classifyre-cli 0.4.66__tar.gz → 0.4.68__tar.gz

{classifyre_cli-0.4.66 → classifyre_cli-0.4.68}/.turbo/turbo-build.log

@@ -1,3 +1,3 @@
 $ uv sync
-Resolved 300 packages in 215ms
+Resolved 300 packages in 269ms
 Checked 51 packages in 1ms

{classifyre_cli-0.4.66 → classifyre_cli-0.4.68}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: classifyre-cli
-Version: 0.4.66
+Version: 0.4.68
 Summary: Classifyre CLI — scan and classify unstructured data sources
 License: MIT
 Keywords: data,ingestion,metadata,pii,secrets,unstructured
@@ -84,7 +84,7 @@ Extract output options:
 
 - `--output-type rest|file|console`
 - `--output-batch-size <int>`
-- `--output-rest-url <url>`
+- `--output-rest-url <url>` (complete API base, including the namespace path)
 - `--output-file-path <path>`
 - `--source-id <uuid>`
 - `--runner-id <uuid>`
@@ -131,7 +131,7 @@ uv run main.py extract ./wordpress-recipe.json \
 Notes:
 
 - `--runner-id` optional for manual runs. If omitted, CLI creates external runner automatically.
-- `--output-rest-url` is optional. If omitted, CLI uses `CLASSIFYRE_OUTPUT_REST_URL`, then `API_URL`, then `http://localhost:8000`.
+- `--output-rest-url` is optional. If omitted, CLI uses `CLASSIFYRE_OUTPUT_REST_URL`, then `API_URL`, then `http://localhost:8000`. In a namespaced deployment, pass the complete base (for example `https://api.example/ns-id`); the CLI appends all asset, finding, runner, and source endpoints beneath it.
 - `--managed-runner` should be used only for API-orchestrated runs where runner already exists.
 
 ### 4) REST output with explicit runner (managed/orchestrated style)

{classifyre_cli-0.4.66 → classifyre_cli-0.4.68}/README.md

@@ -67,7 +67,7 @@ Extract output options:
 
 - `--output-type rest|file|console`
 - `--output-batch-size <int>`
-- `--output-rest-url <url>`
+- `--output-rest-url <url>` (complete API base, including the namespace path)
 - `--output-file-path <path>`
 - `--source-id <uuid>`
 - `--runner-id <uuid>`
@@ -114,7 +114,7 @@ uv run main.py extract ./wordpress-recipe.json \
 Notes:
 
 - `--runner-id` optional for manual runs. If omitted, CLI creates external runner automatically.
-- `--output-rest-url` is optional. If omitted, CLI uses `CLASSIFYRE_OUTPUT_REST_URL`, then `API_URL`, then `http://localhost:8000`.
+- `--output-rest-url` is optional. If omitted, CLI uses `CLASSIFYRE_OUTPUT_REST_URL`, then `API_URL`, then `http://localhost:8000`. In a namespaced deployment, pass the complete base (for example `https://api.example/ns-id`); the CLI appends all asset, finding, runner, and source endpoints beneath it.
 - `--managed-runner` should be used only for API-orchestrated runs where runner already exists.
 
 ### 4) REST output with explicit runner (managed/orchestrated style)

{classifyre_cli-0.4.66 → classifyre_cli-0.4.68}/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@classifyre/cli",
-  "version": "0.4.66",
+  "version": "0.4.68",
   "private": true,
   "scripts": {
     "build": "uv sync",

{classifyre_cli-0.4.66 → classifyre_cli-0.4.68}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "classifyre-cli"
-version = "0.4.66"
+version = "0.4.68"
 description = "Classifyre CLI — scan and classify unstructured data sources"
 readme = "README.md"
 requires-python = ">=3.12"

{classifyre_cli-0.4.66 → classifyre_cli-0.4.68}/src/main.py

@@ -400,7 +400,7 @@ async def run_command_async(args: argparse.Namespace, recipe: dict[str, Any]) ->
                                     try:
                                         error_msg = str(exc) or type(exc).__name__
                                         await sink.update_asset_status(
-                                            asset_hash, "ERROR", error_msg
+                                            asset_hash, "ERROR", error_message=error_msg
                                         )
                                     except Exception:
                                         pass
@@ -612,8 +612,8 @@ def main() -> None:
         "--output-rest-url",
         default=None,
         help=(
-            "REST output base URL (defaults to CLASSIFYRE_OUTPUT_REST_URL, API_URL, "
-            "or http://localhost:8000)"
+            "Complete REST API base URL, including any namespace/path prefix "
+            "(defaults to CLASSIFYRE_OUTPUT_REST_URL, API_URL, or http://localhost:8000)"
         ),
     )
     parser.add_argument(

{classifyre_cli-0.4.66 → classifyre_cli-0.4.68}/src/outputs/rest.py

@@ -334,6 +334,7 @@ class RestOutputSink:
         self,
         asset_hash: str,
         status: str,
+        *,
         error_message: str | None = None,
         findings_total: int | None = None,
         findings_by_severity: dict[str, int] | None = None,

{classifyre_cli-0.4.66 → classifyre_cli-0.4.68}/src/sources/email/source.py

@@ -318,7 +318,14 @@ class EmailSource(BaseSource):
         if self.include_attachments:
             for idx, att in enumerate(msg.attachments or []):
                 asset = self._attachment_to_asset(
-                    att, idx, message_id, email_hash, email_url, folder, msg.uid, created
+                    att,
+                    idx,
+                    message_id=message_id,
+                    email_hash=email_hash,
+                    email_url=email_url,
+                    folder=folder,
+                    uid=msg.uid,
+                    created=created,
                 )
                 attachment_assets.append(asset)
                 attachment_hashes.append(asset.hash)
@@ -376,6 +383,7 @@ class EmailSource(BaseSource):
         self,
         att: Any,
         idx: int,
+        *,
         message_id: str,
         email_hash: str,
         email_url: str,

{classifyre_cli-0.4.66 → classifyre_cli-0.4.68}/src/sources/mssql/source.py

@@ -209,6 +209,7 @@ class MSSQLSource(BaseTabularSource):
         self,
         conn: Any,
         base_query: str,
+        *,
         page_size: int,
         pk_columns: list[str],
         pk_order: str,

{classifyre_cli-0.4.66 → classifyre_cli-0.4.68}/src/sources/oracle/source.py

@@ -178,6 +178,7 @@ class OracleSource(BaseTabularSource):
         self,
         conn: Any,
         base_query: str,
+        *,
         page_size: int,
         pk_columns: list[str],
         pk_order: str,

{classifyre_cli-0.4.66 → classifyre_cli-0.4.68}/src/sources/tabular_base.py

@@ -9,6 +9,7 @@ excluded schemas, random function, etc.).
 from __future__ import annotations
 
 import asyncio
+import functools
 import logging
 import threading
 from abc import abstractmethod
@@ -536,6 +537,7 @@ class BaseTabularSource(BaseSource):
         self,
         conn: Any,
         base_query: str,
+        *,
         page_size: int,
         pk_columns: list[str],
         pk_order: str,
@@ -659,7 +661,12 @@ class BaseTabularSource(BaseSource):
             last_pk_values = saved_pk if isinstance(saved_pk, list) and saved_pk else None
             pk_order = ", ".join(self._quote_identifier(c) for c in pk_columns)
             rows, column_names = self._fetch_page_keyset(
-                conn, base_query, rows_per_page, pk_columns, pk_order, last_pk_values
+                conn,
+                base_query,
+                page_size=rows_per_page,
+                pk_columns=pk_columns,
+                pk_order=pk_order,
+                last_pk_values=last_pk_values,
             )
             if not rows or len(rows) < rows_per_page:
                 next_state: dict[str, Any] | None = None  # exhausted → wrap next run
@@ -919,13 +926,15 @@ class BaseTabularSource(BaseSource):
 
                 if use_keyset:
                     rows, column_names = await asyncio.to_thread(
-                        self._fetch_page_keyset,
-                        conn,
-                        query,
-                        rows_per_page,
-                        pk_columns,
-                        pk_order,
-                        last_pk_values,
+                        functools.partial(
+                            self._fetch_page_keyset,
+                            conn,
+                            query,
+                            page_size=rows_per_page,
+                            pk_columns=pk_columns,
+                            pk_order=pk_order,
+                            last_pk_values=last_pk_values,
+                        )
                     )
                 else:
                     rows = await asyncio.to_thread(self._cursor_fetchmany, cursor, rows_per_page)

{classifyre_cli-0.4.66 → classifyre_cli-0.4.68}/tests/test_email_source.py

@@ -29,6 +29,7 @@ class FakeMsg:
         uid,
         subject,
         from_,
+        *,
         to=(),
         cc=(),
         date=None,

{classifyre_cli-0.4.66 → classifyre_cli-0.4.68}/tests/test_outputs.py

@@ -215,6 +215,45 @@ async def test_rest_output_managed_runner_flow(monkeypatch: pytest.MonkeyPatch)
     assert "samplingCursor" not in fake_session.calls[1]["json"]
 
 
+@pytest.mark.asyncio
+async def test_rest_output_keeps_namespace_base_for_discovery_and_finding_batches(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    fake_session = _FakeSession(responses=[_FakeResponse({}), _FakeResponse({})])
+    monkeypatch.setattr("src.outputs.rest.requests.Session", lambda: fake_session)
+
+    context = OutputRuntimeContext(
+        source_id="source-1",
+        runner_id="runner-1",
+        managed_runner=True,
+        batch_size=20,
+    )
+    sink = RestOutputSink(
+        context,
+        base_url="http://api.internal/prefix/namespace-id/",
+        timeout_sec=30,
+    )
+
+    await sink.register_discovered_assets(["hash-1", "hash-2"])
+    await sink.emit_batch(
+        [
+            {
+                "hash": "hash-1",
+                "findings": [{"finding_type": "EMAIL", "matched_content": "a@b.test"}],
+            }
+        ]
+    )
+
+    assert fake_session.calls[0]["url"] == (
+        "http://api.internal/prefix/namespace-id/runners/runner-1/assets/discover"
+    )
+    assert fake_session.calls[0]["json"]["assetHashes"] == ["hash-1", "hash-2"]
+    assert fake_session.calls[1]["url"] == (
+        "http://api.internal/prefix/namespace-id/sources/source-1/assets/bulk"
+    )
+    assert fake_session.calls[1]["json"]["assets"][0]["findings"][0]["finding_type"] == "EMAIL"
+
+
 @pytest.mark.asyncio
 async def test_rest_output_finalize_includes_sampling_cursor(
     monkeypatch: pytest.MonkeyPatch,