canned-prompts/reference/tests/test_canned_prompts.py
tegwick c5f1640454 CANP-WP-0002 T04: eval schema, render checks and output criteria
`evals/` was a reserved path holding unvalidated blobs: section 12 named the
directory and gave an illustrative snippet, but nothing was specified, so no
tool could act on an eval file.

Every eval file must now declare a `schema`, and CPF defines exactly one —
`canned-prompts/eval-rubric/v0.1`. Unrecognized schemas stay legal and are
skipped rather than rejected, so the format gains something actionable without
becoming an evaluation language, which remains a non-goal.

The schema splits along the same seam as T01 and T03. Render checks
(`contains`, `not_contains`, `resolves_all`) assert properties of the rendered
prompt text, need no model, and are therefore run by the reference CLI. Output
criteria describe a good result and are declared but not run, because judging
them requires a model. That division is now the format's consistent answer to
"deterministic locally, or not".

An eval references a fixture already declared in the manifest's `examples`
rather than carrying its own copy, so an example that is also an eval fixture
stays honest — both break together.

An eval declares assessment and must not record outcomes. Results are run
evidence and live outside the immutable package, per INTENT.md and section 17.

Spec: 12 rewritten with 12.1, 18 (rules 17-18), 21 (`eval` verb).

Reference CLI: read_eval, validate_eval, load_example_values,
run_render_checks, cmd_eval; a failed render check exits non-zero.
Tests 42 -> 51.

examples/pqrst-estimate/evals/quality.yaml is a real eval with four render
checks and four output criteria, and it passes.

Fixes a latent bug reaching a fixture exposed: coerce_value assumed every
value was a command-line string, so a YAML fixture carrying a real type
(include_rationale: true) crashed on .lower(). Typed values are now validated
but not re-parsed.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Bjefh8NUiEiahN4JLwoSKM

Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 388925@bnt-lap001
Assistant-Session: 3507023f-e0fd-4a1e-9d90-a0d4217d1502
2026-09-06 01:38:11 +02:00

617 lines
18 KiB
Python

from pathlib import Path
import pytest
import canned_prompts as cp
@pytest.fixture()
def package(tmp_path: Path) -> Path:
pkg = tmp_path / "pkg"
pkg.mkdir()
(pkg / "prompt.yaml").write_text(
"""\
format: canned-prompt/v0.1
id: demo/hello
name: Hello
version: 1.0.0
summary: Say hello.
template: prompt.md
inputs:
- name: person
required: true
parameters:
tone:
type: enum
values: [warm, formal]
default: warm
""",
encoding="utf-8",
)
(pkg / "prompt.md").write_text(
"Say hello to {{ person }} in a {{ tone }} tone.\n", encoding="utf-8"
)
return pkg
def test_validate_and_render(package: Path) -> None:
manifest = cp.validate_package(package)
values = cp.resolve_values(manifest, {"person": "Ada"})
rendered = cp.render_template((package / "prompt.md").read_text(), values)
assert rendered == "Say hello to Ada in a warm tone.\n"
def test_missing_required_input_fails(package: Path) -> None:
manifest = cp.validate_package(package)
with pytest.raises(cp.CannedPromptError, match="missing required input"):
cp.resolve_values(manifest, {})
def test_undeclared_placeholder_fails(package: Path) -> None:
(package / "prompt.md").write_text("{{ missing }}\n", encoding="utf-8")
with pytest.raises(cp.CannedPromptError, match="undeclared placeholders"):
cp.validate_package(package)
def write_pkg(pkg: Path, manifest: str, template: str = "{{ greeting }}\n") -> Path:
pkg.mkdir(exist_ok=True)
(pkg / "prompt.yaml").write_text(manifest, encoding="utf-8")
(pkg / "prompt.md").write_text(template, encoding="utf-8")
return pkg
BASE = """\
format: canned-prompt/v0.1
id: demo/defaults
name: Defaults
version: 1.0.0
summary: Exercise input defaults.
template: prompt.md
"""
def test_static_default_fills_optional_input(tmp_path: Path) -> None:
pkg = write_pkg(
tmp_path / "p",
BASE
+ """\
inputs:
- name: greeting
required: false
default: "hello there"
""",
)
manifest = cp.validate_package(pkg)
resolution = cp.resolve_inputs(manifest, {})
assert resolution.values["greeting"] == "hello there"
assert resolution.origins["greeting"] == "default"
assert cp.render_template("{{ greeting }}", resolution.values) == "hello there"
def test_supplied_value_overrides_static_default(tmp_path: Path) -> None:
pkg = write_pkg(
tmp_path / "p",
BASE
+ """\
inputs:
- name: greeting
required: false
default: "hello there"
""",
)
manifest = cp.validate_package(pkg)
resolution = cp.resolve_inputs(manifest, {"greeting": "hi"})
assert resolution.values["greeting"] == "hi"
assert resolution.origins["greeting"] == "supplied"
def test_derived_default_uses_static_fallback(tmp_path: Path) -> None:
pkg = write_pkg(
tmp_path / "p",
BASE
+ """\
dependencies:
prompts:
- id: context/greeting
version: 1.0.0
requirement: generate
inputs:
- name: greeting
required: false
default:
derive: context/greeting
value: "(none)"
""",
)
manifest = cp.validate_package(pkg)
resolution = cp.resolve_inputs(manifest, {})
assert resolution.values["greeting"] == "(none)"
assert resolution.origins["greeting"] == "fallback (not derived)"
assert resolution.underivable == []
def test_derived_default_without_fallback_is_underivable(tmp_path: Path) -> None:
pkg = write_pkg(
tmp_path / "p",
BASE
+ """\
dependencies:
prompts:
- id: context/greeting
version: 1.0.0
requirement: generate
inputs:
- name: greeting
required: false
default:
derive: context/greeting
""",
)
manifest = cp.validate_package(pkg)
resolution = cp.resolve_inputs(manifest, {})
assert resolution.underivable == ["greeting"]
assert "greeting" not in resolution.values
with pytest.raises(cp.CannedPromptError, match="unresolved placeholder"):
cp.render_template("{{ greeting }}", resolution.values)
def test_inline_derive_is_valid(tmp_path: Path) -> None:
pkg = write_pkg(
tmp_path / "p",
BASE
+ """\
inputs:
- name: greeting
required: false
default:
derive:
prompt: Produce a greeting suited to the audience.
value: "(none)"
""",
)
manifest = cp.validate_package(pkg)
assert cp.resolve_inputs(manifest, {}).values["greeting"] == "(none)"
def test_default_with_required_true_fails(tmp_path: Path) -> None:
pkg = write_pkg(
tmp_path / "p",
BASE
+ """\
inputs:
- name: greeting
required: true
default: "hello"
""",
)
with pytest.raises(cp.CannedPromptError, match="required: true"):
cp.validate_package(pkg)
def test_derive_reference_must_be_declared(tmp_path: Path) -> None:
pkg = write_pkg(
tmp_path / "p",
BASE
+ """\
inputs:
- name: greeting
required: false
default:
derive: context/greeting
""",
)
with pytest.raises(cp.CannedPromptError, match="not declared in dependencies"):
cp.validate_package(pkg)
def test_inline_derive_cannot_also_reference(tmp_path: Path) -> None:
pkg = write_pkg(
tmp_path / "p",
BASE
+ """\
inputs:
- name: greeting
required: false
default:
derive:
prompt: Produce a greeting.
id: context/greeting
""",
)
with pytest.raises(cp.CannedPromptError, match="cannot also reference"):
cp.validate_package(pkg)
MINIMAL = """\
format: canned-prompt/v0.1
id: practice/thing
name: Thing
version: 1.0.0
summary: A thing.
template: prompt.md
inputs:
- name: greeting
required: false
default: hi
"""
def test_parse_reference() -> None:
assert cp.parse_reference("practice/thing") == (None, "practice/thing")
assert cp.parse_reference("house:practice/thing") == ("house", "practice/thing")
with pytest.raises(cp.CannedPromptError, match="malformed reference"):
cp.parse_reference("house:")
def test_registry_name_falls_back_to_basename(tmp_path: Path) -> None:
registry = tmp_path / "upstream"
registry.mkdir()
assert cp.registry_name(registry) == "upstream"
def test_registry_name_from_manifest(tmp_path: Path) -> None:
registry = tmp_path / "some-dir"
registry.mkdir()
(registry / "registry.yaml").write_text(
"format: canned-prompt-registry/v0.1\nname: house\n", encoding="utf-8"
)
assert cp.registry_name(registry) == "house"
def test_registry_manifest_rejects_bad_format(tmp_path: Path) -> None:
registry = tmp_path / "r"
registry.mkdir()
(registry / "registry.yaml").write_text(
"format: something-else\nname: house\n", encoding="utf-8"
)
with pytest.raises(cp.CannedPromptError, match="unsupported registry format"):
cp.read_registry_manifest(registry)
def test_registry_manifest_rejects_bad_policy(tmp_path: Path) -> None:
registry = tmp_path / "r"
registry.mkdir()
(registry / "registry.yaml").write_text(
"format: canned-prompt-registry/v0.1\n"
"name: house\n"
"namespaces:\n practice:\n policy: maybe\n",
encoding="utf-8",
)
with pytest.raises(cp.CannedPromptError, match="policy must be"):
cp.read_registry_manifest(registry)
def test_namespace_policy(tmp_path: Path) -> None:
registry = tmp_path / "r"
registry.mkdir()
(registry / "registry.yaml").write_text(
"format: canned-prompt-registry/v0.1\n"
"name: house\n"
"namespaces:\n practice:\n owner: Ada\n policy: closed\n",
encoding="utf-8",
)
assert cp.namespace_policy(registry, "practice/thing")[0] == "closed"
assert cp.namespace_policy(registry, "scratch/thing")[0] == "open"
def install_into(catalog: Path, registry: str) -> None:
"""Place a package in the catalog under a given registry name."""
dst = cp.catalog_package_path(catalog, registry, "practice/thing", "1.0.0")
dst.mkdir(parents=True)
(dst / "prompt.yaml").write_text(MINIMAL, encoding="utf-8")
(dst / "prompt.md").write_text("{{ greeting }}\n", encoding="utf-8")
def test_same_id_from_two_registries_coexists(tmp_path: Path) -> None:
catalog = tmp_path / "catalog"
install_into(catalog, "house")
install_into(catalog, "upstream")
assert cp.catalog_registries(catalog) == ["house", "upstream"]
package_dir, registry = cp.resolve_installed(catalog, "house:practice/thing", None)
assert registry == "house"
assert package_dir.is_dir()
def test_bare_id_in_two_registries_is_ambiguous(tmp_path: Path) -> None:
catalog = tmp_path / "catalog"
install_into(catalog, "house")
install_into(catalog, "upstream")
with pytest.raises(cp.CannedPromptError, match="more than one registry"):
cp.resolve_installed(catalog, "practice/thing", None)
def test_bare_id_in_one_registry_resolves(tmp_path: Path) -> None:
catalog = tmp_path / "catalog"
install_into(catalog, "house")
_, registry = cp.resolve_installed(catalog, "practice/thing", None)
assert registry == "house"
def test_legacy_catalog_layout_is_reported(tmp_path: Path) -> None:
catalog = tmp_path / "catalog"
legacy = catalog / "practice" / "thing" / "1.0.0"
legacy.mkdir(parents=True)
(legacy / "prompt.yaml").write_text(MINIMAL, encoding="utf-8")
(legacy / "prompt.md").write_text("{{ greeting }}\n", encoding="utf-8")
with pytest.raises(cp.CannedPromptError, match="pre-registry-scoped"):
cp.resolve_installed(catalog, "practice/thing", None)
# --- version selectors (§ 10.1) ---
AVAILABLE = ["2.1.0", "2.0.0", "1.5.0", "1.0.0"]
@pytest.mark.parametrize(
"available,selector,expected",
[
(AVAILABLE, None, "2.1.0"),
(AVAILABLE, "any", "2.1.0"),
(AVAILABLE, "newest", "2.1.0"),
(AVAILABLE, "1.5.0", "1.5.0"),
(AVAILABLE, ">=2.0.0", "2.1.0"),
(AVAILABLE, "9.9.9", None),
(AVAILABLE, ">=9.9.9", None),
(["1.5.0", "1.0.0"], ">=1.2.0", "1.5.0"),
([], "newest", None),
],
)
def test_select_version(available, selector, expected) -> None:
assert cp.select_version(available, selector) == expected
@pytest.mark.parametrize("bad", ["^1.0.0", "~1.2", "1.x", ">=nope", "", "latest"])
def test_range_syntax_is_rejected(bad) -> None:
with pytest.raises(cp.CannedPromptError):
cp.validate_version_selector(bad, "dep")
# --- composition (§ 10.2) ---
FRAGMENT = """\
format: canned-prompt/v0.1
id: style/house
name: House Style
version: 1.0.0
summary: Shared style block.
type: fragment
template: prompt.md
parameters:
tone:
type: enum
values: [neutral, blunt]
default: neutral
"""
COMPOSER = """\
format: canned-prompt/v0.1
id: review/change
name: Change Review
version: 1.0.0
summary: Composes the shared style block.
template: prompt.md
dependencies:
prompts:
- id: style/house
version: 1.0.0
inputs:
- name: house_style
required: false
default:
include: style/house
parameters:
tone:
type: enum
values: [neutral, blunt]
default: blunt
"""
def place(catalog: Path, registry: str, package_id: str, version: str,
manifest: str, template: str) -> None:
dst = cp.catalog_package_path(catalog, registry, package_id, version)
dst.mkdir(parents=True)
(dst / "prompt.yaml").write_text(manifest, encoding="utf-8")
(dst / "prompt.md").write_text(template, encoding="utf-8")
@pytest.fixture()
def composed(tmp_path: Path) -> Path:
catalog = tmp_path / "catalog"
place(catalog, "local", "style/house", "1.0.0", FRAGMENT, "Tone is {{ tone }}.")
place(catalog, "local", "review/change", "1.0.0", COMPOSER, "S: {{ house_style }}")
return catalog
def test_include_inlines_rendered_template(composed: Path) -> None:
package_dir, _ = cp.resolve_installed(composed, "review/change", None)
manifest = cp.validate_package(package_dir)
resolution = cp.resolve_inputs(manifest, {}, composer=cp.CatalogComposer(composed))
assert resolution.values["house_style"] == "Tone is blunt."
assert resolution.origins["house_style"] == "included from style/house"
def test_include_inherits_outer_parameters(composed: Path) -> None:
"""The fragment's own default is neutral; the including package says blunt."""
package_dir, _ = cp.resolve_installed(composed, "review/change", None)
manifest = cp.validate_package(package_dir)
resolution = cp.resolve_inputs(
manifest, {"tone": "neutral"}, composer=cp.CatalogComposer(composed)
)
assert resolution.values["house_style"] == "Tone is neutral."
def test_include_without_composer_falls_back_to_unresolved(composed: Path) -> None:
package_dir, _ = cp.resolve_installed(composed, "review/change", None)
manifest = cp.validate_package(package_dir)
resolution = cp.resolve_inputs(manifest, {})
assert resolution.underivable == ["house_style"]
def test_inclusion_cycle_is_detected(tmp_path: Path) -> None:
catalog = tmp_path / "catalog"
for this, other in (("cyc/a", "cyc/b"), ("cyc/b", "cyc/a")):
manifest = (
"format: canned-prompt/v0.1\n"
f"id: {this}\nname: X\nversion: 1.0.0\nsummary: s\ntemplate: prompt.md\n"
f"dependencies:\n prompts:\n - id: {other}\n version: 1.0.0\n"
f"inputs:\n - name: other\n required: false\n"
f" default:\n include: {other}\n"
)
place(catalog, "local", this, "1.0.0", manifest, "{{ other }}")
package_dir, _ = cp.resolve_installed(catalog, "cyc/a", None)
manifest = cp.validate_package(package_dir)
with pytest.raises(cp.CannedPromptError, match="inclusion cycle"):
cp.resolve_inputs(manifest, {}, composer=cp.CatalogComposer(catalog))
def test_include_and_derive_together_is_rejected(tmp_path: Path) -> None:
pkg = write_pkg(
tmp_path / "p",
BASE
+ """\
dependencies:
prompts:
- id: style/house
version: 1.0.0
inputs:
- name: greeting
required: false
default:
include: style/house
derive: style/house
""",
)
with pytest.raises(cp.CannedPromptError, match="at most one of"):
cp.validate_package(pkg)
def test_composed_dependency_must_declare_a_version(tmp_path: Path) -> None:
pkg = write_pkg(
tmp_path / "p",
BASE
+ """\
dependencies:
prompts:
- id: style/house
inputs:
- name: greeting
required: false
default:
include: style/house
""",
)
with pytest.raises(cp.CannedPromptError, match="must declare a version"):
cp.validate_package(pkg)
# --- evals (§ 12) ---
EVAL_BASE = """\
format: canned-prompt/v0.1
id: demo/evaluated
name: Evaluated
version: 1.0.0
summary: Exercise eval files.
template: prompt.md
examples:
- examples/basic.yaml
evals:
- evals/quality.yaml
"""
def write_evaluated(pkg: Path, eval_body: str, template: str = "Sum to 100%. {{ topic }}\n") -> Path:
pkg.mkdir(exist_ok=True)
(pkg / "prompt.yaml").write_text(
EVAL_BASE + "inputs:\n - name: topic\n required: false\n default: cats\n",
encoding="utf-8",
)
(pkg / "prompt.md").write_text(template, encoding="utf-8")
(pkg / "examples").mkdir(exist_ok=True)
(pkg / "examples" / "basic.yaml").write_text(
"name: basic\nvalues:\n topic: dogs\n", encoding="utf-8"
)
(pkg / "evals").mkdir(exist_ok=True)
(pkg / "evals" / "quality.yaml").write_text(eval_body, encoding="utf-8")
return pkg
RUBRIC = """\
schema: canned-prompts/eval-rubric/v0.1
name: quality
example: examples/basic.yaml
render:
- contains: "Sum to 100%"
- not_contains: "{{"
- resolves_all: true
output:
criteria:
- Answers the question.
"""
def test_valid_eval_passes_validation(tmp_path: Path) -> None:
pkg = write_evaluated(tmp_path / "p", RUBRIC)
assert cp.validate_package(pkg)["id"] == "demo/evaluated"
def test_eval_must_declare_a_schema(tmp_path: Path) -> None:
pkg = write_evaluated(tmp_path / "p", "name: quality\nrender: []\n")
with pytest.raises(cp.CannedPromptError, match="must declare a schema"):
cp.validate_package(pkg)
def test_unknown_eval_schema_is_ignored(tmp_path: Path) -> None:
pkg = write_evaluated(tmp_path / "p", "schema: someone/else/v1\nwhatever: true\n")
assert cp.validate_package(pkg)["id"] == "demo/evaluated"
def test_eval_asserting_nothing_is_rejected(tmp_path: Path) -> None:
pkg = write_evaluated(
tmp_path / "p", "schema: canned-prompts/eval-rubric/v0.1\nname: empty\n"
)
with pytest.raises(cp.CannedPromptError, match="asserts nothing"):
cp.validate_package(pkg)
def test_unknown_render_check_is_rejected(tmp_path: Path) -> None:
pkg = write_evaluated(
tmp_path / "p",
"schema: canned-prompts/eval-rubric/v0.1\nname: q\nrender:\n - matches: 'x.*'\n",
)
with pytest.raises(cp.CannedPromptError, match="unknown render check"):
cp.validate_package(pkg)
def test_eval_example_must_be_declared(tmp_path: Path) -> None:
pkg = write_evaluated(
tmp_path / "p",
"schema: canned-prompts/eval-rubric/v0.1\nname: q\n"
"example: examples/missing.yaml\nrender:\n - contains: x\n",
)
with pytest.raises(cp.CannedPromptError, match="not declared in the manifest"):
cp.validate_package(pkg)
def test_render_checks_evaluate(tmp_path: Path) -> None:
resolution = cp.Resolution(values={"topic": "dogs"}, origins={"topic": "supplied"})
checks = [{"contains": "dogs"}, {"contains": "cats"}, {"not_contains": "cats"}]
outcomes = cp.run_render_checks("about dogs", resolution, checks)
assert [ok for ok, _ in outcomes] == [True, False, True]
def test_resolves_all_reports_unresolved_names() -> None:
resolution = cp.Resolution(
values={"a": 1}, origins={"a": "supplied", "b": "unresolved (no default)"}
)
outcomes = cp.run_render_checks("text", resolution, [{"resolves_all": True}])
assert outcomes[0][0] is False
assert "b" in outcomes[0][1]
def test_typed_fixture_values_are_not_reparsed(tmp_path: Path) -> None:
"""A YAML fixture carries real types; only CLI strings need parsing."""
manifest = {"parameters": {"flag": {"type": "boolean", "default": False}}}
assert cp.resolve_inputs(manifest, {"flag": True}).values["flag"] is True