties(metadata.name, properties, metadata.property_order)
return NodeSpec(
name=metadata.name,
display_name=metadata.display_name,
description=metadata.description,
llm_hint=metadata.llm_hint,
category=metadata.category,
icon=metadata.icon,
version=metadata.version,
properties=properties,
examples=list(metadata.examples),
graph_constraints=metadata.graph_constraints,
)
def _sort_properties(
spec_name: str,
properties: list[PropertySpec],
property_order: tuple[str, ...],
) -> list[PropertySpec]:
if not property_order:
return properties
property_names = {prop.name for prop in properties}
missing = [name for name in property_order if name not in property_names]
if missing:
raise ValueError(
f"{spec_name}: property_order references unknown properties: {missing}"
)
order_map = {name: idx for idx, name in enumerate(property_order)}
ordered = sorted(
enumerate(properties),
key=lambda item: (order_map.get(item[1].name, len(order_map)), item[0]),
)
return [prop for _, prop in ordered]
def _build_property_spec(
owner_cls: type[BaseModel],
field_name: str,
field: FieldInfo,
) -> PropertySpec | None:
meta = _merged_field_meta(owner_cls, field_name, field)
if meta.get("spec_exclude"):
return None
prop_type = _resolve_property_type(field.annotation, meta)
nested_properties = _resolve_nested_properties(field.annotation, prop_type)
options = _resolve_options(field.annotation, meta, prop_type)
min_value, max_value, min_length, max_length, pattern = _resolve_constraints(
field, meta
)
description = meta.get("description") or field.description
if not description:
raise ValueError(f"{owner_cls.__name__}.{field_name} is missing a description")
return PropertySpec(
name=field_name,
type=prop_type,
display_name=meta.get("display_name") or _humanize_identifier(field_name),
description=description,
llm_hint=meta.get("llm_hint"),
default=_resolve_default(field, meta),
required=_resolve_required(field, meta),
placeholder=meta.get("placeholder"),
display_options=meta.get("display_options"),
options=options,
properties=nested_properties,
min_value=min_value,
max_value=max_value,
min_length=min_length,
max_length=max_length,
pattern=pattern,
editor=meta.get("editor"),
extra=meta.get("extra") or {},
)
def _merged_field_meta(
owner_cls: type[BaseModel],
field_name: str,
field: FieldInfo,
) -> dict[str, Any]:
field_meta = {}
if isinstance(field.json_schema_extra, dict):
field_meta = dict(field.json_schema_extra.get(_SPEC_FIELD_META_KEY, {}) or {})
metadata: NodeSpecMetadata | None = getattr(
owner_cls, "__node_spec_metadata__", None
)
override = (
dict(metadata.field_overrides.get(field_name, {}) or {})
if metadata is not None
else {}
)
merged = dict(field_meta)
merged.update(override)
return merged
def _resolve_property_type(annotation: Any, meta: dict[str, Any]) -> PropertyType:
ui_type = meta.get("ui_type")
if ui_type:
return PropertyType(ui_type)
inner = _strip_optional(annotation)
origin = get_origin(inner)
args = get_args(inner)
if origin is list:
item_type = _strip_optional(args[0]) if args else Any
if isinstance(item_type, type) and issubclass(item_type, BaseModel):
return PropertyType.fixed_collection
raise ValueError(
"List-valued fields must declare an explicit ui_type unless they wrap a "
f"BaseModel row type (field annotation: {annotation!r})."
)
if _is_enum(inner) or _is_literal(inner):
return PropertyType.options
if inner in (str,):
return PropertyType.string
if inner in (int, float):
return PropertyType.number
if inner is bool:
return PropertyType.boolean
if inner in (dict, Any) or origin is dict:
return PropertyType.json
raise ValueError(f"Unable to derive PropertyType for annotation {annotation!r}")
def _resolve_nested_properties(
annotation: Any,
prop_type: PropertyType,
) -> list[PropertySpec] | None:
if prop_type != PropertyType.fixed_collection:
return None
inner = _strip_optional(annotation)
args = get_args(inner)
if not args:
raise ValueError(
f"fixed_collection field annotation is missing row type: {annotation!r}"
)
row_type = _strip_optional(args[0])
if not isinstance(row_type, type) or not issubclass(row_type, BaseModel):
raise ValueError(
f"fixed_collection rows must be BaseModel subclasses: {annotation!r}"
)
properties: list[PropertySpec] = []
for field_name, field in row_type.model_fields.items():
prop = _build_property_spec(row_type, field_name, field)
if prop is not None:
properties.append(prop)
return properties
def _resolve_options(
annotation: Any,
meta: dict[str, Any],
prop_type: PropertyType,
) -> list[PropertyOption] | None:
if prop_type not in (PropertyType.options, PropertyType.multi_options):
return meta.get("options")
if meta.get("options"):
return meta["options"]
inner = _strip_optional(annotation)
if prop_type == PropertyType.multi_options:
inner = _strip_optional(get_args(inner)[0])
if _is_enum(inner):
return [
PropertyOption(
value=member.value, label=_humanize_option_label(member.value)
)
for member in inner
]
if _is_literal(inner):
return [
PropertyOption(value=value, label=_humanize_option_label(value))
for value in get_args(inner)
if value is not None
]
return None
def _resolve_constraints(
field: FieldInfo,
meta: dict[str, Any],
) -> tuple[float | None, float | None, int | None, int | None, str | None]:
min_value = meta.get("min_value")
max_value = meta.get("max_value")
min_length = meta.get("min_length")
max_length = meta.get("max_length")
pattern = meta.get("pattern")
for item in field.metadata:
if min_value is None:
if hasattr(item, "ge") and item.ge is not None:
min_value = item.ge
elif hasattr(item, "gt") and item.gt is not None:
min_value = item.gt
if max_value is None:
if hasattr(item, "le") and item.le is not None:
max_value = item.le
elif hasattr(item, "lt") and item.lt is not None:
max_value = item.lt
if (
min_length is None
and hasattr(item, "min_length")
and item.min_length is not None
):
min_length = item.min_length
if (
max_length is None
and hasattr(item, "max_length")
and item.max_length is not None
):
max_length = item.max_length
if pattern is None and hasattr(item, "pattern") and item.pattern is not None:
pattern = item.pattern
return min_value, max_value, min_length, max_length, pattern
def _resolve_default(field: FieldInfo, meta: dict[str, Any]) -> Any:
if "spec_default" in meta:
return meta["spec_default"]
if field.default is not PydanticUndefined:
return field.default
return None
def _resolve_required(field: FieldInfo, meta: dict[str, Any]) -> bool:
if meta.get("required") is not None:
return bool(meta["required"])
return bool(field.is_required())
def _strip_optional(annotation: Any) -> Any:
origin = get_origin(annotation)
if origin is None:
return annotation
args = [arg for arg in get_args(annotation) if arg is not NoneType]
if len(args) == 1 and len(args) != len(get_args(annotation)):
return args[0]
return annotation
def _is_enum(annotation: Any) -> bool:
return isinstance(annotation, type) and issubclass(annotation, Enum)
def _is_literal(annotation: Any) -> bool:
return get_origin(annotation) is Literal
def _humanize_identifier(name: str) -> str:
return name.replace("_", " ").strip().title()
def _humanize_option_label(value: Any) -> str:
if isinstance(value, str):
return value.replace("_", " ").replace("-", " ").strip().title()
return str(value)

203
api/services/workflow/node_specs/qa.py
View file

@ -1,203 +0,0 @@
"""Spec for the QA Analysis node — runs an LLM quality review on the call
transcript after completion."""
from api.services.workflow.node_specs._base import (
DisplayOptions,
GraphConstraints,
NodeCategory,
NodeExample,
NodeSpec,
PropertyOption,
PropertySpec,
PropertyType,
)
DEFAULT_QA_SYSTEM_PROMPT = """You are a QA analyst evaluating a specific segment of a voice AI conversation.
## Node Purpose
{{node_summary}}
## Previous Conversation Context (For start of conversation, previous conversation summary can be empty.)
{{previous_conversation_summary}}
## Tags to evaluate
Examine the conversation carefully and identify which of the following tags apply:
- UNCLEAR_CONVERSATION - The conversation is not coherent or clear, messages don't connect logically
- ASSISTANT_IN_LOOP - The assistant asks the same question multiple times or gets stuck repeating itself
- ASSISTANT_REPLY_IMPROPER - The assistant did not reply properly to the user's question/query or seems confused by what the user said
- USER_FRUSTRATED - The user seems angry, frustrated, or is complaining about something in the call
- USER_NOT_UNDERSTANDING - The user explicitly says they don't understand or repeatedly asks for clarification
- HEARING_ISSUES - Either party can't hear the other ("hello?", "are you there?", "can you hear me?")
- DEAD_AIR - Unusually long silences in the conversation (use the timestamps to judge)
- USER_REQUESTING_FEATURE - The user asks for something the assistant can't fulfill
- ASSISTANT_LACKS_EMPATHY - The assistant ignores the user's personal situation or emotional state and continues pitching or pushing the agenda.
- USER_DETECTS_AI - The user suspects or identifies that they are talking to an AI/robot/bot rather than a real human.
## Call metrics (pre-computed)
Use these alongside the transcript for your analysis:
{{metrics}}
## Output format
Return ONLY a valid JSON object (no markdown):
{
"tags": [
{
"tag": "TAG_NAME",
"reason": "Short reason with evidence from the transcript"
}
],
"overall_sentiment": "positive|neutral|negative",
"call_quality_score": <1-10>,
"summary": "1-2 sentence summary of this segment"
}
If no tags apply, return an empty tags list. Always provide sentiment, score, and summary."""
SPEC = NodeSpec(
name="qa",
display_name="QA Analysis",
description="Run LLM quality analysis on the call transcript.",
llm_hint=(
"Runs an LLM quality review on the call transcript after completion. "
"Per-node analysis splits the conversation by node and evaluates each "
"segment against the configured system prompt. Sampling, minimum "
"duration, and voicemail filters are supported."
),
category=NodeCategory.integration,
icon="ClipboardCheck",
properties=[
PropertySpec(
name="name",
type=PropertyType.string,
display_name="Name",
description="Short identifier for this QA configuration.",
required=True,
min_length=1,
default="QA Analysis",
),
PropertySpec(
name="qa_enabled",
type=PropertyType.boolean,
display_name="Enabled",
description="When false, the QA run is skipped.",
default=True,
),
PropertySpec(
name="qa_system_prompt",
type=PropertyType.string,
display_name="System Prompt",
description=(
"Instructions to the QA reviewer LLM. Supports placeholders: "
"`{node_summary}`, `{previous_conversation_summary}`, "
"`{transcript}`, `{metrics}`."
),
editor="textarea",
default=DEFAULT_QA_SYSTEM_PROMPT,
),
PropertySpec(
name="qa_min_call_duration",
type=PropertyType.number,
display_name="Minimum Call Duration (seconds)",
description="Calls shorter than this are skipped.",
default=15,
min_value=0,
),
PropertySpec(
name="qa_voicemail_calls",
type=PropertyType.boolean,
display_name="Include Voicemail Calls",
description="When false, calls flagged as voicemail are skipped.",
default=False,
),
PropertySpec(
name="qa_sample_rate",
type=PropertyType.number,
display_name="Sample Rate (%)",
description=(
"Percent of eligible calls QA'd. 100 means every call; lower "
"values use random sampling."
),
default=100,
min_value=1,
max_value=100,
),
# ---- LLM configuration ----
PropertySpec(
name="qa_use_workflow_llm",
type=PropertyType.boolean,
display_name="Use Workflow's LLM",
description=(
"When true, the QA pass uses the same LLM the workflow runs "
"with. Set false to specify a separate provider/model."
),
default=True,
),
PropertySpec(
name="qa_provider",
type=PropertyType.options,
display_name="QA LLM Provider",
description="LLM provider used for the QA pass.",
display_options=DisplayOptions(show={"qa_use_workflow_llm": [False]}),
options=[
PropertyOption(value="openai", label="OpenAI"),
PropertyOption(value="azure", label="Azure OpenAI"),
PropertyOption(value="openrouter", label="OpenRouter"),
PropertyOption(value="anthropic", label="Anthropic"),
],
),
PropertySpec(
name="qa_model",
type=PropertyType.string,
display_name="QA Model",
description=(
"Model identifier (e.g., 'gpt-4o', 'claude-sonnet-4-6'). "
"Provider-specific."
),
display_options=DisplayOptions(show={"qa_use_workflow_llm": [False]}),
default="default",
),
PropertySpec(
name="qa_api_key",
type=PropertyType.string,
display_name="API Key",
description="API key for the chosen provider.",
display_options=DisplayOptions(show={"qa_use_workflow_llm": [False]}),
),
PropertySpec(
name="qa_endpoint",
type=PropertyType.url,
display_name="Azure Endpoint",
description="Required for the Azure provider.",
display_options=DisplayOptions(
show={"qa_use_workflow_llm": [False], "qa_provider": ["azure"]}
),
),
],
examples=[
NodeExample(
name="basic_qa",
data={
"name": "Compliance Check",
"qa_enabled": True,
"qa_system_prompt": (
"You are a compliance reviewer. Review the transcript and "
"produce a JSON object with `tags`, `summary`, "
"`call_quality_score`, and `overall_sentiment`."
),
"qa_min_call_duration": 30,
"qa_sample_rate": 100,
},
),
],
# QA runs post-call against the saved transcript (run_integrations
# scans by type), never as a graph step. Reject any edge into or out
# of a QA node.
graph_constraints=GraphConstraints(
min_incoming=0, max_incoming=0, min_outgoing=0, max_outgoing=0
),
)

250
api/services/workflow/node_specs/start_call.py
View file

@ -1,250 +0,0 @@
"""Spec for the Start Call node — the single entry point of every workflow.
Carries greeting, pre-call data fetch, and the same prompt/extraction/tools
fields as agent nodes."""
from api.services.workflow.node_specs._base import (
DisplayOptions,
GraphConstraints,
NodeCategory,
NodeExample,
NodeSpec,
PropertyOption,
PropertySpec,
PropertyType,
)
SPEC = NodeSpec(
name="startCall",
display_name="Start Call",
description="Entry point of the workflow — plays a greeting and opens the conversation.",
llm_hint=(
"The entry point of every workflow (exactly one required). Plays an "
"optional greeting, can fetch context from an external API before "
"the call begins, and executes the first conversational turn."
),
category=NodeCategory.call_node,
icon="Play",
properties=[
PropertySpec(
name="name",
type=PropertyType.string,
display_name="Name",
description="Short identifier shown in the canvas and call logs.",
required=True,
min_length=1,
default="Start Call",
),
# ---- Greeting (variant via greeting_type) ----
PropertySpec(
name="greeting_type",
type=PropertyType.options,
display_name="Greeting Type",
description=(
"Whether the optional greeting is spoken via TTS from text "
"or played from a pre-recorded audio file."
),
default="text",
options=[
PropertyOption(value="text", label="Text (TTS)"),
PropertyOption(value="audio", label="Pre-recorded Audio"),
],
),
PropertySpec(
name="greeting",
type=PropertyType.string,
display_name="Greeting Text",
description=(
"Text spoken via TTS at the start of the call. Supports "
"{{template_variables}}. Leave empty to skip the greeting."
),
display_options=DisplayOptions(show={"greeting_type": ["text"]}),
editor="textarea",
placeholder="Hi {{first_name}}, this is Sarah from Acme.",
),
PropertySpec(
name="greeting_recording_id",
type=PropertyType.recording_ref,
display_name="Greeting Recording",
description="Pre-recorded audio file played at the start of the call.",
llm_hint=(
"Value is the `recording_id` string. Use the `list_recordings` "
"MCP tool to discover available recordings."
),
display_options=DisplayOptions(show={"greeting_type": ["audio"]}),
),
PropertySpec(
name="prompt",
type=PropertyType.mention_textarea,
display_name="Prompt",
description=(
"Agent system prompt for the opening turn. Supports "
"{{template_variables}} from pre-call fetch and the initial context."
),
required=True,
min_length=1,
placeholder="Greet the caller warmly and ask how you can help today.",
),
# ---- Behavior toggles ----
PropertySpec(
name="allow_interrupt",
type=PropertyType.boolean,
display_name="Allow Interruption",
description=("When true, the user can interrupt the agent mid-utterance."),
default=False,
),
PropertySpec(
name="add_global_prompt",
type=PropertyType.boolean,
display_name="Add Global Prompt",
description=(
"When true and a Global node exists, prepends the global "
"prompt to this node's prompt at runtime."
),
default=True,
),
PropertySpec(
name="delayed_start",
type=PropertyType.boolean,
display_name="Delayed Start",
description=(
"When true, the agent waits before speaking after pickup. "
"Useful for outbound calls where the called party needs a "
"moment to settle."
),
default=False,
),
PropertySpec(
name="delayed_start_duration",
type=PropertyType.number,
display_name="Delay Duration (seconds)",
description="Seconds to wait before the agent speaks. 0.1–10.",
default=2.0,
min_value=0.1,
max_value=10.0,
display_options=DisplayOptions(show={"delayed_start": [True]}),
),
# ---- Variable extraction ----
PropertySpec(
name="extraction_enabled",
type=PropertyType.boolean,
display_name="Enable Variable Extraction",
description=(
"When true, runs an LLM extraction pass on transition out of "
"this node to capture variables from the opening turn."
),
default=False,
),
PropertySpec(
name="extraction_prompt",
type=PropertyType.string,
display_name="Extraction Prompt",
description="Overall instructions guiding variable extraction.",
display_options=DisplayOptions(show={"extraction_enabled": [True]}),
editor="textarea",
),
PropertySpec(
name="extraction_variables",
type=PropertyType.fixed_collection,
display_name="Variables to Extract",
description=(
"Each entry declares one variable to capture, with its name, "
"data type, and per-variable extraction hint."
),
display_options=DisplayOptions(show={"extraction_enabled": [True]}),
properties=[
PropertySpec(
name="name",
type=PropertyType.string,
display_name="Variable Name",
description="snake_case identifier used downstream.",
required=True,
),
PropertySpec(
name="type",
type=PropertyType.options,
display_name="Type",
description="Data type of the extracted value.",
required=True,
default="string",
options=[
PropertyOption(value="string", label="String"),
PropertyOption(value="number", label="Number"),
PropertyOption(value="boolean", label="Boolean"),
],
),
PropertySpec(
name="prompt",
type=PropertyType.string,
display_name="Extraction Hint",
description="Per-variable hint describing what to look for.",
editor="textarea",
),
],
),
# ---- Tools / documents ----
PropertySpec(
name="tool_uuids",
type=PropertyType.tool_refs,
display_name="Tools",
description="Tools the agent can invoke during the opening turn.",
llm_hint="List of tool UUIDs from `list_tools`.",
),
PropertySpec(
name="document_uuids",
type=PropertyType.document_refs,
display_name="Knowledge Base Documents",
description="Documents the agent can reference.",
llm_hint="List of document UUIDs from `list_documents`.",
),
# ---- Pre-call data fetch (advanced) ----
PropertySpec(
name="pre_call_fetch_enabled",
type=PropertyType.boolean,
display_name="Pre-Call Data Fetch",
description=(
"When true, makes a POST request to an external API before "
"the call starts and merges the JSON response into the call "
"context as template variables."
),
default=False,
),
PropertySpec(
name="pre_call_fetch_url",
type=PropertyType.url,
display_name="Endpoint URL",
description=(
"URL the pre-call POST request is sent to. The request body "
"includes caller and called numbers."
),
display_options=DisplayOptions(show={"pre_call_fetch_enabled": [True]}),
placeholder="https://api.example.com/customer-lookup",
),
PropertySpec(
name="pre_call_fetch_credential_uuid",
type=PropertyType.credential_ref,
display_name="Authentication",
description="Optional credential attached to the pre-call request.",
llm_hint="Credential UUID from `list_credentials`.",
display_options=DisplayOptions(show={"pre_call_fetch_enabled": [True]}),
),
],
examples=[
NodeExample(
name="warm_greeting",
data={
"name": "Greeting",
"prompt": "Greet warmly and ask the caller's reason for calling.",
"greeting_type": "text",
"greeting": "Hi {{first_name}}, this is Sarah from Acme.",
"allow_interrupt": True,
},
),
],
# `min_outgoing` is intentionally unset: a startCall is allowed to
# sit on the canvas without an outgoing edge (e.g. a workflow with
# just a greeting). Only constraint: nothing flows INTO the start.
graph_constraints=GraphConstraints(
min_incoming=0,
max_incoming=0,
),
)

79
api/services/workflow/node_specs/trigger.py
View file

@ -1,79 +0,0 @@
"""Spec for the API Trigger node — exposes a public webhook URL that
external systems can hit to launch the workflow."""
from api.services.workflow.node_specs._base import (
GraphConstraints,
NodeCategory,
NodeExample,
NodeSpec,
PropertySpec,
PropertyType,
)
SPEC = NodeSpec(
name="trigger",
display_name="API Trigger",
description=("Public HTTP endpoints that launch the workflow."),
llm_hint=(
"Exposes two public HTTP POST endpoints derived from the auto-generated "
"`trigger_path`:\n"
" • Production: `<backend>/api/v1/public/agent/<trigger_path>` — runs "
"the published agent. Use this from production systems.\n"
" • Test: `<backend>/api/v1/public/agent/test/<trigger_path>` — runs "
"the latest draft, useful for verifying changes before publishing. "
"Falls back to the published agent when no draft exists.\n"
"Both require an API key in the `X-API-Key` header.\n"
"Request body fields:\n"
" • `phone_number` (string, required) — destination to dial.\n"
" • `initial_context` (object, optional) — merged into the run's "
"initial context.\n"
" • `telephony_configuration_id` (int, optional) — pick a specific "
"telephony configuration for the call. Must belong to the same "
"organization as the trigger. When omitted, the org's default "
"outbound configuration is used."
),
category=NodeCategory.trigger,
icon="Webhook",
properties=[
PropertySpec(
name="name",
type=PropertyType.string,
display_name="Name",
description="Short identifier shown in the canvas. No runtime effect.",
required=True,
min_length=1,
default="API Trigger",
),
PropertySpec(
name="enabled",
type=PropertyType.boolean,
display_name="Enabled",
description="When false, the trigger URL returns 404.",
default=True,
),
PropertySpec(
name="trigger_path",
type=PropertyType.string,
display_name="Trigger Path",
description=(
"Auto-generated UUID-style path segment that uniquely "
"identifies this trigger. Used in both URLs:\n"
" • Production: `/api/v1/public/agent/<trigger_path>` — "
"executes the published agent.\n"
" • Test: `/api/v1/public/agent/test/<trigger_path>` — "
"executes the latest draft.\n"
"Do not edit manually."
),
),
],
examples=[
NodeExample(
name="default",
data={"name": "Inbound Trigger", "enabled": True},
),
],
graph_constraints=GraphConstraints(
min_incoming=0,
max_incoming=0,
),
)

133
api/services/workflow/node_specs/webhook.py
View file

@ -1,133 +0,0 @@
"""Spec for the Webhook node — sends an HTTP request to an external system
after the workflow completes."""
from api.services.workflow.node_specs._base import (
GraphConstraints,
NodeCategory,
NodeExample,
NodeSpec,
PropertyOption,
PropertySpec,
PropertyType,
)
SPEC = NodeSpec(
name="webhook",
display_name="Webhook",
description="Send HTTP request after the workflow completes.",
llm_hint=(
"Sends an HTTP request to an external system after the workflow "
"completes. The payload is a Jinja-templated JSON body with access "
"to `workflow_run_id`, `initial_context`, `gathered_context`, "
"`annotations`, and call metadata."
),
category=NodeCategory.integration,
icon="Link2",
properties=[
PropertySpec(
name="name",
type=PropertyType.string,
display_name="Name",
description="Short identifier shown in the canvas and run logs.",
required=True,
min_length=1,
default="Webhook",
),
PropertySpec(
name="enabled",
type=PropertyType.boolean,
display_name="Enabled",
description="When false, the webhook is skipped at run time.",
default=True,
),
PropertySpec(
name="http_method",
type=PropertyType.options,
display_name="HTTP Method",
description="HTTP verb used for the outbound request.",
default="POST",
options=[
PropertyOption(value="GET", label="GET"),
PropertyOption(value="POST", label="POST"),
PropertyOption(value="PUT", label="PUT"),
PropertyOption(value="PATCH", label="PATCH"),
PropertyOption(value="DELETE", label="DELETE"),
],
),
PropertySpec(
name="endpoint_url",
type=PropertyType.url,
display_name="Endpoint URL",
description="URL the request is sent to.",
placeholder="https://api.example.com/webhook",
),
PropertySpec(
name="credential_uuid",
type=PropertyType.credential_ref,
display_name="Authentication",
description="Optional credential applied as the Authorization header.",
llm_hint="Credential UUID from `list_credentials`.",
),
PropertySpec(
name="custom_headers",
type=PropertyType.fixed_collection,
display_name="Custom Headers",
description="Additional HTTP headers to include with the request.",
properties=[
PropertySpec(
name="key",
type=PropertyType.string,
display_name="Header Name",
description="HTTP header name (e.g., 'X-Source').",
required=True,
),
PropertySpec(
name="value",
type=PropertyType.string,
display_name="Header Value",
description="Header value (supports {{template_variables}}).",
required=True,
),
],
),
PropertySpec(
name="payload_template",
type=PropertyType.json,
display_name="Payload Template",
description=(
"JSON body of the request. Values are Jinja-rendered against "
"the run context — `{{workflow_run_id}}`, "
"`{{gathered_context.foo}}`, `{{annotations.qa_xxx}}`, etc."
),
default={
"call_id": "{{workflow_run_id}}",
"first_name": "{{initial_context.first_name}}",
"rsvp": "{{gathered_context.rsvp}}",
"duration": "{{cost_info.call_duration_seconds}}",
"recording_url": "{{recording_url}}",
"transcript_url": "{{transcript_url}}",
},
),
],
examples=[
NodeExample(
name="post_to_crm",
data={
"name": "Notify CRM",
"enabled": True,
"http_method": "POST",
"endpoint_url": "https://crm.example.com/calls",
"payload_template": {
"run_id": "{{workflow_run_id}}",
"outcome": "{{gathered_context.call_disposition}}",
},
},
),
],
# Webhooks fire post-call (run_integrations scans nodes by type),
# never as a graph step. Reject any edge into or out of a webhook so
# the editor can't wire one into the conversation flow.
graph_constraints=GraphConstraints(
min_incoming=0, max_incoming=0, min_outgoing=0, max_outgoing=0
),
)

23
api/services/workflow/pipecat_engine.py
View file

@ -540,7 +540,7 @@ class PipecatEngine:
node = self.workflow.nodes[node_id]
logger.debug(
f"Executing node: name: {node.name} is_static: {node.is_static} allow_interrupt: {node.allow_interrupt} is_end: {node.is_end}"
f"Executing node: name: {node.name} allow_interrupt: {node.allow_interrupt} is_end: {node.is_end}"
)
# Track previous node for transition event
@ -595,11 +595,8 @@ class PipecatEngine:
)
await asyncio.sleep(delay_duration)
if node.is_static:
raise ValueError("Static nodes are not supported!")
else:
# Setup LLM Context with Prompts and Functions
await self._setup_llm_context(node)
# Setup LLM context with prompts and functions.
await self._setup_llm_context(node)
def get_start_greeting(self) -> Optional[tuple[str, Optional[str]]]:
"""Return the greeting info for the start node, or None if not configured.
@ -626,19 +623,13 @@ class PipecatEngine:
async def _handle_end_node(self, node: Node) -> None:
"""Handle end node execution."""
if node.is_static:
raise ValueError("Static nodes are not supported!")
else:
# Setup LLM Context with Prompts and Functions
await self._setup_llm_context(node)
# Setup LLM context with prompts and functions.
await self._setup_llm_context(node)
async def _handle_agent_node(self, node: Node) -> None:
"""Handle agent node execution."""
if node.is_static:
raise ValueError("Static nodes are not supported!")
else:
# Setup LLM Context with Prompts and Functions
await self._setup_llm_context(node)
# Setup LLM context with prompts and functions.
await self._setup_llm_context(node)
async def end_call_with_reason(
self,

23
api/services/workflow/workflow_graph.py
View file

@ -1,10 +1,11 @@
import re
from collections import Counter
from typing import Dict, List, Set
from typing import Any, Dict, List, Set
from api.services.workflow.dto import EdgeDataDTO, NodeType, ReactFlowDTO
from api.services.workflow.errors import ItemKind, WorkflowError
from api.services.workflow.node_specs import REGISTRY
from api.services.workflow.node_data import BaseNodeData
from api.services.workflow.node_specs import get_spec
# Regex for matching {{ variable }} template placeholders.
# Captures: group(1) = variable path, group(2) = filter name, group(3) = filter value.
@ -62,7 +63,7 @@ class Edge:
class Node:
def __init__(self, id: str, node_type: NodeType, data):
def __init__(self, id: str, node_type: str, data: BaseNodeData):
self.id, self.node_type, self.data = id, node_type, data
self.out: Dict[str, "Node"] = {} # forward nodes
self.out_edges: List[Edge] = [] # forward edges with properties
@ -75,7 +76,6 @@ class Node:
# Type-specific fields — read with getattr so this works for every
# node variant in the discriminated union.
self.prompt = getattr(data, "prompt", None)
self.is_static = getattr(data, "is_static", False)
self.allow_interrupt = getattr(data, "allow_interrupt", False)
self.extraction_enabled = getattr(data, "extraction_enabled", False)
self.extraction_prompt = getattr(data, "extraction_prompt", None)
@ -84,7 +84,6 @@ class Node:
self.greeting = getattr(data, "greeting", None)
self.greeting_type = getattr(data, "greeting_type", None)
self.greeting_recording_id = getattr(data, "greeting_recording_id", None)
self.detect_voicemail = getattr(data, "detect_voicemail", False)
self.delayed_start = getattr(data, "delayed_start", False)
self.delayed_start_duration = getattr(data, "delayed_start_duration", None)
self.tool_uuids = getattr(data, "tool_uuids", None)
@ -106,11 +105,11 @@ class WorkflowGraph:
"""
def __init__(self, dto: ReactFlowDTO):
# build adjacency list. n.type comes off the discriminated-union
# variant as a literal string; coerce to NodeType for downstream
# comparisons.
# Build adjacency list from validated DTO nodes. Core node comparisons
# still use NodeType string enums; integration nodes remain plain
# strings and resolve constraints through node specs.
self.nodes: Dict[str, Node] = {
n.id: Node(n.id, NodeType(n.type), n.data) for n in dto.nodes
n.id: Node(n.id, n.type, n.data) for n in dto.nodes
}
# Store all edges
@ -140,7 +139,7 @@ class WorkflowGraph:
# Get a reference to the global node
try:
self.global_node_id = [
n.id for n in dto.nodes if n.type == NodeType.globalNode
n.id for n in dto.nodes if n.type == NodeType.globalNode.value
][0]
except IndexError:
self.global_node_id = None
@ -250,7 +249,7 @@ class WorkflowGraph:
def _assert_global_node(self):
errors: list[WorkflowError] = []
global_node = [
n for n in self.nodes.values() if n.node_type == NodeType.globalNode
n for n in self.nodes.values() if n.node_type == NodeType.globalNode.value
]
if not len(global_node) <= 1:
errors.append(
@ -282,7 +281,7 @@ class WorkflowGraph:
in_deg[m.id] += 1
for n in self.nodes.values():
spec = REGISTRY.get(n.node_type.value)
spec = get_spec(n.node_type)
if spec is None or spec.graph_constraints is None:
continue
gc = spec.graph_constraints

2
api/tasks/campaign_tasks.py
View file

@ -20,7 +20,7 @@ async def sync_campaign_source(ctx: Dict, campaign_id: int) -> None:
Phase 1: Syncs data from configured source to queued_runs table
- Campaign state should already be 'syncing'
- Determines source type from campaign configuration
- Fetches data via appropriate sync service (Google Sheets, HubSpot, etc.)
- Fetches data via the appropriate sync service
- Creates queued_run entries with unique source_uuid
- Updates campaign total_rows
- Transitions campaign state to 'running' on success

46
api/tasks/run_integrations.py
View file

@ -1,7 +1,6 @@
"""Execute integrations (QA analysis, webhooks) after workflow run completion."""
import random
from datetime import UTC, datetime
from typing import Any, Dict, Optional
import httpx
@ -14,6 +13,11 @@ from api.constants import BACKEND_API_ENDPOINT
from api.db import db_client
from api.db.models import WorkflowRunModel
from api.enums import OrganizationConfigurationKey
from api.services.integrations import (
IntegrationCompletionContext,
has_completion_handlers,
run_completion_handlers,
)
from api.services.pipecat.tracing_config import register_org_langfuse_credentials
from api.services.workflow.dto import (
QANodeData,
@ -214,16 +218,20 @@ async def run_integrations_post_workflow_run(_ctx, workflow_run_id: int):
nodes = workflow_definition.get("nodes", [])
qa_nodes = [n for n in nodes if n.get("type") == "qa"]
webhook_nodes = [n for n in nodes if n.get("type") == "webhook"]
has_registered_integrations = has_completion_handlers(workflow_definition)
# Step 4: Generate public access token if webhooks exist or campaign_id is set
# Step 4: Generate a public access token for any run that needs post-call work.
has_campaign = workflow_run.campaign_id is not None
if not webhook_nodes and not qa_nodes and not has_campaign:
if (
not webhook_nodes
and not qa_nodes
and not has_registered_integrations
and not has_campaign
):
logger.debug("No integration nodes and no campaign, skipping")
return
public_token = None
if webhook_nodes or has_campaign:
public_token = await db_client.ensure_public_access_token(workflow_run_id)
public_token = await db_client.ensure_public_access_token(workflow_run_id)
# Step 5: Run QA analysis before webhooks
if qa_nodes:
@ -263,17 +271,37 @@ async def run_integrations_post_workflow_run(_ctx, workflow_run_id: int):
workflow_run_id
)
# Step 6: Execute webhooks
# Step 6: Run registered third-party integrations after uploads are complete
integration_results = await run_completion_handlers(
context=IntegrationCompletionContext(
workflow_run_id=workflow_run_id,
workflow_run=workflow_run,
workflow_definition=workflow_definition,
definition_id=definition_id,
organization_id=organization_id,
public_token=public_token,
)
)
if integration_results:
await db_client.update_workflow_run(
workflow_run_id, annotations=integration_results
)
workflow_run, _ = await db_client.get_workflow_run_with_context(
workflow_run_id
)
# Step 7: Execute webhooks
if not webhook_nodes:
logger.debug("No webhook nodes in workflow")
return
logger.info(f"Found {len(webhook_nodes)} webhook nodes to execute")
# Step 7: Build render context (includes annotations from QA)
# Step 8: Build render context (includes annotations from QA and integrations)
render_context = _build_render_context(workflow_run, public_token)
# Step 8: Execute each webhook node
# Step 9: Execute each webhook node
for node in webhook_nodes:
node_id = node.get("id", "unknown")
try:

37
api/tests/conftest.py
View file

@ -15,16 +15,14 @@ import pytest
from api.services.workflow.dto import (
AgentNodeData,
AgentRFNode,
EdgeDataDTO,
EndCallNodeData,
EndCallRFNode,
ExtractionVariableDTO,
Position,
ReactFlowDTO,
RFEdgeDTO,
RFNodeDTO,
StartCallNodeData,
StartCallRFNode,
VariableType,
)
from api.services.workflow.workflow_graph import WorkflowGraph
@ -270,8 +268,9 @@ def simple_workflow() -> WorkflowGraph:
"""
dto = ReactFlowDTO(
nodes=[
StartCallRFNode(
RFNodeDTO(
id="start",
type="startCall",
position=Position(x=0, y=0),
data=StartCallNodeData(
name="Start Call",
@ -290,8 +289,9 @@ def simple_workflow() -> WorkflowGraph:
],
),
),
EndCallRFNode(
RFNodeDTO(
id="end",
type="endCall",
position=Position(x=0, y=200),
data=EndCallNodeData(
name="End Call",
@ -333,8 +333,9 @@ def three_node_workflow() -> WorkflowGraph:
"""
dto = ReactFlowDTO(
nodes=[
StartCallRFNode(
RFNodeDTO(
id="start",
type="startCall",
position=Position(x=0, y=0),
data=StartCallNodeData(
name="Start Call",
@ -353,8 +354,9 @@ def three_node_workflow() -> WorkflowGraph:
],
),
),
AgentRFNode(
RFNodeDTO(
id="agent",
type="agentNode",
position=Position(x=0, y=200),
data=AgentNodeData(
name="Collect Info",
@ -372,8 +374,9 @@ def three_node_workflow() -> WorkflowGraph:
],
),
),
EndCallRFNode(
RFNodeDTO(
id="end",
type="endCall",
position=Position(x=0, y=400),
data=EndCallNodeData(
name="End Call",
@ -424,8 +427,9 @@ def three_node_workflow_extraction_start_only() -> WorkflowGraph:
"""
dto = ReactFlowDTO(
nodes=[
StartCallRFNode(
RFNodeDTO(
id="start",
type="startCall",
position=Position(x=0, y=0),
data=StartCallNodeData(
name="Start Call",
@ -444,8 +448,9 @@ def three_node_workflow_extraction_start_only() -> WorkflowGraph:
],
),
),
AgentRFNode(
RFNodeDTO(
id="agent",
type="agentNode",
position=Position(x=0, y=200),
data=AgentNodeData(
name="Collect Info",
@ -455,8 +460,9 @@ def three_node_workflow_extraction_start_only() -> WorkflowGraph:
extraction_enabled=False, # Explicitly disabled for testing
),
),
EndCallRFNode(
RFNodeDTO(
id="end",
type="endCall",
position=Position(x=0, y=400),
data=EndCallNodeData(
name="End Call",
@ -503,8 +509,9 @@ def three_node_workflow_no_variable_extraction() -> WorkflowGraph:
"""
dto = ReactFlowDTO(
nodes=[
StartCallRFNode(
RFNodeDTO(
id="start",
type="startCall",
position=Position(x=0, y=0),
data=StartCallNodeData(
name="Start Call",
@ -515,8 +522,9 @@ def three_node_workflow_no_variable_extraction() -> WorkflowGraph:
extraction_enabled=False,
),
),
AgentRFNode(
RFNodeDTO(
id="agent",
type="agentNode",
position=Position(x=0, y=200),
data=AgentNodeData(
name="Collect Info",
@ -526,8 +534,9 @@ def three_node_workflow_no_variable_extraction() -> WorkflowGraph:
extraction_enabled=False, # Explicitly disabled for testing
),
),
EndCallRFNode(
RFNodeDTO(
id="end",
type="endCall",
position=Position(x=0, y=400),
data=EndCallNodeData(
name="End Call",

4
api/tests/dto_fixtures/sample_branching_workflow.json
View file

@ -63,7 +63,6 @@
},
"data": {
"prompt": "Hello, I am Abhishek from Dograh. ",
"is_static": true,
"name": "Start Call",
"is_start": true
},
@ -83,7 +82,6 @@
},
"data": {
"prompt": "Thank you for calling Dograh. Have a great day!",
"is_static": true,
"name": "End Call"
},
"measured": {
@ -161,4 +159,4 @@
"y": 0,
"zoom": 1
}
}
}

11
api/tests/test_dograh_sdk_typed.py
View file

@ -19,6 +19,7 @@ from dograh_sdk.typed import (
Qa,
StartCall,
Trigger,
Tuner,
TypedNode,
Webhook,
)
@ -50,6 +51,7 @@ def client() -> _StubClient:
(Trigger, "trigger"),
(Webhook, "webhook"),
(Qa, "qa"),
(Tuner, "tuner"),
],
ids=lambda v: v.__name__ if isinstance(v, type) else v,
)
@ -68,8 +70,15 @@ def test_typed_class_declares_spec_name(cls: type[TypedNode], expected_type: str
inst = cls(name="t")
elif cls is Webhook:
inst = cls(name="wh")
else: # Qa
elif cls is Qa:
inst = cls(name="qa")
else: # Tuner
inst = cls(
name="tuner",
tuner_agent_id="agent",
tuner_workspace_id=1,
tuner_api_key="secret",
)
assert inst.type == expected_type

31
api/tests/test_dto.py
View file

@ -16,6 +16,37 @@ async def test_dto():
assert dto is not None
def test_dto_ignores_legacy_unknown_node_data_fields():
dto = ReactFlowDTO.model_validate(
{
"nodes": [
{
"id": "n1",
"type": "startCall",
"position": {"x": 0, "y": 0},
"data": {
"name": "Start",
"prompt": "Hello",
"is_static": True,
"detect_voicemail": True,
"wait_for_user_response": False,
"wait_for_user_response_timeout": 2.5,
"legacy_field": "ignored",
},
}
],
"edges": [],
}
)
data = dto.nodes[0].data.model_dump()
assert "is_static" not in data
assert "detect_voicemail" not in data
assert "wait_for_user_response" not in data
assert "wait_for_user_response_timeout" not in data
assert "legacy_field" not in data
def test_sanitize_strips_ui_runtime_fields():
definition = {
"viewport": {"x": 0, "y": 0, "zoom": 1},

237
api/tests/test_node_specs.py
View file

@ -14,7 +14,12 @@ import re
import pytest
from api.services.workflow.dto import NodeType, ReactFlowDTO
from api.services.workflow.dto import (
ReactFlowDTO,
all_node_type_names,
get_node_data_model,
)
from api.services.workflow.node_data import BaseNodeData
from api.services.workflow.node_specs import (
NodeSpec,
PropertySpec,
@ -118,9 +123,9 @@ def test_fixed_collection_has_sub_properties(spec: NodeSpec):
@pytest.mark.parametrize("spec", all_specs(), ids=lambda s: s.name)
def test_spec_name_matches_dto_discriminator(spec: NodeSpec):
valid_names = {t.value for t in NodeType}
valid_names = all_node_type_names()
assert spec.name in valid_names, (
f"NodeSpec {spec.name!r} doesn't match any NodeType discriminator. "
f"NodeSpec {spec.name!r} doesn't match any registered node type. "
f"Valid: {sorted(valid_names)}"
)
@ -187,10 +192,226 @@ def test_examples_validate_against_dto(spec: NodeSpec):
def test_all_dto_types_have_specs():
"""Every NodeType discriminator value must have a registered NodeSpec —
catches the case where someone adds a new node type to dto.py but
forgets to author a spec."""
"""Every registered node type must have a registered NodeSpec."""
spec_names = {s.name for s in all_specs()}
type_values = {t.value for t in NodeType}
type_values = all_node_type_names()
missing = type_values - spec_names
assert not missing, f"NodeType discriminators without specs: {sorted(missing)}"
assert not missing, f"Registered node types without specs: {sorted(missing)}"
def test_all_registered_node_models_inherit_base_node_data():
for type_name in sorted(all_node_type_names()):
data_model = get_node_data_model(type_name)
assert data_model is not None, f"{type_name}: missing node data model"
assert issubclass(data_model, BaseNodeData), (
f"{type_name}: node data model must inherit BaseNodeData"
)
@pytest.mark.parametrize(
("spec_name", "expected_order"),
[
(
"startCall",
[
"name",
"greeting_type",
"greeting",
"greeting_recording_id",
"prompt",
"allow_interrupt",
"add_global_prompt",
"delayed_start",
"delayed_start_duration",
"extraction_enabled",
"extraction_prompt",
"extraction_variables",
"tool_uuids",
"document_uuids",
"pre_call_fetch_enabled",
"pre_call_fetch_url",
"pre_call_fetch_credential_uuid",
],
),
(
"agentNode",
[
"name",
"prompt",
"allow_interrupt",
"add_global_prompt",
"extraction_enabled",
"extraction_prompt",
"extraction_variables",
"tool_uuids",
"document_uuids",
],
),
(
"endCall",
[
"name",
"prompt",
"add_global_prompt",
"extraction_enabled",
"extraction_prompt",
"extraction_variables",
],
),
("globalNode", ["name", "prompt"]),
("trigger", ["name", "enabled", "trigger_path"]),
(
"webhook",
[
"name",
"enabled",
"http_method",
"endpoint_url",
"credential_uuid",
"custom_headers",
"payload_template",
],
),
(
"qa",
[
"name",
"qa_enabled",
"qa_system_prompt",
"qa_min_call_duration",
"qa_voicemail_calls",
"qa_sample_rate",
"qa_use_workflow_llm",
"qa_provider",
"qa_model",
"qa_api_key",
"qa_endpoint",
],
),
(
"tuner",
[
"name",
"tuner_enabled",
"tuner_agent_id",
"tuner_workspace_id",
"tuner_api_key",
],
),
],
)
def test_node_spec_property_order_stable(spec_name: str, expected_order: list[str]):
spec = next(spec for spec in all_specs() if spec.name == spec_name)
assert [prop.name for prop in spec.properties] == expected_order
# ─────────────────────────────────────────────────────────────────────────
# `to_mcp_dict` projection — the lean view served by the `get_node_type`
# MCP tool. UI-only metadata is dropped so it doesn't poison LLM context;
# the full spec stays available to the frontend and SDK via other paths.
# ─────────────────────────────────────────────────────────────────────────
# Keys that are UI-rendering concerns and must never reach the LLM view, at
# either the node or property level.
_UI_ONLY_KEYS = frozenset(
{
"display_name",
"icon",
"category",
"version",
"placeholder",
"display_options",
"editor",
"extra",
"label", # PropertyOption display string
}
)
def _walk_dicts(node):
"""Yield every dict nested anywhere inside a projected structure."""
if isinstance(node, dict):
yield node
for value in node.values():
yield from _walk_dicts(value)
elif isinstance(node, list):
for item in node:
yield from _walk_dicts(item)
@pytest.mark.parametrize("spec", all_specs(), ids=lambda s: s.name)
def test_to_mcp_dict_drops_ui_only_keys(spec: NodeSpec):
projected = spec.to_mcp_dict()
for d in _walk_dicts(projected):
leaked = _UI_ONLY_KEYS & d.keys()
assert not leaked, f"{spec.name}: UI-only keys leaked into LLM view: {leaked}"
@pytest.mark.parametrize("spec", all_specs(), ids=lambda s: s.name)
def test_to_mcp_dict_omits_null_and_empty(spec: NodeSpec):
"""The lean view never emits null values — absent means unset/optional,
which is what halves the noise versus the full model dump."""
for d in _walk_dicts(spec.to_mcp_dict()):
for key, value in d.items():
assert value is not None, f"{spec.name}: {key!r} emitted as null"
@pytest.mark.parametrize("spec", all_specs(), ids=lambda s: s.name)
def test_to_mcp_dict_keeps_property_essentials(spec: NodeSpec):
"""Every property in the LLM view carries the minimum an LLM needs to
author a value: machine name, type, and a description."""
def _check(props: list[dict]):
for prop in props:
assert prop.get("name"), f"{spec.name}: property missing name"
assert prop.get("type"), f"{spec.name}.{prop.get('name')}: missing type"
assert prop.get("description"), (
f"{spec.name}.{prop.get('name')}: missing description"
)
if prop.get("properties"):
_check(prop["properties"])
_check(spec.to_mcp_dict()["properties"])
def test_to_mcp_dict_retains_authoring_signal_startcall():
"""startCall is the richest core node — lock in that the projection
keeps the fields an LLM actually authors against while shedding the rest."""
spec = next(s for s in all_specs() if s.name == "startCall")
projected = spec.to_mcp_dict()
assert set(projected) == {
"name",
"description",
"llm_hint",
"properties",
"examples",
"graph_constraints",
}
props = {p["name"]: p for p in projected["properties"]}
# Required field keeps `required`; optional fields omit it.
assert props["prompt"]["required"] is True
assert "required" not in props["greeting"]
# Enum options project to bare values, dropping the UI label.
assert props["greeting_type"]["options"] == [{"value": "text"}, {"value": "audio"}]
# Validation bounds survive (they constrain valid authored values).
assert props["delayed_start_duration"]["min_value"] == 0.1
assert props["delayed_start_duration"]["max_value"] == 10.0
# llm_hint survives where present (catalog-tool references).
assert "list_recordings" in props["greeting_recording_id"]["llm_hint"]
# fixed_collection rows recurse through the same projection.
var_rows = {p["name"]: p for p in props["extraction_variables"]["properties"]}
assert var_rows["type"]["options"] == [
{"value": "string"},
{"value": "number"},
{"value": "boolean"},
]
# graph_constraints drops its null sub-fields.
assert projected["graph_constraints"] == {"min_incoming": 0, "max_incoming": 0}

9
api/tests/test_pipecat_engine_end_call.py
View file

@ -45,12 +45,11 @@ from api.enums import ToolCategory
from api.services.workflow.dto import (
EdgeDataDTO,
EndCallNodeData,
EndCallRFNode,
Position,
ReactFlowDTO,
RFEdgeDTO,
RFNodeDTO,
StartCallNodeData,
StartCallRFNode,
)
from api.services.workflow.pipecat_engine import PipecatEngine
from api.services.workflow.pipecat_engine_custom_tools import CustomToolManager
@ -1014,8 +1013,9 @@ class TestEndCallExtractionBehavior:
# Create a workflow where start node has NO extraction
dto = ReactFlowDTO(
nodes=[
StartCallRFNode(
RFNodeDTO(
id="start",
type="startCall",
position=Position(x=0, y=0),
data=StartCallNodeData(
name="Start Call",
@ -1026,8 +1026,9 @@ class TestEndCallExtractionBehavior:
extraction_enabled=False, # No extraction
),
),
EndCallRFNode(
RFNodeDTO(
id="end",
type="endCall",
position=Position(x=0, y=200),
data=EndCallNodeData(
name="End Call",

27
api/tests/test_text_and_audio_playback.py
View file

@ -34,12 +34,11 @@ from api.services.pipecat.recording_audio_cache import RecordingAudio
from api.services.workflow.dto import (
EdgeDataDTO,
EndCallNodeData,
EndCallRFNode,
Position,
ReactFlowDTO,
RFEdgeDTO,
RFNodeDTO,
StartCallNodeData,
StartCallRFNode,
)
from api.services.workflow.pipecat_engine import PipecatEngine
from api.services.workflow.pipecat_engine_custom_tools import CustomToolManager
@ -65,8 +64,9 @@ def text_workflow() -> WorkflowGraph:
"""Start->End workflow with text greeting and text transition speech."""
dto = ReactFlowDTO(
nodes=[
StartCallRFNode(
RFNodeDTO(
id="start",
type="startCall",
position=Position(x=0, y=0),
data=StartCallNodeData(
name="Start Call",
@ -79,8 +79,9 @@ def text_workflow() -> WorkflowGraph:
extraction_enabled=False,
),
),
EndCallRFNode(
RFNodeDTO(
id="end",
type="endCall",
position=Position(x=0, y=200),
data=EndCallNodeData(
name="End Call",
@ -114,8 +115,9 @@ def audio_workflow() -> WorkflowGraph:
"""Start->End workflow with audio greeting and audio transition speech."""
dto = ReactFlowDTO(
nodes=[
StartCallRFNode(
RFNodeDTO(
id="start",
type="startCall",
position=Position(x=0, y=0),
data=StartCallNodeData(
name="Start Call",
@ -128,8 +130,9 @@ def audio_workflow() -> WorkflowGraph:
extraction_enabled=False,
),
),
EndCallRFNode(
RFNodeDTO(
id="end",
type="endCall",
position=Position(x=0, y=200),
data=EndCallNodeData(
name="End Call",
@ -290,8 +293,9 @@ class TestStartGreeting:
"""No greeting configured should return None."""
dto = ReactFlowDTO(
nodes=[
StartCallRFNode(
RFNodeDTO(
id="start",
type="startCall",
position=Position(x=0, y=0),
data=StartCallNodeData(
name="Start",
@ -301,8 +305,9 @@ class TestStartGreeting:
extraction_enabled=False,
),
),
EndCallRFNode(
RFNodeDTO(
id="end",
type="endCall",
position=Position(x=0, y=200),
data=EndCallNodeData(
name="End",
@ -333,8 +338,9 @@ class TestStartGreeting:
"""Text greeting with {{variable}} placeholders should be rendered."""
dto = ReactFlowDTO(
nodes=[
StartCallRFNode(
RFNodeDTO(
id="start",
type="startCall",
position=Position(x=0, y=0),
data=StartCallNodeData(
name="Start",
@ -346,8 +352,9 @@ class TestStartGreeting:
extraction_enabled=False,
),
),
EndCallRFNode(
RFNodeDTO(
id="end",
type="endCall",
position=Position(x=0, y=200),
data=EndCallNodeData(
name="End",

42
api/tests/test_workflow_qa_masking.py
View file

@ -18,6 +18,25 @@ def _qa_node(node_id="qa-1", api_key="", **extra_data):
return {"id": node_id, "type": "qa", "position": {"x": 0, "y": 0}, "data": data}
def _tuner_node(node_id="tuner-1", api_key="", **extra_data):
"""Helper to build a Tuner node."""
data = {
"name": "Tuner",
"tuner_enabled": True,
"tuner_agent_id": "sales-bot",
"tuner_workspace_id": 7,
**extra_data,
}
if api_key:
data["tuner_api_key"] = api_key
return {
"id": node_id,
"type": "tuner",
"position": {"x": 0, "y": 0},
"data": data,
}
def _agent_node(node_id="agent-1"):
"""Helper to build a non-QA node."""
return {
@ -66,6 +85,19 @@ class TestMaskWorkflowDefinition:
assert "qa_api_key" not in masked["nodes"][0]["data"]
assert masked["nodes"][1]["data"]["qa_api_key"] == mask_key("sk-secret1234")
def test_masks_tuner_api_key(self):
"""Tuner node api_key is masked, showing only last 4 chars."""
real_key = "tuner_live_abcdefghijklmnop"
wf = _make_workflow_def([_tuner_node(api_key=real_key)])
masked = mask_workflow_definition(wf)
masked_key = masked["nodes"][0]["data"]["tuner_api_key"]
assert masked_key == mask_key(real_key)
assert masked_key.endswith("mnop")
assert masked_key.startswith("*")
assert real_key not in str(masked)
def test_qa_node_without_api_key(self):
"""QA node with no api_key is left as-is."""
wf = _make_workflow_def([_qa_node()])
@ -154,6 +186,16 @@ class TestMergeWorkflowApiKeys:
assert result["nodes"][0]["data"]["qa_api_key"] == new_key
def test_masked_tuner_key_is_restored(self):
"""Masked Tuner keys round-trip without losing the stored secret."""
real_key = "tuner_live_abcdefghijklmnop"
existing = _make_workflow_def([_tuner_node(api_key=real_key)])
incoming = _make_workflow_def([_tuner_node(api_key=mask_key(real_key))])
result = merge_workflow_api_keys(incoming, existing)
assert result["nodes"][0]["data"]["tuner_api_key"] == real_key
def test_no_incoming_api_key(self):
"""QA node without api_key in incoming is left alone."""
existing = _make_workflow_def([_qa_node(api_key="sk-existing-key1")])