rasa-pro 3.14.0.dev20250825__py3-none-any.whl → 3.14.0.dev20250922__py3-none-any.whl

rasa/shared/importers/utils.py

@@ -1,9 +1,37 @@
-from typing import Iterable, List, Optional, Text
+from typing import Any, Dict, Iterable, List, Optional, Text
+
+from pydantic import BaseModel, Field
 
 from rasa.shared.core.domain import Domain
 from rasa.shared.core.flows import FlowsList
+from rasa.shared.core.flows.yaml_flows_io import KEY_FLOWS, get_flows_as_json
 from rasa.shared.core.training_data.structures import StoryGraph
+from rasa.shared.importers.importer import TrainingDataImporter
+from rasa.shared.nlu.training_data.formats.rasa_yaml import RasaYAMLWriter
 from rasa.shared.nlu.training_data.training_data import TrainingData
+from rasa.utils.json_utils import extract_values
+
+
+class CALMUserData(BaseModel):
+    """All pieces that will be uploaded to Rasa Studio."""
+
+    flows: Dict[str, Any] = Field(default_factory=dict)
+    domain: Dict[str, Any] = Field(default_factory=dict)
+    config: Dict[str, Any] = Field(default_factory=dict)
+    endpoints: Dict[str, Any] = Field(default_factory=dict)
+    nlu: Dict[str, Any] = Field(default_factory=dict)
+
+
+DOMAIN_KEYS = [
+    "version",
+    "actions",
+    "responses",
+    "slots",
+    "intents",
+    "entities",
+    "forms",
+    "session_config",
+]
 
 
 def training_data_from_paths(paths: Iterable[Text], language: Text) -> TrainingData:
@@ -34,3 +62,51 @@ def flows_from_paths(files: List[Text]) -> FlowsList:
         )
     flows.validate()
     return flows
+
+
+def extract_calm_import_parts_from_importer(
+    importer: TrainingDataImporter,
+    config: Optional[Dict[str, Any]] = None,
+    endpoints: Optional[Dict[str, Any]] = None,
+) -> CALMUserData:
+    """Extracts CALMUserData from a TrainingDataImporter.
+
+    Args:
+        importer: The training data importer
+        data_paths: The path(s) to the training data for flows
+        config: Optional config dict, if not provided will use importer.get_config()
+        endpoints: Optional endpoints dict, defaults to empty dict
+
+    Returns:
+        CALMUserData containing flows, domain, config, endpoints, and nlu data
+    """
+    # Extract config
+    if config is None:
+        config = importer.get_config()
+
+    # Extract domain
+    domain_from_files = importer.get_user_domain().as_dict()
+    domain = extract_values(domain_from_files, DOMAIN_KEYS)
+
+    # Extract flows
+    flows = importer.get_user_flows()
+    flows_dict = {KEY_FLOWS: get_flows_as_json(flows)}
+
+    # Extract NLU data
+    nlu_data = importer.get_nlu_data()
+    nlu_examples = nlu_data.filter_training_examples(
+        lambda ex: ex.get("intent") in nlu_data.intents
+    )
+    nlu_dict = RasaYAMLWriter().training_data_to_dict(nlu_examples)
+
+    # Use provided endpoints or default to empty dict
+    if endpoints is None:
+        endpoints = {}
+
+    return CALMUserData(
+        flows=flows_dict or {},
+        domain=domain or {},
+        config=config or {},
+        endpoints=endpoints or {},
+        nlu=nlu_dict or {},
+    )

rasa/shared/nlu/training_data/schemas/responses.yml

@@ -72,6 +72,9 @@ schema;responses:
               allowempty: True
           channel:
             type: "str"
+          allow_interruptions:
+            type: "bool"
+            required: False
           metadata:
             type: "any"
           condition:

rasa/studio/upload.py

@@ -7,7 +7,6 @@ from typing import Any, Dict, Iterable, List, Optional, Set, Text, Tuple, Union
 import questionary
 import requests
 import structlog
-from pydantic import BaseModel, Field
 
 import rasa.cli.telemetry
 import rasa.cli.utils
@@ -24,9 +23,13 @@ from rasa.shared.constants import (
     DEFAULT_DOMAIN_PATHS,
 )
 from rasa.shared.core.domain import Domain
-from rasa.shared.core.flows.yaml_flows_io import YAMLFlowsReader, YamlFlowsWriter
+from rasa.shared.core.flows.yaml_flows_io import YAMLFlowsReader
 from rasa.shared.exceptions import RasaException
-from rasa.shared.importers.importer import FlowSyncImporter, TrainingDataImporter
+from rasa.shared.importers.importer import TrainingDataImporter
+from rasa.shared.importers.utils import (
+    CALMUserData,
+    extract_calm_import_parts_from_importer,
+)
 from rasa.shared.nlu.training_data.formats.rasa_yaml import (
     RasaYAMLReader,
     RasaYAMLWriter,
@@ -34,7 +37,6 @@ from rasa.shared.nlu.training_data.formats.rasa_yaml import (
 from rasa.shared.utils.llm import collect_custom_prompts
 from rasa.shared.utils.yaml import (
     dump_obj_as_yaml_to_string,
-    read_yaml,
     read_yaml_file,
 )
 from rasa.studio import results_logger
@@ -43,6 +45,7 @@ from rasa.studio.config import StudioConfig
 from rasa.studio.results_logger import StudioResult, with_studio_error_handler
 from rasa.studio.utils import validate_argument_paths
 from rasa.telemetry import track_upload_to_studio_failed
+from rasa.utils.json_utils import extract_values
 
 structlogger = structlog.get_logger()
 
@@ -68,16 +71,6 @@ DOMAIN_KEYS = [
 ]
 
 
-class CALMImportParts(BaseModel):
-    """All pieces that will be uploaded to Rasa Studio."""
-
-    flows: Dict[str, Any]
-    domain: Dict[str, Any]
-    config: Dict[str, Any]
-    endpoints: Dict[str, Any]
-    nlu: Dict[str, Any] = Field(default_factory=dict)
-
-
 def _get_selected_entities_and_intents(
     args: argparse.Namespace,
     intents_from_files: Set[Text],
@@ -195,11 +188,6 @@ config_keys = [
 ]
 
 
-def extract_values(data: Dict, keys: List[Text]) -> Dict:
-    """Extracts values for given keys from a dictionary."""
-    return {key: data.get(key) for key in keys if data.get(key)}
-
-
 def _get_assistant_name(config: Dict[Text, Any]) -> str:
     config_assistant_id = config.get("assistant_id", "")
     assistant_name = questionary.text(
@@ -238,7 +226,7 @@ def build_calm_import_parts(
     config_path: Text,
     endpoints_path: Optional[Text] = None,
     assistant_name: Optional[Text] = None,
-) -> Tuple[str, CALMImportParts]:
+) -> Tuple[str, CALMUserData]:
     """Builds the parts of the assistant to be uploaded to Studio.
 
     Args:
@@ -251,9 +239,11 @@ def build_calm_import_parts(
     Returns:
         The assistant name and the parts to be uploaded
     """
+    training_data_paths = data_path if isinstance(data_path, list) else [str(data_path)]
     importer = TrainingDataImporter.load_from_dict(
         domain_path=domain_path,
         config_path=config_path,
+        training_data_paths=training_data_paths,
         expand_env_vars=False,
     )
 
@@ -261,34 +251,10 @@ def build_calm_import_parts(
     endpoints = read_yaml_file(endpoints_path, expand_env_vars=False)
     assistant_name = assistant_name or _get_assistant_name(config)
 
-    domain_from_files = importer.get_user_domain().as_dict()
-    domain = extract_values(domain_from_files, DOMAIN_KEYS)
-
-    training_data_paths = data_path if isinstance(data_path, list) else [str(data_path)]
-    flow_importer = FlowSyncImporter.load_from_dict(
-        training_data_paths=training_data_paths, expand_env_vars=False
-    )
-
-    flows = list(flow_importer.get_user_flows())
-    flows_yaml = YamlFlowsWriter().dumps(flows)
-    flows = read_yaml(flows_yaml, expand_env_vars=False)
-
-    nlu_importer = TrainingDataImporter.load_from_dict(
-        training_data_paths=training_data_paths, expand_env_vars=False
-    )
-    nlu_data = nlu_importer.get_nlu_data()
-    nlu_examples = nlu_data.filter_training_examples(
-        lambda ex: ex.get("intent") in nlu_data.intents
-    )
-    nlu_examples_yaml = RasaYAMLWriter().dumps(nlu_examples)
-    nlu = read_yaml(nlu_examples_yaml, expand_env_vars=False)
-
-    parts = CALMImportParts(
-        flows=flows,
-        domain=domain,
+    parts = extract_calm_import_parts_from_importer(
+        importer=importer,
         config=config,
         endpoints=endpoints,
-        nlu=nlu,
     )
 
     return assistant_name, parts

rasa/telemetry.py

@@ -3,7 +3,6 @@ import contextlib
 import hashlib
 import inspect
 import json
-import logging
 import multiprocessing
 import os
 import platform
@@ -70,7 +69,7 @@ if typing.TYPE_CHECKING:
     from rasa.shared.importers.importer import TrainingDataImporter
     from rasa.shared.nlu.training_data.training_data import TrainingData
 
-logger = logging.getLogger(__name__)
+structlogger = structlog.get_logger()
 
 SEGMENT_TRACK_ENDPOINT = "https://api.segment.io/v1/track"
 SEGMENT_IDENTIFY_ENDPOINT = "https://api.segment.io/v1/identify"
@@ -197,6 +196,10 @@ TELEMETRY_E2E_TEST_CONVERSION_EVENT = "E2E Test Conversion Completed"
 E2E_TEST_CONVERSION_FILE_TYPE = "file_type"
 E2E_TEST_CONVERSION_TEST_CASE_COUNT = "test_case_count"
 
+# Copilot telemetry
+TELEMETRY_COPILOT_USER_MESSAGE_EVENT = "copilot_user_message"
+TELEMETRY_COPILOT_BOT_MESSAGE_EVENT = "copilot_bot_message"
+
 
 def print_telemetry_reporting_info() -> None:
     """Print telemetry information to std out."""
@@ -255,7 +258,11 @@ def _is_telemetry_enabled_in_configuration() -> bool:
 
         return stored_config[CONFIG_TELEMETRY_ENABLED]
     except ValueError as e:
-        logger.debug(f"Could not read telemetry settings from configuration file: {e}")
+        structlogger.debug(
+            "telemetry.is_telemetry_enabled_in_configuration.error",
+            error=str(e),
+            event_info="Could not read telemetry settings from configuration file",
+        )
 
         # seems like there is no config, we'll create one and enable telemetry
         success = _write_default_telemetry_configuration()
@@ -272,7 +279,10 @@ def is_telemetry_enabled() -> bool:
     from rasa.utils import licensing
 
     if licensing.is_champion_server_license():
-        logger.debug("Telemetry is enabled for developer licenses.")
+        structlogger.debug(
+            "telemetry.enabled.developer_license",
+            event_info="Telemetry is enabled for developer licenses.",
+        )
         return True
 
     telemetry_environ = os.environ.get(TELEMETRY_ENABLED_ENVIRONMENT_VARIABLE)
@@ -308,9 +318,13 @@ def initialize_telemetry() -> bool:
 
         return telemetry_environ.lower() == "true"
     except Exception as e:  # skipcq:PYL-W0703
-        logger.exception(
-            f"Failed to initialize telemetry reporting: {e}."
-            f"Telemetry reporting will be disabled."
+        structlogger.exception(
+            "telemetry.initialize_telemetry.error",
+            error=str(e),
+            event_info=(
+                "Failed to initialize telemetry reporting. "
+                "Telemetry reporting will be disabled."
+            ),
         )
         return False
 
@@ -481,7 +495,10 @@ def print_telemetry_payload(payload: Dict[Text, Any]) -> None:
         payload: payload to be delivered to segment.
     """
     payload_json = json.dumps(payload, indent=2)
-    logger.debug(f"Telemetry payload: {payload_json}")
+    structlogger.debug(
+        "telemetry.print_telemetry_payload.debug",
+        event_info=f"Telemetry payload: {payload_json}",
+    )
 
 
 def _get_telemetry_write_key() -> Optional[Text]:
@@ -535,10 +552,24 @@ def _send_request(url: Text, payload: Dict[Text, Any]) -> None:
     if not write_key:
         # If RASA_TELEMETRY_WRITE_KEY is empty or `None`, telemetry has not
         # been enabled for this build (e.g. because it is running from source)
-        logger.debug("Skipping request to external service: telemetry key not set.")
+        structlogger.debug(
+            "telemetry.send_request.no_telemetry_key",
+            event_info="Skipping request to external service: telemetry key not set.",
+        )
         return
 
-    headers = rasa.telemetry.segment_request_header(write_key)
+    send_segment_request(url, payload, write_key)
+
+
+def send_segment_request(url: Text, payload: Dict[Text, Any], write_key: Text) -> None:
+    """Send a request to the Segment API.
+
+    Args:
+        url: URL of the Segment API endpoint
+        payload: payload to send to the Segment API
+        write_key: write key for the Segment API
+    """
+    headers = segment_request_header(write_key)
 
     resp = requests.post(
         url=url,
@@ -548,15 +579,22 @@ def _send_request(url: Text, payload: Dict[Text, Any]) -> None:
     )
     # handle different failure cases
     if resp.status_code != 200:
-        logger.debug(
-            f"Segment telemetry request returned a {resp.status_code} response. "
-            f"Body: {resp.text}"
+        structlogger.debug(
+            "telemetry.send_segment_request.error_response",
+            event_info=(
+                f"Segment telemetry request returned a {resp.status_code} "
+                f"response. Body: {resp.text}"
+            ),
         )
     else:
         data = resp.json()
         if not data.get("success"):
-            logger.debug(
-                f"Segment telemetry request returned a failure. Response: {data}"
+            structlogger.debug(
+                "telemetry.send_segment_request.failure",
+                event_info=(
+                    f"Segment telemetry request returned a failure. "
+                    f"Response: {data}"
+                ),
             )
 
 
@@ -609,6 +647,15 @@ def with_default_context_fields(
     return {**_default_context_fields(), **context}
 
 
+def get_deployment_stack() -> Text:
+    """Return the deployment stack.
+
+    Returns:
+        The deployment stack.
+    """
+    return os.environ.get("DEPLOYMENT_STACK", "")
+
+
 def _default_context_fields() -> Dict[Text, Any]:
     """Return a dictionary that contains the default context values.
 
@@ -632,6 +679,7 @@ def _default_context_fields() -> Dict[Text, Any]:
             "cpu": multiprocessing.cpu_count(),
             "docker": _is_docker(),
             "license_hash": get_license_hash(),
+            "deployment_stack": get_deployment_stack(),
             "company": property_of_active_license(
                 lambda active_license: active_license.company
             ),
@@ -663,7 +711,10 @@ def _track(
         telemetry_id = get_telemetry_id()
 
         if not telemetry_id:
-            logger.debug("Will not report telemetry events as no ID was found.")
+            structlogger.debug(
+                "telemetry.track.no_id_found",
+                event_info="Will not report telemetry events as no ID was found.",
+            )
             return
 
         if not properties:
@@ -681,7 +732,11 @@ def _track(
                 with_default_context_fields(context),
             )
     except Exception as e:  # skipcq:PYL-W0703
-        logger.debug(f"Skipping telemetry reporting: {e}")
+        structlogger.debug(
+            "telemetry.track.error",
+            error=str(e),
+            event_info="Skipping telemetry reporting",
+        )
 
 
 def _identify(
@@ -702,7 +757,10 @@ def _identify(
         telemetry_id = get_telemetry_id()
 
         if not telemetry_id:
-            logger.debug("Will not report telemetry events as no ID was found.")
+            structlogger.debug(
+                "telemetry.identify.no_id_found",
+                event_info="Will not report telemetry events as no ID was found.",
+            )
             return
 
         if not traits:
@@ -710,7 +768,11 @@ def _identify(
 
         _send_traits(telemetry_id, traits, with_default_context_fields(context))
     except Exception as e:
-        logger.debug(f"Skipping telemetry reporting: {e}")
+        structlogger.debug(
+            "telemetry.identify.error",
+            error=str(e),
+            event_info="Skipping telemetry reporting",
+        )
 
 
 def _send_traits(
@@ -868,13 +930,16 @@ def strip_sensitive_data_from_sentry_event(
 
 
 @ensure_telemetry_enabled
-def initialize_error_reporting() -> None:
+def initialize_error_reporting(private_mode: bool = True) -> None:
     """Sets up automated error reporting.
 
     Exceptions are reported to sentry. We avoid sending any metadata (local
     variables, paths, ...) to make sure we don't compromise any data. Only the
     exception and its stacktrace is logged and only if the exception origins
     from the `rasa` package.
+
+    Args:
+        private_mode: If True, try to send as little data as possible.
     """
     import sentry_sdk
     from sentry_sdk import configure_scope
@@ -892,11 +957,18 @@ def initialize_error_reporting() -> None:
 
     telemetry_id = get_telemetry_id()
 
+    # in hello rasa we use a different project, so we need to be able
+    # to set the whole url. since we can't change the behavior of sentry in pro
+    # we have two kinds of keys, full urls and jsut the key within the fixed rasa
+    # pro project.
+    if not key.startswith("https://"):
+        key = f"https://{key}.ingest.sentry.io/2801673"
+
     # this is a very defensive configuration, avoiding as many integrations as
     # possible. it also submits very little data (exception with error message
     # and line numbers).
     sentry_sdk.init(
-        f"https://{key}.ingest.sentry.io/2801673",
+        key,
         before_send=before_send,
         integrations=[
             ExcepthookIntegration(),
@@ -916,7 +988,7 @@ def initialize_error_reporting() -> None:
             OSError,
         ],
         in_app_include=["rasa"],  # only submit errors in this package
-        include_local_variables=False,  # don't submit local variables
+        include_local_variables=not private_mode,
         release=f"rasa-{rasa.__version__}",
         default_integrations=False,
         environment="development" if in_continuous_integration() else "production",
@@ -937,6 +1009,7 @@ def initialize_error_reporting() -> None:
                 # os is a nested dict, hence we report it separately
                 scope.set_context("Operating System", default_context.pop("os"))
             scope.set_context("Environment", default_context)
+    structlogger.debug("telemetry.sentry.initialized")
 
 
 @contextlib.contextmanager
@@ -1426,6 +1499,7 @@ def track_shell_started(model_type: Text, assistant_id: Text) -> None:
 
     Args:
         model_type: Type of the model, core / nlu or rasa.
+        assistant_id: ID of the assistant being inspected.
     """
     _track(
         TELEMETRY_SHELL_STARTED_EVENT,
@@ -1997,7 +2071,7 @@ def _extract_stream_pii(event_broker: Optional["EventBroker"]) -> bool:
 def track_privacy_enabled(
     privacy_config: "PrivacyConfig", event_broker: Optional["EventBroker"]
 ) -> None:
-    """Track when PII management capability is enabled"""
+    """Track when PII management capability is enabled."""
     stream_pii = _extract_stream_pii(event_broker)
     privacy_properties = _extract_privacy_enabled_event_properties(
         privacy_config, stream_pii

rasa/utils/io.py

@@ -26,6 +26,7 @@ from typing_extensions import Protocol
 
 import rasa.shared.constants
 import rasa.shared.utils.io
+from rasa.shared.exceptions import RasaException
 
 if TYPE_CHECKING:
     from prompt_toolkit.validation import Validator
@@ -124,9 +125,7 @@ def create_path(file_path: Text) -> None:
 def file_type_validator(
     valid_file_types: List[Text], error_message: Text
 ) -> Type["Validator"]:
-    """Creates a `Validator` class which can be used with `questionary` to validate
-    file paths.
-    """
+    """Creates a file type validator class for the questionary package."""
 
     def is_valid(path: Text) -> bool:
         return path is not None and any(
@@ -137,9 +136,7 @@ def file_type_validator(
 
 
 def not_empty_validator(error_message: Text) -> Type["Validator"]:
-    """Creates a `Validator` class which can be used with `questionary` to validate
-    that the user entered something other than whitespace.
-    """
+    """Creates a not empty validator class for the questionary package."""
 
     def is_valid(input: Text) -> bool:
         return input is not None and input.strip() != ""
@@ -150,9 +147,7 @@ def not_empty_validator(error_message: Text) -> Type["Validator"]:
 def create_validator(
     function: Callable[[Text], bool], error_message: Text
 ) -> Type["Validator"]:
-    """Helper method to create `Validator` classes from callable functions. Should be
-    removed when questionary supports `Validator` objects.
-    """
+    """Helper method to create a validator class from a callable function."""
     from prompt_toolkit.document import Document
     from prompt_toolkit.validation import ValidationError, Validator
 
@@ -250,3 +245,26 @@ def write_yaml(
 
     with Path(target).open("w", encoding="utf-8") as outfile:
         dumper.dump(data, outfile, transform=transform)
+
+
+class InvalidPathException(RasaException):
+    """Raised if a path is invalid - e.g. path traversal is detected."""
+
+
+def subpath(parent: str, child: str) -> str:
+    """Return the path to the child directory of the parent directory.
+
+    Ensures, that child doesn't navigate to parent directories. Prevents
+    path traversal. Raises an InvalidPathException if the path is invalid.
+
+    Based on Snyk's directory traversal mitigation:
+    https://learn.snyk.io/lesson/directory-traversal/
+    """
+    safe_path = os.path.abspath(os.path.join(parent, child))
+    parent = os.path.abspath(parent)
+
+    common_base = os.path.commonpath([parent, safe_path])
+    if common_base != parent:
+        raise InvalidPathException(f"Invalid path: {safe_path}")
+
+    return safe_path

rasa/utils/json_utils.py

@@ -1,6 +1,6 @@
 import json
 from decimal import Decimal
-from typing import Any, Text
+from typing import Any, Dict, List, Text
 
 
 class DecimalEncoder(json.JSONEncoder):
@@ -58,3 +58,8 @@ def replace_decimals_with_floats(obj: Any) -> Any:
         Input `obj` with all `Decimal` types replaced by `float`s.
     """
     return json.loads(json.dumps(obj, cls=DecimalEncoder))
+
+
+def extract_values(data: Dict, keys: List[Text]) -> Dict:
+    """Extracts values for given keys from a dictionary."""
+    return {key: data.get(key) for key in keys if data.get(key)}

rasa/utils/log_utils.py

@@ -3,7 +3,7 @@ from __future__ import annotations
 import logging
 import os
 import sys
-from typing import Any, Optional
+from typing import Any, List, Optional
 
 import structlog
 from structlog.dev import ConsoleRenderer
@@ -37,6 +37,7 @@ class HumanConsoleRenderer(ConsoleRenderer):
 def configure_structlog(
     log_level: Optional[int] = None,
     include_time: bool = False,
+    additional_processors: Optional[List[structlog.typing.Processor]] = None,
 ) -> None:
     """Configure logging of the server."""
     if log_level is None:  # Log level NOTSET is 0 so we use `is None` here
@@ -75,6 +76,9 @@ def configure_structlog(
     if include_time:
         shared_processors.append(structlog.processors.TimeStamper(fmt="iso"))
 
+    if additional_processors:
+        shared_processors.extend(additional_processors)
+
     if not FORCE_JSON_LOGGING and sys.stderr.isatty():
         # Pretty printing when we run in a terminal session.
         # Automatically prints pretty tracebacks when "rich" is installed