ebbe.bass/ping-mee-self-service-platform
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

basic BMAD setup

Browse Source
This commit is contained in:
Ebbe Baß
2026-10-15 08:57:23 +02:00
parent 44029127dc
commit 5e747654b9
438 changed files with 41818 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.agents/skills/bmad-retrospective/scripts/git_evidence.py
+295
View File
@@ -0,0 +1,295 @@
# /// script
# requires-python = ">=3.11"
# ///
"""Measure git commit and file-change evidence over a revision range.
Prints ONLY JSON to stdout. Errors are emitted as JSON to stdout with a
non-zero exit code: 2 for invalid arguments (rejected before git runs),
1 for git or I/O failures. This script only MEASURES — it never judges
acceleration or violations. The model interprets the numbers.
Two git passes. The first lists every commit in the range (merges included)
and sums the per-file churn of the non-merge commits, which is what `files`
reports. The second runs only when the range contains merges and measures
those merges alone, reported separately as `merge_files` — never folded into
`files`, because a merge's diff against its first parent restates the churn
of the commits it merged in, which the first pass already counted.
"""
import argparse
import json
import os
import re
import subprocess
import sys
UNIT_SEP = "\x1f"
# sha, space-separated parents (empty for a root commit), subject.
LOG_FORMAT = f"--format=%H{UNIT_SEP}%P{UNIT_SEP}%s"
def _emit(obj, code=0):
sys.stdout.write(json.dumps(obj))
sys.exit(code)
class JsonArgumentParser(argparse.ArgumentParser):
"""Emit argparse failures on the JSON-only stdout contract, not usage text.
The parser is constructed with ``add_help=False``. The override below covers
``error()``, but ``-h`` never reaches it: the built-in help action calls
``print_help()`` and ``exit(0)`` directly, which would put plain usage text
on stdout with a zero exit and break the JSON-only contract. Removing the
action instead of intercepting it routes ``-h`` through the already-tested
``error()`` path as an ordinary unrecognized argument. The cost is that the
``help=`` strings are unreachable from the CLI; the skill's references carry
the usage a human needs.
"""
def error(self, message):
_emit({"ok": False, "error": f"argument error: {message}"}, 2)
def _parse_numstat_line(line):
# numstat lines: "<added>\t<deleted>\t<path>"; binary files use "-".
parts = line.split("\t")
if len(parts) < 3:
return None
added_raw, deleted_raw, path = parts[0], parts[1], "\t".join(parts[2:])
added = None if added_raw == "-" else int(added_raw)
deleted = None if deleted_raw == "-" else int(deleted_raw)
return added, deleted, path
def _git_log(repo, extra_args, rng):
"""Run one `git log --numstat` pass over `rng` and return its stdout.
`core.quotePath=false` keeps non-ASCII paths as real UTF-8 strings instead
of octal escapes, and `--no-renames` makes a rename an honest delete + add
instead of an unopenable "src/{a => b}" pseudo-path that splits one file's
churn across several keys. Both matter for every pass, so both live here.
`log.diffMerges=separate` is pinned on the command line because it is what
`-m` means: a user or repo config setting it to `off` makes pass 2 emit no
file rows at all, so `merge_files` would come back empty beside a non-zero
`merges_measured` and read as "the merges changed nothing".
"""
cmd = [
"git",
"-c",
"core.quotePath=false",
"-c",
"log.diffMerges=separate",
"-C",
repo,
"log",
"--numstat",
"--no-renames",
*extra_args,
LOG_FORMAT,
rng,
"--", # terminate rev parsing so the range can never match a pathspec
]
try:
# Decode explicitly: git emits UTF-8 path bytes regardless of the
# caller's locale, and a C locale would otherwise decode them as ASCII.
# surrogateescape, not replace: replace maps every invalid byte to the
# same U+FFFD, so two distinct non-UTF-8 paths would collapse into one
# `files` key with their churn silently summed. Lone surrogates survive
# json.dumps (escaped as \udcXX under ensure_ascii) and json.loads.
proc = subprocess.run(
cmd,
capture_output=True,
text=True,
encoding="utf-8",
errors="surrogateescape",
env={k: v for k, v in os.environ.items() if not k.startswith("GIT_")},
)
except Exception as exc: # noqa: BLE001
_emit({"ok": False, "error": str(exc)}, 1)
if proc.returncode != 0:
# stderr can be empty (a signal kill, a quiet failure); the exit code is
# then the only thing left to report, so never emit an empty error.
_emit(
{
"ok": False,
"error": proc.stderr.strip() or f"git exited {proc.returncode}",
},
1,
)
return proc.stdout
def _parse_log(output, stories):
"""Turn one pass's log output into (commits, files_map). Shared by both."""
commits = []
files = {} # path -> {path, _added, _deleted, binary_revisions, commit_count}
seen = set()
counting = True
for raw in output.splitlines():
if UNIT_SEP in raw:
sha, parents, subject = raw.split(UNIT_SEP, 2)
# Under -m, git repeats a merge's header once per parent unless it
# also honours --first-parent (git 2.31+). Count only the first
# block for a sha — git emits parents in order, so that block is
# the first-parent diff either way, and no churn is double counted.
counting = sha not in seen
if not counting:
continue
seen.add(sha)
commits.append(
{
"sha": sha,
"subject": subject,
# Every id the subject names, in --stories order: a commit
# spanning two stories belongs to both. Word-boundary match
# so a story id like "1-2" does not also match "11-2".
"stories": [sid for sid in stories if re.search(rf"\b{re.escape(sid)}\b", subject)],
"is_merge": len(parents.split()) > 1,
}
)
continue
if not counting or not raw.strip():
continue
parsed = _parse_numstat_line(raw)
if parsed is None:
continue
added, deleted, path = parsed
entry = files.get(path)
if entry is None:
# _added/_deleted are running sums over the path's text revisions.
entry = {
"path": path,
"_added": 0,
"_deleted": 0,
"binary_revisions": 0,
"commit_count": 0,
}
files[path] = entry
entry["commit_count"] += 1
if added is None or deleted is None:
# A binary revision is unmeasurable, not zero — count it alongside
# the sums instead of nulling the path's real measured churn.
entry["binary_revisions"] += 1
else:
entry["_added"] += added
entry["_deleted"] += deleted
return commits, files
def _file_list(files):
return [
{
"path": entry["path"],
"added": entry["_added"],
"deleted": entry["_deleted"],
"net": entry["_added"] - entry["_deleted"],
"commit_count": entry["commit_count"],
"binary_revisions": entry["binary_revisions"],
}
for entry in files.values()
]
def main(argv=None):
parser = JsonArgumentParser(
description=(
"Measure commit and per-file change evidence over a git revision range. Measures only; does not judge."
),
add_help=False,
)
parser.add_argument("--repo", default=".", help="Path to the git repo (default: .)")
parser.add_argument("--range", dest="range", help="Revision range REV..REV")
parser.add_argument(
"--stories",
help="Comma-separated story ids to match against commit subjects.",
)
args = parser.parse_args(argv)
stories = []
if args.stories:
# dict.fromkeys dedupes while keeping the caller's order: a repeated id
# would otherwise land twice in a commit's `stories`, double counting
# that commit in any per-story total built from the output.
stories = list(dict.fromkeys(s.strip() for s in args.stories.split(",") if s.strip()))
if not args.range:
_emit(
{
"range": None,
"note": "no range supplied",
"commits": [],
"files": [],
}
)
# Accept only an explicit REV..REV range. Anything else silently measures
# the wrong thing: a leading "-" is consumed by git as an option, a single
# rev logs all history up to it, a bare pathspec logs by path, an empty
# endpoint ("..", "a..", "..b") makes git default that side to HEAD, and a
# three-dot "A...B" is a symmetric difference — a different commit set
# entirely. partition splits at the FIRST "..", so any of those extra-dot
# shapes leaves `right` empty or dot-prefixed.
left, _, right = args.range.partition("..")
if args.range != args.range.strip() or args.range.startswith("-") or not left or not right or right.startswith("."):
_emit(
{
"ok": False,
"error": f"invalid --range {args.range!r}: expected a revision range like REV..REV",
},
2,
)
# Pass 1 — the listing. No extra args, so full topology: every commit in
# the range including merges, which is what per-story attribution reads.
# Merges contribute no numstat rows here, so `files` is non-merge churn.
commits, files = _parse_log(_git_log(args.repo, [], args.range), stories)
merge_count = sum(1 for commit in commits if commit["is_merge"])
# Pass 2 — merge churn, only when there is any. `-m --first-parent
# --min-parents=2` walks the range head's first-parent spine and emits
# exactly one diff-against-first-parent block per merge sitting on it.
# Merges off that spine are counted in merge_count and never measured,
# which is precisely why merges_measured is a separate key: the gap
# between the two is a visible statement that some merges went
# unmeasured. This never folds into `files` — a merge's first-parent diff
# restates the churn of the commits it merged in, which pass 1 already
# counted, so adding it in would double count.
merge_commits, merge_files = [], {}
if merge_count:
merge_commits, merge_files = _parse_log(
_git_log(
args.repo,
["-m", "--first-parent", "--min-parents=2"],
args.range,
),
stories,
)
_emit(
{
"range": args.range,
"commit_count": len(commits),
"merge_count": merge_count,
"merges_measured": len(merge_commits),
"commits": commits,
"files": _file_list(files),
"merge_files": _file_list(merge_files),
"stories_supplied": stories,
}
)
if __name__ == "__main__":
if sys.platform == "win32":
# Piped output on Windows defaults to a legacy code page, not UTF-8.
sys.stdout.reconfigure(encoding="utf-8")
sys.stderr.reconfigure(encoding="utf-8")
main()
.agents/skills/bmad-retrospective/scripts/tests/test_git_evidence.py
+605
View File
@@ -0,0 +1,605 @@
# /// script
# requires-python = ">=3.11"
# dependencies = ["pytest>=8.0"]
# ///
"""Tests for git_evidence.py — measurement over a real temp git repo.
Run: uv run scripts/tests/test_git_evidence.py
or: uv run --with pytest -m pytest scripts/tests/test_git_evidence.py
"""
import json
import os
import subprocess
import sys
import unicodedata
from pathlib import Path
import pytest
SCRIPT = Path(__file__).resolve().parents[1] / "git_evidence.py"
# The fixture commit identity, shared by both git helpers below.
_IDENT = {
"GIT_AUTHOR_NAME": "T",
"GIT_AUTHOR_EMAIL": "t@t",
"GIT_COMMITTER_NAME": "T",
"GIT_COMMITTER_EMAIL": "t@t",
}
def _git_env(repo):
"""The environment every fixture git runs under, layered outward.
Inherit the real environment (PATH above all: git lives in /opt/homebrew,
/usr/local, or a nix store as readily as /usr/bin, and an env holding only
GIT_* vars sends execvp to os.defpath), then strip every ambient GIT_* var
-- GIT_DIR, GIT_WORK_TREE and GIT_CONFIG_COUNT would each silently redirect
or reconfigure the fixture -- and pin identity plus every source git reads
for settings, so nothing on the developer's machine can reach the fixture:
- gitconfig (commit.gpgsign, core.autocrlf, core.hooksPath,
init.defaultBranch). GIT_CONFIG_NOSYSTEM/GIT_CONFIG_GLOBAL cover
git >= 2.32; HOME and XDG_CONFIG_HOME cover older git, and are set to the
repo's parent directory -- always a per-test directory under pytest's
tmp_path -- so nothing is ever planted inside the working tree.
- gitattributes, a separate source GIT_CONFIG_NOSYSTEM does not cover: a
system `* -diff` rule would make numstat call every path binary and take
the churn assertions down with it. GIT_ATTR_NOSYSTEM shuts it out.
- the locale. LC_ALL/LANG are pinned to C, matching _run/_proc's existing
pin, so fixture git's text output cannot vary with the developer's
locale. Inheriting the environment is what makes this pin necessary:
the old four-variable env had no locale in it to inherit.
"""
env = {k: v for k, v in os.environ.items() if not k.startswith("GIT_")}
env.update(_IDENT)
env["GIT_CONFIG_NOSYSTEM"] = "1"
env["GIT_ATTR_NOSYSTEM"] = "1"
env["GIT_CONFIG_GLOBAL"] = os.devnull
env["HOME"] = env["XDG_CONFIG_HOME"] = str(Path(repo).parent)
env["LC_ALL"] = env["LANG"] = "C"
return env
def _json(proc):
"""Parse the JSON-only stdout contract, surfacing a crash instead of hiding
it behind a JSONDecodeError."""
assert proc.stdout, f"empty stdout; stderr was: {proc.stderr}"
assert "Traceback" not in proc.stderr, proc.stderr
return json.loads(proc.stdout)
def _run(*args):
# LC_ALL=C keeps git's error strings in English so assertions on them
# are stable across locales.
proc = subprocess.run(
["uv", "run", str(SCRIPT), *args],
capture_output=True,
text=True,
env={**os.environ, "LC_ALL": "C", "LANG": "C"},
)
return proc.returncode, _json(proc)
def _proc(*args, env=None):
"""Run the script and return the raw process, so a test can assert on the
exit code and stderr together — and so `env` can carry an overlay (a
locale, an ambient GIT_DIR) that `_run` has no way to pass."""
overlay = {"LC_ALL": "C", "LANG": "C"}
if env:
overlay.update(env)
return subprocess.run(
["uv", "run", str(SCRIPT), *args],
capture_output=True,
text=True,
env={**os.environ, **overlay},
)
def _git(repo, *args):
subprocess.run(
["git", "-C", str(repo), *args],
check=True,
capture_output=True,
env=_git_env(repo),
)
def _git_unchecked(repo, *args):
"""`git` that tolerates a non-zero exit — the conflicting merge in
`_merge_repo` is supposed to fail, and the hand resolution comes after it.
Same environment as `_git`, which runs with check=True."""
return subprocess.run(
["git", "-C", str(repo), *args],
capture_output=True,
text=True,
env=_git_env(repo),
)
def _make_repo(tmp_path):
repo = tmp_path / "repo"
repo.mkdir()
_git(repo, "init", "-q")
(repo / "a.py").write_text("one\ntwo\n")
_git(repo, "add", "-A")
_git(repo, "commit", "-qm", "epic-1-1 initial a")
(repo / "a.py").write_text("one\ntwo\nthree\nfour\n")
(repo / "b.py").write_text("x\n")
_git(repo, "add", "-A")
_git(repo, "commit", "-qm", "epic-1-2 grow a, add b")
return repo
def test_no_range_returns_empty(tmp_path):
repo = _make_repo(tmp_path)
code, out = _run("--repo", str(repo))
assert code == 0
assert out["range"] is None
assert out["commits"] == [] and out["files"] == []
def test_measures_commits_and_files_with_attribution(tmp_path):
repo = _make_repo(tmp_path)
code, out = _run("--repo", str(repo), "--range", "HEAD~1..HEAD", "--stories", "1-2,1-1")
assert code == 0
assert out["range"] == "HEAD~1..HEAD"
assert out["commit_count"] == 1
# The single commit in range is the second one; attributed to story "1-2".
assert out["commits"][0]["stories"] == ["1-2"]
files = {f["path"]: f for f in out["files"]}
# a.py grew by two lines, b.py added one — measured, not judged.
assert files["a.py"]["added"] == 2 and files["a.py"]["net"] == 2
assert files["b.py"]["added"] == 1
def test_story_attribution_respects_word_boundary(tmp_path):
# Story id "1-2" must NOT match a commit subject mentioning "11-2".
repo = tmp_path / "repo"
repo.mkdir()
_git(repo, "init", "-q")
(repo / "f.py").write_text("a\n")
_git(repo, "add", "-A")
_git(repo, "commit", "-qm", "base")
(repo / "f.py").write_text("a\nb\n")
_git(repo, "add", "-A")
_git(repo, "commit", "-qm", "epic-11-2 unrelated story")
code, out = _run("--repo", str(repo), "--range", "HEAD~1..HEAD", "--stories", "1-2")
assert code == 0
assert out["commits"][0]["stories"] == []
def test_bad_range_errors_as_json(tmp_path):
repo = _make_repo(tmp_path)
code, out = _run("--repo", str(repo), "--range", "nope..alsonope")
assert code == 1
assert out["ok"] is False and out["error"]
def test_single_rev_range_rejected(tmp_path):
# A single rev is not a range: git would log ALL history up to it and the
# script would report the whole repo as the epic's evidence.
repo = _make_repo(tmp_path)
code, out = _run("--repo", str(repo), "--range", "HEAD")
assert code == 2
assert out["ok"] is False and "invalid --range" in out["error"]
def test_pathspec_range_rejected(tmp_path):
# A path that exists must not be silently consumed as a pathspec.
repo = _make_repo(tmp_path)
code, out = _run("--repo", str(repo), "--range", "a.py")
assert code == 2
assert out["ok"] is False and "invalid --range" in out["error"]
def test_range_shaped_pathspec_forced_to_rev_parse(tmp_path):
# A committed file literally named "a..b" passes the REV..REV shape check;
# without the trailing "--" in the git argv, git silently logs that FILE's
# history with exit 0. The "--" forces rev interpretation, so this must
# error instead of measuring the decoy.
repo = _make_repo(tmp_path)
(repo / "a..b").write_text("decoy\n")
_git(repo, "add", "-A")
_git(repo, "commit", "-qm", "add decoy file named like a range")
code, out = _run("--repo", str(repo), "--range", "a..b")
assert code == 1
assert out["ok"] is False and "bad revision" in out["error"]
def test_option_like_range_rejected(tmp_path):
# A range starting with "-" must never reach git, where it would be
# consumed as an option (e.g. --output=... writes an arbitrary file).
repo = _make_repo(tmp_path)
code, out = _run("--repo", str(repo), "--range=--output=evil.txt")
assert code == 2
assert out["ok"] is False and "invalid --range" in out["error"]
assert not (repo / "evil.txt").exists()
def test_degenerate_range_shapes_rejected(tmp_path):
# Shapes that contain ".." but are not REV..REV: git would silently
# default an empty endpoint to HEAD ("..", "a..", "..HEAD"), a leading
# dash must never reach git even when dots are present ("-3..HEAD"),
# unstripped values must not slip past the dash guard, and a three-dot
# range is a symmetric difference — git would measure commits reachable
# from either endpoint but not both, a different evidence set entirely.
repo = _make_repo(tmp_path)
for bad in (
"..",
"a..",
"..HEAD",
"-3..HEAD",
" HEAD~1..HEAD",
"HEAD~1...HEAD",
"a...b",
):
code, out = _run("--repo", str(repo), f"--range={bad}")
assert code == 2, f"accepted {bad!r}"
assert out["ok"] is False and "invalid --range" in out["error"], bad
def test_malformed_args_emit_json_not_usage(tmp_path):
# An unknown flag must still land on the JSON contract, not argparse's
# plain usage text on stderr.
code, out = _run("--bogus-flag")
assert code != 0
assert out["ok"] is False and out["error"]
def test_help_flags_emit_json_not_usage():
# argparse's built-in help action bypasses the error() override entirely --
# it prints usage text on stdout and exits 0, which breaks the JSON-only
# contract for a machine consumer. add_help=False demotes -h to an ordinary
# unrecognized argument, which error() already handles.
for flag in ("-h", "--help"):
proc = _proc(flag)
# Exit 2 specifically: the module docstring reserves 2 for argument
# errors and 1 for git/I-O failures, so collapsing them must fail here.
assert proc.returncode == 2, flag
assert "usage:" not in proc.stdout, flag
out = _json(proc)
assert out["ok"] is False and out["error"], flag
# --- helpers for the fixtures below -----------------------------------------
def _rev(repo, ref):
return _git_unchecked(repo, "rev-parse", ref).stdout.strip()
def _merge_repo(tmp_path):
"""Two story branches merged into the mainline; the second merge conflicts
and is resolved by hand, adding a line neither branch had. Returns
(repo, base_sha) — `base_sha..HEAD` is the epic range."""
repo = tmp_path / "repo"
repo.mkdir()
_git(repo, "init", "-q", "-b", "main")
(repo / "s.py").write_text("l1\nl2\nl3\n")
_git(repo, "add", "-A")
_git(repo, "commit", "-qm", "base")
base = _rev(repo, "HEAD")
_git(repo, "checkout", "-q", "-b", "s1")
(repo / "s.py").write_text("l1\nA\nl3\n")
_git(repo, "commit", "-qam", "epic-1-2 story one")
_git(repo, "checkout", "-q", "main")
_git(repo, "merge", "-q", "--no-ff", "s1", "-m", "merge story 1-2")
_git(repo, "checkout", "-q", "-b", "s2", base)
(repo / "s.py").write_text("l1\nB\nl3\n")
_git(repo, "commit", "-qam", "epic-1-3 story two")
_git(repo, "checkout", "-q", "main")
conflicted = _git_unchecked(repo, "merge", "--no-ff", "s2", "-m", "merge story 1-3")
assert conflicted.returncode != 0, "fixture expected a merge conflict"
(repo / "s.py").write_text("l1\nAB\nl3\nl4\n") # hand resolution
_git(repo, "add", "-A")
_git(repo, "commit", "-qm", "merge story 1-3")
return repo, base
def test_rename_yields_two_openable_paths(tmp_path):
# git's default rename detection emits "src/{mod.py => renamed.py}" — an
# unopenable pseudo-path that also splits one file's churn across keys.
# --no-renames makes the rename an honest delete + add.
repo = tmp_path / "repo"
repo.mkdir()
_git(repo, "init", "-q", "-b", "main")
(repo / "src").mkdir()
(repo / "src" / "mod.py").write_text("l1\nl2\nl3\nl4\nl5\nl6\n")
_git(repo, "add", "-A")
_git(repo, "commit", "-qm", "base")
base = _rev(repo, "HEAD")
_git(repo, "mv", "src/mod.py", "src/renamed.py")
_git(repo, "commit", "-qm", "rename mod")
(repo / "src" / "renamed.py").write_text("l1\nl2\nl3\nl4\nl5\nl6\nl7\n")
_git(repo, "commit", "-qam", "add a line after the rename")
out = _json(_proc("--repo", str(repo), "--range", f"{base}..HEAD"))
files = {f["path"]: f for f in out["files"]}
assert not any("=>" in path for path in files), sorted(files)
assert files["src/mod.py"]["added"] == 0
assert files["src/mod.py"]["deleted"] == 6
assert files["src/renamed.py"]["added"] == 7
assert files["src/renamed.py"]["deleted"] == 0
def _accented_repo(tmp_path):
repo = tmp_path / "repo"
repo.mkdir()
_git(repo, "init", "-q", "-b", "main")
(repo / "src").mkdir()
(repo / "src" / "café.py").write_text("ca\n")
_git(repo, "add", "-A")
_git(repo, "commit", "-qm", "base")
base = _rev(repo, "HEAD")
(repo / "src" / "café.py").write_text("ca\ncb\n")
_git(repo, "commit", "-qam", "touch the accented file")
return repo, base
def _assert_accented_path(repo, out):
paths = [f["path"] for f in out["files"]]
assert len(paths) == 1
assert "\\" not in paths[0] and '"' not in paths[0], paths
assert unicodedata.normalize("NFC", paths[0]) == "src/café.py"
# The reported path is a real path: it opens under --repo.
assert (repo / paths[0]).read_text() == "ca\ncb\n"
def test_non_ascii_path_is_a_real_string(tmp_path):
# Without core.quotePath=false git emits "src/caf\303\251.py" — quoted and
# octal-escaped, so the documented "open the ranked files" step cannot.
repo, base = _accented_repo(tmp_path)
_assert_accented_path(repo, _json(_proc("--repo", str(repo), "--range", f"{base}..HEAD")))
def test_non_ascii_path_survives_a_non_utf8_locale(tmp_path):
# Pins the explicit encoding="utf-8" on the subprocess. Modern CPython's
# UTF-8 mode hides its absence even under LC_ALL=C, so the pin only bites
# with UTF-8 mode and C-locale coercion both off — where the interpreter
# default is US-ASCII and git's UTF-8 path bytes fail to decode, taking the
# whole measurement down with them.
repo, base = _accented_repo(tmp_path)
out = _json(
_proc(
"--repo",
str(repo),
"--range",
f"{base}..HEAD",
env={"PYTHONUTF8": "0", "PYTHONCOERCECLOCALE": "0"},
)
)
_assert_accented_path(repo, out)
def test_merge_churn_is_measured_and_counted(tmp_path):
repo, base = _merge_repo(tmp_path)
out = _json(_proc("--repo", str(repo), "--range", f"{base}..HEAD"))
assert out["commit_count"] == 4
assert out["merge_count"] == 2
assert out["merges_measured"] == 2
# Both merges' first-parent churn: 1/1 for the clean merge, 2/1 for the
# hand-resolved one (the resolution added a line neither branch had).
merge_files = {f["path"]: f for f in out["merge_files"]}
assert merge_files["s.py"]["added"] == 3
assert merge_files["s.py"]["deleted"] == 2
assert merge_files["s.py"]["net"] == 1
assert merge_files["s.py"]["commit_count"] == 2
def test_merge_commits_listed_but_excluded_from_files(tmp_path):
repo, base = _merge_repo(tmp_path)
out = _json(_proc("--repo", str(repo), "--range", f"{base}..HEAD"))
by_subject = {c["subject"]: c for c in out["commits"]}
assert by_subject["merge story 1-2"]["is_merge"] is True
assert by_subject["merge story 1-3"]["is_merge"] is True
assert by_subject["epic-1-2 story one"]["is_merge"] is False
# `files` is the two story commits only — 1/1 each. Folding the merges in
# would double count: their diff restates the churn they merged.
files = {f["path"]: f for f in out["files"]}
assert files["s.py"]["added"] == 2
assert files["s.py"]["deleted"] == 2
assert files["s.py"]["commit_count"] == 2
def test_story_attribution_survives_merges(tmp_path):
repo, base = _merge_repo(tmp_path)
out = _json(_proc("--repo", str(repo), "--range", f"{base}..HEAD", "--stories", "1-2,1-3"))
by_subject = {c["subject"]: c for c in out["commits"]}
assert by_subject["epic-1-2 story one"]["stories"] == ["1-2"]
assert by_subject["epic-1-3 story two"]["stories"] == ["1-3"]
def test_off_spine_merge_is_counted_but_not_measured(tmp_path):
# A back-merge of the mainline into a story branch is a merge in the range,
# but its first-parent diff would restate unrelated mainline content as
# epic churn. It stays in merge_count and out of merges_measured, so the
# gap between the two says plainly that a merge went unmeasured.
repo = tmp_path / "repo"
repo.mkdir()
_git(repo, "init", "-q", "-b", "main")
(repo / "f.txt").write_text("base\n")
_git(repo, "add", "-A")
_git(repo, "commit", "-qm", "base")
base = _rev(repo, "HEAD")
(repo / "f.txt").write_text("base\nmain1\n")
_git(repo, "commit", "-qam", "mainline work")
_git(repo, "checkout", "-q", "-b", "s1", base)
(repo / "s1.txt").write_text("s1\n")
_git(repo, "add", "-A")
_git(repo, "commit", "-qm", "epic-1-2 story one")
_git(repo, "merge", "-q", "--no-ff", "main", "-m", "back-merge main into s1")
_git(repo, "checkout", "-q", "main")
_git(repo, "merge", "-q", "--no-ff", "s1", "-m", "merge story 1-2")
out = _json(_proc("--repo", str(repo), "--range", f"{base}..HEAD"))
assert out["merge_count"] == 2
assert out["merges_measured"] == 1
merge_files = {f["path"]: f for f in out["merge_files"]}
assert set(merge_files) == {"s1.txt"}
def test_merge_pass_survives_a_hostile_log_diffmerges_config(tmp_path):
# `-m` means "whatever log.diffMerges says", so a user or repo config of
# `off` makes the merge pass emit no file rows: merge_files comes back
# empty beside a non-zero merges_measured and reads as "the merges changed
# nothing". The command-line -c pin beats the config.
repo, base = _merge_repo(tmp_path)
_git(repo, "config", "log.diffMerges", "off")
out = _json(_proc("--repo", str(repo), "--range", f"{base}..HEAD"))
assert out["merges_measured"] == 2
merge_files = {f["path"]: f for f in out["merge_files"]}
assert merge_files["s.py"]["added"] == 3
assert merge_files["s.py"]["deleted"] == 2
def test_valid_range_with_no_commits_keeps_the_full_shape(tmp_path):
# A mis-specified epic range is a valid, empty range. It must still answer
# with every documented key rather than a differently-shaped stub.
repo = _make_repo(tmp_path)
proc = _proc("--repo", str(repo), "--range", "HEAD..HEAD")
out = _json(proc)
assert proc.returncode == 0
assert set(out) == {
"range",
"commit_count",
"merge_count",
"merges_measured",
"commits",
"files",
"merge_files",
"stories_supplied",
}
assert out["commit_count"] == 0
assert out["merge_count"] == 0
assert out["merges_measured"] == 0
assert out["commits"] == [] and out["files"] == [] and out["merge_files"] == []
def test_linear_history_reports_no_merges(tmp_path):
repo = _make_repo(tmp_path)
out = _json(_proc("--repo", str(repo), "--range", "HEAD~1..HEAD"))
assert out["merge_count"] == 0
assert out["merges_measured"] == 0
assert out["merge_files"] == []
def test_multi_story_subject_attributes_to_every_match(tmp_path):
# First-match-wins silently dropped the second story from the attribution.
repo = tmp_path / "repo"
repo.mkdir()
_git(repo, "init", "-q", "-b", "main")
(repo / "f.py").write_text("a\n")
_git(repo, "add", "-A")
_git(repo, "commit", "-qm", "base")
(repo / "f.py").write_text("a\nb\n")
_git(repo, "commit", "-qam", "fix seam between 1-2 and 1-3")
out = _json(_proc("--repo", str(repo), "--range", "HEAD~1..HEAD", "--stories", "1-3,1-2"))
# Every match, in --stories order — not whichever id was passed first.
assert out["commits"][0]["stories"] == ["1-3", "1-2"]
# A repeated id must not list the commit twice: any per-story total built
# from `stories` would count it twice.
repeated = _json(_proc("--repo", str(repo), "--range", "HEAD~1..HEAD", "--stories", "1-3,1-2,1-3"))
assert repeated["commits"][0]["stories"] == ["1-3", "1-2"]
assert repeated["stories_supplied"] == ["1-3", "1-2"]
def test_subject_naming_no_story_gets_an_empty_list(tmp_path):
repo = tmp_path / "repo"
repo.mkdir()
_git(repo, "init", "-q", "-b", "main")
(repo / "f.py").write_text("a\n")
_git(repo, "add", "-A")
_git(repo, "commit", "-qm", "base")
(repo / "f.py").write_text("a\nb\n")
_git(repo, "commit", "-qam", "chore: tidy imports")
out = _json(_proc("--repo", str(repo), "--range", "HEAD~1..HEAD", "--stories", "1-2,1-3"))
assert out["commits"][0]["stories"] == []
def _binary_repo(tmp_path):
"""A binary-only path plus a path that is binary twice and text once."""
repo = tmp_path / "repo"
repo.mkdir()
_git(repo, "init", "-q", "-b", "main")
(repo / "keep.txt").write_text("keep\n")
_git(repo, "add", "-A")
_git(repo, "commit", "-qm", "base")
base = _rev(repo, "HEAD")
(repo / "src").mkdir()
(repo / "src" / "x.py").write_bytes(b"\x00\x01bin\n")
(repo / "blob.bin").write_bytes(b"\x00\x01blob\n")
_git(repo, "add", "-A")
_git(repo, "commit", "-qm", "add binary content")
(repo / "src" / "x.py").write_text("one\ntwo\n") # binary -> text: still binary
_git(repo, "commit", "-qam", "x.py becomes text")
(repo / "src" / "x.py").write_text("one\ntwo\nthree\n") # text -> text: measured
_git(repo, "commit", "-qam", "grow x.py")
(repo / "blob.bin").write_bytes(b"\x00\x02blob\n")
_git(repo, "commit", "-qam", "churn the blob")
return repo, base
def test_binary_revisions_no_longer_erase_measured_text_churn(tmp_path):
repo, base = _binary_repo(tmp_path)
out = _json(_proc("--repo", str(repo), "--range", f"{base}..HEAD"))
x = {f["path"]: f for f in out["files"]}["src/x.py"]
assert x["added"] == 1 and x["deleted"] == 0 and x["net"] == 1
assert x["binary_revisions"] == 2
assert x["commit_count"] == 3
def test_binary_only_path_reports_zero_sums_and_its_revision_count(tmp_path):
repo, base = _binary_repo(tmp_path)
out = _json(_proc("--repo", str(repo), "--range", f"{base}..HEAD"))
blob = {f["path"]: f for f in out["files"]}["blob.bin"]
assert blob["added"] == 0 and blob["deleted"] == 0 and blob["net"] == 0
assert blob["binary_revisions"] == 2
assert blob["commit_count"] == 2
def test_success_shape_carries_every_documented_key(tmp_path):
repo = _make_repo(tmp_path)
out = _json(_proc("--repo", str(repo), "--range", "HEAD~1..HEAD"))
assert set(out) >= {
"range",
"commit_count",
"merge_count",
"merges_measured",
"commits",
"files",
"merge_files",
"stories_supplied",
}
assert set(out["commits"][0]) == {"sha", "subject", "stories", "is_merge"}
assert set(out["files"][0]) == {
"path",
"added",
"deleted",
"net",
"commit_count",
"binary_revisions",
}
def test_explicit_repo_ignores_ambient_git_dir(tmp_path):
repo = _make_repo(tmp_path)
proc = _proc(
"--repo",
str(repo),
"--range",
"HEAD~1..HEAD",
env={"GIT_DIR": str(tmp_path / "wrong-git-dir")},
)
assert _json(proc)["commit_count"] == 1
if __name__ == "__main__":
sys.exit(pytest.main([__file__, "-q"]))