classifyre-cli 0.4.55__tar.gz → 0.4.57__tar.gz

{classifyre_cli-0.4.55 → classifyre_cli-0.4.57}/.turbo/turbo-build.log

@@ -1,3 +1,3 @@
 $ uv sync
-Resolved 292 packages in 12ms
+Resolved 292 packages in 247ms
 Checked 51 packages in 1ms

{classifyre_cli-0.4.55 → classifyre_cli-0.4.57}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: classifyre-cli
-Version: 0.4.55
+Version: 0.4.57
 Summary: Classifyre CLI — scan and classify unstructured data sources
 License: MIT
 Keywords: data,ingestion,metadata,pii,secrets,unstructured
@@ -54,7 +54,7 @@ Commands:
 - `test` - test source connection.
 - `discover` - discover source resources.
 - `extract` - run extraction and emit batched output.
-- `sandbox` - run sandbox parsing/detectors for a local file.
+- `evaluate-file` - internally evaluate detectors against one local file.
 
 ## Extract Output Model
 
@@ -78,7 +78,7 @@ Default behavior:
 Global/common:
 
 - `--debug` - enable debug logging.
-- `--detectors-file <path>` - sandbox only.
+- `--detectors-file <path>` - file evaluation only.
 
 Extract output options:
 

{classifyre_cli-0.4.55 → classifyre_cli-0.4.57}/README.md

@@ -37,7 +37,7 @@ Commands:
 - `test` - test source connection.
 - `discover` - discover source resources.
 - `extract` - run extraction and emit batched output.
-- `sandbox` - run sandbox parsing/detectors for a local file.
+- `evaluate-file` - internally evaluate detectors against one local file.
 
 ## Extract Output Model
 
@@ -61,7 +61,7 @@ Default behavior:
 Global/common:
 
 - `--debug` - enable debug logging.
-- `--detectors-file <path>` - sandbox only.
+- `--detectors-file <path>` - file evaluation only.
 
 Extract output options:
 

{classifyre_cli-0.4.55 → classifyre_cli-0.4.57}/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@classifyre/cli",
-  "version": "0.4.55",
+  "version": "0.4.57",
   "private": true,
   "scripts": {
     "build": "uv sync",

{classifyre_cli-0.4.55 → classifyre_cli-0.4.57}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "classifyre-cli"
-version = "0.4.55"
+version = "0.4.57"
 description = "Classifyre CLI — scan and classify unstructured data sources"
 readme = "README.md"
 requires-python = ">=3.12"
@@ -83,7 +83,6 @@ content = [
 ]
 quality = [
     "datasketch>=1.10.0",
-    "sentence-transformers>=5.5.0",
     "textstat>=0.7.13",
     "transformers>=4.50.0,<6.0.0",
     "torch>=2.12.0",
@@ -101,7 +100,6 @@ custom = [
     "datasets>=4.8.5",
     "scikit-learn>=1.7.2",
     "gliner2>=1.3.1",
-    "sentence-transformers>=5.5.0",
     # Direct declaration so the [tool.uv.sources] cpu-index pin applies (timm
     # pulls torchvision transitively; see the ocr group note).
     "torchvision>=0.27.0",

{classifyre_cli-0.4.55 → classifyre_cli-0.4.57}/src/detectors/custom/runners/__init__.py

@@ -14,7 +14,6 @@ from ._base import (
     _resolve_pipeline_severity,
 )
 from ._factory import create_runner
-from ._feature_extraction import FeatureExtractionRunner, _chunk_text_with_offsets, _pool_hidden
 from ._gliner2 import (
     GLiNER2Runner,
     _apply_classification_validation,
@@ -35,7 +34,6 @@ __all__ = [
     "_IMAGE_CONTENT_TYPES",
     "_TEXT_CONTENT_TYPES",
     "BaseRunner",
-    "FeatureExtractionRunner",
     "GLiNER2Runner",
     "ImageClassificationRunner",
     "LLMRunner",
@@ -45,12 +43,10 @@ __all__ = [
     "_apply_classification_validation",
     "_apply_entity_validation",
     "_chunk_text",
-    "_chunk_text_with_offsets",
     "_load_regex_engine",
     "_normalise_classification_output",
     "_normalise_entity_output",
     "_normalise_span",
-    "_pool_hidden",
     "_resolve_pipeline_severity",
     "create_runner",
 ]

{classifyre_cli-0.4.55 → classifyre_cli-0.4.57}/src/detectors/custom/runners/_factory.py

@@ -3,7 +3,6 @@
 from __future__ import annotations
 
 from ....models.generated_detectors import (
-    FeatureExtractionPipelineSchema,
     GLiNER2PipelineSchema,
     ImageClassificationPipelineSchema,
     LLMPipelineSchema,
@@ -12,7 +11,6 @@ from ....models.generated_detectors import (
     TextClassificationPipelineSchema,
 )
 from ._base import BaseRunner
-from ._feature_extraction import FeatureExtractionRunner
 from ._gliner2 import GLiNER2Runner
 from ._image_classification import ImageClassificationRunner
 from ._llm import LLMRunner
@@ -28,7 +26,6 @@ def create_runner(
         | LLMPipelineSchema
         | TextClassificationPipelineSchema
         | ImageClassificationPipelineSchema
-        | FeatureExtractionPipelineSchema
         | ObjectDetectionPipelineSchema
     ),
     detector_key: str = "",
@@ -39,8 +36,6 @@ def create_runner(
         return TextClassificationRunner(schema, detector_key, detector_name)
     if isinstance(schema, ImageClassificationPipelineSchema):
         return ImageClassificationRunner(schema, detector_key, detector_name)
-    if isinstance(schema, FeatureExtractionPipelineSchema):
-        return FeatureExtractionRunner(schema, detector_key, detector_name)
     if isinstance(schema, ObjectDetectionPipelineSchema):
         return ObjectDetectionRunner(schema, detector_key, detector_name)
     if isinstance(schema, RegexPipelineSchema):

classifyre_cli-0.4.57/src/file_evaluation/__init__.py

@@ -0,0 +1,5 @@
+"""Internal runner for evaluating detectors on local files."""
+
+from .runner import FileEvaluationRunner
+
+__all__ = ["FileEvaluationRunner"]

{classifyre_cli-0.4.55/src/sandbox → classifyre_cli-0.4.57/src/file_evaluation}/runner.py

@@ -1,4 +1,4 @@
-"""SandboxRunner: run detectors on a local file."""
+"""FileEvaluationRunner: run detectors on an ephemeral local file."""
 
 from __future__ import annotations
 
@@ -15,7 +15,7 @@ from ..utils.file_parser import ParsedFile, parse_file
 logger = logging.getLogger(__name__)
 
 
-class SandboxRunner:
+class FileEvaluationRunner:
     """Run a set of detectors against a single local file."""
 
     def __init__(self, detectors_config: list[dict[str, Any]]) -> None:
@@ -41,7 +41,7 @@ class SandboxRunner:
 
                 detector = get_detector(detector_name, typed_config)
                 detectors.append(detector)
-                logger.info(f"Initialized sandbox detector: {detector_name}")
+                logger.info(f"Initialized file-evaluation detector: {detector_name}")
             except Exception as e:
                 logger.error(f"Failed to initialize detector {detector_type}: {e}")
 
@@ -121,19 +121,23 @@ class SandboxRunner:
                 and self._is_binary_detector(detector)
                 and self._supports_mime(supported, mime_type)
             ):
-                logger.info("Sandbox: dispatching '%s' on file bytes (%s)", label, mime_type)
+                logger.info(
+                    "File evaluation: dispatching '%s' on file bytes (%s)", label, mime_type
+                )
                 tasks.append(detector.detect(_get_raw_bytes(), mime_type))
                 active_detectors.append(detector)
             # Text delivery: text detectors get the extracted text layer.
             elif "text/plain" in supported and text.strip():
                 logger.info(
-                    "Sandbox: dispatching '%s' on extracted text (%d chars)", label, len(text)
+                    "File evaluation: dispatching '%s' on extracted text (%d chars)",
+                    label,
+                    len(text),
                 )
                 tasks.append(detector.detect(text, "text/plain"))
                 active_detectors.append(detector)
             else:
                 logger.info(
-                    "Sandbox: '%s' not dispatched on whole file (supports=%s, file_mime=%s)",
+                    "File evaluation: '%s' not dispatched on whole file (supports=%s, file_mime=%s)",
                     label,
                     supported,
                     file_mime,
@@ -158,18 +162,20 @@ class SandboxRunner:
         for detector, result in zip(active_detectors, results, strict=False):
             label = self._detector_label(detector)
             if isinstance(result, Exception):
-                logger.error("Sandbox: '%s' failed on whole file: %s", label, result)
+                logger.error("File evaluation: '%s' failed on whole file: %s", label, result)
                 continue
             if isinstance(result, list):
                 detector_findings = [f for f in result if isinstance(f, DetectionResult)]
                 logger.info(
-                    "Sandbox: '%s' on whole file → %d finding(s)", label, len(detector_findings)
+                    "File evaluation: '%s' on whole file → %d finding(s)",
+                    label,
+                    len(detector_findings),
                 )
                 for finding in detector_findings:
                     all_findings.append(
                         finding.model_copy(
                             update={
-                                "runner_id": "sandbox",
+                                "runner_id": "file-evaluation",
                                 "detected_at": detected_at,
                             }
                         )
@@ -203,14 +209,14 @@ class SandboxRunner:
         binary_detectors = [d for d in detectors if self._is_binary_detector(d)]
         if not binary_detectors:
             logger.info(
-                "Sandbox: %s embeds images but no image-capable detectors are configured; "
+                "File evaluation: %s embeds images but no image-capable detectors are configured; "
                 "skipping embedded-image scan",
                 mime_type,
             )
             return []
 
         logger.info(
-            "Sandbox: scanning images embedded in %s with image detectors: [%s]",
+            "File evaluation: scanning images embedded in %s with image detectors: [%s]",
             mime_type,
             ", ".join(self._detector_label(d) for d in binary_detectors),
         )
@@ -227,14 +233,14 @@ class SandboxRunner:
             ]
             if not compatible:
                 logger.info(
-                    "Sandbox: embedded image %s (%s, %.0f KB) — no compatible detector",
+                    "File evaluation: embedded image %s (%s, %.0f KB) — no compatible detector",
                     image.location,
                     image.mime_type,
                     size_kb,
                 )
                 continue
             logger.info(
-                "Sandbox: embedded image %s (%s, %.0f KB) → dispatching [%s]",
+                "File evaluation: embedded image %s (%s, %.0f KB) → dispatching [%s]",
                 image.location,
                 image.mime_type,
                 size_kb,
@@ -246,7 +252,7 @@ class SandboxRunner:
                     result = await detector.detect(image.image_bytes, image.mime_type)
                 except Exception as exc:
                     logger.error(
-                        "Sandbox: '%s' failed on embedded image %s: %s",
+                        "File evaluation: '%s' failed on embedded image %s: %s",
                         label,
                         image.location,
                         exc,
@@ -258,7 +264,7 @@ class SandboxRunner:
                     else []
                 )
                 logger.info(
-                    "Sandbox: '%s' on embedded image %s → %d finding(s)",
+                    "File evaluation: '%s' on embedded image %s → %d finding(s)",
                     label,
                     image.location,
                     len(detector_findings),
@@ -267,7 +273,7 @@ class SandboxRunner:
                     findings.append(self._tag_embedded(finding, image.location, detected_at))
 
         logger.info(
-            "Sandbox: embedded-image scan complete — %d image(s) scanned, %d finding(s)",
+            "File evaluation: embedded-image scan complete — %d image(s) scanned, %d finding(s)",
             image_count,
             len(findings),
         )
@@ -296,7 +302,7 @@ class SandboxRunner:
             location = location.model_copy(update={"path": location_label})
         return finding.model_copy(
             update={
-                "runner_id": "sandbox",
+                "runner_id": "file-evaluation",
                 "detected_at": detected_at,
                 "metadata": metadata,
                 "location": location,

{classifyre_cli-0.4.55 → classifyre_cli-0.4.57}/src/main.py

@@ -131,6 +131,10 @@ async def run_command_async(args: argparse.Namespace, recipe: dict[str, Any]) ->
     source_id = args.source_id or os.environ.get("SOURCE_ID")
     if source_id:
         os.environ["SOURCE_ID"] = source_id
+    if getattr(args, "output_rest_url", None):
+        # Sources such as SANDBOX use the same managed-job API base URL as the
+        # REST output sink to list and stream their input content.
+        os.environ["CLASSIFYRE_OUTPUT_REST_URL"] = args.output_rest_url
 
     try:
         try:
@@ -264,7 +268,7 @@ async def run_command_async(args: argparse.Namespace, recipe: dict[str, Any]) ->
                     logger.info("Phase 1 complete: %d assets discovered", total_assets)
 
                     # --- Phase 2: Processing ---
-                    if has_detectors and all_stubs:
+                    if all_stubs:
                         import asyncio as _asyncio
 
                         processed_count = 0
@@ -319,6 +323,10 @@ async def run_command_async(args: argparse.Namespace, recipe: dict[str, Any]) ->
                                 )
                                 payload = _asset_to_payload(result)
                                 await sink.emit_batch([payload], skip_findings=False)
+                                if hasattr(sink, "emit_text_chunks"):
+                                    artifact = pipeline.take_text_artifact(asset_hash)
+                                    if artifact is not None:
+                                        await sink.emit_text_chunks(asset_hash, artifact)
 
                                 if hasattr(sink, "update_asset_status"):
                                     f_total, f_by_sev, f_by_det = _compute_findings_counts(
@@ -353,22 +361,6 @@ async def run_command_async(args: argparse.Namespace, recipe: dict[str, Any]) ->
                             processed_count,
                             error_count,
                         )
-                    elif all_stubs and hasattr(sink, "update_asset_status"):
-                        # No detectors configured: mark discovered assets as PROCESSED
-                        import asyncio as _asyncio
-
-                        async def _mark_processed(asset: Any) -> None:
-                            asset_hash = getattr(asset, "hash", None) or ""
-                            await sink.update_asset_status(
-                                asset_hash, "PROCESSED", findings_total=0
-                            )
-
-                        tasks = [_asyncio.create_task(_mark_processed(a)) for a in all_stubs]
-                        await _asyncio.gather(*tasks, return_exceptions=True)
-                        logger.info(
-                            "Phase 2 skipped (no detectors): %d assets marked processed",
-                            len(all_stubs),
-                        )
 
                     # Persist the advanced AUTOMATIC sampling cursor (no-op for
                     # other strategies, which return None). Only on the normal
@@ -473,13 +465,13 @@ def run_train_command(args: argparse.Namespace) -> None:
     print(json.dumps(result.to_dict()))
 
 
-def run_sandbox_command(args: argparse.Namespace) -> None:
-    """Execute the sandbox command: parse file + run detectors."""
-    from .sandbox import SandboxRunner
+def run_evaluate_file_command(args: argparse.Namespace) -> None:
+    """Evaluate detector configs against one ephemeral local file."""
+    from .file_evaluation import FileEvaluationRunner
 
     file_path_str: str | None = args.recipe
     if not file_path_str:
-        logger.error("sandbox command requires a file path as the first argument")
+        logger.error("evaluate-file requires a file path as the first argument")
         sys.exit(1)
 
     file_path = Path(file_path_str)
@@ -504,7 +496,7 @@ def run_sandbox_command(args: argparse.Namespace) -> None:
             sys.exit(1)
 
     try:
-        runner = SandboxRunner(detectors)
+        runner = FileEvaluationRunner(detectors)
         parsed, findings = runner.run(file_path)
         if parsed.parse_error:
             logger.warning("File parse warning: %s", parsed.parse_error)
@@ -516,7 +508,7 @@ def run_sandbox_command(args: argparse.Namespace) -> None:
             output["parse_error"] = parsed.parse_error
         print(json.dumps(_sanitize_for_json(output), ensure_ascii=False))
     except Exception as e:
-        logger.error("Sandbox run failed: %s", e, exc_info=True)
+        logger.error("File evaluation failed: %s", e, exc_info=True)
         sys.exit(1)
 
 
@@ -532,14 +524,14 @@ def main() -> None:
     parser = argparse.ArgumentParser(description="Classifyre Metadata Extraction CLI")
     parser.add_argument(
         "command",
-        choices=["test", "extract", "discover", "sandbox", "train"],
+        choices=["test", "extract", "discover", "evaluate-file", "train"],
         help="Command to run",
     )
     parser.add_argument(
         "recipe",
         nargs="?",
         default=None,
-        help="Path to recipe JSON (or file path for sandbox command)",
+        help="Path to recipe JSON (or file path for evaluate-file)",
     )
     parser.add_argument("--debug", action="store_true", help="Enable debug logging")
     parser.add_argument(
@@ -577,7 +569,7 @@ def main() -> None:
     parser.add_argument(
         "--detectors-file",
         default=None,
-        help="Path to JSON file with detector configs (sandbox command only)",
+        help="Path to JSON file with detector configs (evaluate-file only)",
     )
     # train-command arguments
     parser.add_argument(
@@ -641,8 +633,8 @@ def main() -> None:
     if args.debug:
         logging.getLogger().setLevel(logging.DEBUG)
 
-    if args.command == "sandbox":
-        run_sandbox_command(args)
+    if args.command == "evaluate-file":
+        run_evaluate_file_command(args)
         return
 
     if args.command == "train":

{classifyre_cli-0.4.55 → classifyre_cli-0.4.57}/src/models/generated_detectors.py

@@ -75,6 +75,7 @@ class SourceAssetType(StrEnum):
     ORACLE = 'ORACLE'
     HIVE = 'HIVE'
     POWERBI = 'POWERBI'
+    SANDBOX = 'SANDBOX'
 
 
 class DetectorLifecycleStatus(StrEnum):
@@ -1255,78 +1256,6 @@ class ImageClassificationPipelineSchema(BaseModel):
 
 
 class Type7(StrEnum):
-    FEATURE_EXTRACTION = 'FEATURE_EXTRACTION'
-
-
-class PoolingStrategy(StrEnum):
-    """
-    How to aggregate per-token hidden states into a single embedding vector.
-    """
-
-    mean = 'mean'
-    cls = 'cls'
-    max = 'max'
-    none = 'none'
-
-
-class ChunkSize2(RootModel[int]):
-    root: int = Field(
-        None,
-        description='Split text into chunks of this many characters before embedding. Each chunk produces its own finding.',
-        ge=1,
-    )
-
-
-class FeatureExtractionPipelineSchema(BaseModel):
-    """
-    Feature extraction (embedding) pipeline using a HuggingFace model. Runs a single encoder; create multiple custom detectors to run multiple embedding models.
-    """
-
-    model_config = ConfigDict(
-        extra='forbid',
-    )
-    type: Literal['FEATURE_EXTRACTION']
-    model: str = Field(
-        ...,
-        description="HuggingFace hub ID (e.g. 'BAAI/bge-base-en-v1.5', 'sentence-transformers/all-MiniLM-L6-v2') or absolute local directory path.",
-    )
-    model_revision: str | None = Field(
-        None,
-        description='Git branch, tag, or commit hash when fetching from the HuggingFace hub.',
-    )
-    device: str | None = Field(
-        'cpu',
-        description="Inference device: 'cpu' (default), 'cuda', 'mps', or a CUDA device string like 'cuda:0'.",
-    )
-    pooling_strategy: PoolingStrategy | None = Field(
-        'mean',
-        description='How to aggregate per-token hidden states into a single embedding vector.',
-    )
-    normalize_embeddings: bool | None = Field(
-        True,
-        description='L2-normalise the final embedding vector. Recommended for cosine-similarity workloads.',
-    )
-    truncation: bool | None = Field(
-        True, description="Truncate input to the model's maximum sequence length."
-    )
-    max_length: int | None = Field(
-        None, description="Override the tokenizer's default maximum sequence length."
-    )
-    batch_size: int | None = Field(
-        8, description='Number of texts to encode in a single forward pass.'
-    )
-    chunk_size: ChunkSize2 | None = Field(
-        None,
-        description='Split text into chunks of this many characters before embedding. Each chunk produces its own finding.',
-    )
-    chunk_overlap: ChunkOverlap1 | None = Field(
-        0,
-        description='Character overlap between consecutive chunks.',
-        validate_default=True,
-    )
-
-
-class Type8(StrEnum):
     OBJECT_DETECTION = 'OBJECT_DETECTION'
 
 
@@ -1407,7 +1336,6 @@ class CustomDetectorConfig(DetectorConfig):
         | LLMPipelineSchema
         | TextClassificationPipelineSchema
         | ImageClassificationPipelineSchema
-        | FeatureExtractionPipelineSchema
         | ObjectDetectionPipelineSchema
         | None
     ) = Field(None, discriminator='type', title='AnyPipelineSchema')

{classifyre_cli-0.4.55 → classifyre_cli-0.4.57}/src/models/generated_input.py

@@ -54,6 +54,7 @@ class AssetType(StrEnum):
     LOCAL_FOLDER = 'LOCAL_FOLDER'
     MICROSOFT_365 = 'MICROSOFT_365'
     GOOGLE_WORKSPACE = 'GOOGLE_WORKSPACE'
+    SANDBOX = 'SANDBOX'
 
 
 class DetectorType(StrEnum):
@@ -353,6 +354,7 @@ class Type(StrEnum):
     LOCAL_FOLDER = 'LOCAL_FOLDER'
     MICROSOFT_365 = 'MICROSOFT_365'
     GOOGLE_WORKSPACE = 'GOOGLE_WORKSPACE'
+    SANDBOX = 'SANDBOX'
 
 
 class YouTubeRequired(BaseModel):
@@ -648,6 +650,32 @@ class LocalFolderRequired(BaseModel):
     )
 
 
+class SandboxRequired(BaseModel):
+    """
+    Sandbox files are uploaded separately through the source files API.
+    """
+
+    model_config = ConfigDict(
+        extra='forbid',
+    )
+
+
+class SandboxMasked(BaseModel):
+    """
+    Sandbox sources do not require credentials.
+    """
+
+    model_config = ConfigDict(
+        extra='forbid',
+    )
+
+
+class SandboxOptional(BaseModel):
+    model_config = ConfigDict(
+        extra='forbid',
+    )
+
+
 class LocalFolderMasked(BaseModel):
     """
     Local folder scans run with the desktop application's filesystem permissions; no credentials are required.
@@ -2170,6 +2198,24 @@ class LocalFolderInput(CoreInput):
     resources: ResourceOverrides | None = None
 
 
+class SandboxInput(CoreInput):
+    type: Literal['SANDBOX'] | None = Field(
+        None, description='Type of the asset or source'
+    )
+    required: SandboxRequired
+    masked: SandboxMasked | None = None
+    optional: SandboxOptional | None = None
+    detectors: list[Detector] | None = Field(
+        None, description='Detectors to run on ingested content'
+    )
+    custom_detectors: list[CustomDetectorSelection] | None = Field(
+        None,
+        description='Reusable custom detector IDs selected from the custom detector catalog.',
+    )
+    sampling: SamplingConfig
+    resources: ResourceOverrides | None = None
+
+
 class AzureBlobStorageInput(CoreInput):
     type: Literal['AZURE_BLOB_STORAGE'] | None = Field(
         None, description='Type of the asset or source'
@@ -2601,7 +2647,7 @@ class ConfluenceOptionalConnection(BaseModel):
     )
 
 
-class Type19(StrEnum):
+class Type20(StrEnum):
     """
     Filter spaces by space type
     """
@@ -2638,7 +2684,7 @@ class ConfluenceOptionalScopeSpaces(BaseModel):
     keys: list[str] | None = Field(
         None, description='Filter spaces by keys (up to 250)', max_length=250
     )
-    type: Type19 | None = Field(None, description='Filter spaces by space type')
+    type: Type20 | None = Field(None, description='Filter spaces by space type')
     status: Status | None = Field(None, description='Filter spaces by status')
     labels: list[str] | None = Field(
         None,
@@ -2904,7 +2950,7 @@ class ServiceDeskOptional(BaseModel):
     content: ServiceDeskOptionalContent | None = None
 
 
-class Type20(StrEnum):
+class Type21(StrEnum):
     """
     Type of the asset or source
     """
@@ -2941,6 +2987,7 @@ class Type20(StrEnum):
     LOCAL_FOLDER = 'LOCAL_FOLDER'
     MICROSOFT_365 = 'MICROSOFT_365'
     GOOGLE_WORKSPACE = 'GOOGLE_WORKSPACE'
+    SANDBOX = 'SANDBOX'
 
 
 class ConfluenceInput(CoreInput):
@@ -4075,7 +4122,8 @@ class IcebergInput(CoreInput):
 
 class SourceInput(
     RootModel[
-        SlackInput
+        SandboxInput
+        | SlackInput
         | S3CompatibleStorageInput
         | LocalFolderInput
         | AzureBlobStorageInput
@@ -4110,7 +4158,8 @@ class SourceInput(
     ]
 ):
     root: (
-        SlackInput
+        SandboxInput
+        | SlackInput
         | S3CompatibleStorageInput
         | LocalFolderInput
         | AzureBlobStorageInput

{classifyre_cli-0.4.55 → classifyre_cli-0.4.57}/src/models/generated_single_asset_scan_results.py

@@ -87,6 +87,19 @@ class Location(BaseModel):
     end: int | None = Field(None, description='End offset (0-indexed)')
 
 
+class TextExtractionStatus(StrEnum):
+    """
+    Structured text coverage outcome. EXTRACTED means detector-visible text was produced. EMPTY means extraction completed without an error but yielded no text. ENGINE_UNAVAILABLE, ZERO_FRAMES, and FAILED are incomplete coverage states and must not be treated as an empty document.
+    """
+
+    NOT_APPLICABLE = 'NOT_APPLICABLE'
+    EXTRACTED = 'EXTRACTED'
+    EMPTY = 'EMPTY'
+    ENGINE_UNAVAILABLE = 'ENGINE_UNAVAILABLE'
+    ZERO_FRAMES = 'ZERO_FRAMES'
+    FAILED = 'FAILED'
+
+
 class DetectionResult(BaseModel):
     """
     Result from detector scan
@@ -221,6 +234,10 @@ class ScanStats(BaseModel):
         None,
         description="True when an asset that should carry text yielded none. Most significant for assets whose text is derived rather than native (OCR'd images and scanned PDFs, transcribed audio/video): empty derived text means the content may have been missed entirely, not that the document is blank. Distinct from an error — nothing failed — so it is reported as coverage, not as a run failure.",
     )
+    text_extraction_status: TextExtractionStatus | None = Field(
+        None,
+        description='Structured text coverage outcome. EXTRACTED means detector-visible text was produced. EMPTY means extraction completed without an error but yielded no text. ENGINE_UNAVAILABLE, ZERO_FRAMES, and FAILED are incomplete coverage states and must not be treated as an empty document.',
+    )
     findings_count: int | None = Field(
         None, description='Total number of findings detected'
     )