implemented steps 1-5

This commit is contained in:
John Lancaster
2026-06-20 14:08:59 -05:00
parent c273ecfc54
commit 19f3c1740a
53 changed files with 1454 additions and 762 deletions
+139 -140
View File
@@ -1,172 +1,171 @@
from pathlib import Path
from __future__ import annotations
from typing import Any
import yaml
from fastmcp import FastMCP
from personal_mcp.skills.document_loader import DocsRegistry, SkillRecord
from personal_mcp.skills.document_loader import load_skill_document_from_metadata
catalog_server = FastMCP("catalog")
DEFAULT_LIMIT = 20
MAX_LIMIT = 100
def _skills_dir() -> Path:
return Path(__file__).resolve().parents[1] / "skills"
def _load_skill_registry() -> dict[str, Any]:
registry: dict[str, Any] = {}
for metadata_path in sorted(_skills_dir().glob("*/metadata.yaml")):
with metadata_path.open("r", encoding="utf-8") as handle:
metadata = yaml.safe_load(handle) or {}
skill_key = metadata_path.parent.name
registry[skill_key] = {
"namespace": skill_key,
"metadata": metadata,
}
return registry
def _normalize_pattern(namespace: str, metadata: dict[str, Any]) -> dict[str, Any]:
pattern_id = metadata.get("id", namespace)
capabilities = metadata.get("capabilities", [])
def _pattern_payload(skill: SkillRecord) -> dict[str, Any]:
return {
"id": pattern_id,
"namespace": namespace,
"name": metadata.get("name", pattern_id),
"version": metadata.get("version", "0.1.0"),
"description": metadata.get("description", ""),
"tags": metadata.get("tags", []),
"depends_on": metadata.get("depends_on", []),
"capabilities": capabilities,
# Expose resources explicitly for clients that treat resources as the primary interface.
"resources": capabilities,
"id": skill.skill_id,
"name": skill.name,
"version": skill.version,
"description": skill.description,
"tags": list(skill.tags),
"depends_on": list(skill.depends_on),
"capabilities": list(skill.capabilities),
"resources": list(skill.capabilities),
}
def _normalized_patterns() -> list[dict[str, Any]]:
registry = _load_skill_registry()
return [
_normalize_pattern(namespace, entry["metadata"])
for namespace, entry in registry.items()
def _summary_payload(skill: SkillRecord) -> dict[str, Any]:
return {
"id": skill.skill_id,
"name": skill.name,
"description": skill.description,
"tags": list(skill.tags),
"capabilities": list(skill.capabilities),
"version": skill.version,
"document_uri": skill.document_uri,
"detail_uri": f"resource://catalog/skills/{skill.skill_id}",
"resources": {
"document": skill.document_uri,
"references": [
f"resource://skills/{skill.skill_id}/references/{ref_id}"
for ref_id in sorted(skill.references)
],
},
}
def _skill_matches(
skill: SkillRecord,
*,
query: str | None,
tag: str | None,
capability: str | None,
) -> bool:
if query:
lowered = query.strip().lower()
if lowered:
haystack = " ".join(
[
skill.skill_id,
skill.name,
skill.description,
" ".join(skill.tags),
]
).lower()
terms = [term for term in lowered.replace("-", " ").split() if term]
if any(term not in haystack for term in terms):
return False
if tag and tag not in skill.tags:
return False
if capability and capability not in skill.capabilities:
return False
return True
def build_skills_index_payload(
registry: DocsRegistry,
*,
query: str | None = None,
tag: str | None = None,
capability: str | None = None,
cursor: str | None = None,
limit: int | None = None,
) -> dict[str, Any]:
normalized_limit = DEFAULT_LIMIT if limit is None else max(1, min(limit, MAX_LIMIT))
try:
start = 0 if cursor is None else max(0, int(cursor))
except ValueError as exc:
raise ValueError("cursor must be an integer string") from exc
ordered = [registry.skills_by_id[skill_id] for skill_id in registry.skills_in_load_order]
matches = [
skill
for skill in ordered
if _skill_matches(skill, query=query, tag=tag, capability=capability)
]
page = matches[start : start + normalized_limit]
next_cursor = start + normalized_limit
def _matches_query(pattern: dict[str, Any], query: str) -> bool:
if not query:
return True
lowered = query.strip().lower()
if not lowered:
return True
query_terms = [term for term in lowered.replace("-", " ").split() if term]
if not query_terms:
return True
haystack = " ".join(
[
str(pattern.get("id", "")),
str(pattern.get("namespace", "")),
str(pattern.get("name", "")),
str(pattern.get("description", "")),
" ".join(str(tag) for tag in pattern.get("tags", [])),
]
).lower()
return all(term in haystack for term in query_terms)
return {
"skills": [_summary_payload(skill) for skill in page],
"total": len(matches),
"cursor": str(start),
"limit": normalized_limit,
"next_cursor": str(next_cursor) if next_cursor < len(matches) else None,
}
def _matches_tags(pattern: dict[str, Any], tags: list[str] | None) -> bool:
if not tags:
return True
def build_skill_detail_payload(registry: DocsRegistry, skill_id: str) -> dict[str, Any]:
if skill_id not in registry.skills_by_id:
raise KeyError(skill_id)
requested = [tag.strip().lower() for tag in tags if tag and tag.strip()]
if not requested:
return True
pattern_tags = {str(tag).lower() for tag in pattern.get("tags", [])}
return all(tag in pattern_tags for tag in requested)
skill = registry.skills_by_id[skill_id]
return {
"id": skill.skill_id,
"name": skill.name,
"description": skill.description,
"version": skill.version,
"tags": list(skill.tags),
"depends_on": list(skill.depends_on),
"capabilities": list(skill.capabilities),
"resources": {
"document": skill.document_uri,
"references": {
ref_id: {
"uri": ref.uri,
"mime_type": ref.mime_type,
"title": ref.title,
"path": ref.relpath,
}
for ref_id, ref in sorted(skill.references.items())
},
},
}
@catalog_server.resource("resource://catalog/skills_index")
def skills_index() -> dict[str, Any]:
"""Return a compact discovery index for all available pattern modules."""
return {"patterns": _normalized_patterns()}
@catalog_server.resource("resource://catalog/skills_details")
def skills_details() -> dict[str, Any]:
"""Return full metadata for all mounted pattern modules."""
return {"patterns": _load_skill_registry()}
@catalog_server.resource("resource://catalog/patterns")
def patterns() -> dict[str, Any]:
"""Return normalized pattern records for resource-first clients."""
return {"patterns": _normalized_patterns()}
@catalog_server.resource("resource://catalog/patterns_by_id")
def patterns_by_id() -> dict[str, Any]:
"""Return normalized pattern records indexed by stable pattern id."""
indexed: dict[str, Any] = {}
for pattern in _normalized_patterns():
indexed[pattern["id"]] = pattern
return {"patterns_by_id": indexed}
@catalog_server.tool
def search_patterns(
def search_patterns_payload(
registry: DocsRegistry,
*,
query: str = "",
tags: list[str] | None = None,
skip: int = 0,
limit: int = 20,
limit: int = DEFAULT_LIMIT,
) -> dict[str, Any]:
"""Search normalized pattern metadata with optional tags and pagination."""
normalized_skip = max(skip, 0)
normalized_limit = min(max(limit, 1), 100)
normalized_limit = max(1, min(limit, MAX_LIMIT))
matches = [
pattern
for pattern in _normalized_patterns()
if _matches_query(pattern, query) and _matches_tags(pattern, tags)
]
requested_tags = [tag.strip() for tag in (tags or []) if tag and tag.strip()]
matches: list[SkillRecord] = []
for skill_id in registry.skills_in_load_order:
skill = registry.skills_by_id[skill_id]
if not _skill_matches(skill, query=query, tag=None, capability=None):
continue
if requested_tags and any(tag not in skill.tags for tag in requested_tags):
continue
matches.append(skill)
page = matches[normalized_skip : normalized_skip + normalized_limit]
return {
"patterns": page,
"patterns": [_pattern_payload(skill) for skill in page],
"total": len(matches),
"skip": normalized_skip,
"limit": normalized_limit,
}
@catalog_server.tool
def get_pattern_by_id(id: str) -> dict[str, Any]:
"""Return one normalized pattern by stable id."""
for pattern in _normalized_patterns():
if pattern["id"] == id:
return {"found": True, "pattern": pattern}
return {"found": False, "id": id}
@catalog_server.tool
def get_skill_document_by_id(skill_id: str) -> dict[str, Any]:
"""Return the canonical skill document payload for a stable skill id."""
registry = _load_skill_registry()
for namespace, entry in registry.items():
metadata = entry.get("metadata", {})
pattern_id = metadata.get("id", namespace)
if pattern_id != skill_id:
continue
return {
"found": True,
"document": load_skill_document_from_metadata(
skill_id=skill_id,
namespace=namespace,
metadata=metadata,
),
}
return {"found": False, "id": skill_id}
def get_pattern_by_id_payload(registry: DocsRegistry, skill_id: str) -> dict[str, Any]:
if skill_id not in registry.skills_by_id:
return {"found": False, "id": skill_id}
return {"found": True, "pattern": _pattern_payload(registry.skills_by_id[skill_id])}