data-designer-config 0.4.0rc2__tar.gz → 0.4.0rc3__tar.gz

{data_designer_config-0.4.0rc2 → data_designer_config-0.4.0rc3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: data-designer-config
-Version: 0.4.0rc2
+Version: 0.4.0rc3
 Summary: Configuration layer for DataDesigner synthetic data generation
 License-Expression: Apache-2.0
 Classifier: Development Status :: 4 - Beta

{data_designer_config-0.4.0rc2 → data_designer_config-0.4.0rc3}/src/data_designer/config/_version.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '0.4.0rc2'
-__version_tuple__ = version_tuple = (0, 4, 0, 'rc2')
+__version__ = version = '0.4.0rc3'
+__version_tuple__ = version_tuple = (0, 4, 0, 'rc3')
 
 __commit_id__ = commit_id = None

{data_designer_config-0.4.0rc2 → data_designer_config-0.4.0rc3}/src/data_designer/config/column_configs.py

@@ -14,7 +14,7 @@ from data_designer.config.errors import InvalidConfigError
 from data_designer.config.models import ImageContext
 from data_designer.config.sampler_params import SamplerParamsT, SamplerType
 from data_designer.config.utils.code_lang import CodeLang
-from data_designer.config.utils.constants import REASONING_TRACE_COLUMN_POSTFIX
+from data_designer.config.utils.constants import TRACE_COLUMN_POSTFIX
 from data_designer.config.utils.misc import assert_valid_jinja2_template, extract_keywords_from_jinja2_template
 from data_designer.config.validator_params import ValidatorParamsT, ValidatorType
 
@@ -143,8 +143,8 @@ class LLMTextColumnConfig(SingleColumnConfig):
 
     LLM text columns generate free-form text content using language models via LiteLLM.
     Prompts support Jinja2 templating to reference values from other columns, enabling
-    context-aware generation. The generated text can optionally include reasoning traces
-    when models support extended thinking.
+    context-aware generation. The generated text can optionally include message traces
+    capturing the full conversation history.
 
     Attributes:
         prompt: Prompt template for text generation. Supports Jinja2 syntax to
@@ -159,6 +159,10 @@ class LLMTextColumnConfig(SingleColumnConfig):
             `LLMStructuredColumnConfig` for structured output, `LLMCodeColumnConfig` for code.
         multi_modal_context: Optional list of image contexts for multi-modal generation.
             Enables vision-capable models to generate text based on image inputs.
+        with_trace: If True, creates a `{column_name}__trace` column containing the full
+            ordered message history (system/user/assistant) for the generation.
+            Can be overridden globally via `RunConfig.debug_override_save_all_column_traces`.
+            Defaults to False.
         column_type: Discriminator field, always "llm-text" for this configuration type.
     """
 
@@ -166,6 +170,7 @@ class LLMTextColumnConfig(SingleColumnConfig):
     model_alias: str
     system_prompt: str | None = None
     multi_modal_context: list[ImageContext] | None = None
+    with_trace: bool = False
     column_type: Literal["llm-text"] = "llm-text"
 
     @staticmethod
@@ -186,14 +191,15 @@ class LLMTextColumnConfig(SingleColumnConfig):
 
     @property
     def side_effect_columns(self) -> list[str]:
-        """Returns the reasoning trace column, which may be generated alongside the main column.
+        """Returns the trace column, which may be generated alongside the main column.
 
-        Reasoning traces are only returned if the served model parses and returns reasoning content.
+        Traces are generated when `with_trace=True` on the column config or
+        when `RunConfig.debug_override_save_all_column_traces=True` globally.
 
         Returns:
-            List containing the reasoning trace column name.
+            List containing the trace column name.
         """
-        return [f"{self.name}{REASONING_TRACE_COLUMN_POSTFIX}"]
+        return [f"{self.name}{TRACE_COLUMN_POSTFIX}"]
 
     @model_validator(mode="after")
     def assert_prompt_valid_jinja(self) -> Self:

{data_designer_config-0.4.0rc2 → data_designer_config-0.4.0rc3}/src/data_designer/config/run_config.py

@@ -33,6 +33,10 @@ 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
@@ -42,6 +46,7 @@ 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-0.4.0rc2 → data_designer_config-0.4.0rc3}/src/data_designer/config/utils/code_lang.py

@@ -7,9 +7,14 @@ from enum import Enum
 
 
 class CodeLang(str, Enum):
+    BASH = "bash"
+    C = "c"
+    COBOL = "cobol"
+    CPP = "cpp"
+    CSHARP = "csharp"
     GO = "go"
-    JAVASCRIPT = "javascript"
     JAVA = "java"
+    JAVASCRIPT = "javascript"
     KOTLIN = "kotlin"
     PYTHON = "python"
     RUBY = "ruby"
@@ -63,15 +68,21 @@ def code_lang_to_syntax_lexer(code_lang: CodeLang | str) -> str:
     Reference: https://pygments.org/docs/lexers/
     """
     code_lang_to_lexer = {
+        CodeLang.BASH: "bash",
+        CodeLang.C: "c",
+        CodeLang.COBOL: "cobol",
+        CodeLang.CPP: "cpp",
+        CodeLang.CSHARP: "csharp",
         CodeLang.GO: "golang",
-        CodeLang.JAVASCRIPT: "javascript",
         CodeLang.JAVA: "java",
+        CodeLang.JAVASCRIPT: "javascript",
         CodeLang.KOTLIN: "kotlin",
         CodeLang.PYTHON: "python",
         CodeLang.RUBY: "ruby",
         CodeLang.RUST: "rust",
         CodeLang.SCALA: "scala",
         CodeLang.SWIFT: "swift",
+        CodeLang.TYPESCRIPT: "typescript",
         CodeLang.SQL_SQLITE: "sql",
         CodeLang.SQL_ANSI: "sql",
         CodeLang.SQL_TSQL: "tsql",

{data_designer_config-0.4.0rc2 → data_designer_config-0.4.0rc3}/src/data_designer/config/utils/constants.py

@@ -166,7 +166,7 @@ MIN_TEMPERATURE = 0.0
 MAX_TOP_P = 1.0
 MIN_TOP_P = 0.0
 MIN_MAX_TOKENS = 1
-REASONING_TRACE_COLUMN_POSTFIX = "__reasoning_trace"
+TRACE_COLUMN_POSTFIX = "__trace"
 
 AVAILABLE_LOCALES = [
     "ar_AA",

{data_designer_config-0.4.0rc2 → data_designer_config-0.4.0rc3}/src/data_designer/logging.py

@@ -50,6 +50,14 @@ class LoggingConfig:
 class RandomEmoji:
     """A generator for various themed emoji collections."""
 
+    def __init__(self) -> None:
+        self._progress_style = random.choice(_PROGRESS_STYLES)
+
+    def progress(self, percent: float) -> str:
+        """Get a progress emoji based on completion percentage (0-100)."""
+        phase_idx = min(int(percent / 25), len(self._progress_style) - 1)
+        return self._progress_style[phase_idx]
+
     @staticmethod
     def cooking() -> str:
         """Get a random cooking or food preparation emoji."""
@@ -163,3 +171,10 @@ def _make_stream_formatter() -> logging.Formatter:
 
 
 _DEFAULT_NOISY_LOGGERS = ["httpx", "matplotlib"]
+
+
+_PROGRESS_STYLES: list[list[str]] = [
+    ["🌑", "🌘", "🌗", "🌖", "🌕"],  # Moon phases
+    ["🌧️", "🌦️", "⛅", "🌤️", "☀️"],  # Weather (storm to sun)
+    ["🥚", "🐣", "🐥", "🐤", "🐔"],  # Hatching (egg to chicken)
+]

{data_designer_config-0.4.0rc2 → data_designer_config-0.4.0rc3}/tests/config/test_columns.py

@@ -85,7 +85,7 @@ def test_llm_text_column_config():
     assert llm_text_column_config.system_prompt == stub_system_prompt
     assert llm_text_column_config.column_type == DataDesignerColumnType.LLM_TEXT
     assert set(llm_text_column_config.required_columns) == {"some_column", "some_other_column"}
-    assert llm_text_column_config.side_effect_columns == ["test_llm_text__reasoning_trace"]
+    assert llm_text_column_config.side_effect_columns == ["test_llm_text__trace"]
 
     # invalid prompt
     with pytest.raises(

{data_designer_config-0.4.0rc2 → data_designer_config-0.4.0rc3}/tests/config/utils/test_code_lang.py

@@ -26,7 +26,7 @@ def test_parse_dialect():
 
 
 def test_supported_values():
-    assert len(CodeLang.supported_values()) == 16
+    assert len(CodeLang.supported_values()) == 21
 
 
 def test_code_lang_to_syntax_lexer():

{data_designer_config-0.4.0rc2 → data_designer_config-0.4.0rc3}/tests/test_logging.py

@@ -208,3 +208,54 @@ def test_random_emoji_randomness():
     emojis = [RandomEmoji.magic() for _ in range(100)]
     # If we get 100 samples, we should get at least 2 different emojis
     assert len(set(emojis)) > 1
+
+
+def test_random_emoji_progress_returns_valid_emoji() -> None:
+    emoji_gen = RandomEmoji()
+    emoji = emoji_gen.progress(50.0)
+    assert emoji is not None
+    assert len(emoji) > 0
+
+
+def test_random_emoji_progress_is_deterministic() -> None:
+    emoji_gen = RandomEmoji()
+    # Same percentage should always return the same emoji for a given instance
+    assert emoji_gen.progress(0.0) == emoji_gen.progress(0.0)
+    assert emoji_gen.progress(50.0) == emoji_gen.progress(50.0)
+    assert emoji_gen.progress(100.0) == emoji_gen.progress(100.0)
+
+
+def test_random_emoji_progress_phases_are_distinct() -> None:
+    emoji_gen = RandomEmoji()
+    # Each 25% phase should return a different emoji
+    phase_emojis = [
+        emoji_gen.progress(0.0),  # phase 0
+        emoji_gen.progress(25.0),  # phase 1
+        emoji_gen.progress(50.0),  # phase 2
+        emoji_gen.progress(75.0),  # phase 3
+        emoji_gen.progress(100.0),  # phase 4
+    ]
+    # All 5 phases should have distinct emojis
+    assert len(set(phase_emojis)) == 5
+
+
+def test_random_emoji_progress_phase_boundaries() -> None:
+    emoji_gen = RandomEmoji()
+    # Values within the same phase should return the same emoji
+    assert emoji_gen.progress(0.0) == emoji_gen.progress(24.9)
+    assert emoji_gen.progress(25.0) == emoji_gen.progress(49.9)
+    assert emoji_gen.progress(50.0) == emoji_gen.progress(74.9)
+    assert emoji_gen.progress(75.0) == emoji_gen.progress(99.9)
+    # Phase transitions should return different emojis
+    assert emoji_gen.progress(24.9) != emoji_gen.progress(25.0)
+    assert emoji_gen.progress(49.9) != emoji_gen.progress(50.0)
+    assert emoji_gen.progress(74.9) != emoji_gen.progress(75.0)
+    assert emoji_gen.progress(99.9) != emoji_gen.progress(100.0)
+
+
+def test_random_emoji_progress_clamps_over_100() -> None:
+    emoji_gen = RandomEmoji()
+    emoji_100 = emoji_gen.progress(100.0)
+    emoji_over = emoji_gen.progress(150.0)
+    # Both should return the same final emoji
+    assert emoji_100 == emoji_over