mammoth-cli 2.2.87__tar.gz → 2.2.89__tar.gz

{mammoth_cli-2.2.87 → mammoth_cli-2.2.89}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mammoth-cli
-Version: 2.2.87
+Version: 2.2.89
 Summary: Command-line interface for the Mammoth Analytics platform
 Project-URL: homepage, https://mammoth.io
 Project-URL: repository, https://github.com/EdgeMetric/mammothsdk

{mammoth_cli-2.2.87 → mammoth_cli-2.2.89}/mammoth_cli/__init__.py

@@ -6,7 +6,7 @@ not implement a second HTTP client and does not call private SDK members.
 
 from __future__ import annotations
 
-__version__ = "2.2.87"
+__version__ = "2.2.89"
 
 # The versioned machine output envelope contract.
 SCHEMA_VERSION = 1

{mammoth_cli-2.2.87 → mammoth_cli-2.2.89}/mammoth_cli/bundled_skill/mammoth-cli/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: mammoth-cli
-version: 2.2.87
+version: 2.2.89
 description: "Use Mammoth Analytics from a terminal: install or authenticate the CLI, discover its live command contract, and safely manage projects, data, views, pipelines (join, merge, pivot, filter, clean), dashboards, exports, and handoffs."
 ---
 

{mammoth_cli-2.2.87 → mammoth_cli-2.2.89}/mammoth_cli/commands/dataset.py

@@ -40,6 +40,8 @@ from mammoth_cli.services.delete_check import ensure_deleted, find_dependents
 from mammoth_cli.services.field_enums import DATA_PULL_FILE_VALUES, allowed_values_text
 from mammoth_cli.services.listing import (
     DATASET_ROW_FIELDS,
+    NAMES_DATA_BUDGET,
+    NAMES_MAX_ROWS,
     ambiguity_note,
     compact_columns,
     dataset_summary,
@@ -755,6 +757,10 @@ def dataset_list(invocation: Invocation) -> HandlerResult:
     only the cheap fields, so it holds no row counts or column names: ``view list
     DATASET_ID`` shows a dataset's columns, and ``dataset find --input '{"columns":
     [...]}'`` finds the dataset that has given columns.
+    The result carries ``total``, the project's whole dataset count, so "how many
+    datasets" never needs paging: read ``total`` with the first page's newest names.
+    For a list of names (e.g. "which files can I see?") pass ``names: true``: ONE call
+    returns up to 500 bare ``{id, name}`` rows, newest first, with ``total`` and ``more``.
     ``full: true`` returns the raw ``{id, name}`` list instead. ``name`` keeps only datasets
     whose name contains it (case-insensitive) across every page, as short rows without
     column lists; ``limit``/``offset`` then page over the matches.
@@ -765,6 +771,8 @@ def dataset_list(invocation: Invocation) -> HandlerResult:
     kwargs: dict[str, Any] = {"project_id": project_id}
     _forward_optional(document, kwargs, ("limit", "offset", "sort"))
     name = document.get("name")
+    if document.get("names") and not (isinstance(name, str) and name.strip()):
+        return _dataset_names(invocation, project_id, document)
     if isinstance(name, str) and name.strip():
         return _dataset_name_search(invocation, project_id, name.strip(), document)
     compact = not document.get("full")
@@ -772,13 +780,54 @@ def dataset_list(invocation: Invocation) -> HandlerResult:
         kwargs["fields"] = DATASET_ROW_FIELDS
     with open_service(invocation) as (service, auth):
         data = service.call(_symbol(invocation), **kwargs)
-    if compact:
-        data = _compact_dataset_list(
-            data, kwargs.get("offset", 0), kwargs.get("sort"), kwargs.get("limit", 100)
-        )
+        if compact:
+            data = _compact_dataset_list(
+                data, kwargs.get("offset", 0), kwargs.get("sort"), kwargs.get("limit", 100)
+            )
+            if isinstance(data, dict) and "shown" in data:
+                data["total"] = _dataset_total(service, project_id, data, kwargs.get("offset", 0))
     return data, _meta(invocation, auth.workspace_id, project_id)
 
 
+def _dataset_names(
+    invocation: Invocation, project_id: int, document: dict[str, Any]
+) -> HandlerResult:
+    """``dataset list`` with ``names``: every ``{id, name}`` of the project in one result.
+
+    Capped at ``NAMES_MAX_ROWS`` rows and ``NAMES_DATA_BUDGET`` bytes; ``total`` is the whole
+    count and ``more`` says the cap cut the list (``name`` then narrows it).
+    """
+    with open_service(invocation) as (service, auth):
+        data = service.call(
+            "mammoth.api.datasets.DatasetsAPI.list_all",
+            project_id=project_id,
+            sort=document.get("sort", "(created_at:desc)"),
+            fields="id,name",
+        )
+    records = data.get("datasets", []) if isinstance(data, dict) else []
+    rows = [{"id": r["id"], "name": r.get("name")} for r in records if isinstance(r, dict)]
+    kept, _cut = fit_budget(rows[:NAMES_MAX_ROWS], budget=NAMES_DATA_BUDGET)
+    result: dict[str, Any] = {"datasets": kept, "shown": len(kept), "total": len(rows)}
+    if len(kept) < len(rows):
+        result["more"] = True
+        result["note"] = (
+            f"Only the newest {len(kept)} of {len(rows)} names fit one call; narrow with "
+            '--input \'{"name": "<text>"}\' to find the rest.'
+        )
+    return result, _meta(invocation, auth.workspace_id, project_id)
+
+
+def _dataset_total(service: Any, project_id: int, page: dict[str, Any], offset: int) -> int:
+    """The project's whole dataset count. The list route sends none, so a page that
+    is the last one counts itself; otherwise the ids are read once, here, in one call."""
+    if not page.get("more"):
+        return int(offset) + page["shown"]
+    everything = service.call(
+        "mammoth.api.datasets.DatasetsAPI.list_all", project_id=project_id, fields="id"
+    )
+    return len(everything.get("datasets", []))
+
+
 def _dataset_name_search(
     invocation: Invocation, project_id: int, name: str, document: dict[str, Any]
 ) -> HandlerResult:

{mammoth_cli-2.2.87 → mammoth_cli-2.2.89}/mammoth_cli/services/command_contract.py

@@ -751,11 +751,13 @@ _S7_ADDITIONAL_INPUT_FIELDS: dict[str, tuple[FieldSpec, ...]] = {
     "view.data.query": (
         FieldSpec("text_date_format", required=False, annotation=str | None, default=None),
     ),
-    # ``full`` returns the raw ``{id, name}`` list instead of the summaries; ``name`` keeps
+    # ``names`` returns up to 500 bare ``{id, name}`` rows in one call; ``full`` returns the raw
+    # ``{id, name}`` list instead of the summaries; ``name`` keeps
     # only datasets whose name contains it (case-insensitive) and drops the column lists.
     "dataset.list": (
         FieldSpec("full", required=False, annotation=bool, default=False),
         FieldSpec("name", required=False, annotation=str | None, default=None),
+        FieldSpec("names", required=False, annotation=bool, default=False),
     ),
     # ``view list`` records are trimmed to the brief shape; ``full`` keeps
     # them. ``dataset_offset`` resumes the no-DATASET_ID, every-dataset-in-

{mammoth_cli-2.2.87 → mammoth_cli-2.2.89}/mammoth_cli/services/listing.py

@@ -21,6 +21,11 @@ from mammoth_cli.services.stored_stats import stored_facts
 
 #: Characters of ``data`` a list may use; the agent tool caps a whole result at 4,000.
 LIST_DATA_BUDGET = 3500
+#: ``dataset list`` with ``names: true``: bare ``{id, name}`` rows, so far more fit. Kept under
+#: the agent dispatcher's 50,000-byte output cap, with room for the envelope.
+NAMES_DATA_BUDGET = 40_000
+#: Most names ``dataset list`` with ``names: true`` returns in one call.
+NAMES_MAX_ROWS = 500
 #: ``fields`` asked of the dataset list route: everything the summary shows.
 DATASET_LIST_FIELDS = (
     "id,name,created_at,updated_at,status,stats,sources,data_schema,additional_info"

{mammoth_cli-2.2.87 → mammoth_cli-2.2.89}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "mammoth-cli"
-version = "2.2.87"
+version = "2.2.89"
 description = "Command-line interface for the Mammoth Analytics platform"
 authors = [{name = "Mammoth Analytics", email = "support@mammoth.io"}]
 readme = "README.md"