[claude] SOUL.md Framework — template, authoring guide, versioning (#854) (#1327)
Some checks failed
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled

This commit was merged in pull request #1327.
This commit is contained in:
2026-03-24 02:23:46 +00:00
parent c5e4657e23
commit c0fad202ea
11 changed files with 1516 additions and 12 deletions

320
scripts/validate_soul.py Normal file
View File

@@ -0,0 +1,320 @@
#!/usr/bin/env python3
"""
validate_soul.py — SOUL.md validator
Checks that a SOUL.md file conforms to the framework defined in
docs/soul/SOUL_TEMPLATE.md and docs/soul/AUTHORING_GUIDE.md.
Usage:
python scripts/validate_soul.py <path/to/soul.md>
python scripts/validate_soul.py docs/soul/extensions/seer.md
python scripts/validate_soul.py memory/self/soul.md
Exit codes:
0 — valid
1 — validation errors found
"""
from __future__ import annotations
import re
import sys
from dataclasses import dataclass, field
from pathlib import Path
# ---------------------------------------------------------------------------
# Required sections (H2 headings that must be present)
# ---------------------------------------------------------------------------
REQUIRED_SECTIONS = [
"Identity",
"Prime Directive",
"Values",
"Audience Awareness",
"Constraints",
"Changelog",
]
# Sections required only for sub-agents (those with 'extends' in frontmatter)
EXTENSION_ONLY_SECTIONS = [
"Role Extension",
]
# ---------------------------------------------------------------------------
# Contradiction detection — pairs of phrases that are likely contradictory
# if both appear in the same document.
# ---------------------------------------------------------------------------
CONTRADICTION_PAIRS: list[tuple[str, str]] = [
# honesty vs deception
(r"\bnever deceive\b", r"\bdeceive the user\b"),
(r"\bnever fabricate\b", r"\bfabricate\b.*\bwhen needed\b"),
# refusal patterns
(r"\bnever refuse\b", r"\bwill not\b"),
# data handling
(r"\bnever store.*credentials\b", r"\bstore.*credentials\b.*\bwhen\b"),
(r"\bnever exfiltrate\b", r"\bexfiltrate.*\bif authorized\b"),
# autonomy
(r"\bask.*before.*executing\b", r"\bexecute.*without.*asking\b"),
]
# ---------------------------------------------------------------------------
# Semver pattern
# ---------------------------------------------------------------------------
SEMVER_PATTERN = re.compile(r"^\d+\.\d+\.\d+$")
# ---------------------------------------------------------------------------
# Frontmatter fields that must be present and non-empty
# ---------------------------------------------------------------------------
REQUIRED_FRONTMATTER_FIELDS = [
"soul_version",
"agent_name",
"created",
"updated",
]
# ---------------------------------------------------------------------------
# Data structures
# ---------------------------------------------------------------------------
@dataclass
class ValidationResult:
path: Path
errors: list[str] = field(default_factory=list)
warnings: list[str] = field(default_factory=list)
@property
def is_valid(self) -> bool:
return len(self.errors) == 0
def error(self, msg: str) -> None:
self.errors.append(msg)
def warn(self, msg: str) -> None:
self.warnings.append(msg)
# ---------------------------------------------------------------------------
# Parsing helpers
# ---------------------------------------------------------------------------
def _extract_frontmatter(text: str) -> dict[str, str]:
"""Extract YAML-style frontmatter between --- delimiters."""
match = re.match(r"^---\n(.*?)\n---", text, re.DOTALL)
if not match:
return {}
fm: dict[str, str] = {}
for line in match.group(1).splitlines():
if ":" in line:
key, _, value = line.partition(":")
fm[key.strip()] = value.strip().strip('"')
return fm
def _extract_sections(text: str) -> set[str]:
"""Return the set of H2 section names found in the document."""
return {m.group(1).strip() for m in re.finditer(r"^## (.+)$", text, re.MULTILINE)}
def _body_text(text: str) -> str:
"""Return document text without frontmatter block."""
return re.sub(r"^---\n.*?\n---\n?", "", text, flags=re.DOTALL)
# ---------------------------------------------------------------------------
# Validation steps
# ---------------------------------------------------------------------------
def _check_frontmatter(text: str, result: ValidationResult) -> dict[str, str]:
fm = _extract_frontmatter(text)
if not fm:
result.error("No frontmatter found. Add a --- block at the top.")
return fm
for field_name in REQUIRED_FRONTMATTER_FIELDS:
if field_name not in fm:
result.error(f"Frontmatter missing required field: {field_name!r}")
elif not fm[field_name] or fm[field_name] in ("<AgentName>", "YYYY-MM-DD"):
result.error(
f"Frontmatter field {field_name!r} is empty or still a placeholder."
)
version = fm.get("soul_version", "")
if version and not SEMVER_PATTERN.match(version):
result.error(
f"soul_version {version!r} is not valid semver (expected MAJOR.MINOR.PATCH)."
)
return fm
def _check_required_sections(
text: str, fm: dict[str, str], result: ValidationResult
) -> None:
sections = _extract_sections(text)
is_extension = "extends" in fm
for section in REQUIRED_SECTIONS:
if section not in sections:
result.error(f"Required section missing: ## {section}")
if is_extension:
for section in EXTENSION_ONLY_SECTIONS:
if section not in sections:
result.warn(
f"Sub-agent soul is missing recommended section: ## {section}"
)
def _check_values_section(text: str, result: ValidationResult) -> None:
"""Check that values section contains at least 3 numbered items."""
body = _body_text(text)
values_match = re.search(
r"## Values\n(.*?)(?=\n## |\Z)", body, re.DOTALL
)
if not values_match:
return # Already reported as missing section
values_text = values_match.group(1)
numbered_items = re.findall(r"^\d+\.", values_text, re.MULTILINE)
count = len(numbered_items)
if count < 3:
result.error(
f"Values section has {count} item(s); minimum is 3. "
"Values must be numbered (1. 2. 3. ...)"
)
if count > 8:
result.warn(
f"Values section has {count} items; recommended maximum is 8. "
"Consider consolidating."
)
def _check_constraints_section(text: str, result: ValidationResult) -> None:
"""Check that constraints section contains at least 3 bullet points."""
body = _body_text(text)
constraints_match = re.search(
r"## Constraints\n(.*?)(?=\n## |\Z)", body, re.DOTALL
)
if not constraints_match:
return # Already reported as missing section
constraints_text = constraints_match.group(1)
bullets = re.findall(r"^- \*\*Never\*\*", constraints_text, re.MULTILINE)
if len(bullets) < 3:
result.error(
f"Constraints section has {len(bullets)} 'Never' constraint(s); "
"minimum is 3. Constraints must start with '- **Never**'."
)
def _check_changelog(text: str, result: ValidationResult) -> None:
"""Check that changelog has at least one entry row."""
body = _body_text(text)
changelog_match = re.search(
r"## Changelog\n(.*?)(?=\n## |\Z)", body, re.DOTALL
)
if not changelog_match:
return # Already reported as missing section
# Table rows have 4 | delimiters (version | date | author | summary)
rows = [
line
for line in changelog_match.group(1).splitlines()
if line.count("|") >= 3
and not line.startswith("|---")
and "Version" not in line
]
if not rows:
result.error("Changelog table has no entries. Add at least one row.")
def _check_contradictions(text: str, result: ValidationResult) -> None:
"""Heuristic check for contradictory directive pairs."""
lower = text.lower()
for pattern_a, pattern_b in CONTRADICTION_PAIRS:
match_a = re.search(pattern_a, lower)
match_b = re.search(pattern_b, lower)
if match_a and match_b:
result.warn(
f"Possible contradiction detected: "
f"'{pattern_a}' and '{pattern_b}' both appear in the document. "
"Review for conflicting directives."
)
def _check_placeholders(text: str, result: ValidationResult) -> None:
"""Check for unfilled template placeholders."""
placeholders = re.findall(r"<[A-Z][A-Za-z ]+>", text)
for ph in set(placeholders):
result.error(f"Unfilled placeholder found: {ph}")
# ---------------------------------------------------------------------------
# Main validator
# ---------------------------------------------------------------------------
def validate(path: Path) -> ValidationResult:
result = ValidationResult(path=path)
if not path.exists():
result.error(f"File not found: {path}")
return result
text = path.read_text(encoding="utf-8")
fm = _check_frontmatter(text, result)
_check_required_sections(text, fm, result)
_check_values_section(text, result)
_check_constraints_section(text, result)
_check_changelog(text, result)
_check_contradictions(text, result)
_check_placeholders(text, result)
return result
def _print_result(result: ValidationResult) -> None:
path_str = str(result.path)
if result.is_valid and not result.warnings:
print(f"[PASS] {path_str}")
return
if result.is_valid:
print(f"[WARN] {path_str}")
else:
print(f"[FAIL] {path_str}")
for err in result.errors:
print(f" ERROR: {err}")
for warn in result.warnings:
print(f" WARN: {warn}")
# ---------------------------------------------------------------------------
# CLI entry point
# ---------------------------------------------------------------------------
def main() -> int:
if len(sys.argv) < 2:
print("Usage: python scripts/validate_soul.py <path/to/soul.md> [...]")
print()
print("Examples:")
print(" python scripts/validate_soul.py memory/self/soul.md")
print(" python scripts/validate_soul.py docs/soul/extensions/seer.md")
print(" python scripts/validate_soul.py docs/soul/extensions/*.md")
return 1
paths = [Path(arg) for arg in sys.argv[1:]]
results = [validate(p) for p in paths]
any_failed = False
for r in results:
_print_result(r)
if not r.is_valid:
any_failed = True
if len(results) > 1:
passed = sum(1 for r in results if r.is_valid)
print(f"\n{passed}/{len(results)} soul files passed validation.")
return 1 if any_failed else 0
if __name__ == "__main__":
sys.exit(main())