9ba615c8ee
Template for building hosted MCP servers over a product's public
documentation. Distilled from one production build; everything
product-specific has been factored out.
Contents:
- PLAN.md — comprehensive build guide. 13 phases from project
skeleton through weekly_digest. Includes the gotchas
("fetch-depth: 0 always", reranker per-pair token limit,
Cloudflare body cap, dash-not-bash on Gitea runners), the
decisions worth carrying forward, and a per-product
customization checklist.
- CLAUDE.md — guidance for Claude Code working in a clone of this
template. Phase identification table, conventions (env-gating +
operator confirmation for side-effecting tools, defensive
fallback for retrieval components), common commands.
- README.md — quick-start summary.
Scaffolded code (all signature-stable, with NotImplementedError
stubs where phase-specific work is required):
docs_mcp/server.py FastMCP server, stateless_http=True, with
search_docs / get_page / list_versions
baseline tools and commented stubs for the
rest of the phase set.
docs_mcp/usage.py TimedCall telemetry, JSONL, daily rotation,
90-day retention. Reusable as-is.
rag/embeddings.py Ollama embedder (nomic-embed-text default),
load-balanced across N URLs. Reusable.
rag/chunk.py Paragraph-aware chunker with synthetic
chunk 0. Per-product tunable.
rag/index.py Chroma + BM25 builder. --rebuild and
--bm25-only flags.
rag/bm25.py SQLite FTS5 lexical index. Reusable.
scrape/changelog.py --cached / --ref / --json / --history-out.
Reusable.
scrape/README.md What you write per-product.
eval/queries.jsonl.example
Curate ~25 hand-labeled queries here.
eval/retrievers.py Retriever protocol + stub classes.
eval/run_eval.py MRR / Recall@K / nDCG@K harness skeleton.
scripts/usage_report.py
Standalone log analyzer; the
FOLLOW-UP CHECKS pattern noted in the
module docstring.
scripts/registry_gc.py
Gitea container registry cleanup. Reusable.
Deployment + CI:
Dockerfile Python 3.12-slim; COPY corpus + chroma
+ bm25 last for cache efficiency.
deploy/docker-compose.yml MCP + reranker sidecar + Watchtower.
Templated with <placeholders>.
.gitea/workflows/refresh.yml Weekly cron + manual dispatch.
fetch-depth: 0, retry-on-race,
three-tag image scheme.
.gitea/workflows/image-only.yml Code-only ship cycle, ~18min.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
109 lines
3.3 KiB
Python
109 lines
3.3 KiB
Python
"""Gitea container-registry garbage collection.
|
|
|
|
Lists package versions for one container package and deletes versions
|
|
older than --keep-days. Always preserves:
|
|
|
|
- the :latest tag
|
|
- the --keep-latest most-recent date-tagged versions
|
|
- anything pushed in the last --keep-days days
|
|
|
|
The actual disk reclaim happens on Gitea's next package GC cron (admin
|
|
site settings). This script just marks the versions for deletion.
|
|
|
|
Usage:
|
|
|
|
python scripts/registry_gc.py \\
|
|
--owner <user> \\
|
|
--package <product>-docs-mcp \\
|
|
--keep-days 90 \\
|
|
--keep-latest 5
|
|
|
|
Auth: reads GITEA_TOKEN from env (set in the workflow as a secret).
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import argparse
|
|
import os
|
|
import sys
|
|
from datetime import datetime, timedelta, timezone
|
|
from urllib.request import Request, urlopen
|
|
from urllib.error import HTTPError
|
|
import json
|
|
|
|
|
|
GITEA_HOST = os.environ.get("GITEA_HOST", "https://git.jpaul.io")
|
|
|
|
|
|
def api(token: str, method: str, path: str) -> object:
|
|
req = Request(f"{GITEA_HOST}{path}",
|
|
headers={"Authorization": f"token {token}"},
|
|
method=method)
|
|
try:
|
|
with urlopen(req, timeout=30) as r:
|
|
body = r.read()
|
|
return json.loads(body) if body else None
|
|
except HTTPError as e:
|
|
if e.code == 404:
|
|
return None
|
|
raise
|
|
|
|
|
|
def main() -> int:
|
|
p = argparse.ArgumentParser()
|
|
p.add_argument("--owner", required=True)
|
|
p.add_argument("--package", required=True)
|
|
p.add_argument("--keep-days", type=int, default=90)
|
|
p.add_argument("--keep-latest", type=int, default=5)
|
|
p.add_argument("--dry-run", action="store_true")
|
|
args = p.parse_args()
|
|
|
|
token = os.environ.get("GITEA_TOKEN")
|
|
if not token:
|
|
print("GITEA_TOKEN not set", file=sys.stderr)
|
|
return 1
|
|
|
|
versions = api(token, "GET",
|
|
f"/api/v1/packages/{args.owner}/container/{args.package}/versions") or []
|
|
if not versions:
|
|
print(f"no versions found for {args.owner}/{args.package}")
|
|
return 0
|
|
|
|
cutoff = datetime.now(timezone.utc) - timedelta(days=args.keep_days)
|
|
|
|
# Date-tagged versions (YYYY.MM.DD), newest first
|
|
date_tagged = []
|
|
for v in versions:
|
|
tags = v.get("tags") or []
|
|
for t in tags:
|
|
if len(t) == 10 and t[4] == "." and t[7] == ".":
|
|
date_tagged.append((t, v))
|
|
break
|
|
date_tagged.sort(key=lambda kv: kv[0], reverse=True)
|
|
keep_date_tags = {t for t, _ in date_tagged[:args.keep_latest]}
|
|
|
|
deleted = 0
|
|
for v in versions:
|
|
tags = v.get("tags") or []
|
|
if "latest" in tags:
|
|
continue
|
|
if any(t in keep_date_tags for t in tags):
|
|
continue
|
|
try:
|
|
created = datetime.fromisoformat(v["created_at"].replace("Z", "+00:00"))
|
|
except (KeyError, ValueError):
|
|
continue
|
|
if created >= cutoff:
|
|
continue
|
|
version_id = v.get("id")
|
|
print(f" deleting v{version_id} tags={tags} created={v['created_at']}")
|
|
if not args.dry_run:
|
|
api(token, "DELETE",
|
|
f"/api/v1/packages/{args.owner}/container/{args.package}/versions/{version_id}")
|
|
deleted += 1
|
|
print(f"done: {deleted} version(s) deleted")
|
|
return 0
|
|
|
|
|
|
if __name__ == "__main__":
|
|
sys.exit(main())
|