feat(kvb-check-score): score journal, backfill and per-metric burndown overlays (006)
score.py names the Cost and Time metrics Tokens and Velocity from one label file and appends every scored block to a score journal in the council root. backfill.py rebuilds that journal from commit messages with its own label mapping, deterministic and idempotent, so another host can import its history. The hub serves the journal, and the Gantt burndown draws each metric as its own overlay on a right 0-100 % axis, every overlay off by default and switched by legend chips whose state the view store keeps. 🎯 Fix: 90 % 💥 Break: 5 % 💸 Cost: 100 % ⏱️ Time: 100 % 🛡️ Security: 100 % 🏆 Score: 86 🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 % Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
1 parent
3418738993
commit
5b55c39b64
30 files changed
+1806
-142
No files matched your search
@@ -33,8 +33,8 @@ NEW_B = "💰 value ?:? (cost 0/day; pass --value with evidence; kvb-b new: all
|
||||
CHEAP = "print('cheap')\n"
|
||||
COSTLY = "data = list(range(2_000_000))\nprint(sum(data))\n"
|
||||
LINE = re.compile(
|
||||
r"^💸 cost (?P<mark>~?)(?P<efficiency>\d+) % \(cpu \d+\.\d\d→\d+\.\d\d s, ram \d+\.\d→\d+\.\d MB\) · "
|
||||
r"⏱️ time (?P<speed_mark>~?)(?P<speed>\d+) % \((?P<basis>wall|cpu) \d+\.\d\d→\d+\.\d\d s\)(?P<tail>.*)$"
|
||||
r"^💸 tokens (?P<mark>~?)(?P<efficiency>\d+) % \(cpu \d+\.\d\d→\d+\.\d\d s, ram \d+\.\d→\d+\.\d MB\) · "
|
||||
r"⏱️ velocity (?P<speed_mark>~?)(?P<speed>\d+) % \((?P<basis>wall|cpu) \d+\.\d\d→\d+\.\d\d s\)(?P<tail>.*)$"
|
||||
)
|
||||
|
||||
|
||||
@@ -121,7 +121,7 @@ class TestTokens(GitRepo):
|
||||
self.write("skills/kvb-a/scripts/tool.py", "print(1)\n" * 50)
|
||||
result = self.tokens()
|
||||
self.assertEqual(
|
||||
result.stdout.splitlines(), ["💸 cost 50 % (skills 100→50 tokens; listing 3→3 words)", NO_VALUE]
|
||||
result.stdout.splitlines(), ["💸 tokens 50 % (skills 100→50 tokens; listing 3→3 words)", NO_VALUE]
|
||||
)
|
||||
self.assertEqual(result.returncode, 0, result.stderr)
|
||||
|
||||
@@ -130,7 +130,7 @@ class TestTokens(GitRepo):
|
||||
self.write("skills/kvb-b/SKILL.md", SKILL_B.ljust(200, "y"))
|
||||
result = self.tokens()
|
||||
self.assertEqual(
|
||||
result.stdout.splitlines(), ["💸 cost 200 % (skills 100→200 tokens; listing 3→5 words)", NEW_B]
|
||||
result.stdout.splitlines(), ["💸 tokens 200 % (skills 100→200 tokens; listing 3→5 words)", NEW_B]
|
||||
)
|
||||
self.assertEqual(result.returncode, 3)
|
||||
result = self.tokens("--json")
|
||||
@@ -157,7 +157,7 @@ class TestTokens(GitRepo):
|
||||
def test_only_new_files_print_new(self):
|
||||
self.write("skills/kvb-b/SKILL.md", SKILL_B.ljust(200, "y"))
|
||||
result = self.tokens()
|
||||
self.assertEqual(result.stdout.splitlines(), ["💸 cost new (+50 tokens; listing 3→5 words)", NEW_B])
|
||||
self.assertEqual(result.stdout.splitlines(), ["💸 tokens new (+50 tokens; listing 3→5 words)", NEW_B])
|
||||
self.assertEqual(result.returncode, 3)
|
||||
self.assertIsNone(json.loads(self.tokens("--json").stdout)["efficiency"])
|
||||
|
||||
@@ -165,14 +165,14 @@ class TestTokens(GitRepo):
|
||||
self.git("mv", "skills/kvb-a/notes.md", "skills/kvb-a/moved.md")
|
||||
result = self.tokens()
|
||||
self.assertEqual(
|
||||
result.stdout.splitlines(), ["💸 cost 100 % (skills 100→100 tokens; listing 3→3 words)", NO_VALUE]
|
||||
result.stdout.splitlines(), ["💸 tokens 100 % (skills 100→100 tokens; listing 3→3 words)", NO_VALUE]
|
||||
)
|
||||
self.assertEqual(result.returncode, 0)
|
||||
|
||||
def test_no_change_is_100(self):
|
||||
result = self.tokens()
|
||||
self.assertEqual(
|
||||
result.stdout.splitlines(), ["💸 cost 100 % (skills 0→0 tokens; listing 3→3 words)", NO_VALUE]
|
||||
result.stdout.splitlines(), ["💸 tokens 100 % (skills 0→0 tokens; listing 3→3 words)", NO_VALUE]
|
||||
)
|
||||
self.assertEqual(result.returncode, 0)
|
||||
|
||||
@@ -193,7 +193,7 @@ class TestTokens(GitRepo):
|
||||
self.assertEqual(
|
||||
result.stdout.splitlines(),
|
||||
[
|
||||
"💸 cost 869 % (skills 13→113 tokens; listing 3→5 words)",
|
||||
"💸 tokens 869 % (skills 13→113 tokens; listing 3→5 words)",
|
||||
"💰 value ?:? (cost 203/day; pass --value with evidence)",
|
||||
],
|
||||
)
|
||||
@@ -235,6 +235,22 @@ class TestTokens(GitRepo):
|
||||
)
|
||||
self.assertEqual(result.returncode, 3)
|
||||
|
||||
def test_a_malformed_label_file_exits_2_with_one_stderr_line(self):
|
||||
for text in ("{broken", json.dumps({"metrics": {"tokens": {"emoji": 1, "label": "Tokens"}}}), "[]"):
|
||||
with self.subTest(labels=text):
|
||||
labels = self.base / "labels.json"
|
||||
labels.write_text(text, encoding="utf-8")
|
||||
out, err = io.StringIO(), io.StringIO()
|
||||
argv = ["--repo", str(self.repo), "--base", "HEAD", "--transcripts", str(self.base / "projects")]
|
||||
with mock.patch.object(skill_tokens, "LABELS", labels), contextlib.redirect_stdout(out), contextlib.redirect_stderr(err):
|
||||
try:
|
||||
code = skill_tokens.main(argv)
|
||||
except SystemExit as stop:
|
||||
code = stop.code
|
||||
self.assertEqual((code, out.getvalue()), (2, ""))
|
||||
self.assertEqual(len(err.getvalue().splitlines()), 1, err.getvalue())
|
||||
self.assertTrue(err.getvalue().startswith(f"tokens: labels {labels}: "), err.getvalue())
|
||||
|
||||
def test_usage_errors_exit_2(self):
|
||||
self.assertEqual(self.tokens("--value", "5").returncode, 2)
|
||||
self.assertEqual(self.tokens("--evidence", "why").returncode, 2)
|
||||
@@ -381,6 +397,15 @@ class TestMeasure(GitRepo):
|
||||
self.assertEqual(trees, [f"worktree {self.repo.resolve()}"])
|
||||
self.assertLessEqual(set(Path("/tmp").glob("kvb-measure-*")), self.leftovers)
|
||||
|
||||
def test_a_malformed_label_file_exits_2_before_any_run(self):
|
||||
labels = self.base / "labels.json"
|
||||
labels.write_text(json.dumps({"metrics": {"tokens": {"emoji": "💸", "label": "Tokens"}}}), encoding="utf-8")
|
||||
with mock.patch.object(measure, "LABELS", labels):
|
||||
code, out, err, samples = self.measured("--base", "HEAD", "--", sys.executable, "work.py")
|
||||
self.assertEqual((code, out, samples), (2, "", 0))
|
||||
self.assertEqual(len(err.splitlines()), 1, err)
|
||||
self.assertTrue(err.startswith(f"measure: labels {labels}: "), err)
|
||||
|
||||
def test_cheaper_head_stops_after_one_run_each(self):
|
||||
self.write("pkg/work.py", CHEAP)
|
||||
code, out, err, samples = self.measured("--base", "HEAD", "--", sys.executable, "work.py")
|
||||
|
||||
Reference in new issue
Block a user