feat(git): kvb-git-orphans-find for merged and abandoned branches
orphans.py classifies every local branch and detached worktree as merged-clean, merged-dirty, stale-open or active (ancestor or patch-equivalent of origin/<default>, dirty and unpushed counts, last activity, live council claims, busy processes) and proposes kvb-git-branch-gc, ask or keep; it reads only. The skill asks one question before any per-row round. kvb-dream step 8 runs it per repository in scope, kvb-cleanup at watch stage warn or with large worktrees. 🎯 Fix: 92 % 💥 Break: 3 % 💸 Cost: 148 % ⏱️ Time: – 🛡️ Security: 100 % 💰 Value: ? 🏆 Score: 60 🚦 Gate: ⚠️ cost 148 % > 100: ask the operator before the commit Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Kevin Veen-BirkenbachandClaude Opus 5.5 committed
1 parent
03c56f0801
commit
b8d0b6cf87
6 files changed
+776
-13
No files matched your search
@@ -56,6 +56,7 @@ flowchart LR
|
||||
git --> git_pr_label[kvb-git-pr-label]
|
||||
git --> git_update_branches[kvb-git-update-branches]
|
||||
git --> git_branch_gc[kvb-git-branch-gc]
|
||||
git --> git_orphans_find[kvb-git-orphans-find]
|
||||
git --> git_changelog[kvb-git-changelog]
|
||||
git --> git_hotfix[kvb-git-hotfix]
|
||||
check --> check_legal[kvb-check-legal]
|
||||
@@ -156,6 +157,7 @@ flowchart LR
|
||||
pr_label[kvb-git-pr-label]
|
||||
update_branches[kvb-git-update-branches]
|
||||
branch_gc[kvb-git-branch-gc]
|
||||
orphans_find[kvb-git-orphans-find]
|
||||
changelog[kvb-git-changelog]
|
||||
hotfix[kvb-git-hotfix]
|
||||
end
|
||||
@@ -261,8 +263,11 @@ flowchart LR
|
||||
|
||||
coordinate --> democracy
|
||||
cleanup --> democracy
|
||||
cleanup --> branch_gc
|
||||
cleanup --> orphans_find
|
||||
branch_gc --> democracy
|
||||
orphans_find --> branch_gc
|
||||
orphans_find --> choice
|
||||
orphans_find --> operator
|
||||
funnel --> democracy
|
||||
funnel --> dialectic
|
||||
funnel --> subagent_model
|
||||
@@ -312,7 +317,7 @@ flowchart LR
|
||||
dream --> dialectic
|
||||
dream --> optimize
|
||||
dream --> cleanup
|
||||
dream --> branch_gc
|
||||
dream --> orphans_find
|
||||
optimize --> skill_cleanup
|
||||
optimize --> transcend
|
||||
optimize --> autoskill
|
||||
|
||||
@@ -21,20 +21,21 @@ request and stop, or, when the operator ordered the cleanup here, first
|
||||
## Step 1: inventory
|
||||
|
||||
Read-only, in parallel, with sizes, only in the agent write scope (Claude
|
||||
Code: `sandbox.filesystem.allowWrite`) and session scratch dirs, even where
|
||||
more is readable; never another user's files. Prefer the project's cleanup
|
||||
and teardown targets; obey rules forbidding raw commands.
|
||||
Code: `sandbox.filesystem.allowWrite`) and session scratch dirs; never
|
||||
another user's files. Prefer the project's cleanup and teardown targets; obey
|
||||
rules forbidding raw commands.
|
||||
|
||||
- **/tmp**: `du -sh` per own top-level entry; system entries (`.X11-unix`,
|
||||
`.ICE-unix`, `systemd-private-*`, `ssh-*`, `tmux-*`, sockets) are never
|
||||
candidates.
|
||||
- **Docker**, **worktrees**: read `docker.md` (its `⚠ Volumes` checklist
|
||||
joins Step 4) and `worktrees.md` next to this file when present.
|
||||
joins Step 4) and `worktrees.md` next to this file when present. Only at
|
||||
watch stage `warn` or worse, or with worktrees among the biggest consumers:
|
||||
`kvb-git-orphans-find --sizes`, its largest orphaned worktrees as candidates.
|
||||
- **Agent dirs**: pip, npm, pre-commit, act, gh, buildx caches; Ansible and
|
||||
build temp dirs.
|
||||
- **Register**: `council.py list --long`; `rasci.py artifacts` (`kvb-org-artefacts`,
|
||||
`--ended` for candidates): workdir, branch, artifacts, status and worker per
|
||||
`kvb-org-rasci` task.
|
||||
`--ended` for candidates).
|
||||
- **Live use**: `fuser`, `lsof`, `ps -o pid,etime,comm`, never full command
|
||||
lines or environments (credentials). Sandboxed, an empty result proves
|
||||
nothing.
|
||||
@@ -54,8 +55,8 @@ First match wins: claimed by a peer, `keep`; in a register task not `done`,
|
||||
`stopped` or `stale`, `keep (task <task>)` (an ended task's items are its
|
||||
worker's candidates); a running deploy, gate, test, swarm run or build, `keep
|
||||
(running)`; a silent peer's, `keep (no answer from <peer>)`, silence is not
|
||||
consent; sandboxed, anything touched within 24 hours (`find -mtime +0` lists
|
||||
the older), `keep (recent, possibly in use)`; archive duty,
|
||||
consent; sandboxed, anything touched within 24 hours, `keep (recent,
|
||||
possibly in use)`; archive duty,
|
||||
`archive first`, never a plain delete. Else a candidate:
|
||||
|
||||
- **low**, regenerated cheaply: stopped containers without volumes, dangling
|
||||
|
||||
@@ -75,9 +75,9 @@ in-scope session's scripts, tests and skills into their repositories.
|
||||
|
||||
The `kvb-cleanup` skill for the disk, `/tmp`, Docker and agent directories the
|
||||
window filled, with the finished tasks' artifacts (`rasci.py artifacts
|
||||
--ended`) as candidates; then the `kvb-git-branch-gc` skill for every
|
||||
in-scope repository's merged branches and worktrees. Each keeps its own
|
||||
confirmations; the dream never writes, deletes or commits for them. Close
|
||||
--ended`) as candidates; then `kvb-git-orphans-find` per in-scope
|
||||
repository, which hands merged-clean rows to `kvb-git-branch-gc`. Each keeps
|
||||
its own confirmations; the dream never writes, deletes or commits for them. Close
|
||||
with `date +%s > ~/.claude/.dream-stamps/"$CLAUDE_CODE_SESSION_ID"`, so the
|
||||
next hint is twelve hours out.
|
||||
|
||||
|
||||
@@ -0,0 +1,88 @@
|
||||
---
|
||||
name: kvb-git-orphans-find
|
||||
description: >
|
||||
Find merged and abandoned branches and worktrees, propose deleting them.
|
||||
---
|
||||
|
||||
Finds merged branches and worktrees and those with open changes nobody works
|
||||
on any more, then proposes a step for each. The script only reads; nothing
|
||||
goes without the operator's pick in this run.
|
||||
|
||||
## When
|
||||
|
||||
On "verwaiste branches", "alte worktrees", "was kann weg"; from step 8 of
|
||||
`kvb-dream`; from `kvb-cleanup` with `--sizes` when disk runs short.
|
||||
|
||||
## Step 1: find
|
||||
|
||||
Per repository in scope:
|
||||
|
||||
1. Fetch first: `git fetch --no-auto-maintenance origin`, never a plain
|
||||
fetch (the `kvb-git-branch-gc` reason) and no `--prune`, which deletes
|
||||
refs.
|
||||
2. `python3 ${CLAUDE_SKILL_DIR}/scripts/orphans.py --repo <dir> --default
|
||||
<branch> --stale-days 7 --top 5 --full /tmp/orphans-<repo>-<N>.md`:
|
||||
`--default` the branch `origin/HEAD` names, another limit only on the
|
||||
operator's word. `--sizes` adds and orders by each orphan's worktree size;
|
||||
it walks every file, so only when disk matters. `--json` lists every row.
|
||||
|
||||
The summary counts each class and shows its top rows, oldest or largest
|
||||
first; the `--full` file holds all.
|
||||
|
||||
Merged means the tip is on `origin/<default>`, or `git cherry` finds every
|
||||
commit's patch there. That catches squash and rebase merges only partly: a
|
||||
squash of several commits, a rebase that changed a patch or a merge commit
|
||||
on the branch stays unmerged. Say so above the summaries.
|
||||
|
||||
| Class | Means | Proposal |
|
||||
| --- | --- | --- |
|
||||
| `merged-clean` | merged, nothing dirty | `kvb-git-branch-gc` |
|
||||
| `merged-dirty` | merged, dirty files | `ask` |
|
||||
| `stale-open` | unmerged, dirty or unpushed (no upstream counts), idle beyond the limit, no live claim, not busy | `ask` |
|
||||
| `active` | anything else; always the main worktree, the default branch and `archive/` branches | `keep` |
|
||||
|
||||
A merged row with a live claim or a busy process proposes `keep (claimed)`
|
||||
or `keep (busy)`: never offer it. Busy is unknown without the agents-council
|
||||
config, and a sandbox hides other PID namespaces: say so.
|
||||
|
||||
## Step 2: propose
|
||||
|
||||
Print each repository's summary, then:
|
||||
|
||||
- **merged-clean**: the rows go to the `kvb-git-branch-gc` skill; its dry
|
||||
run, claims step and pick decide. A row its dry run does not list stays.
|
||||
- **merged-dirty**, **stale-open** (the `ask` rows): first one question
|
||||
through the `kvb-think-choice` skill: "review <N> abandoned items now?".
|
||||
No ends here. Yes: rounds of at most four rows in summary order, taken
|
||||
from the `--full` file, one question per row naming what a delete loses
|
||||
(dirty files, unpushed commits):
|
||||
- `archive` (recommended, loses nothing): the owner commits or stashes
|
||||
the changes, then `git branch -m <branch> archive/<branch>` and `git
|
||||
worktree remove <path>` once clean. Owner gone: an `operator.py`
|
||||
`decision` row for the changes.
|
||||
- `keep`: nothing changes.
|
||||
- `delete`: the worktree and the branch go.
|
||||
|
||||
## Step 3: act
|
||||
|
||||
Only on the operator's pick for that row, never widened:
|
||||
|
||||
- An agent never runs `git branch -D`, `git worktree remove --force` or
|
||||
anything outside the sandbox. Each such command becomes its own
|
||||
`operator.py add` row (`kvb-org-operator`): `--dir <repo>`, the command,
|
||||
the reason, `--check absent:<worktree path>` for a worktree, and for a
|
||||
branch `absent:<git common dir>/refs/heads/<branch>` while that loose ref
|
||||
file exists, else `manual`. The worktree row comes first: git refuses to
|
||||
delete a checked-out branch.
|
||||
- Never delete a peer's worktree without the operator's pick; afterwards
|
||||
`radio.py post --to <peer>` (`kvb-org-radio`) names what went.
|
||||
|
||||
## Step 4: report
|
||||
|
||||
Per repository: rows handed to gc, archived, kept and deleted, each with its
|
||||
reason, then the `operator.py run` block.
|
||||
|
||||
## Rules
|
||||
|
||||
- A pick from an earlier run does not carry over.
|
||||
- Never route around a refusal through another command or a peer.
|
||||
+425
@@ -0,0 +1,425 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Find merged and abandoned branches and worktrees of a repository and propose a step for each.
|
||||
|
||||
Reads only: no fetch, delete or edit; the caller fetches first. Every git call
|
||||
runs with GIT_OPTIONAL_LOCKS=0, because a plain `git status` refreshes the
|
||||
index and so moves the index mtime this script reads as activity.
|
||||
|
||||
Args:
|
||||
--repo: any worktree of the repository.
|
||||
--default: the default branch; merged means merged into origin/<default>.
|
||||
--stale-days: an unmerged row idle for longer may be stale-open.
|
||||
--top: rows per class the summary shows, 0 for the counts only.
|
||||
--full: file that receives the complete table of every row but the active
|
||||
ones; the summary names it.
|
||||
--sizes: measure the worktree of every row but the active ones (bytes of
|
||||
its regular files, .git skipped, no symlink followed), show it and
|
||||
order by it, largest first; slow, as it walks every file.
|
||||
--json: print every row, active ones included, as JSON instead of the
|
||||
summary; --top does not shorten it.
|
||||
|
||||
Environment:
|
||||
AGENTS_COUNCIL_ROOT: council directory of the kvb-org-organize skill, read
|
||||
through its council.py for claims.
|
||||
AGENTS_COUNCIL_CONFIG: config of its watch.py, whose busy_processes name
|
||||
the busy processes; without the file busy is unknown (null).
|
||||
|
||||
Rows, one per local branch with the worktree holding it, and one per worktree
|
||||
with a detached HEAD:
|
||||
merged: `ancestor` when the tip is an ancestor of origin/<default>,
|
||||
`patch` when `git cherry` finds a patch-equivalent there for every
|
||||
commit outside it. That catches squash and rebase merges only partly:
|
||||
a squash of several commits, a rebase that changed a patch or a merge
|
||||
commit outside origin/<default> stays unmerged.
|
||||
dirty: changed and untracked files of the worktree.
|
||||
unpushed: commits outside origin/<default> without a patch-equivalent
|
||||
there that the upstream lacks; without an upstream on a remote, those
|
||||
no remote-tracking ref holds. Always 0 when merged.
|
||||
upstream: the remote-tracking upstream, null when none resolves; null
|
||||
counts as unpushed for an unmerged row.
|
||||
last activity: newest of the tip's commit date, the worktree's index mtime
|
||||
and the mtimes of its changed files.
|
||||
claims: council claims whose work names the worktree path or the branch;
|
||||
only a live one protects.
|
||||
busy: a busy_processes process works inside the worktree; processes of
|
||||
another PID namespace stay unseen.
|
||||
size: bytes with --sizes, else null; null for active rows and rows
|
||||
without a worktree.
|
||||
|
||||
Classes, first match wins:
|
||||
active: the main worktree, the default branch and archive/ branches.
|
||||
merged-clean: merged, nothing dirty; proposal kvb-git-branch-gc.
|
||||
merged-dirty: merged with dirty files; proposal ask.
|
||||
stale-open: unmerged, dirty or unpushed, last activity older than
|
||||
--stale-days, no live claim, not busy; proposal ask.
|
||||
active: anything else; proposal keep.
|
||||
A merged row with a live claim or a busy process proposes keep (claimed)
|
||||
or keep (busy) instead.
|
||||
|
||||
Output:
|
||||
A summary: one line per class with its count and proposal, the --full
|
||||
file, claims or busy that could not be checked; then the table `| Class |
|
||||
Branch | Worktree | Dirty | Unpushed | Last activity | Claim | Proposal |`
|
||||
of the top rows per class but active, oldest last activity first, with
|
||||
--sizes largest first and a Size column after Worktree. The --full file
|
||||
holds the same table with every row but the active ones.
|
||||
|
||||
Exit codes:
|
||||
0 done, 2 usage error, a failed git call or origin/<default> missing.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import contextlib
|
||||
import dataclasses
|
||||
import importlib.util
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
import stat
|
||||
import subprocess
|
||||
import sys
|
||||
import time
|
||||
from collections.abc import Callable
|
||||
from pathlib import Path
|
||||
from types import ModuleType
|
||||
from typing import NoReturn
|
||||
|
||||
ORGANIZE = Path(__file__).resolve().parents[2] / "kvb-org-organize" / "scripts"
|
||||
DAY = 86400
|
||||
ORDER = ("merged-clean", "merged-dirty", "stale-open", "active")
|
||||
HEADER = ("Class", "Branch", "Worktree", "Dirty", "Unpushed", "Last activity", "Claim", "Proposal")
|
||||
GC = "kvb-git-branch-gc"
|
||||
PROPOSALS = {"merged-clean": GC, "merged-dirty": "ask", "stale-open": "ask", "active": "keep, listed by --json"}
|
||||
UNITS = ("KiB", "MiB", "GiB", "TiB")
|
||||
DETACHED = "(detached)"
|
||||
ARCHIVE = "refs/heads/archive/"
|
||||
|
||||
|
||||
@dataclasses.dataclass(frozen=True)
|
||||
class Scan:
|
||||
repo: str
|
||||
base: str
|
||||
default: str
|
||||
claims: list[dict]
|
||||
busy: Callable[[str], bool] | None
|
||||
now: float
|
||||
limit: float
|
||||
|
||||
|
||||
def fail(message: str) -> NoReturn:
|
||||
print(f"orphans: {message}", file=sys.stderr)
|
||||
sys.exit(2)
|
||||
|
||||
|
||||
def module(name: str) -> ModuleType | None:
|
||||
path = ORGANIZE / f"{name}.py"
|
||||
if not path.is_file():
|
||||
return None
|
||||
spec = importlib.util.spec_from_file_location(name, path)
|
||||
loaded = importlib.util.module_from_spec(spec)
|
||||
spec.loader.exec_module(loaded)
|
||||
return loaded
|
||||
|
||||
|
||||
def git(where: str, *args: str) -> subprocess.CompletedProcess:
|
||||
try:
|
||||
return subprocess.run(
|
||||
["git", *args], cwd=where, stdin=subprocess.DEVNULL, capture_output=True, text=True,
|
||||
env={**os.environ, "GIT_OPTIONAL_LOCKS": "0"}, check=False,
|
||||
)
|
||||
except OSError as error:
|
||||
return subprocess.CompletedProcess(["git", *args], 128, "", str(error))
|
||||
|
||||
|
||||
def git_out(where: str, *args: str) -> str:
|
||||
result = git(where, *args)
|
||||
if result.returncode:
|
||||
fail(f"git {' '.join(args)} in {where}: {(result.stderr or result.stdout).strip()}")
|
||||
return result.stdout
|
||||
|
||||
|
||||
def resolves(where: str, ref: str) -> bool:
|
||||
return git(where, "rev-parse", "--verify", "--quiet", f"{ref}^{{commit}}").returncode == 0
|
||||
|
||||
|
||||
def worktrees(repo: str) -> list[dict]:
|
||||
trees: list[dict] = []
|
||||
for line in git_out(repo, "worktree", "list", "--porcelain").splitlines():
|
||||
key, _, value = line.partition(" ")
|
||||
if key == "worktree":
|
||||
trees.append({"path": value, "head": None, "branch": None, "main": not trees, "bare": False})
|
||||
elif trees and key == "HEAD":
|
||||
trees[-1]["head"] = value
|
||||
elif trees and key == "branch":
|
||||
trees[-1]["branch"] = value
|
||||
elif trees and key == "bare":
|
||||
trees[-1]["bare"] = True
|
||||
return trees
|
||||
|
||||
|
||||
def branches(repo: str) -> list[list[str]]:
|
||||
out = git_out(repo, "branch", "--list", "--format=%(refname)\t%(upstream)\t%(committerdate:unix)")
|
||||
return [line.split("\t") for line in out.splitlines() if line]
|
||||
|
||||
|
||||
def committed(repo: str, rev: str) -> int:
|
||||
return int(git_out(repo, "log", "-1", "--format=%ct", rev).strip())
|
||||
|
||||
|
||||
def measure(scan: Scan, ref: str, upstream: str) -> tuple[str | None, int, str | None]:
|
||||
tracked = upstream if upstream.startswith("refs/remotes/") and resolves(scan.repo, upstream) else None
|
||||
outside = set(git_out(scan.repo, "rev-list", ref, f"^{scan.base}").split())
|
||||
if not outside:
|
||||
return "ancestor", 0, tracked
|
||||
cherry = git_out(scan.repo, "cherry", scan.base, ref).splitlines()
|
||||
equivalent = {line[2:] for line in cherry if line.startswith("- ")}
|
||||
if equivalent == outside:
|
||||
return "patch", 0, tracked
|
||||
held = [f"^{tracked}"] if tracked else ["--not", "--remotes"]
|
||||
local = set(git_out(scan.repo, "rev-list", ref, *held).split())
|
||||
return None, len(local & (outside - equivalent)), tracked
|
||||
|
||||
|
||||
def index_mtime(tree: str) -> float:
|
||||
path = git_out(tree, "rev-parse", "--path-format=absolute", "--git-path", "index").strip()
|
||||
try:
|
||||
return os.stat(path).st_mtime
|
||||
except OSError:
|
||||
return 0.0
|
||||
|
||||
|
||||
def changes(tree: str) -> tuple[int, float]:
|
||||
fields = git_out(tree, "status", "--porcelain=v1", "-z", "--untracked-files=all").split("\0")
|
||||
count, newest, at = 0, 0.0, 0
|
||||
while at < len(fields):
|
||||
entry = fields[at]
|
||||
at += 2 if "R" in entry[:2] or "C" in entry[:2] else 1
|
||||
if not entry:
|
||||
continue
|
||||
count += 1
|
||||
with contextlib.suppress(OSError):
|
||||
newest = max(newest, os.lstat(os.path.join(tree, entry[3:])).st_mtime)
|
||||
return count, newest
|
||||
|
||||
|
||||
def mentions(text: str, name: str) -> bool:
|
||||
return re.search(rf"(?<![\w./-]){re.escape(name)}(?![\w-]|\.\w)", text) is not None
|
||||
|
||||
|
||||
def classify(item: dict, scan: Scan, ref: str) -> str:
|
||||
if item["main"] or item["default"] or ref.startswith(ARCHIVE):
|
||||
return "active"
|
||||
if item["merged"]:
|
||||
return "merged-dirty" if item["dirty"] else "merged-clean"
|
||||
pending = bool(item["dirty"] or item["unpushed"] or not item["upstream"])
|
||||
idle = scan.now - item["last_activity"] > scan.limit
|
||||
guarded = any(claim["live"] for claim in item["claims"]) or item["busy"]
|
||||
return "stale-open" if pending and idle and not guarded else "active"
|
||||
|
||||
|
||||
def proposal(item: dict) -> str:
|
||||
if item["class"] == "active":
|
||||
return "keep"
|
||||
if any(claim["live"] for claim in item["claims"]):
|
||||
return "keep (claimed)"
|
||||
if item["busy"]:
|
||||
return "keep (busy)"
|
||||
return GC if item["class"] == "merged-clean" else "ask"
|
||||
|
||||
|
||||
def inspect(scan: Scan, ref: str, upstream: str, date: int, tree: dict | None) -> dict:
|
||||
name = ref.removeprefix("refs/heads/") if ref.startswith("refs/heads/") else DETACHED
|
||||
merged, unpushed, tracked = measure(scan, ref, upstream)
|
||||
path = tree["path"] if tree else None
|
||||
present = path is not None and os.path.isdir(path)
|
||||
activity, dirty, busy = float(date), None, False
|
||||
if present:
|
||||
activity = max(activity, index_mtime(path))
|
||||
dirty, changed = changes(path)
|
||||
activity = max(activity, changed)
|
||||
busy = scan.busy(path) if scan.busy else None
|
||||
names = {path, os.path.realpath(path)} if path else set()
|
||||
if ref.startswith("refs/heads/"):
|
||||
names.add(name)
|
||||
item = {
|
||||
"branch": name,
|
||||
"worktree": path,
|
||||
"missing": path is not None and not present,
|
||||
"main": bool(tree and tree["main"]),
|
||||
"default": ref == f"refs/heads/{scan.default}",
|
||||
"merged": merged,
|
||||
"dirty": dirty,
|
||||
"unpushed": unpushed,
|
||||
"upstream": tracked,
|
||||
"last_activity": int(activity),
|
||||
"claims": [
|
||||
{key: claim[key] for key in ("office", "holder", "live")}
|
||||
for claim in scan.claims
|
||||
if any(mentions(claim["work"], each) for each in names)
|
||||
],
|
||||
"busy": busy,
|
||||
}
|
||||
item["class"] = classify(item, scan, ref)
|
||||
item["proposal"] = proposal(item)
|
||||
return item
|
||||
|
||||
|
||||
def tree_size(top: str) -> int:
|
||||
total = 0
|
||||
for base, dirs, files in os.walk(top):
|
||||
dirs[:] = [name for name in dirs if name != ".git"]
|
||||
for name in files:
|
||||
if name == ".git":
|
||||
continue
|
||||
with contextlib.suppress(OSError):
|
||||
found = os.lstat(os.path.join(base, name))
|
||||
if stat.S_ISREG(found.st_mode):
|
||||
total += found.st_size
|
||||
return total
|
||||
|
||||
|
||||
def human(size: int | None) -> str:
|
||||
if size is None:
|
||||
return "-"
|
||||
if size < 1024:
|
||||
return f"{size} B"
|
||||
value = float(size)
|
||||
for unit in UNITS:
|
||||
value /= 1024
|
||||
if value < 1024 or unit == UNITS[-1]:
|
||||
break
|
||||
return f"{value:.1f} {unit}"
|
||||
|
||||
|
||||
def cells(item: dict, now: float, sizes: bool) -> list[str]:
|
||||
worktree = (item["worktree"] or "-") + (" (missing)" if item["missing"] else "")
|
||||
unpushed = str(item["unpushed"]) + (" (no upstream)" if not item["upstream"] and not item["merged"] else "")
|
||||
day = time.strftime("%Y-%m-%d", time.localtime(item["last_activity"]))
|
||||
age = int((now - item["last_activity"]) // DAY)
|
||||
claims = [f"{c['office']} ({c['holder']}{'' if c['live'] else ', ended'})" for c in item["claims"]]
|
||||
if item["busy"]:
|
||||
claims.append("busy")
|
||||
values = [
|
||||
item["class"], item["branch"], worktree, *([human(item["size"])] if sizes else []),
|
||||
"-" if item["dirty"] is None else str(item["dirty"]), unpushed, f"{day} ({age} d)",
|
||||
", ".join(claims) or "-", item["proposal"],
|
||||
]
|
||||
return [value.replace("|", "\\|") for value in values]
|
||||
|
||||
|
||||
def table(items: list[dict], now: float, sizes: bool) -> list[str]:
|
||||
header = [*HEADER[:3], *(["Size"] if sizes else []), *HEADER[3:]]
|
||||
lines = ["| " + " | ".join(header) + " |", "| " + " | ".join("---" for _ in header) + " |"]
|
||||
return lines + ["| " + " | ".join(cells(item, now, sizes)) + " |" for item in items]
|
||||
|
||||
|
||||
def rank(item: dict, sizes: bool) -> tuple:
|
||||
largest = -(item["size"] or 0) if sizes else 0
|
||||
return ORDER.index(item["class"]), largest, item["last_activity"], item["branch"], item["worktree"] or ""
|
||||
|
||||
|
||||
def parse() -> argparse.Namespace:
|
||||
parser = argparse.ArgumentParser(description=__doc__.splitlines()[0])
|
||||
parser.add_argument("--repo", required=True)
|
||||
parser.add_argument("--default", required=True)
|
||||
parser.add_argument("--stale-days", type=int, required=True)
|
||||
parser.add_argument("--top", type=int, required=True)
|
||||
parser.add_argument("--full")
|
||||
parser.add_argument("--sizes", action="store_true")
|
||||
parser.add_argument("--json", action="store_true")
|
||||
args = parser.parse_args()
|
||||
if args.stale_days < 0:
|
||||
fail("--stale-days must be 0 or more")
|
||||
if args.top < 0:
|
||||
fail("--top must be 0 or more")
|
||||
return args
|
||||
|
||||
|
||||
def target(args: argparse.Namespace) -> tuple[str, str]:
|
||||
repo = os.path.realpath(args.repo)
|
||||
if not os.path.isdir(repo):
|
||||
fail(f"--repo {args.repo} is no directory")
|
||||
if args.default.startswith("-") or git(repo, "check-ref-format", f"refs/heads/{args.default}").returncode:
|
||||
fail(f"--default {args.default!r} is no valid branch name")
|
||||
base = f"refs/remotes/origin/{args.default}"
|
||||
if not resolves(repo, base):
|
||||
fail(f"origin/{args.default} does not resolve in {repo}; fetch first")
|
||||
return repo, base
|
||||
|
||||
|
||||
def council_claims(council: ModuleType | None) -> list[dict]:
|
||||
if council is None:
|
||||
return []
|
||||
live = council.live_sessions()
|
||||
return [
|
||||
{
|
||||
"office": office,
|
||||
"holder": claim.get("name") or claim.get("session"),
|
||||
"live": not council.is_stale(claim, live),
|
||||
"work": str(claim.get("work", "")),
|
||||
}
|
||||
for office, claim in council.claims()
|
||||
]
|
||||
|
||||
|
||||
def rows(scan: Scan, sizes: bool) -> list[dict]:
|
||||
trees = worktrees(scan.repo)
|
||||
held = {tree["branch"]: tree for tree in trees if tree["branch"]}
|
||||
items = [inspect(scan, ref, upstream, int(date), held.get(ref)) for ref, upstream, date in branches(scan.repo)]
|
||||
items += [
|
||||
inspect(scan, tree["head"], "", committed(scan.repo, tree["head"]), tree)
|
||||
for tree in trees
|
||||
if not tree["bare"] and tree["branch"] is None and tree["head"]
|
||||
]
|
||||
for item in items:
|
||||
measured = sizes and item["class"] != "active" and item["worktree"] and not item["missing"]
|
||||
item["size"] = tree_size(item["worktree"]) if measured else None
|
||||
items.sort(key=lambda item: rank(item, sizes))
|
||||
return items
|
||||
|
||||
|
||||
def main() -> int:
|
||||
args = parse()
|
||||
repo, base = target(args)
|
||||
council, watch = module("council"), module("watch")
|
||||
config = watch.load_config() if watch else None
|
||||
names = config["busy_processes"] if config else None
|
||||
scan = Scan(
|
||||
repo=repo, base=base, default=args.default, claims=council_claims(council),
|
||||
busy=(lambda tree: watch.busy(tree, names)) if names is not None else None,
|
||||
now=time.time(), limit=args.stale_days * DAY,
|
||||
)
|
||||
items = rows(scan, args.sizes)
|
||||
orphans = [item for item in items if item["class"] != "active"]
|
||||
full = os.path.abspath(args.full) if args.full is not None else None
|
||||
if full is not None:
|
||||
try:
|
||||
Path(full).write_text("\n".join(table(orphans, scan.now, args.sizes)) + "\n", encoding="utf-8")
|
||||
except OSError as error:
|
||||
fail(f"--full {args.full}: {error.strerror or error}")
|
||||
if args.json:
|
||||
print(json.dumps({
|
||||
"repo": repo, "default": args.default, "stale_days": args.stale_days,
|
||||
"claims_checked": council is not None, "busy_checked": names is not None, "rows": items,
|
||||
}, indent=1))
|
||||
return 0
|
||||
print(f"orphans in {repo}, merged into origin/{args.default}, stale after {args.stale_days} days:")
|
||||
for name in ORDER:
|
||||
print(f"- {name}: {sum(item['class'] == name for item in items)} ({PROPOSALS[name]})")
|
||||
if full is not None:
|
||||
print(f"- full table: {full}")
|
||||
if council is None:
|
||||
print("- claims unknown: council.py of kvb-org-organize is missing")
|
||||
if names is None:
|
||||
print("- busy unknown: no agents-council config")
|
||||
top = [item for name in ORDER[:-1] for item in [o for o in orphans if o["class"] == name][: args.top]]
|
||||
if top:
|
||||
print(f"\nTop {args.top} per class, {'largest' if args.sizes else 'oldest'} first:\n")
|
||||
print("\n".join(table(top, scan.now, args.sizes)))
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
sys.exit(main())
|
||||
@@ -0,0 +1,244 @@
|
||||
"""Exercise kvb-git-orphans-find: merged, stale and active branches and worktrees, read only."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import os
|
||||
import subprocess
|
||||
import sys
|
||||
import tempfile
|
||||
import time
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
|
||||
REPO_ROOT = Path(__file__).resolve().parents[1]
|
||||
ORPHANS = REPO_ROOT / "skills" / "kvb-git-orphans-find" / "scripts" / "orphans.py"
|
||||
DAY = 86400
|
||||
OLD = time.time() - 30 * DAY
|
||||
AGES = {"stale": OLD, "claimed": OLD, "ended": OLD - 5 * DAY, "busy": OLD, "recent": OLD}
|
||||
BIG = 50_000
|
||||
IDENTITY = {
|
||||
"GIT_AUTHOR_NAME": "Test",
|
||||
"GIT_AUTHOR_EMAIL": "test@example.org",
|
||||
"GIT_COMMITTER_NAME": "Test",
|
||||
"GIT_COMMITTER_EMAIL": "test@example.org",
|
||||
"GIT_CONFIG_NOSYSTEM": "1",
|
||||
}
|
||||
TABLE = {
|
||||
"merged": ("merged-clean", "kvb-git-branch-gc"),
|
||||
"squashed": ("merged-clean", "kvb-git-branch-gc"),
|
||||
"mdirty": ("merged-dirty", "ask"),
|
||||
"ended": ("stale-open", "ask"),
|
||||
"stale": ("stale-open", "ask"),
|
||||
}
|
||||
ACTIVE = ("archive/old", "busy", "claimed", "main", "recent")
|
||||
COUNTS = [
|
||||
"- merged-clean: 2 (kvb-git-branch-gc)",
|
||||
"- merged-dirty: 1 (ask)",
|
||||
"- stale-open: 2 (ask)",
|
||||
"- active: 5 (keep, listed by --json)",
|
||||
]
|
||||
|
||||
|
||||
def rows_of(text: str) -> list[dict[str, str]]:
|
||||
lines = [line for line in text.splitlines() if line.startswith("| ")]
|
||||
if not lines:
|
||||
return []
|
||||
header = lines[0].strip("| ").split(" | ")
|
||||
return [dict(zip(header, line.strip("| ").split(" | "), strict=True)) for line in lines[2:]]
|
||||
|
||||
|
||||
class TestOrphans(unittest.TestCase):
|
||||
@classmethod
|
||||
def setUpClass(cls):
|
||||
tmp = tempfile.TemporaryDirectory()
|
||||
cls.addClassCleanup(tmp.cleanup)
|
||||
cls.base = Path(tmp.name).resolve()
|
||||
home = cls.base / "home"
|
||||
(home / ".claude" / "sessions").mkdir(parents=True)
|
||||
cls.root = cls.base / "council"
|
||||
config = cls.base / "config.json"
|
||||
config.write_text(json.dumps({"busy_processes": ["sleep"]}), encoding="utf-8")
|
||||
cls.env = {
|
||||
"PATH": "/usr/bin:/bin",
|
||||
"HOME": str(home),
|
||||
"AGENTS_COUNCIL_ROOT": str(cls.root),
|
||||
"AGENTS_COUNCIL_CONFIG": str(config),
|
||||
"GIT_CEILING_DIRECTORIES": str(cls.base),
|
||||
**IDENTITY,
|
||||
}
|
||||
origin = cls.base / "origin.git"
|
||||
cls.git(cls.base, "init", "-q", "--bare", "-b", "main", str(origin))
|
||||
cls.main = cls.base / "main"
|
||||
cls.main.mkdir()
|
||||
cls.git(cls.main, "init", "-q", "-b", "main")
|
||||
cls.commit(cls.main, "app.txt", "one\n", "init", None)
|
||||
cls.git(cls.main, "remote", "add", "origin", str(origin))
|
||||
cls.git(cls.main, "push", "-q", "-u", "origin", "main")
|
||||
|
||||
cls.trees = {name: cls.base / f"wt-{name}" for name in ("merged", "mdirty", *AGES)}
|
||||
cls.add_tree("merged")
|
||||
cls.commit(cls.trees["merged"], "m.txt", "m\n", "merged work", None)
|
||||
cls.git(cls.main, "merge", "-q", "--ff-only", "merged")
|
||||
|
||||
cls.git(cls.main, "switch", "-q", "-c", "squashed")
|
||||
cls.commit(cls.main, "sq.txt", "sq\n", "squashed work", OLD)
|
||||
cls.git(cls.main, "switch", "-q", "main")
|
||||
cls.git(cls.main, "merge", "-q", "--squash", "squashed")
|
||||
cls.git(cls.main, "commit", "-q", "-m", "squashed work, squashed")
|
||||
cls.git(cls.main, "push", "-q", "origin", "main")
|
||||
|
||||
cls.add_tree("mdirty")
|
||||
(cls.trees["mdirty"] / "scratch.txt").write_text("left over\n", encoding="utf-8")
|
||||
for name, when in AGES.items():
|
||||
cls.add_tree(name)
|
||||
cls.commit(cls.trees[name], f"{name}.txt", "one\n", f"{name} work", when)
|
||||
(cls.trees[name] / f"{name}.txt").write_text("two\n", encoding="utf-8")
|
||||
if name != "recent":
|
||||
os.utime(cls.trees[name] / f"{name}.txt", (when, when))
|
||||
os.utime(cls.index(cls.trees[name]), (when, when))
|
||||
huge = cls.base / "huge.bin"
|
||||
huge.write_bytes(b"x" * 4 * BIG)
|
||||
big, link = cls.trees["stale"] / "big.bin", cls.trees["stale"] / "outside"
|
||||
big.write_bytes(b"x" * BIG)
|
||||
link.symlink_to(huge)
|
||||
os.utime(big, (OLD, OLD))
|
||||
os.utime(link, (OLD, OLD), follow_symlinks=False)
|
||||
cls.git(cls.main, "branch", "archive/old", "stale")
|
||||
notes = cls.main / "notes.txt"
|
||||
notes.write_text("main worktree scratch\n", encoding="utf-8")
|
||||
os.utime(notes, (OLD, OLD))
|
||||
|
||||
cls.claim("work/claimed-job", {"session": "peer", "runtime": "other", "name": "Peer", "beat": time.time(),
|
||||
"work": f"finish {cls.trees['claimed']}"})
|
||||
cls.claim("work/ended-job", {"session": "gone", "runtime": "claude-code", "name": None, "beat": OLD,
|
||||
"work": "rebase ended onto main"})
|
||||
cls.sleeper = subprocess.Popen(["sleep", "120"], cwd=cls.trees["busy"])
|
||||
cls.addClassCleanup(cls.sleeper.wait)
|
||||
cls.addClassCleanup(cls.sleeper.kill)
|
||||
|
||||
@classmethod
|
||||
def run_git(cls, cwd: Path, env: dict[str, str], *args: str) -> str:
|
||||
return subprocess.run(["git", *args], cwd=cwd, env=env, capture_output=True, text=True, check=True).stdout
|
||||
|
||||
@classmethod
|
||||
def git(cls, cwd: Path, *args: str) -> str:
|
||||
return cls.run_git(cwd, cls.env, *args)
|
||||
|
||||
@classmethod
|
||||
def commit(cls, repo: Path, name: str, text: str, message: str, when: float | None) -> None:
|
||||
"""Commit one file.
|
||||
|
||||
Args:
|
||||
when: author and committer date as epoch seconds; None means now.
|
||||
"""
|
||||
(repo / name).write_text(text, encoding="utf-8")
|
||||
cls.git(repo, "add", name)
|
||||
dated = {} if when is None else {"GIT_AUTHOR_DATE": f"@{int(when)} +0000", "GIT_COMMITTER_DATE": f"@{int(when)} +0000"}
|
||||
cls.run_git(repo, {**cls.env, **dated}, "commit", "-q", "-m", message)
|
||||
|
||||
@classmethod
|
||||
def add_tree(cls, name: str) -> None:
|
||||
cls.git(cls.main, "worktree", "add", "-q", "-b", name, str(cls.trees[name]), "main")
|
||||
|
||||
@classmethod
|
||||
def index(cls, tree: Path) -> Path:
|
||||
return Path(cls.git(tree, "rev-parse", "--path-format=absolute", "--git-path", "index").strip())
|
||||
|
||||
@classmethod
|
||||
def claim(cls, office: str, fields: dict) -> None:
|
||||
path = cls.root / office
|
||||
path.mkdir(parents=True)
|
||||
claim = {"office": office, "since": "2026-11-01T00:00:00+00:00", **fields}
|
||||
(path / "claim.json").write_text(json.dumps(claim), encoding="utf-8")
|
||||
|
||||
def orphans(self, *extra: str) -> subprocess.CompletedProcess:
|
||||
return subprocess.run(
|
||||
[sys.executable, str(ORPHANS), "--repo", str(self.main), "--default", "main", "--stale-days", "7", *extra],
|
||||
capture_output=True, text=True, env=self.env, cwd=self.base, check=False,
|
||||
)
|
||||
|
||||
def out(self, *extra: str) -> str:
|
||||
result = self.orphans(*extra)
|
||||
self.assertEqual(result.returncode, 0, result.stderr)
|
||||
return result.stdout
|
||||
|
||||
def rows(self, *extra: str) -> dict[str, dict]:
|
||||
return {row["branch"]: row for row in json.loads(self.out("--json", "--top", "1", *extra))["rows"]}
|
||||
|
||||
def test_the_summary_counts_every_class_then_shows_the_oldest_rows_per_class(self):
|
||||
lines = self.out("--top", "1").splitlines()
|
||||
self.assertEqual(lines[1:5], COUNTS)
|
||||
self.assertNotIn("busy unknown", "\n".join(lines))
|
||||
self.assertIn("Top 1 per class, oldest first:", lines)
|
||||
self.assertEqual([(row["Branch"], row["Class"], row["Proposal"]) for row in rows_of("\n".join(lines))],
|
||||
[("squashed", *TABLE["squashed"]), ("mdirty", *TABLE["mdirty"]),
|
||||
("ended", *TABLE["ended"])])
|
||||
self.assertEqual([row["Branch"] for row in rows_of(self.out("--top", "2"))],
|
||||
["squashed", "merged", "mdirty", "ended", "stale"])
|
||||
counts_only = self.out("--top", "0")
|
||||
self.assertEqual((counts_only.splitlines()[1:5], rows_of(counts_only)), (COUNTS, []))
|
||||
|
||||
def test_the_full_file_holds_every_row_but_the_active_ones(self):
|
||||
full = self.base / "full.md"
|
||||
lines = self.out("--top", "1", "--full", str(full)).splitlines()
|
||||
self.assertIn(f"- full table: {full}", lines)
|
||||
rows = {row["Branch"]: row for row in rows_of(full.read_text(encoding="utf-8"))}
|
||||
self.assertEqual({branch: (row["Class"], row["Proposal"]) for branch, row in rows.items()}, TABLE)
|
||||
stale = rows["stale"]
|
||||
self.assertEqual((stale["Worktree"], stale["Dirty"], stale["Unpushed"]), (str(self.trees["stale"]), "3",
|
||||
"1 (no upstream)"))
|
||||
self.assertTrue(stale["Last activity"].endswith("(30 d)"), stale["Last activity"])
|
||||
self.assertEqual(rows["ended"]["Claim"], "work/ended-job (gone, ended)")
|
||||
self.assertEqual((rows["squashed"]["Worktree"], rows["squashed"]["Dirty"], rows["squashed"]["Unpushed"]),
|
||||
("-", "-", "0"))
|
||||
self.assertNotIn("Size", rows["stale"])
|
||||
|
||||
def test_sizes_order_the_largest_first_and_never_follow_a_symlink(self):
|
||||
shown = rows_of(self.out("--top", "1", "--sizes"))
|
||||
self.assertEqual([(row["Branch"], row["Size"]) for row in shown],
|
||||
[("merged", "6 B"), ("mdirty", "19 B"), ("stale", "48.8 KiB")])
|
||||
rows = self.rows("--sizes")
|
||||
self.assertEqual({branch: rows[branch]["size"] for branch in ("stale", "ended", "merged", "mdirty")},
|
||||
{"stale": BIG + 13, "ended": 13, "merged": 6, "mdirty": 19})
|
||||
for branch in ("squashed", *ACTIVE):
|
||||
with self.subTest(branch=branch):
|
||||
self.assertIsNone(rows[branch]["size"])
|
||||
self.assertIsNone(self.rows()["stale"]["size"])
|
||||
|
||||
def test_json_keeps_the_main_worktree_claimed_busy_recent_and_archived_rows(self):
|
||||
rows = self.rows()
|
||||
self.assertEqual(sorted(rows), sorted([*TABLE, *ACTIVE]))
|
||||
for branch in ACTIVE:
|
||||
with self.subTest(branch=branch):
|
||||
self.assertEqual((rows[branch]["class"], rows[branch]["proposal"]), ("active", "keep"))
|
||||
self.assertEqual((rows["merged"]["merged"], rows["squashed"]["merged"]), ("ancestor", "patch"))
|
||||
self.assertTrue(rows["main"]["main"])
|
||||
self.assertEqual(rows["main"]["dirty"], 1)
|
||||
self.assertEqual(rows["claimed"]["claims"], [{"office": "work/claimed-job", "holder": "Peer", "live": True}])
|
||||
self.assertTrue(rows["busy"]["busy"])
|
||||
self.assertFalse(rows["stale"]["busy"])
|
||||
self.assertGreater(rows["recent"]["last_activity"], time.time() - DAY)
|
||||
self.assertIsNone(rows["stale"]["merged"])
|
||||
self.assertIsNone(rows["merged"]["upstream"])
|
||||
|
||||
def test_the_scan_changes_nothing_in_the_repository(self):
|
||||
indexes = [self.index(tree) for tree in (self.main, *self.trees.values())]
|
||||
before = [os.stat(index).st_mtime_ns for index in indexes]
|
||||
refs = self.git(self.main, "for-each-ref")
|
||||
self.out("--top", "5", "--sizes")
|
||||
self.out("--json", "--top", "5")
|
||||
self.assertEqual([os.stat(index).st_mtime_ns for index in indexes], before)
|
||||
self.assertEqual(self.git(self.main, "for-each-ref"), refs)
|
||||
|
||||
def test_a_missing_origin_default_or_bad_input_exits_2(self):
|
||||
for args in (("--default", "nope"), ("--stale-days", "-1"), ("--default", "a..b"), ("--top", "-1"),
|
||||
("--full", str(self.base / "absent" / "full.md"))):
|
||||
with self.subTest(args=args):
|
||||
result = self.orphans("--top", "1", *args)
|
||||
self.assertEqual((result.returncode, result.stdout), (2, ""), result.stderr)
|
||||
self.assertEqual(self.orphans().returncode, 2)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
Reference in new issue
Block a user