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
This commit is contained in:
tegwick 2026-09-06 01:38:11 +02:00
parent cac6bc135f
commit c5f1640454
8 changed files with 444 additions and 18 deletions

View file

@ -2,7 +2,7 @@
This is intentionally a **small reference implementation**, not the intended final architecture.
It demonstrates seven verbs:
It demonstrates eight verbs:
```text
add PATH
@ -10,6 +10,7 @@ search QUERY
show ID
resolve ID --set key=value
render ID --set key=value
eval ID
install ID [--version VERSION]
publish PATH
```
@ -71,6 +72,10 @@ rather than resolved by guessing.
print qualified `<registry>:<id>` references.
- `include` defaults are satisfied (inclusion is deterministic); `derive`
defaults are reported, not run. Inclusion cycles are detected and named.
- `eval` runs the deterministic render checks of any eval declaring the
`canned-prompts/eval-rubric/v0.1` schema, and reports output criteria as
declared but not run. Unrecognized schemas are skipped, not rejected. A
failed render check exits non-zero.
- An optional `registry.yaml` names a registry and records namespace claims.
`publish` warns when a namespace is declared `closed` — it cannot
authenticate a publisher, and says so rather than implying it checked.

View file

@ -23,6 +23,8 @@ FORMAT = "canned-prompt/v0.1"
REGISTRY_FORMAT = "canned-prompt-registry/v0.1"
LOCAL_REGISTRY = "local"
REGISTRY_NAME_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._-]*$")
EVAL_RUBRIC_SCHEMA = "canned-prompts/eval-rubric/v0.1"
RENDER_CHECKS = ("contains", "not_contains", "resolves_all")
PLACEHOLDER_RE = re.compile(r"{{\s*([A-Za-z_][A-Za-z0-9_.-]*)\s*}}")
SEMVER_RE = re.compile(r"^(0|[1-9]\d*)\.(0|[1-9]\d*)\.(0|[1-9]\d*)(?:[-+].*)?$")
REQUIRED_FIELDS = ("format", "id", "name", "version", "summary", "template")
@ -135,6 +137,64 @@ def prompt_dependencies(manifest: dict[str, Any]) -> dict[str, dict[str, Any]]:
return declared
def read_eval(package_dir: Path, relative: str) -> dict[str, Any]:
path = safe_relative_file(package_dir, relative, "evals")
try:
data = yaml.safe_load(path.read_text(encoding="utf-8"))
except yaml.YAMLError as exc:
raise CannedPromptError(f"invalid YAML in {relative}: {exc}") from exc
if not isinstance(data, dict):
raise CannedPromptError(f"{relative}: an eval file must contain a mapping")
if not isinstance(data.get("schema"), str) or not data["schema"].strip():
raise CannedPromptError(f"{relative}: an eval file must declare a schema")
return data
def validate_eval(relative: str, spec: dict[str, Any], declared_examples: list[str]) -> None:
"""Validation rules 17-18 of § 18. Unknown schemas are ignored, not rejected."""
if spec["schema"] != EVAL_RUBRIC_SCHEMA:
return
if not isinstance(spec.get("name"), str) or not spec["name"].strip():
raise CannedPromptError(f"{relative}: eval must declare a name")
render = spec.get("render") or []
output = spec.get("output") or {}
if not render and not output:
raise CannedPromptError(
f"{relative}: eval asserts nothing; declare render checks or output criteria"
)
if not isinstance(render, list):
raise CannedPromptError(f"{relative}: render must be a list of checks")
for check in render:
if not isinstance(check, dict) or len(check) != 1:
raise CannedPromptError(
f"{relative}: each render check must be a single-key mapping"
)
(kind,) = check
if kind not in RENDER_CHECKS:
raise CannedPromptError(
f"{relative}: unknown render check {kind!r}; expected one of "
+ ", ".join(RENDER_CHECKS)
)
if output:
if not isinstance(output, dict):
raise CannedPromptError(f"{relative}: output must be a mapping")
criteria = output.get("criteria") or []
if not isinstance(criteria, list) or not all(isinstance(c, str) for c in criteria):
raise CannedPromptError(f"{relative}: output.criteria must be a list of strings")
example = spec.get("example")
if example is not None:
if not isinstance(example, str):
raise CannedPromptError(f"{relative}: example must be a path string")
if example not in declared_examples:
raise CannedPromptError(
f"{relative}: example {example!r} is not declared in the manifest's examples"
)
def check_composition_reference(
name: str, reference: str, field: str, declared: dict[str, dict[str, Any]]
) -> None:
@ -243,6 +303,10 @@ def validate_package(package_dir: Path) -> dict[str, Any]:
for item in manifest.get("inputs") or []:
validate_input_default(item, declared)
declared_examples = [str(path) for path in (manifest.get("examples") or [])]
for relative in manifest.get("evals") or []:
validate_eval(relative, read_eval(package_dir, relative), declared_examples)
template = template_path.read_text(encoding="utf-8")
placeholders = set(PLACEHOLDER_RE.findall(template))
undeclared = sorted(placeholders - names)
@ -572,8 +636,16 @@ def cmd_show(args: argparse.Namespace) -> None:
print(yaml.safe_dump(manifest, sort_keys=False, allow_unicode=True).rstrip())
def coerce_value(raw: str, spec: dict[str, Any]) -> Any:
def coerce_value(raw: Any, spec: dict[str, Any]) -> Any:
kind = spec.get("type", "string")
if not isinstance(raw, str):
# Already typed — from a YAML fixture rather than the command line.
# Validate membership, but do not try to parse it.
if kind == "enum" and raw not in (spec.get("values") or []):
raise CannedPromptError(
f"invalid enum value {raw!r}; expected one of {spec.get('values') or []}"
)
return raw
if kind == "boolean":
lowered = raw.lower()
if lowered in {"true", "1", "yes", "on"}:
@ -875,6 +947,91 @@ def cmd_resolve(args: argparse.Namespace) -> None:
)
def load_example_values(package_dir: Path, relative: str) -> dict[str, Any]:
path = safe_relative_file(package_dir, relative, "examples")
try:
data = yaml.safe_load(path.read_text(encoding="utf-8"))
except yaml.YAMLError as exc:
raise CannedPromptError(f"invalid YAML in {relative}: {exc}") from exc
if not isinstance(data, dict):
raise CannedPromptError(f"{relative}: an example must contain a mapping")
values = data.get("values") or {}
if not isinstance(values, dict):
raise CannedPromptError(f"{relative}: example values must be a mapping")
return values
def run_render_checks(
rendered: str, resolution: Resolution, checks: list[dict[str, Any]]
) -> list[tuple[bool, str]]:
"""Evaluate § 12.1 render checks. Deterministic: no model is involved."""
results: list[tuple[bool, str]] = []
for check in checks:
(kind,) = check
expected = check[kind]
if kind == "contains":
results.append((str(expected) in rendered, f'contains "{expected}"'))
elif kind == "not_contains":
results.append((str(expected) not in rendered, f'not_contains "{expected}"'))
elif kind == "resolves_all":
unresolved = sorted(set(resolution.origins) - set(resolution.values))
ok = (not unresolved) if expected else bool(unresolved)
detail = f" ({', '.join(unresolved)})" if unresolved else ""
results.append((ok, f"resolves_all{detail}"))
return results
def cmd_eval(args: argparse.Namespace) -> None:
catalog = Path(args.catalog).expanduser()
package_dir, registry = resolve_installed(catalog, args.id, args.version)
manifest = validate_package(package_dir)
template_path = safe_relative_file(package_dir, manifest["template"], "template")
template = template_path.read_text(encoding="utf-8")
relatives = manifest.get("evals") or []
if not relatives:
print(f"{registry}:{manifest['id']}@{manifest['version']} no evals declared")
return
print(f"{registry}:{manifest['id']}@{manifest['version']}")
failures = 0
for relative in relatives:
spec = read_eval(package_dir, relative)
if spec["schema"] != EVAL_RUBRIC_SCHEMA:
print(f" {relative} schema {spec['schema']} not recognized — skipped")
continue
print(f" {relative} ({spec['name']})")
checks = spec.get("render") or []
if checks:
values = (
load_example_values(package_dir, spec["example"])
if spec.get("example")
else {}
)
resolution = resolve_inputs(
manifest, values, composer=CatalogComposer(catalog)
)
missing = sorted(set(PLACEHOLDER_RE.findall(template)) - set(resolution.values))
rendered = "" if missing else render_template(template, resolution.values)
if missing:
print(f" render FAIL cannot render: unresolved {', '.join(missing)}")
failures += 1
for ok, label in run_render_checks(rendered, resolution, checks):
print(f" render {'PASS' if ok else 'FAIL'} {label}")
failures += 0 if ok else 1
criteria = (spec.get("output") or {}).get("criteria") or []
if criteria:
print(
f" output -- {len(criteria)} criteria declared "
"(not run: judging output needs a model)"
)
if failures:
raise CannedPromptError(f"{failures} render check(s) failed")
def build_parser() -> argparse.ArgumentParser:
parser = argparse.ArgumentParser(prog="canned-prompts", description=__doc__)
sub = parser.add_subparsers(dest="command", required=True)
@ -911,6 +1068,12 @@ def build_parser() -> argparse.ArgumentParser:
render.add_argument("--set", dest="set_values", action="append", default=[], metavar="NAME=VALUE")
render.set_defaults(func=cmd_render)
evaluate = sub.add_parser("eval", help="run an installed package's render checks")
evaluate.add_argument("id")
evaluate.add_argument("--version")
evaluate.add_argument("--catalog", default=str(default_catalog()))
evaluate.set_defaults(func=cmd_eval)
resolve = sub.add_parser("resolve", help="report how each input and parameter resolves")
resolve.add_argument("id")
resolve.add_argument("--version")

View file

@ -504,3 +504,114 @@ inputs:
)
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