data-designer-config 0.4.0rc3__py3-none-any.whl → 0.5.0rc1__py3-none-any.whl

data_designer/config/mcp.py

@@ -0,0 +1,109 @@
+# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+
+from __future__ import annotations
+
+from typing import Annotated, Literal
+
+from pydantic import Field
+from typing_extensions import TypeAlias
+
+from data_designer.config.base import ConfigBase
+
+
+class MCPProvider(ConfigBase):
+    """Configuration for a remote MCP server connection.
+
+    MCPProvider is used to connect to pre-existing MCP servers via SSE (Server-Sent Events)
+    transport. For local subprocess-based MCP servers, use LocalStdioMCPProvider instead.
+
+    Attributes:
+        name (str): Unique name used to reference this MCP provider.
+        endpoint (str): SSE endpoint URL for connecting to the remote MCP server.
+        api_key (str | None): Optional API key for authentication. Defaults to None.
+        provider_type (Literal["sse"]): Transport type discriminator, always "sse".
+
+    Examples:
+        Remote SSE transport:
+
+        >>> MCPProvider(
+        ...     name="remote-mcp",
+        ...     endpoint="http://localhost:8080/sse",
+        ...     api_key="your-api-key",
+        ... )
+    """
+
+    provider_type: Literal["sse"] = "sse"
+    name: str
+    endpoint: str
+    api_key: str | None = None
+
+
+class LocalStdioMCPProvider(ConfigBase):
+    """Configuration for launching a local MCP server via stdio transport.
+
+    LocalStdioMCPProvider is used to launch MCP servers as subprocesses using stdio
+    for communication. For connecting to remote/pre-existing MCP servers, use MCPProvider instead.
+
+    Attributes:
+        name (str): Unique name used to reference this MCP provider.
+        command (str): Executable to launch the MCP server via stdio transport.
+        args (list[str]): Arguments passed to the MCP server executable. Defaults to [].
+        env (dict[str, str]): Environment variables passed to the MCP server subprocess. Defaults to {}.
+        provider_type (Literal["stdio"]): Transport type discriminator, always "stdio".
+
+    Examples:
+        Stdio (subprocess) transport:
+
+        >>> LocalStdioMCPProvider(
+        ...     name="demo-mcp",
+        ...     command="python",
+        ...     args=["-m", "data_designer_e2e_tests.mcp_demo_server"],
+        ...     env={"PYTHONPATH": "/path/to/project"},
+        ... )
+    """
+
+    provider_type: Literal["stdio"] = "stdio"
+    name: str
+    command: str
+    args: list[str] = Field(default_factory=list)
+    env: dict[str, str] = Field(default_factory=dict)
+
+
+MCPProviderT: TypeAlias = Annotated[MCPProvider | LocalStdioMCPProvider, Field(discriminator="provider_type")]
+
+
+class ToolConfig(ConfigBase):
+    """Configuration for permitting MCP tools on an LLM column.
+
+    ToolConfig defines which tools are available for use during LLM generation.
+    It references one or more MCP providers by name and can optionally restrict
+    which tools from those providers are permitted.
+
+    Attributes:
+        tool_alias (str): User-defined alias to reference this tool configuration in column configs.
+        providers (list[str]): Names of the MCP providers to use for tool calls. Tools can be
+            drawn from multiple providers.
+        allow_tools (list[str] | None): Optional allowlist of tool names that restricts which
+            tools are permitted. If None, all tools from the specified providers are allowed.
+            Defaults to None.
+        max_tool_call_turns (int): Maximum number of tool-calling turns permitted in a single
+            generation. A turn is one iteration where the LLM requests tool calls. With parallel
+            tool calling, a single turn may execute multiple tools simultaneously. Defaults to 5.
+        timeout_sec (float | None): Timeout in seconds for MCP tool calls. Defaults to None (no timeout).
+
+    Examples:
+        >>> ToolConfig(
+        ...     tool_alias="search-tools",
+        ...     providers=["doc-search-mcp", "web-search-mcp"],
+        ...     allow_tools=["search_docs", "list_docs"],
+        ...     max_tool_call_turns=10,
+        ...     timeout_sec=30.0,
+        ... )
+    """
+
+    tool_alias: str
+    providers: list[str]
+    allow_tools: list[str] | None = None
+    max_tool_call_turns: int = Field(default=5, ge=1)
+    timeout_sec: float | None = Field(default=None, gt=0)

data_designer/config/run_config.py

@@ -1,4 +1,4 @@
-# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 # SPDX-License-Identifier: Apache-2.0
 
 from __future__ import annotations
@@ -33,10 +33,6 @@ class RunConfig(ConfigBase):
         max_conversation_correction_steps: Maximum number of correction rounds permitted within a
             single conversation when generation tasks call `ModelFacade.generate(...)`. Must be >= 0.
             Default is 0.
-        debug_override_save_all_column_traces: If True, overrides per-column `with_trace` settings
-            and includes `__trace` columns for ALL LLM generations, containing the full ordered
-            message history (system/user/assistant) for the final generation attempt.
-            Useful for debugging. Default is False.
     """
 
     disable_early_shutdown: bool = False
@@ -46,7 +42,6 @@ class RunConfig(ConfigBase):
     non_inference_max_parallel_workers: int = Field(default=4, ge=1)
     max_conversation_restarts: int = Field(default=5, ge=0)
     max_conversation_correction_steps: int = Field(default=0, ge=0)
-    debug_override_save_all_column_traces: bool = False
 
     @model_validator(mode="after")
     def normalize_shutdown_settings(self) -> Self:

data_designer/config/utils/constants.py

@@ -167,6 +167,7 @@ MAX_TOP_P = 1.0
 MIN_TOP_P = 0.0
 MIN_MAX_TOKENS = 1
 TRACE_COLUMN_POSTFIX = "__trace"
+REASONING_CONTENT_COLUMN_POSTFIX = "__reasoning_content"
 
 AVAILABLE_LOCALES = [
     "ar_AA",
@@ -276,6 +277,14 @@ MODEL_PROVIDERS_FILE_NAME = "model_providers.yaml"
 
 MODEL_PROVIDERS_FILE_PATH = DATA_DESIGNER_HOME / MODEL_PROVIDERS_FILE_NAME
 
+MCP_PROVIDERS_FILE_NAME = "mcp_providers.yaml"
+
+MCP_PROVIDERS_FILE_PATH = DATA_DESIGNER_HOME / MCP_PROVIDERS_FILE_NAME
+
+TOOL_CONFIGS_FILE_NAME = "tool_configs.yaml"
+
+TOOL_CONFIGS_FILE_PATH = DATA_DESIGNER_HOME / TOOL_CONFIGS_FILE_NAME
+
 NVIDIA_PROVIDER_NAME = "nvidia"
 
 NVIDIA_API_KEY_ENV_VAR_NAME = "NVIDIA_API_KEY"

data_designer/config/utils/trace_type.py

@@ -0,0 +1,24 @@
+# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+
+from __future__ import annotations
+
+from data_designer.config.utils.type_helpers import StrEnum
+
+
+class TraceType(StrEnum):
+    """Specifies the type of reasoning trace to capture for LLM columns.
+
+    Traces capture the conversation history during LLM generation, which is
+    useful for debugging, analysis, and understanding model behavior.
+
+    Attributes:
+        NONE: No trace is captured. This is the default.
+        LAST_MESSAGE: Only the final assistant message is captured.
+        ALL_MESSAGES: The full conversation history (system/user/assistant/tool)
+            is captured.
+    """
+
+    NONE = "none"
+    LAST_MESSAGE = "last_message"
+    ALL_MESSAGES = "all_messages"

data_designer/config/utils/visualization.py

@@ -203,6 +203,7 @@ def display_sample_record(
         + config_builder.get_columns_of_type(DataDesignerColumnType.LLM_TEXT)
         + config_builder.get_columns_of_type(DataDesignerColumnType.LLM_STRUCTURED)
         + config_builder.get_columns_of_type(DataDesignerColumnType.EMBEDDING)
+        + config_builder.get_columns_of_type(DataDesignerColumnType.CUSTOM)
     )
     if len(non_code_columns) > 0:
         table = Table(title="Generated Columns", **table_kws)
@@ -215,6 +216,11 @@ def display_sample_record(
                         get_truncated_list_as_string(embd) for embd in record[col.name].get("embeddings")
                     ]
                 table.add_row(col.name, convert_to_row_element(record[col.name]))
+                # Also display side_effect_columns for custom generators
+                if col.column_type == DataDesignerColumnType.CUSTOM:
+                    for output_col in col.side_effect_columns:
+                        if output_col in record:
+                            table.add_row(output_col, convert_to_row_element(record[output_col]))
         render_list.append(pad_console_element(table))
 
     for col in config_builder.get_columns_of_type(DataDesignerColumnType.LLM_CODE):

{data_designer_config-0.4.0rc3.dist-info → data_designer_config-0.5.0rc1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: data-designer-config
-Version: 0.4.0rc3
+Version: 0.5.0rc1
 Summary: Configuration layer for DataDesigner synthetic data generation
 License-Expression: Apache-2.0
 Classifier: Development Status :: 4 - Beta

{data_designer_config-0.4.0rc3.dist-info → data_designer_config-0.5.0rc1.dist-info}/RECORD

@@ -2,22 +2,24 @@ data_designer/errors.py,sha256=r1pBvmvRBAsPmb7oF_veubhkxZ2uPo9cGEDwykLziX4,220
 data_designer/lazy_heavy_imports.py,sha256=5X04vUj9TYbKgfDmY2qvhzRf5-IZWKOanIpi3_u7fmM,1662
 data_designer/logging.py,sha256=Xq2cRwxmDJ-r8_s9NWnk15efLRsrKm5iVScHy6HkjiE,6044
 data_designer/plugin_manager.py,sha256=C2ZkZiXlcMRiaxfrrho5Shz6DKdExVeBha7ch-d4CnU,2695
-data_designer/config/__init__.py,sha256=MWzRZhXA41sTpc0sL_xq2baA3kSlV37alT6g8RlP8dU,4919
-data_designer/config/_version.py,sha256=DTeqqEr2nu3d0J3qZZfx7FpCHf1Ai3akZDbCReLKmgY,714
-data_designer/config/base.py,sha256=IGj6sy_GnKzC94uu2rdxe12EqR_AmGJ6O3rl2MxOv6g,2449
-data_designer/config/column_configs.py,sha256=QEHXbxljbGEfOEnzNsiR3_CRpaCukQsayBbHQyhMhbc,20720
-data_designer/config/column_types.py,sha256=xGXuu0EBy3Y5Jd74f2VM6x5jHq72GmK9leA6qOnAz8c,5423
-data_designer/config/config_builder.py,sha256=vuPibkodbJxbCXdaI1tt1Uyo1SVCnAOfLBAW1AmhajI,24707
-data_designer/config/data_designer_config.py,sha256=qOojviug05vHR2S4800sjd4OmxhSVi6kB8SAFXLlPog,1891
+data_designer/config/__init__.py,sha256=Joc1wgUNdtQROIW4x3si5_B1yZVVrM_wRBBQ3VREECU,10192
+data_designer/config/base.py,sha256=uiZRsDkDx5Gt_Bd54YIzo8as0mZPCxaUrnCMlgRQ8YY,2456
+data_designer/config/column_configs.py,sha256=ghYwuwVplAvihHu2ZFQvwYubI8r2nILUHnsPHI3GAbI,25769
+data_designer/config/column_types.py,sha256=Su-wnzUMKZwTMxn4bKrAMrv6m7s-2AlRJV9WqMPvQOY,5566
+data_designer/config/config_builder.py,sha256=msvu_PE0MfLtRFNBHQgO5fx7cF4fhm1rM2Vj9TowdUM,28623
+data_designer/config/custom_column.py,sha256=Ks5DX2SMx3jTUkitarAlvR7hxS-rONAy9UYZCLcZC8c,2515
+data_designer/config/data_designer_config.py,sha256=HnTaBYwNiD37_3aHVTDRqCjCDYVUCq7FIqKiNOT2Fdo,2170
 data_designer/config/dataset_builders.py,sha256=jdCujJYFlKAiSkPNX2Qeyrs683GrRcCDv_m8ZZhtg64,368
 data_designer/config/dataset_metadata.py,sha256=UTlEgnHWgjwPuc7bP95T7gaKmcr7pIhFMy9vvbUwMV4,647
 data_designer/config/default_model_settings.py,sha256=c-llH2otfG0tMCMsxoz3ZcS1nFxIQQPfRedFXAydDbc,4868
 data_designer/config/errors.py,sha256=JhvUYecfLmP0gZjQzqA3OmfaSs9TRlC5E-ubnV_-3gs,560
+data_designer/config/exportable_config.py,sha256=634mOo2yB84Hq9S-oiAuJbomFgJGvSEqep2VoRZcMEg,2214
 data_designer/config/interface.py,sha256=ikmpm_KwencTpM-yg0auo7XMgcmMSa67S75IqdpFLfk,1676
+data_designer/config/mcp.py,sha256=GqDWPieqzMWp6Nj5ikfHSzB1_w3pfjg8NA_QrLjrv9o,4295
 data_designer/config/models.py,sha256=_NctRk4brgBeb5q5V7r_hXE5OORlLh6SCVZP0eu2LGo,16721
 data_designer/config/preview_results.py,sha256=WnPlDcHElIHNfjV_P-nLu_Dpul8D3Eyb5qyi3E173Gs,1744
 data_designer/config/processors.py,sha256=lnyUZA1EhO9NWjjVFFioYxSgeYpoAaM1J7UzwOYkvms,6028
-data_designer/config/run_config.py,sha256=m_rrqEmNHR533AYJ_OR5yq0a9Pegy9vPGZgyfD4x9cI,3052
+data_designer/config/run_config.py,sha256=FjZi9DMePGJiGyXG9-XXAfg4enb2fs0fJQR47HQLP88,2668
 data_designer/config/sampler_constraints.py,sha256=tQI1XLF5bS4TnyKMLo0nArvefnXI8dWCzov38r4qNCQ,1197
 data_designer/config/sampler_params.py,sha256=Gio-53vjSYOdPhF2CEq4HSWCXCaZMy4WpGPbuFVcWOM,27965
 data_designer/config/seed.py,sha256=eShSqOcSUzfCEZBnqY-rB0qZpRGxjeOE3fSaJAwacec,4668
@@ -33,18 +35,19 @@ data_designer/config/analysis/utils/reporting.py,sha256=teTzd1OHtpI4vbIinGOGsKXy
 data_designer/config/testing/__init__.py,sha256=vxFrIOqDoDfOx-MWjC5lb_hvmB4kRKvh1QdTv--QYFM,222
 data_designer/config/testing/fixtures.py,sha256=J1bcWjerAIoVUIZBVPbUcuvEa2laj_kspVcLS7UZMbo,10876
 data_designer/config/utils/code_lang.py,sha256=nUeWjuzSYBVF5gwOiUE2-EsYCEDzRZaw31RIivt7GPI,2638
-data_designer/config/utils/constants.py,sha256=lprfeF_bIzGJ_oGrZBhvHEbLVgrGfFtVbCdWJHf_6B8,8953
+data_designer/config/utils/constants.py,sha256=FYQgrBuX6JVrLnMjNk-TSmbcvgOofBt06RDvgTew0a4,9246
 data_designer/config/utils/errors.py,sha256=HCjer0YrF0bMn5j8gmgWaLb0395LAr_hxMD1ftOsOc8,520
 data_designer/config/utils/info.py,sha256=yOa4U8kI_CY4OfCKZxCm2okU8klAiThvyjKM5tG-F0A,3469
 data_designer/config/utils/io_helpers.py,sha256=kzvOR7QgqijkqU-O2enIlpCWwHvzc3oRaEl4Lsjh1Do,8466
 data_designer/config/utils/misc.py,sha256=7n_0txc78IoK6V39CwZY-65KtYcjh38WDl0Q1bQM-EA,2481
 data_designer/config/utils/numerical_helpers.py,sha256=DIubKzc8q2_Bw7xRjyOGwxYulTV3dt3JxCdpH560dak,838
+data_designer/config/utils/trace_type.py,sha256=PtUXGdM-9n77M83sJ7gaYknj1KrFfjGDVUksO7g4X3s,830
 data_designer/config/utils/type_helpers.py,sha256=XyVup24F4Bl7uNze_yUW9oD6EzFbfsJWKhpeMN2901A,4059
-data_designer/config/utils/visualization.py,sha256=_0Mn-jva0Oz1tVTQH1mnWSARpqZ2kh1JSzJEuikyy9s,18491
+data_designer/config/utils/visualization.py,sha256=clfDqFOsny6aEHW_dyMmItVnjPv93sAX_3RIlmGQJOc,18919
 data_designer/plugins/__init__.py,sha256=qe1alcTEtnMSMdzknjb57vvjqKgFE5cEHXxBj8tPWMI,275
 data_designer/plugins/errors.py,sha256=d7FMed3ueQvZHwuhwyPLzF4E34bO1mdj3aBVEw6p34o,386
 data_designer/plugins/plugin.py,sha256=TVyyOaQBWAt0FQwUmtihTZ9MDJD85HwggrQ3L9CviPQ,5367
 data_designer/plugins/registry.py,sha256=Cnt33Q25o9bS2v2YDbV3QPM57VNrtIBKAb4ERQRE_dY,3053
-data_designer_config-0.4.0rc3.dist-info/METADATA,sha256=7FQwABHHNXZOEomFztSQi4heVz8ioAouK_vIhreW0Tw,2286
-data_designer_config-0.4.0rc3.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-data_designer_config-0.4.0rc3.dist-info/RECORD,,
+data_designer_config-0.5.0rc1.dist-info/METADATA,sha256=Jl2IswRqm6fHQra4g44_tUGMkGCypsGskTBPWhnLQr8,2286
+data_designer_config-0.5.0rc1.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+data_designer_config-0.5.0rc1.dist-info/RECORD,,

data_designer/config/_version.py

@@ -1,34 +0,0 @@
-# file generated by setuptools-scm
-# don't change, don't track in version control
-
-__all__ = [
-    "__version__",
-    "__version_tuple__",
-    "version",
-    "version_tuple",
-    "__commit_id__",
-    "commit_id",
-]
-
-TYPE_CHECKING = False
-if TYPE_CHECKING:
-    from typing import Tuple
-    from typing import Union
-
-    VERSION_TUPLE = Tuple[Union[int, str], ...]
-    COMMIT_ID = Union[str, None]
-else:
-    VERSION_TUPLE = object
-    COMMIT_ID = object
-
-version: str
-__version__: str
-__version_tuple__: VERSION_TUPLE
-version_tuple: VERSION_TUPLE
-commit_id: COMMIT_ID
-__commit_id__: COMMIT_ID
-
-__version__ = version = '0.4.0rc3'
-__version_tuple__ = version_tuple = (0, 4, 0, 'rc3')
-
-__commit_id__ = commit_id = None