feat(evaluator): make a stored task runner-polymorphic via kind

docs/_scripts/lint_python_snippets.py

@@ -51,7 +51,9 @@
     "<!-- @nemo-docs: skip-python-type-check -->",
     "<!-- @nemo-nb: skip-type-check -->",
 }
-DEFAULT_IGNORED_TY_RULES = ("possibly-unbound-attribute",)
+# ``possibly-unbound-attribute`` was renamed upstream; passing the old name makes ty emit
+# ``warning[unknown-rule]``, which fails this check for every doc regardless of its snippets.
+DEFAULT_IGNORED_TY_RULES = ("possibly-missing-attribute",)
 
 
 @dataclass(frozen=True)

docs/evaluator/manage-tasks-tasksets.mdx

@@ -73,47 +73,82 @@ Reference the stored metric with a `MetricRef` (`workspace/name`, or a bare `nam
 the task's workspace). The service returns the stored `Task`.
 
 ```python
-from nemo_evaluator.api.schemas import MetadataItem, MetricRef, TaskInput, TaskInputs
+from nemo_evaluator.api.schemas import EvaluatorTaskDefinition, MetadataItem, MetricRef, TaskInput, TaskInputs
 
 task = TaskInput(
-    intent="Answer the user's geography question with the capital city.",
-    inputs=TaskInputs(instruction="What is the capital of France?"),
-    metrics=[MetricRef("default/answer-exact-match")],
+    spec=EvaluatorTaskDefinition(
+        kind="evaluator",
+        intent="Answer the user's geography question with the capital city.",
+        inputs=TaskInputs(instruction="What is the capital of France?"),
+        metrics=[MetricRef("default/answer-exact-match")],
+    ),
     metadata=[MetadataItem(key="suite", value="geography")],
 )
 
 stored = tasks.create("capital-of-france", task=task)
-print(stored.id, stored.metrics)
+print(stored.id, stored.spec.metrics)
 ```
 
 ### `TaskInput` fields
 
+| Field | Type | Required | Description |
+|-------|------|----------|-------------|
+| `spec` | `TaskDefinition` | Yes | The task's content, discriminated by `kind` — see below. |
+| `metadata` | `list[MetadataItem]` | No | Key/value annotations. Keys must be unique. |
+| `tags` | `list[str]` | No | Tags to point at the revision this request publishes. `latest` is always applied server-side. |
+
+### Task kinds
+
+A task is an evaluation unit; its `kind` says which runner executes it. There are two:
+
+- `evaluator` — the task's content is fields you author, scored by platform metrics.
+- `harbor` — the task's content is a packaged directory of files, scored by Harbor's own reward.
+
+Both are stored as the same record type, so a taskset can group them and you manage every evaluation
+unit in one place regardless of which runner executes it.
+
+`EvaluatorTaskDefinition` (`kind="evaluator"`):
+
 | Field | Type | Required | Description |
 |-------|------|----------|-------------|
 | `intent` | `str` | Yes | Human-readable description of the desired agent behavior. |
 | `inputs` | `TaskInputs` | No | The task's recognized input fields. `instruction` is the agent's prompt; it falls back to `intent` when unset. |
+| `reference` | `dict[str, Any]` | No | Grader-only ground truth (held-out tests, expected outputs, rubric data). Surfaced to metrics but never seeded into the agent's workspace or shown to the agent. Held out from the *agent*, not from the API. |
 | `metrics` | `list[MetricRefOrInline]` | No | The metrics that score the task, as `MetricRef` references (`workspace/name`) to stored metrics. Pre-built inline metric bundles (`MetricInline`) are also accepted and are normalized to stored metrics on create. |
 | `views` | `dict[str, SemanticView]` | No | Optional reporting views mapping metric outputs into named semantic scores. |
-| `metadata` | `list[MetadataItem]` | No | Key/value annotations. Keys must be unique. |
-| `tags` | `list[str]` | No | Tags to point at the revision this request publishes. `latest` is always applied server-side. |
+
+`HarborTaskDefinition` (`kind="harbor"`):
+
+| Field | Type | Required | Description |
+|-------|------|----------|-------------|
+| `archive_ref` | `str` | Yes | Files reference to the task's packaged directory (`workspace/fileset#path`). One fileset per task, so a task shared by several tasksets is stored once. |
+| `archive_digest` | `str` | Yes | Content hash Harbor computed over the task directory. |
+| `instruction` | `str` | No | The task's instruction text, when it has one. |
+| `config` | `dict` | No | Harbor's own task configuration (verifier, agent, environment, steps), stored as published. |
+
+<Note>
+Storing a Harbor task is supported; **running one from storage is not yet**. A taskset may group both
+kinds, but expanding a `harbor` member is rejected with `422` before the run starts, whatever target
+you submit against. Harbor evaluations continue to run through the existing dataset-driven path.
+</Note>
 
 <Note>
 A stored task holds **metric references only**. Any inline metric bundle you pass on create is stored
 as a content-addressed *derived* metric, and the task record is normalized to reference it. This is
-why `stored.metrics` always comes back as a list of `MetricRef` references.
+why `stored.spec.metrics` always comes back as a list of `MetricRef` references.
 </Note>
 
 ### Retrieve, list, and delete
 
 ```python
 # Retrieve one task by name (its current content)
 task = tasks.retrieve("capital-of-france")
-print(task.revision, task.tags)  # e.g. 1 {'latest': 1}
+print(task.spec.kind, task.revision, task.tags)  # e.g. evaluator 1 {'latest': 1}
 
 # List tasks in the workspace (paginated)
 page = tasks.list(page=1, page_size=100, sort="-created_at")
 for item in page.data:
-    print(item.name, item.intent)
+    print(item.name, item.spec.kind)
 
 # Delete a task (this also removes all of its revisions)
 tasks.delete("capital-of-france")
@@ -131,9 +166,12 @@ no existence check.
 
 ```python
 revised_task = TaskInput(
-    intent="Answer the user's geography question with the capital city.",
-    inputs=TaskInputs(instruction="Name the capital city of France."),
-    metrics=[MetricRef("default/answer-exact-match")],
+    spec=EvaluatorTaskDefinition(
+        kind="evaluator",
+        intent="Answer the user's geography question with the capital city.",
+        inputs=TaskInputs(instruction="Name the capital city of France."),
+        metrics=[MetricRef("default/answer-exact-match")],
+    ),
     metadata=[MetadataItem(key="suite", value="geography")],
 )
 
@@ -169,7 +207,7 @@ original = tasks.retrieve("capital-of-france", revision=digest)  # revision 1, a
 current = tasks.retrieve("capital-of-france")                    # revision 2, the current content
 
 assert original.revision == 1 and current.revision == 2
-assert original.inputs.instruction != current.inputs.instruction
+assert original.spec.inputs.instruction != current.spec.inputs.instruction
 ```
 
 ### Tag a revision
@@ -361,9 +399,10 @@ A fragment that no longer resolves fails the evaluation rather than falling back
 revision.
 
 <Note>
-Stored tasks carry no grader-only `reference` (held-out ground truth): that field lives only on inline
-`AgentEvalTaskInput`. Taskset-driven tasks therefore run with an empty `reference`, so use a taskset
-when your metrics score the agent's output directly rather than against per-task held-out data.
+A member's grader-only `reference` (held-out ground truth) is loaded from the pinned revision along
+with the rest of its content, so a taskset-driven run grades against the ground truth that revision
+fixed. Because `reference` is covered by the revision digest, changing it publishes a new revision —
+a pin fixes the grading, not just the prompt.
 </Note>
 
 ## Async usage

packages/nemo_platform_plugin/src/nemo_platform_plugin/refs.py

@@ -93,6 +93,14 @@ class LocalDir(StrRef):
     __cli_metavar__: ClassVar[str | None] = "PATH"
 
 
+#: Regex form of the shape :func:`parse_entity_ref` accepts: ``name`` or ``workspace/name``, each
+#: segment using the platform name charset.  Pydantic fields that hold a reference declare
+#: ``pattern=ENTITY_REF_PATTERN`` so a malformed ref is rejected at validation rather than surfacing
+#: as a confusing failure during parsing; :func:`parse_entity_ref` then only has to split.  Kept
+#: beside the parser so the two cannot drift apart.
+ENTITY_REF_PATTERN = r"^[\w\-.]+(/[\w\-.]+)?$"
+
+
 class FilesetRef(StrRef):
     """A NeMo Platform fileset reference (``"name"`` or ``"workspace/name"``).
 
@@ -104,6 +112,14 @@ class FilesetRef(StrRef):
     __cli_metavar__: ClassVar[str | None] = "FILESET_REF"
 
 
+#: A reference to a *file inside* a fileset: ``workspace/fileset#path/inside.ext``.  Unlike
+#: :data:`ENTITY_REF_PATTERN` the workspace is mandatory (a stored reference must be unambiguous
+#: wherever it is later read from), and the ``#`` fragment is a file path, so it admits ``/`` and
+#: ``.``.  Declared as a field pattern so a malformed reference is rejected when it is stored rather
+#: than surfacing as a download failure mid-run.
+FILESET_REF_PATTERN = r"^[\w\-.]+/[\w\-.]+#[\w\-./]+$"
+
+
 # Documentary union alias — the wire shape is still ``str``.  The
 # ``_spec_flags`` generator collapses this to a single ``--output`` flag
 # of type ``str``; the disambiguation between the two arms happens in
@@ -182,6 +198,8 @@ def parse_entity_ref(identifier: str, default_workspace: str | None = None) -> P
 
 
 __all__ = [
+    "ENTITY_REF_PATTERN",
+    "FILESET_REF_PATTERN",
     "EndpointURL",
     "FilesetRef",
     "LocalDir",