Pre-launch — Gluecron is in final validation. Public signups and git hosting for non-owner users open after launch review.
CodeIssuesDiscussionsWikiPull RequestsProjectsCommitsActionsReleasesContributorsPulse● GatesSecuritySettingsDeploymentsPipelineInsightsAgents✨ Explain✨ Ask AI✨ Workspace✨ Spec✨ Tests▓ Debt Map✨ NL Search🏛 Archaeology
claude/adoring-hopper-5x74bqclaude/affectionate-feynman-ykrf1hclaude/architecture-audit-design-wxprenclaude/build-status-update-3MXsfclaude/charming-meitner-mllb5rclaude/compare-gate-gluecron-s4mFQclaude/confident-faraday-tikcwbclaude/continue-work-XMTlIclaude/crontech-gluecron-deploy-7MIECclaude/crontech-platform-setup-SeKfwclaude/design-2026claude/ecstatic-ptolemy-jMdigclaude/enhance-github-integration-QNHdGclaude/fix-aa-loop-issue-PonMQclaude/fix-actions-and-processclaude/fix-desktop-errors-XqoW8claude/fix-red-workflowsclaude/fix-website-access-6FKJNclaude/gatetest-integration-hardeningclaude/github-audit-improvements-bDFr9claude/gluecron-launch-status-FoMRlclaude/hopeful-lamport-olfCTclaude/issue-to-pr-and-protectionsclaude/jolly-heisenberg-2sg1Qclaude/launch-preparation-QmTb6claude/new-session-xk1l7claude/plan-platform-architecture-kkN4yclaude/platform-analysis-roadmap-1nUGLclaude/platform-launch-assessment-8dWV8claude/polish-platform-release-AeDrUclaude/resume-previous-work-KzyLwclaude/review-crontech-handoff-qYEVqclaude/review-project-completeness-lHhS2claude/review-readme-docs-ulqPKclaude/serene-edison-rj87weclaude/setup-multi-repo-dev-BCwNQclaude/ship-fixes-and-tests-Jvz1cclaude/site-audit-competitive-pctlwgclaude/site-migration-vercel-XstpKclaude/standalone-product-repos-XHFTDcopilot/feat-smart-empty-states-keyboard-first-enhancementcopilot/feat-smart-morning-digest-review-context-restorecopilot/fix-and-process-workflowscopilot/update-ai-powered-code-reviewfeat/debt-mapfeat/push-policy-codeowners-hardeningfeat/smart-digest-contextfeat/stage-impactfeat/t1-secret-migrationfeat/u-polishfeat/w-self-hostfeat/w2-claude-configfix/agent-journey-orphan-sweepgatetest/auto-fix-1776586424172gatetest/auto-fix-1776586534814gatetest/auto-fix-1776590685143gatetest/auto-fix-1776590808199mainops/redeploy-retriggerstyle/dxt-cta-themeworktree-agent-a3377aad30d55da26worktree-agent-a7ef607b7ee1d6c74
repo-size.ts6.6 KB · 246 lines
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
/**
 * Block J31 — Repository size audit.
 *
 * Pure helpers that answer "where are the bytes?" for a working-tree
 * snapshot at a given ref: total size, largest files, distribution by
 * top-level directory, and a size-class histogram.
 *
 * Consumes the same `{path, size}` shape produced by
 * `git ls-tree -r -l -z` (via `listTreeRecursive`), so the route stays
 * a thin shell over `buildSizeReport`.
 */
export interface RepoSizeEntry {
  path: string;
  size: number;
}

export const DEFAULT_TOP_N = 25;

/** Five size classes, ranked tiny → xlarge. Boundaries are inclusive-below. */
export const SIZE_CLASSES = [
  { key: "tiny", label: "< 1 KB", max: 1024 },
  { key: "small", label: "1 KB – 100 KB", max: 100 * 1024 },
  { key: "medium", label: "100 KB – 1 MB", max: 1024 * 1024 },
  { key: "large", label: "1 MB – 10 MB", max: 10 * 1024 * 1024 },
  { key: "xlarge", label: "≥ 10 MB", max: Number.POSITIVE_INFINITY },
] as const;

export type SizeClassKey = (typeof SIZE_CLASSES)[number]["key"];

export interface SizeSummary {
  totalFiles: number;
  countedFiles: number;
  totalBytes: number;
  averageBytes: number;
  medianBytes: number;
  largestBytes: number;
  smallestBytes: number;
}

export interface SizeBucket {
  key: SizeClassKey;
  label: string;
  fileCount: number;
  bytes: number;
}

export interface DirectoryBucket {
  /** Top-level segment. Root files live under the "." pseudo-bucket. */
  name: string;
  fileCount: number;
  bytes: number;
  percent: number;
}

export interface LargestFile {
  path: string;
  size: number;
  percent: number;
  /** First path segment (or "." for root files). */
  topDir: string;
}

export interface RepoSizeReport {
  summary: SizeSummary;
  buckets: SizeBucket[];
  directories: DirectoryBucket[];
  largest: LargestFile[];
}

/** Path → top-level segment (`src/foo/bar.ts` → `src`, `README.md` → `.`). */
export function topLevelDir(path: string): string {
  if (typeof path !== "string" || path.length === 0) return ".";
  const normal = path.startsWith("/") ? path.slice(1) : path;
  const i = normal.indexOf("/");
  return i === -1 ? "." : normal.slice(0, i);
}

/** Keep only sane, finite, non-negative-sized string paths. */
function validEntries(
  entries: readonly RepoSizeEntry[]
): RepoSizeEntry[] {
  const out: RepoSizeEntry[] = [];
  for (const e of entries) {
    if (!e || typeof e.path !== "string" || e.path.length === 0) continue;
    const sz = Number(e.size);
    if (!Number.isFinite(sz) || sz < 0) continue;
    out.push({ path: e.path, size: sz });
  }
  return out;
}

function median(sortedAsc: readonly number[]): number {
  const n = sortedAsc.length;
  if (n === 0) return 0;
  if (n % 2 === 1) return sortedAsc[(n - 1) / 2]!;
  const a = sortedAsc[n / 2 - 1]!;
  const b = sortedAsc[n / 2]!;
  return Math.round((a + b) / 2);
}

export function summariseSize(entries: readonly RepoSizeEntry[]): SizeSummary {
  const valid = validEntries(entries);
  const sizes = valid.map((e) => e.size).sort((a, b) => a - b);
  const total = sizes.reduce((acc, n) => acc + n, 0);
  const n = sizes.length;
  return {
    totalFiles: entries.length,
    countedFiles: n,
    totalBytes: total,
    averageBytes: n === 0 ? 0 : Math.round(total / n),
    medianBytes: median(sizes),
    largestBytes: n === 0 ? 0 : sizes[n - 1]!,
    smallestBytes: n === 0 ? 0 : sizes[0]!,
  };
}

export function classifyFileSize(size: number): SizeClassKey {
  if (!Number.isFinite(size) || size < 0) return "tiny";
  for (const c of SIZE_CLASSES) {
    if (size < c.max) return c.key;
  }
  // Math says we can't get here (last class max = Infinity), but be defensive.
  return "xlarge";
}

export function bucketBySize(
  entries: readonly RepoSizeEntry[]
): SizeBucket[] {
  const valid = validEntries(entries);
  const out: SizeBucket[] = SIZE_CLASSES.map((c) => ({
    key: c.key,
    label: c.label,
    fileCount: 0,
    bytes: 0,
  }));
  for (const e of valid) {
    const key = classifyFileSize(e.size);
    const b = out.find((x) => x.key === key)!;
    b.fileCount++;
    b.bytes += e.size;
  }
  return out;
}

export interface TopLargestOptions {
  /** Max files to return. Default `DEFAULT_TOP_N`. */
  limit?: number;
  /** Minimum bytes for inclusion. Default 0 (= no floor). */
  minBytes?: number;
}

export function topLargestFiles(
  entries: readonly RepoSizeEntry[],
  opts: TopLargestOptions = {}
): LargestFile[] {
  const limit =
    opts.limit !== undefined && opts.limit > 0
      ? Math.floor(opts.limit)
      : DEFAULT_TOP_N;
  const minBytes = opts.minBytes ?? 0;

  const valid = validEntries(entries).filter((e) => e.size >= minBytes);
  const total = valid.reduce((acc, e) => acc + e.size, 0);

  const sorted = valid.slice().sort((a, b) => {
    if (a.size !== b.size) return b.size - a.size;
    return a.path.localeCompare(b.path);
  });

  return sorted.slice(0, limit).map((e) => ({
    path: e.path,
    size: e.size,
    percent: total === 0 ? 0 : (e.size / total) * 100,
    topDir: topLevelDir(e.path),
  }));
}

export function summariseByTopDir(
  entries: readonly RepoSizeEntry[]
): DirectoryBucket[] {
  const valid = validEntries(entries);
  const total = valid.reduce((acc, e) => acc + e.size, 0);
  const byDir = new Map<string, { fileCount: number; bytes: number }>();

  for (const e of valid) {
    const key = topLevelDir(e.path);
    const agg = byDir.get(key) ?? { fileCount: 0, bytes: 0 };
    agg.fileCount++;
    agg.bytes += e.size;
    byDir.set(key, agg);
  }

  const out: DirectoryBucket[] = [];
  for (const [name, { fileCount, bytes }] of byDir) {
    out.push({
      name,
      fileCount,
      bytes,
      percent: total === 0 ? 0 : (bytes / total) * 100,
    });
  }

  out.sort((a, b) => {
    if (a.bytes !== b.bytes) return b.bytes - a.bytes;
    // Root bucket sorts last on ties so real directories surface first.
    if (a.name === "." && b.name !== ".") return 1;
    if (b.name === "." && a.name !== ".") return -1;
    return a.name.localeCompare(b.name);
  });

  return out;
}

export interface BuildSizeReportOptions {
  entries: readonly RepoSizeEntry[];
  topN?: number;
  minBytesForLargest?: number;
}

export function buildSizeReport(
  opts: BuildSizeReportOptions
): RepoSizeReport {
  return {
    summary: summariseSize(opts.entries),
    buckets: bucketBySize(opts.entries),
    directories: summariseByTopDir(opts.entries),
    largest: topLargestFiles(opts.entries, {
      limit: opts.topN,
      minBytes: opts.minBytesForLargest,
    }),
  };
}

export const __internal = {
  SIZE_CLASSES,
  DEFAULT_TOP_N,
  topLevelDir,
  classifyFileSize,
  summariseSize,
  bucketBySize,
  topLargestFiles,
  summariseByTopDir,
  buildSizeReport,
  median,
  validEntries,
};