rasa-pro 3.13.8__py3-none-any.whl → 3.14.0a2__py3-none-any.whl

rasa/core/policies/enterprise_search_policy.py

@@ -781,7 +781,7 @@ class EnterpriseSearchPolicy(LLMHealthCheckMixin, EmbeddingsHealthCheckMixin, Po
         if not os.path.exists(docs_folder) or not os.path.isdir(docs_folder):
             error_message = (
                 f"Document source directory does not exist or is not a "
-                f"directory: '{docs_folder}'. "
+                f"directory: '{os.path.abspath(docs_folder)}'. "
                 "Please specify a valid path to the documents source directory in the "
                 "vector_store configuration."
             )
@@ -1130,8 +1130,7 @@ class EnterpriseSearchPolicy(LLMHealthCheckMixin, EmbeddingsHealthCheckMixin, Po
         embeddings_config: Dict[Text, Any],
         log_source_method: str,
     ) -> None:
-        """
-        Perform the health checks using resolved LLM and embeddings configurations.
+        """Perform the health checks using resolved LLM and embeddings configurations.
         Resolved means the configuration is either:
         - A reference to a model group that has already been expanded into
           its corresponding configuration using the information from
@@ -1160,8 +1159,7 @@ class EnterpriseSearchPolicy(LLMHealthCheckMixin, EmbeddingsHealthCheckMixin, Po
 
     @classmethod
     def get_system_default_prompt_based_on_config(cls, config: Dict[str, Any]) -> str:
-        """
-        Resolves the default prompt template for Enterprise Search Policy based on
+        """Resolves the default prompt template for Enterprise Search Policy based on
         the component's configuration.
 
         - The old prompt is selected when both citation and relevancy check are either
@@ -1192,8 +1190,7 @@ class EnterpriseSearchPolicy(LLMHealthCheckMixin, EmbeddingsHealthCheckMixin, Po
         relevancy_check_enabled: bool,
         citation_enabled: bool,
     ) -> str:
-        """
-        Returns the appropriate default prompt template based on the feature flags.
+        """Returns the appropriate default prompt template based on the feature flags.
 
         The selection follows this priority:
         1. If relevancy check is enabled, return the prompt that includes both relevancy

rasa/core/policies/flows/flow_executor.py

@@ -740,7 +740,14 @@ def _run_action_step(
             # do not log about non-existing validation actions of collect steps
             utter_action_name = render_template_variables("{{context.utter}}", context)
             if utter_action_name not in available_actions:
-                structlogger.warning("flow.step.run.action.unknown", action=action_name)
+                structlogger.warning(
+                    "flow.step.run.action.unknown",
+                    action=action_name,
+                    event_info=(
+                        f"The action '{action_name}' is not defined in the domain but "
+                        f"getting triggered by the flow '{step.flow_id}'."
+                    ),
+                )
         return ContinueFlowWithNextStep(events=initial_events)
 
 

rasa/core/run.py

@@ -42,10 +42,20 @@ from rasa.utils import licensing
 logger = logging.getLogger()  # get the root logger
 
 
-def create_http_input_channels(
+def create_input_channels(
     channel: Optional[Text], credentials_file: Optional[Text]
 ) -> List[InputChannel]:
-    """Instantiate the chosen input channel."""
+    """Instantiate the chosen input channel.
+
+    Args:
+        channel (optional): The name of the specific input channel to create.
+        credentials_file: Path to the credentials file containing channel credentials.
+
+    Returns:
+        A list of instantiated input channels. If a specific channel is provided,
+        it returns a list with that single channel. If no channel is specified,
+        it returns a list of all channels defined in the credentials file.
+    """
     if credentials_file:
         all_credentials = read_config_file(credentials_file)
     else:
@@ -253,7 +263,7 @@ def serve_application(
     if not channel and not credentials:
         channel = "cmdline"
 
-    input_channels = create_http_input_channels(channel, credentials)
+    input_channels = create_input_channels(channel, credentials)
 
     if inspect:
         logger.info("Starting development inspector.")

rasa/dialogue_understanding/generator/flow_retrieval.py

@@ -219,11 +219,6 @@ class FlowRetrieval(EmbeddingsHealthCheckMixin):
         if self.vector_store is not None:
             with self._model_storage.write_to(self._resource) as model_path:
                 self.vector_store.save_local(model_path)
-        else:
-            structlogger.warning(
-                "flow_retrieval.persist_vector_store.not_initialized",
-                event_info="Vector store is None, not persisted.",
-            )
 
     def _persist_config(self) -> None:
         with self._model_storage.write_to(self._resource) as path:
@@ -249,6 +244,16 @@ class FlowRetrieval(EmbeddingsHealthCheckMixin):
         )
 
         flows_to_embedd = flows.exclude_link_only_flows()
+
+        if not flows_to_embedd:
+            structlogger.debug(
+                "flow_retrieval.populate_vector_store.no_flows_to_embed",
+                event_info=(
+                    "No flows to embed in the vector store, skipping population."
+                ),
+            )
+            return
+
         embeddings = self._create_embedder(self.config)
         documents = self._generate_flow_documents(flows_to_embedd, domain)
         try:
@@ -420,10 +425,6 @@ class FlowRetrieval(EmbeddingsHealthCheckMixin):
             The top k documents with similarity scores.
         """
         if self.vector_store is None:
-            structlogger.error(
-                "flow_retrieval.query_vector_store.vector_store_not_configured",
-                event_info="Vector store is not configured",
-            )
             return []
         try:
             documents_with_scores = (

rasa/dialogue_understanding/patterns/default_flows_for_patterns.yml

@@ -81,7 +81,7 @@ responses:
         rephrase: True
 
   utter_inform_hangup:
-    - text: It seems you are not there anymore. I will hang up shortly.
+    - text: I haven’t heard from you, so I’ll end our conversation shortly.
       metadata:
         rephrase: True
 

rasa/dialogue_understanding_test/du_test_schema.yml

@@ -5,12 +5,12 @@ mapping:
     sequence:
       - type: map
         mapping:
-          regex;(^[a-zA-Z_]+[a-zA-Z0-9_]*$):
+          regex;(^[a-zA-Z_]+[a-zA-Z0-9_\-]*$):
             type: "seq"
             sequence:
               - type: map
                 mapping:
-                  regex;(^[a-zA-Z_]+[a-zA-Z0-9_]*$):
+                  regex;(^[a-zA-Z_]+[a-zA-Z0-9_\-]*$):
                     type: any
 
   metadata:
@@ -129,7 +129,7 @@ mapping:
             type: "seq"
             sequence:
               - type: "str"
-                pattern: ^[a-zA-Z_]+[a-zA-Z0-9_]*$
+                pattern: ^[a-zA-Z_]+[a-zA-Z0-9_\-]*$
           metadata:
             type: "str"
             pattern: ^[a-zA-Z_]+[a-zA-Z0-9_]*$

rasa/e2e_test/e2e_test_schema.yml

@@ -5,12 +5,12 @@ mapping:
     sequence:
       - type: map
         mapping:
-          regex;(^[a-zA-Z_]+[a-zA-Z0-9_]*$):
+          regex;(^[a-zA-Z_]+[a-zA-Z0-9_\-]*$):
             type: "seq"
             sequence:
               - type: map
                 mapping:
-                  regex;(^[a-zA-Z_]+[a-zA-Z0-9_]*$):
+                  regex;(^[a-zA-Z_]+[a-zA-Z0-9_\-]*$):
                     type: any
 
   metadata:
@@ -129,7 +129,7 @@ mapping:
             type: "seq"
             sequence:
               - type: "str"
-                pattern: ^[a-zA-Z_]+[a-zA-Z0-9_]*$
+                pattern: ^[a-zA-Z_]+[a-zA-Z0-9_\-]*$
           metadata:
             type: "str"
             pattern: ^[a-zA-Z_]+[a-zA-Z0-9_]*$

rasa/engine/graph.py

@@ -69,6 +69,7 @@ class SchemaNode:
 
     def matches_type(self, node_type: Type, include_subtypes: bool = True) -> bool:
         """Checks if schema node's 'uses' is of specified node type.
+
         By default, it also checks for subtypes of the specified node type.
         """
         return (self.uses is node_type) or (
@@ -171,6 +172,7 @@ class GraphSchema:
 
     def has_node(self, node_type: Type, include_subtypes: bool = True) -> bool:
         """Checks if the graph schema contains a node of the specified node type.
+
         By default, it also checks for subtypes of the specified node type.
         """
         for node in self.nodes.values():
@@ -181,7 +183,7 @@ class GraphSchema:
     def count_nodes_of_a_given_type(
         self, node_type: Type, include_subtypes: bool = True
     ) -> int:
-        """Counts the number of the nodes of specified class"""
+        """Counts the number of the nodes of specified class."""
         counter = 0
         for node in self.nodes.values():
             if (node.uses is node_type) or (
@@ -353,6 +355,7 @@ class ExecutionContext:
 
     def has_node(self, node_type: Type, include_subtypes: bool = True) -> bool:
         """Checks if the graph node of the given type is present in the graph schema.
+
         By default, it also checks for subtypes of the specified node type.
         """
         return self.graph_schema.has_node(node_type, include_subtypes)
@@ -555,6 +558,7 @@ class GraphNode:
                 structlogger.error(
                     "graph.node.error_running_component",
                     node_name=self._node_name,
+                    error=str(e),
                 )
                 raise
 

rasa/engine/storage/local_model_storage.py

@@ -10,7 +10,7 @@ import uuid
 from contextlib import contextmanager
 from datetime import datetime
 from pathlib import Path
-from typing import Callable, Generator, Optional, Text, Tuple, Union
+from typing import Callable, Generator, List, Optional, Text, Tuple, Union
 
 from tarsafe import TarSafe
 
@@ -158,16 +158,24 @@ class LocalModelStorage(ModelStorage):
                     # before trying the \\?\ prefix approach first
                     prev_filter = getattr(tar, "extraction_filter", None)
                     tar.extraction_filter = create_combined_filter(prev_filter)
-                    tar.extractall(f"\\\\?\\{temporary_directory}")
+                    tar.extractall(
+                        f"\\\\?\\{temporary_directory}",
+                        members=yield_safe_members(tar.getmembers()),
+                    )
                 except Exception:
                     # Fallback for Python versions with tarfile security fix
                     logger.warning(
                         "Failed to extract model archive with long path support. "
                         "Falling back to regular extraction."
                     )
-                    tar.extractall(temporary_directory)
+                    tar.extractall(
+                        temporary_directory,
+                        members=yield_safe_members(tar.getmembers()),
+                    )
             else:
-                tar.extractall(temporary_directory)
+                tar.extractall(
+                    temporary_directory, members=yield_safe_members(tar.getmembers())
+                )
         LocalModelStorage._assert_not_rasa2_archive(temporary_directory)
 
     @staticmethod
@@ -287,3 +295,32 @@ class LocalModelStorage(ModelStorage):
             core_target=model_configuration.core_target,
             nlu_target=model_configuration.nlu_target,
         )
+
+
+def yield_safe_members(
+    members: List[tarfile.TarInfo],
+) -> Generator[tarfile.TarInfo, None, None]:
+    """
+    Filter function for tar.extractall members parameter.
+    Validates each member and yields only safe ones.
+
+    Args:
+        members: Iterator of TarInfo objects from tar.getmembers()
+
+    Yields:
+        TarInfo: Safe members to extract
+    """
+    for member in members:
+        # Skip absolute paths
+        if Path(member.name).is_absolute():
+            continue
+
+        # Skip paths with directory traversal sequences
+        if ".." in member.name or "\\.." in member.name:
+            continue
+
+        # Skip special file types unless you need them
+        if member.isdev() or member.issym():
+            continue
+
+        yield member

rasa/model_manager/model_api.py

@@ -39,11 +39,9 @@ from rasa.model_manager.trainer_service import (
     update_training_status,
 )
 from rasa.model_manager.utils import (
-    InvalidPathException,
     get_logs_content,
     logs_base_path,
     models_base_path,
-    subpath,
 )
 from rasa.model_manager.warm_rasa_process import (
     initialize_warm_rasa_process,
@@ -53,6 +51,7 @@ from rasa.server import ErrorResponse
 from rasa.shared.exceptions import InvalidConfigException
 from rasa.shared.utils.yaml import dump_obj_as_yaml_to_string
 from rasa.studio.upload import build_calm_import_parts
+from rasa.utils.io import InvalidPathException, subpath
 
 dotenv.load_dotenv()
 
@@ -571,10 +570,10 @@ def external_blueprint() -> Blueprint:
     """Create a blueprint for the model manager API."""
     from rasa.core.channels.socketio import SocketBlueprint
 
-    sio = AsyncServer(async_mode="sanic", cors_allowed_origins=[])
-    bp = SocketBlueprint(sio, "", "model_api_external")
+    sio_server = AsyncServer(async_mode="sanic", cors_allowed_origins="*")
+    bp = SocketBlueprint(sio_server, "", "model_api_external")
 
-    create_bridge_server(sio, running_bots)
+    create_bridge_server(sio_server, running_bots)
 
     @bp.get("/health")
     async def health(request: Request) -> response.HTTPResponse:

rasa/model_manager/runner_service.py

@@ -15,11 +15,11 @@ from rasa.model_manager import config
 from rasa.model_manager.utils import (
     logs_path,
     models_base_path,
-    subpath,
     write_encoded_data_to_file,
 )
 from rasa.model_manager.warm_rasa_process import start_rasa_process
 from rasa.studio.prompts import handle_prompts
+from rasa.utils.io import subpath
 
 structlogger = structlog.get_logger()
 

rasa/model_manager/socket_bridge.py

@@ -2,8 +2,7 @@ import json
 from typing import Any, Dict, Optional
 
 import structlog
-from socketio import AsyncServer
-from socketio.asyncio_client import AsyncClient
+from socketio import AsyncClient, AsyncServer  # type: ignore[attr-defined]
 from socketio.exceptions import ConnectionRefusedError
 
 from rasa.model_manager.runner_service import BotSession
@@ -20,7 +19,7 @@ socket_proxy_clients = {}
 
 
 async def socketio_websocket_traffic_wrapper(
-    sio: AsyncServer,
+    sio_server: AsyncServer,
     running_bots: Dict[str, BotSession],
     sid: str,
     auth: Optional[Dict],
@@ -56,7 +55,9 @@ async def socketio_websocket_traffic_wrapper(
         structlogger.error("model_runner.bot_not_alive", deployment_id=deployment_id)
         raise ConnectionRefusedError("model_runner.bot_not_alive")
 
-    client = await create_bridge_client(sio, bot.internal_url, sid, deployment_id)
+    client = await create_bridge_client(
+        sio_server, bot.internal_url, sid, deployment_id
+    )
 
     if client.sid is not None:
         structlogger.debug(
@@ -71,20 +72,24 @@ async def socketio_websocket_traffic_wrapper(
         raise ConnectionRefusedError("model_runner.bot_connection_failed")
 
 
-def create_bridge_server(sio: AsyncServer, running_bots: Dict[str, BotSession]) -> None:
+def create_bridge_server(
+    sio_server: AsyncServer, running_bots: Dict[str, BotSession]
+) -> None:
     """Create handlers for the socket server side.
 
     Forwards messages coming from the user to the bot.
     """
 
-    @sio.on("connect")
+    @sio_server.on("connect")
     async def socketio_websocket_traffic(
         sid: str, environ: Dict, auth: Optional[Dict]
     ) -> bool:
         """Bridge websockets between user chat socket and bot server."""
-        return await socketio_websocket_traffic_wrapper(sio, running_bots, sid, auth)
+        return await socketio_websocket_traffic_wrapper(
+            sio_server, running_bots, sid, auth
+        )
 
-    @sio.on("disconnect")
+    @sio_server.on("disconnect")
     async def disconnect(sid: str) -> None:
         """Disconnect the bot connection."""
         structlogger.debug("model_runner.bot_disconnect", sid=sid)
@@ -92,7 +97,7 @@ def create_bridge_server(sio: AsyncServer, running_bots: Dict[str, BotSession])
             await socket_proxy_clients[sid].disconnect()
             del socket_proxy_clients[sid]
 
-    @sio.on("*")
+    @sio_server.on("*")
     async def handle_message(event: str, sid: str, data: Dict[str, Any]) -> None:
         """Bridge messages between user and bot.
 
@@ -109,7 +114,7 @@ def create_bridge_server(sio: AsyncServer, running_bots: Dict[str, BotSession])
 
 
 async def create_bridge_client(
-    sio: AsyncServer, url: str, sid: str, deployment_id: str
+    sio_server: AsyncServer, url: str, sid: str, deployment_id: str
 ) -> AsyncClient:
     """Create a new socket bridge client.
 
@@ -124,29 +129,36 @@ async def create_bridge_client(
         structlogger.debug(
             "model_runner.bot_session_confirmed", deployment_id=deployment_id
         )
-        await sio.emit("session_confirm", room=sid)
+        await sio_server.emit("session_confirm", room=sid)
 
     @client.event  # type: ignore[misc]
     async def bot_message(data: Dict[str, Any]) -> None:
         structlogger.debug("model_runner.bot_message", deployment_id=deployment_id)
-        await sio.emit("bot_message", data, room=sid)
+        await sio_server.emit("bot_message", data, room=sid)
+
+    @client.event  # type: ignore[misc]
+    async def error(data: Dict[str, Any]) -> None:
+        structlogger.debug(
+            "model_runner.bot_error", deployment_id=deployment_id, data=data
+        )
+        await sio_server.emit("error", data, room=sid)
 
     @client.event  # type: ignore[misc]
     async def tracker(data: Dict[str, Any]) -> None:
-        await sio.emit("tracker", json.loads(data), room=sid)
+        await sio_server.emit("tracker", json.loads(data), room=sid)
 
     @client.event  # type: ignore[misc]
     async def disconnect() -> None:
         structlogger.debug(
             "model_runner.bot_connection_closed", deployment_id=deployment_id
         )
-        await sio.emit("disconnect", room=sid)
+        await sio_server.emit("disconnect", room=sid)
 
     @client.event  # type: ignore[misc]
     async def connect_error() -> None:
         structlogger.error(
             "model_runner.bot_connection_error", deployment_id=deployment_id
         )
-        await sio.emit("disconnect", room=sid)
+        await sio_server.emit("disconnect", room=sid)
 
     return client

rasa/model_manager/trainer_service.py

@@ -14,7 +14,6 @@ from rasa.model_manager.utils import (
     ensure_base_directory_exists,
     logs_path,
     models_base_path,
-    subpath,
     write_encoded_data_to_file,
 )
 from rasa.model_manager.warm_rasa_process import (
@@ -22,6 +21,7 @@ from rasa.model_manager.warm_rasa_process import (
 )
 from rasa.model_training import generate_random_model_name
 from rasa.studio.prompts import handle_prompts
+from rasa.utils.io import subpath
 
 structlogger = structlog.get_logger()
 
@@ -53,6 +53,15 @@ class TrainingSession(BaseModel):
         """Check if the training is running."""
         return self.status == TrainingSessionStatus.RUNNING
 
+    def has_just_finished(self) -> bool:
+        if not self.is_status_indicating_alive():
+            # skip if the training is not running
+            return False
+        if self.process.poll() is None:
+            # process is still running
+            return False
+        return True
+
     def model_path(self) -> str:
         """Return the path to the model."""
         return subpath(models_base_path(), f"{self.model_name}.tar.gz")
@@ -89,14 +98,8 @@ def terminate_training(training: TrainingSession) -> None:
 
 
 def update_training_status(training: TrainingSession) -> None:
-    if not training.is_status_indicating_alive():
-        # skip if the training is not running
-        return
-    if training.process.poll() is None:
-        # process is still running
-        return
-
-    complete_training(training)
+    if training.has_just_finished():
+        complete_training(training)
 
 
 def complete_training(training: TrainingSession) -> None:

rasa/model_manager/utils.py

@@ -5,15 +5,11 @@ from typing import Optional
 import structlog
 
 from rasa.model_manager import config
-from rasa.shared.exceptions import RasaException
+from rasa.utils.io import subpath
 
 structlogger = structlog.get_logger()
 
 
-class InvalidPathException(RasaException):
-    """Raised if a path is invalid - e.g. path traversal is detected."""
-
-
 def write_encoded_data_to_file(encoded_data: bytes, file: str) -> None:
     """Write base64 encoded data to a file."""
     # create the directory if it does not exist of the parent directory
@@ -53,30 +49,6 @@ def logs_path(action_id: str) -> str:
     return subpath(logs_base_path(), f"{action_id}.txt")
 
 
-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}")
-
-    if os.path.basename(safe_path) != child:
-        raise InvalidPathException(
-            f"Invalid path - path traversal detected: {safe_path}"
-        )
-
-    return safe_path
-
-
 def get_logs_content(action_id: str) -> Optional[str]:
     """Return the content of the log file for a given action id."""
     try: